We have created a content-based image retrieval framework for computed tomography images of pulmonary nodules. When presented with a nodule image, the system retrieves images of similar nodules from a collection prepared by the Lung Image Database Consortium (LIDC). The system (1) extracts images of individual nodules from the LIDC collection based on LIDC expert annotations, (2) stores the extracted data in a flat XML database, (3) calculates a set of quantitative descriptors for each nodule that provide a high-level characterization of its texture, and (4) uses various measures to determine the similarity of two nodules and perform queries on a selected query nodule. Using our framework, we compared three feature extraction methods: Haralick co-occurrence, Gabor filters, and Markov random fields. Gabor and Markov descriptors perform better at retrieving similar nodules than do Haralick co-occurrence techniques, with best retrieval precisions in excess of 88%. Because the software we have developed and the reference images are both open source and publicly available they may be incorporated into both commercial and academic imaging workstations and extended by others in their research.
Content-based image retrieval; open source; lung; computer-aided diagnosis (CAD); extensible markup language (XML); image database; software design; computed tomography; texture feature; nodule
We are developing a computer-aided diagnosis (CAD) system to classify malignant and benign lung nodules found on CT scans. A fully automated system was designed to segment the nodule from its surrounding structured background in a local volume of interest (VOI) and to extract image features for classification. Image segmentation was performed with a three-dimensional (3D) active contour (AC) method. A data set of 96 lung nodules (44 malignant, 52 benign) from 58 patients was used in this study. The 3D AC model is based on two-dimensional AC with the addition of three new energy components to take advantage of 3D information: (1) 3D gradient, which guides the active contour to seek the object surface, (2) 3D curvature, which imposes a smoothness constraint in the z direction, and (3) mask energy, which penalizes contours that grow beyond the pleura or thoracic wall. The search for the best energy weights in the 3D AC model was guided by a simplex optimization method. Morphological and gray-level features were extracted from the segmented nodule. The rubber band straightening transform (RBST) was applied to the shell of voxels surrounding the nodule. Texture features based on run-length statistics were extracted from the RBST image. A linear discriminant analysis classifier with stepwise feature selection was designed using a second simplex optimization to select the most effective features. Leave-one-case-out resampling was used to train and test the CAD system. The system achieved a test area under the receiver operating characteristic curve (Az) of 0.83±0.04. Our preliminary results indicate that use of the 3D AC model and the 3D texture features surrounding the nodule is a promising approach to the segmentation and classification of lung nodules with CAD. The segmentation performance of the 3D AC model trained with our data set was evaluated with 23 nodules available in the Lung Image Database Consortium (LIDC). The lung nodule volumes segmented by the 3D AC model for best classification were generally larger than those outlined by the LIDC radiologists using visual judgment of nodule boundaries.
computer-aided diagnosis; active contour model; object segmentation; classification; texture analysis; computed tomography (CT); malignancy; pulmonary nodule
Rationale and Objectives
To investigate the effects of choosing between different metrics in estimating the size of pulmonary nodules as a factor both of nodule characterization and of performance of computer aided detection systems, since the latters are always qualified with respect to a given size range of nodules.
Materials and Methods
This study used 265 whole-lung CT scans documented by the Lung Image Database Consortium using their protocol for nodule evaluation. Each inspected lesion was reviewed independently by four experienced radiologists who provided boundary markings for nodules larger than 3 mm. Four size metrics, based on the boundary markings, were considered: a uni-dimensional and two bi-dimensional measures on a single image slice and a volumetric measurement based on all the image slices. The radiologist boundaries were processed and those with four markings were analyzed to characterize the inter-radiologist variation, while those with at least one marking were used to examine the difference between the metrics.
The processing of the annotations found 127 nodules marked by all of the four radiologists and an extended set of 518 nodules each having at least one observation with three-dimensional sizes ranging from 2.03 to 29.4 mm (average 7.05 mm, median 5.71 mm). A very high inter-observer variation was observed for all these metrics: 95% of estimated standard deviations were in the following ranges [0.49, 1.25], [0.67, 2.55], [0.78, 2.11], and [0.96, 2.69] for the three-dimensional, the uni-dimensional, and the two bi-dimensional size metrics respectively (in mm). Also a very large difference among the metrics was observed: 0.95 probability-coverage region widths for the volume estimation conditional on uni-dimensional, and the two bi-dimensional size measurements of 10mm were 7.32, 7.72, and 6.29 mm respectively.
The selection of data subsets for performance evaluation is highly impacted by the size metric choice. The LIDC plans to include a single size measure for each nodule in its database. This metric is not intended as a gold standard for nodule size; rather, it is intended to facilitate the selection of unique repeatable size limited nodule subsets.
