Computerized characterization of breast masses on three-dimensional ultrasound volumes

Evaluation of efficacy of artificial intelligence in orthopantomogram in detecting and classifying radiolucent lesions

Aim and Objective

The objective of our study was to build a convolutional neural network (CNN) model and detection and classification of benign and malignant radiolucent lesions in orthopantomogram (OPG) by implementing CNN.

Method

Two basic CNN models were implemented on Anaconda with Python 3 on 64-bit, CNN-I for detection of radiolucency and CNN-II for classification of radiolucency into benign and malignant lesions. One hundred fifty eight OPG with radiolucency and 115 OPG without radiolucency was used for training and validation of CNN models. Data augmentation was performed for the training and validation dataset. The evaluation of the performance of both CNN by new data consisting (60 OPG images) 30 benign and 30 malignant lesions.

Statistical Analysis

Performed using SPSS (Statistical package for social science) 20.0 version. The descriptive statistics was performed. The Cohen kappa correlation coefficient was used for assessment of reliability of the diagnostic methods. P < .05 was considered statistically significant. Determination of sensitivity, specificity, positive and negative predictive value was also performed.

Result

CNN-I showing sensitivity for detection of the benign lesion is 76.6% and sensitivity for the malignant lesion is 63.3% with overall sensitivity is 70%. CNN-II showing sensitivity for classification of the benign lesion is 70% and for classification of the malignant lesion is 63.3% with overall classification sensitivity is 66.6%. The kappa correlation coefficient value for diagnosis made by CNN-II is 0.333 and P < .05.

Conclusion

Both CNN showed statistically significant and satisfactory results in detecting and classifying radiolucency in OPG.

Impact of Original and Artificially Improved Artificial Intelligence-based Computer-aided Diagnosis on Breast US Interpretation

OBJECTIVE

For breast US interpretation, to assess impact of computer-aided diagnosis (CADx) in original mode or with improved sensitivity or specificity.

METHODS

In this IRB approved protocol, orthogonal-paired US images of 319 lesions identified on screening, including 88 (27.6%) cancers (median 7 mm, range 1-34 mm), were reviewed by 9 breast imaging radiologists. Each observer provided BI-RADS assessments (2, 3, 4A, 4B, 4C, 5) before and after CADx in a mode-balanced design: mode 1, original CADx (outputs benign, probably benign, suspicious, or malignant); mode 2, artificially-high-sensitivity CADx (benign or malignant); and mode 3, artificially-high-specificity CADx (benign or malignant). Area under the receiver operating characteristic curve (AUC) was estimated under each modality and for standalone CADx outputs. Multi-reader analysis accounted for inter-reader variability and correlation between same-lesion assessments.

RESULTS

AUC of standalone CADx was 0.77 (95% CI: 0.72-0.83). For mode 1, average reader AUC was 0.82 (range 0.76-0.84) without CADx and not significantly changed with CADx. In high-sensitivity mode, all observers' AUCs increased: average AUC 0.83 (range 0.78-0.86) before CADx increased to 0.88 (range 0.84-0.90), P < 0.001. In high-specificity mode, all observers' AUCs increased: average AUC 0.82 (range 0.76-0.84) before CADx increased to 0.89 (range 0.87-0.92), P < 0.0001. Radiologists responded more frequently to malignant CADx cues in high-specificity mode (42.7% vs 23.2% mode 1, and 27.0% mode 2, P = 0.008).

CONCLUSION

Original CADx did not substantially impact radiologists' interpretations. Radiologists showed improved performance and were more responsive when CADx produced fewer false-positive malignant cues.

Towards clinical application of image mining: a systematic review on artificial intelligence and radiomics

PURPOSE

The aim of this systematic review was to analyse literature on artificial intelligence (AI) and radiomics, including all medical imaging modalities, for oncological and non-oncological applications, in order to assess how far the image mining research stands from routine medical application. To do this, we applied a trial phases classification inspired from the drug development process.

METHODS

Among the articles we considered for inclusion from PubMed were multimodality AI and radiomics investigations, with a validation analysis aimed at relevant clinical objectives. Quality assessment of selected papers was performed according to the QUADAS-2 criteria. We developed the phases classification criteria for image mining studies.

RESULTS

Overall 34,626 articles were retrieved, 300 were selected applying the inclusion/exclusion criteria, and 171 high-quality papers (QUADAS-2 ≥ 7) were identified and analysed. In 27/171 (16%), 141/171 (82%), and 3/171 (2%) studies the development of an AI-based algorithm, radiomics model, and a combined radiomics/AI approach, respectively, was described. A total of 26/27(96%) and 1/27 (4%) AI studies were classified as phase II and III, respectively. Consequently, 13/141 (9%), 10/141 (7%), 111/141 (79%), and 7/141 (5%) radiomics studies were classified as phase 0, I, II, and III, respectively. All three radiomics/AI studies were categorised as phase II trials.

CONCLUSIONS

The results of the studies are promising but still not mature enough for image mining tools to be implemented in the clinical setting and be widely used. The transfer learning from the well-known drug development process, with some specific adaptations to the image mining discipline could represent the most effective way for radiomics and AI algorithms to become the standard of care tools.

Breast ultrasound lesions recognition: end-to-end deep learning approaches

Multistage processing of automated breast ultrasound lesions recognition is dependent on the performance of prior stages. To improve the current state of the art, we propose the use of end-to-end deep learning approaches using fully convolutional networks (FCNs), namely FCN-AlexNet, FCN-32s, FCN-16s, and FCN-8s for semantic segmentation of breast lesions. We use pretrained models based on ImageNet and transfer learning to overcome the issue of data deficiency. We evaluate our results on two datasets, which consist of a total of 113 malignant and 356 benign lesions. To assess the performance, we conduct fivefold cross validation using the following split: 70% for training data, 10% for validation data, and 20% testing data. The results showed that our proposed method performed better on benign lesions, with a top "mean Dice" score of 0.7626 with FCN-16s, when compared with the malignant lesions with a top mean Dice score of 0.5484 with FCN-8s. When considering the number of images with Dice score > 0.5 , 89.6% of the benign lesions were successfully segmented and correctly recognised, whereas 60.6% of the malignant lesions were successfully segmented and correctly recognized. We conclude the paper by addressing the future challenges of the work.

