Yaofei Duan , Tao Tan , Zhiyuan Zhu , Yuhao Huang , Yuanji Zhang , Rui Gao , Patrick Cheong-Iao Pang , Xinru Gao , Guowei Tao , Xiang Cong , Zhou Li , Lianying Liang , Guangzhi He , Linliang Yin , Xuedong Deng , Xin Yang , Dong Ni
{"title":"FetalFlex: Anatomy-guided diffusion model for flexible control on fetal ultrasound image synthesis","authors":"Yaofei Duan , Tao Tan , Zhiyuan Zhu , Yuhao Huang , Yuanji Zhang , Rui Gao , Patrick Cheong-Iao Pang , Xinru Gao , Guowei Tao , Xiang Cong , Zhou Li , Lianying Liang , Guangzhi He , Linliang Yin , Xuedong Deng , Xin Yang , Dong Ni","doi":"10.1016/j.media.2025.103725","DOIUrl":null,"url":null,"abstract":"<div><div>Fetal ultrasound (US) examinations require the acquisition of multiple planes, each providing unique diagnostic information to evaluate fetal development and screening for congenital anomalies. However, obtaining a thorough, multi-plane annotated fetal US dataset remains challenging, particularly for rare or complex anomalies owing to their low incidence and numerous subtypes. This poses difficulties in training novice radiologists and developing robust AI models, especially for detecting abnormal fetuses. In this study, we introduce a Flexible Fetal US image generation framework (FetalFlex) to address these challenges, which leverages anatomical structures and multimodal information to enable controllable synthesis of fetal US images across diverse planes. Specifically, FetalFlex incorporates a pre-alignment module to enhance controllability and introduces a repaint strategy to ensure consistent texture and appearance. Moreover, a two-stage adaptive sampling strategy is developed to progressively refine image quality from coarse to fine levels. We believe that FetalFlex is the first method capable of generating both in-distribution normal and out-of-distribution abnormal fetal US images, without requiring any abnormal data. Experiments on multi-center datasets demonstrate that FetalFlex achieved state-of-the-art performance across multiple image quality metrics. Comprehensive reader studies further confirms the close alignment of the generated results with expert visual assessments and clinical-level fidelity. Furthermore, synthetic images by FetalFlex significantly improve the performance of six typical deep models in downstream classification and anomaly detection tasks. Lastly, FetalFlex’s anatomy-level controllable generation offers a unique advantage for anomaly simulation and creating paired or counterfactual data at the pixel level. The demo is available at: <span><span>https://dyf1023.github.io/FetalFlex/</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":18328,"journal":{"name":"Medical image analysis","volume":"105 ","pages":"Article 103725"},"PeriodicalIF":11.8000,"publicationDate":"2025-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Medical image analysis","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1361841525002725","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0
Abstract
Fetal ultrasound (US) examinations require the acquisition of multiple planes, each providing unique diagnostic information to evaluate fetal development and screening for congenital anomalies. However, obtaining a thorough, multi-plane annotated fetal US dataset remains challenging, particularly for rare or complex anomalies owing to their low incidence and numerous subtypes. This poses difficulties in training novice radiologists and developing robust AI models, especially for detecting abnormal fetuses. In this study, we introduce a Flexible Fetal US image generation framework (FetalFlex) to address these challenges, which leverages anatomical structures and multimodal information to enable controllable synthesis of fetal US images across diverse planes. Specifically, FetalFlex incorporates a pre-alignment module to enhance controllability and introduces a repaint strategy to ensure consistent texture and appearance. Moreover, a two-stage adaptive sampling strategy is developed to progressively refine image quality from coarse to fine levels. We believe that FetalFlex is the first method capable of generating both in-distribution normal and out-of-distribution abnormal fetal US images, without requiring any abnormal data. Experiments on multi-center datasets demonstrate that FetalFlex achieved state-of-the-art performance across multiple image quality metrics. Comprehensive reader studies further confirms the close alignment of the generated results with expert visual assessments and clinical-level fidelity. Furthermore, synthetic images by FetalFlex significantly improve the performance of six typical deep models in downstream classification and anomaly detection tasks. Lastly, FetalFlex’s anatomy-level controllable generation offers a unique advantage for anomaly simulation and creating paired or counterfactual data at the pixel level. The demo is available at: https://dyf1023.github.io/FetalFlex/.
期刊介绍:
Medical Image Analysis serves as a platform for sharing new research findings in the realm of medical and biological image analysis, with a focus on applications of computer vision, virtual reality, and robotics to biomedical imaging challenges. The journal prioritizes the publication of high-quality, original papers contributing to the fundamental science of processing, analyzing, and utilizing medical and biological images. It welcomes approaches utilizing biomedical image datasets across all spatial scales, from molecular/cellular imaging to tissue/organ imaging.