The detection of objects of interest in high-resolution digital pathological images is a key part of diagnosis and is a labor-intensive task for pathologists. In this paper, we describe a Faster R-CNN-based approach for the detection of glomeruli in multistained whole slide images (WSIs) of human renal tissue sections. Faster R-CNN is a state-of-the-art general object detection method based on a convolutional neural network, which simultaneously proposes object bounds and objectness scores at each point in an image. The method takes an image obtained from a WSI with a sliding window and classifies and localizes every glomerulus in the image by drawing the bounding boxes. We configured Faster R-CNN with a pretrained Inception-ResNet model and retrained it to be adapted to our task, then evaluated it based on a large dataset consisting of more than 33,000 annotated glomeruli obtained from 800 WSIs. The results showed the approach produces comparable or higher than average F-measures with different stains compared to other recently published approaches. This approach could have practical application in hospitals and laboratories for the quantitative analysis of glomeruli in WSIs and, potentially, lead to a better understanding of chronic glomerulonephritis.

Introduction Diagnosing renal pathologies is important for performing treatments. However, classifying every glomerulus is difficult for clinicians; thus, a support system, such as a computer, is required. This paper describes the automatic classification of glomerular images using a convolutional neural network (CNN). Method To generate appropriate labeled data, annotation criteria including 12 features (e.g., “fibrous crescent”) were defined. The concordance among 5 clinicians was evaluated for 100 images using the kappa (κ) coefficient for each feature. Using the annotation criteria, 1 clinician annotated 10,102 images. We trained the CNNs to classify the features with an average κ ≥0.4 and evaluated their performance using the receiver operating characteristic–area under the curve (ROC–AUC). An error analysis was conducted and the gradient-weighted class activation mapping (Grad-CAM) was also applied; it expresses the CNN’s focusing point with a heat map when the CNN classifies the glomerular image for a feature. Results The average κ coefficient of the features ranged from 0.28 to 0.50. The ROC–AUC of the CNNs for test data varied from 0.65 to 0.98. Among the features, “capillary collapse” and “fibrous crescent” had high ROC–AUC values of 0.98 and 0.91, respectively. The error analysis and the Grad-CAM visually showed that the CNN could not distinguish between 2 different features that had similar visual structures or that occurred simultaneously. Conclusion The differences in the texture or frequency of the co-occurrence between the different features affected the CNN performance; thus, to improve the classification accuracy, methods such as segmentation are required.

To clarify the significance of quantitative analyses of amyloid proteins in clinical practice and in research relating to systemic amyloidoses, we applied mass spectrometry-based quantification by isotope-labeled cell-free products (MS-QBIC) to formalin-fixed, paraffin-embedded (FFPE) tissues. The technique was applied to amyloid tissues collected by laser microdissection of Congo red-stained lesions of FFPE specimens. Twelve of 13 amyloid precursor proteins were successfully quantified, including serum amyloid A (SAA), transthyretin (TTR), immunoglobulin kappa light chain (IGK), immunoglobulin lambda light chain (IGL), beta-2-microglobulin (B2M), apolipoprotein (Apo) A1, Apo A4, Apo E, lysozyme, Apo A2, gelsolin, and fibrinogen alpha chain; leukocyte cell-derived chemotaxin-2 was not detected. The quantification of SAA, TTR, IGK, IGL, and B2M confirmed the responsible proteins, even when the immunohistochemical results were not decisive. Considerable amounts of Apo A1, Apo A4, and Apo E were deposited in parallel amounts with the responsible proteins. Quantification of amyloid protein by MS-QBIC is feasible and useful for the classification of and research on systemic amyloidoses.

Crystalglobulinemia is an extremely rare complication of monoclonal gammopathy and is characterized by crystal thrombi within systemic organs. We herein report the first described case of crystalglobulinemia accompanied by laminar crystal deposition in the large vessels. A 44-year-old man presented with a history of numbness, pain, and swelling of the left leg in addition to visual impairment. Renal and skin biopsies revealed crystal thrombi within the capillary lumens. The patient was finally diagnosed with crystalglobulinemia associated with multiple myeloma. He was treated with hemodialysis and chemotherapy but died of the disease 15 months after admission. Autopsy demonstrated a huge amount of crystal deposition in the subintimal layer of the vascular wall throughout the thoracic to abdominal aorta. The characteristic deposition extended to the iliac arteries, common carotid arteries, and subclavian arteries but did not affect the bilateral renal arteries. Antemortem computed tomography demonstrated higher intensity in the wall of the abdominal aorta but not in the walls of the renal arteries, suggesting that a finding of high intensity on computed tomography could be a clinical marker of systemic crystal deposition.

No abstract