Computer-aided classification of mammographic masses using visually sensitive image features.

High false-positive recall rate is an important clinical issue that reduces efficacy of screening mammography. Aiming to help improve accuracy of classification between the benign and malignant breast masses and then reduce false-positive recalls, we developed and tested a new computer-aided diagnosis (CAD) scheme for mass classification using a database including 600 verified mass regions. The mass regions were segmented from regions of interest (ROIs) with a fixed size of 512×512 pixels. The mass regions were first segmented by an automated scheme, with manual corrections to the mass boundary performed if there was noticeable segmentation error. We randomly divided the 600 ROIs into 400 ROIs (200 malignant and 200 benign) for training, and 200 ROIs (100 malignant and 100 benign) for testing. We computed and analyzed 124 shape, texture, contrast, and spiculation based features in this study. Combining with previously computed 27 regional and shape based features for each of the ROIs in our database, we built an initial image feature pool. From this pool of 151 features, we extracted 13 features by applying the Sequential Forward Floating Selection algorithm on the ROIs in the training dataset. We then trained a multilayer perceptron model using these 13 features, and applied the trained model to the ROIs in the testing dataset. Receiver operating characteristic (ROC) analysis was used to evaluate classification accuracy. The area under the ROC curve was 0.8814±0.025 for the testing dataset. The results show a higher CAD mass classification performance, which needs to be validated further in a more comprehensive study.

Computer-vision techniques based on wavelets are presented with applications to computer-aided diagnosis (CAD) in medical images. CAD is a method for assisting radiologists’ interpretation of medical images. CAD schemes act as a second reader and alert radiologists to suspicious lesions. Development of CAD schemes is an active area of research, motivated by the fact that radiologists tend to misdiagnose cancerous lesions in medical images. In the past several years, we have been extensively developing wavelet-based techniques for CAD schemes. Development of these techniques has led to a new CAD scheme and has yielded significant improvements in the performance of the existing CAD schemes. This chapter describes two wavelet-based, low-level computer vision techniques: simultaneous segmentation and registration, and matching pursuit with optimally weighted wavelet packets. We present their application to the computer-aided detection of lung nodules in chest radiographs and microcalcifications in mammograms.

As the rapid advance of digital imaging technologies, the content-based image retrieval (CBIR) has became one of the most vivid research areas in computer vision. In the last several years, developing computer-aided detection and/or diagnosis (CAD) schemes that use CBIR to search for the clinically relevant and visually similar medical images (or regions) depicting suspicious lesions has also been attracting research interest. CBIR-based CAD schemes have potential to provide radiologists with "visual aid" and increase their confidence in accepting CAD-cued results in the decision making. The CAD performance and reliability depends on a number of factors including the optimization of lesion segmentation, feature selection, reference database size, computational efficiency, and relationship between the clinical relevance and visual similarity of the CAD results. By presenting and comparing a number of approaches commonly used in previous studies, this article identifies and discusses the optimal approaches in developing CBIR-based CAD schemes and assessing their performance. Although preliminary studies have suggested that using CBIR-based CAD schemes might improve radiologists' performance and/or increase their confidence in the decision making, this technology is still in the early development stage. Much research work is needed before the CBIR-based CAD schemes can be accepted in the clinical practice.

The purpose of this study was to evaluate the performance of a computer-aided diagnosis (CAD) system on the detection of pulmonary nodules in multidetector row computed tomography (MDCT) images by using two independent datasets. We collected CT cases of 63 patients with 132 nodules ranging 4–30 mm in diameter from a hospital in Spain (20 patients) and a hospital in France (43 patients). CT examinations were acquired by using a SOMATOM Emotion CT scanner in Spain, and a dual-source SOMATOM Definition CT scanner in France (Siemens Medical System, Forchheim, Germany), with the following parameters: 6 × 1.0 mm collimation, 130 kVp, 70 mA (Emotion 6); or 64 × 0.6 mm collimation, 100–120 kVp, and 100–110 mAs (Definition 64). Nodules were detected independently by three experienced chest radiologists, and their detection results were used as the reference standard. The CAD scheme was developed with an advanced 3D iris filter for improving nodule detection. The performance of the CAD scheme was tested with an independent evaluation method based on the two databases. Free-response receiver operating characteristic curves, sensitivity and number of false-positive per scan, were employed to evaluate the performance of the CAD scheme. The study was approved by the Institutional Review Board. At an average false positive (FP) rate of 5 per scan, our CAD scheme achieved sensitivities of 79.5% for all nodules, 80.3% for solid, 60.0% for non-solid, 58.1% for spiculated, and 86.1% for non-spiculated nodules. In conclusion, our CAD scheme could be utilized to help radiologists in the detection of lung nodules in CT. However, in this study we confirmed that significant differences could be found in the performance of the system depending on the testing database.

