CNN in CT Image Segmentation: Beyound Loss Function for Expoliting Ground Truth Images
This work addresses a domain-specific challenge in medical imaging segmentation, offering an incremental improvement over existing methods.
The paper tackles the problem of improving CNN performance in CT image segmentation by exploiting ground truth images beyond loss functions, proposing a method that enforces consistency between feature maps of CNNs trained on ground truth and CT images, and reports that it outperforms competitive methods on two datasets.
Exploiting more information from ground truth (GT) images now is a new research direction for further improving CNN's performance in CT image segmentation. Previous methods focus on devising the loss function for fulfilling such a purpose. However, it is rather difficult to devise a general and optimization-friendly loss function. We here present a novel and practical method that exploits GT images beyond the loss function. Our insight is that feature maps of two CNNs trained respectively on GT and CT images should be similar on some metric space, because they both are used to describe the same objects for the same purpose. We hence exploit GT images by enforcing such two CNNs' feature maps to be consistent. We assess the proposed method on two data sets, and compare its performance to several competitive methods. Extensive experimental results show that the proposed method is effective, outperforming all the compared methods.