Automated 3D ultrasound image segmentation to aid breast cancer image interpretation

Segmentation of an ultrasound image into functional tissues is of great importance to clinical diagnosis of breast cancer. However, many studies are found to segment only the mass of interest and not all major tissues. Differences and inconsistencies in ultrasound interpretation call for an automated segmentation method to make results operator-independent. Furthermore, manual segmentation of entire three-dimensional (3D) ultrasound volumes is time-consuming, resource-intensive, and clinically impractical. Here, we propose an automated algorithm to segment 3D ultrasound volumes into three major tissue types: cyst/mass, fatty tissue, and fibro-glandular tissue. To test its efficacy and consistency, the proposed automated method was employed on a database of 21 cases of whole breast ultrasound. Experimental results show that our proposed method not only distinguishes fat and non-fat tissues correctly, but performs well in classifying cyst/mass. Comparison of density assessment between the automated method and manual segmentation demonstrates good consistency with an accuracy of 85.7%. Quantitative comparison of corresponding tissue volumes, which uses overlap ratio, gives an average similarity of 74.54%, consistent with values seen in MRI brain segmentations. Thus, our proposed method exhibits great potential as an automated approach to segment 3D whole breast ultrasound volumes into functionally distinct tissues that may help to correct ultrasound speed of sound aberrations and assist in density based prognosis of breast cancer.

Going beyond a First Reader: A Machine Learning Methodology for Optimizing Cost and Performance in Breast Ultrasound Diagnosis

The goal of this study was to devise a machine learning methodology as a viable low-cost alternative to a second reader to help augment physicians' interpretations of breast ultrasound images in differentiating benign and malignant masses. Two independent feature sets consisting of visual features based on a radiologist's interpretation of images and computer-extracted features when used as first and second readers and combined by adaptive boosting (AdaBoost) and a pruning classifier resulted in a very high level of diagnostic performance (area under the receiver operating characteristic curve = 0.98) at a cost of pruning a fraction (20%) of the cases for further evaluation by independent methods. AdaBoost also improved the diagnostic performance of the individual human observers and increased the agreement between their analyses. Pairing AdaBoost with selective pruning is a principled methodology for achieving high diagnostic performance without the added cost of an additional reader for differentiating solid breast masses by ultrasound.

Computer-aided assessment of tumor grade for breast cancer in ultrasound images

This study involved developing a computer-aided diagnosis (CAD) system for discriminating the grades of breast cancer tumors in ultrasound (US) images. Histological tumor grades of breast cancer lesions are standard prognostic indicators. Tumor grade information enables physicians to determine appropriate treatments for their patients. US imaging is a noninvasive approach to breast cancer examination. In this study, 148 3-dimensional US images of malignant breast tumors were obtained. Textural, morphological, ellipsoid fitting, and posterior acoustic features were quantified to characterize the tumor masses. A support vector machine was developed to classify breast tumor grades as either low or high. The proposed CAD system achieved an accuracy of 85.14% (126/148), a sensitivity of 79.31% (23/29), a specificity of 86.55% (103/119), and an A_Z of 0.7940.

Quantification of heterogeneity as a biomarker in tumor imaging: a systematic review

BACKGROUND

Many techniques are proposed for the quantification of tumor heterogeneity as an imaging biomarker for differentiation between tumor types, tumor grading, response monitoring and outcome prediction. However, in clinical practice these methods are barely used. This study evaluates the reported performance of the described methods and identifies barriers to their implementation in clinical practice.

METHODOLOGY

The Ovid, Embase, and Cochrane Central databases were searched up to 20 September 2013. Heterogeneity analysis methods were classified into four categories, i.e., non-spatial methods (NSM), spatial grey level methods (SGLM), fractal analysis (FA) methods, and filters and transforms (F&T). The performance of the different methods was compared.

PRINCIPAL FINDINGS

Of the 7351 potentially relevant publications, 209 were included. Of these studies, 58% reported the use of NSM, 49% SGLM, 10% FA, and 28% F&T. Differentiation between tumor types, tumor grading and/or outcome prediction was the goal in 87% of the studies. Overall, the reported area under the curve (AUC) ranged from 0.5 to 1 (median 0.87). No relation was found between the performance and the quantification methods used, or between the performance and the imaging modality. A negative correlation was found between the tumor-feature ratio and the AUC, which is presumably caused by overfitting in small datasets. Cross-validation was reported in 63% of the classification studies. Retrospective analyses were conducted in 57% of the studies without a clear description.

CONCLUSIONS

In a research setting, heterogeneity quantification methods can differentiate between tumor types, grade tumors, and predict outcome and monitor treatment effects. To translate these methods to clinical practice, more prospective studies are required that use external datasets for validation: these datasets should be made available to the community to facilitate the development of new and improved methods.

Cancer prediction based on radical basis function neural network with particle swarm optimization

This paper addresses cancer prediction based on radial basis function neural network optimized by particle swarm optimization. Today, cancer hazard to people is increasing, and it is often difficult to cure cancer. The occurrence of cancer can be predicted by the method of the computer so that people can take timely and effective measures to prevent the occurrence of cancer. In this paper, the occurrence of cancer is predicted by the means of Radial Basis Function Neural Network Optimized by Particle Swarm Optimization. The neural network parameters to be optimized include the weight vector between network hidden layer and output layer, and the threshold of output layer neurons. The experimental data were obtained from the Wisconsin breast cancer database. A total of 12 experiments were done by setting 12 different sets of experimental result reliability. The findings show that the method can improve the accuracy, reliability and stability of cancer prediction greatly and effectively.

Evaluating lesion segmentation on breast sonography as related to lesion type

Breast sonography currently provides a complementary diagnosis when other modalities are not conclusive. However, lesion segmentation on sonography is still a challenging problem due to the presence of artifacts. To solve these problems, Markov random fields and maximum a posteriori-based methods are used to estimate a distortion field while identifying regions of similar intensity inhomogeneity. In this study, different initialization approaches were exhaustively evaluated using a database of 212 B-mode breast sonograms and considering the lesion types. Finally, conclusions about the relationship between the segmentation results and lesions types are described.

A similarity study of content-based image retrieval system for breast cancer using decision tree

PURPOSE

We are developing a decision tree content-based image retrieval (DTCBIR) CADx system to assist radiologists in characterization of breast masses on ultrasound images.

METHODS

Three DTCBIR configurations, including decision tree with boosting (DTb), decision tree with full leaf features (DTL), and decision tree with selected leaf features (DTLs) were compared. For DTb, features of a query mass were combined first into a merged feature score and then masses with similar scores were retrieved. For DTL and DTLs, similar masses were retrieved based on the Euclidean distance between feature vectors of the query and those of selected references. For each DTCBIR configuration, we investigated the use of full feature set and subset of features selected by the stepwise linear discriminant analysis (LDA) and simplex optimization method, resulting in six retrieval methods and selected five, DTb-lda, DTL-lda, DTb-full, DTL-full, and DTLs-full, for the observer study. Three MQSA radiologists rated similarities between the query mass and computer-retrieved three most similar masses using nine-point similarity scale (9 = very similar).

RESULTS

For DTb-lda, DTL-lda, DTb-full, DTL-full, and DTLs-full, average A(z) values were 0.90 ± 0.03, 0.85 ± 0.04, 0.87 ± 0.04, 0.79 ± 0.05, and 0.71 ± 0.06, respectively, and average similarity ratings were 5.00, 5.41, 4.96, 5.33, and 5.13, respectively.

