Version 1
: Received: 2 November 2024 / Approved: 4 November 2024 / Online: 5 November 2024 (09:20:56 CET)
How to cite:
Carreras, J.; Roncador, G.; Hamoudi, R. Ulcerative Colitis, LAIR1 and TOX2 expression and Colorectal Cancer Deep Learning Image Classification Using Convolutional Neural Networks. Preprints2024, 2024110211. https://doi.org/10.20944/preprints202411.0211.v1
Carreras, J.; Roncador, G.; Hamoudi, R. Ulcerative Colitis, LAIR1 and TOX2 expression and Colorectal Cancer Deep Learning Image Classification Using Convolutional Neural Networks. Preprints 2024, 2024110211. https://doi.org/10.20944/preprints202411.0211.v1
Carreras, J.; Roncador, G.; Hamoudi, R. Ulcerative Colitis, LAIR1 and TOX2 expression and Colorectal Cancer Deep Learning Image Classification Using Convolutional Neural Networks. Preprints2024, 2024110211. https://doi.org/10.20944/preprints202411.0211.v1
APA Style
Carreras, J., Roncador, G., & Hamoudi, R. (2024). Ulcerative Colitis, LAIR1 and TOX2 expression and Colorectal Cancer Deep Learning Image Classification Using Convolutional Neural Networks. Preprints. https://doi.org/10.20944/preprints202411.0211.v1
Chicago/Turabian Style
Carreras, J., Giovanna Roncador and Rifat Hamoudi. 2024 "Ulcerative Colitis, LAIR1 and TOX2 expression and Colorectal Cancer Deep Learning Image Classification Using Convolutional Neural Networks" Preprints. https://doi.org/10.20944/preprints202411.0211.v1
Abstract
Background: Ulcerative colitis is a chronic inflammatory bowel disease of the colon mucosa associated with a higher risk of colorectal cancer. Objective: This study is a proof-of-concept analysis aimed to test the feasibility of classifying hematoxylin and eosin (H&E) histological images of ulcerative colitis, normal colon, and colorectal cancer using Artificial Intelligence (AI); Methods: A convolutional neural network (CNN) was designed and trained to classify the 3 types of diagnosis, including 35 cases of ulcerative colitis (n = 9,281 images), 21 colon control (n = 12,246), and 18 colorectal cancer (n = 63,725). The data were partitioned into training (70%) and validation sets (10%) for training the network, and a test set (20%) to test the performance on the new data. Explainable artificial intelligence for computer vision was performed using gradient-weighted class activation mapping (Grad-CAM) to understand the classification decisions; and additional LAIR1 and TOX2 immunohistochemistry was performed in ulcerative colitis to analyze the immune microenvironment; Results: The trained network classified the 3 diagnoses with high performance. The model classified ulcerative colitis with an accuracy of 99.1%, precision of 97.1%, recall of 94.8%, an F1-score of 95.9%, and specificity of 99.6%. For colorectal cancer, the performance was as follows: accuracy, 99.8%; precision, 99.9%; recall, 99.8%; F1-score 99.9%; and specificity, 99.7%. The Grad-CAM heatmap confirmed which parts of the image were most important for classification. The CNN also managed to differentiate between steroid-requiring (SR) and nonsteroid requiring (non-SR) ulcerative colitis based on H&E, LAIR1 and TOX2 staining; Conclusions: Convolutional neural networks are essential tools for deep learning and are especially suited for image recognition in conditions such as ulcerative colitis and colorectal cancer; LAIR1 and TOX2 are promising immuno-oncology markers in ulcerative colitis.
Medicine and Pharmacology, Pathology and Pathobiology
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
