Alexey A. Kolchev

Ultrasound (US) remains the main modality for the differential diagnosis of changes revealed by mammography. However, the US images themselves are subject to various types of noise and artifacts from reflections, which can worsen the quality of their analysis. Deep learning methods have a number of disadvantages, including the often insufficient substantiation of the model, and the complexity of collecting a representative training database. Therefore, it is necessary to develop effective algorithms for the segmentation, classification, and analysis of US images. The aim of the work is to develop a method for the automated detection of pathological lesions in breast US images and their segmentation. A method is proposed that includes two stages of video image processing: (1) searching for a region of interest using a random forest classifier, which classifies normal tissues, (2) selecting the contour of the lesion based on the difference in brightness of image pixels. The test set included 52 ultrasound videos which contained histologically proven suspicious lesions. The average frequency of lesion detection per frame was 91.89%, and the average accuracy of contour selection according to the IoU metric was 0.871. The proposed method can be used to segment a suspicious lesion.

Aim: to develop the module of automated calcification identification (MACI) capable to mark the different types of breast calcifications and suitable for incorporation into the computer-aided detection (CAD) system for mammography, as well as to assess its clinical efficiency. Material and methods. We performed prospective, randomized study included 9078 women who underwent the mammography. All the subjects were randomized (1:1) into the control (CAD) and experimental (CAD + MACI) arms. In the CAD arm the mammography images were processed with the help of CAD MammCheck (with no MACI). In the CAD + MACI arm we used the combined CAD and MACI image processing. After the primary screening completion the subjects were followed for minimum 3 years. Results. During the visual mammography image analysis in the CAD + MACI и CAD arms 170 (3.74%) и 159 (3.50%; р = 0.3716) breast carcinoma (BC) cases were proven, respectively. After the CAD markings analysis we additionally proven 10 and 6 BC cases, respectively (р = 0.8175). During the subsequent MACI markings analysis in the CAD + MACI arm 7 (0.15%) BC cases were verified. Totally, during the primary screening we found 187 and 165 BC cases, respectively (р = 0.0477). During the 3-year follow-up in the CAD + MACI arm 16 BC cases were proven (0.35%), of them in 2 (0.04%) cases the microcalcifications were found in the area of the subsequently verified BC. In the CAD arm the corresponding values were 22 (0.48%) and 9 (0.20%) BC cases (р = 0.054). Conclusion. MACI incorporation into the CAD design significantly increases (5.81%) the detection rate of BC associated with microcalcifications at the expense of small (0.89%) increase of the recall rate.

INTRODUCTION: Previously we developed the computer aided detection system (CAD) for mammography MammCheck II that increased the detection rate of small and difficult to detect breast carcinomas (BC). However this system was not specifically designed for calcification detection and discrimination. On the other hand, the calcifications had no influence on the CAD capability to detect BCs that appeared as a focal lesions.OBJECTIVE: To develop the approach for automated differentiation of benign and suspicious calcifications on the mammography images and assess its clinical value.MATERIALS AND METHODS: For the developed software testing we used a set of 390 mammography images with calcifications of all possible types (278 images with benign and 112 images with suspicious calcifications). For classification we used linear support vector machine (SVM) model, that was trained on the set of 126 images (70 — benign and 56 — suspicious). We developed two SVM models: with no vascular calcification analysis and with it. Statistics: for comparison between the normally distributed samples we used the Student’s T-test, for non-normally distributed — Wilcoxon signed-rank or Chi-square tests. For correlation testing of normally distributed samples the Paerson coefficient was calculated, for non-normally distributed samples — the Spearman or Kendall correlation coefficients. The statistical significance corresponded to Р-values RESULTS: During the testing of the first model version with no vascular calcification analysis we discovered the similarity of small early vascular calcifications and the suspicious ones. As a result this model falsely classified 14 of 23 (60.87%) vascular calcification clusters as suspicious. Therefore the model was improved. The final discrimination results for all calcification types (both benign and suspicious) obtained with the help of improved model were the following: true positive conclusions — 375/390 (96.15%), false positive conclusions — 15/390 (3.84%). In both cases when suspicious calcifications were classified as benign the wrong results were een only on one mammography view. At the same time, on another view the suspicious calcifications were correctly classified.DISCUSSION: During the CAD development it seems important not only mark the suspicious areas but also suppress false positive markings corresponding to the obviously benign lesions. However it is important during this operation not to suppress the true positive markings. Therefore such systems are inevitably characterized by a certain shift to decreased prognostic value of suspicious markings at the expense of the highest possible prognostic value of benign markings. In our viewpoint, the developed approach meets this requirement. Moreover, its integration into the CAD allows to suppress the markings of soft tissue lesions associated with typical benign calcifications, appeared on the previous processing steps. This capability may decrease the false positive rate of the main CAD module.CONCLUSION: The developed approach to benign and suspicious calcification discrimination (version with vascular calcification analysis) on the mammography image provided the sensitivity — 98.21%, specificity — 95.32%, negative predictive value (benign marking) — 99.25%, positive predictive value (suspicious marking) — 89.43%.