CONCLUSIONS

The DTL-lda is a promising DTCBIR CADx configuration which had simple tree structure, good classification performance, and highest similarity rating.

Computer-aided lesion diagnosis in automated 3-D breast ultrasound using coronal spiculation

A computer-aided diagnosis (CAD) system for the classification of lesions as malignant or benign in automated 3-D breast ultrasound (ABUS) images, is presented. Lesions are automatically segmented when a seed point is provided, using dynamic programming in combination with a spiral scanning technique. A novel aspect of ABUS imaging is the presence of spiculation patterns in coronal planes perpendicular to the transducer. Spiculation patterns are characteristic for malignant lesions. Therefore, we compute spiculation features and combine them with features related to echotexture, echogenicity, shape, posterior acoustic behavior and margins. Classification experiments were performed using a support vector machine classifier and evaluation was done with leave-one-patient-out cross-validation. Receiver operator characteristic (ROC) analysis was used to determine performance of the system on a dataset of 201 lesions. We found that spiculation was among the most discriminative features. Using all features, the area under the ROC curve (A(z)) was 0.93, which was significantly higher than the performance without spiculation features (A(z)=0.90, p=0.02). On a subset of 88 cases, classification performance of CAD (A(z)=0.90) was comparable to the average performance of 10 readers (A(z)=0.87).

Similarity evaluation in a content-based image retrieval (CBIR) CADx system for characterization of breast masses on ultrasound images

PURPOSE

The authors are developing a content-based image retrieval (CBIR) CADx system to assist radiologists in characterization of breast masses on ultrasound images. In this study, the authors compared seven similarity measures to be considered for the CBIR system. The similarity between the query and the retrieved masses was evaluated based on radiologists' visual similarity assessments.

METHODS

The CADx system retrieves masses that are similar to a query mass from a reference library based on computer-extracted features using a k-nearest neighbor (k-NN) approach. Among seven similarity measures evaluated for the CBIR system, four similarity measures including linear discriminant analysis (LDA), Bayesian neural network (BNN), cosine similarity measure (Cos), and Euclidean distance (ED) similarity measure were compared by radiologists' visual assessment. For LDA and BNN, the features of a query mass were combined first into a malignancy score and then masses with similar scores were retrieved. For Cos and ED, similar masses were retrieved based on the normalized dot product and the Euclidean distance, respectively, between two feature vectors. For the observer study, three most similar masses were retrieved for a given query mass with each method. All query-retrieved mass pairs were mixed and presented to the radiologists in random order. Three Mammography Quality Standards Act (MQSA) radiologists rated the similarity between each pair using a nine-point similarity scale (1 = very dissimilar, 9 = very similar). The accuracy of the CBIR CADx system using the different similarity measures to characterize malignant and benign masses was evaluated by ROC analysis.

RESULTS

The BNN measure used with the k-NN classifier provided slightly higher performance for classification of malignant and benign masses (A(z) values of 0.87) than those with the LDA, Cos, and ED measures (A(z) of 0.86, 0.84, and 0.81, respectively). The average similarity ratings of all radiologists for LDA, BNN, Cos, and ED were 4.71, 4.95, 5.18, and 5.32, respectively. The k-NN with the ED measures retrieved masses of significantly higher similarity (p < 0.008) than LDA and BNN.

CONCLUSIONS

Similarity measures using the resemblance of individual features in the multidimensional feature space can retrieve visually more similar masses than similarity measures using the resemblance of the classifier scores. A CBIR system that can most effectively retrieve similar masses to the query may not have the best A(z).

Three-dimensional ultrasonography for breast malignancy detection

INTRODUCTION

Breast ultrasound is used not only to differentiate a solid breast mass from a cyst and to assist in guided biopsy, but also to classify benign and malignant lesions, with good resolution gray-scale imaging equipped with color Doppler adequate for daily clinical practice in most circumstances.

AREAS COVERED

This article critically reviews three-dimensional (3D) ultrasound for the detection of breast malignancies in comparison with the popular two-dimensional ultrasound, highlighting the advantages it has over other imaging modalities as well as the drawbacks that are presented. In particular, the article looks at how 3D ultrasound planes help us to define more clearly the margins, that is, microlobulation and papillomas, of breast tumors. This paper also highlights how the resolution and multiple planes of 3D ultrasound can clearly demonstrate skin tumor infiltration for evaluation and how it can be used for planning, monitoring and treatment of breast cancer.

EXPERT OPINION

As with any new technology, 3D ultrasound has a learning curve and clinicians will need to master the technology in order to use this tool to its full potential. Although 3D ultrasound does have its limitations, a better understanding of its settings along with the optimization of image acquisition and a better ability to manipulate data during analysis will lead to 3D ultrasound becoming a useful tool for breast malignancy detection.

Multimodality computer-aided breast cancer diagnosis with FFDM and DCE-MRI

RATIONALE AND OBJECTIVES

To investigate a multimodality computer-aided diagnosis (CAD) scheme that combines image information from full-field digital mammography (FFDM) and dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) for computerized breast cancer classification.

MATERIALS AND METHODS

From a retrospective FFDM database with 432 lesions (255 malignant, 177 benign) and a retrospective DCE-MRI database including 476 lesions (347 malignant, 129 benign), we constructed a multimodality dataset of 213 lesions (168 malignant, 45 benign). Each lesion was present on both FFDM and DCE-MRI images and deemed to be a difficult case given the necessity of having both clinical imaging exams. Using a manually indicated lesion location (ie, a seed point on FFDM images or a region of interest on DCE-MRI images, the computer automatically segmented the mass lesions and extracted lesion features). A subset of features was selected using linear stepwise feature selection and merged by a Bayesian artificial neural network to yield an estimate of the probability of malignancy. Receiver operating characteristic (ROC) analysis was used to evaluate the performance of the selected features in distinguishing between malignant and benign lesions.

RESULTS

With leave-one-lesion-out cross-validation on the multimodality dataset, the mammography-only features yielded an area under the ROC curve (AUC) of 0.74 +/- 0.04, and the DCE-MRI-only features yielded an AUC of 0.78 +/- 0.04. The combination of these two modalities, which included a spiculation feature from mammography and two kinetic features from DCE-MRI, yielded an AUC of 0.87 +/- 0.03. The improvement of combining multimodality information was statistically significant as compared to the use of single modality information alone.

CONCLUSIONS

A CAD scheme that combines features extracted from FFDM and DCE-MRI images may be advantageous to single-modality CAD in the task of differentiating between malignant and benign lesions.

