Rethinking low-cost microscopy workflow: Image enhancement using deep based Extended Depth of Field methods
Microscopic techniques in low-to-middle income countries are constrained by the lack of adequate equipment and trained operators. Since light microscopy delivers crucial methods for the diagnosis and screening of numerous diseases, several efforts have been made by the scientific community to develo...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2023-02-01
|
Series: | Intelligent Systems with Applications |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2667305322001077 |
_version_ | 1811170988979650560 |
---|---|
author | Tomé Albuquerque Luís Rosado Ricardo Cruz Maria João M. Vasconcelos Tiago Oliveira Jaime S. Cardoso |
author_facet | Tomé Albuquerque Luís Rosado Ricardo Cruz Maria João M. Vasconcelos Tiago Oliveira Jaime S. Cardoso |
author_sort | Tomé Albuquerque |
collection | DOAJ |
description | Microscopic techniques in low-to-middle income countries are constrained by the lack of adequate equipment and trained operators. Since light microscopy delivers crucial methods for the diagnosis and screening of numerous diseases, several efforts have been made by the scientific community to develop low-cost devices such as 3D-printed portable microscopes. Nevertheless, these devices present some drawbacks that directly affect image quality: the capture of the samples is done via mobile phones; more affordable lenses are usually used, leading to poorer physical properties and images with lower depth of field; misalignments in the microscopic set-up regarding optical, mechanical, and illumination components are frequent, causing image distortions such as chromatic aberrations. This work investigates several pre-processing methods to tackle the presented issues and proposed a new workflow for low-cost microscopy. Additionally, two new deep learning models based on Convolutional Neural Networks are also proposed (EDoF-CNN-Fast and EDoF-CNN-Pairwise) to generate Extended Depth of Field (EDoF) images, and compared against state-of-the-art approaches. The models were tested using two different datasets of cytology microscopic images: public Cervix93 and a new dataset that has been made publicly available containing images captured with μSmartScope. Experimental results demonstrate that the proposed workflow can achieve state-of-the-art performance when generating EDoF images from low-cost microscopes. |
first_indexed | 2024-04-10T17:05:59Z |
format | Article |
id | doaj.art-36b27f510910459186c70a3190adeb1c |
institution | Directory Open Access Journal |
issn | 2667-3053 |
language | English |
last_indexed | 2024-04-10T17:05:59Z |
publishDate | 2023-02-01 |
publisher | Elsevier |
record_format | Article |
series | Intelligent Systems with Applications |
spelling | doaj.art-36b27f510910459186c70a3190adeb1c2023-02-06T04:06:26ZengElsevierIntelligent Systems with Applications2667-30532023-02-0117200170Rethinking low-cost microscopy workflow: Image enhancement using deep based Extended Depth of Field methodsTomé Albuquerque0Luís Rosado1Ricardo Cruz2Maria João M. Vasconcelos3Tiago Oliveira4Jaime S. Cardoso5INESC TEC, Rua Dr. Roberto Frias, Porto, 4200-465, Portugal; FEUP, Rua Dr. Roberto Frias, Porto, 4200-465, Portugal; Corresponding author.Fraunhofer Portugal AICOS, Rua Alfredo Allen 455/461, Porto, 4200-135, PortugalINESC TEC, Rua Dr. Roberto Frias, Porto, 4200-465, Portugal; FEUP, Rua Dr. Roberto Frias, Porto, 4200-465, PortugalFraunhofer Portugal AICOS, Rua Alfredo Allen 455/461, Porto, 4200-135, PortugalFirst Solutions - Sistemas de Informação S.A., Rua Conselheiro Costa Braga 502 F, Matosinhos, 4450-102, PortugalINESC TEC, Rua Dr. Roberto Frias, Porto, 4200-465, Portugal; FEUP, Rua Dr. Roberto Frias, Porto, 4200-465, PortugalMicroscopic techniques in low-to-middle income countries are constrained by the lack of adequate equipment and trained operators. Since light microscopy delivers crucial methods for the diagnosis and screening of numerous diseases, several efforts have been made by the scientific community to develop low-cost devices such as 3D-printed portable microscopes. Nevertheless, these devices present some drawbacks that directly affect image quality: the capture of the samples is done via mobile phones; more affordable lenses are usually used, leading to poorer physical properties and images with lower depth of field; misalignments in the microscopic set-up regarding optical, mechanical, and illumination components are frequent, causing image distortions such as chromatic aberrations. This work investigates several pre-processing methods to tackle the presented issues and proposed a new workflow for low-cost microscopy. Additionally, two new deep learning models based on Convolutional Neural Networks are also proposed (EDoF-CNN-Fast and EDoF-CNN-Pairwise) to generate Extended Depth of Field (EDoF) images, and compared against state-of-the-art approaches. The models were tested using two different datasets of cytology microscopic images: public Cervix93 and a new dataset that has been made publicly available containing images captured with μSmartScope. Experimental results demonstrate that the proposed workflow can achieve state-of-the-art performance when generating EDoF images from low-cost microscopes.http://www.sciencedirect.com/science/article/pii/S2667305322001077Extended Depth of FieldCNNMicroscopy workflowMobile healthCervical cytology |
spellingShingle | Tomé Albuquerque Luís Rosado Ricardo Cruz Maria João M. Vasconcelos Tiago Oliveira Jaime S. Cardoso Rethinking low-cost microscopy workflow: Image enhancement using deep based Extended Depth of Field methods Intelligent Systems with Applications Extended Depth of Field CNN Microscopy workflow Mobile health Cervical cytology |
title | Rethinking low-cost microscopy workflow: Image enhancement using deep based Extended Depth of Field methods |
title_full | Rethinking low-cost microscopy workflow: Image enhancement using deep based Extended Depth of Field methods |
title_fullStr | Rethinking low-cost microscopy workflow: Image enhancement using deep based Extended Depth of Field methods |
title_full_unstemmed | Rethinking low-cost microscopy workflow: Image enhancement using deep based Extended Depth of Field methods |
title_short | Rethinking low-cost microscopy workflow: Image enhancement using deep based Extended Depth of Field methods |
title_sort | rethinking low cost microscopy workflow image enhancement using deep based extended depth of field methods |
topic | Extended Depth of Field CNN Microscopy workflow Mobile health Cervical cytology |
url | http://www.sciencedirect.com/science/article/pii/S2667305322001077 |
work_keys_str_mv | AT tomealbuquerque rethinkinglowcostmicroscopyworkflowimageenhancementusingdeepbasedextendeddepthoffieldmethods AT luisrosado rethinkinglowcostmicroscopyworkflowimageenhancementusingdeepbasedextendeddepthoffieldmethods AT ricardocruz rethinkinglowcostmicroscopyworkflowimageenhancementusingdeepbasedextendeddepthoffieldmethods AT mariajoaomvasconcelos rethinkinglowcostmicroscopyworkflowimageenhancementusingdeepbasedextendeddepthoffieldmethods AT tiagooliveira rethinkinglowcostmicroscopyworkflowimageenhancementusingdeepbasedextendeddepthoffieldmethods AT jaimescardoso rethinkinglowcostmicroscopyworkflowimageenhancementusingdeepbasedextendeddepthoffieldmethods |