损失函数对黑色素瘤诊断中神经网络性能的影响
On Impact of Loss Function on the Performance of Neural Networks in Melanoma Diagnosis
- Technological University Dublin（都柏林理工大学）
- Research Ireland Centre for Research Training in Machine Learning, ML-Labs（爱尔兰研究中心机器学习研究培训中心，机器学习实验室）
- Dublin City University（都柏林城市大学）
- University College Dublin（都柏林大学学院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本研究探讨不同损失函数对黑色素瘤诊断深度模型性能的影响，发现focal loss能同时兼顾AUC性能与不确定性校准（ECE）。
AI中文摘要：
黑色素瘤是最致命的皮肤癌类型，其早期诊断对患者的生存至关重要。使用深度学习模型的图像分类在黑色素瘤诊断中已显示出有前景的结果。然而，这些模型在诸如SIIM-ISIC黑色素瘤分类数据集等黑色素瘤数据集上的性能因类别不平衡而面临挑战。应对这一挑战的方法之一是使用损失函数修改。在本工作中，我们研究了不同损失函数对深度神经网络性能的影响。我们使用focal loss、logit-adjusted softmax交叉熵（CE）损失和加权softmax CE损失训练了这些网络，并报告了用于评估性能和不确定性校准的不同指标。我们的结果表明，focal loss在AUC方面的性能与在预期校准误差（ECE）方面的不确定性校准之间提供了良好的组合。
英文摘要：
Melanoma is the deadliest type of skin cancer, whose early diagnosis is crucial for patients' survival. Image classification using deep learning models has shown promising results for melanoma diagnosis. However, the performance of these models on the melanoma datasets such as SIIM-ISIC melanoma classification dataset is a challenge due to the class imbalance. One of the methods to deal with this challenge is using loss function modifications. In this work, we have investigated the effect of different loss functions on the performance of deep neural networks. We trained these networks using focal loss, logit-adjusted softmax cross-entropy (CE) loss, and weighted softmax CE loss, and we report different metrics for evaluating performance and uncertainty calibration. Our results suggest that focal loss delivers a good combination of performance in terms of AUC and uncertainty calibration in terms of expected calibration error (ECE) simultaneously.
