The early detection and accurate histopathological diagnosis of gastric cancer increase the chances of successful treatment. The worldwide shortage of pathologists offers a unique opportunity for the use of artificial intelligence assistance systems to alleviate the workload and increase diagnostic accuracy. Here, we report a clinically applicable system developed at the Chinese PLA General Hospital, China, using a deep convolutional neural network trained with 2,123 pixel-level annotated H&E-stained whole slide images. The model achieves a sensitivity near 100% and an average specificity of 80.6% on a real-world test dataset with 3,212 whole slide images digitalized by three scanners. We show that the system could aid pathologists in improving diagnostic accuracy and preventing misdiagnoses. Moreover, we demonstrate that our system performs robustly with 1,582 whole slide images from two other medical centres. Our study suggests the feasibility and benefits of using histopathological artificial intelligence assistance systems in routine practice scenarios.

No abstract

These authors contributed equally to this work. ⇤ Corresponding authors.Gastric cancer is among the malignant tumors with the highest incidence and mortality rates.Early detection and accurate histopathological diagnosis of gastric cancer are essential factors that can help increase the chances of successful treatment. While the worldwide shortage of pathologists has imposed burdens on the current histopathology service, it also offers a unique opportunity for the use of artificial intelligence assistance systems to alleviate the workload and increase diagnostic accuracy. To the best of our knowledge, there has not been a clinically applicable histopathological assistance system with high accuracy, and can generalize to whole slide images created with diverse digital scanner models from different hospitals. Here, we report the clinically applicable artificial intelligence assistance system developed at the Chinese PLA General Hospital, China, using a deep convolutional neural network trained with 2,123 pixel-level annotated whole slide images. The model achieved a sensitivity near 100% and an average specificity of 80.6% on a real world test dataset, which included 3,212 whole slide images digitalized with three scanner models. We showed that the system would aid pathologists in improving diagnostic accuracy and preventing misdiagnosis. Moreover, we demonstrated that our system could perform robustly with 1,582 whole slide images from two other medical centers. Our study proves the feasibility and benefits of using histopathological artificial intelligence assistance systems in routine practice scenarios.Gastric cancer is the fifth most common cancer worldwide and the third leading cause of cancer death 1 . There is a wide geographic difference in its incidence, with the highest incidence rate in East Asian populations 2 . In China, about 498,000 new cases were diagnosed in 2015, which was the second leading cause of cancer-associated mortality 3 . As early detection, accurate diagnosis and surgical intervention are crucial factors to reduce gastric cancer mortality, robust

No abstract

ObjectivesThe microscopic evaluation of slides has been gradually moving towards all digital in recent years, leading to the possibility for computer-aided diagnosis. It is worthwhile to know the similarities between deep learning models and pathologists before we put them into practical scenarios. The simple criteria of colorectal adenoma diagnosis make it to be a perfect testbed for this study.DesignThe deep learning model was trained by 177 accurately labelled training slides (156 with adenoma). The detailed labelling was performed on a self-developed annotation system based on iPad. We built the model based on DeepLab v2 with ResNet-34. The model performance was tested on 194 test slides and compared with five pathologists. Furthermore, the generalisation ability of the learning model was tested by extra 168 slides (111 with adenoma) collected from two other hospitals.ResultsThe deep learning model achieved an area under the curve of 0.92 and obtained a slide-level accuracy of over 90% on slides from two other hospitals. The performance was on par with the performance of experienced pathologists, exceeding the average pathologist. By investigating the feature maps and cases misdiagnosed by the model, we found the concordance of thinking process in diagnosis between the deep learning model and pathologists.ConclusionsThe deep learning model for colorectal adenoma diagnosis is quite similar to pathologists. It is on-par with pathologists’ performance, makes similar mistakes and learns rational reasoning logics. Meanwhile, it obtains high accuracy on slides collected from different hospitals with significant staining configuration variations.