This study aims to construct and evaluate a deep learning model, utilizing ultrasound images, to accurately differentiate benign and malignant thyroid nodules. The objective includes visualizing the model’s process for interpretability and comparing its diagnostic precision with a cohort of 80 radiologists. We employed ResNet as the classification backbone for thyroid nodule prediction. The model was trained using 2096 ultrasound images of 655 distinct thyroid nodules. For performance evaluation, an independent test set comprising 100 cases of thyroid nodules was curated. In addition, to demonstrate the superiority of the artificial intelligence (AI) model over radiologists, a Turing test was conducted with 80 radiologists of varying clinical experience. This was meant to assess which group of radiologists’ conclusions were in closer alignment with AI predictions. Furthermore, to highlight the interpretability of the AI model, gradient-weighted class activation mapping (Grad-CAM) was employed to visualize the model’s areas of focus during its prediction process. In this cohort, AI diagnostics demonstrated a sensitivity of 81.67%, a specificity of 60%, and an overall diagnostic accuracy of 73%. In comparison, the panel of radiologists on average exhibited a diagnostic accuracy of 62.9%. The AI’s diagnostic process was significantly faster than that of the radiologists. The generated heat-maps highlighted the model’s focus on areas characterized by calcification, solid echo and higher echo intensity, suggesting these areas might be indicative of malignant thyroid nodules. Our study supports the notion that deep learning can be a valuable diagnostic tool with comparable accuracy to experienced senior radiologists in the diagnosis of malignant thyroid nodules. The interpretability of the AI model’s process suggests that it could be clinically meaningful. Further studies are necessary to improve diagnostic accuracy and support auxiliary diagnoses in primary care settings.

中文翻译：

---

深度学习诊断性能和视觉洞察在超声图像上区分良恶性甲状腺结节

本研究旨在构建和评估深度学习模型，利用超声图像准确区分良性和恶性甲状腺结节。目标包括可视化模型的可解释过程，并将其诊断精度与 80 名放射科医生的队列进行比较。我们采用 ResNet 作为甲状腺结节预测的分类主干。该模型使用 655 个不同甲状腺结节的 2096 张超声图像进行训练。为了进行性能评估，我们策划了一个包含 100 例甲状腺结节病例的独立测试集。此外，为了证明人工智能 (AI) 模型相对于放射科医生的优越性，我们对 80 名具有不同临床经验的放射科医生进行了图灵测试。这是为了评估哪组放射科医生的结论与人工智能预测更接近。此外，为了突出人工智能模型的可解释性，采用梯度加权类激活映射（Grad-CAM）来可视化模型在预测过程中的关注区域。在该队列中，AI 诊断的敏感性为 81.67%，特异性为 60%，总体诊断准确性为 73%。相比之下，放射科医生小组的平均诊断准确率为 62.9%。人工智能的诊断过程明显快于放射科医生的诊断过程。生成的热图突出显示了模型重点关注以钙化、实性回声和较高回声强度为特征的区域，表明这些区域可能预示着恶性甲状腺结节。我们的研究支持这样一种观点，即深度学习可以成为一种有价值的诊断工具，在诊断恶性甲状腺结节时其准确性可与经验丰富的高级放射科医生相媲美。人工智能模型过程的可解释性表明它可能具有临床意义。需要进一步的研究来提高诊断准确性并支持初级保健机构的辅助诊断。