Since segmentation of magnetic resonance images is one of the most important initial steps in brain magnetic resonance image processing, success in this part has a great influence on the quality of outcomes of subsequent steps. In the past few decades, numerous methods have been introduced for classification of such images, but typically they perform well only on a specific subset of images, do not generalize well to other image sets, and have poor computational performance. In this study, we provided a method for segmentation of magnetic resonance images of the brain that despite its simplicity has a high accuracy. We compare the performance of our proposed algorithm with similar evolutionary algorithms on a pixel-by-pixel basis. Our algorithm is tested across varying sets of magnetic resonance images and demonstrates high speed and accuracy. It should be noted that in initial steps, the algorithm is computationally intensive requiring a large number of calculations; however, in subsequent steps of the search process, the number is reduced with the segmentation focused only in the target area.
Image processing; Segmentation; Optimization algorithm; Ant colony optimization
The National Institutes of Health have placed significant emphasis on sharing of research data to support secondary research. Investigators have been encouraged to publish their clinical and imaging data as part of fulfilling their grant obligations. Realizing it was not sufficient to merely ask investigators to publish their collection of imaging and clinical data, the National Cancer Institute (NCI) created the open source National Biomedical Image Archive software package as a mechanism for centralized hosting of cancer related imaging. NCI has contracted with Washington University in Saint Louis to create The Cancer Imaging Archive (TCIA)—an open-source, open-access information resource to support research, development, and educational initiatives utilizing advanced medical imaging of cancer. In its first year of operation, TCIA accumulated 23 collections (3.3 million images). Operating and maintaining a high-availability image archive is a complex challenge involving varied archive-specific resources and driven by the needs of both image submitters and image consumers. Quality archives of any type (traditional library, PubMed, refereed journals) require management and customer service. This paper describes the management tasks and user support model for TCIA.
TCIA; NBIA; Cancer imaging; Image archive; Biomedical image analysis; Cancer detection
Characterization of hepatocellular carcinomas (HCCs) and metastatic carcinomas (METs) from B-mode ultrasound presents a daunting challenge for radiologists due to their highly overlapping appearances. The differential diagnosis between HCCs and METs is often carried out by observing the texture of regions inside the lesion and the texture of background liver on which the lesion has evolved. The present study investigates the contribution made by texture patterns of regions inside and outside of the lesions for binary classification between HCC and MET lesions. The study is performed on 51 real ultrasound liver images with 54 malignant lesions, i.e., 27 images with 27 solitary HCCs (13 small HCCs and 14 large HCCs) and 24 images with 27 MET lesions (12 typical cases and 15 atypical cases). A total of 120 within-lesion regions of interest and 54 surrounding lesion regions of interest are cropped from 54 lesions. Subsequently, 112 texture features (56 texture features and 56 texture ratio features) are computed by statistical, spectral, and spatial filtering based texture features extraction methods. A two-step methodology is used for feature set optimization, i.e., feature pruning by removal of nondiscriminatory features followed by feature selection by genetic algorithm–support vector machine (SVM) approach. The SVM classifier is designed based on optimum features. The proposed computer-aided diagnostic system achieved the overall classification accuracy of 91.6 % with sensitivity of 90 % and 93.3 % for HCCs and METs, respectively. The promising results obtained by the proposed system indicate its usefulness to assist radiologists in diagnosing liver malignancies.
