Shigeng Wang(王世耿)

Shigeng Wang(王世耿)

A computer science PhD student of BUPT, interested in computer vision,tinyml and model quantization.

Publications

Development and multi-center validation of machine learning model for early detection of fungal keratitis

Published in eBioMedicine, 2023

Fungal keratitis (FK) is a leading cause of corneal blindness in developing countries due to poor clinical recognition and laboratory identification. Here, we aimed to identify the distinct clinical signature of FK and develop a diagnostic model to differentiate FK from other types of infectious keratitis.Our model enables rapid identification of FK, which will help ophthalmologists to establish a preliminary diagnosis and to improve the diagnostic accuracy in clinic.

Recommended citation: Wei Z, Wang S, Wang Z, et al. Development and multi-center validation of machine learning model for early detection of fungal keratitis[J]. eBioMedicine, 2023, 88: 104438. https://www.thelancet.com/journals/ebiom/article/PIIS2352-3964(23)00003-8/fulltext

Deep learning-based classification of infectious keratitis on slit-lamp images

Published in Therapeutic Advances in Chronic Disease, 2022

Infectious keratitis (IK) is an ocular emergency caused by a variety of microorganisms, including bacteria, fungi, viruses, and parasites. Culture-based methods were the gold standard for diagnosing IK, but difficult biopsy, delaying report, and low positive rate limited their clinical application. This study aims to construct a deep-learning-based auxiliary diagnostic model for early IK diagnosis. KeratitisNet demonstrates a good performance on clinical IK diagnosis and classification. Deep learning could provide an auxiliary diagnostic method to help clinicians suspect IK using different corneal manifestations.

Recommended citation: Zhang Z, Wang H, Wang S, et al. Deep learning-based classification of infectious keratitis on slit-lamp images[J]. Therapeutic Advances in Chronic Disease, 2022, 13: 20406223221136071. https://journals.sagepub.com/doi/pdf/10.1177/20406223221136071

PowerDet:Efficient and Lightweight Object Detection for Electric Power Open Scenes

Published in CCIS, 2021

There are problems with the schemes in open electric power scenes, e.g., only able to detect single category, low detection accuracy of multi-scale objects, and difficulty in deploying models on mobile devices. To address the challenges mentioned above, we propose an object detection model, named PowerDet. It is able to detect 9 different types of power facilities efficiently with low cost.

Recommended citation: S. Wang, Z. Ou and M. Song, "PowerDet: Efficient and Lightweight Object Detection for Electric Power Open Scenes," 2021 IEEE 7th International Conference on Cloud Computing and Intelligent Systems (CCIS), Xi'an, China, 2021, pp. 198-202, doi: 10.1109/CCIS53392.2021.9754678. https://ieeexplore.ieee.org/document/9754678