Automated morphometrics on microscopy images of Atlantic cod larvae using Mask R-CNN and classical machine vision techniques
Measurements of morphometrical parameters on i.e., fish larvae are useful for assessing the quality and condition of the specimen in environmental research or optimal growth in the cultivation industry. Manually acquiring morphometrical parameters from microscopy images can be time consuming and ted...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-01-01
|
| Series: | MethodsX |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2215016121003885 |
| _version_ | 1811178677451358208 |
|---|---|
| author | Bjarne Kvæstad Bjørn Henrik Hansen Emlyn Davies |
| author_facet | Bjarne Kvæstad Bjørn Henrik Hansen Emlyn Davies |
| author_sort | Bjarne Kvæstad |
| collection | DOAJ |
| description | Measurements of morphometrical parameters on i.e., fish larvae are useful for assessing the quality and condition of the specimen in environmental research or optimal growth in the cultivation industry. Manually acquiring morphometrical parameters from microscopy images can be time consuming and tedious, this can be a limiting factor when acquiring samples for an experiment. Mask R-CNN, an instance segmentation neural network architecture, has been implemented for finding outlines on parts of interest on fish larvae (Atlantic cod, Gadus morhua). Using classical machine vision techniques on the outlines makes it is possible to acquire morphometrics such as area, diameter, length, and height. The combination of these techniques is providing accurate-, consistent-, and high-volume information on the morphometrics of small organisms, making it possible to sample more data for morphometric analysis. • Capabilities to automatically analyse a set of microscopy images in approximately 2-3 seconds per image, with results that have a high degree of accuracy when compared to morphometrics acquired manually by an expert. • Can be implemented on other species of ichthyoplankton or zooplankton and has successfully been tested on ballan wrasse, zebrafish, lumpsucker and calanoid copepods. |
| first_indexed | 2024-04-11T06:22:21Z |
| format | Article |
| id | doaj.art-e8c8c49fca414ede9c93b1aff336cc97 |
| institution | Directory Open Access Journal |
| issn | 2215-0161 |
| language | English |
| last_indexed | 2024-04-11T06:22:21Z |
| publishDate | 2022-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | MethodsX |
| spelling | doaj.art-e8c8c49fca414ede9c93b1aff336cc972022-12-22T04:40:31ZengElsevierMethodsX2215-01612022-01-019101598Automated morphometrics on microscopy images of Atlantic cod larvae using Mask R-CNN and classical machine vision techniquesBjarne Kvæstad0Bjørn Henrik Hansen1Emlyn Davies2Corresponding author.; SINTEF Ocean, Environment and New Resources, Brattørkaia 17C, Trondheim NO-7010, NorwaySINTEF Ocean, Environment and New Resources, Brattørkaia 17C, Trondheim NO-7010, NorwaySINTEF Ocean, Environment and New Resources, Brattørkaia 17C, Trondheim NO-7010, NorwayMeasurements of morphometrical parameters on i.e., fish larvae are useful for assessing the quality and condition of the specimen in environmental research or optimal growth in the cultivation industry. Manually acquiring morphometrical parameters from microscopy images can be time consuming and tedious, this can be a limiting factor when acquiring samples for an experiment. Mask R-CNN, an instance segmentation neural network architecture, has been implemented for finding outlines on parts of interest on fish larvae (Atlantic cod, Gadus morhua). Using classical machine vision techniques on the outlines makes it is possible to acquire morphometrics such as area, diameter, length, and height. The combination of these techniques is providing accurate-, consistent-, and high-volume information on the morphometrics of small organisms, making it possible to sample more data for morphometric analysis. • Capabilities to automatically analyse a set of microscopy images in approximately 2-3 seconds per image, with results that have a high degree of accuracy when compared to morphometrics acquired manually by an expert. • Can be implemented on other species of ichthyoplankton or zooplankton and has successfully been tested on ballan wrasse, zebrafish, lumpsucker and calanoid copepods.http://www.sciencedirect.com/science/article/pii/S2215016121003885AutoMOMI (Automated Morphometrics On Microscope Images) |
| spellingShingle | Bjarne Kvæstad Bjørn Henrik Hansen Emlyn Davies Automated morphometrics on microscopy images of Atlantic cod larvae using Mask R-CNN and classical machine vision techniques MethodsX AutoMOMI (Automated Morphometrics On Microscope Images) |
| title | Automated morphometrics on microscopy images of Atlantic cod larvae using Mask R-CNN and classical machine vision techniques |
| title_full | Automated morphometrics on microscopy images of Atlantic cod larvae using Mask R-CNN and classical machine vision techniques |
| title_fullStr | Automated morphometrics on microscopy images of Atlantic cod larvae using Mask R-CNN and classical machine vision techniques |
| title_full_unstemmed | Automated morphometrics on microscopy images of Atlantic cod larvae using Mask R-CNN and classical machine vision techniques |
| title_short | Automated morphometrics on microscopy images of Atlantic cod larvae using Mask R-CNN and classical machine vision techniques |
| title_sort | automated morphometrics on microscopy images of atlantic cod larvae using mask r cnn and classical machine vision techniques |
| topic | AutoMOMI (Automated Morphometrics On Microscope Images) |
| url | http://www.sciencedirect.com/science/article/pii/S2215016121003885 |
| work_keys_str_mv | AT bjarnekvæstad automatedmorphometricsonmicroscopyimagesofatlanticcodlarvaeusingmaskrcnnandclassicalmachinevisiontechniques AT bjørnhenrikhansen automatedmorphometricsonmicroscopyimagesofatlanticcodlarvaeusingmaskrcnnandclassicalmachinevisiontechniques AT emlyndavies automatedmorphometricsonmicroscopyimagesofatlanticcodlarvaeusingmaskrcnnandclassicalmachinevisiontechniques |