Texture analysis; B-Mode liver ultrasound; Hepatocellular carcinoma; Metastasis; Primary malignant liver lesion; Secondary malignant liver lesion; Genetic algorithm; Support vector machine classifier; Small hepatocellular carcinoma; Large hepatocellular carcinoma; Typical metastasis; Atypical metastasis; Focal liver lesions
The accuracy of an ultrasound (US) computer-aided diagnosis (CAD) system was evaluated for the classification of BI-RADS category 3, probably benign masses. The US database used in this study contained 69 breast masses (21 malignant and 48 benign masses) that at blinded retrospective interpretation were assigned to BI-RADS category 3 by at least one of five radiologists. For computer-aided analysis, multiple morphology (shape, orientation, margin, lesions boundary, and posterior acoustic features) and texture (echo patterns) features based on BI-RADS lexicon were implemented, and the binary logistic regression model was used for classification. The receiver operating characteristic curve analysis was used for statistical analysis. The area under the curve (Az) of morphology, texture, and combined features were 0.90, 0.75, and 0.95, respectively. The combined features achieved the best performance and were significantly better than using texture features only (0.95 vs. 0.75, p value = 0.0163). The cut-off point at the sensitivity of 86 % (18/21), 95 % (20/21), and 100 % (21/21) achieved the specificity of 90 % (43/48), 73 % (35/48), and 33 % (16/48), respectively. In conclusion, the proposed CAD system has the potential to be used in upgrading malignant masses misclassified as BI-RADS category 3 on US by the radiologists.
Breast cancer; BI-RADS; Ultrasound; Computer-assisted diagnosis
Speech recognition (SR) speeds patient care processes by reducing report turnaround times. However, concerns have emerged about prolonged training and an added secretarial burden for radiologists. We assessed how much proofing radiologists who have years of experience with SR and radiologists new to SR must perform, and estimated how quickly the new users become as skilled as the experienced users. We studied SR log entries for 0.25 million reports from 154 radiologists and after careful exclusions, defined a group of 11 experienced radiologists and 71 radiologists new to SR (24,833 and 122,093 reports, respectively). Data were analyzed for sound file and report lengths, character-based error rates, and words unknown to the SR’s dictionary. Experienced radiologists corrected 6 characters for each report and for new users, 11. Some users presented a very unfavorable learning curve, with error rates not declining as expected. New users’ reports were longer, and data for the experienced users indicates that their reports, initially equally lengthy, shortened over a period of several years. For most radiologists, only minor corrections of dictated reports were necessary. While new users adopted SR quickly, with a subset outperforming experienced users from the start, identification of users struggling with SR will help facilitate troubleshooting and support.
Speech recognition; Radiology reporting; Workflow; Statistic analysis
The main goal of this study was to determine the reproducibility of the reading of wrist trauma case radiographs using three different media: laser film, a picture archiving and communication systems (PACS) workstation, and paper with an optimized layout. The study was conducted retrospectively in 200 consecutive patients consulting at the emergency department for wrist trauma and who underwent wrist X-ray investigation using a computed radiography system. There were 82 men and 118 women. The mean age was 48.3 years (16–95 years). Our institutional review board does not require patient approval or informed consent for retrospective review of case records. The readings were made by two independent readers who analyzed the 200 patient radiographs consecutively in one session for each type of media: paper, laser film, and on a PACS dual-screen workstation. The inter-reader agreements were substantial or almost perfect, with kappa values of 0.83 (0.76–0.90) for the PACS, 0.83 (0.76–0.90) for film, and 0.80 (0.72–0.87) for paper. The inter-technique agreement was almost perfect in all cases. There is a high interobserver agreement between PACS, laser film, and paper readings for wrist trauma cases. With a layout of one radiograph on each sheet, paper could replace laser films to communicate the results of wrist radiographs in trauma cases for outpatients.
