Computer-aided diagnosis systems (CADs) present valuable second opinions to radiologists in diagnosis. Many studies on thyroid nodules have proposed various CADs to provide a binary result, benignity or malignancy, for doctors, ignoring interpretability of more ultrasonic features that could be more useful. We develop an interpretable CADs (iCADS) that utilizes deep-learning networks’ classification power and interpretability potential of clinical guidelines, like TIRADS, a well-established scale for thyroid nodules. iCADS incorporates a main neural-networks model and six neural-network based interpreters. The outputs of the six interpreters are compared with TIRADS guidelines and the matched result will form a report, more than a benignity or malignancy result, for radiologists. Clinical images of 16,946 thyroid nodules from 5,885 patients were used to train the proposed iCADS. An extra experimental data set containing 501 images were used to test the performance of the model. For better illustrating the assistant ability of iCADS, we also recruited ten junior radiologists to make diagnosis decisions with or without the help of different versions of iCADS. The experiments demonstrated that iCADS can largely improve junior radiologists diagnosis with the help of interpreter strategy. These experiments are also the very first attempt to evaluate the effect of interpretability of deep-learning based CADs in clinical practice. Comparison experiments with other deep-learning based CADs and traditional CADs indicated that the interpreter strategy can easily be combined to other intelligent CADs without the loss of performance. The framework of iCADS can also inspire more research on the development of CADs.

中文翻译：

---

基于临床经验的新型可解释性超声甲状​​腺结节计算机辅助诊断系统

计算机辅助诊断系统 (CAD) 为放射科医生的诊断提供了宝贵的第二意见。许多关于甲状腺结节的研究提出了各种 CAD，以为医生提供二元结果，良性或恶性，忽略可能更有用的更多超声特征的可解释性。我们开发了一种可解释的 CAD (iCADS)，它利用了深度学习网络的分类能力和临床指南的可解释性潜力，例如 TIRADS，这是一种完善的甲状腺结节量表。iCADS 包含一个主要的神经网络模型和六个基于神经网络的解释器。将六名口译员的输出与 TIRADS 指南进行比较，匹配的结果将为放射科医生形成一份报告，不仅仅是良性或恶性结果。来自 5 个国家的 16,946 个甲状腺结节的临床图像，885 名患者被用于训练提议的 iCADS。包含 501 张图像的额外实验数据集用于测试模型的性能。为了更好地展示 iCADS 的辅助能力，我们还招募了 10 名初级放射科医师，在不同版本的 iCADS 的帮助下或不帮助下做出诊断决策。实验表明，iCADS 可以在解释器策略的帮助下极大地改善初级放射科医生的诊断。这些实验也是评估基于深度学习的 CAD 在临床实践中的可解释性效果的第一次尝试。与其他基于深度学习的 CAD 和传统 CAD 的比较实验表明，解释器策略可以轻松地与其他智能 CAD 结合而不会损失性能。