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
This work demonstrates the image qualities between two popular JPEG2000 programs. Two medical image compression algorithms are both coded using JPEG2000, but they are different regarding the interface, convenience, speed of computation, and their characteristic options influenced by the encoder, quantization, tiling, etc. The differences in image quality and compression ratio are also affected by the modality and compression algorithm implementation. Do they provide the same quality? The qualities of compressed medical images from two image compression programs named Apollo and JJ2000 were evaluated extensively using objective metrics. These algorithms were applied to three medical image modalities at various compression ratios ranging from 10:1 to 100:1. Following that, the quality of the reconstructed images was evaluated using five objective metrics. The Spearman rank correlation coefficients were measured under every metric in the two programs. We found that JJ2000 and Apollo exhibited indistinguishable image quality for all images evaluated using the above five metrics (r > 0.98, p < 0.001). It can be concluded that the image quality of the JJ2000 and Apollo algorithms is statistically equivalent for medical image compression.
Image compression; JPEG2000; Image quality
Computer-aided diagnosis (CAD) systems are software programs that use algorithms to find patterns associated with breast cancer on breast magnetic resonance imaging (MRI). The most commonly used CAD systems in the USA are CADstream (CS) (Merge Healthcare Inc., Chicago, IL) and DynaCAD for Breast (DC) (Invivo, Gainesville, FL). Our primary objective in this study was to compare the CS and DC breast MRI CAD systems for diagnostic accuracy and postprocessed image quality. Our secondary objective was to compare the evaluation times of radiologists using each system. Three radiologists evaluated 30 biopsy-proven malignant lesions and 29 benign lesions on CS and DC and rated the lesions’ malignancy status using the Breast Imaging Reporting and Data System. Image quality was ranked on a 0–5 scale, and mean reading times were also recorded. CS detected 70 % of the malignant and 32 % of the benign lesions while DC detected 81 % of the malignant lesions and 34 % of the benign lesions. Analysis of the area under the receiver operating characteristic curve revealed that the difference in diagnostic performance was not statistically significant. On image quality scores, CS had significantly higher volume rendering (VR) (p < 0.0001) and motion correction (MC) scores (p < 0.0001). There were no statistically significant differences in the remaining image quality scores. Differences in evaluation times between DC and CS were also not statistically significant. We conclude that both CS and DC perform similarly in aiding detection of breast cancer on MRI. MRI CAD selection will likely be based on other factors, such as user interface and image quality preferences, including MC and VR.
Breast; Breast diseases; Computer-assisted detection; Computer-aided diagnosis (CAD); Diagnostic imaging; MR imaging
Automatic detection of the nipple in mammograms is an important step in computerized systems that combine multiview information for accurate detection and diagnosis of breast cancer. Locating the nipple is a difficult task owing to variations in image quality, presence of noise, and distortion and displacement of the breast tissue due to compression. In this work, we propose a novel Hessian-based method to locate automatically the nipple in screen-film and full-field digital mammograms (FFDMs). The method includes detection of a plausible nipple/retroareolar area in a mammogram using geometrical constraints, analysis of the gradient vector field by mean and Gaussian curvature measurements, and local shape-based conditions. The proposed procedure was tested on 566 mammographic images consisting of 372 randomly selected scanned films from two public databases (mini-MIAS and DDSM), and 194 digital mammograms acquired with a GE Senographe 2000D FFDM system. A radiologist independently marked the centers of the nipples for evaluation of the results. The average error obtained was 6.7 mm (22 pixels) with reference to the center of the nipple as identified by the radiologist. Only two out of the 566 detected nipples (0.35 %) had an error larger than 50 mm. The method was also directly compared with two other techniques for the detection of the nipple. The results indicate that the proposed method outperforms other algorithms presented in the literature and can be used to identify accurately the nipple on various types of mammographic images.
