A Tumour and Liver Automatic Segmentation (ATLAS) Dataset on Contrast-Enhanced Magnetic Resonance Imaging for Hepatocellular Carcinoma

Liver cancer is the sixth most common in world and fourth leading cause of mortality. In unresectable liver cancers, especially hepatocellular carcinoma (HCC), transarterial radioembolisation (TARE) can be considered for treatment. TARE treatment involves a contrast-enhanced magnetic resonance imaging (CE-MRI) exam performed beforehand to delineate tumour(s) order perform dosimetry calculation. Due significant amount time expertise required delineation process, there strong need automation. Unfortunately, lack publicly available CE-MRI datasets with tumour annotations has hindered development fully automatic solutions segmentation. The “Tumour Automatic Segmentation” (ATLAS) dataset that we present consists 90 liver-focused covering entire patients HCC, along segmentation masks. To best our knowledge, ATLAS first public providing HCC annotations. availability this should greatly facilitate automated tools designed optimise which essential planning patients.