Digital radiography; Wrist trauma; Scaphoid; Fracture; PACS
Multiclass brain tumor classification is performed by using a diversified dataset of 428 post-contrast T1-weighted MR images from 55 patients. These images are of primary brain tumors namely astrocytoma (AS), glioblastoma multiforme (GBM), childhood tumor-medulloblastoma (MED), meningioma (MEN), secondary tumor-metastatic (MET), and normal regions (NR). Eight hundred fifty-six regions of interest (SROIs) are extracted by a content-based active contour model. Two hundred eighteen intensity and texture features are extracted from these SROIs. In this study, principal component analysis (PCA) is used for reduction of dimensionality of the feature space. These six classes are then classified by artificial neural network (ANN). Hence, this approach is named as PCA-ANN approach. Three sets of experiments have been performed. In the first experiment, classification accuracy by ANN approach is performed. In the second experiment, PCA-ANN approach with random sub-sampling has been used in which the SROIs from the same patient may get repeated during testing. It is observed that the classification accuracy has increased from 77 to 91 %. PCA-ANN has delivered high accuracy for each class: AS—90.74 %, GBM—88.46 %, MED—85 %, MEN—90.70 %, MET—96.67 %, and NR—93.78 %. In the third experiment, to remove bias and to test the robustness of the proposed system, data is partitioned in a manner such that the SROIs from the same patient are not common for training and testing sets. In this case also, the proposed system has performed well by delivering an overall accuracy of 85.23 %. The individual class accuracy for each class is: AS—86.15 %, GBM—65.1 %, MED—63.36 %, MEN—91.5 %, MET—65.21 %, and NR—93.3 %. A computer-aided diagnostic system comprising of developed methods for segmentation, feature extraction, and classification of brain tumors can be beneficial to radiologists for precise localization, diagnosis, and interpretation of brain tumors on MR images.
Multiclass brain tumor classification; Content-based active contour (CBAC); Feature extraction; Principal component analysis (PCA); Segmented regions of interest (SROIs)
Published information on contrast detection threshold is based primarily on research using a location-known methodology. In previous work on testing the Digital Imaging and Communications in Medicine (DICOM) Grayscale Standard Display Function (GSDF) for perceptual linearity, this research group used a location-unknown methodology to more closely reflect clinical practice. A high false-positive rate resulted in a high variance leading to the conclusion that the impact on results of employing a location-known methodology needed to be explored. Fourteen readers reviewed two sets of simulated mammographic background images, one with the location-unknown and one with the location-known methodology. The results of the reader study were analyzed using Reader Operating Characteristic (ROC) methodology and a paired t test. Contrast detection threshold was analyzed using contingency tables. No statistically significant difference was found in GSDF testing, but a highly statistical significant difference (p value <0.0001) was seen in the ROC (AUC) curve between the location-unknown and the location-known methodologies. Location-known methodology not only improved the power of the GSDF test but also affected the contrast detection threshold which changed from +3 when the location was unknown to +2 gray levels for the location-known images. The selection of location known versus unknown in experimental design must be carefully considered to ensure that the conclusions of the experiment reflect the study’s objectives.
Image perception; contrast threshold; GSDF; ROC; SKE; LKE
There has been increasing interest in adjusting CT radiation dose data for patient body size. A method for automated computation of the abdominal effective diameter of a patient from a CT image has previously only been tested in adult patients. In this work, we tested the method on a set of 128 pediatric patients aged 0.8 to 12.9 years (average 8.0 years, SD = 3.7 years) who had CT abdomen/pelvis exams performed on a Toshiba Aquilion 64 scanner. For this set of patients, age-predicted abdominal effective diameter extrapolated based on data from the International Commission on Radiation Units and Measurements was a relatively poor predictor of measured effective diameter. The mean absolute percentage error between the CTDI normalization coefficient calculated from a manually measured effective diameter and the coefficient determined by age-predicted effective diameter was 12.3 % with respect to a 32 cm phantom (range 0.0–52.8 %, SD 8.7 %) and 12.9 % with respect to a 16 cm phantom (range 0.0–56.4 %, SD 9.2 %). In contrast, there is a close correspondence between the automated and manually measured patient effective diameters, with a mean absolute error of 0.6 cm (error range 0.2–1.3 cm). This correspondence translates into a high degree of correspondence between normalization coefficients determined by automated and manual measurements; the mean absolute percentage error was 2.1 % with respect to a 32 cm phantom (range 0.0–8.1 %, SD = 1.4 %) and 2.3 % with respect to a 16 cm phantom (range 0.0–9.3 %, SD = 1.6 %).
