Artificial Intelligence (AI)-based image analysis has immense potential to support diagnostic histopathology, including cancer diagnostics. However, developing supervised AI methods requires large-scale annotated datasets. A potentially powerful solution is to augment training data with synthetic data. Latent diffusion models, which can generate high-quality, diverse synthetic images, are promising. However, the most common implementations rely on detailed textual descriptions, which are not generally available in this domain. This work proposes a method that constructs structured textual prompts from automatically extracted image features. We experiment with the PCam dataset, composed of tissue patches only loosely annotated as healthy or cancerous. We show that including image-derived features in the prompt, as opposed to only healthy and cancerous labels, improves the Fréchet Inception Distance (FID) by 88.6. We also show that pathologists find it challenging to detect synthetic images, with a median sensitivity/specificity of 0.55/0.55. Finally, we show that synthetic data effectively train AI models.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC11241396PMC
http://dx.doi.org/10.3390/diagnostics14131442DOI Listing

Publication Analysis

Top Keywords

latent diffusion
8
diffusion models
8
synthetic data
8
synthetic images
8
healthy cancerous
8
models image-derived
4
image-derived annotations
4
annotations enhanced
4
enhanced ai-assisted
4
ai-assisted cancer
4

Similar Publications

RetinaRegNet: A zero-shot approach for retinal image registration.

Comput Biol Med

January 2025

Department of Electrical and Computer Engineering, University of Florida, Gainesville, FL, 32610, United States; Department of Medicine, University of Florida, Gainesville, FL, 32610, United States; Department of Health Outcomes and Biomedical Informatics, University of Florida, Gainesville, FL, 32610, United States; Intelligent Clinical Care Center, University of Florida, Gainesville, FL, 32610, United States. Electronic address:

Retinal image registration is essential for monitoring eye diseases and planning treatments, yet it remains challenging due to large deformations, minimal overlap, and varying image quality. To address these challenges, we propose RetinaRegNet, a multi-stage image registration model with zero-shot generalizability across multiple retinal imaging modalities. RetinaRegNet begins by extracting image features using a pretrained latent diffusion model.

View Article and Find Full Text PDF

Distribution of Airway Findings in ANCA-Associated Vasculitis: A 20-Year Observational Analysis.

Diagnostics (Basel)

December 2024

Department of Internal Medicine, Division of Rheumatology, Mayo Clinic, Jacksonville, FL 32224, USA.

Pulmonary involvement is commonly observed in anti-neutrophil cytoplasmic antibody (ANCA)-associated vasculitis (AAV), presenting with manifestations such as diffuse alveolar hemorrhage, inflammatory infiltrates, pulmonary nodules, and tracheobronchial disease. We aimed to identify distinct subgroups of tracheobronchial disease patterns in patients with anti-neutrophil cytoplasmic antibody (ANCA)-associated vasculitis (AAV) using latent class analysis (LCA), and to evaluate their clinical characteristics and outcomes. We conducted a retrospective cohort study using electronic medical records of patients aged >18 years diagnosed with AAV and tracheobronchial disease between 1 January 2002 and 6 September 2022.

View Article and Find Full Text PDF

Amyloid PET imaging plays a crucial role in the diagnosis and research of Alzheimer's disease (AD), allowing non-invasive detection of amyloid-β plaques in the brain. However, the low spatial resolution of PET scans limits the accurate quantification of amyloid deposition due to partial volume effects (PVE). In this study, we propose a novel approach to addressing PVE using a latent diffusion model for resolution recovery (LDM-RR) of PET imaging.

View Article and Find Full Text PDF

Understanding cellular responses to external stimuli is critical for parsing biological mechanisms and advancing therapeutic development. High-content image-based assays provide a cost-effective approach to examine cellular phenotypes induced by diverse interventions, which offers valuable insights into biological processes and cellular states. In this paper, we introduce MorphoDiff, a generative pipeline to predict high-resolution cell morphological responses under different conditions based on perturbation encoding.

View Article and Find Full Text PDF

Visual attribution in medical imaging seeks to make evident the diagnostically-relevant components of a medical image, in contrast to the more common detection of diseased tissue deployed in standard machine vision pipelines (which are less straightforwardly interpretable/explainable to clinicians). We here present a novel generative visual attribution technique, one that leverages latent diffusion models in combination with domain-specific large language models, in order to generate normal counterparts of abnormal images. The discrepancy between the two hence gives rise to a mapping indicating the diagnostically-relevant image components.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!