Valizadeh Parya, Jannatdoust Payam, Ghadimi Delaram J, Bagherieh Sara, Hassankhani Amir, Amoukhteh Melika, Adli Paniz, Gholamrezanezhad Ali
School of Medicine, Tehran University of Medical Sciences, Tehran, Iran.
School of Medicine, Shahid Beheshti University of Medical Sciences, Tehran, Iran.
Clin Imaging. 2025 Mar;119:110392. doi: 10.1016/j.clinimag.2024.110392. Epub 2024 Dec 24.
Thyroid cancer, a common endocrine malignancy, has seen increasing incidence, making lymph node metastasis (LNM) a critical factor for recurrence and survival. Radiomics and deep learning (DL) advancements offer the potential for improved LNM prediction using CT and MRI, though challenges in diagnostic accuracy remain.
A systematic review and meta-analysis were conducted per established guidelines, with searches across PubMed, Scopus, Web of Science, and Embase up to February 15, 2024. Studies developing CT/MRI-based radiomics and/or DL models for preoperative LNM assessment in thyroid cancer patients were included. Data were extracted and analyzed using R software.
Sixteen studies were analyzed. In internal validation sets, sensitivity was 81.1 % (95 % CI: 75.6 %-85.6 %) and specificity 76.4 % (95 % CI: 68.4 %-82.9 %). Training sets showed a sensitivity of 84.4 % (95 % CI: 81.5 %-87 %) and a specificity of 84.7 % (95 % CI: 74.4 %-91.4 %). The pooled AUC was 86 % for internal validation and 87 % for training. Handcrafted radiomics had a sensitivity of 79.4 % and specificity of 69.2 %, while DL models showed 80.8 % sensitivity and 78.7 % specificity. Subgroup analysis revealed that models for papillary thyroid cancer (PTC) had a pooled specificity of 76.3 %, while those including other or unspecified cancers showed 68.3 % specificity. Despite heterogeneity, significant differences (p = 0.037) were noted between models with and without clinical data.
Radiomics and DL models show promising potential for detecting LNM in thyroid cancer, particularly in PTC. However, study heterogeneity underscores the need for further research to optimize these imaging tools.
甲状腺癌是一种常见的内分泌恶性肿瘤，其发病率呈上升趋势，使得淋巴结转移（LNM）成为复发和生存的关键因素。放射组学和深度学习（DL）的进展为利用CT和MRI改善LNM预测提供了潜力，尽管在诊断准确性方面仍存在挑战。
按照既定指南进行系统评价和荟萃分析，检索截至2024年2月15日的PubMed、Scopus、科学网和Embase。纳入为甲状腺癌患者术前LNM评估开发基于CT/MRI的放射组学和/或DL模型的研究。使用R软件提取和分析数据。
分析了16项研究。在内部验证集中，敏感性为81.1%（95%CI：75.6%-85.6%），特异性为76.4%（95%CI：68.4%-82.9%）。训练集的敏感性为84.4%（95%CI：81.5%-87%），特异性为84.7%（95%CI：74.4%-91.4%）。内部验证的合并AUC为86%，训练的合并AUC为87%。手工制作的放射组学敏感性为79.4%，特异性为69.2%，而DL模型的敏感性为80.8%，特异性为78.7%。亚组分析显示，甲状腺乳头状癌（PTC）模型合并特异性为76.3%，而包括其他或未明确癌症的模型特异性为68.3%。尽管存在异质性，但有临床数据和无临床数据的模型之间存在显著差异（p = 0.037）。
放射组学和DL模型在检测甲状腺癌LNM方面显示出有前景的潜力，尤其是在PTC中。然而，研究的异质性突出了进一步研究以优化这些成像工具的必要性。