Computed tomography; Radiation dose; Body imaging; Quality control; Image analysis; Pediatrics
To improve evaluations of cortical and subcortical diffusivity in neurological diseases, it is necessary to improve the accuracy of brain diffusion tensor imaging (DTI) data segmentation. The conventional partial volume segmentation method fails to classify voxels with multiple white matter (WM) fiber orientations such as fiber-crossing regions. Our purpose was to improve the performance of segmentation by taking into account the partial volume effects due to both multiple tissue types and multiple WM fiber orientations. We quantitatively evaluated the overall performance of the proposed method using digital DTI phantom data. Moreover, we applied our method to human DTI data, and compared our results with those of a conventional method. In the phantom experiments, the conventional method and proposed method yielded almost the same root mean square error (RMSE) for gray matter (GM) and cerebrospinal fluid (CSF), while the RMSE in the proposed method was smaller than that in the conventional method for WM. The volume overlap measures between our segmentation results and the ground truth of the digital phantom were more than 0.8 in all three tissue types, and were greater than those in the conventional method. In visual comparisons for human data, the WM/GM/CSF regions obtained using our method were in better agreement with the corresponding regions depicted in the structural image than those obtained using the conventional method. The results of the digital phantom experiment and human data demonstrated that our method improved accuracy in the segmentation of brain tissue data on DTI compared to the conventional method.
DTI; Brain tissue segmentation; Digital DTI phantom; Partial volume effect; Multiple-tensor estimation
This study aimed to determine if phantom-based methodologies for optimization of hepatic lesion detection with computed tomography (CT) require randomization of lesion placement and inclusion of normal images. A phantom containing fixed opacities of varying size (diameters, 2.4, 4.8, and 9.5 mm) was scanned at various exposure and slice thickness settings. Two image sets were compared: All images in the first image set contained opacities with known location; the second image set contained images with opacities in random locations. Following Institutional Review Board approval, nine experienced observers scored opacity visualization using a 4-point confidence scale. Comparisons between image sets were performed using Spearman, Kappa, and Wilcoxon techniques. Observer scores demonstrated strong correlation between both approaches when all opacity sizes were combined (r = 0.92, p < 0.0001), for the 9.5 mm opacity (r = 0.96, p < 0.0001) and for the 2.4 mm opacity (r = 0.64, p < 0.05). There was no significant correlation for the 4.8 mm opacity. A significantly higher sensitivity score for the known compared with the unknown location was found for the 9.5 mm opacity and 4.8 mm opacity for a single slice thickness and exposure condition (p < 0.05). Phantom-based optimization of CT hepatic examinations requires randomized lesion location when investigating challenging conditions; however, a standard phantom with fixed lesion location is suitable for the optimization of routine liver protocols. The development of more sophisticated phantoms or methods than those currently available is indicated for the optimization of CT protocols for diagnostic tasks involving the detection of subtle change.
Dose optimization; Radiation; Phantom; Computed tomography
The purpose of this study was to determine whether it would be possible to minimise the delay that occurs between the time a radiological image becomes available for viewing on PACS and the time that it is actually seen by the requesting physician. The study was conducted at Sir Charles Gairdner Hospital in Perth Western Australia. Participants in the study were all junior doctors. The first part of the study measured the current time delay between images being available on PACS and actually being viewed. In the second part of the study, the doctors were notified by a paging system when the images were available. The reduction in time delay was then compared. Following pager notification, the mean average time delay reduced from a mean of 180.02 min (95 % confidence interval (CI), 135.1 to 225 min) to a mean of 33.94 min (95 % CI, 24.1 to 43.8 min; P < 0.0001). The study has demonstrated that it is possible to modify clinicians’ usage of PACS; however, there remain questions regarding the sustainability of such an intervention and the impact that this may have on overall patient outcome. There may be potential for integration of the rapidly expanding technologies such as tablets, iPads and iPhones in order to automate this type of notification and this may be a focus of future research.
