Gifu University of Medical Science

MYH9-related disease (MYH9-RD) is characterized by macrothrombocytopenia, hearing loss, and progressive kidney dysfunction. Due to thrombocytopenia, kidney biopsy is seldom performed, and pathological findings remain unclear. Although case reports have described focal segmental glomerulosclerosis (FSGS) and glomerular basement membrane (GBM) abnormalities like Alport syndrome, no cross-sectional studies of MYH9-RD have been performed. This study aimed to clarify kidney pathological findings through a nationwide survey.

We conducted a nationwide survey of MYH9-RD patients and collected tissues from kidney biopsies, along with immunofluorescence and electron microscopy images. Multiple pathologists examined all samples.

Nine kidney biopsy samples were included. Mesangial matrix expansion was observed in all samples (100%), while FSGS was observed in two (22%). Segmental foot process effacement was observed in all samples (100%), with irregularly aggregated podocyte dense material in seven (78%). Immunofluorescence analysis revealed that three samples (33%) had immunoglobulin and/or complement deposition: the types of depositions varied among patients. Electron dense deposits (EDD) were found in five samples (56%). GBM abnormalities - thinning, irregular thickening, and splitting of the lamina densa - were observed in five samples (56%), but no basket-weave appearance was noted. Endothelial cell swelling was found in seven samples (78%).

Mesangial expansion and segmental foot process effacement were commonly observed in MYH9-RD patients. Additional findings included immunoglobulin and complement deposition with EDD, and GBM abnormalities. Although patients may have had relatively severe disease, which limits generalizability, these results provide valuable insights into the disease mechanisms and potential therapeutic targets of MYH9-RD.

Recently, western countries have built evidence on mammographic artificial Intelligence—computer-aided diagnosis (AI-CADx) systems; however, their effectiveness has not yet been sufficiently validated in Japanese women. In this study, we aimed to establish a Japanese mammographic AI-CADx system for the first time.

We retrospectively collected screening or diagnostic mammograms from 63 institutions in Japan. We then randomly divided the images into training, validation, and test datasets in a balanced ratio of 8:1:1 on a case-level basis. The gold standard of annotation for the AI-CADx system is mammographic findings based on pathologic references. The AI-CADx system was developed using SE-ResNet modules and a sliding window algorithm. A cut-off concentration gradient of the heatmap image was set at 15%. The AI-CADx system was considered accurate if it detected the presence of a malignant lesion in a breast cancer mammogram. The primary endpoint of the AI-CADx system was defined as a sensitivity and specificity of over 80% for breast cancer diagnosis in the test dataset.

We collected 20,638 mammograms from 11,450 Japanese women with a median age of 55 years. The mammograms included 5019 breast cancer (24.3%), 5026 benign (24.4%), and 10,593 normal (51.3%) mammograms. In the test dataset of 2059 mammograms, the AI-CADx system achieved a sensitivity of 83.5% and a specificity of 84.7% for breast cancer diagnosis. The AUC in the test dataset was 0.841 (DeLong 95% CI; 0.822–0.859). The Accuracy was almost consistent independent of breast density, mammographic findings, type of cancer, and mammography vendors (AUC (range); 0.639–0.906).

The developed Japanese mammographic AI-CADx system diagnosed breast cancer with a pre-specified sensitivity and specificity. We are planning a prospective study to validate the breast cancer diagnostic performance of Japanese physicians using this AI-CADx system as a second reader.

UMIN, trial number UMIN000039009. Registered 26 December 2019, https://www.umin.ac.jp/ctr/

The purpose of this study is to identify image features in images with well-spread mammary glands, which are difficult to determine with human observation skills. We prepared images with sufficient mammary gland spread and images with insufficient mammary gland spread. We extracted image features from each and used statistical processing to examine the differences between the images. There were differences in 80 image features. There were many image features that differed in the high-frequency portion of the wavelet features.