Digital mammography; Computer-aided detection and diagnosis; Breast imaging; Nipple detection; Image processing; Hessian
In this paper, we propose a graphcut method to segment the cardiac right ventricle (RV) and left ventricle (LV) by using context information from each other. Contextual information is very helpful in medical image segmentation because the relative arrangement of different organs is the same. In addition to the conventional log-likelihood penalty, we also include a “context penalty” that captures the geometric relationship between the RV and LV. Contextual information for the RV is obtained by learning its geometrical relationship with respect to the LV. Similarly, RV provides geometrical context information for LV segmentation. The smoothness cost is formulated as a function of the learned context which helps in accurate labeling of pixels. Experimental results on real patient datasets from the STACOM database show the efficacy of our method in accurately segmenting the LV and RV. We also conduct experiments on simulated datasets to investigate our method’s robustness to noise and inaccurate segmentations.
Mutual context information; LV; RV; Segmentation; Cardiac; MRI; Graph cuts
Increasing incidence of Crohn’s disease (CD) in the Western world has made its accurate diagnosis an important medical challenge. The current reference standard for diagnosis, colonoscopy, is time-consuming and invasive while magnetic resonance imaging (MRI) has emerged as the preferred noninvasive procedure over colonoscopy. Current MRI approaches assess rate of contrast enhancement and bowel wall thickness, and rely on extensive manual segmentation for accurate analysis. We propose a supervised learning method for the identification and localization of regions in abdominal magnetic resonance images that have been affected by CD. Low-level features like intensity and texture are used with shape asymmetry information to distinguish between diseased and normal regions. Particular emphasis is laid on a novel entropy-based shape asymmetry method and higher-order statistics like skewness and kurtosis. Multi-scale feature extraction renders the method robust. Experiments on real patient data show that our features achieve a high level of accuracy and perform better than two competing methods.
Crohn’s Disease; Detection; Classifiers; Features
This study measured reading workstation monitors and the viewing environment currently available within BreastScreen New South Wales (BSNSW) centres to determine levels of adherence to national and international guidelines. Thirteen workstations from four BSNSW service centres were assessed using the American Association of Physicists in Medicine Task Group 18 Quality Control test pattern. Reading workstation monitor performance and ambient light levels when interpreting screening mammographic images were assessed using spectroradiometer CS-2000 and chroma meter CL-200. Overall, radiologic monitors within BSNSW were operating at good acceptable levels. Some non-adherence to published guidelines included the percentage difference in maximum luminance between pairs of primary monitors at individual workstations (61.5 % or 30.8 % of workstations depending on specific guidelines), maximum luminance (23.1 % of workstations), luminance non-uniformity (11.5 % of workstations) and minimum luminance (3.8 % of workstations). A number of ambient light measurements did not comply with the only available evidence-based guideline relevant to the methodology used in this study. Larger ambient light variations across sites are shown when monitors were switched off, suggesting that differences in ambient lighting between sites can be masked when a standard mammogram is displayed for photometric measurements. Overall, BSNSW demonstrated good adherence to available guidelines, although some non-compliance has been shown. Recently updated United Kingdom and Australian guidelines should help reduce confusion generated by the plethora and sometimes dated nature of currently available recommendations.
Mammography; Monitor performance; Ambient light; BreastScreen; 5 M-pixel monitor
Radiologists routinely make decisions with only limited information when assigning protocol instructions for the performance of advanced medical imaging examinations. Opportunity exists to simultaneously improve the safety, quality and efficiency of this workflow through the application of an electronic solution leveraging health system resources to provide concise, tailored information and decision support in real-time. Such a system has been developed using an open source, open standards design for use within the Veterans Health Administration. The Radiology Protocol Tool Recorder (RAPTOR) project identified key process attributes as well as inherent weaknesses of paper processes and electronic emulators of paper processes to guide the development of its optimized electronic solution. The design provides a kernel that can be expanded to create an integrated radiology environment. RAPTOR has implications relevant to the greater health care community, and serves as a case model for modernization of legacy government health information systems.
