Development of a deep learning-based model to diagnose mixed-type gastric cancer accurately.

Objective: The accurate diagnosis of mixed-type gastric cancer from pathology images presents a formidable challenge for pathologists, given its intricate features and resemblance to other subtypes of gastric cancer. Artificial Intelligence has the potential to overcome this hurdle. This study aimed to leverage deep machine learning techniques to establish a precise and efficient diagnostic approach for this cancer type which can also predict the metastatic risk using two software, U-Net and QuPath, which have not been trialled in gastric cancers.

Methods: A U-Net neural network was trained to recognise, and segment differentiated components from 186 pathology images of mixed-type gastric cancer. Undifferentiated components in the same images were annotated using the open-source pathology imaging software QuPath. The outcomes from U-Net and QuPath were used to calculate the ratios of differentiation/undifferentiated components which were correlated to lymph node metastasis.

Results: The models established by U-Net recognised ∼91% of the regions of interest, with precision, recall, and F1 values of 90.2%, 90.9% and 94.6%, respectively, indicating a high level of accuracy and reliability. Furthermore, the receiver operating characteristic curve analysis showed an area under the cure of 91%, indicating good performance. A bell-curve correlation between the differentiated/undifferentiated ratio and lymphatic metastasis was found (highest risk between 0.683 and 1.03), which is paradigm-shifting.

Conclusion: U-Net and QuPath exhibit promising accuracy in the identification of differentiated and undifferentiated components in mixed-type gastric cancer, as well as paradigm-shifting prediction of metastasis. These findings bring us one step closer to their potential clinical application.