Junxian He
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Junxian He has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Cong Shi
Chongqing University
3 shared publications - Liyuan Liu
Institute of Semiconductors, Chinese Academy of Sciences, Beijing, China
3 shared publications - Tengxiao Wang
School of Microelectronics and Communication Engineering, Chongqing University, Chongqing, China
3 shared publications - Gang Luo
Schepens Eye Research Institute of Mass Eye and Ear, Department of Ophthalmology, Harvard Medical School, Boston, MA, USA
2 shared publications - Haibing Wang
School of Microelectronics and Communication Engineering, Chongqing University, Chongqing, China
2 shared publications - Jiawei Zhang
Department of Ophthalmology, Eye & ENT Hospital of Fudan University, Shanghai, China
2 shared publications
Latest Publications
- Open Access
- 4 November 2025
- Published by JMIR Publications Inc. in JMIR Formative Research
- Vol. 9, e79280
Quantitative Assessment of Strabismus Using Cloud AI Computing: Validation Study
Background: Strabismus measurement is essential in vision assessment and screening. It typically requires skilled clinicians or specialized equipment. Photographic strabismus measurement methods have value in terms of accessibility and convenience of use. Objective: This study aimed to evaluate Eyeturn Cloud, a cloud-based artificial intelligence (AI) system for measuring strabismus angles based on eye images captured with smartphone cameras under cover test conditions. Methods: The Eyeturn Cloud web app uses AI models to recognize eyes, eye lid, and iris, and then to segment iris precisely. It then computes strabismus based on ellipse fitting of the iris boundary and corneal reflection. The system was evaluated in patients (without glasses) with manifest strabismus and control participants. Clinicians measured eye deviations using the prism alternate cover test and also captured pictures of their eyes under alternate cover and unilateral cover conditions. The pictures were processed by Eyeturn Cloud. Results: In total, 79 (mean age 11.9, SD 6.3 years; esotropia: n=15, exotropia: n=55, orthotropia: n=9) participants were enrolled; of which, data were available for 71 participants (8/79, 10.1% processing failure). The range of prism alternate cover test strabismus magnitude was from 78 base in to 78 base out prism diopters (PDs). A strong correlation was found between Eyeturn Cloud and clinical measurements (R2=0.95; slope=0.91; P<.001). Bland-Altman analysis revealed that 95% limits of agreement between the 2 measurements were –20.2 to 14.6 PD. A repeatability test with 15 participants (4 photos each) found a 1.53 PD SD. Conclusions: The cloud AI web app can compute strabismus angles reliably under alternate and unilateral cover conditions in clinical settings, and its potential for use in telehealth settings needs further evaluation.
- 4 November 2025
- Published by JMIR Publications Inc. in JMIR Formative Research
- Vol. 9, e79280
Open AccessQuantitative Assessment of Strabismus Using Cloud AI Computing: Validation Study
Background: Strabismus measurement is essential in vision assessment and screening. It typically requires skilled clinicians or specialized equipment. Photographic strabismus measurement methods have value in terms of accessibility and convenience of use. Objective: This study aimed to evaluate Eyeturn Cloud, a cloud-based artificial intelligence (AI) system for measuring strabismus angles based on eye images captured with smartphone cameras under cover test conditions. Methods: The Eyeturn Cloud web app uses AI models to recognize eyes, eye lid, and iris, and then to segment iris precisely. It then computes strabismus based on ellipse fitting of the iris boundary and corneal reflection. The system was evaluated in patients (without glasses) with manifest strabismus and control participants. Clinicians measured eye deviations using the prism alternate cover test and also captured pictures of their eyes under alternate cover and unilateral cover conditions. The pictures were processed by Eyeturn Cloud. Results: In total, 79 (mean age 11.9, SD 6.3 years; esotropia: n=15, exotropia: n=55, orthotropia: n=9) participants were enrolled; of which, data were available for 71 participants (8/79, 10.1% processing failure). The range of prism alternate cover test strabismus magnitude was from 78 base in to 78 base out prism diopters (PDs). A strong correlation was found between Eyeturn Cloud and clinical measurements (R2=0.95; slope=0.91; P<.001). Bland-Altman analysis revealed that 95% limits of agreement between the 2 measurements were –20.2 to 14.6 PD. A repeatability test with 15 participants (4 photos each) found a 1.53 PD SD. Conclusions: The cloud AI web app can compute strabismus angles reliably under alternate and unilateral cover conditions in clinical settings, and its potential for use in telehealth settings needs further evaluation.
