eess.IVNov 6, 2026

Frequency-consistent synthesis and selective transfer for medical image analysis

Authors: Zhuhui Wang, Jianwei Zuo, Xin Peng, Kai Zhong, Xuliang Deng, Jiajia Luo

Organizations: Institute of Medical Technology, Peking University Health Science Center, Beijing, 100191, China. · Biomedical Engineering Department, Institute of Advanced Clinical Medicine, Peking University, Beijing, 100191, China. · Department of Oral and Maxillofacial Surgery, Peking University School and Hospital of Stomatology, Beijing, 100081, China. · National Clinical Research Center for Oral Diseases, National Engineering Laboratory for Digital and Material Technology of Stomatology, Beijing Key Laboratory of Digital Stomatology, Beijing, 100081, China. · 

Abstract

Complementary imaging is not always available, and realistic synthesis does not necessarily improve downstream analysis. Here we introduce a training framework linking medical image synthesis to task learning through adaptive frequency consistency and selective feature transfer. Image-specific frequency constraints encourage consistency of structure and detail. Features are transferred only when a teacher using synthetic images achieves a lower task-error score than the student by a task-specific margin on a labelled training sample. Evaluations across five datasets show improved translation fidelity with three adversarial and diffusion-based translators trained without paired supervision, alongside gains in brain-tumour segmentation on tumour-containing slices and lesion centre-point detection. All 105 reported paired comparisons yielded point estimates favouring the proposed methods, including 36 external translation comparisons on post?treatment MRI without retraining. These findings support synthetic modalities as task-oriented complements to acquired scans when complementary imaging is unavailable.

Figures & tables

Explore similar work

CardsList
  1. Posterior Samplings are Missing Modalities Generators for Medical Image Translation

    Jul 21, 2026Jonghun KimMissing-Modality LearningImage-to-Image Translation

  2. Prob-BBDM: a Probabilistic Brownian Bridge Diffusion Model for MRI sequence image-to-image translation

    Jun 23, 2026Martin Valls, Pascal Bourdon, Christine Fernandez-Maloigne +2Image-to-Image TranslationMagnetic Resonance Imaging

  3. Cross Modality Image Translation In Medical Imaging Using Generative Frameworks

    May 13, 2026Giulia Romoli, Filippo Ruffini, Francesco Di Feola +20Image-to-Image TranslationMedical Image Modality Translation