The results of Olympus’ ongoing joint research programme to create an AI-based pathology diagnostic tool with the potential to streamline pathologists’ workloads were announced at the Japan Society of Digital Pathology Study annual meeting.
The diagnostic tool achieved 100% sensitivity and ≥50% specificity for all gastric biopsy pathology specimens analysed.
The ongoing shortage of pathologists has led to a demand for artificial intelligence (AI)-based pathology diagnostic tools. Olympus, through its Office of Innovation, began a collaboration with the Kure Medical Center and Chugoku Cancer Center in Japan in 2017 to develop an AI-based pathology diagnostic tool. In the initial testing phase, the AI was trained using 368 gastric biopsy pathology slide images.
The second phase of research began in November 2020, where the diagnostic tool was expanded to six hospitals in Japan, with the aim of verifying the versatility and improving the accuracy of the AI tool. Specifically, it was important to test whether or not the tool works correctly on pathology slides that vary in thickness and color. The goal of this programme is to deliver AI pathology diagnosis software that can assist pathologists by 2023.
The AI-based pathology tool uses a convolutional neural network (CNN) optimised to analyse pathology images. This technology enables the tool to identify adenocarcinoma versus non-adenocarcinoma tissue in an image. Once the AI was trained, it was tested using 1200 pathology whole-slide images from the six institutions participating in the study. The AI classified each image as either adenocarcinoma or non-adenocarcinoma. The AI tool was able to achieve 100% sensitivity and ≥50% specificity for slides from all six facilities. The robustness of the results will enable Olympus to pursue commercialisation of the AI tool in the future.
