Chisako Muramatsu

Usefulness of Texture Analysis for Computerized Classification of Breast Lesions on Mammograms

This work presents the usefulness of texture features in the classification of breast lesions in 5518 images of regions of interest, which were obtained from the Digital Database for Screening Mammography that included microcalcifications, masses, and normal cases. Sixteen texture features were used, i.e., 13 were based on the spatial gray-level dependence matrix and 3 on the wavelet transform. The nonparametric K-NN classifier was used in the classification stage. The results obtained from receiver operating characteristic analysis indicated that the texture features can be used for separating normal regions and lesions with masses and microcalcifications, yielding the area under the curve (AUC) values of 0.957 and 0.859, respectively. However, the texture features were not very effective for distinguishing between malignant and benign lesions because the AUC was 0.617 for masses and 0.607 for microcalcifications. The study showed that the texture features can be used for the detection of suspicious regions in mammograms.

An Investigation of Radiologists' Perception of Lesion Similarity. Observations with Paired Breast Masses on Mammograms and Paired Lung Nodules on CT Images

RATIONALE AND OBJECTIVES We conducted an observer study to investigate whether radiologists can judge similarities in pairs of breast masses and lung nodules consistently and reproducibly. MATERIALS AND METHODS Institutional review board approval and informed observer consent were obtained. This study was compliant with the Health Insurance Portability and Accountability Act. We used eight pairs of breast masses on mammograms and eight pairs of lung nodules on computed tomographic images, for which subjective similarity ratings ranging from 0 to 1 were determined in our previous studies. From these, four sets of image pairs were created (ie, a set of eight mass pairs, a set of eight nodule pairs, and two mixed sets of four mass and four nodule pairs). Eight radiologists, including four breast radiologists and four chest radiologists, compared all combinations of the eight pairs in each set using a two-alternative forced-choice (2AFC) method to determine the similarity ranking scores by identifying which pair was more similar than the other pair based on the overall impression for diagnosis. RESULTS In the mass set and nodule set, the relationship between the average subjective similarity ratings and the average similarity ranking scores by 2AFC indicated very high correlations (r = 0.91 and 0.88). Moreover, in the two mixed sets, the correlations between the average subjective similarity ratings and the average similarity ranking scores were also very high (r = 0.90 and 0.98). Thus, radiologists were able to compare the similarities for pairs of lesions consistently, even in the unusual comparison of pairs of completely different types of lesions. CONCLUSION The subjective similarity of a pair of lesions in medical images can be quantified consistently by a group of radiologists. The concept of similarity of lesions in medical images can be subjected to rigorous scientific research and investigation in the future.

Presentation of Similar Images as a Reference for Distinction Between Benign and Malignant Masses on Mammograms: Analysis of Initial Observer Study

The effect of the presentation of similar images for distinction between benign and malignant masses on mammograms was evaluated in the observer performance study. Images of masses were obtained from the Digital Database for Screening Mammography. We selected 50 benign and 50 malignant masses by a stratified randomization method. For each case, similar images were selected based on the size of masses and the similarity measures. Radiologists were shown images with unknown masses and asked to provide their confidence level that the lesions were malignant before and after the presentation of the similar images. Eleven observers, including three attending breast radiologists, three breast imaging fellows, and five residents, participated. The average areas under the receiver operating characteristic curves without and with the presentation of the similar images were almost equivalent. However, there were many cases in which the similar images caused beneficial effects to the observers, whereas there were a small number of cases in which the similar images had detrimental effects. From a detailed analysis of the reasons for these detrimental effects, we found that the similar images would not be useful for diagnosis of rare and very difficult cases, i.e., benign-looking malignant and malignant-looking benign cases. In addition, these cases should not be included in the reference database, because radiologists would be confused by these unusual cases. The results of this study could be very important and useful for the future development and improvement of a computer-aided diagnosis system.

