School of Software, Nanchang University, 235 East Nanjing Road, Nanchang, 330047, China.
School of Computer Information Engineering, Jiangxi Normal University, 99 Ziyang Avenue, Nanchang, 330022, China.
Comput Biol Med. 2024 Nov;182:109182. doi: 10.1016/j.compbiomed.2024.109182. Epub 2024 Sep 27.
Polyp segmentation remains challenging for two reasons: (a) the size and shape of colon polyps are variable and diverse; (b) the distinction between polyps and mucosa is not obvious. To solve the above two challenging problems and enhance the generalization ability of segmentation method, we propose the Localized Transformer Fusion with Balanced Constraint (BCL-Former) for Polyp Segmentation. In BCL-Former, the Strip Local Enhancement module (SLE module) is proposed to capture the enhanced local features. The Progressive Feature Fusion module (PFF module) is presented to make the feature aggregation smoother and eliminate the difference between high-level and low-level features. Moreover, the Tversky-based Appropriate Constrained Loss (TacLoss) is proposed to achieve the balance and constraint between True Positives and False Negatives, improving the ability to generalize across datasets. Extensive experiments are conducted on four benchmark datasets. Results show that our proposed method achieves state-of-the-art performance in both segmentation precision and generalization ability. Also, the proposed method is 5%-8% faster than the benchmark method in training and inference. The code is available at: https://github.com/sjc-lbj/BCL-Former.
息肉分割仍然具有挑战性，原因有二：(a) 结肠息肉的大小和形状是可变和多样的；(b) 息肉和黏膜之间的区别并不明显。为了解决上述两个具有挑战性的问题，并提高分割方法的泛化能力，我们提出了用于息肉分割的带平衡约束的局部化 Transformer 融合（BCL-Former）。在 BCL-Former 中，提出了 Strip Local Enhancement 模块（SLE 模块）来捕获增强的局部特征。提出了 Progressive Feature Fusion 模块（PFF 模块），使特征聚合更加平滑，并消除高低层特征之间的差异。此外，提出了基于 Tversky 的适当约束损失（TacLoss），以实现真阳性和假阴性之间的平衡和约束，从而提高跨数据集的泛化能力。在四个基准数据集上进行了广泛的实验。结果表明，我们提出的方法在分割精度和泛化能力方面都达到了最先进的水平。此外，与基准方法相比，我们提出的方法在训练和推理方面快 5%-8%。代码可在：https://github.com/sjc-lbj/BCL-Former 获得。