Quantitative image analysis; X-ray CT; Detection; Lung nodule annotation; Size metrics
Ideally, an image should be reported and interpreted in the same way (e.g., the same perceived likelihood of malignancy) or similarly by any two radiologists; however, as much research has demonstrated, this is not often the case. Various efforts have made an attempt at tackling the problem of reducing the variability in radiologists’ interpretations of images. The Lung Image Database Consortium (LIDC) has provided a database of lung nodule images and associated radiologist ratings in an effort to provide images to aid in the analysis of computer-aided tools. Likewise, the Radiological Society of North America has developed a radiological lexicon called RadLex. As such, the goal of this paper is to investigate the feasibility of associating LIDC characteristics and terminology with RadLex terminology. If matches between LIDC characteristics and RadLex terms are found, probabilistic models based on image features may be used as decision-based rules to predict if an image or lung nodule could be
characterized or classified as an associated RadLex term. The results of this study were matches for 25 (74%) out of 34 LIDC terms in RadLex. This suggests that LIDC characteristics and associated rating terminology may be better conceptualized or reduced to produce even more matches with RadLex. Ultimately, the goal is to identify and establish a more standardized rating system and terminology to reduce the subjective variability between radiologist annotations. A standardized rating system can then be utilized by future researchers to develop automatic annotation models and tools for computer-aided decision systems.
Chest CT; digital imaging; image data; image interpretation; imaging informatics; lung; radiographic image interpretation; computer-assisted; reporting; RadLex; semantic; LIDC
Rationale and Objectives
Computer-aided diagnostic (CAD) systems fundamentally require the opinions of expert human observers to establish “truth” for algorithm development, training, and testing. The integrity of this “truth,” however, must be established before investigators commit to this “gold standard” as the basis for their research. The purpose of this study was to develop a quality assurance (QA) model as an integral component of the “truth” collection process concerning the location and spatial extent of lung nodules observed on computed tomography (CT) scans to be included in the Lung Image Database Consortium (LIDC) public database.
Materials and Methods
One hundred CT scans were interpreted by four radiologists through a two-phase process. For the first of these reads (the “blinded read phase”), radiologists independently identified and annotated lesions, assigning each to one of three categories: “nodule ≥ 3mm,” “nodule < 3mm,” or “non-nodule ≥ 3mm.” For the second read (the “unblinded read phase”), the same radiologists independently evaluated the same CT scans but with all of the annotations from the previously performed blinded reads presented; each radiologist could add marks, edit or delete their own marks, change the lesion category of their own marks, or leave their marks unchanged. The post-unblinded-read set of marks was grouped into discrete nodules and subjected to the QA process, which consisted of (1) identification of potential errors introduced during the complete image annotation process (such as two marks on what appears to be a single lesion or an incomplete nodule contour) and (2) correction of those errors. Seven categories of potential error were defined; any nodule with a mark that satisfied the criterion for one of these categories was referred to the radiologist who assigned that mark for either correction or confirmation that the mark was intentional.
A total of 105 QA issues were identified across 45 (45.0%) of the 100 CT scans. Radiologist review resulted in modifications to 101 (96.2%) of these potential errors. Twenty-one lesions erroneously marked as lung nodules after the unblinded reads had this designation removed through the QA process.
The establishment of “truth” must incorporate a QA process to guarantee the integrity of the datasets that will provide the basis for the development, training, and testing of CAD systems.
lung nodule; computed tomography (CT); thoracic imaging; database construction; computer-aided diagnosis (CAD); annnotation; quality assurance (QA)
The purpose of this study was to develop a new method for automated lung nodule detection in serial section CT images with using the characteristics of the 3D appearance of the nodules that distinguish themselves from the vessels.
Materials and Methods
Lung nodules were detected in four steps. First, to reduce the number of region of interests (ROIs) and the computation time, the lung regions of the CTs were segmented using Genetic Cellular Neural Networks (G-CNN). Then, for each lung region, ROIs were specified with using the 8 directional search; +1 or -1 values were assigned to each voxel. The 3D ROI image was obtained by combining all the 2-Dimensional (2D) ROI images. A 3D template was created to find the nodule-like structures on the 3D ROI image. Convolution of the 3D ROI image with the proposed template strengthens the shapes that are similar to those of the template and it weakens the other ones. Finally, fuzzy rule based thresholding was applied and the ROI's were found. To test the system's efficiency, we used 16 cases with a total of 425 slices, which were taken from the Lung Image Database Consortium (LIDC) dataset.
The computer aided diagnosis (CAD) system achieved 100% sensitivity with 13.375 FPs per case when the nodule thickness was greater than or equal to 5.625 mm.
Our results indicate that the detection performance of our algorithm is satisfactory, and this may well improve the performance of computer-aided detection of lung nodules.
Computer aided lung nodule detection; ROI specification, Genetic algorithm; Cellular neural networks; Fuzzy logic, 3D template matching
Lung cancer is a leading cause of death worldwide; it refers to the uncontrolled growth of abnormal cells in the lung. A computed tomography (CT) scan of the thorax is the most sensitive method for detecting cancerous lung nodules. A lung nodule is a round lesion which can be either non-cancerous or cancerous. In the CT, the lung cancer is observed as round white shadow nodules. The possibility to obtain a manually accurate interpretation from CT scans demands a big effort by the radiologist and might be a fatiguing process. Therefore, the design of a computer-aided diagnosis (CADx) system would be helpful as a second opinion tool.