PACS management; PACS reading; Time and motion studies
Diabetic retinopathy (DR) is increasing progressively pushing the demand of automatic extraction and classification of severity of diseases. Blood vessel extraction from the fundus image is a vital and challenging task. Therefore, this paper presents a new, computationally simple, and automatic method to extract the retinal blood vessel. The proposed method comprises several basic image processing techniques, namely edge enhancement by standard template, noise removal, thresholding, morphological operation, and object classification. The proposed method has been tested on a set of retinal images. The retinal images were collected from the DRIVE database and we have employed robust performance analysis to evaluate the accuracy. The results obtained from this study reveal that the proposed method offers an average accuracy of about 97 %, sensitivity of 99 %, specificity of 86 %, and predictive value of 98 %, which is superior to various well-known techniques.
Diabetic retinopathy; Kirsch’s template; Object classification; Vessel detection; Image processing
In this paper, we present automatic image segmentation and classification technique for carotid artery ultrasound images based on active contour approach. For early detection of the plaque in carotid artery to avoid serious brain strokes, active contour-based techniques have been applied successfully to segment out the carotid artery ultrasound images. Further, ultrasound images might be affected due to rotation, scaling, or translational factors during acquisition process. Keeping in view these facts, image alignment is used as a preprocessing step to align the carotid artery ultrasound images. In our experimental study, we exploit intima–media thickness (IMT) measurement to detect the presence of plaque in the artery. Support vector machine (SVM) classification is employed using these segmented images to distinguish the normal and diseased artery images. IMT measurement is used to form the feature vector. Our proposed approach segments the carotid artery images in an automatic way and further classifies them using SVM. Experimental results show the learning capability of SVM classifier and validate the usefulness of our proposed approach. Further, the proposed approach needs minimum interaction from a user for an early detection of plaque in carotid artery. Regarding the usefulness of the proposed approach in healthcare, it can be effectively used in remote areas as a preliminary clinical step even in the absence of highly skilled radiologists.
Plaque detection; IMT measurement; Image segmentation; Image registration; SVM classification
Monitoring the openness of the major temporal arcade (MTA) and how it changes over time could facilitate diagnosis and treatment of proliferative diabetic retinopathy (PDR). We present methods for user-guided semiautomated modeling and measurement of the openness of the MTA based on Gabor filters for the detection of retinal vessels, morphological image processing, and a form of the generalized Hough transform for the detection of parabolas. The methods, implemented via a graphical user interface, were tested with retinal fundus images of 11 normal individuals and 11 patients with PDR in the present pilot study on potential clinical application. A method of arcade angle measurement was used for comparative analysis. The results using the openness parameters of single- and dual-parabolic models as well as the arcade angle measurements indicate areas under the receiver operating characteristics of Az = 0.87, 0.82, and 0.80, respectively. The proposed methods are expected to facilitate quantitative analysis of the architecture of the MTA, as well as assist in detection and diagnosis of PDR.
Gabor filters; Hough transform; Parabolic modeling; Proliferative diabetic retinopathy; Retinal fundus imaging; Retinal vessels; Temporal arcade; Temporal arcade angle
Picture Archiving and Communications System (PACS) was originally developed for radiology services over 20 years ago to capture medical images electronically. Medical diagnosis methods are based on images such as clinical radiographs, ultrasounds, CT scans, MRIs, or other imaging modalities. Information obtained from these images is correlated with patient information. So with regards to the important role of PACS in hospitals, we aimed to evaluate the PACS and survey the information security needed in the Radiological Information system. First, we surveyed the different aspects of PACS that should be in any health organizations based on Department of Health standards and prepared checklists for assessing the PACS in different hospitals. Second, we surveyed the security controls that should be implemented in PACS. Checklists reliability is affirmed by professors of Tehran Science University. Then, the final data are inputted in SPSS software and analyzed. The results indicate that PACS in hospitals can transfer patient demographic information but they do not show route of information. These systems are not open source. They don’t use XML-based standard and HL7 standard for exchanging the data. They do not use DS digital signature. They use passwords and the user can correct or change the medical information. PACS can detect alternation rendered. The survey of results demonstrates that PACS in all hospitals has the same features. These systems have the patient demographic data but they do not have suitable flexibility to interface network or taking reports. For the privacy of PACS in all hospitals, there were passwords for users and the system could show the changes that have been made; but there was no water making or digital signature for the users.
