Cinepro: Robust Training of Foundation Models for Cancer Detection in Prostate Ultrasound Cineloops

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Harmanani, Mohamed, Jamzad, Amoon, To, Minh Nguyen Nhat, Wilson, Paul F. R., Guo, Zhuoxin, Fooladgar, Fahimeh, Sojoudi, Samira, Gilany, Mahdi, Chang, Silvia, Black, Peter, Leveridge, Michael, Siemens, Robert, Abolmaesumi, Purang, Mousavi, Parvin
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913837736787968
author Harmanani, Mohamed
Jamzad, Amoon
To, Minh Nguyen Nhat
Wilson, Paul F. R.
Guo, Zhuoxin
Fooladgar, Fahimeh
Sojoudi, Samira
Gilany, Mahdi
Chang, Silvia
Black, Peter
Leveridge, Michael
Siemens, Robert
Abolmaesumi, Purang
Mousavi, Parvin
author_facet Harmanani, Mohamed
Jamzad, Amoon
To, Minh Nguyen Nhat
Wilson, Paul F. R.
Guo, Zhuoxin
Fooladgar, Fahimeh
Sojoudi, Samira
Gilany, Mahdi
Chang, Silvia
Black, Peter
Leveridge, Michael
Siemens, Robert
Abolmaesumi, Purang
Mousavi, Parvin
contents Prostate cancer (PCa) detection using deep learning (DL) models has shown potential for enhancing real-time guidance during biopsies. However, prostate ultrasound images lack pixel-level cancer annotations, introducing label noise. Current approaches often focus on limited regions of interest (ROIs), disregarding anatomical context necessary for accurate diagnosis. Foundation models can overcome this limitation by analyzing entire images to capture global spatial relationships; however, they still encounter challenges stemming from the weak labels associated with coarse pathology annotations in ultrasound data. We introduce Cinepro, a novel framework that strengthens foundation models' ability to localize PCa in ultrasound cineloops. Cinepro adapts robust training by integrating the proportion of cancer tissue reported by pathology in a biopsy core into its loss function to address label noise, providing a more nuanced supervision. Additionally, it leverages temporal data across multiple frames to apply robust augmentations, enhancing the model's ability to learn stable cancer-related features. Cinepro demonstrates superior performance on a multi-center prostate ultrasound dataset, achieving an AUROC of 77.1% and a balanced accuracy of 83.8%, surpassing current benchmarks. These findings underscore Cinepro's promise in advancing foundation models for weakly labeled ultrasound data.
format Preprint
id arxiv_https___arxiv_org_abs_2501_12331
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Cinepro: Robust Training of Foundation Models for Cancer Detection in Prostate Ultrasound Cineloops
Harmanani, Mohamed
Jamzad, Amoon
To, Minh Nguyen Nhat
Wilson, Paul F. R.
Guo, Zhuoxin
Fooladgar, Fahimeh
Sojoudi, Samira
Gilany, Mahdi
Chang, Silvia
Black, Peter
Leveridge, Michael
Siemens, Robert
Abolmaesumi, Purang
Mousavi, Parvin
Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
Tissues and Organs
Prostate cancer (PCa) detection using deep learning (DL) models has shown potential for enhancing real-time guidance during biopsies. However, prostate ultrasound images lack pixel-level cancer annotations, introducing label noise. Current approaches often focus on limited regions of interest (ROIs), disregarding anatomical context necessary for accurate diagnosis. Foundation models can overcome this limitation by analyzing entire images to capture global spatial relationships; however, they still encounter challenges stemming from the weak labels associated with coarse pathology annotations in ultrasound data. We introduce Cinepro, a novel framework that strengthens foundation models' ability to localize PCa in ultrasound cineloops. Cinepro adapts robust training by integrating the proportion of cancer tissue reported by pathology in a biopsy core into its loss function to address label noise, providing a more nuanced supervision. Additionally, it leverages temporal data across multiple frames to apply robust augmentations, enhancing the model's ability to learn stable cancer-related features. Cinepro demonstrates superior performance on a multi-center prostate ultrasound dataset, achieving an AUROC of 77.1% and a balanced accuracy of 83.8%, surpassing current benchmarks. These findings underscore Cinepro's promise in advancing foundation models for weakly labeled ultrasound data.
title Cinepro: Robust Training of Foundation Models for Cancer Detection in Prostate Ultrasound Cineloops
topic Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
Tissues and Organs
url https://arxiv.org/abs/2501.12331