Background: Pancreatic cancer is one of the most aggressive cancers, with poor survival rates. Endoscopic ultrasound (EUS) is a key diagnostic modality, but its effectiveness is constrained by operator subjectivity. This study evaluates a Vision Transformer-based deep learning segmentation model for pancreatic tumors. Methods: A segmentation model using the USFM framework with a Vision Transformer backbone was trained and validated with 17,367 EUS images (from two public datasets) in 5-fold cross-validation. The model was tested on an independent dataset of 350 EUS images from another public dataset, manually segmented by radiologists. Preprocessing included grayscale conversion, cropping, and resizing to 512x512 pixels. Metrics included Dice similarity coefficient (DSC), intersection over union (IoU), sensitivity, specificity, and accuracy. Results: In 5-fold cross-validation, the model achieved a mean DSC of 0.651 +/- 0.738, IoU of 0.579 +/- 0.658, sensitivity of 69.8%, specificity of 98.8%, and accuracy of 97.5%. For the external validation set, the model achieved a DSC of 0.657 (95% CI: 0.634-0.769), IoU of 0.614 (95% CI: 0.590-0.689), sensitivity of 71.8%, and specificity of 97.7%. Results were consistent, but 9.7% of cases exhibited erroneous multiple predictions. Conclusions: The Vision Transformer-based model demonstrated strong performance for pancreatic tumor segmentation in EUS images. However, dataset heterogeneity and limited external validation highlight the need for further refinement, standardization, and prospective studies.

翻译：背景：胰腺癌是最具侵袭性的癌症之一，生存率极低。内镜超声（EUS）是一种关键的诊断手段，但其有效性受限于操作者的主观性。本研究评估了一种基于Vision Transformer的深度学习分割模型在胰腺肿瘤分割中的应用。方法：采用以Vision Transformer为骨干网络的USFM框架构建分割模型，使用来自两个公共数据集的17,367张EUS图像进行5折交叉验证训练与验证。模型在一个独立的测试集（来自另一公共数据集、由放射科医师手动分割的350张EUS图像）上进行评估。预处理包括灰度转换、裁剪及缩放至512x512像素。评估指标包括Dice相似系数（DSC）、交并比（IoU）、敏感性、特异性及准确率。结果：在5折交叉验证中，模型的平均DSC为0.651 +/- 0.738，IoU为0.579 +/- 0.658，敏感性为69.8%，特异性为98.8%，准确率为97.5%。在外部验证集上，模型取得DSC为0.657（95% CI: 0.634-0.769），IoU为0.614（95% CI: 0.590-0.689），敏感性为71.8%，特异性为97.7%。结果具有一致性，但9.7%的病例出现错误的多重预测。结论：基于Vision Transformer的模型在EUS图像胰腺肿瘤分割中表现出较强的性能。然而，数据集的异质性和有限的外部验证表明，该模型仍需进一步优化、标准化并进行前瞻性研究。