Rapid image stitching and computer-aided detection for multipass automated breast ultrasound

PURPOSE

Breast ultrasound (US) is recently becoming more and more popular for detecting breast lesions. However, screening results in hundreds of US images for each subject. This magnitude of images can lead to fatigue in radiologist, causing failure in the detection of lesions of a subtle nature. In this study, an image stitching technique is proposed for combining multipass images of the whole breast into a series of full-view images, and a fully automatic screening system that works off these images is also presented.

METHODS

Using the registration technique based on the simple sum of absolute block-mean difference (SBMD) measure, three-pass images were merged into full-view US images. An automatic screening system was then developed for detecting tumors from these full-view images. The preprocessing step was used to reduce the tumor detection time of the system and to improve image quality. The gray-level slicing method was then used to divide images into numerous regions. Finally, seven computerized features--darkness, uniformity, width-height ratio, area size, nonpersistence, coronal area size, and region continuity--were defined and used to determine whether or not each region was a part of a tumor.

RESULTS

In the experiment, there was a total of 25 experimental cases with 26 lesions, and each case was composed of 252 images (three passes, 84 images/pass). The processing time of the proposed stitching procedure for each case was within 30 s with a Pentium IV 2.0 processor, and the detection sensitivity of the proposed CAD system was 92.3% with 1.76 false positives per case.

CONCLUSIONS

The proposed automatic screening system can be applied to the whole breast images stitched together via SBMD-based registration in order to detect tumors.

Computer-aided diagnostic models in breast cancer screening

Mammography is the most common modality for breast cancer detection and diagnosis and is often complemented by ultrasound and MRI. However, similarities between early signs of breast cancer and normal structures in these images make detection and diagnosis of breast cancer a difficult task. To aid physicians in detection and diagnosis, computer-aided detection and computer-aided diagnostic (CADx) models have been proposed. A large number of studies have been published for both computer-aided detection and CADx models in the last 20 years. The purpose of this article is to provide a comprehensive survey of the CADx models that have been proposed to aid in mammography, ultrasound and MRI interpretation. We summarize the noteworthy studies according to the screening modality they consider and describe the type of computer model, input data size, feature selection method, input feature type, reference standard and performance measures for each study. We also list the limitations of the existing CADx models and provide several possible future research directions.

Computer-aided diagnosis of soft-tissue tumors using sonographic morphologic and texture features

RATIONALE AND OBJECTIVES

The aim of this study was to develop a computer-aided diagnosis (CAD) system in assessing the sonographic morphologic and texture features of soft-tissue tumors.

MATERIALS AND METHODS

The retrospective study involved 114 pathology proven cases including 73 benign and 41 malignant soft-tissue tumors. The tumor regions were delineated by an experienced radiologist who was unknown to the pathologic result. Then, we applied 10 morphologic features and 6 gray-level co-occurrence matrix texture features to analyze the tumor regions. To classify the tumors as benign or malignant, we used two methods, a linear discriminant analysis with stepwise feature selection and a multilayer neural network with the back-propagation algorithm as classifiers. The classification performances are evaluated by the area A(z) under the receiver operating characteristic. Furthermore, four radiologists provided malignancy grades for all tumors in the comparison of the CAD system.

RESULTS

In this analysis, the CAD system based on the combination of morphologic and texture feature sets can give the optimal CAD result by LDA with an accuracy of 89.5%, a sensitivity of 90.2%, a specificity of 89.0%, a positive predictive value (PPV) of 82.2%, negative predictive value (NPV) of 94.2%, and A(z) value of 0.96, and by the multilayer perception with an accuracy of 88.6%, a sensitivity of 90.2%, a specificity of 87.5%, a positive predictive value of 80.4%, negative predictive value of 94.2%, and A(z) value of 0.95. The A(z) values of the four radiologists were ranged between 0.74 and 0.86, and the optimal CAD results were shown the highest A(z) values than the four radiologists' rankings.

CONCLUSIONS

This study has shown that performing the CAD system with both morphologic and texture features on sonography, can successfully distinguish between benign and malignant soft-tissue tumors. Moreover, it can also provide a second opinion for the tumor diagnosis and avert unnecessary biopsy.

A new automated method for the segmentation and characterization of breast masses on ultrasound images

Segmentation is one of the first steps in most computer-aided diagnosis systems for characterization of masses as malignant or benign. In this study, the authors designed an automated method for segmentation of breast masses on ultrasound (US) images. The method automatically estimated an initial contour based on a manually identified point approximately at the mass center. A two-stage active contour method iteratively refined the initial contour and performed self-examination and correction on the segmentation result. To evaluate the method, the authors compared it with manual segmentation by two experienced radiologists (R1 and R2) on a data set of 488 US images from 250 biopsy-proven masses (100 malignant and 150 benign). Two area overlap ratios (AOR1 and AOR2) and an area error measure were used as performance measures to evaluate the segmentation accuracy. Values for AOR1, defined as the ratio of the intersection of the computer and the reference segmented areas to the reference segmented area, were 0.82 +/- 0.16 and 0.84 +/- 0.18, respectively, when manually segmented mass regions by R1 and R2 were used as the reference. Although this indicated a high agreement between the computer and manual segmentations, the two radiologists' manual segmentation results were significantly (p < 0.03) more consistent, with AOR1 = 0.84 +/- 0.16 and 0.91 +/- 0.12, respectively, when the segmented regions by R1 and R2 were used as the reference. To evaluate the segmentation method in terms of lesion classification accuracy, feature spaces were formed by extracting texture, width-to-height, and posterior shadowing features based on either automated computer segmentation or the radiologists' manual segmentation. A linear discriminant analysis classifier was designed using stepwise feature selection and two-fold cross validation to characterize the mass as malignant or benign. For features extracted from computer segmentation, the case-based test A(z) values ranged from 0.88 +/- 0.03 to 0.92 +/- 0.02, indicating a comparable performance to those extracted from manual segmentation by radiologists (A(z) value range: 0.87 +/- 0.03 to 0.90 +/- 0.03).

Multi-modality CADx: ROC study of the effect on radiologists' accuracy in characterizing breast masses on mammograms and 3D ultrasound images

RATIONALE AND OBJECTIVES

To investigate the effect of a computer-aided diagnosis (CADx) system on radiologists' performance in discriminating malignant and benign masses on mammograms and three-dimensional (3D) ultrasound (US) images.

MATERIALS AND METHODS

Our dataset contained mammograms and 3D US volumes from 67 women (median age, 51; range: 27-86) with 67 biopsy-proven breast masses (32 benign and 35 malignant). A CADx system was designed to automatically delineate the mass boundaries on mammograms and the US volumes, extract features, and merge the extracted features into a multi-modality malignancy score. Ten experienced readers (subspecialty academic breast imaging radiologists) first viewed the mammograms alone, and provided likelihood of malignancy (LM) ratings and Breast Imaging and Reporting System assessments. Subsequently, the reader viewed the US images with the mammograms, and provided LM and action category ratings. Finally, the CADx score was shown and the reader had the opportunity to revise the ratings. The LM ratings were analyzed using receiver-operating characteristic (ROC) methodology, and the action category ratings were used to determine the sensitivity and specificity of cancer diagnosis.

