Phytoplankton detection and recognition in freshwater digital microscopy images using deep learning object detectors
Water quality can be negatively affected by the presence of some toxic phytoplankton species, whose toxins are difficult to remove by conventional purification systems. This creates the need for periodic analyses, which are nowadays manually performed by experts. These labor-intensive processes are...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-02-01
|
| Series: | Heliyon |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405844024013987 |
| _version_ | 1797304460966363136 |
|---|---|
| author | Jorge Figueroa David Rivas-Villar José Rouco Jorge Novo |
| author_facet | Jorge Figueroa David Rivas-Villar José Rouco Jorge Novo |
| author_sort | Jorge Figueroa |
| collection | DOAJ |
| description | Water quality can be negatively affected by the presence of some toxic phytoplankton species, whose toxins are difficult to remove by conventional purification systems. This creates the need for periodic analyses, which are nowadays manually performed by experts. These labor-intensive processes are affected by subjectivity and expertise, causing unreliability. Some automatic systems have been proposed to address these limitations. However, most of them are based on classical image processing pipelines with not easily scalable designs. In this context, deep learning techniques are more adequate for the detection and recognition of phytoplankton specimens in multi-specimen microscopy images, as they integrate both tasks in a single end-to-end trainable module that is able to automatize the adaption to such a complex domain. In this work, we explore the use of two different object detectors: Faster R-CNN and RetinaNet, from the one-stage and two-stage paradigms respectively. We use a dataset composed of multi-specimen microscopy images captured using a systematic protocol. This allows the use of widely available optical microscopes, also avoiding manual adjustments on a per-specimen basis, which would require expert knowledge. We have made our dataset publicly available to improve the reproducibility and to foment the development of new alternatives in the field. The selected Faster R-CNN methodology reaches maximum recall levels of 95.35%, 84.69%, and 79.81%, and precisions of 94.68%, 89.30% and 82.61%, for W. naegeliana, A. spiroides, and D. sociale, respectively. The system is able to adapt to the dataset problems and improves the results overall with respect to the reference state-of-the-art work. In addition, the proposed system improves the automation and abstraction from the domain and simplifies the workflow and adjustment. |
| first_indexed | 2024-03-08T00:09:50Z |
| format | Article |
| id | doaj.art-19d7733abe854ac8a7b2f1b10407b3f0 |
| institution | Directory Open Access Journal |
| issn | 2405-8440 |
| language | English |
| last_indexed | 2024-03-08T00:09:50Z |
| publishDate | 2024-02-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Heliyon |
| spelling | doaj.art-19d7733abe854ac8a7b2f1b10407b3f02024-02-17T06:40:52ZengElsevierHeliyon2405-84402024-02-01103e25367Phytoplankton detection and recognition in freshwater digital microscopy images using deep learning object detectorsJorge Figueroa0David Rivas-Villar1José Rouco2Jorge Novo3Centro de investigacion CITIC, Universidade da Coruña, 15071 A Coruña, Spain; Grupo VARPA, Instituto de Investigacion Biomédica de A Coruña (INIBIC), Universidade da Coruna, 15006 A Coruña, Spain; Corresponding author at: Centro de investigacion CITIC, Universidade da Coruña, 15071 A Coruña, Spain.Centro de investigacion CITIC, Universidade da Coruña, 15071 A Coruña, Spain; Grupo VARPA, Instituto de Investigacion Biomédica de A Coruña (INIBIC), Universidade da Coruna, 15006 A Coruña, SpainCentro de investigacion CITIC, Universidade da Coruña, 15071 A Coruña, Spain; Grupo VARPA, Instituto de Investigacion Biomédica de A Coruña (INIBIC), Universidade da Coruna, 15006 A Coruña, SpainCentro de investigacion CITIC, Universidade da Coruña, 15071 A Coruña, Spain; Grupo VARPA, Instituto de Investigacion Biomédica de A Coruña (INIBIC), Universidade da Coruna, 15006 A Coruña, SpainWater quality can be negatively affected by the presence of some toxic phytoplankton species, whose toxins are difficult to remove by conventional purification systems. This creates the need for periodic analyses, which are nowadays manually performed by experts. These labor-intensive processes are affected by subjectivity and expertise, causing unreliability. Some automatic systems have been proposed to address these limitations. However, most of them are based on classical image processing pipelines with not easily scalable designs. In this context, deep learning techniques are more adequate for the detection and recognition of phytoplankton specimens in multi-specimen microscopy images, as they integrate both tasks in a single end-to-end trainable module that is able to automatize the adaption to such a complex domain. In this work, we explore the use of two different object detectors: Faster R-CNN and RetinaNet, from the one-stage and two-stage paradigms respectively. We use a dataset composed of multi-specimen microscopy images captured using a systematic protocol. This allows the use of widely available optical microscopes, also avoiding manual adjustments on a per-specimen basis, which would require expert knowledge. We have made our dataset publicly available to improve the reproducibility and to foment the development of new alternatives in the field. The selected Faster R-CNN methodology reaches maximum recall levels of 95.35%, 84.69%, and 79.81%, and precisions of 94.68%, 89.30% and 82.61%, for W. naegeliana, A. spiroides, and D. sociale, respectively. The system is able to adapt to the dataset problems and improves the results overall with respect to the reference state-of-the-art work. In addition, the proposed system improves the automation and abstraction from the domain and simplifies the workflow and adjustment.http://www.sciencedirect.com/science/article/pii/S2405844024013987Microscopy imagesPhytoplankton detectionDeep learningFaster R-CNNRetinaNet |
| spellingShingle | Jorge Figueroa David Rivas-Villar José Rouco Jorge Novo Phytoplankton detection and recognition in freshwater digital microscopy images using deep learning object detectors Heliyon Microscopy images Phytoplankton detection Deep learning Faster R-CNN RetinaNet |
| title | Phytoplankton detection and recognition in freshwater digital microscopy images using deep learning object detectors |
| title_full | Phytoplankton detection and recognition in freshwater digital microscopy images using deep learning object detectors |
| title_fullStr | Phytoplankton detection and recognition in freshwater digital microscopy images using deep learning object detectors |
| title_full_unstemmed | Phytoplankton detection and recognition in freshwater digital microscopy images using deep learning object detectors |
| title_short | Phytoplankton detection and recognition in freshwater digital microscopy images using deep learning object detectors |
| title_sort | phytoplankton detection and recognition in freshwater digital microscopy images using deep learning object detectors |
| topic | Microscopy images Phytoplankton detection Deep learning Faster R-CNN RetinaNet |
| url | http://www.sciencedirect.com/science/article/pii/S2405844024013987 |
| work_keys_str_mv | AT jorgefigueroa phytoplanktondetectionandrecognitioninfreshwaterdigitalmicroscopyimagesusingdeeplearningobjectdetectors AT davidrivasvillar phytoplanktondetectionandrecognitioninfreshwaterdigitalmicroscopyimagesusingdeeplearningobjectdetectors AT joserouco phytoplanktondetectionandrecognitioninfreshwaterdigitalmicroscopyimagesusingdeeplearningobjectdetectors AT jorgenovo phytoplanktondetectionandrecognitioninfreshwaterdigitalmicroscopyimagesusingdeeplearningobjectdetectors |