AI models for automated segmentation of engineered polycystic kidney tubules
Abstract Autosomal dominant polycystic kidney disease (ADPKD) is a monogenic, rare disease, characterized by the formation of multiple cysts that grow out of the renal tubules. Despite intensive attempts to develop new drugs or repurpose existing ones, there is currently no definitive cure for ADPKD...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-02-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-024-52677-1 |
| _version_ | 1797274650067075072 |
|---|---|
| author | Simone Monaco Nicole Bussola Sara Buttò Diego Sona Flavio Giobergia Giuseppe Jurman Christodoulos Xinaris Daniele Apiletti |
| author_facet | Simone Monaco Nicole Bussola Sara Buttò Diego Sona Flavio Giobergia Giuseppe Jurman Christodoulos Xinaris Daniele Apiletti |
| author_sort | Simone Monaco |
| collection | DOAJ |
| description | Abstract Autosomal dominant polycystic kidney disease (ADPKD) is a monogenic, rare disease, characterized by the formation of multiple cysts that grow out of the renal tubules. Despite intensive attempts to develop new drugs or repurpose existing ones, there is currently no definitive cure for ADPKD. This is primarily due to the complex and variable pathogenesis of the disease and the lack of models that can faithfully reproduce the human phenotype. Therefore, the development of models that allow automated detection of cysts’ growth directly on human kidney tissue is a crucial step in the search for efficient therapeutic solutions. Artificial Intelligence methods, and deep learning algorithms in particular, can provide powerful and effective solutions to such tasks, and indeed various architectures have been proposed in the literature in recent years. Here, we comparatively review state-of-the-art deep learning segmentation models, using as a testbed a set of sequential RGB immunofluorescence images from 4 in vitro experiments with 32 engineered polycystic kidney tubules. To gain a deeper understanding of the detection process, we implemented both pixel-wise and cyst-wise performance metrics to evaluate the algorithms. Overall, two models stand out as the best performing, namely UNet++ and UACANet: the latter uses a self-attention mechanism introducing some explainability aspects that can be further exploited in future developments, thus making it the most promising algorithm to build upon towards a more refined cyst-detection platform. UACANet model achieves a cyst-wise Intersection over Union of 0.83, 0.91 for Recall, and 0.92 for Precision when applied to detect large-size cysts. On all-size cysts, UACANet averages at 0.624 pixel-wise Intersection over Union. The code to reproduce all results is freely available in a public GitHub repository. |
| first_indexed | 2024-03-07T15:02:19Z |
| format | Article |
| id | doaj.art-697e7ac4757d4de2b8f1248c5b9ee9de |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-03-07T15:02:19Z |
| publishDate | 2024-02-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-697e7ac4757d4de2b8f1248c5b9ee9de2024-03-05T19:05:51ZengNature PortfolioScientific Reports2045-23222024-02-0114111610.1038/s41598-024-52677-1AI models for automated segmentation of engineered polycystic kidney tubulesSimone Monaco0Nicole Bussola1Sara Buttò2Diego Sona3Flavio Giobergia4Giuseppe Jurman5Christodoulos Xinaris6Daniele Apiletti7DAUIN, Politecnico di TorinoFondazione Bruno KesslerIstituto di Ricerche Farmacologiche Mario Negri - IRCCSFondazione Bruno KesslerDAUIN, Politecnico di TorinoFondazione Bruno KesslerIstituto di Ricerche Farmacologiche Mario Negri - IRCCSDAUIN, Politecnico di TorinoAbstract Autosomal dominant polycystic kidney disease (ADPKD) is a monogenic, rare disease, characterized by the formation of multiple cysts that grow out of the renal tubules. Despite intensive attempts to develop new drugs or repurpose existing ones, there is currently no definitive cure for ADPKD. This is primarily due to the complex and variable pathogenesis of the disease and the lack of models that can faithfully reproduce the human phenotype. Therefore, the development of models that allow automated detection of cysts’ growth directly on human kidney tissue is a crucial step in the search for efficient therapeutic solutions. Artificial Intelligence methods, and deep learning algorithms in particular, can provide powerful and effective solutions to such tasks, and indeed various architectures have been proposed in the literature in recent years. Here, we comparatively review state-of-the-art deep learning segmentation models, using as a testbed a set of sequential RGB immunofluorescence images from 4 in vitro experiments with 32 engineered polycystic kidney tubules. To gain a deeper understanding of the detection process, we implemented both pixel-wise and cyst-wise performance metrics to evaluate the algorithms. Overall, two models stand out as the best performing, namely UNet++ and UACANet: the latter uses a self-attention mechanism introducing some explainability aspects that can be further exploited in future developments, thus making it the most promising algorithm to build upon towards a more refined cyst-detection platform. UACANet model achieves a cyst-wise Intersection over Union of 0.83, 0.91 for Recall, and 0.92 for Precision when applied to detect large-size cysts. On all-size cysts, UACANet averages at 0.624 pixel-wise Intersection over Union. The code to reproduce all results is freely available in a public GitHub repository.https://doi.org/10.1038/s41598-024-52677-1 |
| spellingShingle | Simone Monaco Nicole Bussola Sara Buttò Diego Sona Flavio Giobergia Giuseppe Jurman Christodoulos Xinaris Daniele Apiletti AI models for automated segmentation of engineered polycystic kidney tubules Scientific Reports |
| title | AI models for automated segmentation of engineered polycystic kidney tubules |
| title_full | AI models for automated segmentation of engineered polycystic kidney tubules |
| title_fullStr | AI models for automated segmentation of engineered polycystic kidney tubules |
| title_full_unstemmed | AI models for automated segmentation of engineered polycystic kidney tubules |
| title_short | AI models for automated segmentation of engineered polycystic kidney tubules |
| title_sort | ai models for automated segmentation of engineered polycystic kidney tubules |
| url | https://doi.org/10.1038/s41598-024-52677-1 |
| work_keys_str_mv | AT simonemonaco aimodelsforautomatedsegmentationofengineeredpolycystickidneytubules AT nicolebussola aimodelsforautomatedsegmentationofengineeredpolycystickidneytubules AT sarabutto aimodelsforautomatedsegmentationofengineeredpolycystickidneytubules AT diegosona aimodelsforautomatedsegmentationofengineeredpolycystickidneytubules AT flaviogiobergia aimodelsforautomatedsegmentationofengineeredpolycystickidneytubules AT giuseppejurman aimodelsforautomatedsegmentationofengineeredpolycystickidneytubules AT christodoulosxinaris aimodelsforautomatedsegmentationofengineeredpolycystickidneytubules AT danieleapiletti aimodelsforautomatedsegmentationofengineeredpolycystickidneytubules |