AIMIC: Deep Learning for Microscopic Image Classification. (November 2022)

• Record Type: Journal Article
• Authors: Liu, Rui; Dai, Wei; Wu, Tianyi; Wang, Min; Wan, Song; Liu, Jun
• Is Part Of: Computer methods and programs in biomedicine. Volume 226(2022)
• Publication Date: 2022-11
• Subjects: Code-free deep learning -- Artificial intelligence -- AI platform -- Microscopic image analysis; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2022.107162
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: Deep learning techniques significantly improve results in microscopic image recognition. A universal platform is developed to lower the implementation barrier for clinical users to apply deep learning technology. ResNeXt-50-32 × 4d is a preferable model for blood cell classification. MobileNet-V2 can well balance the classification performance and the computational cost for microscopic image recognition. ShuffleNet-v2 × 1 has relatively low inference latency for microscopic image analysis. Abstract: Background and Objective: Deep learning techniques are powerful tools for image analysis. However, the lack of programming experience makes it difficult for novice users to apply this technology. This project aims to lower the barrier for clinical users to implement deep learning methods in microscopic image classification. Methods: In this study, an out-of-the-box software, AIMIC (artificial intelligence-based microscopy image classifier), was developed for users to apply deep learning technology in a code-free manner. The platform was equipped with state-of-the-art deep learning techniques and data preprocessing approaches. Furthermore, we evaluated the built-in networks on four benchmark microscopy image datasets to assist entry-level practitioners in selecting a suitable algorithm. Results: The entire deep learning pipeline, from training a new network to inferring unseen samples using the trained model, could be implemented on the proposed platform without the need for programming. In the evaluation experiments, the ResNeXt-50-32 × 4d outperformed other competitor algorithms in terms of average accuracy (96.83%) and average F1-score (96.82%). In addition, the MobileNet-V2 achieved a good balance between the performance (accuracy of 95.72%) and computational cost (inference time of 0.109s for identifying one sample). Conclusions: The proposed AI platform allows people without programming experience to use artificial intelligence methods in microscopy image analysis. Besides, the ResNeXt-50-32 × 4d is a preferable solution for microscopic image classification, and MobileNet-V2 is most likely to be an alternative selection for the scenario when computing resources are limited.