Representation of Lesion Similarity by Use of Multidimensional Scaling for Breast Masses on Mammograms

Presentation of similar reference images can be useful for diagnosis of new lesions. A similarity map which can visually present the overview of the relationship between the lesions with different types may provide the supplemental information to the reference images. A new method for constructing the similarity map by multidimensional scaling (MDS) for breast masses on mammograms was investigated. Nine pathologic types were included; three regions of interests each from the nine groups were employed in this study. Subjective similarity ratings by expert readers were obtained for all possible 351 pairs of masses. Using the average ratings, MDS similarity map was created. Each axis of the MDS configuration was fitted by the linear model with 13 image features to reconstruct the similarity map. Dissimilarity based on the distance in the reconstructed space was determined and compared with the subjective rating. The MDS map consistently represented the similarity between cysts and fibroadenomas, invasive lobular carcinomas and scirrhous carcinomas, and ductal carcinomas in situ, solid–tubular carcinomas, and papillotubular carcinomas with the experts’ data. The correlation between the average subjective ratings and the dissimilarities based on the distance in the reconstructed feature space was much greater (−0.87) than that of the dissimilarities based on the distance in the conventional feature space (−0.65). The new similarity map by MDS can be useful for visualizing the relationship between breast masses with different pathologic types. It has potential usefulness in selecting the similarity measures and providing the supplemental information.

Correspondence among subjective and objective similarities and pathologic types of breast masses on digital mammography

In multi-modality, multi-information breast cancer diagnosis framework, radiologists take into account all the information available in making diagnosis, one of which can be the information from reference cases. The purpose of this study is to investigate the relationship between pathological concordance and image similarity of breast masses for exploring the utility of similar images and determining the effective similarity index for image retrieval. Twenty-seven images of masses, three from each of 9 pathologic types, were used in this study. Subjective similarity ratings for all possible pairs (351 pairs) were provided by 8 expert readers. Thirteen image features were determined, and their usefulness as a similarity index was examined. Generally, masses with the same pathologic types were considered more similar (0.75) than those with different types (0.43) by the experts, although cysts and fibroadenomas appeared very similar on mammograms. Perimeter, ellipticity, radial gradient index, and full-width at half maximum of radial gradient histogram were considered potentially useful (correlation, r>0.4) for estimating subjective similarity among image features. Similar images together with their clinical data may serve as a useful reference for diagnosis of breast lesions.

Classifying breast masses in volumetric whole breast ultrasound data: a 2.5-dimensional approach

The aim of this paper is to investigate a 2.5-dimensional approach in classifying masses as benign or malignant in volumetric anisotropic voxel whole breast ultrasound data In this paper, the term 2.5-dimensional refers to the use of a series of 2-dimensional images While mammography is very effective in breast cancer screening in general, it is less sensitivity in detecting breast cancer in younger women or women with dense breasts Breast ultrasonography does not have the same limitation and is a valuable adjunct in breast cancer detection We have previously reported on the clinical value of volumetric data collected from a prototype whole breast ultrasound scanner The current study focuses on a new 2.5-dimensional approach in analyzing the volumetric whole breast ultrasound data for mass classification Sixty-three mass lesions were studied Of them 33 were malignant and 30 benign Features based on compactness, orientation, shape, depth-to-width ratio, homogeneity and posterior echo were measured Linear discriminant analysis and receiver operating characteristic (ROC) analysis were employed for classification and performance evaluation The area under the ROC curve (AUC) was 0.91 using all breast masses for training and testing and 0.87 using the leave-one-mass-out cross-validation method Clinically significance of the results will be evaluated using a larger dataset from multi-clinics.

Presentation of similar images for diagnosis of breast masses on mammograms: analysis of the effect on residents

We have been developing a computerized scheme for selecting visually similar images that would be useful to radiologists in the diagnosis of masses on mammograms. Based on the results of the observer performance study, the presentation of similar images was useful, especially for less experienced observers. The test cases included 50 benign and 50 malignant masses. Ten observers, including five breast radiologists and five residents, were asked to provide the confidence level of the lesions being malignant before and after the presentation of similar images. By use of multireader, multi-case receiver operating characteristic analysis, the average areas under the curves for the five residents were 0.880 and 0.896 without and with similar images, respectively (p=0.040). There were four malignant cases in which the initial ratings were relatively low, but the similar images alerted the residents to increase their confidence levels of malignancy close to those by the breast radiologists. The presentation of similar images may cause some observers falsely to increase their suspicion for some benign cases; however, if similar images can alert radiologists to recognize the signs of malignancy and also help them to decrease their suspicion correctly for some benign cases, they can be useful in the diagnosis on mammograms.