TumorGen: Boundary-Aware Tumor-Mask Synthesis with Rectified Flow Matching

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Liu, Shengyuan, Chen, Wenting, Zheng, Boyun, Pan, Wentao, Li, Xiang, Yuan, Yixuan
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913867777441792
author Liu, Shengyuan
Chen, Wenting
Zheng, Boyun
Pan, Wentao
Li, Xiang
Yuan, Yixuan
author_facet Liu, Shengyuan
Chen, Wenting
Zheng, Boyun
Pan, Wentao
Li, Xiang
Yuan, Yixuan
contents Tumor data synthesis offers a promising solution to the shortage of annotated medical datasets. However, current approaches either limit tumor diversity by using predefined masks or employ computationally expensive two-stage processes with multiple denoising steps, causing computational inefficiency. Additionally, these methods typically rely on binary masks that fail to capture the gradual transitions characteristic of tumor boundaries. We present TumorGen, a novel Boundary-Aware Tumor-Mask Synthesis with Rectified Flow Matching for efficient 3D tumor synthesis with three key components: a Boundary-Aware Pseudo Mask Generation module that replaces strict binary masks with flexible bounding boxes; a Spatial-Constraint Vector Field Estimator that simultaneously synthesizes tumor latents and masks using rectified flow matching to ensure computational efficiency; and a VAE-guided mask refiner that enhances boundary realism. TumorGen significantly improves computational efficiency by requiring fewer sampling steps while maintaining pathological accuracy through coarse and fine-grained spatial constraints. Experimental results demonstrate TumorGen's superior performance over existing tumor synthesis methods in both efficiency and realism, offering a valuable contribution to AI-driven cancer diagnostics.
format Preprint
id arxiv_https___arxiv_org_abs_2505_24687
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TumorGen: Boundary-Aware Tumor-Mask Synthesis with Rectified Flow Matching
Liu, Shengyuan
Chen, Wenting
Zheng, Boyun
Pan, Wentao
Li, Xiang
Yuan, Yixuan
Image and Video Processing
Computer Vision and Pattern Recognition
Tumor data synthesis offers a promising solution to the shortage of annotated medical datasets. However, current approaches either limit tumor diversity by using predefined masks or employ computationally expensive two-stage processes with multiple denoising steps, causing computational inefficiency. Additionally, these methods typically rely on binary masks that fail to capture the gradual transitions characteristic of tumor boundaries. We present TumorGen, a novel Boundary-Aware Tumor-Mask Synthesis with Rectified Flow Matching for efficient 3D tumor synthesis with three key components: a Boundary-Aware Pseudo Mask Generation module that replaces strict binary masks with flexible bounding boxes; a Spatial-Constraint Vector Field Estimator that simultaneously synthesizes tumor latents and masks using rectified flow matching to ensure computational efficiency; and a VAE-guided mask refiner that enhances boundary realism. TumorGen significantly improves computational efficiency by requiring fewer sampling steps while maintaining pathological accuracy through coarse and fine-grained spatial constraints. Experimental results demonstrate TumorGen's superior performance over existing tumor synthesis methods in both efficiency and realism, offering a valuable contribution to AI-driven cancer diagnostics.
title TumorGen: Boundary-Aware Tumor-Mask Synthesis with Rectified Flow Matching
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.24687