The stages of the proposed CADx are: a supervised extraction of the region of interest to eliminate the shape differences among CT images. The Daubechies db1, db2, and db4 wavelet transforms are computed with one and two levels of decomposition. After that, 19 features are computed from each wavelet sub-band. Then, the sub-band and attribute selection is performed. As a result, 11 features are selected and combined in pairs as inputs to the support vector machine (SVM), which is used to distinguish CT images containing cancerous nodules from those not containing nodules.
The clinical data set used for experiments consists of 45 CT scans from ELCAP and LIDC. For the training stage 61 CT images were used (36 with cancerous lung nodules and 25 without lung nodules). The system performance was tested with 45 CT scans (23 CT scans with lung nodules and 22 without nodules), different from that used for training. The results obtained show that the methodology successfully classifies cancerous nodules with a diameter from 2 mm to 30 mm. The total preciseness obtained was 82%; the sensitivity was 90.90%, whereas the specificity was 73.91%.
The CADx system presented is competitive with other literature systems in terms of sensitivity. The system reduces the complexity of classification by not performing the typical segmentation stage of most CADx systems. Additionally, the novelty of the algorithm is the use of a wavelet feature descriptor.
CADx system; Lung nodules; CT scan; Wavelet feature descriptor; Gray level co-ocurrence matrix; Support vector machine; Texture
Lung CAD systems require the ability to classify a variety of pulmonary structures as part of the diagnostic process. The purpose of this work was to develop a methodology for fully automated voxel-by-voxel classification of airways, fissures, nodules, and vessels from chest CT images using a single feature set and classification method. Twenty-nine thin section CT scans were obtained from the Lung Image Database Consortium (LIDC). Multiple radiologists labeled voxels corresponding to the following structures: airways (trachea to 6th generation), major and minor lobar fissures, nodules, and vessels (hilum to peripheral), and normal lung parenchyma. The labeled data was used in conjunction with a supervised machine learning approach (AdaBoost) to train a set of ensemble classifiers. Each ensemble classifier was trained to detect voxels part of a specific structure (either airway, fissure, nodule, vessel, or parenchyma). The feature set consisted of voxel attenuation and a small number of features based on the eigenvalues of the Hessian matrix (used to differentiate structures by shape). When each ensemble classifier was composed of 20 weak classifiers, the AUC values for the airway, fissure, nodule, vessel, and parenchyma classifiers were 0.984 ± 0.011, 0.949 ± 0.009, 0.945 ± 0.018, 0.953 ± 0.016, and 0.931± 0.015 respectively. The strong results suggest that this could be an effective input to higher-level anatomical based segmentation models with the potential to improve CAD performance.
AdaBoost; Bronchovascular segmentation; Computed tomography; Computer-aided diagnosis
A fully automated and three-dimensional (3D) segmentation method for the identification of the pulmonary parenchyma in thorax X-ray computed tomography (CT) datasets is proposed. It is meant to be used as pre-processing step in the computer-assisted detection (CAD) system for malignant lung nodule detection that is being developed by the Medical Applications in a Grid Infrastructure Connection (MAGIC-5) Project. In this new approach the segmentation of the external airways (trachea and bronchi), is obtained by 3D region growing with wavefront simulation and suitable stop conditions, thus allowing an accurate handling of the hilar region, notoriously difficult to be segmented. Particular attention was also devoted to checking and solving the problem of the apparent ‘fusion’ between the lungs, caused by partial-volume effects, while 3D morphology operations ensure the accurate inclusion of all the nodules (internal, pleural, and vascular) in the segmented volume. The new algorithm was initially developed and tested on a dataset of 130 CT scans from the Italung-CT trial, and was then applied to the ANODE09-competition images (55 scans) and to the LIDC database (84 scans), giving very satisfactory results. In particular, the lung contour was adequately located in 96% of the CT scans, with incorrect segmentation of the external airways in the remaining cases. Segmentation metrics were calculated that quantitatively express the consistency between automatic and manual segmentations: the mean overlap degree of the segmentation masks is 0.96 ± 0.02, and the mean and the maximum distance between the mask borders (averaged on the whole dataset) are 0.74 ± 0.05 and 4.5 ± 1.5, respectively, which confirms that the automatic segmentations quite correctly reproduce the borders traced by the radiologist. Moreover, no tissue containing internal and pleural nodules was removed in the segmentation process, so that this method proved to be fit for the use in the framework of a CAD system. Finally, in the comparison with a two-dimensional segmentation procedure, inter-slice smoothness was calculated, showing that the masks created by the 3D algorithm are significantly smoother than those calculated by the 2D-only procedure.
CAD; image segmentation; lung nodules; region growing; grid; 3D imaging; biomedical image analysis
In 1979 Haralick famously introduced a method for analyzing the texture of an image: a set of statistics extracted from the co-occurrence matrix. In this paper we investigate novel sets of texture descriptors extracted from the co-occurrence matrix; in addition, we compare and combine different strategies for extending these descriptors. The following approaches are compared: the standard approach proposed by Haralick, two methods that consider the co-occurrence matrix as a three-dimensional shape, a gray-level run-length set of features and the direct use of the co-occurrence matrix projected onto a lower dimensional subspace by principal component analysis. Texture descriptors are extracted from the co-occurrence matrix evaluated at multiple scales. Moreover, the descriptors are extracted not only from the entire co-occurrence matrix but also from subwindows. The resulting texture descriptors are used to train a support vector machine and ensembles. Results show that our novel extraction methods improve the performance of standard methods. We validate our approach across six medical datasets representing different image classification problems using the Wilcoxon signed rank test. The source code used for the approaches tested in this paper will be available at: http://www.dei.unipd.it/wdyn/?IDsezione=3314&IDgruppo_pass=124&preview=.
