Liver bile-duct cancer is also called as cholangio- carcinoma that stands a significant global health hazard, due of its low 5-year survival rate that is about (2-24%). So Precise and prompt diagnoses is vital in order to improve patient diagnosis and increase survival rates. Hyperspectral imaging (HSI) offers a promising avenue for improving liver cancer diagnosis due to its ability to capture detailed continuous spectral plus spatial information that is beyond the visible range of the human eye. Classifying cholangiocarcinoma through HSI is complex because of its high dimensionality. To solve this,a network called as MedisawHSI is introduced in this article. Inspired from Jigsaw HSI that demonstrates superior performance compared to other Neural Networks. In this article we present Medisaw-based clas- sification involves dividing the hyperspectral image into smaller non – overlapping patches, which are then classified individually based on their spectral characteristics. Results demonstrate that we have achieved better results in comparison with the literature. This will help the surgeons in image – guided surgery, ultimately reducing the burden of liver cancer on global healthcare systems.