RIS; Protocol; Informatics; Efficiency; Quality; Patient safety; Open source; Drupal; Content management; Workflow; Web services
This study aims to evaluate whether the distribution of vessels inside and adjacent to tumor region at three-dimensional (3-D) power Doppler ultrasonography (US) can be used for the differentiation of benign and malignant breast tumors. 3-D power Doppler US images of 113 solid breast masses (60 benign and 53 malignant) were used in this study. Blood vessels within and adjacent to tumor were estimated individually in 3-D power Doppler US images for differential diagnosis. Six features including volume of vessels, vascularity index, volume of tumor, vascularity index in tumor, vascularity index in normal tissue, and vascularity index in surrounding region of tumor within 2 cm were evaluated. Neural network was then used to classify tumors by using these vascular features. The receiver operating characteristic (ROC) curve analysis and Student’s t test were used to estimate the performance. All the six proposed vascular features are statistically significant (p < 0.001) for classifying the breast tumors as benign or malignant. The AZ (area under ROC curve) values for the classification result were 0.9138. Accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of the diagnosis performance based on all six proposed features were 82.30 (93/113), 86.79 (46/53), 78.33 (47/60), 77.97 (46/59), and 87.04 % (47/54), respectively. The p value of AZ values between the proposed method and conventional vascularity index method using z test was 0.04.
3-D ultrasound; Power Doppler ultrasound; Breast tumor; Vascularity
Today, most medical images are stored as a set of single-frame composite Digital Imaging and Communications in Medicine (DICOM) objects that contain the four levels of the DICOM information model—patient, study, series, and instance. Although DICOM addresses most of the issues related to medical image archiving, it has some limitations. Replicating the header information with each DICOM object increases the study size and the parsing overhead. Multi-frame DICOM (MFD) was developed to address this, among other issues. The MFD combines all DICOM objects belonging to a series into a single DICOM object. Hence, the series-level attributes are normalized, and the amount of header data repetition is reduced. In this paper, multi-series DICOM (MSD) is introduced as a potential extension to the DICOM standard that allows faster parsing, transmission, and storage of studies. MSD extends the MFD de-duplication of series-level attributes to study-level attributes. A single DICOM object that stores the whole study is proposed. An efficient algorithm, called the one-pass de-duplication algorithm, was developed to find and eliminate the replicated data elements within the study. A group of experiments were done that evaluate MSD and the one-pass de-duplication algorithm performance. The experiments show that MSD significantly reduces the amount of data repetition and decreases the time required to read and parse DICOM studies. MSD is one possible solution that addresses the DICOM limitations regarding header information repetition.
DICOM; Algorithms; Imaging informatics; Image data; Multi-frame DICOM; Multi-series DICOM
Diabetic maculopathy is one of the retinal abnormalities in which a diabetic patient suffers from severe vision loss due to the affected macula. It affects the central vision of the person and causes blindness in severe cases. In this article, we propose an automated medical system for the grading of diabetic maculopathy that will assist the ophthalmologists in early detection of the disease. The proposed system extracts the macula from digital retinal image using the vascular structure and optic disc location. It creates a binary map for possible exudate regions using filter banks and formulates a detailed feature vector for all regions. The system uses a Gaussian Mixture Model-based classifier to the retinal image in different stages of maculopathy by using the macula coordinates and exudate feature set. The evaluation of proposed system is performed by using publicly available standard retinal image databases. The results of our system have been compared with other methods in the literature in terms of sensitivity, specificity, positive predictive value and accuracy. Our system gives higher values as compared to others on the same databases which makes it suitable for an automated medical system for grading of diabetic maculopathy.
Diabetic maculopathy; Exudates; Macula; Feature extraction; Gaussian mixture model
A study was conducted to evaluate the sensitivity of computer-aided detection (CAD) with full-field digital mammography in detection of breast cancer, based on mammographic appearance and histopathology. Retrospectively, CAD sensitivity was assessed in total group of 152 cases for subgroups based on breast density, mammographic presentation, lesion size, and results of histopathological examination. The overall sensitivity of CAD was 91 % (139 of 152 cases). CAD detected 100 % (47/47) of cancers manifested as microcalcifications; 98 % (62/63) of those manifested as non-calcified masses; 100 % (15/15) of those manifested as mixed masses and microcalcifications; 75 % (12/16) of those manifested as architectural distortions, and 69 % (18/26) of those manifested as focal asymmetry. CAD sensitivity was 83 % (10/12) for cancers measuring 1–10 mm, 92 % (37/40) for those measuring 11–20 mm, and 92 % (92/100) for those measuring >20 mm. There was no significant difference in CAD detection efficiency between cancers in dense breasts (88 %; 69/78) and those in non-dense breasts (95 %; 70/74). CAD showed a high sensitivity of 91 % (139/152) for the mammographic appearance of cancer and 100 % sensitivity for identifying cancers manifested as microcalcifications. Sensitivity was not influenced by breast density or lesion size. CAD should be effective for helping radiologists detect breast cancer at an earlier stage.
