Artificial-Intelligence-Assisted Detection of Metastatic Colorectal Cancer Cells in Ascitic Fluid

Abstract

Simple Summary Ascites cytology serves as a cost-effective and noninvasive primary screening test for metastatic colorectal cancer (CRC). Diagnosing metastatic carcinoma of the peritoneum based on biopsy results is challenging, and analyzing ascitic aspiration cytology shows a limited sensitivity and specificity, along with a high variability between observers. Our study aimed to develop an artificial intelligence (AI) model that enhances pathologists' ability to accurately diagnose metastatic CRC within ascitic fluid, improving the diagnostic accuracy, specificity, and sensitivity. This deep learning approach demonstrated a high accuracy, sensitivity, and specificity in distinguishing between malignant and benign ascites. The findings from this proposed deep learning method hold significant promise for integrating AI into clinical practice to enhance the precision of diagnosing metastatic CRC cells in ascitic fluid.Abstract Ascites cytology is a cost-effective test for metastatic colorectal cancer (CRC) in the abdominal cavity. However, metastatic carcinoma of the peritoneum is difficult to diagnose based on biopsy findings, and ascitic aspiration cytology has a low sensitivity and specificity and a high inter-observer variability. The aim of the present study was to apply artificial intelligence (AI) to classify benign and malignant cells in ascites cytology patch images of metastatic CRC using a deep convolutional neural network. Datasets were collected from The OPEN AI Dataset Project, a nationwide cytology dataset for AI research. The numbers of patch images used for training, validation, and testing were 56,560, 7068, and 6534, respectively. We evaluated 1041 patch images of benign and metastatic CRC in the ascitic fluid to compare the performance of pathologists and an AI algorithm, and to examine whether the diagnostic accuracy of pathologists improved with the assistance of AI. This AI method showed an accuracy, a sensitivity, and a specificity of 93.74%, 87.76%, and 99.75%, respectively, for the differential diagnosis of malignant and benign ascites. The diagnostic accuracy and sensitivity of the pathologist with the assistance of the proposed AI method increased from 86.8% to 90.5% and from 73.3% to 79.3%, respectively. The proposed deep learning method may assist pathologists with different levels of experience in diagnosing metastatic CRC cells of ascites.