Major challenges in current computer-aided detection (CADe) schemes for nodule detection in chest radiographs (CXRs) are to detect nodules that overlap with ribs and/or clavicles and to reduce the frequent false positives (FPs) caused by ribs. Detection of such nodules by a CADe scheme is very important, because radiologists are likely to miss such subtle nodules. Our purpose in this study was to develop a CADe scheme with improved sensitivity and specificity by use of “virtual dual-energy” (VDE) CXRs where ribs and clavicles are suppressed with massive-training artificial neural networks (MTANNs). To reduce rib-induced FPs and detect nodules overlapping with ribs, we incorporated the VDE technology in our CADe scheme. The VDE technology suppressed rib and clavicle opacities in CXRs while maintaining soft-tissue opacity by use of the MTANN technique that had been trained with real dual-energy imaging. Our scheme detected nodule candidates on VDE images by use of a morphologic filtering technique. Sixty morphologic and gray-level-based features were extracted from each candidate from both original and VDE CXRs. A nonlinear support vector classifier was employed for classification of the nodule candidates. A publicly available database containing 140 nodules in 140 CXRs and 93 normal CXRs was used for testing our CADe scheme. All nodules were confirmed by computed tomography examinations, and the average size of the nodules was 17.8 mm. Thirty percent (42/140) of the nodules were rated “extremely subtle” or “very subtle” by a radiologist. The original scheme without VDE technology achieved a sensitivity of 78.6% (110/140) with 5 (1165/233) FPs per image. By use of the VDE technology, more nodules overlapping with ribs or clavicles were detected and the sensitivity was improved substantially to 85.0% (119/140) at the same FP rate in a leave-one-out cross-validation test, whereas the FP rate was reduced to 2.5 (583/233) per image at the same sensitivity level as the original CADe scheme obtained (Difference between the specificities of the original and the VDE-based CADe schemes was statistically significant). In particular, the sensitivity of our VDE-based CADe scheme for subtle nodules (66.7% = 28/42) was statistically significantly higher than that of the original CADe scheme (57.1% = 24/42). Therefore, by use of VDE technology, the sensitivity and specificity of our CADe scheme for detection of nodules, especially subtle nodules, in CXRs were improved substantially.
Chest radiography (CXR); computer-aided diagnosis (CAD); lung cancer; rib suppression; virtual dual energy (VDE)
This paper describes part of content-based image retrieval (CBIR) system that has been developed for mammograms. Details are presented of methods implemented to derive measures of similarity based upon structural characteristics and distributions of density of the fibroglandular tissue, as well as the anatomical size and shape of the breast region as seen on the mammogram. Well-known features related to shape, size, and texture (statistics of the gray-level histogram, Haralick’s texture features, and moment-based features) were applied, as well as less-explored features based in the Radon domain and granulometric measures. The Kohonen self-organizing map (SOM) neural network was used to perform the retrieval operation. Performance evaluation was done using precision and recall curves obtained from comparison between the query and retrieved images. The proposed methodology was tested with 1,080 mammograms, including craniocaudal and mediolateral-oblique views. Precision rates obtained are in the range from 79% to 83% considering the total image set. Considering the first 50% of the retrieved mages, the precision rates are in the range from 78% to 83%; the rates are in the range from 79% to 86% considering the first 25% of the retrieved images. Results obtained indicate the potential of the implemented methodology to serve as a part of a CBIR system for mammography.
Mammography; contend-based image retrieval; Kohonen self-organizing map; texture features; granulometric measures; radon transform domain; breast density
Computed tomography (CT) is an important imaging modality. Physicians, surgeons, and oncologists prefer CT scan for diagnosis of lung cancer. However, some nodules are missed in CT scan. Computer aided diagnosis methods are useful for radiologists for detection of these nodules and early diagnosis of lung cancer. Early detection of malignant nodule is helpful for treatment. Computer aided diagnosis of lung cancer involves lung segmentation, potential nodules identification, features extraction from the potential nodules, and classification of the nodules. In this paper, we are presenting an automatic method for detection and segmentation of lung nodules from CT scan for subsequent features extraction and classification. Contribution of the work is the detection and segmentation of small sized nodules, low and high contrast nodules, nodules attached with vasculature, nodules attached to pleura membrane, and nodules in close vicinity of the diaphragm and lung wall in one-go. The particular techniques of the method are multistep threshold for the nodule detection and shape index threshold for false positive reduction. We used 60 CT scans of “Lung Image Database Consortium-Image Database Resource Initiative” taken by GE medical systems LightSpeed16 scanner as dataset and correctly detected 92% nodules. The results are reproducible.
To determine the value of contourlet textural features obtained from solitary pulmonary nodules in two dimensional CT images used in diagnoses of lung cancer.