Since computer-aided diagnosis (CAD) schemes of medical images usually computes large number of image features, which creates a challenge of how to identify a small and optimal feature vector to build robust machine learning models, the objective of this study is to investigate feasibility of applying a random projection algorithm (RPA) to build an optimal feature vector from the initially CAD-generated large feature pool and improve performance of machine learning model. We assemble a retrospective dataset involving 1,487 cases of mammograms in which 644 cases have confirmed malignant mass lesions and 843 have benign lesions. A CAD scheme is first applied to segment mass regions and initially compute 181 features. Then, support vector machine (SVM) models embedded with several feature dimensionality reduction methods are built to predict likelihood of lesions being malignant. All SVM models are trained and tested using a leave-one-case-out cross-validation method. SVM generates a likelihood score of each segmented mass region depicting on one-view mammogram. By fusion of two scores of the same mass depicting on two-view mammograms, a case-based likelihood score is also evaluated. Comparing with the principle component analyses, nonnegative matrix factorization, and Chi-squared methods, SVM embedded with RPA yielded a significantly higher case-based lesion classification performance with the area under ROC curve of 0.84 ± 0.01 (p<0.02). The study demonstrates that RPA is a promising method to generate optimal feature vectors and improve SVM performance. This study presents a new method to develop CAD schemes with significantly higher and robust performance.

We have developed a novel method called local contralateral subtraction for reduction of false positives reported by a computer-aided diagnosis (CAD) scheme for detection of lung nodules in chest radiographs. Our method is based on the removal of normal structures in the regions of interest (ROIs), based on symmetry between the left and right lungs. In our method, two ROIs were extracted, one from the position where a candidate of a nodule is located, and the other from the anatomically corresponding location in the opposite lung, which contains similar normal structures. We employed a wavelet-based multiresolution image registration method to match the two ROIs, and subtraction was performed. A signal- to-noise ratio (SNR) between a central region and the adjacent background region was calculated for quantification of the remaining structures in the subtracted ROI. The SNR was then used for distinction between nodules and false positives. In an analysis of 550 ROIs consisting of 51 nodules and 499 false positives reported as detected nodules by our current CAD scheme, we were able to eliminate 44% of false positives with loss of only one nodule with this new method. This result indicates that our new method is effective in reducing false positives due to normal anatomic structures, and thus can improve the performance of our CAD scheme for detection of pulmonary nodules in chest radiographs.

To assess whether a computer-aided, diagnosis (CAD) system can predict pathological CompleteResponse (pCR) to neoadjuvant chemotherapy (NAC) prior to treatment using texture features. Response to treatment of 44 patients was defined according to the histopatology of resected tumour and extracted axillary nodes in two ways: (a) pCR+ (Smith's Grade = 5) vs pCR- (Smith's Grade<5); (b) pCRN+ (pCR+ and absence of residual lymph node metastases) vs pCRN - . A CAD system was developed to: (i) segment the breasts; (ii) register the DCE-MRI sequence; (iii) detect the lesion and (iv) extract 27 3D texture features. The role of individual texture features, multiparametric models and Bayesian classifiers in predicting patients' response to NAC were evaluated. A cross-validated Bayesian classifier fed with 6 features was able to predict pCR with a specificity of 72% and a sensitivity of 67%. Conversely, 2 features were used by the Bayesian classifier to predict pCRN, obtaining a sensitivity of 69% and a specificity of 61%. A CAD scheme, that extracts texture features from an automatically segmented 3D mask of the tumour, could predict pathological response to NAC. Additional research should be performed to validate these promising results on a larger cohort of patients and using different classification strategies. Advances in knowledge: This is the first study assessing the role of an automatic CAD system in predicting the pathological response to NAC before treatment. Fully automatic methods represent the backbone of standardized analysis and may help in timely managing patients candidate to NAC.

We have previously evaluated the effects of computer-aided diagnosis (CAD) on radiologists' characterization of malignant and benign breast masses in single-view serial mammograms. In this study, we conducted observer performance experiments with ROC methodology in which the radiologists read the serial mammograms in two-views (CC and MLO) without and with CAD. 47 temporal pairs of two-view serial mammograms (27 malignant and 20 benign) containing masses were chosen from 39 patient files and digitized. The corresponding masses on each temporal pair were analyzed by the CAD program. For this data set, the computer classifier achieved a test Az value of 0.90. Five MQSA radiologists assessed the two-view temporal pairs and provided estimates of the likelihood of malignancy without and then with CAD. For the five radiologists, the average Az was 0.81 (range: 0.72-0.88) without CAD and improved to 0.88 (range: 0.86-0.90) with CAD. The improvement was statistically significant (p=0.038). In comparison, the test Az value of the computer classifier for single view analysis was 0.87. The average Az of the radiologists for reading the single view temporal pairs without CAD was 0.78 (range: 0.73-0.83) and was improved significantly (p=0.002) to 0.84 (range: 0.77-0.88) with CAD. CAD using interval change analysis can significantly improve radiologists' accuracy in classification of masses. Classification based on information from two-views is more accurate than that based on single view for both the radiologists and the computer classifier. CAD can further improve radiologists' performance even in two-view reading.

