Class Distance Weighted Cross-Entropy Loss for Ulcerative Colitis Severity Estimation
This work addresses the challenge of ordinal regression in medical imaging for ulcerative colitis severity estimation, offering an incremental improvement over existing methods.
The authors tackled the problem of ulcerative colitis severity estimation by proposing a novel loss function, class distance weighted cross-entropy (CDW-CE), which respects ordinal class relationships; experimental results show that models trained with CDW-CE outperform those using conventional categorical cross-entropy and other ordinal regression loss functions.
In scoring systems used to measure the endoscopic activity of ulcerative colitis, such as Mayo endoscopic score or Ulcerative Colitis Endoscopic Index Severity, levels increase with severity of the disease activity. Such relative ranking among the scores makes it an ordinal regression problem. On the other hand, most studies use categorical cross-entropy loss function to train deep learning models, which is not optimal for the ordinal regression problem. In this study, we propose a novel loss function, class distance weighted cross-entropy (CDW-CE), that respects the order of the classes and takes the distance of the classes into account in calculation of the cost. Experimental evaluations show that models trained with CDW-CE outperform the models trained with conventional categorical cross-entropy and other commonly used loss functions which are designed for the ordinal regression problems. In addition, the class activation maps of models trained with CDW-CE loss are more class-discriminative and they are found to be more reasonable by the domain experts.