Scholarlink

<p>Neoadjuvant therapy (NAT) is an important treatment strategy in surgical oncology, but not all patients benefit equally from it. This systematic review is the first to evaluate artificial intelligence (AI) models predicting NAT response from hematoxylin and eosin (H&amp;E)-stained biopsies slides of solid tumors. A systematic search across five databases was performed following Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, and study quality was assessed using the Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2). Out of 235 studies, 25 met the inclusion criteria and were analyzed regarding their AI methodologies, data modalities, and type of NAT. Most studies reported area under the curve (AUC) ranging from 0.70 to 0.90, and approximately 40% included external validation cohorts. In conclusion, AI models show promise in predicting NAT response from pathological slides, but future work should emphasize standardized data acquisition, patient-level validation, data transparency, and code sharing.</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

Predicting response to neoadjuvant therapy using artificial intelligence on digitized histopathology slides: a systematic review

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月3日

查看全文
  • Soogyeong Shin,
  • Koen Kwakkenbos,
  • Denise E. Hilling,
  • Andrew P. Stubbs,
  • Jifke F. Veenland,
  • Michail Doukas,
  • Cornelis Verhoef,
  • Carolien H. M. van Deurzen,
  • Jan H. von der Thüsen,
  • Farhan Akram

摘要

Neoadjuvant therapy (NAT) is an important treatment strategy in surgical oncology, but not all patients benefit equally from it. This systematic review is the first to evaluate artificial intelligence (AI) models predicting NAT response from hematoxylin and eosin (H&E)-stained biopsies slides of solid tumors. A systematic search across five databases was performed following Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, and study quality was assessed using the Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2). Out of 235 studies, 25 met the inclusion criteria and were analyzed regarding their AI methodologies, data modalities, and type of NAT. Most studies reported area under the curve (AUC) ranging from 0.70 to 0.90, and approximately 40% included external validation cohorts. In conclusion, AI models show promise in predicting NAT response from pathological slides, but future work should emphasize standardized data acquisition, patient-level validation, data transparency, and code sharing.