A TransUNet model with an adaptive fuzzy focal loss for medical image segmentation

Segmentation of medical images is a critical step in assisting doctors in making accurate diagnoses and planning appropriate treatments. Deep learning architectures often serve as the basis for computer models used for this task. However, a common challenge faced by segmentation models is class imbalance, which leads to a bias towards classes with a larger number of pixels, resulting in reduced accuracy for the minority-class regions. To address this problem, the α -balanced variant of the focal loss function introduces a α modulation factor that reduces the weight assigned to majority classes and gives greater weight to minority classes. This study proposes the use of a fuzzy inference system to automatically adjust the α factor, rather than maintaining a fixed value as commonly implemented. The adaptive fuzzy focal loss (AFFL) achieves an appropriate adjustment in α by employing fifteen fuzzy rules. To evaluate the effectiveness of AFFL, we implement an encoder-decoder segmentation model based on the UNet and Transformer architectures (AFFL-TransUNet) using the CHAOS dataset. We compare the performance of seven segmentation models implemented using the same data partition and hardware equipment. A statistical analysis, considering the DICE coefficient metric, demonstrates that AFFL-TransUNet outperforms four baseline models and performs comparably to the remaining models. Remarkably, AFFL-TransUNet achieves this high performance while significantly reducing training processing time by 66.31–72.39%. This reduction is attributed to the fuzzy system that effectively adapts the α value of the loss function, stabilizing the model within just a few epochs.