Scholarlink

Background <p>Radiomics investigation strategies can be applied to head and neck tumours, including lesion segmentation, tumour grading and staging prediction. Texture features from PET/CT radiomics, particularly those reflecting metabolic heterogeneity within the primary tumour, have shown substantial predictive value for lymph node metastasis in oral cancer. Accurate prediction of cervical lymph node metastasis in oral cancer is crucial, as it is the most significant prognostic factor influencing treatment planning and patient survival.</p> Method <p>An extensive search across PubMed, Scopus, and Wiley Online Library, adhering to PRISMA guidelines, was carried out. The present review included 40 studies, of which 33 were included in the meta-analysis of the prediction of lymph node metastasis and tumour grading.</p> Results <p>The pooled sensitivity, specificity and Diagnostic Odds Ratio (DOR) of the AI models for the prediction of LN metastases were 0.86 (95% CI 0.80–0.90), 0.91 (95% CI 0.87–0.93), and 56.58 (95% CI 21.68–91.48), respectively. The pooled sensitivity, specificity and DOR of the AI models for the grading of OSCC were 0.88 (95% CI 0.54–0.98), 0.82 (95% CI 0.76–0.87), and 34.38 (95% CI 24.24–103), respectively.</p> Conclusion <p>To mitigate the elevated misinterpretation rate of lymph node metastasis (LNMs), it is prudent to incorporate ML/DL into the imaging identification of LNMs in oral cancer. Radiomic CT characteristics of oral cancer indicate tumour heterogeneity and can forecast histopathologic attributes. These exploratory investigations suggest that the AI and radiomics prediction framework may function as an additional non-invasive diagnostic tool for oral cancer, enhancing the objectivity and accuracy of tumour staging and grading and providing guidance for future therapies.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Application of artificial intelligence and radiomics in the prediction of lymph node metastasis and tumour grading of oral cancer - a systematic review and meta analysis

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年1月13日

查看全文
  • Khadijah Mohideen,
  • Snehashish Ghosh,
  • Chandrasekaran Krithika,
  • Bhavana Sujana Mulk,
  • Revant Chole,
  • Juhi Chatterjee,
  • Safal Dhungel

摘要

Background

Radiomics investigation strategies can be applied to head and neck tumours, including lesion segmentation, tumour grading and staging prediction. Texture features from PET/CT radiomics, particularly those reflecting metabolic heterogeneity within the primary tumour, have shown substantial predictive value for lymph node metastasis in oral cancer. Accurate prediction of cervical lymph node metastasis in oral cancer is crucial, as it is the most significant prognostic factor influencing treatment planning and patient survival.

Method

An extensive search across PubMed, Scopus, and Wiley Online Library, adhering to PRISMA guidelines, was carried out. The present review included 40 studies, of which 33 were included in the meta-analysis of the prediction of lymph node metastasis and tumour grading.

Results

The pooled sensitivity, specificity and Diagnostic Odds Ratio (DOR) of the AI models for the prediction of LN metastases were 0.86 (95% CI 0.80–0.90), 0.91 (95% CI 0.87–0.93), and 56.58 (95% CI 21.68–91.48), respectively. The pooled sensitivity, specificity and DOR of the AI models for the grading of OSCC were 0.88 (95% CI 0.54–0.98), 0.82 (95% CI 0.76–0.87), and 34.38 (95% CI 24.24–103), respectively.

Conclusion

To mitigate the elevated misinterpretation rate of lymph node metastasis (LNMs), it is prudent to incorporate ML/DL into the imaging identification of LNMs in oral cancer. Radiomic CT characteristics of oral cancer indicate tumour heterogeneity and can forecast histopathologic attributes. These exploratory investigations suggest that the AI and radiomics prediction framework may function as an additional non-invasive diagnostic tool for oral cancer, enhancing the objectivity and accuracy of tumour staging and grading and providing guidance for future therapies.