Haofei Song

Haofei Song

Auto-generated profile, based on publicly available information

Haofei Song

East China Normal University

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 April 2024 in IEEE Transactions on Medical Imaging
Verified
Journal Article
Closed access
HSHaofei Song
Haofei Song
XMXintian Mao
Xintian Mao
JYJing Yu
Jing Yu
Qingli LiQingli Li
Qingli Li
Yan WangYan Wang
Yan Wang
Medical imaging is limited by acquisition time and scanning equipment. CT and MR volumes, reconstructed with thicker slices, are anisotropic with high in-plane resolution and low through-plane resolution. We reveal an intriguing phenomenon that due to the mentioned nature of data, performing slice-wise interpolation from the axial view can yield greater benefits than performing super-resolution from other views. Based on this observation, we propose an Inter-Intra-slice Interpolation Network (I 3 Net), which fully explores information from high in-plane resolution and compensates for low through-plane resolution. The through-plane branch supplements the limited information contained in low through-plane resolution from high in-plane resolution and enables continual and diverse feature learning. In-plane branch transforms features to the frequency domain and enforces an equal learning opportunity for all frequency bands in a global context learning paradigm. We further propose a cross-view block to take advantage of the information from all three views online. Extensive experiments on two public datasets demonstrate the effectiveness of I 3 Net, and noticeably outperforms state-of-the-art super-resolution, video frame interpolation and slice interpolation methods by a large margin. We achieve 43.90dB in PSNR, with at least 1.14dB improvement under the upscale factor of ×2 on MSD dataset with faster inference.

28 October 2024
Verified
Conference Paper
Open access
SXSiyuan Xu
Siyuan Xu
GLGuannan Li
Guannan Li
HSHaofei Song
Haofei Song
Jiansheng WangJiansheng Wang
Jiansheng Wang
Yan WangYan Wang
Yan Wang
Qingli LiQingli Li
Qingli Li
Immunohistochemistry (IHC) plays a crucial role in understanding disease mechanisms, diagnosing pathology and guiding treatment decisions. The precise analysis heavily depends on accurate nucleus segmentation. However, segmentation is challenging due to significant inter- and intra-nucleus variability in morphology and distribution, stemming from inherent characteristics, imaging techniques, tissue differences and other factors. While current deep learning-based methods have shown promising results, their generalization performance is limited, inevitably requiring specific training data. To address the problem, we propose a novel Ge neral framework for Nucleus Seg mentation in IHC images (GeNSeg-Net). GeNSeg-Net effectively segments nuclei across diverse tissue types and imaging techniques with high variability using a small subset for training. It comprises an enhancement model and a segmentation model. Initially, all nuclei are enhanced to a uniform morphology with distinct features by the enhancement model through generation. The subsequent segmentation task is thereby simplified, leading to higher accuracy. We design a lightweight generator and discriminator to improve both enhancement quality and computational efficiency. Extensive experiments demonstrate the effectiveness of each component within GeNSeg-Net. Compared to existing methods, GeNSeg-Net achieves state-of-the-art (SOTA) segmentation accuracy and generalization performance on both private and public datasets, while maintaining highly competitive processing speed. Code is available at https://github.com/SikangSHU/GeNSeg-Net.

1 September 2025
Verified
Conference Paper
Open access
PDF file
SXSiyuan Xu
Siyuan Xu
HSHaofei Song
Haofei Song
YDYingjiao Deng
Yingjiao Deng
JWJiansheng Wang
Jiansheng Wang
Yan WangYan Wang
Yan Wang
Qingli LiQingli Li
Qingli Li
Histopathological examination primarily relies on hematoxylin and eosin (H&E) and immunohistochemical (IHC) staining. Though IHC provides more crucial molecular information for diagnosis, it is more costly than H&E staining. Stain transfer technology seeks to efficiently generate virtual IHC images from H&E images. While current deep learning-based methods have made progress, they still struggle to maintain pathological and structural consistency across biomarkers without pixel-level aligned reference. To address the problem, we propose an Auxiliary Task supervision-based Stain Transfer method for multi-biomarkers (ATST-Net), which pioneeringly employs human annotation-free masks as ground truth (GT). ATST-Net ensures pathological consistency, structural preservation and style transfer. It automatically annotates H&E masks in a cost-effective manner by utilizing consecutive IHC sections. Multiple auxiliary tasks provide diverse supervisory information on the location and intensity of biomarker expression, ensuring model accuracy and interpretability. We design a pretrained model-based generator to extract deep feature in H&E images, improving generalization performance. Extensive experiments demonstrate the effectiveness of ATST-Net's components. Compared to existing methods, ATST-Net achieves state-of-the-art (SOTA) accuracy on datasets with multiple biomarkers and intensity levels, while also reflecting high practical value. Code is available at https://github.com/SikangSHU/ATST-Net.


22 September 2026
Verified
Book Chapter
Closed access
PDF file
HSHaofei Song
Haofei Song
SXSiyuan Xu
Siyuan Xu
XMXintian Mao
Xintian Mao
SGShaojie Guo
Shaojie Guo
Qingli LiQingli Li
Qingli Li
Yan WangYan Wang
Yan Wang

5 May 2024 in arXiv
Verified
Preprint
Open access
PDF file
HSHaofei Song
Haofei Song
XMXintian Mao
Xintian Mao
JYJing Yu
Jing Yu
Qingli LiQingli Li
Qingli Li
Yan WangYan Wang
Yan Wang
Medical imaging is limited by acquisition time and scanning equipment. CT and MR volumes, reconstructed with thicker slices, are anisotropic with high in-plane resolution and low through-plane resolution. We reveal an intriguing phenomenon that due to the mentioned nature of data, performing slice-wise interpolation from the axial view can yield greater benefits than performing super-resolution from other views. Based on this observation, we propose an Inter-Intra-slice Interpolation Network (I$^3$Net), which fully explores information from high in-plane resolution and compensates for low through-plane resolution. The through-plane branch supplements the limited information contained in low through-plane resolution from high in-plane resolution and enables continual and diverse feature learning. In-plane branch transforms features to the frequency domain and enforces an equal learning opportunity for all frequency bands in a global context learning paradigm. We further propose a cross-view block to take advantage of the information from all three views online. Extensive experiments on two public datasets demonstrate the effectiveness of I$^3$Net, and noticeably outperforms state-of-the-art super-resolution, video frame interpolation and slice interpolation methods by a large margin. We achieve 43.90dB in PSNR, with at least 1.14dB improvement under the upscale factor of $\times$2 on MSD dataset with faster inference. Code is available at https://github.com/DeepMed-Lab-ECNU/Medical-Image-Reconstruction.