2024/07/07 by Chun-Mei Feng, Feng, Chun-Mei · 5 citations
Computer Science · Medicine · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Handwritten Text Recognition Techniques #Image Retrieval and Classification Techniques #Image and Video Processing (eess.IV) #Radiomics and Machine Learning in Medical Imaging #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2407.05323
openalex publication_date 2024/07/07 · openalex created_date 2024/07/10 · openalex updated_date 2026/07/28
Aside from offering state-of-the-art performance in medical image generation, denoising diffusion probabilistic models (DPM) can also serve as a representation learner to capture semantic information and potentially be used as an image representation for downstream tasks, e.g., segmentation. However, these latent semantic representations rely heavily on labor-intensive pixel-level annotations as supervision, limiting the usability of DPM in medical image segmentation. To address this limitation, we propose an enhanced diffusion segmentation model, called TextDiff, that improves semantic representation through inexpensive medical text annotations, thereby explicitly establishing semantic representation and language correspondence for diffusion models. Concretely, TextDiff extracts intermediate activations of the Markov step of the reverse diffusion process in a pretrained diffusion model on large-scale natural images and learns additional expert knowledge by combining them with complementary and readily available diagnostic text information. TextDiff freezes the dual-branch multi-modal structure and mines the latent alignment of semantic features in diffusion models with diagnostic descriptions by only training the cross-attention mechanism and pixel classifier, making it possible to enhance semantic representation with inexpensive text. Extensive experiments on public QaTa-COVID19 and MoNuSeg datasets show that our TextDiff is significantly superior to the state-of-the-art multi-modal segmentation methods with only a few training samples.