Efficient local cloud-based solution for liver cancer detection using deep learning

Liver cancer is one the most common forms of cancer. As per statistics in 2018 published by the World Health Organization, a quarter of all cancer cases are caused by infections, particularly prevalent in developing countries, including hepatitis B. The mortality rate is higher in liver cancer as compared to other types of cancer. Quick and reliable diagnosis tools are of paramount importance for detecting and treating liver cancer in the early stage, thus improving the likely course of a medical condition of patient. The authors have developed a cloud-based solution for liver tumour segmentation, classification, and detection in CT images based on GoogleNet architecture of convolutional neural network. The experiment is carried out with training and test sets derived from TCIA repository. The results yield 96.7% accuracy for classification of tumour cells. GoogleNet architecture is used for implementation. The GoogleNet has 70,000 images in diagnosis of malignant tumor in liver cancer, providing a rich database for testing. The algorithm has been deployed in Azure cloud.