Materials and Methods
A total of 6,299 CT images were acquired from 336 patients, with 1,454 benign pulmonary nodule images from 84 patients (50 male, 34 female) and 4,845 malignant from 252 patients (150 male, 102 female). Further to this, nineteen patient information categories, which included seven demographic parameters and twelve morphological features, were also collected. A contourlet was used to extract fourteen types of textural features. These were then used to establish three support vector machine models. One comprised a database constructed of nineteen collected patient information categories, another included contourlet textural features and the third one contained both sets of information. Ten-fold cross-validation was used to evaluate the diagnosis results for the three databases, with sensitivity, specificity, accuracy, the area under the curve (AUC), precision, Youden index, and F-measure were used as the assessment criteria. In addition, the synthetic minority over-sampling technique (SMOTE) was used to preprocess the unbalanced data.
Using a database containing textural features and patient information, sensitivity, specificity, accuracy, AUC, precision, Youden index, and F-measure were: 0.95, 0.71, 0.89, 0.89, 0.92, 0.66, and 0.93 respectively. These results were higher than results derived using the database without textural features (0.82, 0.47, 0.74, 0.67, 0.84, 0.29, and 0.83 respectively) as well as the database comprising only textural features (0.81, 0.64, 0.67, 0.72, 0.88, 0.44, and 0.85 respectively). Using the SMOTE as a pre-processing procedure, new balanced database generated, including observations of 5,816 benign ROIs and 5,815 malignant ROIs, and accuracy was 0.93.
Our results indicate that the combined contourlet textural features of solitary pulmonary nodules in CT images with patient profile information could potentially improve the diagnosis of lung cancer.
We present an image retrieval framework based on automatic query expansion in a concept feature space by generalizing the vector space model of information retrieval. In this framework, images are represented by vectors of weighted concepts similar to the keyword-based representation used in text retrieval. To generate the concept vocabularies, a statistical model is built by utilizing Support Vector Machine (SVM)-based classification techniques. The images are represented as “bag of concepts” that comprise perceptually and/or semantically distinguishable color and texture patches from local image regions in a multi-dimensional feature space. To explore the correlation between the concepts and overcome the assumption of feature independence in this model, we propose query expansion techniques in the image domain from a new perspective based on both local and global analysis. For the local analysis, the correlations between the concepts based on the co-occurrence pattern, and the metrical constraints based on the neighborhood proximity between the concepts in encoded images, are analyzed by considering local feedback information. We also analyze the concept similarities in the collection as a whole in the form of a similarity thesaurus and propose an efficient query expansion based on the global analysis. The experimental results on a photographic collection of natural scenes and a biomedical database of different imaging modalities demonstrate the effectiveness of the proposed framework in terms of precision and recall.
Image Retrieval; Vector Space Model; Support Vector Machine; Relevance Feedback; Query Expansion
There are lots of work being done to develop computer-assisted diagnosis and detection (CAD) technologies and systems to improve the diagnostic quality for pulmonary nodules. Another way to improve accuracy of diagnosis on new images is to recall or find images with similar features from archived historical images which already have confirmed diagnostic results, and the content-based image retrieval (CBIR) technology has been proposed for this purpose. In this paper, we present a method to find and select texture features of solitary pulmonary nodules (SPNs) detected by computed tomography (CT) and evaluate the performance of support vector machine (SVM)-based classifiers in differentiating benign from malignant SPNs. Seventy-seven biopsy-confirmed CT cases of SPNs were included in this study. A total of 67 features were extracted by a feature extraction procedure, and around 25 features were finally selected after 300 genetic generations. We constructed the SVM-based classifier with the selected features and evaluated the performance of the classifier by comparing the classification results of the SVM-based classifier with six senior radiologists′ observations. The evaluation results not only showed that most of the selected features are characteristics frequently considered by radiologists and used in CAD analyses previously reported in classifying SPNs, but also indicated that some newly found features have important contribution in differentiating benign from malignant SPNs in SVM-based feature space. The results of this research can be used to build the highly efficient feature index of a CBIR system for CT images with pulmonary nodules.
Feature selection; content-based image retrieval; classification; CT images; lung diseases
To explore the role of the texture features of images in the diagnosis of solitary pulmonary nodules (SPNs) in different sizes.
Materials and methods
A total of 379 patients with pathologically confirmed SPNs were enrolled in this study. They were divided into three groups based on the SPN sizes: ≤10, 11-20, and >20 mm. Their texture features were segmented and extracted. The differences in the image features between benign and malignant SPNs were compared. The SPNs in these three groups were determined and analyzed with the texture features of images.
These 379 SPNs were successfully segmented using the 2D Otsu threshold method and the self-adaptive threshold segmentation method. The texture features of these SPNs were obtained using the method of grey level co-occurrence matrix (GLCM). Of these 379 patients, 120 had benign SPNs and 259 had malignant SPNs. The entropy, contrast, energy, homogeneity, and correlation were 3.5597±0.6470, 0.5384±0.2561, 0.1921±0.1256, 0.8281±0.0604, and 0.8748±0.0740 in the benign SPNs and 3.8007±0.6235, 0.6088±0.2961, 0.1673±0.1070, 0.7980±0.0555, and 0.8550±0.0869 in the malignant SPNs (all P<0.05). The sensitivity, specificity, and accuracy of the texture features of images were 83.3%, 90.0%, and 86.8%, respectively, for SPNs sized ≤10 mm, and were 86.6%, 88.2%, and 87.1%, respectively, for SPNs sized
11-20 mm and 94.7%, 91.8%, and 93.9%, respectively, for SPNs sized >20 mm.
