EUVIMEDEUVIMED entdecken
Open Access

Interpretable dynamic quantitative vascular morphometry features using SHAP for anti-angiogenic therapy response prediction

Kui Hu iD, Qian Cai iD, Jia Xu iD, Shuangquan Ai iD, Wuling Ou iD, Yulin Liu iD

Science Advances · 24.07.2026 · 12 (30)

DOI: 10.1126/sciadv.aeb3543 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Science Advances, erschienen am 24.07.2026. Verfasst von Kui Hu und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Hubei Cancer Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei, China. Hauptthemen laut MEDLINE: Angiogenesis Inhibitors, Lung Neoplasms, Neovascularization, Pathologic. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: Hubei Provincial Key Technology Foundation of China, Chutian Talents of Hubei, Talent Project of Hubei Cancer Hospital.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Anti-angiogenic therapy benefits vary, with response rates of 40 to 70%, highlighting the need for early biomarkers to identify responders. We developed an automated machine learning framework that uses delta quantitative vascular morphometry features from standard contrast-enhanced CT to evaluate treatment response. This workflow combines automated tumor and vessel segmentation with feature extraction from routine scans for clinical use. Shapley additive explanations (SHAP)–based attributions identify key vascular and clinical features, providing meaningful, imaging-visible evidence aligned with therapy targets beyond traditional radiomics. Using baseline and follow-up CTs from 163 patients with lung cancer, we built three models using fivefold cross-validation, with the delta-merge model achieving high accuracy (area under the receiver operating characteristic curve = 0.842 internally, 0.806 externally). SHAP analysis uncovered an “arterial-dominant, venous-adaptive” pattern, where arterial involvement and venous recovery distinguish responders. This automated workflow and visualization support early, imaging-based response assessment and personalized treatment.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Angiogenesis InhibitorsLung NeoplasmsNeovascularization, PathologicHumansRadiomicsTomography, X-Ray ComputedMachine LearningROC CurveTreatment OutcomeFemale

Substanzen

Angiogenesis Inhibitors

Autor:innen und Institutionen

  • Department of Radiology, Hubei Cancer Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei, China.
  • Hubei Key Laboratory of Medical Information Analysis and Tumor Diagnosis & Treatment, Wuhan 430074, China.
  • Thoracic Inner Department I, Hubei Cancer Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei, China.
  • College of Biomedical Engineering, South-Central Minzu University, Wuhan, Hubei, China.

ORCID-Profile: Kui Hu, Qian Cai, Jia Xu, Shuangquan Ai, Wuling Ou, Yulin Liu

Förderung

  • Hubei Provincial Key Technology Foundation of China
  • Chutian Talents of Hubei
  • Talent Project of Hubei Cancer Hospital

Zitieren

APA

Hu, K., Cai, Q., Xu, J., Ai, S., Ou, W., & Liu, Y. (2026). Interpretable dynamic quantitative vascular morphometry features using SHAP for anti-angiogenic therapy response prediction. Science Advances, 12(30). https://doi.org/10.1126/sciadv.aeb3543

Vancouver

Hu K, Cai Q, Xu J, Ai S, Ou W, Liu Y. Interpretable dynamic quantitative vascular morphometry features using SHAP for anti-angiogenic therapy response prediction. Science Advances. 2026;12(30). doi:10.1126/sciadv.aeb3543

BibTeX
@article{Hu2026,
  author = {Hu, Kui and Cai, Qian and Xu, Jia and Ai, Shuangquan and Ou, Wuling and Liu, Yulin},
  title = {Interpretable dynamic quantitative vascular morphometry features using SHAP for anti-angiogenic therapy response prediction},
  journal = {Science Advances},
  year = {2026},
  volume = {12},
  number = {30},
  doi = {10.1126/sciadv.aeb3543}
}
Kostenlos starten →