bioRxiv (Cold Spring Harbor Laboratory) · 2018 · 19 citations · 36 references
MedicineNephrologyPathologyBiomedical ImagingComputer VisionRenal PathologyChronic Kidney DiseaseGlomerular DiseasesGlomerular InjuryRenal AssessmentRenal DiseaseRenal ImagingConvolutional Neural Network DetectionConvolutional Neural Network SegmentationConvolutional Neural NetworksDeep Learning DetectionKidney Biopsy AssessmentKidney DiseasesRenal Biopsy FindingsRenal Morphology Assessment
ABSTRACT Introduction The number of glomeruli and glomerulosclerosis evaluated on kidney biopsy slides constitute as standard components of a renal pathology report. Prevailing methods for glomerular assessment remain manual, labor intensive and non-standardized. We developed a deep learning framework to accurately identify and segment glomeruli from digitized images of human kidney biopsies. Methods Trichrome-stained images (n=275) from renal biopsies of 171 chronic kidney disease patients treated at the Boston Medical Center from 2009-12 were analyzed. A sliding window operation was defined to crop each original image to smaller images. Each cropped image was then evaluated by three experts into three categories: (a) No glomerulus, (b) Normal or partially sclerosed glomerulus and (c) Globally sclerosed glomerulus. This led to identification of 751 unique images representing nonglomerular regions, 611 images with either normal or partially sclerosed (NPS) glomeruli and 134 images with globally sclerosed (GS) glomeruli. A convolutional neural network (CNN) was trained with cropped images as inputs and corresponding labels as output. Using this model, an image processing routine was developed to scan the test data images to segment the GS glomeruli. Results The CNN model was able to accurately discriminate non-glomerular images from NPS and GS images (Performance on test data - Accuracy: 92.67±2.02% and Kappa: 0.8681±0.0392). The segmentation model that was based on the CNN multi-label classifier accurately marked the GS glomeruli on the test data (Matthews correlation coefficient = 0.628). Conclusion This work demonstrates the power of deep learning for assessing complex histologic structures from digitized human kidney biopsies.
36
Rethinking the Inception Architecture for Computer Vision
Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe et al. · 2016 · 30.9K citations
Dermatologist-level classification of skin cancer with deep neural networks
Andre Esteva, Brett Kuprel, Roberto A. Novoa et al. · Nature · 2017 · 13.8K citations · Full text