본문으로 건너뛰기
← 뒤로

GUIDE-US: grade-informed unpaired distillation of encoder knowledge from histopathology to micro-ultrasound.

International journal of computer assisted radiology and surgery 2026

Elghareb T, Willis E, Wilson PFR, To MNN, Abootorabi MM, Jamzad A, Wodlinger B, Mousavi P, Abolmaesumi P

📝 환자 설명용 한 줄

[PURPOSE] Non-invasive grading of prostate cancer (PCa) from micro-ultrasound (micro-US) could expedite triage and guide biopsies toward the most aggressive regions, yet current models struggle to inf

🔬 핵심 임상 통계 (초록에서 자동 추출 — 원문 검증 권장)
  • Sensitivity 60%
  • Specificity 3.5%

이 논문을 인용하기

BibTeX ↓ RIS ↓
APA Elghareb T, Willis E, et al. (2026). GUIDE-US: grade-informed unpaired distillation of encoder knowledge from histopathology to micro-ultrasound.. International journal of computer assisted radiology and surgery. https://doi.org/10.1007/s11548-026-03630-2
MLA Elghareb T, et al.. "GUIDE-US: grade-informed unpaired distillation of encoder knowledge from histopathology to micro-ultrasound.." International journal of computer assisted radiology and surgery, 2026.
PMID 42001367

Abstract

[PURPOSE] Non-invasive grading of prostate cancer (PCa) from micro-ultrasound (micro-US) could expedite triage and guide biopsies toward the most aggressive regions, yet current models struggle to infer tissue micro-structure at coarse imaging resolutions.

[METHODS] We introduce an unpaired histopathology knowledge-distillation strategy that trains a micro-US encoder to emulate the embedding distribution of a pretrained histopathology foundation model, conditioned on International Society of Urological Pathology (ISUP) grades. Training requires no patient-level pairing or image registration, and histopathology inputs are not used at inference.

[RESULTS] Compared to the current state of the art, our approach increases sensitivity to clinically significant PCa (csPCa) at 60% specificity by 3.5% and improves overall sensitivity at 60% specificity by 1.2%.

[CONCLUSION] By enabling earlier and more dependable cancer risk stratification solely from imaging, our method advances clinical feasibility. Source code is available at https://github.com/DeepRCL/GUIDE-US.