- Open Access
- 19 June 2025
- Published by JMIR Publications Inc. in JMIR Preprints
Quantitative Assessment of Strabismus Using Cloud AI Computing: Validation Study (Preprint)
BACKGROUND Strabismus measurement is essential in vision assessment and screening. It typically requires skilled clinicians or specialized equipment. Photographic strabismus measurement methods have value in terms of accessibility and convenience of use. OBJECTIVE This study aimed to evaluate Eyeturn Cloud, a cloud-based artificial intelligence (AI) system for measuring strabismus angles based on eye images captured with smartphone cameras under cover test conditions. METHODS The Eyeturn Cloud web app uses AI models to recognize eyes, eye lid, and iris, and then to segment iris precisely. It then computes strabismus based on ellipse fitting of the iris boundary and corneal reflection. The system was evaluated in patients (without glasses) with manifest strabismus and control participants. Clinicians measured eye deviations using the prism alternate cover test and also captured pictures of their eyes under alternate cover and unilateral cover conditions. The pictures were processed by Eyeturn Cloud. RESULTS In total, 79 (mean age 11.9, SD 6.3 years; esotropia: n=15, exotropia: n=55, orthotropia: n=9) participants were enrolled; of which, data were available for 71 participants (8/79, 10.1% processing failure). The range of prism alternate cover test strabismus magnitude was from 78 base in to 78 base out prism diopters (PDs). A strong correlation was found between Eyeturn Cloud and clinical measurements (R2=0.95; slope=0.91; P<.001). Bland-Altman analysis revealed that 95% limits of agreement between the 2 measurements were –20.2 to 14.6 PD. A repeatability test with 15 participants (4 photos each) found a 1.53 PD SD. CONCLUSIONS The cloud AI web app can compute strabismus angles reliably under alternate and unilateral cover conditions in clinical settings, and its potential for use in telehealth settings needs further evaluation.
- 19 June 2025
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessQuantitative Assessment of Strabismus Using Cloud AI Computing: Validation Study (Preprint)
BACKGROUND Strabismus measurement is essential in vision assessment and screening. It typically requires skilled clinicians or specialized equipment. Photographic strabismus measurement methods have value in terms of accessibility and convenience of use. OBJECTIVE This study aimed to evaluate Eyeturn Cloud, a cloud-based artificial intelligence (AI) system for measuring strabismus angles based on eye images captured with smartphone cameras under cover test conditions. METHODS The Eyeturn Cloud web app uses AI models to recognize eyes, eye lid, and iris, and then to segment iris precisely. It then computes strabismus based on ellipse fitting of the iris boundary and corneal reflection. The system was evaluated in patients (without glasses) with manifest strabismus and control participants. Clinicians measured eye deviations using the prism alternate cover test and also captured pictures of their eyes under alternate cover and unilateral cover conditions. The pictures were processed by Eyeturn Cloud. RESULTS In total, 79 (mean age 11.9, SD 6.3 years; esotropia: n=15, exotropia: n=55, orthotropia: n=9) participants were enrolled; of which, data were available for 71 participants (8/79, 10.1% processing failure). The range of prism alternate cover test strabismus magnitude was from 78 base in to 78 base out prism diopters (PDs). A strong correlation was found between Eyeturn Cloud and clinical measurements (R2=0.95; slope=0.91; P<.001). Bland-Altman analysis revealed that 95% limits of agreement between the 2 measurements were –20.2 to 14.6 PD. A repeatability test with 15 participants (4 photos each) found a 1.53 PD SD. CONCLUSIONS The cloud AI web app can compute strabismus angles reliably under alternate and unilateral cover conditions in clinical settings, and its potential for use in telehealth settings needs further evaluation.
- 19 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems II: Express Briefs
- Vol. 72 (7) , 943-947
A Visual-Cortex-Mimetic Tiny Neuromorphic Vision Processor Based on Reconfigurable Cortical Neuron Unit
Edge visual systems demand high energy-efficiency vision processors like neuromorphic hardware leveraging spikebased computations. But their disability of directly interacting with non-spike information in the real world requests additional components to execute image pre-processing, spike encoding and decoding, severely increasing overall system cost, energy and latency. To overcome such drawback, this brief proposes a tiny neuromorphic vision processor which emulates functional regions along the ventral pathway in the visual cortex. It performs image pre-processing, spike encoding, spike-based feature extraction and classification, spike decoding as well as decision making on a single chip. To reduce hardware resources, our processor builds on a reconfigurable cortical neuron (RCN) unit, which runs different neuron models for different visual cortex regions in a timemultiplexing fashion. It also embeds biological learning circuits to better adapt the processor to dynamic edge scenarios. Our neuromorphic processor was prototyped on a very-low-cost Xilinx Zynq-7010 device. On the MNIST dataset, it exhibited a real-time inference speed of 696 frame/s covering image pre-processing to final decision and a high on-chip learning accuracy of 97.12%, while only delivering a power consumption as low as 118 mW.
