Automatically detecting Crohn's disease and Ulcerative Colitis from endoscopic imaging

Review Radiology, Nuclear Medicine & Medical Imaging

Transfer learning for medical image classification: a literature review

Hee E. Kim et al.

Summary: Transfer learning with convolutional neural networks has made significant contributions to medical image analysis by leveraging prior knowledge from similar tasks to improve performance on new tasks. This review paper provides guidance on selecting models and transfer learning approaches for medical image classification. The majority of studies evaluated multiple models empirically, with deep models like Inception being the most commonly used. Deep models as feature extractors, such as ResNet or Inception, are recommended to save computational costs and time without compromising predictive power.

BMC MEDICAL IMAGING (2022)

Add to Collection

Article Gastroenterology & Hepatology

Clinical applications of artificial intelligence and machine learning-based methods in inflammatory bowel disease

Shirley Cohen-Mekelburg et al.

Summary: Applying artificial intelligence to inflammatory bowel disease has the potential to reduce care variation and improve quality, but it is still in its early stages with great potential for future transformation.

JOURNAL OF GASTROENTEROLOGY AND HEPATOLOGY (2021)

Add to Collection

Article Health Care Sciences & Services

Machine Learning Models Cannot Replace Screening Colonoscopy for the Prediction of Advanced Colorectal Adenoma

Georg Semmler et al.

Summary: This study evaluated the potential of machine learning methods to predict advanced adenomas in a screening program for colorectal cancer, showing that machine learning based on point-prevalence laboratory and clinical information does not accurately predict advanced adenomas.

JOURNAL OF PERSONALIZED MEDICINE (2021)

Add to Collection

Review Gastroenterology & Hepatology

Artificial intelligence in gastrointestinal endoscopy for inflammatory bowel disease: a systematic review and new horizons

Gian Eugenio Tontini et al.

Summary: AI-assisted endoscopy in the field of IBD is a rapidly growing research area with promising technical results, showing potential to enhance patient management in clinical practice and gastrointestinal endoscopy. Additional confirmation from real-life clinical settings is needed to validate the benefits of AI in assessing UC mucosal activity and CD capsule endoscopy.

THERAPEUTIC ADVANCES IN GASTROENTEROLOGY (2021)

Add to Collection

Article Biotechnology & Applied Microbiology