RESULTS

Without CADx, readers' average area under the ROC curve, A(z), was 0.93 (range, 0.86-0.96) for combined assessment of the mass on both the US volume and mammograms. With CADx, their average A(z) increased to 0.95 (range, 0.91-0.98), which was borderline significant (P = .05). The average sensitivity of the readers increased from 98% to 99% with CADx, while the average specificity increased from 27% to 29%. The change in sensitivity with CADx did not achieve statistical significance for the individual radiologists, and the change in specificity was statistically significant for one of the radiologists.

CONCLUSIONS

A well-trained CADx system that combines features extracted from mammograms and US images may have the potential to improve radiologists' performance in distinguishing malignant from benign breast masses and making decisions about biopsies.

A comparison of linear and mixture models for discriminant analysis under nonnormality

Methods for discriminant analysis were compared with respect to classification accuracy under nonnormality through Monte Carlo simulation. The methods compared were linear discriminant analyses based both on raw scores and on ranks; linear logistic discrimination; and mixture discriminant analysis. Linear discriminant analysis and linear logistic discrimination were suboptimal in a number of scenarios with skewed predictors. Linear discriminant analysis based on ranks yielded the highest rates of classification accuracy in only a limited number of situations and did not produce a practically important advantage over competing methods. Mixture discriminant analysis, with a relatively small number of components in each group, attained relatively high rates of classification accuracy and was most useful for conditions in which skewed predictors had relatively small values of kurtosis.

Anniversary paper: History and status of CAD and quantitative image analysis: the role of Medical Physics and AAPM

The roles of physicists in medical imaging have expanded over the years, from the study of imaging systems (sources and detectors) and dose to the assessment of image quality and perception, the development of image processing techniques, and the development of image analysis methods to assist in detection and diagnosis. The latter is a natural extension of medical physicists' goals in developing imaging techniques to help physicians acquire diagnostic information and improve clinical decisions. Studies indicate that radiologists do not detect all abnormalities on images that are visible on retrospective review, and they do not always correctly characterize abnormalities that are found. Since the 1950s, the potential use of computers had been considered for analysis of radiographic abnormalities. In the mid-1980s, however, medical physicists and radiologists began major research efforts for computer-aided detection or computer-aided diagnosis (CAD), that is, using the computer output as an aid to radiologists-as opposed to a completely automatic computer interpretation-focusing initially on methods for the detection of lesions on chest radiographs and mammograms. Since then, extensive investigations of computerized image analysis for detection or diagnosis of abnormalities in a variety of 2D and 3D medical images have been conducted. The growth of CAD over the past 20 years has been tremendous-from the early days of time-consuming film digitization and CPU-intensive computations on a limited number of cases to its current status in which developed CAD approaches are evaluated rigorously on large clinically relevant databases. CAD research by medical physicists includes many aspects-collecting relevant normal and pathological cases; developing computer algorithms appropriate for the medical interpretation task including those for segmentation, feature extraction, and classifier design; developing methodology for assessing CAD performance; validating the algorithms using appropriate cases to measure performance and robustness; conducting observer studies with which to evaluate radiologists in the diagnostic task without and with the use of the computer aid; and ultimately assessing performance with a clinical trial. Medical physicists also have an important role in quantitative imaging, by validating the quantitative integrity of scanners and developing imaging techniques, and image analysis tools that extract quantitative data in a more accurate and automated fashion. As imaging systems become more complex and the need for better quantitative information from images grows, the future includes the combined research efforts from physicists working in CAD with those working on quantitative imaging systems to readily yield information on morphology, function, molecular structure, and more-from animal imaging research to clinical patient care. A historical review of CAD and a discussion of challenges for the future are presented here, along with the extension to quantitative image analysis.

Advances in computer-aided diagnosis for breast cancer

PURPOSE OF REVIEW

Computer-aided diagnosis (CAD) is a technology used for the detection and characterization of cancer. Although CAD is not limited to a single type of cancer, a large number of CAD systems to date have been designed and used for breast cancer. The aim of this review is to discuss the current state of the CAD systems for breast-cancer diagnosis, their application as a second reader in clinical practice, and studies that have evaluated the effect of CAD on radiologists' performance.

RECENT FINDINGS

A large number of CAD applications are being developed for different imaging modalities. Owing to commercially available Food and Drug Administration (FDA) approved systems, the main clinical use of CAD to date is for screen-film mammography. Many studies have shown that CAD improves radiologists' performance. A large number of academic institutions have devoted a substantial research effort to developing CAD methods.

SUMMARY

CAD systems will play an increasingly important role in the clinic as a second reader. Clinical trials have shown that CAD can improve the accuracy of breast-cancer detection. Preclinical studies have demonstrated the potential of CAD to improve the classification of malignant and benign lesions. An increased number of CAD systems are being developed for different breast-imaging modalities.

Ultrasound of the fingers for human identification using biometrics

It was hypothesized that the use of internal finger structure as imaged using commercially available ultrasound (US) scanners could act as a supplement to standard methods of biometric identification, as well as a means of assessing physiological and cardiovascular status. Anatomical structures in the finger including bone contour, tendon and features along the interphalangeal joint were investigated as potential biometric identifiers. Thirty-six pairs of three-dimensional (3D) gray-scale images of second to fourth finger (index, middle and ring) data taken from 20 individuals were spatially registered using MIAMI-Fuse software developed at our institution and also visually matched by four readers. The image-based registration met the criteria for matching successfully in 14 out of 15 image pairs on the same individual and did not meet criteria for matching in any of the 12 image pairs from different subjects, providing a sensitivity and specificity of 0.93 and 1.00, respectively. Visual matching of all image pairs by four readers yielded 96% successful match. Power Doppler imaging was performed to calculate the change in color pixel density due to physical exercise as a surrogate of stress level and to provide basic physiological information. (E-mail: gnarayan@umich.edu).

