Early and highly accurate prediction of colorectal polyps, as an important sign of one of the most dangerous types of cancer, will result in saving more lives. Despite the advancements in colorectal polyp classification, many challenges remain in obtaining an automated polyp prediction system that is able to diagnose the difficult-to-predict polyps accompanied by different features in real scenarios, where the model can handle imbalanced data, label distribution shift, and cross-modality generalization successfully. In this study, we propose Polyp-D2ATL, a novel framework accompanied by a specific training strategy, which mitigates these limitations and effectively predicts the different classes of polyps belonging to the NICE classification. Our extensive experiments on the PICCOLO validation and test sets demonstrate that the proposed Polyp-D2ATL significantly outperforms existing state-of-the-art models across various reliable metrics, achieving an accuracy of 82.38%, a Macro-F1 of 77.49%, and a specificity of 87.47% on the validation set, alongside consistent improvements on the held-out test set which demonstrates the generalization capacity and clinical applicability of the proposed approach.

翻译：摘要：对结直肠息肉——作为最危险癌症类型之一的重要标志——进行早期且高精度预测，将有助于挽救更多生命。尽管结直肠息肉分类技术已取得进展，但在实际场景中构建能够诊断伴随不同特征的难预测息肉、并成功应对数据不平衡、标签分布偏移及跨模态泛化问题的自动化预测系统，仍面临诸多挑战。本研究提出Polyp-D2ATL——一种结合特定训练策略的新型框架，可缓解上述局限性，并有效预测属于NICE分类的不同息肉类别。我们在PICCOLO验证集与测试集上的大量实验表明，所提出的Polyp-D2ATL在多项可靠指标上显著优于现有最优模型：在验证集上实现了82.38%的准确率、77.49%的宏平均F1分数及87.47%的特异性，同时在留出测试集上保持了一致性提升，验证了该方法的泛化能力与临床适用性。