Medical Image Analysis using Deep Relational Learning
This addresses the problem of leveraging relational data in medical imaging for improved segmentation and mosaicing, with incremental advancements in specific domains.
The paper tackles the challenge of using relational information in medical images by proposing two deep relational learning solutions: a context-aware fully convolutional network for segmentation, achieving state-of-the-art results on BraTS2017 and BraTS2018 datasets, and a hierarchical homography estimation network for mosaicing, outperforming other methods on the UCL Fetoscopy Placenta dataset.
In the past ten years, with the help of deep learning, especially the rapid development of deep neural networks, medical image analysis has made remarkable progress. However, how to effectively use the relational information between various tissues or organs in medical images is still a very challenging problem, and it has not been fully studied. In this thesis, we propose two novel solutions to this problem based on deep relational learning. First, we propose a context-aware fully convolutional network that effectively models implicit relation information between features to perform medical image segmentation. The network achieves the state-of-the-art segmentation results on the Multi Modal Brain Tumor Segmentation 2017 (BraTS2017) and Multi Modal Brain Tumor Segmentation 2018 (BraTS2018) data sets. Subsequently, we propose a new hierarchical homography estimation network to achieve accurate medical image mosaicing by learning the explicit spatial relationship between adjacent frames. We use the UCL Fetoscopy Placenta dataset to conduct experiments and our hierarchical homography estimation network outperforms the other state-of-the-art mosaicing methods while generating robust and meaningful mosaicing result on unseen frames.