Picture Archiving and Communications System; Radiological Information System; Information Security
The Radiological Society of North America (RSNA) has developed a set of templates for structured reporting of radiology results. To measure how much of the content of conventional narrative (“free-text”) reports is covered by the concepts included in the RSNA reporting templates, we selected five reporting templates that represented a variety of imaging modalities and organ systems. From a sample of 8,275 consecutive, de-identified radiology reports from an academic medical center, we identified one corresponding imaging procedure code for each reporting template. The reports were annotated with RadLex and SNOMED CT terms using the BioPortal Annotator web service. The reporting templates we examined accounted for 17 to 49 % of the concepts that actually appeared in a sample of corresponding radiology reports. The findings suggest that the concepts that appear in the reporting templates occur frequently within free-text clinical reports; thus, the templates provide useful coverage of the “domain of discourse” in radiology reports. The techniques used in this study may be helpful to guide the development of reporting templates by identifying concepts that occur frequently in radiology reports, to evaluate the coverage of existing templates, and to establish global benchmarks for reporting templates.
Radiology; Reporting; Structured reports; Narrative (free-text) reports; Reporting templates; Biomedical ontologies; RadLex; SNOMED CT; BioPortal Annotator
The objective of this study is to evaluate a natural language processing (NLP) algorithm that determines American College of Radiology Breast Imaging Reporting and Data System (BI-RADS) final assessment categories from radiology reports. This HIPAA-compliant study was granted institutional review board approval with waiver of informed consent. This cross-sectional study involved 1,165 breast imaging reports in the electronic medical record (EMR) from a tertiary care academic breast imaging center from 2009. Reports included screening mammography, diagnostic mammography, breast ultrasound, combined diagnostic mammography and breast ultrasound, and breast magnetic resonance imaging studies. Over 220 reports were included from each study type. The recall (sensitivity) and precision (positive predictive value) of a NLP algorithm to collect BI-RADS final assessment categories stated in the report final text was evaluated against a manual human review standard reference. For all breast imaging reports, the NLP algorithm demonstrated a recall of 100.0 % (95 % confidence interval (CI), 99.7, 100.0 %) and a precision of 96.6 % (95 % CI, 95.4, 97.5 %) for correct identification of BI-RADS final assessment categories. The NLP algorithm demonstrated high recall and precision for extraction of BI-RADS final assessment categories from the free text of breast imaging reports. NLP may provide an accurate, scalable data extraction mechanism from reports within EMRs to create databases to track breast imaging performance measures and facilitate optimal breast cancer population management strategies.
Breast Imaging Reporting and Data System (BI-RADS); Natural language processing; Imaging informatics; Breast
Introduce the notion of cross-sectional relatedness as an informational dependence relation between sentences in the conclusion section of a breast radiology report and sentences in the findings section of the same report. Assess inter-rater agreement of breast radiologists. Develop and evaluate a support vector machine (SVM) classifier for automatically detecting cross-sectional relatedness. A standard reference is manually created from 444 breast radiology reports by the first author. A subset of 37 reports is annotated by five breast radiologists. Inter-rater agreement is computed among their annotations and standard reference. Thirteen numerical features are developed to characterize pairs of sentences; the optimal feature set is sought through forward selection. Inter-rater agreement is F-measure 0.623. SVM classifier has F-measure of 0.699 in the 12-fold cross-validation protocol against standard reference. Report length does not correlate with the classifier’s performance (correlation coefficient = −0.073). SVM classifier has average F-measure of 0.505 against annotations by breast radiologists. Mediocre inter-rater agreement is possibly caused by: (1) definition is insufficiently actionable, (2) fine-grained nature of cross-sectional relatedness on sentence level, instead of, for instance, on paragraph level, and (3) higher-than-average complexity of 37-report sample. SVM classifier performs better against standard reference than against breast radiologists’s annotations. This is supportive of (3). SVM’s performance on standard reference is satisfactory. Since optimal feature set is not breast specific, results may transfer to non-breast anatomies. Applications include a smart report viewing environment and data mining.