Analysis of tumor vascularity using three-dimensional power Doppler ultrasound images

Tumor vascularity is an important factor that has been shown to correlate with tumor malignancy and was demonstrated as a prognostic indicator for a wide range of cancers. Three-dimensional (3-D) power Doppler ultrasound (PDUS) offers a convenient tool for investigators to inspect the signals of blood flow and vascular structures in breast cancer. In this paper, a new computer-aided diagnosis (CAD) system for quantifying Doppler ultrasound images based on 3-D thinning algorithm and neural network is proposed. We extracted the skeleton of blood vessels from 3-D PDUS data to facilitate the capturing of morphological changes. Nine features including vessel-to-volume ratio, number of vascular trees, length of vessels, number of branching, mean of radius, number of cycles, and three tortuosity measures, were extracted from the thinning result. Benign and malignant tumors can therefore be differentiated by a score computed by a multilayered perceptron (MLP) neural network using these features as parameters. The proposed system was tested on 221 breast tumors, including 110 benign and 111 malignant lesions. The accuracy, sensitivity, specificity, and positive and negative predictive values were 88.69% (196/221), 91.89% (102/111), 85.45% (94/110), 86.44% (102/118), and 91.26% (94/103), respectively. The Az value of the ROC curve was 0.94. The results demonstrate a correlation between the morphology of blood vessels and tumor malignancy, indicating that the newly proposed method can retrieves a high accuracy in the classification of benign and malignant breast tumors.

Automated volume analysis of head and neck lesions on CT scans using 3D level set segmentation

The authors have developed a semiautomatic system for segmentation of a diverse set of lesions in head and neck CT scans. The system takes as input an approximate bounding box, and uses a multistage level set to perform the final segmentation. A data set consisting of 69 lesions marked on 33 scans from 23 patients was used to evaluate the performance of the system. The contours from automatic segmentation were compared to both 2D and 3D gold standard contours manually drawn by three experienced radiologists. Three performance metric measures were used for the comparison. In addition, a radiologist provided quality ratings on a 1 to 10 scale for all of the automatic segmentations. For this pilot study, the authors observed that the differences between the automatic and gold standard contours were larger than the interobserver differences. However, the system performed comparably to the radiologists, achieving an average area intersection ratio of 85.4% compared to an average of 91.2% between two radiologists. The average absolute area error was 21.1% compared to 10.8%, and the average 2D distance was 1.38 mm compared to 0.84 mm between the radiologists. In addition, the quality rating data showed that, despite the very lax assumptions made on the lesion characteristics in designing the system, the automatic contours approximated many of the lesions very well.

Development of a fully automatic scheme for detection of masses in whole breast ultrasound images

Ultrasonography has been used for breast cancer screening in Japan. Screening using a conventional hand-held probe is operator dependent and thus it is possible that some areas of the breast may not be scanned. To overcome such problems, a mechanical whole breast ultrasound (US) scanner has been proposed and developed for screening purposes. However, another issue is that radiologists might tire while interpreting all images in a large-volume screening; this increases the likelihood that masses may remain undetected. Therefore, the aim of this study is to develop a fully automatic scheme for the detection of masses in whole breast US images in order to assist the interpretations of radiologists and potentially improve the screening accuracy. The authors database comprised 109 whole breast US imagoes, which include 36 masses (16 malignant masses, 5 fibroadenomas, and 15 cysts). A whole breast US image with 84 slice images (interval between two slice images: 2 mm) was obtained by the ASU-1004 US scanner (ALOKA Co., Ltd., Japan). The feature based on the edge directions in each slice and a method for subtracting between the slice images were used for the detection of masses in the authors proposed scheme. The Canny edge detector was applied to detect edges in US images; these edges were classified as near-vertical edges or near-horizontal edges using a morphological method. The positions of mass candidates were located using the near-vertical edges as a cue. Then, the located positions were segmented by the watershed algorithm and mass candidate regions were detected using the segmented regions and the low-density regions extracted by the slice subtraction method. For the removal of false positives (FPs), rule-based schemes and a quadratic discriminant analysis were applied for the distribution between masses and FPs. As a result, the sensitivity of the authors scheme for the detection of masses was 80.6% (29/36) with 3.8 FPs per whole breast image. The authors scheme for a computer-aided detection may be useful in improving the screening performance and efficiency.

3D strain imaging using a rectilinear 2D array

Under mechanical compression, tissue movements are inherently three-dimensional. 2-D strain imaging can suffer from decorrelation noise caused by out-of-plane tissue movement in elevation. With 3-D strain imaging, all tissue movements can be estimated and compensated, hence minimizing out-of-plane decorrelation noise. Promising 3-D strain imaging results have been shown using 1-D arrays with mechanical translation in elevation. However, the relatively large slice thickness and mechanical translation can degrade image quality. Using 2-D arrays, an improved elevational resolution can be achieved with electronic focusing. Furthermore, scanning with 2-D arrays is also done electronically, which eliminates the need for mechanical translation. In this paper, we demonstrate the feasibility of 3-D strain imaging using a 4 cm x 4 cm ultrasonic sparse rectilinear 2-D array operating at 5MHz. The signal processing combinations of 2-D or 3-D beamforming followed by 2-D or 3-D strain imaging are studied and compared to each other to evaluate the performance of our 3-D strain imaging system. 3-D beamforming followed by 3-D strain imaging showed best performance in all experiments.

Reliable evaluation of performance level for computer-aided diagnostic scheme

RATIONALE AND OBJECTIVES

Computer-aided diagnostic (CAD) schemes have been developed for assisting radiologists in the detection of various lesions in medical images. The reliable evaluation of CAD schemes is an important task in the field of CAD research.

MATERIALS AND METHODS

Many evaluation approaches have been proposed for evaluating the performance of various CAD schemes in the past. However, some important issues in the evaluation of CAD schemes have not been systematically analyzed. The first important issue is the analysis and comparison of various evaluation methods in terms of certain characteristics. The second includes the analysis of pitfalls in the incorrect use of various evaluation methods and the effective approaches to the reduction of the bias and variance caused by these pitfalls. We attempt to address the first important issue in details in this article by conducting Monte Carlo simulation experiments, and to discuss the second issue in the Discussion section.

RESULTS

No single evaluation method is universally superior to the others; different situations of CAD applications require different evaluation methods, as recommended in this article. Bias and variance in the estimated performance levels caused by various pitfalls can be reduced considerably by the correct use of good evaluation methods.

CONCLUSIONS

This article would be useful to researchers in the field of CAD research for selecting appropriate evaluation methods and for improving the reliability of the estimated performance of their CAD schemes.

Solid breast masses: neural network analysis of vascular features at three-dimensional power Doppler US for benign or malignant classification

PURPOSE

To retrospectively evaluate the accuracy of neural network analysis of tumor vascular features at three-dimensional (3D) power Doppler ultrasonography (US) for classification of breast tumors as benign or malignant, with histologic findings as the reference standard.

MATERIALS AND METHODS

This study was approved by the local ethics committee; informed consent was waived. Three-dimensional power Doppler US images of 221 solid breast masses (110 benign, 111 malignant) were obtained in 221 women (mean age, 46 years; range, 25-71 years). After narrowing down vessels to skeletons with a 3D thinning algorithm, six vascular feature values--vessel-to-volume ratio, number of vascular trees, total vessel length, longest path length, number of bifurcations, and vessel diameter-were computed. A neural network was used to classify tumors by using these features. Independent-samples t test and receiver operating characteristic (ROC) curve analysis were used.

