Saved in:
Bibliographic Details
Main Authors: Grabke, Emerson P., Taati, Babak, Haider, Masoom A.
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.10230
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917190357221376
author Grabke, Emerson P.
Taati, Babak
Haider, Masoom A.
author_facet Grabke, Emerson P.
Taati, Babak
Haider, Masoom A.
contents Objective: Latent diffusion models (LDM) could alleviate data scarcity challenges affecting machine learning development for medical imaging. However, medical LDM strategies typically rely on short-prompt text encoders, nonmedical LDMs, or large data volumes. These strategies can limit performance and scientific accessibility. We propose a novel LDM conditioning approach to address these limitations. Methods: We propose Class-Conditioned Efficient Large Language model Adapter (CCELLA), a novel dual-head conditioning approach that simultaneously conditions the LDM U-Net with free-text clinical reports and radiology classification. We also propose a data-efficient LDM pipeline centered around CCELLA and a proposed joint loss function. We first evaluate our method on 3D prostate MRI against state-of-the-art. We then augment a downstream classifier model training dataset with synthetic images from our method. Results: Our method achieves a 3D FID score of 0.025 on a size-limited 3D prostate MRI dataset, significantly outperforming a recent foundation model with FID 0.070. When training a classifier for prostate cancer prediction, adding synthetic images generated by our method during training improves classifier accuracy from 69% to 74% and outperforms classifiers trained on images generated by prior state-of-the-art. Classifier training solely on our method's synthetic images achieved comparable performance to real image training. Conclusion: We show that our method improved both synthetic image quality and downstream classifier performance using limited data and minimal human annotation. Significance: The proposed CCELLA-centric pipeline enables radiology report and class-conditioned LDM training for high-quality medical image synthesis given limited data volume and human data annotation, improving LDM performance and scientific accessibility.
format Preprint
id arxiv_https___arxiv_org_abs_2506_10230
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Leveraging Clinical Text and Class Conditioning for 3D Prostate MRI Generation
Grabke, Emerson P.
Taati, Babak
Haider, Masoom A.
Image and Video Processing
Computer Vision and Pattern Recognition
Objective: Latent diffusion models (LDM) could alleviate data scarcity challenges affecting machine learning development for medical imaging. However, medical LDM strategies typically rely on short-prompt text encoders, nonmedical LDMs, or large data volumes. These strategies can limit performance and scientific accessibility. We propose a novel LDM conditioning approach to address these limitations. Methods: We propose Class-Conditioned Efficient Large Language model Adapter (CCELLA), a novel dual-head conditioning approach that simultaneously conditions the LDM U-Net with free-text clinical reports and radiology classification. We also propose a data-efficient LDM pipeline centered around CCELLA and a proposed joint loss function. We first evaluate our method on 3D prostate MRI against state-of-the-art. We then augment a downstream classifier model training dataset with synthetic images from our method. Results: Our method achieves a 3D FID score of 0.025 on a size-limited 3D prostate MRI dataset, significantly outperforming a recent foundation model with FID 0.070. When training a classifier for prostate cancer prediction, adding synthetic images generated by our method during training improves classifier accuracy from 69% to 74% and outperforms classifiers trained on images generated by prior state-of-the-art. Classifier training solely on our method's synthetic images achieved comparable performance to real image training. Conclusion: We show that our method improved both synthetic image quality and downstream classifier performance using limited data and minimal human annotation. Significance: The proposed CCELLA-centric pipeline enables radiology report and class-conditioned LDM training for high-quality medical image synthesis given limited data volume and human data annotation, improving LDM performance and scientific accessibility.
title Leveraging Clinical Text and Class Conditioning for 3D Prostate MRI Generation
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.10230