FDFei Dai

Fei Dai

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Fei Dai has a total of 21 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    CausalDiffTab: Mixed-Type Causal-Aware Diffusion for Tabular Data Generation

    by Jia-Chen Zhang, Zheng Zhou, Yu-Jie Xiong, Chun-Ming Xia, Fei Dai

    Training data has been proven to be one of the most critical components in training generative AI. However, obtaining high-quality data remains challenging, with data privacy issues presenting a significant hurdle. To address the need for high-quality data. Synthesize data has emerged as a mainstream solution, demonstrating impressive performance in areas such as images, audio, and video. Generating mixed-type data, especially high-quality tabular data, still faces significant challenges. These primarily include its inherent heterogeneous data types, complex inter-variable relationships, and intricate column-wise distributions. In this paper, we introduce CausalDiffTab, a diffusion model-based generative model specifically designed to handle mixed tabular data containing both numerical and categorical features, while being more flexible in capturing complex interactions among variables. We further propose a hybrid adaptive causal regularization method based on the principle of Hierarchical Prior Fusion. This approach adaptively controls the weight of causal regularization, enhancing the model's performance without compromising its generative capabilities. Comprehensive experiments conducted on seven datasets demonstrate that CausalDiffTab outperforms baseline methods across all metrics. Our code is publicly available at: https://github.com/Godz-z/CausalDiffTab.

  • Aberrant Sylvian Vein Diverticulum and Tegmen Dehiscence–Induced Venous Pulsatile Tinnitus Phenotype Can Be Treated Via Transtemporal Surgery: A Case Report with 4D-Flow Magnetic Resonance Imaging

    by Yue-Lin Hsieh, Xu Liu, Fei Dai, Shenjiang Wang, Xiuli Gao, Deyuan Wen, Wuqing Wang

    Objective: To report the first successful surgical treatment of a rare subtype of venous pulsatile tinnitus (PT) caused by aberrant sylvian vein and tegmen dehiscence (SVTD) with a diverticulum and soft tissue enclosing the middle ear ossicles. Patients: A 35-year-old female participant presented with more than 10-year left-side PT due to SVTD diverticulum. Intervention(s): The participant underwent transtemporal surgery with a lateral minimally invasive approach to the epitympanum and aditus ad antrum after finding SVTD and diverticulum. Main Outcome Measures: Contrast-enhanced CT, various magnetic resonance (MR) techniques, including the 4D-flow MR method, and transcanal recording examinations were utilized. The Tinnitus Handicap Inventory (THI) was employed to quantify the surgical efficacy in treating PT. Results: PT was successfully resolved following resurfacing of the diverticulum located on the medial wall of the epitympanic space, with the patient achieving a THI score of 0. The 4D-flow MR indicated that the mean and largest velocities at the dehiscence area were 20.8 cm/s and 54.9 cm/s, respectively. The main frequency of PT fluctuated below 750 hz. Conclusion: SVTD diverticulum–induced venous PT can be successfully treated via the transtemporal pathway. Additionally, this finding underscores the importance to carefully examine tegmen dehiscence and the exposed vasculature when managing venous PT.


  • Generative Adversarial Registration Network for Multi-Contrast Liver MRI Registration and Added Value to Hepatocellular Carcinoma Segmentation: A Multicentre Study

    by Hang Yu, Shu Wu, Rencheng Zheng, Ruokun Li, Qidong Wang, Caizhong Chen, Fei Dai, Weibo Chen, Chengyan Wang, He Wang

    Diffusion-weighted imaging (DWI) and dynamic contrast-enhanced (DCE) imaging are essential for the diagnosis of hepatocellular carcinoma (HCC) but suffer from severe displacement due to respiratory and cardiac motions. The currently available registration algorithms do not align the multi-contrast liver images satisfactorily, which hinders the efficacy of automatic lesion segmentation and radiomics analysis. We proposed a deep learning-based generative adversarial registration network (GARNET) for multi-contrast liver image registration and explored the added value on HCC lesion segmentation in patients with cirrhosis. The proposed model applied a pre-trained generative adversarial network to synthesize DCE images from DWI and then used diffeomorphic based symmetric image normalization (SyN) algorithm for registration. Furthermore, an attention-based U-net (AU-NET) was used to segment the HCC lesion from registered DWI and DCE images. GARNET was developed and validated on 901 patients collected between January 2013 and February 2021 across five medical centers, including 517 HCC patients, total of 597 HCCs, and every case was interpolated to 32 slices. GARNET achieved the highest liver registration Dice (0.812 ± 0.045) among all comparative methods, and the lowest tumor target registration error (3.470 ± 1.652 mm) for DWI/DCE registrations. In addition, the performance of HCC segmentation was significantly improved when using registered images from GARNET, with Dice improvements from 0.36 ± 0.22 to 0.45 ± 0.22; 0.53 ± 0.25 to 0.58 ± 0.21; and 0.44 ± 0.26 to 0.56 ± 0.19 in three validation centers. Experimental results showed that GARNET significantly improved the liver registration performances among multi-contrast images, thereby improving the further identification and segmentation of HCCs.


  • Open Access

    MAGnitude-Image-to-Complex K-space (MAGIC-K) Net: A Data Augmentation Network for Image Reconstruction

    by Fanwen Wang, Hui Zhang, Fei Dai, Weibo Chen, Chengyan Wang, He Wang

    Deep learning has demonstrated superior performance in image reconstruction compared to most conventional iterative algorithms. However, their effectiveness and generalization capability are highly dependent on the sample size and diversity of the training data. Deep learning-based reconstruction requires multi-coil raw k-space data, which are not collected by routine scans. On the other hand, large amounts of magnitude images are readily available in hospitals. Hence, we proposed the MAGnitude Images to Complex K-space (MAGIC-K) Net to generate multi-coil k-space data from existing magnitude images and a limited number of required raw k-space data to facilitate the reconstruction. Compared to some basic data augmentation methods applying global intensity and displacement transformations to the source images, the MAGIC-K Net can generate more realistic intensity variations and displacements from pairs of anatomical Digital Imaging and Communications in Medicine (DICOM) images. The reconstruction performance was validated in 30 healthy volunteers and 6 patients with different types of tumors. The experimental results demonstrated that the high-resolution Diffusion Weighted Image (DWI) reconstruction benefited from the proposed augmentation method. The MAGIC-K Net enabled the deep learning network to reconstruct images with superior performance in both healthy and tumor patients, qualitatively and quantitatively.