MicrosMobiNet: A Deep Lightweight Network With Hierarchical Feature Fusion Scheme for Microscopy Image Analysis in Mobile-Edge Computing.

In recent advancements of lightweight deep architectures for edge devices, most of the works follow typical MobileNet pipeline designed for computer vision tasks which is not very appropriate for microscopy image analysis. Certainly, design of dedicated lightweight network for highly complex microscopy image analysis has not been attempted so far. Therefore, this work proposes a new deep lightweight network, “MicrosMobiNet” having multi-scale feature extraction mechanism for bright-field microscopy image analysis on mobile-edge computing framework. It consists of three key attributes—depth-wise separable convolution for making the network lightweight, multiple kernels with hierarchical feature fusion to extract complex features, and residual connection to keep network deep. Experimental validations have been conducted by two different microscopy image datasets—plant (potato tuber) and histopathology (cancer cell) generated by two different image generation modalities. In experiment, multi-class and multi-label classification tasks have been evaluated by measuring accuracy, F1-score, and error. In ablation study, the key attributes of the network have been verified. The results and analysis show that the MicrosMobiNet can achieve classification accuracy upto 98.43% and 96.25% for plant and cancer cells with minimum error 8.38% and 10.03% respectively. In comparative study, the MicrosMobiNet outperforms the existing lightweight state-of-the-art methods with fewer parameters (1.9M) and FLOPs count (42M). Finally, the new network has been implemented on an edge device, Smartphone (Android platform) which is working satisfactorily with high speed (140ms) and very low memory (7.4 MB). Hence, the network exhibits its superiority in bright-field microscopy image analysis on mobile-edge computing platforms in lightweight deep learning framework.