The entropy and contrast of malignant pulmonary nodules have been demonstrated to be higher in comparison to those of benign pulmonary nodules, while the energy, homogeneity correlation of malignant pulmonary nodules are lower than those of benign pulmonary nodules. The texture features of images can reflect the tissue features and have high sensitivity, specificity, and accuracy in differentiating SPNs. The sensitivity and accuracy increase for larger SPNs.
Solitary pulmonary nodules (SPNs); differentiation; textures; image features
Rationale and Objectives
Integral to the mission of the National Institutes of Health–sponsored Lung Imaging Database Consortium is the accurate definition of the spatial location of pulmonary nodules. Because the majority of small lung nodules are not resected, a reference standard from histopathology is generally unavailable. Thus assessing the source of variability in defining the spatial location of lung nodules by expert radiologists using different software tools as an alternative form of truth is necessary.
Materials and Methods
The relative differences in performance of six radiologists each applying three annotation methods to the task of defining the spatial extent of 23 different lung nodules were evaluated. The variability of radiologists’ spatial definitions for a nodule was measured using both volumes and probability maps (p-map). Results were analyzed using a linear mixed-effects model that included nested random effects.
Across the combination of all nodules, volume and p-map model parameters were found to be significant at P < .05 for all methods, all radiologists, and all second-order interactions except one. The radiologist and methods variables accounted for 15% and 3.5% of the total p-map variance, respectively, and 40.4% and 31.1% of the total volume variance, respectively.
Radiologists represent the major source of variance as compared with drawing tools independent of drawing metric used. Although the random noise component is larger for the p-map analysis than for volume estimation, the p-map analysis appears to have more power to detect differences in radiologist-method combinations. The standard deviation of the volume measurement task appears to be proportional to nodule volume.
LIDC drawing experiment; lung nodule annotation; edge mask; p-map; volume; linear mixed-effects model
Rationale and Objectives
To retrospectively investigate the effect of a computer aided detection (CAD) system on radiologists’ performance for detecting small pulmonary nodules in CT examinations, with a panel of expert radiologists serving as the reference standard.
Materials and Methods
Institutional review board approval was obtained. Our data set contained 52 CT examinations collected by the Lung Image Database Consortium, and 33 from our institution. All CTs were read by multiple expert thoracic radiologists to identify the reference standard for detection. Six other thoracic radiologists read the CT examinations first without, and then with CAD. Performance was evaluated using free-response receiver operating characteristics (FROC) and the jackknife FROC analysis methods (JAFROC) for nodules above different diameter thresholds.
241 nodules, ranging in size from 3.0 to 18.6 mm (mean 5.3 mm) were identified as the reference standard. At diameter thresholds of 3, 4, 5, and 6 mm, the CAD system had a sensitivity of 54%, 64%, 68%, and 76%, respectively, with an average of 5.6 false-positives (FPs) per scan. Without CAD, the average figures-of-merit (FOMs) for the six radiologists, obtained from JAFROC analysis, were 0.661, 0.729, 0.793 and 0.838 for the same nodule diameter thresholds, respectively. With CAD, the corresponding average FOMs improved to 0.705, 0.763, 0.810 and 0.862, respectively. The improvement achieved statistical significance for nodules at the 3 and 4 mm thresholds (p=0.002 and 0.020, respectively), and did not achieve significance at 5 and 6 mm (p=0.18 and 0.13, respectively). At a nodule diameter threshold of 3 mm, the radiologists’ average sensitivity and FP rate were 0.56 and 0.67, respectively, without CAD, and 0.67 and 0.78 with CAD.
CAD improves thoracic radiologists’ performance for detecting pulmonary nodules under 5 mm on CT examinations, which are often overlooked by visual inspection alone.
Lung Nodule; CT; Computer-aided detection
The aim of this study is to investigate the relationship between16-slice spiral CT perfusion imaging and tumor angiogenesis and VEGF (vascular endothelial growth factor) expression in patients with benign and malignant pulmonary nodules, and differential diagnosis between benign and malignant pulmonary nodules.
Sixty-four patients with benign and malignant pulmonary nodules underwent 16-slice spiral CT perfusion imaging. The CT perfusion imaging was analyzed for TDC (time density curve), perfusion parametric maps, and the respective perfusion parameters. Immunohistochemical findings of MVD (microvessel density) measurement and VEGF expression was evaluated.