Developing a computer-aided diagnosis (CAD) scheme to classify between malignant and benign breast lesions can play an important role in improving MRI screening efficacy. This study demonstrates that extracting features from both spatial and frequency domains, and applying an efficient combination of data reduction and classifier methods, had the potential to significantly improve accuracy in classifying between malignant and benign breast masses. By applying our CAD scheme to the testing dataset, we obtained an accuracy of 83.1% for the best combination of data reduction and classification (DNE-SVM).

Although the computer-aided diagnosis (CAD) system can be applied for classifying the breast masses, the effects of this method on improvement of the radiologist' accuracy for distinguishing malignant from benign lesions still remain unclear. This study provided a novel method to classify breast masses by integrating the intelligence of human and machine. In this research, 224 breast masses were selected in mammography from database of DDSM with Breast Imaging Reporting and Data System (BI-RADS) categories. Three observers (a senior and a junior radiologist, as well as a radiology resident) were employed to independently read and classify these masses utilizing the Positive Predictive Values (PPV) for each BI-RADS category. Meanwhile, a CAD system was also implemented for classification of these breast masses between malignant and benign. To combine the decisions from the radiologists and CAD, the fusion method of the Multi-Agent was provided. Significant improvements are observed for the fusion system over solely radiologist or CAD. The area under the receiver operating characteristic curve (AUC) of the fusion system increased by 9.6%, 10.3% and 21% compared to that of radiologists with senior, junior and resident level, respectively. In addition, the AUC of this method based on the fusion of each radiologist and CAD are 3.5%, 3.6% and 3.3% higher than that of CAD alone. Finally, the fusion of the three radiologists with CAD achieved AUC value of 0.957, which was 5.6% larger compared to CAD. Our results indicated that the proposed fusion method has better performance than radiologist or CAD alone.

We conducted an observer performance study using receiver operating characteristic (ROC) methodology to evaluate the effects of computer-aided diagnosis (CAD) on radiologists' performance for characterization of masses on serial mammograms. The automated CAD system, previously developed in our laboratory, can classify masses as malignant or benign based on interval change information on serial mammograms. In this study, 126 temporal image pairs (73 malignant and 53 benign) from 52 patients containing masses on serial mammograms were used. The corresponding masses on each temporal pair were identified by an experienced radiologist and automatically segmented by the CAD program. Morphological, texture, and spiculation features of the mass on the current and the prior mammograms were extracted. The individual features and the difference between the corresponding current and prior features formed a multidimensional feature space. A subset of the most effective features that contained the current, prior, and interval change information was selected by a stepwise procedure and used as input predictor variables to a linear discriminant classifier in a leave-one-case-out training and testing resampling scheme. The linear discriminant classifier estimated the relative likelihood of malignancy of each mass. The classifier achieved a test Az value of 0.87. For the ROC study, 4 MQSA radiologists and 1 breast imaging fellow assessed the masses on the temporal pairs and provided estimates of the likelihood of malignancy without and with CAD. The average A_z value for the likelihood of malignancy estimated by the radiologists was 0.79 without CAD and improved to 0.87 with CAD. The improvement was statistically significant (p=0.0003). This preliminary result indicated that CAD using interval change analysis can significantly improve radiologists' accuracy in classification of masses and thereby may increase the positive predictive value of mammography.

Objectives: This study aimed to evaluate the role of MRI in differentiation between benign and malignant well-circumscribed breast masses.&#x0D; Methods: A prospective cross-sectional study conducted on selected female patients with Breast mass who their age older than 35 years. All patients underwent examination using 1.5 Tesla magnetic resonance unit (MAGNETOM AERA, SIMENS).&#x0D; Results: 30 female patients were selected (mean age of 44.2±9.2 years, range between 35-69). Final findings of MRI revealed that 6 (20%) women had malignant breast mass while 24 (80%) women had benign breast mass. The histopathology revealed that 4 (13.3%) women were having malignancy while 26 (86.6%) were having benign breast tumor. There was a highly significant association between malignancy and hyperdense mammography findings of women (p&lt;0.001), multiple lymph nodes for women (p&lt;0.001), increased size of mass by MRI (p&lt;0.001), circumscribed macrolabular lesion on MRI, rapid early kinetic phase of enhanced MRI (p&lt;0.001), washout late kinetic phase enhanced MRI (p&lt;0.001), and MRI kinetic curve type 3(p&lt;0.001). There was a highly significant association between homogenous enhanced MRI findings of women and benign lesions (p&lt;0.001).&#x0D; Conclusion: The validity results of MRI in differentiation between benign and malignant circumscribed breast masses are high, except for positive predictive value, and application of kinetic curve dynamic contrast enhancement increases magnetic resonance in differentiation between benign and malignant circumscribed breast masses.

