Ulcerative Colitis, LAIR1 and TOX2 Expression, and Colorectal Cancer Deep Learning Image Classification Using Convolutional Neural Networks DOI Open Access
Joaquim Carreras, Giovanna Roncador, Rifat Hamoudi

et al.

Cancers, Journal Year: 2024, Volume and Issue: 16(24), P. 4230 - 4230

Published: Dec. 19, 2024

Background: Ulcerative colitis is a chronic inflammatory bowel disease of the colon mucosa associated with higher risk colorectal cancer. Objective: This study classified hematoxylin and eosin (H&E) histological images ulcerative colitis, normal colon, cancer using artificial intelligence (deep learning). Methods: A convolutional neural network (CNN) was designed trained to classify three types diagnosis, including 35 cases (n = 9281 patches), 21 control 12,246), 18 63,725). The data were partitioned into training (70%) validation sets (10%) for network, test set (20%) performance on new data. CNNs included transfer learning from ResNet-18, comparison other CNN models performed. Explainable computer vision used Grad-CAM technique, additional LAIR1 TOX2 immunohistochemistry performed in analyze immune microenvironment. Results: Conventional clinicopathological analysis showed that steroid-requiring characterized by endoscopic Baron histologic Geboes scores expression lamina propria, but lower isolated lymphoid follicles (all p values < 0.05) compared mesalazine-responsive colitis. classification accuracy 99.1% 99.8% cancer, control. heatmap confirmed which regions most important. also differentiated between based H&E, LAIR1, staining. Additional 10 (adenocarcinoma) correctly classified. Conclusions: are especially suited image conditions such as cancer; relevant immuno-oncology markers

Language: Английский

Fast-Responsive HClO-Activated Near-Infrared Fluorescent Probe for In Vivo Diagnosis of Inflammatory Bowel Disease and Ex Vivo Optical Fecal Analysis DOI

Kairong Yang,

Yang Tian,

Bingbing Zheng

et al.

Analytical Chemistry, Journal Year: 2024, Volume and Issue: 96(29), P. 12065 - 12073

Published: July 10, 2024

Inflammatory bowel disease (IBD) is an idiopathic intestinal inflammatory disease, whose etiology intimately related to the overproduction of hypochlorous acid (HClO). Optical monitoring HClO in living body favors real-time diagnosis diseases. However, HClO-activated near-infrared (NIR) fluorescent probes with rapid response and high cell uptake are still lacking. Herein, we report activatable acceptor-π-acceptor (A-π-A)-type NIR probe (

Language: Английский

Citations

7
Investigating the dual causative pathways linking immune cells and venous thromboembolism via Mendelian randomization analysis DOI Creative Commons

Ning Qi,

Zhuochen Lyu,

Lu Huang

et al.

Thrombosis Journal, Journal Year: 2025, Volume and Issue: 23(1)

Published: Jan. 23, 2025

Language: Английский

Citations

0
Causal role of immune cells in inflammatory bowel disease: A Mendelian randomization study DOI Creative Commons
Haoyu Chen, Qi Li, Tianyu Gao

et al.

Medicine, Journal Year: 2024, Volume and Issue: 103(14), P. e37537 - e37537

Published: April 5, 2024

Inflammatory bowel disease (IBD) is characterized by an inflammatory response closely related to the immune system, but relationship between inflammation and IBD remains unclear. We performed a comprehensive 2-sample Mendelian randomization (MR) analysis determine causal cell characteristics IBD. Using publicly available genetic data, we explored 731 risk. Inverse-variance weighting was primary analytical method. To test robustness of results, used weighted median-based, MR-Egger, simple mode, mode-based methods. Finally, reverse MR assess possibility causality. identified suggestive associations 2 traits risk ( P = 4.18 × 10 –5 for human leukocyte antigen-DR on CD14+ monocytes, OR: 0.902; 95% CI: 0.859–0.947; CD39+ CD4+ T cells, 6.24 ; 1.042; 1.021–1.063). Sensitivity results these were consistent. In analysis, found no statistically significant association traits. Our study demonstrates close connection cells using MR, providing guidance future clinical basic research.

Language: Английский

Citations

1
Ulcerative Colitis, LAIR1 and TOX2 Expression, and Colorectal Cancer Deep Learning Image Classification Using Convolutional Neural Networks DOI Open Access
Joaquim Carreras, Giovanna Roncador, Rifat Hamoudi

et al.

Cancers, Journal Year: 2024, Volume and Issue: 16(24), P. 4230 - 4230

Published: Dec. 19, 2024

Background: Ulcerative colitis is a chronic inflammatory bowel disease of the colon mucosa associated with higher risk colorectal cancer. Objective: This study classified hematoxylin and eosin (H&E) histological images ulcerative colitis, normal colon, cancer using artificial intelligence (deep learning). Methods: A convolutional neural network (CNN) was designed trained to classify three types diagnosis, including 35 cases (n = 9281 patches), 21 control 12,246), 18 63,725). The data were partitioned into training (70%) validation sets (10%) for network, test set (20%) performance on new data. CNNs included transfer learning from ResNet-18, comparison other CNN models performed. Explainable computer vision used Grad-CAM technique, additional LAIR1 TOX2 immunohistochemistry performed in analyze immune microenvironment. Results: Conventional clinicopathological analysis showed that steroid-requiring characterized by endoscopic Baron histologic Geboes scores expression lamina propria, but lower isolated lymphoid follicles (all p values < 0.05) compared mesalazine-responsive colitis. classification accuracy 99.1% 99.8% cancer, control. heatmap confirmed which regions most important. also differentiated between based H&E, LAIR1, staining. Additional 10 (adenocarcinoma) correctly classified. Conclusions: are especially suited image conditions such as cancer; relevant immuno-oncology markers

Language: Английский

Citations

0