Surveillance after colorectal polyp resection

The histologic features, molecular features, detection and management of serrated polyps: a review

The serrated pathway to colorectal cancers (CRCs) is a significant pathway encompassing five distinct types of lesions, namely hyperplastic polyps (HPs), sessile serrated lesions (SSLs), sessile serrated lesions with dysplasia (SSL-Ds), traditional serrated adenomas (TSAs), and serrated adenoma unclassified. In contrast to the conventional adenoma-carcinoma pathway, the serrated pathway primarily involves two mechanisms: BRAF/KRAS mutations and CpG island methylator phenotype (CIMP). HPs are the most prevalent non-malignant lesions, while SSLs play a crucial role as precursors to CRCs, On the other hand, traditional serrated adenomas (TSAs) are the least frequently encountered subtype, also serving as precursors to CRCs. It is crucial to differentiate these lesions based on their unique morphological characteristics observed in histology and colonoscopy, as the identification and management of these serrated lesions significantly impact colorectal cancer screening programs. The management of these lesions necessitates the crucial steps of removing premalignant lesions and implementing regular surveillance. This article provides a comprehensive summary of the epidemiology, histologic features, molecular features, and detection methods for various serrated polyps, along with recommendations for their management and surveillance.

Accuracy of GPT-4 in histopathological image detection and classification of colorectal adenomas

AIMS

To evaluate the accuracy of Chat Generative Pre-trained Transformer (ChatGPT) powered by GPT-4 in histopathological image detection and classification of colorectal adenomas using the diagnostic consensus provided by pathologists as a reference standard.

METHODS

A study was conducted with 100 colorectal polyp photomicrographs, comprising an equal number of adenomas and non-adenomas, classified by two pathologists. These images were analysed by classic GPT-4 for 1 time in October 2023 and custom GPT-4 for 20 times in December 2023. GPT-4's responses were compared against the reference standard through statistical measures to evaluate its proficiency in histopathological diagnosis, with the pathologists further assessing the model's descriptive accuracy.

RESULTS

GPT-4 demonstrated a median sensitivity of 74% and specificity of 36% for adenoma detection. The median accuracy of polyp classification varied, ranging from 16% for non-specific changes to 36% for tubular adenomas. Its diagnostic consistency, indicated by low kappa values ranging from 0.06 to 0.11, suggested only poor to slight agreement. All of the microscopic descriptions corresponded with their diagnoses. GPT-4 also commented about the limitations in its diagnoses (eg, slide diagnosis best done by pathologists, the inadequacy of single-image diagnostic conclusions, the need for clinical data and a higher magnification view).

CONCLUSIONS

GPT-4 showed high sensitivity but low specificity in detecting adenomas and varied accuracy for polyp classification. However, its diagnostic consistency was low. This artificial intelligence tool acknowledged its diagnostic limitations, emphasising the need for a pathologist's expertise and additional clinical context.