Background/Objectives: Thyroid cancer encompasses distinct histological subtypes with varying biological behavior and treatment implications. Accurate preoperative subtype differentiation remains challenging. Although ultrasound (US) is widely used for thyroid nodule evaluation, qualitative assessment alone is often insufficient to distinguish between papillary (PTC), follicular (FTC), and medullary thyroid carcinoma (MTC).Methods:A retrospective analysis was performed on patients with histologically confirmed PTC, FTC, or MTC. A total of 224 standardized B-mode ultrasound images were analyzed. A set of fully quantitative features was extracted, including morphological characteristics (aspect ratio and perimeter-to-area ratio), internal echotexture (echogenicity and local entropy), boundary sharpness (gradient measures and KL divergence), and structural components (calcifications and cystic areas). Feature extraction was conducted using semi-automatic algorithms implemented in MATLAB. Statistical differences were assessed using the Kruskal–Wallis and Dunn–Šidák tests. A Random Forest classifier was trained and evaluated to determine the discriminatory performance of individual and combined features.Results:Significant differences (p< 0.05) were found among subtypes for key features such as perimeter-to-area ratio, normalized echogenicity, and calcification pattern. The full-feature Random Forest model achieved an overall classification accuracy of 89.3%, with F1-scores of 93.4% for PTC, 85.7% for MTC, and 69.1% for FTC. A reduced model using the top 10 features yielded an even higher accuracy of 91.8%, confirming the robustness and clinical relevance of the selected parameters.Conclusions:Subtype classification of thyroid cancer was effectively performed using quantitative ultrasound features and machine learning. The results suggest that biologically interpretable image-derived metrics may assist in preoperative decision-making and potentially reduce the reliance on invasive diagnostic procedures.
背景/目的：甲状腺癌包含具有不同生物学行为和治疗意义的多种组织学亚型。术前准确区分亚型仍具挑战性。虽然超声被广泛用于甲状腺结节评估，但仅凭定性分析往往不足以区分乳头状癌、滤泡状癌和髓样癌。 方法：对经组织学确诊的乳头状癌、滤泡状癌或髓样癌患者进行回顾性分析。共分析224幅标准化B型超声图像。提取了一套全定量特征，包括形态特征（纵横比和周长面积比）、内部回声结构（回声强度和局部熵值）、边界清晰度（梯度测量和KL散度）以及结构成分（钙化和囊性区域）。特征提取采用MATLAB实现的半自动算法完成。使用克鲁斯卡尔-瓦利斯检验和邓恩-西达克检验评估统计学差异。通过训练和评估随机森林分类器，确定单一特征及组合特征的鉴别性能。 结果：不同亚型在周长面积比、标准化回声强度及钙化模式等关键特征上存在显著差异（p<0.05）。全特征随机森林模型的总体分类准确率达89.3%，其中乳头状癌的F1分数为93.4%，髓样癌为85.7%，滤泡状癌为69.1%。使用前10位特征构建的简化模型获得更高的91.8%准确率，证实了所选参数的稳健性和临床相关性。 结论：通过定量超声特征与机器学习技术，实现了甲状腺癌亚型的有效分类。研究结果表明，具有生物学可解释性的影像衍生指标可能有助于术前决策，并有望减少对侵入性诊断程序的依赖。
肿瘤(癌症)患者之家