RESULTS

Mean values of vessel-to-volume ratio, number of vascular trees, total vessel length, longest path length, number of bifurcations, and vessel diameter were 0.0089 +/- 0.0073 (standard deviation), 26.41 +/- 14.73, 23.02 cm +/- 19.53, 8.44 cm +/- 10.38, 36.31 +/- 37.06, and 0.088 cm +/- 0.021 in malignant tumors, respectively, and 0.0028 +/- 0.0021, 9.69 +/- 6.75, 5.17 cm +/- 4.78, 1.68 cm +/- 1.79, 6.05 +/- 7.55, and 0.064 cm +/- 0.028 in benign tumors, respectively (P < .001 for all six features). Area under ROC curve (A(z)) values of the six features were 0.84, 0.87, 0.87, 0.82, 0.84, and 0.75, respectively. Accuracy, sensitivity, specificity, and positive and negative predictive values were 85% (187 of 221), 83% (96 of 115), 86% (91 of 106), 86% (96 of 111), and 83% (91 of 110), respectively, with A(z) of 0.92 based on all six feature values.

CONCLUSION

Three-dimensional power Doppler US images and neural network analysis of features can aid in classification of breast tumors as benign or malignant.

Malignant and benign breast masses on 3D US volumetric images: effect of computer-aided diagnosis on radiologist accuracy

PURPOSE

To retrospectively investigate the effect of using a custom-designed computer classifier on radiologists' sensitivity and specificity for discriminating malignant masses from benign masses on three-dimensional (3D) volumetric ultrasonographic (US) images, with histologic analysis serving as the reference standard.

MATERIALS AND METHODS

Informed consent and institutional review board approval were obtained. Our data set contained 3D US volumetric images obtained in 101 women (average age, 51 years; age range, 25-86 years) with 101 biopsy-proved breast masses (45 benign, 56 malignant). A computer algorithm was designed to automatically delineate mass boundaries and extract features on the basis of segmented mass shapes and margins. A computer classifier was used to merge features into a malignancy score. Five experienced radiologists participated as readers. Each radiologist read cases first without computer-aided diagnosis (CAD) and immediately thereafter with CAD. Observers' malignancy rating data were analyzed with the receiver operating characteristic (ROC) curve.

RESULTS

Without CAD, the five radiologists had an average area under the ROC curve (A(z)) of 0.83 (range, 0.81-0.87). With CAD, the average A(z) increased significantly (P = .006) to 0.90 (range, 0.86-0.93). When a 2% likelihood of malignancy was used as the threshold for biopsy recommendation, the average sensitivity of radiologists increased from 96% to 98% with CAD, while the average specificity for this data set decreased from 22% to 19%. If a biopsy recommendation threshold could be chosen such that sensitivity would be maintained at 96%, specificity would increase to 45% with CAD.

CONCLUSION

Use of a computer algorithm may improve radiologists' accuracy in distinguishing malignant from benign breast masses on 3D US volumetric images.

Chestwall segmentation in 3D breast ultrasound using a deformable volume model

A deformable volume segmentation method is proposed to detect the breast parenchyma in frontal scanned 3D whole breast ultrasound. Deformable volumes are a viable alternative to the deformable surface paradigm in noisy images with poorly defined object boundaries. A deformable ultrasound volume model was developed containing breast, rib, intercostal space and thoracic shadowing. Using prior knowledge about grey value statistics and shape the parameterized model deforms by optimization to match an ultrasound scan. Additionally a rib shadow enhancement filter was developed based on a Hessian sheet detector. An ROC chestwall detection study on 88 multi-center scans (20 non-visible chestwalls) showed a significant accuracy which improved strongly using the sheet detector. The results show the potential of our methodology to extract breast parenchyma which could help reduce false positives in subsequent computer aided lesion detection.

Computer-Aided Detection and Diagnosis of Breast Cancer

The use of computer-aided detection (CAD) with film or digital mammography is now widely regarded as the standard of practice in mammography and has been shown to increase the rate of breast cancer detection. There are inherent limitations in 2D mammography, and new technologies involving 2D and 3D imaging with X-rays, ultrasound, and MRI are in use or under investigation. CAD can aid in the reduction of oversight error for these modalities and has the potential to assist the physician in unifying the interpretation across alternative modalities. We believe the result will be improved sensitivity and specificity due to both improved detection and diagnosis.

Ultrasound image segmentation: a survey

This paper reviews ultrasound segmentation paper methods, in a broad sense, focusing on techniques developed for medical B-mode ultrasound images. First, we present a review of articles by clinical application to highlight the approaches that have been investigated and degree of validation that has been done in different clinical domains. Then, we present a classification of methodology in terms of use of prior information. We conclude by selecting ten papers which have presented original ideas that have demonstrated particular clinical usefulness or potential specific to the ultrasound segmentation problem.

Differentiating Benign from Malignant Solid Breast Masses: Comparison of Two-dimensional and Three-dimensional US

PURPOSE

To compare prospectively obtained static two-dimensional (2D) and three-dimensional (3D) ultrasonographic (US) images in the diagnostic performance of radiologists with respect to the differentiation of benign from malignant solid breast masses with histopathologic examination as the reference standard.

MATERIALS AND METHODS

This study had institutional review board approval, and patient informed consent was obtained. Conventional 2D and 3D US images were obtained from 141 patients (age range, 25-71 years; mean age, 46 years) with 150 solid breast masses (60 cancers and 90 benign lesions) before excisonal or needle biopsy. Four radiologists who had not performed the examinations independently reviewed 2D US images and stored 3D US data and provided a level of suspicion concerning probability of malignancy. The sensitivity, specificity, and negative predictive values of 2D images were compared with those of 3D US images.

RESULTS

For all readers, 3D US images were the same as or better than 2D US images in terms of sensitivity (100% vs 100% for reader 1; 100% vs 98% for reader 2; 98% vs 93% for reader 3; 93% vs 92% for reader 4), specificity (58% vs 56% for reader 1; 51% vs 46% for reader 2; 83% vs 72% for reader 3; 86% vs 84% for reader 4), and negative predictive values (100% vs 100% for reader 1; 100% vs 98% for reader 2; 99% vs 94% for reader 3; 95% vs 94% for reader 4). These differences, however, were not statistically significant (P > .05).

CONCLUSION

The performance of the radiologists with respect to the characterization of solid breast masses with static 2D US images was similar to that with 3D US data.

