Fanxi Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Fanxi Liu has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Anant Madabhushi
Department of Biomedical Engineering, Emory University, Atlanta, GA
4 shared publications - Cheng Lu
Department of Radiology, Guangdong Provincial People’s Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
4 shared publications - Lei Hu
Department of Radiology, Guangdong Provincial People’s Hospital, Guangdong Academy of Medical Sciences, Southern Medical University, Guangzhou, China
4 shared publications - Peng Gao
Department of Pathology, Qilu Hospital, Shandong University, Jinan, China
4 shared publications - Xiongjun Xu
The Third Affiliated Hospital of Sun Yat-Sen University, Guangzhou 510630, P. R. China
4 shared publications - Xiuming Zhang
Department of Pathology, the First Affiliated Hospital, School of Medicine, Zhejiang University, Hangzhou, China
4 shared publications
Latest Publications
- Open Access
- 15 January 2025
- Published by American Association for Cancer Research (AACR)
Data from BEEx Is an Open-Source Tool That Evaluates Batch Effects in Medical Images to Enable Multicenter Studies
The batch effect is a nonbiological variation that arises from technical differences across different batches of data during the data generation process for acquisition-related reasons, such as collection of images at different sites or using different scanners. This phenomenon can affect the robustness and generalizability of computational pathology- or radiology-based cancer diagnostic models, especially in multicenter studies. To address this issue, we developed an open-source platform, Batch Effect Explorer (BEEx), that is designed to qualitatively and quantitatively determine whether batch effects exist among medical image datasets from different sites. A suite of tools was incorporated into BEEx that provide visualization and quantitative metrics based on intensity, gradient, and texture features to allow users to determine whether there are any image variables or combinations of variables that can distinguish datasets from different sites in an unsupervised manner. BEEx was designed to support various medical imaging techniques, including microscopy and radiology. Four use cases clearly demonstrated the ability of BEEx to identify batch effects and validated the effectiveness of rectification methods for batch effect reduction. Overall, BEEx is a scalable and versatile framework designed to read, process, and analyze a wide range of medical images to facilitate the identification and mitigation of batch effects, which can enhance the reliability and validity of image-based studies.Significance: BEEx is a prescreening tool for image-based analyses that allows researchers to evaluate batch effects in multicenter studies and determine their origin and magnitude to facilitate development of accurate AI–based cancer models.
- 15 January 2025
- Published by American Association for Cancer Research (AACR)
Open AccessData from BEEx Is an Open-Source Tool That Evaluates Batch Effects in Medical Images to Enable Multicenter Studies
The batch effect is a nonbiological variation that arises from technical differences across different batches of data during the data generation process for acquisition-related reasons, such as collection of images at different sites or using different scanners. This phenomenon can affect the robustness and generalizability of computational pathology- or radiology-based cancer diagnostic models, especially in multicenter studies. To address this issue, we developed an open-source platform, Batch Effect Explorer (BEEx), that is designed to qualitatively and quantitatively determine whether batch effects exist among medical image datasets from different sites. A suite of tools was incorporated into BEEx that provide visualization and quantitative metrics based on intensity, gradient, and texture features to allow users to determine whether there are any image variables or combinations of variables that can distinguish datasets from different sites in an unsupervised manner. BEEx was designed to support various medical imaging techniques, including microscopy and radiology. Four use cases clearly demonstrated the ability of BEEx to identify batch effects and validated the effectiveness of rectification methods for batch effect reduction. Overall, BEEx is a scalable and versatile framework designed to read, process, and analyze a wide range of medical images to facilitate the identification and mitigation of batch effects, which can enhance the reliability and validity of image-based studies.Significance: BEEx is a prescreening tool for image-based analyses that allows researchers to evaluate batch effects in multicenter studies and determine their origin and magnitude to facilitate development of accurate AI–based cancer models.
