Scholarlink

Purpose <p>Distinguishing high-risk intraductal papillary mucinous neoplasms (IPMNs) from low-risk lesions remains a clinical challenge, often resulting in unnecessary procedures due to limited specificity of current methods. While radiomics and deep learning (DL) have been explored for pancreatic cancer, cyst-level malignancy risk stratification of IPMNs remains untapped.</p> Methods <p>Our multi-institutional assessed the feasibility of AI for predicting IPMN dysplasia grade using cyst-level image features using 359 T2-weighted (T2W) MRI images from seven centers. We developed and compared 2D and 3D radiomics-only, DL-only, and radiomics-DL fusion models using expert radiologist scoring as a baseline reference. Model performance was evaluated using held-out test data.</p> Results <p>The radiomics-DL fusion model showed the highest discriminatory ability on the test set AUC of 69.2%, outperforming the radiomics-only model, AUC of 66.5%. Expert accuracy varied widely from 37.4% to 66.7%, and the inter-rater agreement varied as well with weighted Cohen’s kappa coefficients of 0.33–0.67.</p> Conclusion <p>The fusion model, which combines DL with radiomics features from routine T2W MRI, shows promise for objective, cyst-level risk stratification of IPMNs in a multi-center cohort, outperforming radiomics-only models and nearly matching expert radiologists using only T2W and T1-weighted (T1W) sequences. While performance requires improvement for standalone clinical use, this approach offers a scalable, non-invasive method to potentially improve diagnostic accuracy and reduce unnecessary surgical interventions.</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

Multi-center evaluation of radiomics and deep learning to stratify malignancy risk of IPMNs

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年1月12日

查看全文
  • Andrea M Bejar,
  • Maria Jaramillo Gonzalez,
  • Ziliang Hong,
  • Gorkem Durak,
  • Elif Keles,
  • Halil Ertugrul Aktas,
  • Zheyuan Zhang,
  • Hongyi Pan,
  • Zeynep Sue Jozwiak,
  • Fergan Bol,
  • Lili Zhao,
  • Chao Chen,
  • Concetto Spampinato,
  • Alpay Medetalibeyoglu,
  • Sukru Mehmet Erturk,
  • Gulbiz Dagoglu Kartal,
  • Yury Velichko,
  • Emil Agarunov,
  • Ziyue Xu,
  • Sachin Jambawalikar,
  • Ivo G Schoots,
  • Marco J Bruno,
  • Chenchan Huang,
  • Tamas Gonda,
  • Candice Bolan,
  • Frank H Miller,
  • Michael B Wallace,
  • Rajesh N Keswani,
  • Pallavi Tiwari,
  • Ulas Bagci

摘要

Purpose

Distinguishing high-risk intraductal papillary mucinous neoplasms (IPMNs) from low-risk lesions remains a clinical challenge, often resulting in unnecessary procedures due to limited specificity of current methods. While radiomics and deep learning (DL) have been explored for pancreatic cancer, cyst-level malignancy risk stratification of IPMNs remains untapped.

Methods

Our multi-institutional assessed the feasibility of AI for predicting IPMN dysplasia grade using cyst-level image features using 359 T2-weighted (T2W) MRI images from seven centers. We developed and compared 2D and 3D radiomics-only, DL-only, and radiomics-DL fusion models using expert radiologist scoring as a baseline reference. Model performance was evaluated using held-out test data.

Results

The radiomics-DL fusion model showed the highest discriminatory ability on the test set AUC of 69.2%, outperforming the radiomics-only model, AUC of 66.5%. Expert accuracy varied widely from 37.4% to 66.7%, and the inter-rater agreement varied as well with weighted Cohen’s kappa coefficients of 0.33–0.67.

Conclusion

The fusion model, which combines DL with radiomics features from routine T2W MRI, shows promise for objective, cyst-level risk stratification of IPMNs in a multi-center cohort, outperforming radiomics-only models and nearly matching expert radiologists using only T2W and T1-weighted (T1W) sequences. While performance requires improvement for standalone clinical use, this approach offers a scalable, non-invasive method to potentially improve diagnostic accuracy and reduce unnecessary surgical interventions.