Introduction The diagnosis of glomerular diseases is primarily based on visual assessment of histologic patterns. Semi-quantitative scoring of active and chronic lesions is often required to assess individual characteristics of the disease. Reproducibility of the visual scoring systems remains debatable, while digital and machine-learning technologies present opportunities to detect, classify and quantify glomerular lesions, also considering their inter- and intraglomerular heterogeneity. Materials and methods: We performed a cross-validated comparison of three modifications of a convolutional neural network (CNN)-based approach for recognition and intraglomerular quantification of nine main glomerular patterns of injury. Reference values provided by two nephropathologists were used for validation. For each glomerular image, visual attention heatmaps were generated with a probability of class attribution for further intraglomerular quantification. The quality of classifier-produced heatmaps was evaluated by intersection over union metrics (IoU) between predicted and ground truth localization heatmaps. Results: A proposed spatially guided modification of the CNN classifier achieved the highest glomerular pattern classification accuracies, with area under curve (AUC) values up to 0.981. With regards to heatmap overlap area and intraglomerular pattern quantification, the spatially guided classifier achieved a significantly higher generalized mean IoU value compared to single-multiclass and multiple-binary classifiers. Conclusions: We propose a spatially guided CNN classifier that in our experiments reveals the potential to achieve high accuracy for the localization of intraglomerular patterns.
Background and objectives: Treatment of a prosthetic vascular graft infection (PVGI) remains a challenging problem in vascular surgery. The aim of this study was to design a novel rat model for treatment of peripheral vascular prosthesis infection caused by Staphylococcus aureus (S. aureus) and to determine the efficacy of different antiseptic solutions in suppressing or eradicating infection from the wound and the graft material itself. Materials and methods: A piece of Dacron vascular prosthesis was surgically implanted at the dorsum of 48 Wistar rats and the wounds were infected with 5 McFarland standard inoculum of S. aureus. Suppurating wounds were daily irrigated with different antiseptic solutions: octenidine dihydrochloride, povidone-iodine, chlorhexidine digluconate, and sterile saline. The antimicrobial action of antiseptics was defined according to their capability to eradicate bacteria from the graft surroundings and bacteriological examination of the graft itself. Extended studies on wound microbiology, cytology, and histopathology were performed with an additional group of 10 rats, treated with the most effective antiseptic-octenidine dihydrochloride. Results: Four-day treatment course with octenidine, povidone-iodine, and chlorhexidine resulted in 99.98% (p = 0.0005), 90.73% (p = 0.002), and 65.97% (p = 0.004) decrease in S. aureus colonies in wound washouts, respectively. The number of S. aureus colonies increased insignificantly by 19.72% (p = 0.765) in control group. Seven-day treatment course with octenidine eradicated viable bacteria from nine out of 10 wound washouts and sterilized one vascular graft. Conclusions: A reproducible rat model of PVGI with a thriving S. aureus infection was designed. It is a first PVGI animal model where different antiseptic solutions were applied as daily irrigations to treat peripheral PVGI. Seven-day treatment with octenidine eradicated bacteria from the wound washouts for 90% of rats and one vascular graft. Further studies are needed to investigate if irrigations with octenidine could properly cure vascular bed from infection to assure a successful implantation of a new synthetic vascular substitute.
Digital image analysis (DA) brings new opportunities to enhance breast cancer pathology testing by providing tools to read tissue microscopy-based data in a more precise, accurate, and high-throughput manner. The applications vary from very practical solutions assisting in quantification of biomarker expression to more complex efforts to analyse multi-dimensional data. We present our DA experiments to enhance HER2 immunohistochemistry (IHC) and FISH testing and to explore multiple IHC biomarker variation profiles in breast cancer.
Approximately 10% of all breast cancer (BC) cases are familial and caused by inheritance of mutant BRCA1, BRCA2, or some other genes from the same DNA reparation pathway. Genetic counseling in families with cancer history is a powerful means for early cancer detection and active risk reduction through preventive interventions. This is the first report of the rare inherited BRCA2 frameshift-deletion mutation c.3847_3848delGT in one Lithuanian pedigree with the intense familial history of BC. Three BRCA2-positive blood relatives with BC of different biological types were identified in this pedigree with the same type mutation. All three cases were diagnosed with advanced stage ductal carcinoma. Markedly, polymorphic cells and numerous mitoses were identified in BC from the cases. Two patients from the family were diagnosed with the triple negative tumors, while one case had early onset of the hormone positive BC. Despite the variation in clinical and biological presentation of BC, all cases showed a good response to conventional treatment. In conclusion, the strong influence of BRCA2 mutation on the onset of BC of various biological types reveals the complexity of genetic counselling in families with BC history.
INTRODUCTION Pathology diagnosis of glomerular diseases is primarily based on visual assessment of histologic patterns. Semi-quantitative scoring of active and chronic lesions is often required to assess individual characteristics of the disease. Reproducibility of the visual scoring systems remains debatable while digital and machine learning technologies open opportunities to detect, classify and quantify glomerular lesions, also considering their inter- and intraglomerular heterogeneity. MATERIALS AND METHODS We performed a cross-validated comparison of three modifications of a convolutional neural network (CNN)-based approach for recognition and intraglomerular quantification of nine main glomerular patterns of injury. Reference values provided by two nephropathologists were used for validation. For each glomerular image, visual attention heatmaps were generated with a probability of class attribution for further intraglomerular quantification. Quality of classifier-produced heatmaps was evaluated by an intersection over union metrics (IoU) between predicted and ground truth localization heatmaps. RESULTS A proposed spatially guided modification of CNN classifier achieved the highest glomerular pattern classification accuracies with AUC values up to 0.981. With regards to heatmap overlap area and intraglomerular pattern quantification, spatially guided classifier achieved significantly higher generalized mean IoU value, compared with single-multiclass and multiple-binary classifiers. CONCLUSIONS We propose a spatially guided CNN classifier which in our experiments reveals the potential to achieve high accuracy for intraglomerular pattern localization.