跳至主導覽 跳至搜尋 跳過主要內容

Less is More: Efficient PET/CT Segmentation and Multimodal Prediction of Recurrence-Free Survival and HPV Status in Head and Neck Cancer

  • Lishan Cai
  • , Xing Long Liang
  • , Tianyu Zhang
  • , Jiaju Huang
  • , Tao Tan
  • , Yunchao Yin
  • Amsterdam University Medical Center
  • Netherlands Cancer Institute
  • Radboud University Nijmegen
  • Macao Polytechnic University

研究成果: Conference contribution › 同儕審查

摘要

Accurate delineation of primary head and neck tumors and metastatic lymph nodes on PET/CT is critical for radiotherapy planning and prognostic assessment. Building on this clinical need, the HECKTOR 2025 challenge uses a large multi-centric dataset to provide a comprehensive benchmark for multimodal methods that integrate imaging and clinical information across three key tasks: segmentation of the primary tumor and involved lymph nodes, recurrence-free survival prediction, and HPV status classification. In this study, we (Team MEDAI) present our solutions for all three challenge tasks. For automated tumor segmentation, we employed an ensemble of ten lightweight STU-Net (small) models, achieving efficient and precise delineation of both primary tumors and metastatic lymph nodes. For recurrence-free survival prediction and HPV status classification, we developed a multimodal framework that integrates volumetric PET/CT imaging, lesion masks derived from the segmentation models, and structured clinical variables. Code is available at https://github.com/Liiiii2101/HECKTOR2025-MEDAI. Team: MEDAI.

原文English
主出版品物標題Head and Neck Tumor Lesion Segmentation, Diagnosis and Prognosis - 4th Challenge, HECKTOR 2025, Held in Conjunction with MICCAI 2025, Proceedings
編輯Numan Saeed, Shahad Hardan, Salma Hassan, Mohammad Yaqub
發行者Springer Science and Business Media Deutschland GmbH
頁面85-96
頁數12
ISBN(列印)9783032257659
DOIs
出版品狀態Published - 2026
事件4th 3D Head and Neck Tumor Segmentation in PET/CT Challenge, HECKTOR 2025, which was held in conjunction with the 28th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2026 - Daejeon, Korea, Republic of
持續時間: 23 9月 2026 → 23 9月 2026

出版品系列

名字Lecture Notes in Computer Science
卷16520 LNCS
ISSN(列印)0302-9743
ISSN(電子)1611-3349

Conference

Conference4th 3D Head and Neck Tumor Segmentation in PET/CT Challenge, HECKTOR 2025, which was held in conjunction with the 28th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2026
國家/地區Korea, Republic of
城市Daejeon
期間23/09/26 → 23/09/26

UN SDG

此研究成果有助於以下永續發展目標

  1. Good health and well being
    Good health and well being

指紋

深入研究「Less is More: Efficient PET/CT Segmentation and Multimodal Prediction of Recurrence-Free Survival and HPV Status in Head and Neck Cancer」主題。共同形成了獨特的指紋。

引用此