CLORG: A contrastive learning-based framework for morphological representation and classification of organoids
Organoids are three-dimensional structures derived from stem cells or primary cells, widely used in disease research and regenerative medicine. However, the presence of significant noise and morphological heterogeneity in their bright-field images makes it challenging to distinguish between differen...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-09-01
|
| Series: | Array |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2590005625000736 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849470700576833536 |
|---|---|
| author | Yafang Wei Pengwei Hu Xun Deng Feng Tan Thomas Herget Mei Gao Lun Hu Xin Luo |
| author_facet | Yafang Wei Pengwei Hu Xun Deng Feng Tan Thomas Herget Mei Gao Lun Hu Xin Luo |
| author_sort | Yafang Wei |
| collection | DOAJ |
| description | Organoids are three-dimensional structures derived from stem cells or primary cells, widely used in disease research and regenerative medicine. However, the presence of significant noise and morphological heterogeneity in their bright-field images makes it challenging to distinguish between different categories of organoids. This study is the first to propose a deep learning framework, CLORG, based on supervised contrastive learning. By narrowing the distance between samples of the same class through contrastive learning and incorporating Fourier transform to enhance the representation of frequency-domain information, the framework efficiently performs multi-class classification of organoids. This, in turn, facilitates the analysis of organoid developmental trends and supports drug screening and evaluation. Experiments on colon and intestinal organoid datasets demonstrate that CLORG achieves accuracies of 91.68% and 86.93%, respectively, with improvements of 3.35% and 1.89% over baseline models. The findings validate the effectiveness of CLORG in organoid image multi-class classification tasks and highlight its significant implications for organoid analysis and research. |
| format | Article |
| id | doaj-art-2ef0b0969e1448019a9415ef85172782 |
| institution | Kabale University |
| issn | 2590-0056 |
| language | English |
| publishDate | 2025-09-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Array |
| spelling | doaj-art-2ef0b0969e1448019a9415ef851727822025-08-20T03:25:04ZengElsevierArray2590-00562025-09-012710044610.1016/j.array.2025.100446CLORG: A contrastive learning-based framework for morphological representation and classification of organoidsYafang Wei0Pengwei Hu1Xun Deng2Feng Tan3Thomas Herget4Mei Gao5Lun Hu6Xin Luo7The Xinjiang Technical institute of Physics and Chemistry, Chinese Academy of Sciences, Urumgi, China; Southwest University, Chongqing, ChinaThe Xinjiang Technical institute of Physics and Chemistry, Chinese Academy of Sciences, Urumgi, China; University of Chinese Academy of Sciences, Beijing, China; Corresponding author at: The Xinjiang Technical institute of Physics and Chemistry, Chinese Academy of Sciences, Urumgi, China.The Xinjiang Technical institute of Physics and Chemistry, Chinese Academy of Sciences, Urumgi, China; University of Chinese Academy of Sciences, Beijing, ChinaAl and Quantum Lab, Merck KGaA, Darmstadt, GermanyScience and Technology Office, Merck KGaA, Darmstadt, GermanyChongqing General Hospital, Chongqing University, Chongqing, ChinaThe Xinjiang Technical institute of Physics and Chemistry, Chinese Academy of Sciences, Urumgi, China; University of Chinese Academy of Sciences, Beijing, ChinaSouthwest University, Chongqing, ChinaOrganoids are three-dimensional structures derived from stem cells or primary cells, widely used in disease research and regenerative medicine. However, the presence of significant noise and morphological heterogeneity in their bright-field images makes it challenging to distinguish between different categories of organoids. This study is the first to propose a deep learning framework, CLORG, based on supervised contrastive learning. By narrowing the distance between samples of the same class through contrastive learning and incorporating Fourier transform to enhance the representation of frequency-domain information, the framework efficiently performs multi-class classification of organoids. This, in turn, facilitates the analysis of organoid developmental trends and supports drug screening and evaluation. Experiments on colon and intestinal organoid datasets demonstrate that CLORG achieves accuracies of 91.68% and 86.93%, respectively, with improvements of 3.35% and 1.89% over baseline models. The findings validate the effectiveness of CLORG in organoid image multi-class classification tasks and highlight its significant implications for organoid analysis and research.http://www.sciencedirect.com/science/article/pii/S2590005625000736OrganoidContrastive learningMulti-class classificationDeep learning |
| spellingShingle | Yafang Wei Pengwei Hu Xun Deng Feng Tan Thomas Herget Mei Gao Lun Hu Xin Luo CLORG: A contrastive learning-based framework for morphological representation and classification of organoids Array Organoid Contrastive learning Multi-class classification Deep learning |
| title | CLORG: A contrastive learning-based framework for morphological representation and classification of organoids |
| title_full | CLORG: A contrastive learning-based framework for morphological representation and classification of organoids |
| title_fullStr | CLORG: A contrastive learning-based framework for morphological representation and classification of organoids |
| title_full_unstemmed | CLORG: A contrastive learning-based framework for morphological representation and classification of organoids |
| title_short | CLORG: A contrastive learning-based framework for morphological representation and classification of organoids |
| title_sort | clorg a contrastive learning based framework for morphological representation and classification of organoids |
| topic | Organoid Contrastive learning Multi-class classification Deep learning |
| url | http://www.sciencedirect.com/science/article/pii/S2590005625000736 |
| work_keys_str_mv | AT yafangwei clorgacontrastivelearningbasedframeworkformorphologicalrepresentationandclassificationoforganoids AT pengweihu clorgacontrastivelearningbasedframeworkformorphologicalrepresentationandclassificationoforganoids AT xundeng clorgacontrastivelearningbasedframeworkformorphologicalrepresentationandclassificationoforganoids AT fengtan clorgacontrastivelearningbasedframeworkformorphologicalrepresentationandclassificationoforganoids AT thomasherget clorgacontrastivelearningbasedframeworkformorphologicalrepresentationandclassificationoforganoids AT meigao clorgacontrastivelearningbasedframeworkformorphologicalrepresentationandclassificationoforganoids AT lunhu clorgacontrastivelearningbasedframeworkformorphologicalrepresentationandclassificationoforganoids AT xinluo clorgacontrastivelearningbasedframeworkformorphologicalrepresentationandclassificationoforganoids |