Liver cancer (Hepatocellular carcinoma) is one of the most common and fatal cancers. Certain subtypes are associated with poor outcomes, and proper characterisation and early detection are crucial. “Macrotrabecular-massive Hepatocellular carcinoma” (MTM-HCC) is a recently identified such aggressive variant. Presence of thick trabeculae (>6cells; >50% of tumour) is the diagnostic criterion. Pathology is gold standard for diagnosis and serves as important surrogate marker of molecular mutations. Manual microscopic examination of tumour tissue slides is very tedious.

Livpath-AI (Liver Pathology AI) is a machine learning app developed by Vivasvat Rastogi and Shashvat Rastogi, which uses a convolutional neural network for the detection of an aggressive variant of Hepatocellular Carcinoma (Macrotrabecular / MTM HCC) from less aggressive variants (Microtrabecular and Pseudoglandular) using Pathology slide images.

Users can input images through camera or gallery, and an instant output is displayed based on which category the image falls in.