Combining the use of CNN classification and strength‐driven compression for the robust identification of bacterial species on hyperspectral culture plate images
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 w...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2018-10-01
|
| Series: | IET Computer Vision |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/iet-cvi.2018.5237 |
| _version_ | 1797684803644948480 |
|---|---|
| author | Alberto Signoroni Mattia Savardi Mario Pezzoni Fabrizio Guerrini Simone Arrigoni Giovanni Turra |
| author_facet | Alberto Signoroni Mattia Savardi Mario Pezzoni Fabrizio Guerrini Simone Arrigoni Giovanni Turra |
| author_sort | Alberto Signoroni |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-12T00:35:05Z |
| format | Article |
| id | doaj.art-59c3ac456b604d83ab24de09b8a6438f |
| institution | Directory Open Access Journal |
| issn | 1751-9632 1751-9640 |
| language | English |
| last_indexed | 2024-03-12T00:35:05Z |
| publishDate | 2018-10-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Computer Vision |
| spelling | doaj.art-59c3ac456b604d83ab24de09b8a6438f2023-09-15T09:52:03ZengWileyIET Computer Vision1751-96321751-96402018-10-0112794194910.1049/iet-cvi.2018.5237Combining the use of CNN classification and strength‐driven compression for the robust identification of bacterial species on hyperspectral culture plate imagesAlberto Signoroni0Mattia Savardi1Mario Pezzoni2Fabrizio Guerrini3Simone Arrigoni4Giovanni Turra5Information Engineering DepartmentUniversity of BresciaBresciaItalyInformation Engineering DepartmentUniversity of BresciaBresciaItalyInformation Engineering DepartmentUniversity of BresciaBresciaItalyInformation Engineering DepartmentUniversity of BresciaBresciaItalyFutura Science Park – Copan Italia S.p.A.BresciaItalyInformation Engineering DepartmentUniversity of BresciaBresciaItalyHuge 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.https://doi.org/10.1049/iet-cvi.2018.5237CNN classificationstrength-driven compressionrobust bacterial species identificationhyperspectral culture plate imagesdiagnostic imagesdigital microbiology imaging |
| spellingShingle | Alberto Signoroni Mattia Savardi Mario Pezzoni Fabrizio Guerrini Simone Arrigoni Giovanni Turra Combining the use of CNN classification and strength‐driven compression for the robust identification of bacterial species on hyperspectral culture plate images IET Computer Vision CNN classification strength-driven compression robust bacterial species identification hyperspectral culture plate images diagnostic images digital microbiology imaging |
| title | Combining the use of CNN classification and strength‐driven compression for the robust identification of bacterial species on hyperspectral culture plate images |
| title_full | Combining the use of CNN classification and strength‐driven compression for the robust identification of bacterial species on hyperspectral culture plate images |
| title_fullStr | Combining the use of CNN classification and strength‐driven compression for the robust identification of bacterial species on hyperspectral culture plate images |
| title_full_unstemmed | Combining the use of CNN classification and strength‐driven compression for the robust identification of bacterial species on hyperspectral culture plate images |
| title_short | Combining the use of CNN classification and strength‐driven compression for the robust identification of bacterial species on hyperspectral culture plate images |
| title_sort | combining the use of cnn classification and strength driven compression for the robust identification of bacterial species on hyperspectral culture plate images |
| topic | CNN classification strength-driven compression robust bacterial species identification hyperspectral culture plate images diagnostic images digital microbiology imaging |
| url | https://doi.org/10.1049/iet-cvi.2018.5237 |
| work_keys_str_mv | AT albertosignoroni combiningtheuseofcnnclassificationandstrengthdrivencompressionfortherobustidentificationofbacterialspeciesonhyperspectralcultureplateimages AT mattiasavardi combiningtheuseofcnnclassificationandstrengthdrivencompressionfortherobustidentificationofbacterialspeciesonhyperspectralcultureplateimages AT mariopezzoni combiningtheuseofcnnclassificationandstrengthdrivencompressionfortherobustidentificationofbacterialspeciesonhyperspectralcultureplateimages AT fabrizioguerrini combiningtheuseofcnnclassificationandstrengthdrivencompressionfortherobustidentificationofbacterialspeciesonhyperspectralcultureplateimages AT simonearrigoni combiningtheuseofcnnclassificationandstrengthdrivencompressionfortherobustidentificationofbacterialspeciesonhyperspectralcultureplateimages AT giovanniturra combiningtheuseofcnnclassificationandstrengthdrivencompressionfortherobustidentificationofbacterialspeciesonhyperspectralcultureplateimages |