A review of breast ultrasound

Frequent advances in transducer design, electronics, computers, and signal processing have improved the quality of ultrasound images to the extent that sonography is now a major mode of imaging for the clinical diagnosis of breast cancer. Breast ultrasound is routinely used for differentiating cysts and solid nodules with high specificity. In combination with mammography, ultrasound is used to characterize solid masses as benign or malignant. There is growing interest in using Doppler ultrasound and contrast agents for measuring tumor blood flow and for imaging tumor vascularity. Ease of use and real-time imaging capability make breast ultrasound a method of choice for guiding breast biopsies and other interventional procedures. Breast ultrasound is used in many forms. B-mode is the most common form of imaging for the breast, although compound imaging and harmonic imaging are being increasingly applied to better visualize breast lesions and to reduce image artifacts. These developments, together with the formulation of a standardized lexicon of solid mass features, have improved the diagnostic performance of breast ultrasound. Several approaches that are currently being investigated to further improve performance include: (1) computer-aided-diagnosis; (2) the assessment of tumor vascularity and tumor blood flow with Doppler ultrasound and contrast agents; and (3) tissue elasticity imaging. In the future, ultrasound will play a greater role in differentiating benign from malignant masses and in the diagnosis of breast cancer.

Reduction of bias and variance for evaluation of computer-aided diagnostic schemes

Computer-aided diagnostic (CAD) schemes have been developed to assist radiologists in detecting various lesions in medical images. In addition to the development, an equally important problem is the reliable evaluation of the performance levels of various CAD schemes. It is good to see that more and more investigators are employing more reliable evaluation methods such as leave-one-out and cross validation, instead of less reliable methods such as resubstitution, for assessing their CAD schemes. However, the common applications of leave-one-out and cross-validation evaluation methods do not necessarily imply that the estimated performance levels are accurate and precise. Pitfalls often occur in the use of leave-one-out and cross-validation evaluation methods, and they lead to unreliable estimation of performance levels. In this study, we first identified a number of typical pitfalls for the evaluation of CAD schemes, and conducted a Monte Carlo simulation experiment for each of the pitfalls to demonstrate quantitatively the extent of bias and/or variance caused by the pitfall. Our experimental results indicate that considerable bias and variance may exist in the estimated performance levels of CAD schemes if one employs various flawed leave-one-out and cross-validation evaluation methods. In addition, for promoting and utilizing a high standard for reliable evaluation of CAD schemes, we attempt to make recommendations, whenever possible, for overcoming these pitfalls. We believe that, with the recommended evaluation methods, we can considerably reduce the bias and variance in the estimated performance levels of CAD schemes.

Robustness of computerized lesion detection and classification scheme across different breast US platforms

PURPOSE

To evaluate the performance of a computerized detection and diagnosis method with breast ultrasonographic (US) images obtained with US equipment from two different manufacturers.

MATERIALS AND METHODS

Two independent clinical breast US databases were used in this performance study. Data collection and database use were HIPAA-compliant and followed institutional review board-approved protocols, with waiver of informed consent. One database consisted of 1740 images obtained in 458 women with Philips US equipment. The other database consisted of 151 images obtained in 151 women with Siemens US equipment. The testing protocols included independent testing and round-robin analysis. The computerized scheme detects potential lesions, calculates imaging features for all candidate lesions, and subsequently classifies candidate lesions into different categories. Two separate classification tasks were evaluated: distinction between all actual lesions and false-positive detections and distinction between actual cancers and all other detected lesion candidates. Statistical analysis was performed by using both receiver operating characteristic (ROC) and free-response ROC methods.

RESULTS

For the distinction between all actual lesions and false-positive detections, area under the ROC curve (A(z)) values ranged between 0.87 and 0.95 for different testing protocols. In two instances, the difference in performance between databases was significant (P < .01), but it was shown that this was due to the difference in size of the databases. In the distinction of cancer from all other detections, the A(z) values ranged between 0.80 and 0.86. No statistically significant difference was found among the different testing protocols in this instance.

CONCLUSION

These results indicate that the performance of this fully automated computerized lesion detection and classification method, which demonstrated robustness over the different US equipment used, is promising.

Multimodality computerized diagnosis of breast lesions using mammography and sonography

RATIONALE AND OBJECTIVES

The purpose of this study is to investigate the use of computer-extracted features of lesions imaged by means of two modalities, mammography and breast ultrasound, in the computerized classification of breast lesions.

MATERIAL AND METHODS

We performed computerized analysis on a database of 97 patients with a total of 100 lesions (40 malignant, 40 benign solid, and 20 cystic lesions). Mammograms and ultrasound images were available for these breast lesions. There was an average of three mammographic images and two ultrasound images per lesion. Based on seed points indicated by a radiologist, the computer automatically segmented lesions from the parenchymal background and automatically extracted a set of characteristic features for each lesion. For each feature, its value averaged over all images pertaining to a given lesion was input to a Bayesian neural network for classification. We also investigated different approaches to combine image-based features into this by-lesion analysis. In that analysis, mean, maximum, and minimum feature values were considered for all images representing a lesion. We considered performance by using a leave-one-lesion-out approach, based on image features from mammography alone (two to five features), ultrasound alone (three to four features), and a combination of features from both modalities (three to five features total).

RESULTS

For the classification task of distinguishing cancer from other abnormalities in a lesion-based analysis by using a single modality, areas under the receiver operating characteristic curves (A(z) values) increased significantly when the computer selected the manner (mean, minimum, or maximum) in which image-based features were combined into lesion-based features. The highest performance was found for lesion-based analysis and automated feature selection from mean, maximum, and minimum values of features from both modalities (resulting in a total of four features being used). That A(z) value for the task of distinguishing cancer was 0.92, showing a statistically significant increase over that achieved with features from either mammography or ultrasound alone.

CONCLUSION

Computerized classification of cancer significantly improved when lesion features from both modalities were combined. Classification performance depended on specific methods for combining features from multiple images per lesion. These results are encouraging and warrant further exploration of computerized methods for multimodality imaging.

3-D ultrasound texture classification using run difference matrix

Ultrasonography is one of the most useful diagnostic tools for human soft tissue and it is in routine use in nearly all hospitals and many physicians' offices and clinics. However, the diagnosis mostly depends upon the personal experiences of the physicians. Moreover, the surface features and internal architecture of a tumor are not easy to be demonstrated simultaneously using the conventional two-dimensional (2-D) ultrasound. Recently, three-dimensional (3-D) ultrasound has been developed and allows the physician to view the 3-D anatomy. 3-D breast US can provide transverse, longitudinal planes as well as in addition simultaneously the coronal plane. This additional information has been proved to be helpful for clinical applications. In this paper, a new approach of texture classification of 3-D ultrasound breast diagnosis using run difference matrix with neural networks is developed. The test 3-D US image database includes 54 malignant and 161 benign tumors. In the experiments, the area index A(z) under the ROC curve of the proposal 3-D RDM method can achieve 0.9680. The accuracy, sensitivity, specificity, positive predictive value and negative predictive value of the proposed 3-D RDM method is 91.9%(148/161), 88.9%(48/54), 93.5%(100/107), 87.3%(48/55), and 94.3%(100/105), respectively.