AxiWorm: a new tool using YOLOv5 to test antiparasitic drugs against Trichinella spiralis
Abstract Background-Objective Trichinella spiralis drug development and control need an objective high throughput system to assess first stage larvae (L1) viability. YOLOv5 is an image recognition tool easily trained to count muscular first stage larvae (L1) and recognize morphological differences....
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-02-01
|
| Series: | Parasites & Vectors |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13071-025-06664-8 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1825197648376758272 |
|---|---|
| author | Javier Sánchez-Montejo Miguel Marín María Alejandra Villamizar-Monsalve María del Carmen Vieira Belén Vicente Rafael Peláez Julio López-Abán Antonio Muro |
| author_facet | Javier Sánchez-Montejo Miguel Marín María Alejandra Villamizar-Monsalve María del Carmen Vieira Belén Vicente Rafael Peláez Julio López-Abán Antonio Muro |
| author_sort | Javier Sánchez-Montejo |
| collection | DOAJ |
| description | Abstract Background-Objective Trichinella spiralis drug development and control need an objective high throughput system to assess first stage larvae (L1) viability. YOLOv5 is an image recognition tool easily trained to count muscular first stage larvae (L1) and recognize morphological differences. Here we developed a semi-automated system based on YOLOv5 to capture photographs of 96 well microplates and use them for L1 count and morphological damage evaluation after experimental drug treatments. Material and methods Morphological properties were used to distinguish L1 from debris after pepsin muscle digestion and distinguish healthy (serpentine) or damaged (coiled) L1s after 72 h untreated or treated with albendazole or mebendazole cultures. An AxiDraw robotic arm with a smartphone was used to scan 96 well microplates and store photographs. Images of L1 were manually annotated, and augmented based on exposure, bounding, blur, noise, and mosaicism. Results A total of 1309 photographs were obtained that after L1 labeling and data augmentation gave 27478 images. The final dataset of 12571 healthy and 14907 affected L1s was used for training, testing, and validating in a ratio of 70/20/10 respectively. A correlation of 92% was found in a blinded comparison with bare-eye assessment by experienced technicians. Conclusion YOLOv5 is capable of accurately counting and distinguishing between healthy and affected L1s, thus improving the performance of the assessment of meat inspection and potential new drugs. Graphical Abstract |
| format | Article |
| id | doaj-art-9b26eb59a5fa45bfb01cbea99fc53b00 |
| institution | Kabale University |
| issn | 1756-3305 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | BMC |
| record_format | Article |
| series | Parasites & Vectors |
| spelling | doaj-art-9b26eb59a5fa45bfb01cbea99fc53b002025-02-09T12:15:14ZengBMCParasites & Vectors1756-33052025-02-0118111010.1186/s13071-025-06664-8AxiWorm: a new tool using YOLOv5 to test antiparasitic drugs against Trichinella spiralisJavier Sánchez-Montejo0Miguel Marín1María Alejandra Villamizar-Monsalve2María del Carmen Vieira3Belén Vicente4Rafael Peláez5Julio López-Abán6Antonio Muro7Infectious and Tropical Diseases Research Group (E-INTRO), Biomedical Research Institute of Salamanca-Research Centre for Tropical Diseases at the University of Salamanca (IBSAL-CIETUS), Faculty of Pharmacy, University of SalamancaDepartment of Pharmaceutical Sciences, Biomedical Research Institute of Salamanca-Research Centre for Tropical Diseases at the University of Salamanca (IBSAL-CIETUS), Faculty of Pharmacy, University of SalamancaInfectious and Tropical Diseases Research Group (E-INTRO), Biomedical Research Institute of Salamanca-Research Centre for Tropical Diseases at the University of Salamanca (IBSAL-CIETUS), Faculty of Pharmacy, University of SalamancaInfectious and Tropical Diseases Research Group (E-INTRO), Biomedical Research Institute of Salamanca-Research Centre for Tropical Diseases at the University of Salamanca (IBSAL-CIETUS), Faculty of Pharmacy, University of SalamancaInfectious and Tropical Diseases Research Group (E-INTRO), Biomedical Research Institute of Salamanca-Research Centre for Tropical Diseases at the University of Salamanca (IBSAL-CIETUS), Faculty of Pharmacy, University of SalamancaDepartment of Pharmaceutical Sciences, Biomedical Research Institute of Salamanca-Research Centre for Tropical Diseases at the University of Salamanca (IBSAL-CIETUS), Faculty of Pharmacy, University of SalamancaInfectious and Tropical Diseases Research Group (E-INTRO), Biomedical Research Institute of Salamanca-Research Centre for Tropical Diseases at the University of Salamanca (IBSAL-CIETUS), Faculty of Pharmacy, University of SalamancaInfectious and Tropical Diseases Research Group (E-INTRO), Biomedical Research Institute of Salamanca-Research Centre for Tropical Diseases at the University of Salamanca (IBSAL-CIETUS), Faculty of Pharmacy, University of SalamancaAbstract Background-Objective Trichinella spiralis drug development and control need an objective high throughput system to assess first stage larvae (L1) viability. YOLOv5 is an image recognition tool easily trained to count muscular first stage larvae (L1) and recognize morphological differences. Here we developed a semi-automated system based on YOLOv5 to capture photographs of 96 well microplates and use them for L1 count and morphological damage evaluation after experimental drug treatments. Material and methods Morphological properties were used to distinguish L1 from debris after pepsin muscle digestion and distinguish healthy (serpentine) or damaged (coiled) L1s after 72 h untreated or treated with albendazole or mebendazole cultures. An AxiDraw robotic arm with a smartphone was used to scan 96 well microplates and store photographs. Images of L1 were manually annotated, and augmented based on exposure, bounding, blur, noise, and mosaicism. Results A total of 1309 photographs were obtained that after L1 labeling and data augmentation gave 27478 images. The final dataset of 12571 healthy and 14907 affected L1s was used for training, testing, and validating in a ratio of 70/20/10 respectively. A correlation of 92% was found in a blinded comparison with bare-eye assessment by experienced technicians. Conclusion YOLOv5 is capable of accurately counting and distinguishing between healthy and affected L1s, thus improving the performance of the assessment of meat inspection and potential new drugs. Graphical Abstracthttps://doi.org/10.1186/s13071-025-06664-8Trichinella spiralisYOLOv5Computer visionDrug screeningAxiWorm |
| spellingShingle | Javier Sánchez-Montejo Miguel Marín María Alejandra Villamizar-Monsalve María del Carmen Vieira Belén Vicente Rafael Peláez Julio López-Abán Antonio Muro AxiWorm: a new tool using YOLOv5 to test antiparasitic drugs against Trichinella spiralis Parasites & Vectors Trichinella spiralis YOLOv5 Computer vision Drug screening AxiWorm |
| title | AxiWorm: a new tool using YOLOv5 to test antiparasitic drugs against Trichinella spiralis |
| title_full | AxiWorm: a new tool using YOLOv5 to test antiparasitic drugs against Trichinella spiralis |
| title_fullStr | AxiWorm: a new tool using YOLOv5 to test antiparasitic drugs against Trichinella spiralis |
| title_full_unstemmed | AxiWorm: a new tool using YOLOv5 to test antiparasitic drugs against Trichinella spiralis |
| title_short | AxiWorm: a new tool using YOLOv5 to test antiparasitic drugs against Trichinella spiralis |
| title_sort | axiworm a new tool using yolov5 to test antiparasitic drugs against trichinella spiralis |
| topic | Trichinella spiralis YOLOv5 Computer vision Drug screening AxiWorm |
| url | https://doi.org/10.1186/s13071-025-06664-8 |
| work_keys_str_mv | AT javiersanchezmontejo axiwormanewtoolusingyolov5totestantiparasiticdrugsagainsttrichinellaspiralis AT miguelmarin axiwormanewtoolusingyolov5totestantiparasiticdrugsagainsttrichinellaspiralis AT mariaalejandravillamizarmonsalve axiwormanewtoolusingyolov5totestantiparasiticdrugsagainsttrichinellaspiralis AT mariadelcarmenvieira axiwormanewtoolusingyolov5totestantiparasiticdrugsagainsttrichinellaspiralis AT belenvicente axiwormanewtoolusingyolov5totestantiparasiticdrugsagainsttrichinellaspiralis AT rafaelpelaez axiwormanewtoolusingyolov5totestantiparasiticdrugsagainsttrichinellaspiralis AT juliolopezaban axiwormanewtoolusingyolov5totestantiparasiticdrugsagainsttrichinellaspiralis AT antoniomuro axiwormanewtoolusingyolov5totestantiparasiticdrugsagainsttrichinellaspiralis |