Electronic supplementary material
The online version of this article (doi:10.1007/s10278-013-9612-9) contains supplementary material, which is available to authorized users.
Radiology reports; Information retrieval; Support vector machine; Text mining; Inter-rater agreement; Textual entailment
Adrenal abnormalities are commonly identified on computed tomography (CT) and are seen in at least 5 % of CT examinations of the thorax and abdomen. Previous studies have suggested that evaluation of Hounsfield units within a region of interest or a histogram analysis of a region of interest can be used to determine the likelihood that an adrenal gland is abnormal. However, the selection of a region of interest can be arbitrary and operator dependent. We hypothesize that segmenting the entire adrenal gland automatically without any human intervention and then performing a histogram analysis can accurately detect adrenal abnormality. We use the random forest classification framework to automatically perform a pixel-wise classification of an entire CT volume (abdomen and pelvis) into three classes namely right adrenal, left adrenal, and background. Once we obtain this classification, we perform histogram analysis to detect adrenal abnormality. The combination of these methods resulted in a sensitivity and specificity of 80 and 90 %, respectively, when analyzing 20 adrenal glands seen on volumetric CT datasets for abnormality.
Adrenal glands; Abnormality detection; Random forest
Identification and classification of left ventricular (LV) regional wall motion (RWM) abnormalities on echocardiograms has fundamental clinical importance for various cardiovascular disease assessments especially in ischemia. In clinical practice, this evaluation is still performed visually which is highly dependent on training and experience of the echocardiographers and therefore suffers from significant interobserver and intraobserver variability. This paper presents a new automatic technique, based on nonrigid image registration for classifying the RWM of LV in a three-point scale. In this algorithm, we register all images of one cycle of heart to a reference image (end-diastolic image) using a hierarchical parametric model. This model is based on an affine transformation for modeling the global LV motion and a B-spline free-form deformation transformation for modeling the local LV deformation. We consider image registration as a multiresolution optimization problem. Finally, a new regional quantitative index based on resultant parameters of the hierarchical transformation model is proposed for classifying RWM in a three-point scale. The results obtained by our method are quantitatively evaluated to those obtained by two experienced echocardiographers visually as gold standard on ten healthy volunteers and 14 patients (two apical views) and resulted in an absolute agreement of 83 % and a relative agreement of 99 %. Therefore, this diagnostic system can be used as a useful tool as well as reference visual assessment to classify RWM abnormalities in clinical evaluation.
Echocardiography images; LV motion; Nonrigid image registration
In this paper, a heuristic approach to automated nipple detection in digital mammograms is presented. A multithresholding algorithm is first applied to segment the mammogram and separate the breast region from the background region. Next, the problem is considered separately for craniocaudal (CC) and mediolateral-oblique (MLO) views. In the simplified algorithm, a search is performed on the segmented image along a band around the centroid and in a direction perpendicular to the pectoral muscle edge in the MLO view image. The direction defaults to the horizontal (perpendicular to the thoracic wall) in case of CC view images. The farthest pixel from the base found in this direction can be approximated as the nipple point. Further, an improved version of the simplified algorithm is proposed which can be considered as a subclass of the Branch and Bound algorithms. The mean Euclidean distance between the ground truth and calculated nipple position for 500 mammograms from the Digital Database for Screening Mammography (DDSM) database was found to be 11.03 mm and the average total time taken by the algorithm was 0.79 s. Results of the proposed algorithm demonstrate that even simple heuristics can achieve the desired result in nipple detection thus reducing the time and computational complexity.
