文献速递细胞病理与分子病理神经与头颈病理

多模态卷积神经网络用于甲状腺细胞学分类与诊断

Multi-modal convolutional neural network-based thyroid cytology classification and diagnosis.
PubMed 文献 · Hum Pathol · 2025-07-04

本研究基于超声引导细针穿刺的甲状腺细胞学涂片图像,提出整合细胞学图像与数字超声图像特征的多模态卷积神经网络模型(CI-DUF),并与仅用细胞学图像的模型(CI)比较。回顾性纳入384例患者的825张甲状腺细胞学图像,按8:2分为训练集与测试集。CI-DUF模型AUROC为0.9326,高于CI模型的0.9119,在甲状腺乳头状癌、滤泡性肿瘤、髓样癌和良性病变的细胞学分类中准确率、敏感性和特异性均显著提高。

要点

  • CI-DUF多模态模型在甲状腺细胞学分类中AUROC达0.9326,优于单模态CI模型。
  • 在乳头状癌、滤泡性肿瘤、髓样癌及良性病变分类中,CI-DUF的准确率、敏感性和特异性显著提升。
  • 该模型基于超声引导细针穿刺细胞学图像与数字超声图像特征整合,具临床辅助潜力。

核心结论

  • 整合细胞学图像与数字超声图像特征的多模态CI-DUF模型在甲状腺细胞学诊断中性能优于仅依赖细胞学图像的CI模型。

研究设计与样本

  • 回顾性分析384例患者的825张甲状腺细胞学图像,按8:2比例分为训练集与测试集,训练并评估CI与CI-DUF两种诊断模型。

主要发现

  • CI模型甲状腺细胞学诊断的AUROC为0.9119,CI-DUF模型为0.9326。
  • 与CI模型相比,CI-DUF模型在乳头状癌、滤泡性肿瘤、髓样癌和良性病变的细胞学分类中准确率、敏感性和特异性均显著提高。

关键数值与推荐

  • CI模型AUROC为0.9119,CI-DUF模型AUROC为0.9326,对象为甲状腺细针穿刺细胞学多分类诊断。
  • 数据集为384例患者的825张甲状腺细胞学图像,训练集与测试集按8:2划分。

临床怎么用

  • CI-DUF模型可辅助病理医师提高甲状腺细针穿刺细胞学多分类诊断的准确率、敏感性和特异性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

BACKGROUND: The cytologic diagnosis of thyroid nodules' benign and malignant nature based on cytological smears obtained through ultrasound-guided fine-needle aspiration is crucial for determining subsequent treatment plans. The development of artificial intelligence (AI) can assist pathologists in improving the efficiency and accuracy of cytological diagnoses. We propose a novel diagnostic model based on a network architecture that integrates cytologic images and digital ultrasound image features (CI-DUF) to solve the multi-class classification task of thyroid fine-needle aspiration cytology. We compare this model with a model relying solely on cytologic images (CI) and evaluate its performance and clinical application potential in thyroid cytology diagnosis. METHODS: A retrospective analysis was conducted on 384 patients with 825 thyroid cytologic images. These images were used as a dataset for training the models, which were divided into training and testing sets in an 8:2 ratio to assess the performance of both the CI and CI-DUF diagnostic models. RESULTS: The AUROC of the CI model for thyroid cytology diagnosis was 0.9119, while the AUROC of the CI-DUF diagnostic model was 0.9326. Compared with the CI model, the CI-DUF model showed significantly increased accuracy, sensitivity, and specificity in the cytologic classification of papillary carcinoma, follicular neoplasm, medullary carcinoma, and benign lesions. CONCLUSIONS: The proposed CI-DUF diagnostic model, which intergrates multi-modal information, shows better diagnostic performance than the CI model that relies only on cytologic images, particularly excelling in thyroid cytology classification.

来源:Hum Pathol,查看原文。版权归原作者所有。

引用

  1. Yang D, Li T, Li L, et al. Multi-modal convolutional neural network-based thyroid cytology classification and diagnosis. Hum Pathol. 2025. PMID: 40617519. doi:10.1016/j.humpath.2025.105868

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。