Many of the tissues/lesions in the medical images may be ambiguous. Therefore, medical segmentation is typically annotated by a group of clinical experts to mitigate personal bias. A common solution to fuse different annotations is the majority vote, e.g., taking the average of multiple labels. However, such a strategy ignores the difference between the grader expertness. Inspired by the observation that medical image segmentation is usually used to assist the disease diagnosis in clinical practice, we propose the diagnosis-first principle, which is to take disease diagnosis as the criterion to calibrate the inter-observer segmentation uncertainty. Following this idea, a framework named Diagnosis-First segmentation Framework (DiFF) is proposed. Specifically, DiFF will first learn to fuse the multi-rater segmentation labels to a single ground-truth which could maximize the disease diagnosis performance. We dubbed the fused ground-truth as Diagnosis-First Ground-truth (DF-GT). Then, the Take and Give Model (T&G Model) to segment DF-GT from the raw image is proposed. With the T&G Model, DiFF can learn the segmentation with the calibrated uncertainty that facilitate the disease diagnosis. We verify the effectiveness of DiFF on three different medical segmentation tasks: optic-disc/optic-cup (OD/OC) segmentation on fundus images, thyroid nodule segmentation on ultrasound images, and skin lesion segmentation on dermoscopic images. Experimental results show that the proposed DiFF can effectively calibrate the segmentation uncertainty, and thus significantly facilitate the corresponding disease diagnosis, which outperforms previous state-of-the-art multi-rater learning methods.

中文翻译：

---

通过诊断优先原则校准观察者间分割不确定性


医学图像中的许多组织/病变可能是模棱两可的。因此，医学分割通常由一组临床专家进行注释，以减少个人偏见。融合不同 annotation 的常见解决方案是多数投票，例如，取多个标签的平均值。但是，这种策略忽略了评分者专业知识之间的差异。受临床实践中医学图像分割通常用于辅助疾病诊断的观察启发，我们提出了诊断优先原则，即以疾病诊断为标准来校准观察者间分割的不确定性。遵循这个想法，提出了一个名为诊断优先分割框架 （DiFF） 的框架。具体来说，DiFF 将首先学习将多评分者分割标签融合到单个真实值中，从而最大限度地提高疾病诊断性能。我们将融合的真实数据称为 Diagnosis-First Ground-truth （DF-GT）。然后，提出了从 Raw 图像中分割 DF-GT 的 Take and Give 模型（T&G 模型）。借助 T&G 模型，DiFF 可以学习具有校准不确定性的分割，从而促进疾病诊断。我们验证了 DiFF 在三种不同的医学分割任务中的有效性：眼底图像上的视盘/视杯 （OD/OC） 分割、超声图像上的甲状腺结节分割和皮肤镜图像上的皮肤病变分割。实验结果表明，所提出的 DiFF 可以有效地校准分割不确定性，从而显着促进相应的疾病诊断，优于以前最先进的多评分者学习方法。