Breast cancer; Nipple detection; Mammography; DDSM database; Multithresholding
This study aims to determine the most informative mammographic features for breast cancer diagnosis using mutual information (MI) analysis. Our Health Insurance Portability and Accountability Act-approved database consists of 44,397 consecutive structured mammography reports for 20,375 patients collected from 2005 to 2008. The reports include demographic risk factors (age, family and personal history of breast cancer, and use of hormone therapy) and mammographic features from the Breast Imaging Reporting and Data System lexicon. We calculated MI using Shannon’s entropy measure for each feature with respect to the outcome (benign/malignant using a cancer registry match as reference standard). In order to evaluate the validity of the MI rankings of features, we trained and tested naïve Bayes classifiers on the feature with tenfold cross-validation, and measured the predictive ability using area under the ROC curve (AUC). We used a bootstrapping approach to assess the distributional properties of our estimates, and the DeLong method to compare AUC. Based on MI, we found that mass margins and mass shape were the most informative features for breast cancer diagnosis. Calcification morphology, mass density, and calcification distribution provided predictive information for distinguishing benign and malignant breast findings. Breast composition, associated findings, and special cases provided little information in this task. We also found that the rankings of mammographic features with MI and AUC were generally consistent. MI analysis provides a framework to determine the value of different mammographic features in the pursuit of optimal (i.e., accurate and efficient) breast cancer diagnosis.
Breast cancer; Mammography; BI-RADS; Decision support; Informatics; Mutual information
It is often difficult for clinicians to decide correctly on either biopsy or follow-up for breast lesions with masses on ultrasonographic images. The purpose of this study was to develop a computerized determination scheme for histological classification of breast mass by using objective features corresponding to clinicians’ subjective impressions for image features on ultrasonographic images. Our database consisted of 363 breast ultrasonographic images obtained from 363 patients. It included 150 malignant (103 invasive and 47 noninvasive carcinomas) and 213 benign masses (87 cysts and 126 fibroadenomas). We divided our database into 65 images (28 malignant and 37 benign masses) for training set and 298 images (122 malignant and 176 benign masses) for test set. An observer study was first conducted to obtain clinicians’ subjective impression for nine image features on mass. In the proposed method, location and area of the mass were determined by an experienced clinician. We defined some feature extraction methods for each of nine image features. For each image feature, we selected the feature extraction method with the highest correlation coefficient between the objective features and the average clinicians’ subjective impressions. We employed multiple discriminant analysis with the nine objective features for determining histological classification of mass. The classification accuracies of the proposed method were 88.4 % (76/86) for invasive carcinomas, 80.6 % (29/36) for noninvasive carcinomas, 86.0 % (92/107) for fibroadenomas, and 84.1 % (58/69) for cysts, respectively. The proposed method would be useful in the differential diagnosis of breast masses on ultrasonographic images as diagnosis aid.
Computer-aided diagnosis; Histological classification; Observer study; Feature extraction method; Ultrasonographic image
Nowadays, the huge volume of medical images represents an enormous challenge towards health-care organizations, as it is often hard for clinicians and researchers to manage, access, and share the image database easily. Content-based medical image retrieval (CBMIR) techniques are employed to facilitate the above process. It is known that a few concrete factors, including visual attributes extracted from images, measures encoding the similarity between images, user interaction, etc. play important roles in determining the retrieval performance. This paper concentrates on the similarity learning problem of CBMIR. A novel similarity learning paradigm is proposed via relative comparison, and a large database composed of 5,000 images is utilized to evaluate the retrieval performance. Extensive experimental results and comprehensive statistical analysis demonstrate the superiority of adopting the newly introduced learning paradigm, compared with several conventional supervised and semi-supervised similarity learning methods, in the presented CBMIR application.
Content-based medical image retrieval; Similarity learning; Relative comparison