We are dedicated to cutting-edge research in advancing healthcare through intelligent imaging, fostering academic talent, and driving innovation in biomedical image processing and analysis.
Contact UsOur research group was established in 2025 at Harbin Institute of Technology (Shenzhen). As enthusiasts of interdisciplinary research between computer science and biomedicine, we focus on developing advanced algorithms and integrated tools for facilitating healthcare, particularly in microscopy image processing and its downstream analysis.
Over the years, we have established close collaborative relationships with numerous research institutions both domestically and internationally, achieving a series of breakthroughs in quantitative microscopy and intelligent endoscopy. Our research findings have been published in top international academic journals such as Nature Communications. We are open to any potential corporations.
Feb 2025:
One paper about quantitative microscopy was accepted by Nature Communications!
Jan 2025:
One paper about super-resolution was accepted by ISBI 2025!
Jan 2025:
We started our IBIL group at HITSZ!
In this area, we are committed to improving the quality of fluorescent microscopy, breaking the imaging limitations caused by physical diffraction limits and laser phototoxicity with generative models. Enhanced image can be used to support downstream tasks such as quantitative biology.
Seeing is believing, but we need to describe what we see strictly. Thus we are developing learning-based algorithms for extracting structures in microscopy images. Here "counting" includes not only collecting the number of target cells but also profiling the boundary of cellular contours.
Integrating advanced algorithms of microscopy analysis with existing workflow of biomedical studies is crucial for the value of applied science. We are working closely with interdisciplinary reasearch groups and exploring high- throughput frameworks in IDEA biomedicine.
Authors: Guoye Guan, Zelin Li, Yiming Ma, Pohao Ye, Jianfeng Cao, et al.
Overview: This research revealed signaling associated with cell fate and size asymmetry through cell lineage-resolved embryonic morphological mapping.
Authors: Jianfeng Cao, Bin Duan, Hong Yan
Overview: This study developed methods for reconstructing dense live-cell microscopy images via learning continuous fluorescence fields.
Authors: Jianfeng Cao, Lihan Hu, Guoye Guan, et al.
Overview: This work presented CShaperApp, a tool for extracting and analyzing cellular morphologies of developing Caenorhabditis elegans embryo.
Authors: Jianfeng Cao, Hon-Chi Yip, Yueyao Chen, et al.
Overview: This study presented intelligent surgical workflow recognition for endoscopic submucosal dissection with real-time animal study validation.
Authors: Jianfeng Cao, Guoye Guan, Vincy Wing Sze Ho, et al.
Overview: This research established a morphological atlas of the Caenorhabditis elegans embryo using deep-learning-based 4D segmentation.
Authors: Jianfeng Cao, Ming-Kin Wong, Zhongying Zhao, Hong Yan
Overview: This work introduced 3DMMS, a robust 3D membrane morphological segmentation method for C. elegans embryo analysis.
Research Focus: MRI, EEG, Deep Learning
Contact: 23b952017@stu.hit.edu.cn
Research Focus: Medical Image Analysis, Deep Learning
Contact: little.bie2233@gmail.com
jianfeng13.cao@gmail.com (primary)
caojianfeng@hit.edu.cn