Yu Zhen, Nguyen Toan D, Ju Lie, Gal Yaniv, Sashindranath Maithili, Bonnington Paul, Zhang Lei, Mar Victoria, Ge Zongyuan
AIM for Health Lab, Faculty of Information Technology, Monash University, Melbourne, VIC, Australia.
e-Research center, Monash University, Melbourne, VIC, Australia.
NPJ Digit Med. 2025 Jan 14;8(1):26. doi: 10.1038/s41746-024-01395-z.
Traditional disease classification models often disregard the clinical significance of misclassifications and lack interpretability. To overcome these challenges, we propose a hierarchical prototypical decision tree (HPDT) for skin lesion classification. HPDT combines prototypical networks and decision trees, leveraging a class hierarchy to guide interpretable predictions from general to specific categories. By incorporating a hierarchy-based distance matrix, the model prioritizes less severe misclassifications while maintaining diagnostic accuracy. Evaluated on a dataset of 235,268 dermoscopic images across 65 conditions, HPDT outperforms flat classifiers and existing hierarchical methods in accuracy, error severity reduction, and interpretability. It also generalizes effectively to unseen classes. These results highlight the value of integrating clinical hierarchies into model design and training to improve diagnostic reliability and decision transparency, demonstrating HPDT's potential for clinical decision support.
传统的疾病分类模型往往忽视错误分类的临床意义且缺乏可解释性。为了克服这些挑战，我们提出了一种用于皮肤病变分类的分层原型决策树（HPDT）。HPDT将原型网络和决策树相结合，利用类层次结构来指导从一般类别到特定类别的可解释预测。通过纳入基于层次结构的距离矩阵，该模型在保持诊断准确性的同时，将不太严重的错误分类作为优先事项。在一个包含65种病症的235,268张皮肤镜图像的数据集上进行评估时，HPDT在准确性、错误严重程度降低和可解释性方面优于平面分类器和现有的分层方法。它还能有效地推广到未见类别。这些结果凸显了将临床层次结构整合到模型设计和训练中以提高诊断可靠性和决策透明度的价值，证明了HPDT在临床决策支持方面的潜力。