We retrospectively evaluated the usefulness of computer-aided diagnosis (CAD) schemes to radiologist performance in the simultaneous detection of vertebral fractures and lung nodules on chest radiographs. We evaluated posteroanterior and lateral chest images of 21 patients with vertebral fractures, 31 patients with lung nodules, and 10 persons acting as controls. The total number of subjects was 60 because both lesions were present in four patients. Eighteen radiologists were asked to detect vertebral fractures and nodules simultaneously on posteroanterior and lateral images. The radiologists indicated their confidence level ratings regarding the presence or absence of lesions and the most likely location of each lesion on either posteroanterior or lateral images, first without and then with CAD output. The observers' performance was evaluated with use of receiver operating characteristic (ROC) and jackknife free-response ROC curves. With the CAD scheme, the average area under the ROC curve for detection of vertebral fractures improved from 0.906 to 0.951 (p = 0.002). That for lung nodules also improved, but the improvement was not statistically significant (0.804-0.816, p = 0.297). The figure-of-merit values obtained with the jackknife free-response ROC program improved from 0.585 to 0.680 (p < 0.001) for vertebral fractures and from 0.622 to 0.650 (p = 0.017) for nodules, both results having statistical significance. Average sensitivity in the detection of lesions improved from 59.8% to 69.3% for vertebral fractures and from 64.9% to 67.6% for nodules. In the detection of vertebral fractures and lung nodules on chest images, diagnostic accuracy among radiologists improves with the use of CAD.

We are investigating the use of special mammographic views, i.e. magnification and spot compression views, into computerized classification schemes for malignant versus benign microcalcification clusters. Radiologists often recall patients with suspicious lesions for additional views. We expect that the fusion, or combination, of information extracted from special views and conventional mammograms will improve the performances of computer-aided diagnosis (CAD) schemes for classification of malignant versus benign microcalcification clusters. It has been shown that reading with CAD improves radiologists' performances. The CAD scheme is applied separately to conventional mammograms and special views. The scheme consists of segmentation of manually-identified microcalcifications, followed by extraction of microcalcification-based geometrical and textural features in addition to cluster-based features. Linear discriminant analysis (LDA) is then applied to each image to classify a cluster as malignant or benign. The leave-one-out technique is used for training and testing the classifier. The resulting likelihoods of malignancy output from the LDA applied separately to the conventional mammograms and special views are combined using the maximum classifier output. We applied the proposed technique to a database of 75 biopsy-proven patients (31 malignant and 44 benign). The case-based performances for classification of malignant versus benign microcalcification clusters resulted in an area under the receiver operating characteristic (ROC) curves, Az, of: 0.771 on conventional mammograms, 0.845 on special views, and 0.908 when merging likelihoods of malignancy from conventional mammograms and special views. These preliminary results indicate that the proposed technique of combining information from special views with that from conventional mammograms can improve computerized classification of microcalcification clusters.

To evaluate the effects of computer-aided diagnosis (CAD) on radiologists' characterization of masses on serial mammograms. Two hundred fifty-three temporal image pairs (138 malignant and 115 benign) obtained from 96 patients who had masses on serial mammograms were evaluated. The temporal pairs were formed by matching masses of the same view from two different examinations. Eight radiologists and two breast imaging fellows assessed the temporal pairs with and without computer aid. The classification of accuracy was quantified by using the area under receiver operating characteristic curve (A(z)). The statistical significance of the difference in A(z) between the different reading conditions was estimated with the Dorfman-Berbaum-Metz method for analysis of multireader multicase data and with the Student paired t test for analysis of observer-specific paired data. The average A(z) for radiologists' estimates of the likelihood of malignancy was 0.79 without CAD and improved to 0.84 with CAD. The improvement was statistically significant (P =.005). The corresponding average partial area index was 0.25 without CAD and improved to 0.37 with CAD. The improvement was also statistically significant (P =.005). On the basis of Breast Imaging Reporting and Data System assessments, it was estimated that with CAD, each radiologist, on average, reduced 0.7% (0.8 of 115) of unnecessary biopsies and correctly recommended 5.7% (7.8 of 138) of additional biopsies. CAD based on analysis of interval changes can significantly increase radiologists' accuracy in classification of masses and thereby may be useful in improving correct biopsy recommendations.