paper-with-me

홈 › Papers

PathLDM: Text conditioned Latent Diffusion Model for Histopathology

2023-09-01 · Srikar Yellapragada, Alexandros Graikos, Prateek Prasanna, Tahsin Kurc, Joel Saltz, Dimitris Samaras

To achieve high-quality results, diffusion models must be trained on large datasets. This can be notably prohibitive for models in specialized domains, such as computational pathology. Conditioning on labeled data is known to help in data-efficient model training. Therefore, histopathology reports, which are rich in valuable clinical information, are an ideal choice as guidance for a histopathology generative model. In this paper, we introduce PathLDM, the first text-conditioned Latent Diffusion Model tailored for generating high-quality histopathology images. Leveraging the rich contextual information provided by pathology text reports, our approach fuses image and textual data to enhance the generation process. By utilizing GPT's capabilities to distill and summarize complex text reports, we establish an effective conditioning mechanism. Through strategic conditioning and necessary architectural enhancements, we achieved a SoTA FID score of 7.64 for text-to-image generation on the TCGA-BRCA dataset, significantly outperforming the closest text-conditioned competitor with FID 30.1.

📄 PDF Abstract BibTeX arXiv:2309.00748

Code (1)

cvlab-stonybrook/pathldm 공식 구현 pytorch

Tasks

Image GenerationmodelText to Image GenerationText-to-Image Generation

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…
Latent Diffusion Model Diffusion models applied to latent spaces, which are normally built with (Variational) Autoencoders.

Similar Papers 제목 키워드 기반

Graph Conditioned Diffusion for Controllable Histopathology Image Generation

2025-10-08 · Sarah Cechnicka, Matthew Baugh, Weitong Zhang, Mischa Dombrowski 외 arxiv

Recent advances in Diffusion Probabilistic Models (DPMs) have set new standards in high-quality image synthesis. Yet, controlled generation remains challenging, particularly in sensitive areas such as medical imaging. Me…

Image Generation

Improving text-conditioned latent diffusion for cancer pathology

2024-12-09 · Aakash Madhav Rao, Debayan Gupta

The development of generative models in the past decade has allowed for hyperrealistic data synthesis. While potentially beneficial, this synthetic data generation process has been relatively underexplored in cancer hist…

GPUSynthetic Data Generation

F2FLDM: Latent Diffusion Models with Histopathology Pre-Trained Embeddings for Unpaired Frozen Section to FFPE Translation

2024-04-19 · Man M. Ho, Shikha Dubey, Yosep Chong, Beatrice Knudsen 외

The Frozen Section (FS) technique is a rapid and efficient method, taking only 15-30 minutes to prepare slides for pathologists' evaluation during surgery, enabling immediate decisions on further surgical interventions. …

DenoisingDiagnosticGenerative Adversarial Network

Co-synthesis of Histopathology Nuclei Image-Label Pairs using a Context-Conditioned Joint Diffusion Model

2024-07-19 · Seonghui Min, Hyun-Jic Oh, Won-Ki Jeong

In multi-class histopathology nuclei analysis tasks, the lack of training data becomes a main bottleneck for the performance of learning-based methods. To tackle this challenge, previous methods have utilized generative …

Gen-SIS: Generative Self-augmentation Improves Self-supervised Learning

2024-12-02 · Varun Belagali, Srikar Yellapragada, Alexandros Graikos, Saarthak Kapse 외

Self-supervised learning (SSL) methods have emerged as strong visual representation learners by training an image encoder to maximize similarity between features of different views of the same image. To perform this view…

Self-Supervised Learning