A pilot study of the endomicroscopic assessment of tumor extension in Barrett's esophagus-associated neoplasia before endoscopic resection

Diagnosis of malignancy in oropharyngeal confocal laser endomicroscopy using GPT 4.0 with vision

PURPOSE

Confocal Laser Endomicroscopy (CLE) is an imaging tool, that has demonstrated potential for intraoperative, real-time, non-invasive, microscopical assessment of surgical margins of oropharyngeal squamous cell carcinoma (OPSCC). However, interpreting CLE images remains challenging. This study investigates the application of OpenAI's Generative Pretrained Transformer (GPT) 4.0 with Vision capabilities for automated classification of CLE images in OPSCC.

METHODS

CLE Images of histological confirmed SCC or healthy mucosa from a database of 12 809 CLE images from 5 patients with OPSCC were retrieved and anonymized. Using a training data set of 16 images, a validation set of 139 images, comprising SCC (83 images, 59.7%) and healthy normal mucosa (56 images, 40.3%) was classified using the application programming interface (API) of GPT4.0. The same set of images was also classified by CLE experts (two surgeons and one pathologist), who were blinded to the histology. Diagnostic metrics, the reliability of GPT and inter-rater reliability were assessed.

RESULTS

Overall accuracy of the GPT model was 71.2%, the intra-rater agreement was κ = 0.837, indicating an almost perfect agreement across the three runs of GPT-generated results. Human experts achieved an accuracy of 88.5% with a substantial level of agreement (κ = 0.773).

CONCLUSIONS

Though limited to a specific clinical framework, patient and image set, this study sheds light on some previously unexplored diagnostic capabilities of large language models using few-shot prompting. It suggests the model`s ability to extrapolate information and classify CLE images with minimal example data. Whether future versions of the model can achieve clinically relevant diagnostic accuracy, especially in uncurated data sets, remains to be investigated.

The Use of Confocal Laser Endomicroscopy in Diagnosing Barrett’s Esophagus and Esophageal Adenocarcinoma

Confocal laser endomicroscopy (CLE) is a diagnostic technique that enables real-time microscopic imaging during microscopic examination and evaluation of epithelial structures with 1000-fold magnification. CLE can be used in the diagnosis of various pathologies, in pneumology, and in urology, and it is very widely utilized in gastroenterology, most importantly in the diagnosis of Barrett’s esophagus (BE), esophageal adenocarcinoma (EAC), biliary strictures, and cystic pancreatic lesions. A literature search was made in MEDLINE/PubMed and Google Scholar databases while focusing on diagnostics using CLE of BE and EAC. We then examined randomized and observational studies, systematic reviews, and meta-analyses relating to the utilization of CLE in BE and EAC diagnostics. Here, we discuss whether CLE can be a suitable diagnostic method for surveillance of BE. Even though many studies have proven that CLE increases diagnostic accuracy in detecting neoplastic transformation of BE, CLE is still not used as a standard diagnostic tool in BE surveillance due to a deficiency of scientific evidence. More studies and data are needed if CLE is to find a place as a new technique in BE surveillance.