Breast neoplasm; Cancer detection; Computer-aided diagnosis (CAD); Digital mammography
A widening array of novel imaging biomarkers is being developed using ever more powerful clinical and preclinical imaging modalities. These biomarkers have demonstrated effectiveness in quantifying biological processes as they occur in vivo and in the early prediction of therapeutic outcomes. However, quantitative imaging biomarker data and knowledge are not standardized, representing a critical barrier to accumulating medical knowledge based on quantitative imaging data. We use an ontology to represent, integrate, and harmonize heterogeneous knowledge across the domain of imaging biomarkers. This advances the goal of developing applications to (1) improve precision and recall of storage and retrieval of quantitative imaging-related data using standardized terminology; (2) streamline the discovery and development of novel imaging biomarkers by normalizing knowledge across heterogeneous resources; (3) effectively annotate imaging experiments thus aiding comprehension, re-use, and reproducibility; and (4) provide validation frameworks through rigorous specification as a basis for testable hypotheses and compliance tests. We have developed the Quantitative Imaging Biomarker Ontology (QIBO), which currently consists of 488 terms spanning the following upper classes: experimental subject, biological intervention, imaging agent, imaging instrument, image post-processing algorithm, biological target, indicated biology, and biomarker application. We have demonstrated that QIBO can be used to annotate imaging experiments with standardized terms in the ontology and to generate hypotheses for novel imaging biomarker–disease associations. Our results established the utility of QIBO in enabling integrated analysis of quantitative imaging data.
Imaging biomarker; Ontology development; Quantitative imaging
The objective of this study was to investigate the method of the combination of radiological and textural features for the differentiation of malignant from benign solitary pulmonary nodules by computed tomography. Features including 13 gray level co-occurrence matrix textural features and 12 radiological features were extracted from 2,117 CT slices, which came from 202 (116 malignant and 86 benign) patients. Lasso-type regularization to a nonlinear regression model was applied to select predictive features and a BP artificial neural network was used to build the diagnostic model. Eight radiological and two textural features were obtained after the Lasso-type regularization procedure. Twelve radiological features alone could reach an area under the ROC curve (AUC) of 0.84 in differentiating between malignant and benign lesions. The 10 selected characters improved the AUC to 0.91. The evaluation results showed that the method of selecting radiological and textural features appears to yield more effective in the distinction of malignant from benign solitary pulmonary nodules by computed tomography.
Radiological features; Textural features; Feature selection; Solitary pulmonary nodules; BP neural network
Efficient segmentation of tumors in medical images is of great practical importance in early diagnosis and radiation plan. This paper proposes a novel semi-automatic segmentation method based on population and individual statistical information to segment brain tumors in magnetic resonance (MR) images. First, high-dimensional image features are extracted. Neighborhood components analysis is proposed to learn two optimal distance metrics, which contain population and patient-specific information, respectively. The probability of each pixel belonging to the foreground (tumor) and the background is estimated by the k-nearest neighborhood classifier under the learned optimal distance metrics. A cost function for segmentation is constructed through these probabilities and is optimized using graph cuts. Finally, some morphological operations are performed to improve the achieved segmentation results. Our dataset consists of 137 brain MR images, including 68 for training and 69 for testing. The proposed method overcomes segmentation difficulties caused by the uneven gray level distribution of the tumors and even can get satisfactory results if the tumors have fuzzy edges. Experimental results demonstrate that the proposed method is robust to brain tumor segmentation.
Neighborhood components analysis; k-nearest neighborhood; Graph cuts; Distance metric learning