GUIDE-US: Grade-Informed Unpaired Distillation of Encoder Knowledge from Histopathology to Micro-UltraSound

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Willis, Emma, Elghareb, Tarek, Wilson, Paul F. R., To, Minh Nguyen Nhat, Abootorabi, Mohammad Mahdi, Jamzad, Amoon, Wodlinger, Brian, Mousavi, Parvin, Abolmaesumi, Purang
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912917602959360
author Willis, Emma
Elghareb, Tarek
Wilson, Paul F. R.
To, Minh Nguyen Nhat
Abootorabi, Mohammad Mahdi
Jamzad, Amoon
Wodlinger, Brian
Mousavi, Parvin
Abolmaesumi, Purang
author_facet Willis, Emma
Elghareb, Tarek
Wilson, Paul F. R.
To, Minh Nguyen Nhat
Abootorabi, Mohammad Mahdi
Jamzad, Amoon
Wodlinger, Brian
Mousavi, Parvin
Abolmaesumi, Purang
contents 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 will be publicly released upon publication.
format Preprint
id arxiv_https___arxiv_org_abs_2602_19005
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle GUIDE-US: Grade-Informed Unpaired Distillation of Encoder Knowledge from Histopathology to Micro-UltraSound
Willis, Emma
Elghareb, Tarek
Wilson, Paul F. R.
To, Minh Nguyen Nhat
Abootorabi, Mohammad Mahdi
Jamzad, Amoon
Wodlinger, Brian
Mousavi, Parvin
Abolmaesumi, Purang
Computer Vision and Pattern Recognition
Machine Learning
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 will be publicly released upon publication.
title GUIDE-US: Grade-Informed Unpaired Distillation of Encoder Knowledge from Histopathology to Micro-UltraSound
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2602.19005