Data augmentation for Gram-stain images based on Vector Quantized Variational AutoEncoder

Availability of large-scale datasets plays a significant role in segmentation and classification tasks using deep learning. However, domains such as healthcare inherently suffer from unavailability and inaccessibility of data. This leads to challenges in deploying CNN-based models for computer-aided...

Full description

Saved in:
Bibliographic Details
Published in:Neurocomputing (Amsterdam) Vol. 600; p. 128123
Main Authors: V, Shwetha, Prasad, Keerthana, Mukhopadhyay, Chiranjay, Banerjee, Barnini
Format: Journal Article
Language:English
Published: Elsevier B.V 01.10.2024
Subjects:
Augmentation
Bacteria detection
CNN based classification
Generative Adversarial network
Semantic segmentation
Transformation
Variational AutoEncoder
VQ-VAE
Augmentation
Generative Adversarial network
Transformation
VQ-VAE
Semantic segmentation
CNN based classification
Bacteria detection
Variational AutoEncoder
ISSN:0925-2312
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Availability of large-scale datasets plays a significant role in segmentation and classification tasks using deep learning. However, domains such as healthcare inherently suffer from unavailability and inaccessibility of data. This leads to challenges in deploying CNN-based models for computer-aided diagnosis. This challenge extends to Gram-stain image analysis for detecting bacterial infections, which is a crucial task. The lack of datasets containing Gram-stained direct and culture smear images exacerbates the significant challenges in deep learning tasks. In this regard, we investigate a novel application of the Variational AutoEncoder. Specifically, the Vector Quantized Variational AutoEncoder model is trained to generate the Gram-stain images. Incorporating a novel loss function, where the quality loss (Lqu) is derived by integrating the LossSSIM, L1, and L2 losses with the VQ-VAE loss (Lossvq) for proposed approach for Gram-stained direct and culture smear images. This modification facilitates the creation of images closely resembling the original input, leading to notable SSIM scores of 0.92 for Gram-stained culture images and 0.88 for Gram-stained direct smear images. The current study compares the proposed method with state-of-the-art machine learning based and CNN based transformations. This work also demonstrates the classification process with and without image augmentation. It shows that the area under the curve in the case of augmentation is higher by an average of 20%. •VQ-VAE based augmentation for Gram-stain images is proposed.•This study tackles the Gram-stain image dataset scarcity in CNN segmentation and classification.•Suitable loss function and its impact on Gram-stain image generation are investigated.•The impact of augmentation on the segmentation and classification process is examined.•A novel image augmentation method for bacteria detection framework is proposed.
ISSN:0925-2312
DOI:10.1016/j.neucom.2024.128123