Current status of artificial intelligence analysis for the treatment of pancreaticobiliary diseases using endoscopic ultrasonography and endoscopic retrograde cholangiopancreatography

Abstract

Pancreatic and biliary diseases encompass a range of conditions requiring accurate diagnosis for appropriate treatment strategies. This diagnosis relies heavily on imaging techniques like endoscopic ultrasonography and endoscopic retrograde cholangiopancreatography. Artificial intelligence (AI), including machine learning and deep learning, is becoming integral in medical imaging and diagnostics, such as the detection of colorectal polyps. AI shows great potential in diagnosing pancreatobiliary diseases. Unlike machine learning, which requires feature extraction and selection, deep learning can utilize images directly as input. Accurate evaluation of AI performance is a complex task due to varied terminologies, evaluation methods, and development stages. Essential aspects of AI evaluation involve defining the AI's purpose, choosing appropriate gold standards, deciding on the validation phase, and selecting reliable validation methods. AI, particularly deep learning, is increasingly employed in endoscopic ultrasonography and endoscopic retrograde cholangiopancreatography diagnostics, achieving high accuracy levels in detecting and classifying various pancreatobiliary diseases. The AI often performs better than doctors, even in tasks like differentiating benign from malignant pancreatic tumors, cysts, and subepithelial lesions, identifying gallbladder lesions, assessing endoscopic retrograde cholangiopancreatography difficulty, and evaluating the biliary strictures. The potential for AI in diagnosing pancreatobiliary diseases, especially where other modalities have limitations, is considerable. However, a crucial constraint is the need for extensive, high-quality annotated data for AI training. Future advances in AI, such as large language models, promise further applications in the medical field.

Keywords: ERCP; EUS; artificial intelligence; deep learning; pancreas.

FIGURE 1

Data splitting method during artificial intelligence (AI) development and validation. (a) External validation: Split the development data into training data and validation data. External validation data was collected from the cohort independent of the development data (e.g., data from other institutions or data collected after AI development). (b) Split‐sample validation. the collected data were randomly divided into training, validation, and test sets. (c) Temporary validation. All data are divided into development and test data by period. Development data is randomly divided into training and validation data. (d) Internal validation (hold‐out method). All data is randomly divided into training and validation data. (e) Internal validation (k‐fold cross‐validation). k‐fold cross‐validation divides the dataset into k groups. One group is used for validation, while the others are used for training the model. This process is repeated k times, and the results are averaged. (f) Internal validation (leave‐one‐out validation). A model is created by dividing one case of a cohort into a validation group and the others into a training group, and after training validation, the same procedure is repeated so that all data are in the validation group, and the validation result of all cases is the final result.

FIGURE 2

Artificial intelligence image for differential diagnosis of pancreatic masses. Endoscopic ultrasonography image (pseudo papillary neoplasms) is used for the diagnosis of carcinoma by artificial intelligence. The probability of one endoscopic ultrasonography image is expressed in the upper left, and AI diagnoses this lesion as non‐carcinoma.

FIGURE 3

Artificial intelligence image for differential diagnosis of pancreatic cyst. Endoscopic ultrasonography image (intraductal papillary mucinous neoplasms, IPMN) is used for the diagnosis of malignancy by artificial intelligence. The probability of one endoscopic ultrasonography image is expressed in the upper left, and artificial intelligence diagnoses this lesion as malignant.

FIGURE 4

Artificial intelligence image for differential diagnosis of subepithelial lesion. Endoscopic ultrasonography (EUS) image (gastrointestinal stromal tumors, GIST) is used for the differential diagnosis of subepithelial lesions by artificial intelligence. The probability of one EUS image is expressed in the upper left and artificial intelligence diagnoses this lesion as GIST.