Due to its irregular shape and varying contour, pancreas segmentation is a recognized challenge in medical image segmentation. Convolutional neural network (CNN) and Transformer-based networks perform well but have limitations: CNN have constrained receptive fields, and Transformer underutilize image features. This work proposes an improved pancreas segmentation method by combining CNN and Transformer. Point-wise separable convolution was introduced in a stage-wise encoder to extract more features with fewer parameters. A densely connected ensemble decoder enabled multi-scale feature fusion, addressing the structural constraints of skip connections. Consistency terms and contrastive loss were integrated into deep supervision to ensure model accuracy. Extensive experiments on the Changhai and National Institute of Health (NIH) pancreas datasets achieved the highest Dice similarity coefficient (DSC) values of 76.32% and 86.78%, with superiority in other metrics. Ablation studies validated each component's contributions to performance and parameter reduction. Results demonstrate that the proposed loss function smooths training and optimizes performance. Overall, the method outperforms other advanced methods, enhances pancreas segmentation performance, supports physician diagnosis, and provides a reliable reference for future research.
Humans ; Neural Networks, Computer ; Pancreas/diagnostic imaging* ; Image Processing, Computer-Assisted/methods* ; Algorithms ; Deep Learning

A 74-year-old female patient was chronically treated with insulin glargine injection, insulin aspart injection, metformin tablets, and nifedipine controlled-release tablets because of type 2 diabetes mellitus and hypertension. Due to poor blood pressure control, candesartan cilexetil 8 mg orally once daily was added. Five days later, the patient developed myalgia and fatigue. Laboratory tests showed myoglobin >2 000 μg/L, creatine kinase 8 567 U/L, creatine kinase MB 279 U/L, aspartate aminotransferase 273 U/L, lactate dehydrogenase 546 U/L, alpha hydroxybutyrate dehydrogenase 498 U/L, and positive protein and occult blood in urine. Rhabdomyolysis caused by candesartan cilexetil was considered. Then the drug was discontinued and symptomatic treatments such as rehydration, alkalinized urine, and diuretics were given. After 7 days of drug withdrawal, the patient′s symptoms were relieved, and after 10 days of drug withdrawal, the laboratory indexes such as myoglobin, creatine kinase, and aspartate aminotransferase returned to normal.

A 74-year-old female patient was chronically treated with insulin glargine injection, insulin aspart injection, metformin tablets, and nifedipine controlled-release tablets because of type 2 diabetes mellitus and hypertension. Due to poor blood pressure control, candesartan cilexetil 8 mg orally once daily was added. Five days later, the patient developed myalgia and fatigue. Laboratory tests showed myoglobin >2 000 μg/L, creatine kinase 8 567 U/L, creatine kinase MB 279 U/L, aspartate aminotransferase 273 U/L, lactate dehydrogenase 546 U/L, alpha hydroxybutyrate dehydrogenase 498 U/L, and positive protein and occult blood in urine. Rhabdomyolysis caused by candesartan cilexetil was considered. Then the drug was discontinued and symptomatic treatments such as rehydration, alkalinized urine, and diuretics were given. After 7 days of drug withdrawal, the patient′s symptoms were relieved, and after 10 days of drug withdrawal, the laboratory indexes such as myoglobin, creatine kinase, and aspartate aminotransferase returned to normal.