甲状腺结节类型的早期检测和诊断非常重要，因为可以在早期阶段更有效地治疗它们。甲状腺结节的类型一般分为意义未明的异型性/意义未明的滤泡性病变（AUS/FLUS）、良性滤泡性和乳头状滤泡性。 AUS/FLUS 的恶性肿瘤风险通常在 5% 至 15% 之间，而一些研究表明风险高达 25%。如果没有完整的组织学，就很难对结节进行分类，而且这些诊断操作既昂贵又危险。为了最大限度地减少繁重的工作量和误诊，最近开发了各种基于人工智能的决策支持系统。在本研究中，开发了一种新颖的基于人工智能的决策支持系统，用于甲状腺结节类型的自动分割和分类。该系统基于混合深度学习程序，分别执行自动甲状腺结节分割和分类任务。在此框架中，使用一些 U-Net 架构（例如 ResUNet 和 ResUNet）执行分割，并与特征提取和上采样以及 dropout 操作集成，以防止过度拟合。结节分类任务是通过各种深度网络架构（例如 VGG-16、DenseNet121、ResNet-50 和 Inception ResNet-v2）实现的，考虑到一些准确的分类标准，例如交并集（IOU）、Dice 系数、准确度、精度和回忆起来。在分析中，通过拍摄超声图像和人口统计数据，总共纳入了 880 名年龄在 10 岁至 90 岁之间的患者。实验评估表明，ResUNet 表现出了出色的分割效果，获得了出色的评估分数，包括 92.4% 的 dice 系数和 89.7% 的平均 IOU。在使用 UNet 分割的图像上训练的 ResNet-50 和 Inception ResNet-v2 在分类准确率方面取得了较高的评估分数（例如分别为 96.6% 和 95.0%），表现出了更好的性能。此外，ResNet-50 和 Inception ResNet-v2 从 UNet 分割的图像中分类 AUS/FLUS，AUC 分别为 97.0% 和 96.0%。所提出的基于 AI 的决策支持系统提高了 AUS/FLUS 的自动分割性能，并提高了 AUS/FLUS 的自动分割性能。在 ACC、Jaccard 和 DICE 损失方面，它比文献中的可用方法表现出更好的性能。该系统对于放射科医生和外科医生的临床应用也具有巨大的潜力。版权所有 © 2023。由 Elsevier B.V. 出版。

Early detection and diagnosis of thyroid nodule types are important because they can be treated more effectively in their early stages. The types of thyroid nodules are generally stated as atypia of undetermined significance/follicular lesion of undetermined significance (AUS/FLUS), benign follicular, and papillary follicular. The risk of malignancy for AUS/FLUS is typically stated to be between 5 and 15 %, while some studies indicate a risk as high as 25 %. Without complete histology, it is difficult to classify nodules and these diagnostic operations are pricey and risky. To minimize laborious workload and misdiagnosis, recently various AI-based decision support systems have been developed.In this study, a novel AI-based decision support system has been developed for the automated segmentation and classification of the types of thyroid nodules. This system is based on a hybrid deep-learning procedure that makes both an automatic thyroid nodule segmentation and classification tasks, respectively. In this framework, the segmentation is executed with some U-Net architectures such as ResUNet and ResUNet++ integrating with the feature extraction and upsampling with dropout operations to prevent overfitting. The nodule classification task is achieved by various deep nets architecture such as VGG-16, DenseNet121, ResNet-50, and Inception ResNet-v2 considering some accurate classification criteria such as Intersection over Union (IOU), Dice coefficient, accuracy, precision, and recall.In analysis, a total of 880 patients with ages ranging from 10 to 90 years were included by taking the ultrasound images and demographics. The experimental evaluations showed that ResUNet++ demonstrated excellent segmentation outcomes, attaining remarkable evaluation scores including a dice coefficient of 92.4 % and a mean IOU of 89.7 %. ResNet-50 and Inception ResNet-v2 trained over the images segmented with UNets have shown better performance in terms of achieving high evaluation scores for the classification accuracy such as 96.6 % and 95.0 %, respectively. In addition, ResNet-50 and Inception ResNet-v2 classified AUS/FLUS from the images segmented with UNets with AUC=97.0 % and 96.0 %, respectively.The proposed AI-based decision support system improves the automatic segmentation performance of AUS/FLUS and it has shown better performance than available approaches in the literature with respect to ACC, Jaccard and DICE losses. This system has great potential for clinical use by both radiologists and surgeons as well.Copyright © 2023. Published by Elsevier B.V.