- 4 December 2024
- Published by American Association for Cancer Research (AACR) in Cancer Research
- Vol. 85 (2) , 218-230
BEEx Is an Open-Source Tool That Evaluates Batch Effects in Medical Images to Enable Multicenter Studies
The batch effect is a nonbiological variation that arises from technical differences across different batches of data during the data generation process for acquisition-related reasons, such as collection of images at different sites or using different scanners. This phenomenon can affect the robustness and generalizability of computational pathology- or radiology-based cancer diagnostic models, especially in multicenter studies. To address this issue, we developed an open-source platform, Batch Effect Explorer (BEEx), that is designed to qualitatively and quantitatively determine whether batch effects exist among medical image datasets from different sites. A suite of tools was incorporated into BEEx that provide visualization and quantitative metrics based on intensity, gradient, and texture features to allow users to determine whether there are any image variables or combinations of variables that can distinguish datasets from different sites in an unsupervised manner. BEEx was designed to support various medical imaging techniques, including microscopy and radiology. Four use cases clearly demonstrated the ability of BEEx to identify batch effects and validated the effectiveness of rectification methods for batch effect reduction. Overall, BEEx is a scalable and versatile framework designed to read, process, and analyze a wide range of medical images to facilitate the identification and mitigation of batch effects, which can enhance the reliability and validity of image-based studies. Significance: BEEx is a prescreening tool for image-based analyses that allows researchers to evaluate batch effects in multicenter studies and determine their origin and magnitude to facilitate development of accurate AI–based cancer models.
- 4 December 2024
- Published by American Association for Cancer Research (AACR) in Cancer Research
- Vol. 85 (2) , 218-230
BEEx Is an Open-Source Tool That Evaluates Batch Effects in Medical Images to Enable Multicenter Studies
The batch effect is a nonbiological variation that arises from technical differences across different batches of data during the data generation process for acquisition-related reasons, such as collection of images at different sites or using different scanners. This phenomenon can affect the robustness and generalizability of computational pathology- or radiology-based cancer diagnostic models, especially in multicenter studies. To address this issue, we developed an open-source platform, Batch Effect Explorer (BEEx), that is designed to qualitatively and quantitatively determine whether batch effects exist among medical image datasets from different sites. A suite of tools was incorporated into BEEx that provide visualization and quantitative metrics based on intensity, gradient, and texture features to allow users to determine whether there are any image variables or combinations of variables that can distinguish datasets from different sites in an unsupervised manner. BEEx was designed to support various medical imaging techniques, including microscopy and radiology. Four use cases clearly demonstrated the ability of BEEx to identify batch effects and validated the effectiveness of rectification methods for batch effect reduction. Overall, BEEx is a scalable and versatile framework designed to read, process, and analyze a wide range of medical images to facilitate the identification and mitigation of batch effects, which can enhance the reliability and validity of image-based studies. Significance: BEEx is a prescreening tool for image-based analyses that allows researchers to evaluate batch effects in multicenter studies and determine their origin and magnitude to facilitate development of accurate AI–based cancer models.
- 8 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Velocity control of Electromagnetic pellet injection based on genetic algorithm in J-TEXT
Electromagnetic pellet injection (EMPI) is a new disruption mitigation system on J-TEXT Tokamak. In the experimental research, there is a great demand for the control accuracy of the injection velocity of the impurity pellet. Therefore, considering the special demand for the armature velocity control of the electromagnetic railgun, a genetic algorithm (GA) based power supply timing optimization method is proposed, which makes the armature move uniformly and linearly through controlling the discharge current waveform smoothly, and makes the pellet reach the preset velocity within the controllable orbit length. In this paper, three strategies of elite retention, mutation and tournament selection crossover are used to generate new population. The results show that not only the current waveform is stable, but also the armature moves in a straight line with almost uniform acceleration. The results show that the optimization method is a practical and effective method to determine the timing of electromagnetic railgun pulse power supply.
- 8 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Velocity control of Electromagnetic pellet injection based on genetic algorithm in J-TEXT
Electromagnetic pellet injection (EMPI) is a new disruption mitigation system on J-TEXT Tokamak. In the experimental research, there is a great demand for the control accuracy of the injection velocity of the impurity pellet. Therefore, considering the special demand for the armature velocity control of the electromagnetic railgun, a genetic algorithm (GA) based power supply timing optimization method is proposed, which makes the armature move uniformly and linearly through controlling the discharge current waveform smoothly, and makes the pellet reach the preset velocity within the controllable orbit length. In this paper, three strategies of elite retention, mutation and tournament selection crossover are used to generate new population. The results show that not only the current waveform is stable, but also the armature moves in a straight line with almost uniform acceleration. The results show that the optimization method is a practical and effective method to determine the timing of electromagnetic railgun pulse power supply.