Although microcalcinates usually are hyperattenuated, which makes them hyperintensive on mammograms, breast cancer is characterized by their small size, which, combined with the small size of their clusters, makes it difficult to identify them, especially against a dense background, which is often noted in fibrous changes in the breast parenchyma. The purpose of the study is to create and evaluate the effectiveness of the block for automatic identification of calcifications and their accumulations on mammograms. Material and methods. Mammograms of patients with suspicious (136 mammograms of 67 patients), as well as benign (299 mammograms of 151 patients) calcifications of various types were analyzed using a proprietary software package. Research results. After analyzing benign calcifications, the system marked all cases (100%) of calcified sediment, rod-shaped, vascular calcifications; 33 out of 36 (92.7%) cases of dystrophic, 66 out of 70 cases (94.3%) of rounded and 12 out of 15 (80%) cases of point calcifications in all patients; as well as 2 out of 3 cases of cutaneous calcifications in 1 out of 2 patients, 103 out of 106 (97.2%) cases of flaky calcifications in 51 out of 52 (98.1%) patients and 19 out of 22 cases (86.4%) of eggshell type calcifications in 10 out of 11 patients (90.9%). Among suspicious calcifications, the system marked 33 out of 39 cases (84.6%) of large heterogeneous calcifications, all 6 cases of small linear branching calcifications and 37 out of 39 (94.9%) cases of small polymorphic calcifications in all patients, as well as 30 out of 36 (83.3%) cases of amorphous calcifications in 15 out of 16 (93.7%) patients and 12 out of 16 (75.0%) cases of small linear calcifications in 6 out of 8 (75.0%) patients. All cases of unmarked suspicious calcifications corresponded to high-intensity soft-tissue shadows associated with indistinctly defined calcifications, which were labeled by the MammCheck II system previously developed by the authors. The frequency of false positive labels was 0.31 per mammogram. Conclusions. Benign calcifications were marked on 282 out of 299 images (94.3%) in 148 out of 151 (98.0%) patients, suspicious calcifications – on 118 out of 136 images (86.8%) in 64 out of 67 patients (95.5%).

The amount of ultrasound (US) breast exams continues to grow because of the wider endorsement of breast cancer screening programs. When a solid lesion is found during the US the primary task is to decide if it requires a biopsy. Therefore, our goal was to develop a noninvasive US grayscale image analysis for benign and malignant solid breast lesion differentiation. We used a dataset consisting of 105 ultrasound images with 50 benign and 55 malignant non-cystic lesions. Features were extracted from the source image, the image of the gradient module after applying the Sobel filter, and the image after the Laplace filter. Subsequently, eight gray-level co-occurrence matrices (GLCM) were constructed for each lesion, and 13 Haralick textural features were calculated for each GLCM. Additionally, we computed the differences in feature values at different spatial shifts and the differences in feature values between the inner and outer areas of the lesion. The LASSO method was employed to determine the most significant features for classification. Finally, the lesion classification was carried out by various methods. The use of LASSO regression for feature selection enabled us to identify the most significant features for classification. Out of the 13 features selected by the LASSO method, four described the perilesional tissue, two represented the inner area of the lesion and five described the image of the gradient module. The final model achieved a sensitivity of 98%, specificity of 96%, and accuracy of 97%. Considering the perilesional area, Haralick feature differences, and the image of the gradient module can provide crucial parameters for accurate classification of US images. Features with a low AUC index (less than 0.6 in our case) can also be important for improving the quality of classification.

Background: We directly compared the mammography image processing results obtained with the help of the YOLOv4 convolutional neural network (CNN) model versus those obtained with the help of the NCA-based nested contours algorithm model. Method: We used 1080 images to train the YOLOv4, plus 100 images with proven breast cancer (BC) and 100 images with proven absence of BC to test both models. Results: the rates of true-positive, false-positive and false-negative outcomes were 60, 10 and 40, respectively, for YOLOv4, and 93, 63 and 7, respectively, for NCA. The sensitivities for the YOLOv4 and the NCA were comparable to each other for star-like lesions, masses with unclear borders, round- or oval-shaped masses with clear borders and partly visualized masses. On the contrary, the NCA was superior to the YOLOv4 in the case of asymmetric density and of changes invisible on the dense parenchyma background. Radiologists changed their earlier decisions in six cases per 100 for NCA. YOLOv4 outputs did not influence the radiologists’ decisions. Conclusions: in our set, NCA clinically significantly surpasses YOLOv4.

Purpose The amount of ultrasound (US) breast examinations continues to grow rapidly because of the wider endorsement of breast cancer screening programs. Cysts are the most commonly diagnosed breast lesions. Atypical breast cysts can be a serious differentiation problem in the US. Our goal was to develop noninvasive automated US grayscale image analysis for the cystic and solid breast lesion differentiation based on mathematical image post-processing. Materials and methods We used a set of 217 ultrasound images of proven 107 cystic (including 53 atypical) and 110 solid lesions. Empirical statistical and morphological models of the lesions were used to obtain features. The AUC indicator and Student’s t test were used to assess the quality of the individual features. The Pearson correlation matrix was used to calculate the correlation between various features. The LASSO and stepwise regression methods were used to determine the most significant features. Finally, the lesion classification was carried out by the various methods. Results The use of LASSO regression for the feature selection made it possible to select the most significant features for classification. The sensitivity increased from 87.1% to 89.2% and the specificity—from 92.2 to 94.8%. After the correlation matrix construction, it was found that features with a high value of the correlation coefficient (0.72; 0.75) can also be used to improve the quality of the classification. Conclusion The construction of the empirical model of the lesion pixels brightness behavior can provide parameters that are important for the correct classification of ultrasound images. The optimal set of features with the maximum discriminant characteristics may not be consistent with the correlation of features and the value of the AUC index. Features with a low AUC index (in our case 0.72) can also be important for improving the quality of the classification.

The paper considers an automated system for ionosphere sounding by chirp signals. The experimental scheme for quasi-vertical sounding of the ionosphere is described. It has been experimentally shown that there is no reciprocity in the characteristics of the signal propagation when changing the direction of propagation. This effect is explained by the difference in the phase incursion due to the rotation of the polarization plane. The results of numerical simulation are presented.