Combining the use of CNN classification and strength‐driven compression for the robust identification of bacterial species on hyperspectral culture plate images. Issue 7 (8th August 2018)

• Record Type: Journal Article
• Authors: Signoroni, Alberto; Savardi, Mattia; Pezzoni, Mario; Guerrini, Fabrizio; Arrigoni, Simone; Turra, Giovanni
• Is Part Of: IET computer vision. Volume 12:Issue 7(2018)
• Page Start: 941
• Page End: 949
• Publication Date: 2018-08-08
• Subjects: biomedical optical imaging -- microorganisms -- medical image processing -- image coding -- data compression -- image classification -- feedforward neural nets -- learning (artificial intelligence) -- wavelet transforms; CNN classification -- strength-driven compression -- robust bacterial species identification -- hyperspectral culture plate images -- diagnostic images -- digital microbiology imaging -- full microbiology laboratory automation systems -- deep learning approach -- pathogen identification -- bacterial growing plates -- hyperspectral acquisitions -- VNIR range -- spatial-spectral processing -- computed spectral signature classification -- bacterial colonies -- urinary tract infections -- clinical context -- convolutional neural network -- lossy data compression -- wavelet-based compression technology -- coding strength-driven operating points -- classification performance degradation; Computer vision -- Periodicals; Pattern recognition systems -- Periodicals; 006.37
• DOI: 10.1049/iet-cvi.2018.5237
• Languages: English
• ISSNs: 1751-9632

Abstract

Abstract : Huge streams of diagnostic images are expected to be produced daily in the emerging field of digital microbiology imaging because of the ongoing worldwide spread of Full Laboratory Automation systems. This is redefining the way microbiologists execute diagnostic tasks. In this context, the authors want to assess the suitability and effectiveness of a deep learning approach to solve the diagnostically relevant but visually challenging task of directly identifying pathogens on bacterial growing plates. In particular, starting from hyperspectral acquisitions in the VNIR range and spatial‐spectral processing of cultured plates, they approach the identification problem as the classification of computed spectral signatures of the bacterial colonies. In a highly relevant clinical context (urinary tract infections) and on a database of acquired hyperspectral images, they designed and trained a convolutional neural network for pathogen identification, assessing its performance and comparing it against conventional classification solutions. At the same time, given the expected data flow and possible conservation and transmission needs, they are interested in evaluating the combined use of classification and lossy data compression. To this end, after selecting a suitable wavelet‐based compression technology, they test coding strength‐driven operating points looking for configurations able to provably prevent any classification performance degradation.