- 19 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems II: Express Briefs
- Vol. 72 (7) , 943-947
A Visual-Cortex-Mimetic Tiny Neuromorphic Vision Processor Based on Reconfigurable Cortical Neuron Unit
Edge visual systems demand high energy-efficiency vision processors like neuromorphic hardware leveraging spikebased computations. But their disability of directly interacting with non-spike information in the real world requests additional components to execute image pre-processing, spike encoding and decoding, severely increasing overall system cost, energy and latency. To overcome such drawback, this brief proposes a tiny neuromorphic vision processor which emulates functional regions along the ventral pathway in the visual cortex. It performs image pre-processing, spike encoding, spike-based feature extraction and classification, spike decoding as well as decision making on a single chip. To reduce hardware resources, our processor builds on a reconfigurable cortical neuron (RCN) unit, which runs different neuron models for different visual cortex regions in a timemultiplexing fashion. It also embeds biological learning circuits to better adapt the processor to dynamic edge scenarios. Our neuromorphic processor was prototyped on a very-low-cost Xilinx Zynq-7010 device. On the MNIST dataset, it exhibited a real-time inference speed of 696 frame/s covering image pre-processing to final decision and a high on-chip learning accuracy of 97.12%, while only delivering a power consumption as low as 118 mW.
- 11 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biomedical Circuits and Systems
- Vol. 19 (1) , 209-225
MorphBungee: A 65-nm 7.2-mm 2 27-µJ/Image Digital Edge Neuromorphic Chip With on-Chip 802-Frame/s Multi-Layer Spiking Neural Network Learning
This paper presents a digital edge neuromorphic spiking neural network (SNN) processor chip for a variety of edge intelligent cognitive applications. This processor allows high-speed, high-accuracy and fully on-chip spike-timing-based multi-layer SNN learning. It is characteristic of hierarchical multi-core architecture, event-driven processing paradigm, meta-crossbar for efficient spike communication, and hybrid and reconfigurable parallelism. A prototype chip occupying an active silicon area of 7.2 mm 2 was fabricated using a 65-nm 1P9M CMOS process. when running a 256-256-256-256-200 4-layer fully-connected SNN on downscaled 16 × 16 MNIST images. it typically achieved a high-speed throughput of 802 and 2270 frames/s for on-chip learning and inference, respectively, with a relatively low power dissipation of around 61 mW at a 100 MHz clock rate under a 1.0V core power supply, Our on-chip learning results in comparably high visual recognition accuracies of 96.06%, 83.38%, 84.53%, 99.22% and 100% on the MNIST, Fashion-MNIST, ETH-80, Yale-10 and ORL-10 datasets, respectively. In addition, we have successfully applied our neuromorphic chip to demonstrate high-resolution satellite cloud image segmentation and non-visual tasks including olfactory classification and textural news categorization. These results indicate that our neuromorphic chip is suitable for various intelligent edge systems under restricted cost, energy and latency budgets while requiring in-situ self-adaptative learning capability.
- 11 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biomedical Circuits and Systems
- Vol. 19 (1) , 209-225
MorphBungee: A 65-nm 7.2-mm 2 27-µJ/Image Digital Edge Neuromorphic Chip With on-Chip 802-Frame/s Multi-Layer Spiking Neural Network Learning
This paper presents a digital edge neuromorphic spiking neural network (SNN) processor chip for a variety of edge intelligent cognitive applications. This processor allows high-speed, high-accuracy and fully on-chip spike-timing-based multi-layer SNN learning. It is characteristic of hierarchical multi-core architecture, event-driven processing paradigm, meta-crossbar for efficient spike communication, and hybrid and reconfigurable parallelism. A prototype chip occupying an active silicon area of 7.2 mm 2 was fabricated using a 65-nm 1P9M CMOS process. when running a 256-256-256-256-200 4-layer fully-connected SNN on downscaled 16 × 16 MNIST images. it typically achieved a high-speed throughput of 802 and 2270 frames/s for on-chip learning and inference, respectively, with a relatively low power dissipation of around 61 mW at a 100 MHz clock rate under a 1.0V core power supply, Our on-chip learning results in comparably high visual recognition accuracies of 96.06%, 83.38%, 84.53%, 99.22% and 100% on the MNIST, Fashion-MNIST, ETH-80, Yale-10 and ORL-10 datasets, respectively. In addition, we have successfully applied our neuromorphic chip to demonstrate high-resolution satellite cloud image segmentation and non-visual tasks including olfactory classification and textural news categorization. These results indicate that our neuromorphic chip is suitable for various intelligent edge systems under restricted cost, energy and latency budgets while requiring in-situ self-adaptative learning capability.