Global ETD Search

1	Deep Neural Network for Classification of H&E-stained Colorectal Polyps : Exploring the Pipeline of Computer-Assisted Histopathology Brunzell, Stina January 2024 (has links) Colorectal cancer is one of the most prevalent malignancies globally and recently introduced digital pathology enables the use of machine learning as an aid for fast diagnostics. This project aimed to develop a deep neural network model to specifically identify and differentiate dysplasia in the epithelium of colorectal polyps and was posed as a binary classification problem. The available dataset consisted of 80 whole slide images of different H&E-stained polyp sections, which were parted info smaller patches, annotated by a pathologist. The best performing model was a pre-trained ResNet-18 utilising a weighted sampler, weight decay and augmentation during fine tuning. Reaching an area under precision-recall curve of 0.9989 and 97.41% accuracy on previously unseen data, the model’s performance was determined to underperform compared to the task’s intra-observer variability and be in alignment with the inter-observer variability. Final model made publicly available at https://github.com/stinabr/classification-of-colorectal-polyps. Machine Learning Deep Learning Neural Network Deep Neural Network ResNet-18 Transfer Learning Image Analysis Image Processing Medical Image Processing Whole Slide Image WSI Pathology Histopathology Digital Pathology Colorectal Cancer Cancer Polyp H&E-stain Medical Image Processing Medicinsk bildbehandling

Search results

Deep Neural Network for Classification of H&amp;E-stained Colorectal Polyps : Exploring the Pipeline of Computer-Assisted Histopathology

Deep Neural Network for Classification of H&E-stained Colorectal Polyps : Exploring the Pipeline of Computer-Assisted Histopathology