跳到正文
原文
Nature 健康护理主题·· 7 天前AI 评分42

Atlas 引导的属性归因排序揭示 C2 骨折分类器的解剖依赖型定位差距

Atlas-guided attribution ranking reveals anatomy-dependent localization gaps in C2 fracture classifiers

AI 导读

一项发表于 Scientific Reports 的研究构建了一个结合多图谱解剖与 Grad-CAM 属性图框架,将二元 C2 骨折分类转化为结构化区域排名。在 RSNA 2022 数据集的 101 例确诊骨折中,Ensemble 检测转定位的 micro-Recall@3 为 0.83;齿状突及椎体–侧块–上关节突复合体检索最可靠,横突、后弓和下关节突检索则减弱或不稳定。

正文

Scientific Reports (2026) Cite this article

We’re sharing this article early to provide faster access to peer-reviewed, accepted research. It is citable and carries a permanent DOI. This version is subject to further edits and will be replaced automatically by the final Version of Record. All legal disclaimers apply.

Abstract

Binary C2 fracture classifiers can identify whether a fracture is present but do not show which part of C2 is fractured. We evaluated a framework that combines detailed C2-specific multi-atlas anatomy with classifier attribution maps to produce regional rankings, without requiring additional model training. Three CT examinations from the RSNA 2022 Cervical Spine Challenge were manually annotated into 16 C2 subregions and used as anatomical atlases. Deformable registration transferred these labels to individual patients. The resulting anatomical maps were combined with Grad-CAM maps from two existing classifiers and their ensemble using Peak-Guided Iterative Region Proposal. Primary localization analysis included 97 examinations classified as positive by at least one classifier; secondary detection-to-localization analysis included all 101 confirmed C2 fracture cases. Three-atlas leave-one-out evaluation of label propagation yielded macro-Dice scores of 0.88 for five anatomical groups and 0.77 for 16 subregions, with weaker agreement for small articular facets. Ensemble mean per-case F1@3 was 0.66 and 0.54, respectively. Ensemble detection-to-localization micro-Recall@3 was 0.83, compared with 0.86 among the 97 detector-positive cases. Odontoid and body–lateral mass–superior articular facet complex fractures were retrieved most reliably; transverse-process, posterior-arch, and pars-inferior-facet retrieval was reduced or variable. This framework converts patient-level fracture predictions into structured anatomical rankings and reveals region-specific weaknesses that are not apparent from patient-level detection performance. These findings suggest opportunities for targeted dataset enrichment and future model refinement.

Funding

The authors declare that no funds, grants, or other support were received for this study.

Author information

Author notes

  1. Ervin Sejdić and Yingming Amy Chen contributed equally as senior authors.

Authors and Affiliations

  1. Department of Electrical and Computer Engineering, University of Toronto, 40 St George St, Toronto, ON, M5S 2E4, Canada

    Zixuan Hu & Ervin Sejdić

  2. Department of Medical Imaging, St Michael’s Hospital, Unity Health Toronto, Toronto, ON, Canada

    Hui Ming Lin, Zakariya Mustafa Khan, Errol Colak & Yingming Amy Chen

  3. Department of Medical Imaging, Faculty of Medicine, University of Toronto, Toronto, ON, Canada

    Taryn Rohringer, Vibeeshan Jegatheeswaran & Errol Colak

  4. Emory University, 201 Dowman Dr, Atlanta, 30322, GA, USA

    Ali Emami

  5. Li Ka Shing Knowledge Institute, St Michael’s Hospital, Unity Health Toronto, Toronto, ON, Canada

    Errol Colak & Christopher D. Witiw

  6. Division of Neurosurgery, Department of Surgery, University of Toronto, Toronto, Canada

    Christopher S. Lozano, Jefferson R. Wilson & Christopher D. Witiw

  7. North York General Hospital, Toronto, ON, Canada

    Ervin Sejdić

Authors

  1. Zixuan Hu
  2. Hui Ming Lin
  3. Taryn Rohringer
  4. Vibeeshan Jegatheeswaran
  5. Zakariya Mustafa Khan
  6. Ali Emami
  7. Errol Colak
  8. Christopher S. Lozano
  9. Jefferson R. Wilson
  10. Christopher D. Witiw
  11. Ervin Sejdić
  12. Yingming Amy Chen

Corresponding author

Correspondence to Zixuan Hu.

Ethics declarations

Ethics approval and informed consent

This study used the publicly available, fully deidentified RSNA 2022 Cervical Spine Fracture Detection Challenge dataset. Ethical approval was obtained by the contributing institutions at the time of data collection, with informed-consent requirements determined by the respective institutional review boards. No additional institutional review board approval or patient consent was required for this secondary analysis.

Figure preparation

All figures were created using Matplotlib (version 3.5.1; https://matplotlib.org/3.5.1/) and Microsoft PowerPoint (version 16.101; https://www.microsoft.com/en-us/microsoft-365/powerpoint).

Use of AI tools

ChatGPT 5.4 (OpenAI, accessed May 01, 2026) was used to refine language and discuss framing in selected sections. All AI-suggested text was reviewed and verified by the authors, who take full responsibility for the manuscript’s content. No AI tool was used for study design, analyses, results, figures, or references.

Competing interests

The authors declare no competing interests.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Hu, Z., Lin, H.M., Rohringer, T. et al. Atlas-guided attribution ranking reveals anatomy-dependent localization gaps in C2 fracture classifiers. Sci Rep (2026). https://doi.org/10.1038/s41598-026-80027-w

Download citation

  • Received: 05 August 2026

  • Accepted: 04 November 2026

  • Published: 13 November 2026

  • DOI: https://doi.org/10.1038/s41598-026-80027-w

Keywords

来源:Nature 健康护理主题 · nature.com