Plankton classification with high-throughput submersible holographic microscopy and transfer learning
Abstract Background Plankton are foundational to marine food webs and an important feature for characterizing ocean health. Recent developments in quantitative imaging devices provide in-flow high-throughput sampling from bulk volumes—opening new ecological challenges exploring microbial eukaryotic...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2021-06-01
|
| Series: | BMC Ecology and Evolution |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12862-021-01839-0 |
| _version_ | 1818692635218411520 |
|---|---|
| author | Liam MacNeil Sergey Missan Junliang Luo Thomas Trappenberg Julie LaRoche |
| author_facet | Liam MacNeil Sergey Missan Junliang Luo Thomas Trappenberg Julie LaRoche |
| author_sort | Liam MacNeil |
| collection | DOAJ |
| description | Abstract Background Plankton are foundational to marine food webs and an important feature for characterizing ocean health. Recent developments in quantitative imaging devices provide in-flow high-throughput sampling from bulk volumes—opening new ecological challenges exploring microbial eukaryotic variation and diversity, alongside technical hurdles to automate classification from large datasets. However, a limited number of deployable imaging instruments have been coupled with the most prominent classification algorithms—effectively limiting the extraction of curated observations from field deployments. Holography offers relatively simple coherent microscopy designs with non-intrusive 3-D image information, and rapid frame rates that support data-driven plankton imaging tasks. Classification benchmarks across different domains have been set with transfer learning approaches, focused on repurposing pre-trained, state-of-the-art deep learning models as classifiers to learn new image features without protracted model training times. Combining the data production of holography, digital image processing, and computer vision could improve in-situ monitoring of plankton communities and contribute to sampling the diversity of microbial eukaryotes. Results Here we use a light and portable digital in-line holographic microscope (The HoloSea) with maximum optical resolution of 1.5 μm, intensity-based object detection through a volume, and four different pre-trained convolutional neural networks to classify > 3800 micro-mesoplankton (> 20 μm) images across 19 classes. The maximum classifier performance was quickly achieved for each convolutional neural network during training and reached F1-scores > 89%. Taking classification further, we show that off-the-shelf classifiers perform strongly across every decision threshold for ranking a majority of the plankton classes. Conclusion These results show compelling baselines for classifying holographic plankton images, both rare and plentiful, including several dinoflagellate and diatom groups. These results also support a broader potential for deployable holographic microscopes to sample diverse microbial eukaryotic communities, and its use for high-throughput plankton monitoring. |
| first_indexed | 2024-12-17T13:00:55Z |
| format | Article |
| id | doaj.art-0dd4e815c310497ba630b6838a88af6e |
| institution | Directory Open Access Journal |
| issn | 2730-7182 |
| language | English |
| last_indexed | 2024-12-17T13:00:55Z |
| publishDate | 2021-06-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Ecology and Evolution |
| spelling | doaj.art-0dd4e815c310497ba630b6838a88af6e2022-12-21T21:47:22ZengBMCBMC Ecology and Evolution2730-71822021-06-0121111110.1186/s12862-021-01839-0Plankton classification with high-throughput submersible holographic microscopy and transfer learningLiam MacNeil0Sergey Missan1Junliang Luo2Thomas Trappenberg3Julie LaRoche4Biology Department, Dalhousie University4Deep inwater imagingDepartment of Computer Science, Dalhousie UniversityDepartment of Computer Science, Dalhousie UniversityBiology Department, Dalhousie UniversityAbstract Background Plankton are foundational to marine food webs and an important feature for characterizing ocean health. Recent developments in quantitative imaging devices provide in-flow high-throughput sampling from bulk volumes—opening new ecological challenges exploring microbial eukaryotic variation and diversity, alongside technical hurdles to automate classification from large datasets. However, a limited number of deployable imaging instruments have been coupled with the most prominent classification algorithms—effectively limiting the extraction of curated observations from field deployments. Holography offers relatively simple coherent microscopy designs with non-intrusive 3-D image information, and rapid frame rates that support data-driven plankton imaging tasks. Classification benchmarks across different domains have been set with transfer learning approaches, focused on repurposing pre-trained, state-of-the-art deep learning models as classifiers to learn new image features without protracted model training times. Combining the data production of holography, digital image processing, and computer vision could improve in-situ monitoring of plankton communities and contribute to sampling the diversity of microbial eukaryotes. Results Here we use a light and portable digital in-line holographic microscope (The HoloSea) with maximum optical resolution of 1.5 μm, intensity-based object detection through a volume, and four different pre-trained convolutional neural networks to classify > 3800 micro-mesoplankton (> 20 μm) images across 19 classes. The maximum classifier performance was quickly achieved for each convolutional neural network during training and reached F1-scores > 89%. Taking classification further, we show that off-the-shelf classifiers perform strongly across every decision threshold for ranking a majority of the plankton classes. Conclusion These results show compelling baselines for classifying holographic plankton images, both rare and plentiful, including several dinoflagellate and diatom groups. These results also support a broader potential for deployable holographic microscopes to sample diverse microbial eukaryotic communities, and its use for high-throughput plankton monitoring.https://doi.org/10.1186/s12862-021-01839-0Holographic microscopyHigh-throughput imagingDeep learningConvolutional neural networksPlanktonClassification workflow |
| spellingShingle | Liam MacNeil Sergey Missan Junliang Luo Thomas Trappenberg Julie LaRoche Plankton classification with high-throughput submersible holographic microscopy and transfer learning BMC Ecology and Evolution Holographic microscopy High-throughput imaging Deep learning Convolutional neural networks Plankton Classification workflow |
| title | Plankton classification with high-throughput submersible holographic microscopy and transfer learning |
| title_full | Plankton classification with high-throughput submersible holographic microscopy and transfer learning |
| title_fullStr | Plankton classification with high-throughput submersible holographic microscopy and transfer learning |
| title_full_unstemmed | Plankton classification with high-throughput submersible holographic microscopy and transfer learning |
| title_short | Plankton classification with high-throughput submersible holographic microscopy and transfer learning |
| title_sort | plankton classification with high throughput submersible holographic microscopy and transfer learning |
| topic | Holographic microscopy High-throughput imaging Deep learning Convolutional neural networks Plankton Classification workflow |
| url | https://doi.org/10.1186/s12862-021-01839-0 |
| work_keys_str_mv | AT liammacneil planktonclassificationwithhighthroughputsubmersibleholographicmicroscopyandtransferlearning AT sergeymissan planktonclassificationwithhighthroughputsubmersibleholographicmicroscopyandtransferlearning AT junliangluo planktonclassificationwithhighthroughputsubmersibleholographicmicroscopyandtransferlearning AT thomastrappenberg planktonclassificationwithhighthroughputsubmersibleholographicmicroscopyandtransferlearning AT julielaroche planktonclassificationwithhighthroughputsubmersibleholographicmicroscopyandtransferlearning |