Class Distance Weighted Cross-Entropy Loss for Ulcerative Colitis Severity Estimation

Creative Commons License

Polat G., Ergenc I., KANİ H. T., ÖZEN ALAHDAB Y., ATUĞ Ö., TEMİZEL A.

26th Annual Conference on Medical Image Understanding and Analysis (MIUA), Cambridge, Kanada, 27 - 29 Temmuz 2022, cilt.13413, ss.157-171 identifier identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Cilt numarası: 13413
  • Doi Numarası: 10.1007/978-3-031-12053-4_12
  • Basıldığı Şehir: Cambridge
  • Basıldığı Ülke: Kanada
  • Sayfa Sayıları: ss.157-171
  • Anahtar Kelimeler: Ordinal regression, Ulcerative colitis, Computer-aided diagnosis, Mayo endoscopic score, Deep learning, Medical imaging, VALIDATION
  • Marmara Üniversitesi Adresli: Evet

Özet

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.