Analysis of Loss Functions for Colorectal Polyp Segmentation Under Class Imbalance †

Koishiyeva D. Kang J.W. Iliev T. Bissembayev A. Mukasheva A.
2025 Multidisciplinary Digital Publishing Institute (MDPI)

Engineering Proceedings
2025 #104 Issue 1

Class imbalance is a persistent limitation in polyp segmentation, commonly resulting in biased predictions and reduced accuracy in identifying clinically relevant structures. This study systematically evaluated 12 loss functions, including standard, weighted, and compound formulas, applied to colon polyp segmentation using the UNet-VGG16 fixed architecture on the Kvasir-SEG dataset. The encoder was frozen to isolate the effect of loss functions under the same training conditions. A fixed random seed was used in all experiments to ensure reproducibility and control variance during training. The results reveal that the combined loss functions, namely WBCE combined with Dice and Tversky combined with Focal, achieved the top Dice scores of 0.8916 and 0.8917, respectively. Tversky plus Focal also provided the highest sensitivity of 0.8885, and WBCE obtained the best average IoU of 0.8120. Tversky loss showed the lowest error rate of 4.99, indicating stable optimization. These results clarify the influence of loss function selection on segmentation performance in scenarios characterized by considerable class imbalance.

deep learning , image imbalance , loss , optimization , segmentation

Text of the article Перейти на текст статьи

School of Information Technology and Engineering, Kazakh-British Technical University, Almaty, 050000, Kazakhstan
Department of Transportation System Engineering, Korea National University of Transportation, Uiwang-Si, 27469, South Korea
Department of Telecommunication, University of Ruse, Ruse, 7004, Bulgaria

School of Information Technology and Engineering
Department of Transportation System Engineering
Department of Telecommunication

10 лет помогаем публиковать статьи Международный издатель

Книга Публикация научной статьи Волощук 2026 Book Publication of a scientific article 2026