IgCONDA-PET: Weakly-Supervised PET Anomaly Detection using Implicitly-Guided Attention-Conditional Counterfactual Diffusion Modeling -- a Multi-Center, Multi-Cancer, and Multi-Tracer Study

Abstract

Minimizing the need for pixel-level annotated data to train PET lesion detection and segmentation networks is highly desired and can be transformative, given time and cost constraints associated with expert annotations. Current unsupervised or weakly-supervised anomaly detection methods rely on autoencoder or generative adversarial networks (GANs) trained only on healthy data. While these approaches reduce annotation dependency, GAN-based methods are notably more challenging to train than non-GAN alternatives (such as autoencoders) due to issues such as the simultaneous optimization of two competing networks, mode collapse, and training instability. In this paper, we present the weakly-supervised $\text{I}$mplicitly-$\text{g}$uided $\text{CO}$u$\text{N}$terfactual diffusion model for $\text{D}$etecting $\text{A}$nomalies in $\text{PET}$ images (IgCONDA-PET). The solution is developed and validated using PET scans from six retrospective cohorts consisting of a total of 2652 cases (multi-cancer, multi-tracer) containing both local and public datasets (spanning multiple centers). The training is conditioned on image class labels (healthy vs. unhealthy) via attention modules, and we employ implicit diffusion guidance. We perform counterfactual generation which facilitates "unhealthy-to-healthy" domain translation by generating a synthetic, healthy version of an unhealthy input image, enabling the detection of anomalies through the calculated differences. The performance of our method was compared against several other deep learning based weakly-supervised or unsupervised methods as well as traditional methods like 41% SUV${}_{\text{max}}$ thresholding. We also highlight the importance of incorporating attention modules in our network for the detection of small anomalies. The code is publicly available at: https://github.com/ahxmeds/IgCONDA-PET.git.

48 pages, 13 figures, 4 tables

References in corpus (16)

• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Denoising Diffusion Probabilistic Models
• Attention Mechanisms in Computer Vision: A Survey
• Hierarchical Text-Conditional Image Generation with CLIP Latents
• Diffusion Models Beat GANs on Image Synthesis
• Generative Modeling by Estimating Gradients of the Data Distribution
• Classifier-Free Diffusion Guidance
• SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis
• Generative AI for Medical Imaging: extending the MONAI Framework
• Diffusion Causal Models for Counterfactual Estimation
• Evaluation of pseudo-healthy image reconstruction for anomaly detection with deep generative models: Application to brain FDG PET
• Anomaly detection using Diffusion-based methods
• Generalized Dice Focal Loss trained 3D Residual UNet for Automated Lesion Segmentation in Whole-Body FDG PET/CT Images
• Weakly Supervised Anomaly Detection for Chest X-Ray Image
• Head and Neck Tumor Segmentation from [18F]F-FDG PET/CT Images Based on 3D Diffusion Model
• Bridging the Gap: Addressing Discrepancies in Diffusion Model Training for Classifier-Free Guidance

Cited by in corpus (1)

• Comprehensive framework for evaluation of deep neural networks in detection and quantification of lymphoma from PET/CT images: clinical insights, pitfalls, and observer agreement analyses