[论文解读] FCB-SwinV2 Transformer for Polyp Segmentation

Kerr Fitzgerald, B.K. Matuszewski|arXiv (Cornell University)|Feb 2, 2023

Colorectal Cancer Screening and Detection被引用 12

一句话总结

这篇论文通过用 SwinV2 Transformer-UNET 替换其 transformer，并对 FCN 做出轻微调整，修改了 FCBFormer，在 Kvasir-SEG 和 CVC-ClinicDB 上实现了最新的息肉分割性能，获得更好的 mDice 分数，并指出数据拆分问题。

ABSTRACT

Polyp segmentation within colonoscopy video frames using deep learning models has the potential to automate the workflow of clinicians. This could help improve the early detection rate and characterization of polyps which could progress to colorectal cancer. Recent state-of-the-art deep learning polyp segmentation models have combined the outputs of Fully Convolutional Network architectures and Transformer Network architectures which work in parallel. In this paper we propose modifications to the current state-of-the-art polyp segmentation model FCBFormer. The transformer architecture of the FCBFormer is replaced with a SwinV2 Transformer-UNET and minor changes to the Fully Convolutional Network architecture are made to create the FCB-SwinV2 Transformer. The performance of the FCB-SwinV2 Transformer is evaluated on the popular colonoscopy segmentation bench-marking datasets Kvasir-SEG and CVC-ClinicDB. Generalizability tests are also conducted. The FCB-SwinV2 Transformer is able to consistently achieve higher mDice scores across all tests conducted and therefore represents new state-of-the-art performance. Issues found with how colonoscopy segmentation model performance is evaluated within literature are also re-ported and discussed. One of the most important issues identified is that when evaluating performance on the CVC-ClinicDB dataset it would be preferable to ensure no data leakage from video sequences occurs during the training/validation/test data partition.

研究动机与目标

• 促使自动化息肉分割以协助早期结直肠癌检测。
• 通过在 FCBFormer 框架中集成 SwinV2 Transformer-UNET 来提升分割性能。
• 评估基准数据集上的泛化性和数据拆分的完整性。

提出的方法

• 将 FCBFormer 中的 transformer 架构替换为 SwinV2 Transformer-UNET。
• 对 Fully Convolutional Network 组件进行轻微修改。
• 在 Kvasir-SEG 和 CVC-ClinicDB 数据集上评估模型。
• 在跨数据集进行泛化测试，并在评估中讨论数据泄露问题。

实验结果

研究问题

• RQ1 SwinV2 Transformer-UNET 的整合是否能提升相对于原始 FCBFormer 的息肉分割性能？
• RQ2 FCB-SwinV2 Transformer 是否在标准的结肠镜分割基准上具有泛化性？
• RQ3 在 CVC-ClinicDB 的评估中，哪些评估陷阱（如数据泄露）会影响报道的性能？
• RQ4 轻微的 FCN 修改如何与基于 transformer 的分割在本任务中相互作用？

主要发现

• FCB-SwinV2 Transformer 在所测试的基准上始终取得比以往方法更高的 mDice 分数。
• 根据报道的指标，该模型在 Kvasir-SEG 和 CVC-ClinicDB 上展示了业界领先的性能。
• 泛化测试支持跨数据集的稳健性能。
• 该研究识别并讨论了评估问题，包括 CVC-ClinicDB 评估中的潜在数据泄露。