Increasing segmentation performance with synthetic agar plate images
Background: Agar plate analysis is vital for microbiological testing in industries like food, pharmaceuticals, and biotechnology. Manual inspection is slow, laborious, and error-prone, while existing automated systems struggle with the complexity of real-world agar plates. A shortage of diverse data...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-02-01
|
| Series: | Heliyon |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405844024017456 |
| _version_ | 1797304417453604864 |
|---|---|
| author | Michal Cicatka Radim Burget Jan Karasek Jan Lancos |
| author_facet | Michal Cicatka Radim Burget Jan Karasek Jan Lancos |
| author_sort | Michal Cicatka |
| collection | DOAJ |
| description | Background: Agar plate analysis is vital for microbiological testing in industries like food, pharmaceuticals, and biotechnology. Manual inspection is slow, laborious, and error-prone, while existing automated systems struggle with the complexity of real-world agar plates. A shortage of diverse datasets hinders the development and evaluation of robust automated systems. Methods: In this paper, two new annotated datasets and a novel methodology for synthetic agar plate generation are presented. The datasets comprise 854 images of cultivated agar plates and 1,588 images of empty agar plates, encompassing various agar plate types and microorganisms. These datasets are an extension of the publicly available BRUKERCOLONY dataset, collectively forming one of the largest publicly available annotated datasets for research. The methodology is based on an efficient image generation pipeline that also simulates cultivation-related phenomena such as haemolysis or chromogenic reactions. Results: The augmentations significantly improved the Dice coefficient of trained U-Net models, increasing it from 0.671 to 0.721. Furthermore, training the U-Net model with a combination of real and 150% synthetic data demonstrated its efficacy, yielding a remarkable Dice coefficient of 0.729, a substantial improvement from the baseline of 0.518. UNet3+ exhibited the highest performance among the U-Net and Attention U-Net architectures, achieving a Dice coefficient of 0.767. Conclusions: Our experiments showed the methodology's applicability to real-world scenarios, even with highly variable agar plates. Our paper contributes to automating agar plate analysis by presenting a new dataset and effective methodology, potentially enhancing fully automated microbiological testing. |
| first_indexed | 2024-03-08T00:10:13Z |
| format | Article |
| id | doaj.art-8364104cc45342e9915de41c3e7b80be |
| institution | Directory Open Access Journal |
| issn | 2405-8440 |
| language | English |
| last_indexed | 2024-03-08T00:10:13Z |
| publishDate | 2024-02-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Heliyon |
| spelling | doaj.art-8364104cc45342e9915de41c3e7b80be2024-02-17T06:41:38ZengElsevierHeliyon2405-84402024-02-01103e25714Increasing segmentation performance with synthetic agar plate imagesMichal Cicatka0Radim Burget1Jan Karasek2Jan Lancos3Brno University of Technology, Faculty of Electrical Engineering and Communications, Dept. of Telecommunication, Technicka 12, Brno, 61600, Czech Republic; Corresponding author.Brno University of Technology, Faculty of Electrical Engineering and Communications, Dept. of Telecommunication, Technicka 12, Brno, 61600, Czech RepublicR&D Automation, Microbiology & Diagnostics, Bruker Daltonics GmbH & Co. KG, Fahrenheitstraße 4, Bremen, 28359, GermanyR&D Automation, Microbiology & Diagnostics, Bruker Daltonics GmbH & Co. KG, Fahrenheitstraße 4, Bremen, 28359, GermanyBackground: Agar plate analysis is vital for microbiological testing in industries like food, pharmaceuticals, and biotechnology. Manual inspection is slow, laborious, and error-prone, while existing automated systems struggle with the complexity of real-world agar plates. A shortage of diverse datasets hinders the development and evaluation of robust automated systems. Methods: In this paper, two new annotated datasets and a novel methodology for synthetic agar plate generation are presented. The datasets comprise 854 images of cultivated agar plates and 1,588 images of empty agar plates, encompassing various agar plate types and microorganisms. These datasets are an extension of the publicly available BRUKERCOLONY dataset, collectively forming one of the largest publicly available annotated datasets for research. The methodology is based on an efficient image generation pipeline that also simulates cultivation-related phenomena such as haemolysis or chromogenic reactions. Results: The augmentations significantly improved the Dice coefficient of trained U-Net models, increasing it from 0.671 to 0.721. Furthermore, training the U-Net model with a combination of real and 150% synthetic data demonstrated its efficacy, yielding a remarkable Dice coefficient of 0.729, a substantial improvement from the baseline of 0.518. UNet3+ exhibited the highest performance among the U-Net and Attention U-Net architectures, achieving a Dice coefficient of 0.767. Conclusions: Our experiments showed the methodology's applicability to real-world scenarios, even with highly variable agar plates. Our paper contributes to automating agar plate analysis by presenting a new dataset and effective methodology, potentially enhancing fully automated microbiological testing.http://www.sciencedirect.com/science/article/pii/S2405844024017456Agar platesSynthetic images generationDeep learningSemantic segmentation |
| spellingShingle | Michal Cicatka Radim Burget Jan Karasek Jan Lancos Increasing segmentation performance with synthetic agar plate images Heliyon Agar plates Synthetic images generation Deep learning Semantic segmentation |
| title | Increasing segmentation performance with synthetic agar plate images |
| title_full | Increasing segmentation performance with synthetic agar plate images |
| title_fullStr | Increasing segmentation performance with synthetic agar plate images |
| title_full_unstemmed | Increasing segmentation performance with synthetic agar plate images |
| title_short | Increasing segmentation performance with synthetic agar plate images |
| title_sort | increasing segmentation performance with synthetic agar plate images |
| topic | Agar plates Synthetic images generation Deep learning Semantic segmentation |
| url | http://www.sciencedirect.com/science/article/pii/S2405844024017456 |
| work_keys_str_mv | AT michalcicatka increasingsegmentationperformancewithsyntheticagarplateimages AT radimburget increasingsegmentationperformancewithsyntheticagarplateimages AT jankarasek increasingsegmentationperformancewithsyntheticagarplateimages AT janlancos increasingsegmentationperformancewithsyntheticagarplateimages |