This paper presents a new robust loss function, the T-Loss, for medical image segmentation. The proposed loss is based on the negative log-likelihood of the Student-t distribution and can effectively handle outliers in the data by controlling its sensitivity with a single parameter. This parameter is updated during the backpropagation process, eliminating the need for additional computation or prior information about the level and spread of noisy labels. Our experiments show that the T-Loss outperforms traditional loss functions in terms of dice scores on two public medical datasets for skin lesion and lung segmentation. We also demonstrate the ability of T-Loss to handle different types of simulated label noise, resembling human error. Our results provide strong evidence that the T-Loss is a promising alternative for medical image segmentation where high levels of noise or outliers in the dataset are a typical phenomenon in practice. The project website can be found at https://robust-tloss.github.io

翻译：本文提出了一种新的鲁棒损失函数——T-Loss，用于医学图像分割。该损失函数基于学生t分布的负对数似然，通过单个参数控制其敏感性，从而有效处理数据中的异常值。该参数在反向传播过程中自动更新，无需额外计算或事先了解噪声标签的程度与分布。实验表明，在皮肤病变和肺部分割两个公开医学数据集上，T-Loss在骰子系数上优于传统损失函数。我们还展示了T-Loss能够处理模拟人类错误的不同类型标签噪声。结果充分证明，T-Loss是医学图像分割中处理高噪声或异常值（实际中常见现象）的理想替代方案。项目网站详见：https://robust-tloss.github.io