Ultrasound Liver Fibrosis Diagnosis using Multi-indicator guided Deep Neural Networks
This work addresses the need for accurate and interpretable liver fibrosis diagnosis in patients with chronic hepatitis B, representing a domain-specific incremental improvement.
The paper tackles the problem of automatically predicting liver fibrosis stages from ultrasound images by introducing a deep learning framework that leverages multiple ultrasound images and an indicator-guided learning mechanism, achieving a state-of-the-art accuracy of 65.6%, which is 20% higher than previous best methods.
Accurate analysis of the fibrosis stage plays very important roles in follow-up of patients with chronic hepatitis B infection. In this paper, a deep learning framework is presented for automatically liver fibrosis prediction. On contrary of previous works, our approach can take use of the information provided by multiple ultrasound images. An indicator-guided learning mechanism is further proposed to ease the training of the proposed model. This follows the workflow of clinical diagnosis and make the prediction procedure interpretable. To support the training, a dataset is well-collected which contains the ultrasound videos/images, indicators and labels of 229 patients. As demonstrated in the experimental results, our proposed model shows its effectiveness by achieving the state-of-the-art performance, specifically, the accuracy is 65.6%(20% higher than previous best).