The shape of the TDC of peripheral lung cancer was similar to those of inflammatory nodule. PH (peak height), PHpm/PHa (peak height ratio of pulmonary nodule to aorta), BF (blood flow), BV (blood volume) value of peripheral lung cancer and inflammatory nodule were not statistically significant (all P > 0.05). Both showed significantly higher PH, PHpm/PHa, BF, BV value than those of benign nodule (all P < 0.05). Peripheral lung cancer showed significantly higher PS (permeability surface) value than that of inflammatory nodule and benign nodule (all P < 0.05). BV, BF, PS, MTT, PH, PHpm/PHa, and MVD among three groups of peripheral lung cancers were not significantly (all P > 0.05). In the case of adenocarcinoma, BV, BF, PS, PHpm/PHa, and MVD between poorly and well differentiation and between poorly and moderately differentiation were statistically significant (all P < 0.05). The peripheral lung cancers with VEGF positive expression showed significantly higher PH, PHpm/PHa, BF, BV, PS, and MVD value than those of the peripheral lung cancer with VEGF negative expression, and than those of benign nodule with VEGF positive expression (all P < 0.05). When investigating VEGF negative expression, it is found that PH, PHpm/PHa, and MVD of inflammatory nodule were significantly higher than those of peripheral lung cancer, PS of inflammatory nodule were significantly lower than that of peripheral lung cancer (all P < 0.05). PH, PHpm/PHa, BF, and BV of benign nodule were significantly lower than those of inflammatory nodule (all P < 0.05), rather than PS and MTT (mean transit time) (all P > 0.05). PH, PHpm/PHa, BV, and PS of benign nodule were significantly lower than those of peripheral lung cancer (all P < 0.05). In the case of VEGF positive expression, MVD was positively correlated with PH, PHpm/PHa, BF, BV, and PS of peripheral lung cancer and PS of benign nodule (all P < 0.05).
Multi-slice spiral CT perfusion imaging closely correlated with tumor angiogenesis and reflected MVD measurement and VEGF expression. It provided not only a non-invasive method of quantitative assessment for blood flow patterns of peripheral pulmonary nodules but also an applicable diagnostic method for peripheral pulmonary nodules.
With the increasing use of images in disease research, education, and clinical medicine, the need for methods that effectively archive, query, and retrieve these images by their content is underscored. This paper describes the implementation of a Web-based retrieval system called SPIRS (Spine Pathology & Image Retrieval System), which permits exploration of a large biomedical database of digitized spine x-ray images and data from a national health survey using a combination of visual and textual queries.
SPIRS is a generalizable framework that consists of four components: a client applet, a gateway, an indexing and retrieval system, and a database of images and associated text data. The prototype system is demonstrated using text and imaging data collected as part of the second U.S. National Health and Nutrition Examination Survey (NHANES II). Users search the image data by providing a sketch of the vertebral outline or selecting an example vertebral image and some relevant text parameters. Pertinent pathology on the image/sketch can be annotated and weighted to indicate importance.
During the course of development, we explored different algorithms to perform functions such as segmentation, indexing, and retrieval. Each algorithm was tested individually and then implemented as part of SPIRS. To evaluate the overall system, we first tested the system’s ability to return similar vertebral shapes from the database given a query shape. Initial evaluations using visual queries only (no text) have shown that the system achieves up to 68% accuracy in finding images in the database that exhibit similar abnormality type and severity. Relevance feedback mechanisms have been shown to increase accuracy by an additional 22% after three iterations. While we primarily demonstrate this system in the context of retrieving vertebral shape, our framework has also been adapted to search a collection of 100,000 uterine cervix images to study the progression of cervical cancer.
SPIRS is automated, easily accessible, and integratable with other complementary information retrieval systems. The system supports the ability for users to intuitively query large amounts of imaging data by providing visual examples and text keywords and has beneficial implications in the areas of research, education, and patient care.
Medical informatics applications; Information storage and retrieval; Content-based image retrieval; Visual access methods; Web-based systems
Searching for relevant knowledge across heterogeneous geospatial databases requires an extensive knowledge of the semantic meaning of images, a keen eye for visual patterns, and efficient strategies for collecting and analyzing data with minimal human intervention. In this paper, we present our recently developed content-based multimodal Geospatial Information Retrieval and Indexing System (GeoIRIS) which includes automatic feature extraction, visual content mining from large-scale image databases, and high-dimensional database indexing for fast retrieval. Using these underpinnings, we have developed techniques for complex queries that merge information from heterogeneous geospatial databases, retrievals of objects based on shape and visual characteristics, analysis of multiobject relationships for the retrieval of objects in specific spatial configurations, and semantic models to link low-level image features with high-level visual descriptors. GeoIRIS brings this diverse set of technologies together into a coherent system with an aim of allowing image analysts to more rapidly identify relevant imagery. GeoIRIS is able to answer analysts’ questions in seconds, such as “given a query image, show me database satellite images that have similar objects and spatial relationship that are within a certain radius of a landmark.”
Geospatial intelligence; image database; information mining
Communication of critical results from diagnostic procedures between caregivers is a Joint Commission national patient safety goal. Evaluating critical result communication often requires manual analysis of voluminous data, especially when reviewing unstructured textual results of radiologic findings. Information retrieval (IR) tools can facilitate this process by enabling automated retrieval of radiology reports that cite critical imaging findings. However, IR tools that have been developed for one disease or imaging modality often need substantial reconfiguration before they can be utilized for another disease entity.
This paper: 1) describes the process of customizing two Natural Language Processing (NLP) and Information Retrieval/Extraction applications – an open-source toolkit, A Nearly New Information Extraction system (ANNIE); and an application developed in-house, Information for Searching Content with an Ontology-Utilizing Toolkit (iSCOUT) – to illustrate the varying levels of customization required for different disease entities and; 2) evaluates each application’s performance in identifying and retrieving radiology reports citing critical imaging findings for three distinct diseases, pulmonary nodule, pneumothorax, and pulmonary embolus.
Both applications can be utilized for retrieval. iSCOUT and ANNIE had precision values between 0.90-0.98 and recall values between 0.79 and 0.94. ANNIE had consistently higher precision but required more customization.
Understanding the customizations involved in utilizing NLP applications for various diseases will enable users to select the most suitable tool for specific tasks.
Critical imaging findings; critical test results; document retrieval; radiology report retrieval.
We have been developing a computer-aided diagnostic (CAD) scheme for lung nodule detection in order to assist radiologists in the detection of lung cancer in thin-section computed tomography (CT) images. Our database consisted of 117 thin-section CT scans with 153 nodules, obtained from a lung cancer screening program at a Japanese university (85 scans, 91 nodules) and from clinical work at an American university (32 scans, 62 nodules). The database included nodules of different sizes (4-28 mm, mean 10.2 mm), shapes, and patterns (solid and ground-glass opacity (GGO)). Our CAD scheme consisted of modules for lung segmentation, selective nodule enhancement, initial nodule detection, feature extraction, and classification. The selective nodule enhancement filter was a key technique for significant enhancement of nodules and suppression of normal anatomic structures such as blood vessels, which are the main sources of false positives. Use of an automated rule-based classifier for reduction of false positives was another key technique; it resulted in a minimized overtraining effect and an improved classification performance. We employed a case-based four-fold cross-validation testing method for evaluation of the performance levels of our computerized detection scheme. Our CAD scheme achieved an overall sensitivity of 86% (small: 76%, medium-sized: 94%, large: 95%; solid: 86%, mixed GGO: 89%, pure GGO: 81%) with 6.6 false positives per scan; an overall sensitivity of 81% (small: 69%, medium-sized: 91%, large: 91%; solid: 79%, mixed GGO: 88%, pure GGO: 81%) with 3.3 false positives per scan; and an overall sensitivity of 75% (small: 60%, medium-sized: 88%, large: 87%; solid: 70%, mixed GGO: 87%, pure GGO: 81%) with 1.6 false positives per scan. The experimental results indicate that our CAD scheme with its two key techniques can achieve a relatively high performance for nodules presenting large variations in size, shape, and pattern.
nodule detection; computer-aided diagnosis; CAD; CT scan; rule-based classifier
Positron emission tomography (PET) with 18-fluorodeoxyglucose (FDG) is recommended for the non-invasive diagnosis of pulmonary nodules suspicious for lung cancer. In populations with endemic infectious lung disease, FDG-PET may not accurately identify malignant lesions.
To estimate the diagnostic accuracy of FDG-PET for pulmonary nodules suspicious for lung cancer in regions where infectious lung disease is endemic and compare the test accuracy in regions where infectious lung disease is rare.
Data Sources and Study Selection
Databases of MEDLINE, EMBASE and the Web of Science were searched from October 1, 2000, through April 28, 2014. Articles reporting information sufficient to calculate sensitivity and specificity of FDG-PET to diagnose lung cancer were included. Only studies that enrolled more than 10 participants with benign and malignant lesions were included. Database searches yielded 1923 articles, of which 257 were assessed for eligibility. Seventy studies were included in the analysis. Studies reported on a total of 8511 nodules; 5105 (60%) were malignant.
Data Extraction and Synthesis
Abstracts meeting eligibility criteria were collected by a research librarian and reviewed by 2 independent reviewers. Hierarchical summary receiver operating characteristic curves were constructed. A random-effects logistic regression model was used to summarize and assess the effect of endemic infectious lung disease on test performance.
Main Outcome and Measures
The sensitivity and specificity for FDG-PET test performance.
Heterogeneity for sensitivity (I2=87%) and specificity (I2=82%) was observed across studies. The pooled (unadjusted) sensitivity was 89% (95% CI, 86%-91%) and specificity was 75% (95% CI, 71%-79%). There was a 16% lower average adjusted specificity in regions with endemic infectious lung disease (61% [95% CI, 49%-72%]) compared with nonendemic regions (77% [95% CI, 73%-80%]). Lower specificity was observed when the analysis was limited to rigorously conducted and well-controlled studies. In general, sensitivity did not change appreciably by endemic infection status, even after adjusting for relevant factors.
Conclusions and Relevance
The accuracy of FDG-PET for diagnosing lung nodules was extremely heterogeneous. Use of FDG-PET combined with computed tomography was less specific in diagnosing malignancy in populations with endemic infectious lung disease compared with nonendemic regions. These data do not support use of FDG-PET to diagnose lung cancer in endemic areas unless an institution achieves test performance accuracy similar to that found in nonendemic regions.
Lung cancer; diagnosis; FDG-PET; meta-analysis