1
|
Greatbatch CJ, Lu Q, Hung S, Tran SN, Wing K, Liang H, Han X, Zhou T, Siggs OM, Mackey DA, Liu GS, Cook AL, Powell JE, Craig JE, MacGregor S, Hewitt AW. Deep Learning-Based Identification of Intraocular Pressure-Associated Genes Influencing Trabecular Meshwork Cell Morphology. OPHTHALMOLOGY SCIENCE 2024; 4:100504. [PMID: 38682030 PMCID: PMC11046128 DOI: 10.1016/j.xops.2024.100504] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 07/19/2023] [Revised: 02/27/2024] [Accepted: 02/27/2024] [Indexed: 05/01/2024]
Abstract
Purpose Genome-wide association studies have recently uncovered many loci associated with variation in intraocular pressure (IOP). Artificial intelligence (AI) can be used to interrogate the effect of specific genetic knockouts on the morphology of trabecular meshwork cells (TMCs) and thus, IOP regulation. Design Experimental study. Subjects Primary TMCs collected from human donors. Methods Sixty-two genes at 55 loci associated with IOP variation were knocked out in primary TMC lines. All cells underwent high-throughput microscopy imaging after being stained with a 5-channel fluorescent cell staining protocol. A convolutional neural network was trained to distinguish between gene knockout and normal control cell images. The area under the receiver operator curve (AUC) metric was used to quantify morphological variation in gene knockouts to identify potential pathological perturbations. Main Outcome Measures Degree of morphological variation as measured by deep learning algorithm accuracy of differentiation from normal controls. Results Cells where LTBP2 or BCAS3 had been perturbed demonstrated the greatest morphological variation from normal TMCs (AUC 0.851, standard deviation [SD] 0.030; and AUC 0.845, SD 0.020, respectively). Of 7 multigene loci, 5 had statistically significant differences in AUC (P < 0.05) between genes, allowing for pathological gene prioritization. The mitochondrial channel most frequently showed the greatest degree of morphological variation (33.9% of cell lines). Conclusions We demonstrate a robust method for functionally interrogating genome-wide association signals using high-throughput microscopy and AI. Genetic variations inducing marked morphological variation can be readily identified, allowing for the gene-based dissection of loci associated with complex traits. Financial Disclosures Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.
Collapse
Affiliation(s)
- Connor J. Greatbatch
- Menzies Institute for Medical Research, University of Tasmania, Hobart, Tasmania, Australia
| | - Qinyi Lu
- Menzies Institute for Medical Research, University of Tasmania, Hobart, Tasmania, Australia
| | - Sandy Hung
- Centre for Eye Research Australia, University of Melbourne, Melbourne, Victoria, Australia
| | - Son N. Tran
- Department of Information and Communication Technology, University of Tasmania, Hobart, Tasmania, Australia
| | - Kristof Wing
- Menzies Institute for Medical Research, University of Tasmania, Hobart, Tasmania, Australia
| | - Helena Liang
- Centre for Eye Research Australia, University of Melbourne, Melbourne, Victoria, Australia
| | - Xikun Han
- Statistical Genetics Laboratory, QIMR Berghofer Medical Research Institute, Brisbane, Australia
| | - Tiger Zhou
- Department of Ophthalmology, Flinders Medical Centre, Flinders University, Bedford Park, Australia
| | - Owen M. Siggs
- Cellular Genomics Group, Garvan Institute of Medical Research, Sydney, New South Wales, Australia
- Faculty of Medicine and Health, School of Clinical Medicine, UNSW, Sydney, New South Wales, Australia
| | - David A. Mackey
- Menzies Institute for Medical Research, University of Tasmania, Hobart, Tasmania, Australia
- Lions Eye Institute, Centre for Ophthalmology and Visual Science, University of Western Australia, Perth, Western Australia, Australia
| | - Guei-Sheung Liu
- Menzies Institute for Medical Research, University of Tasmania, Hobart, Tasmania, Australia
- Centre for Eye Research Australia, University of Melbourne, Melbourne, Victoria, Australia
| | - Anthony L. Cook
- Wicking Dementia Research and Education Centre, University of Tasmania, Hobart, Tasmania, Australia
| | - Joseph E. Powell
- Garvan-Weizmann Centre for Cellular Genomics, Garvan Institute of Medical Research, Sydney, New South Wales, Australia
- UNSW Cellular Genomics Futures Institute, UNSW, Sydney, New South Wales, Australia
| | - Jamie E. Craig
- Department of Ophthalmology, Flinders Medical Centre, Flinders University, Bedford Park, Australia
| | - Stuart MacGregor
- Statistical Genetics Laboratory, QIMR Berghofer Medical Research Institute, Brisbane, Australia
| | - Alex W. Hewitt
- Menzies Institute for Medical Research, University of Tasmania, Hobart, Tasmania, Australia
- Centre for Eye Research Australia, University of Melbourne, Melbourne, Victoria, Australia
| |
Collapse
|
2
|
Wang J, Peng H, Chen S, Ren S. Ensemble learning for retinal disease recognition under limited resources. Med Biol Eng Comput 2024:10.1007/s11517-024-03101-3. [PMID: 38698189 DOI: 10.1007/s11517-024-03101-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/28/2023] [Accepted: 04/17/2024] [Indexed: 05/05/2024]
Abstract
Retinal optical coherence tomography (OCT) images provide crucial insights into the health of the posterior ocular segment. Therefore, the advancement of automated image analysis methods is imperative to equip clinicians and researchers with quantitative data, thereby facilitating informed decision-making. The application of deep learning (DL)-based approaches has gained extensive traction for executing these analysis tasks, demonstrating remarkable performance compared to labor-intensive manual analyses. However, the acquisition of retinal OCT images often presents challenges stemming from privacy concerns and the resource-intensive labeling procedures, which contradicts the prevailing notion that DL models necessitate substantial data volumes for achieving superior performance. Moreover, limitations in available computational resources constrain the progress of high-performance medical artificial intelligence, particularly in less developed regions and countries. This paper introduces a novel ensemble learning mechanism designed for recognizing retinal diseases under limited resources (e.g., data, computation). The mechanism leverages insights from multiple pre-trained models, facilitating the transfer and adaptation of their knowledge to retinal OCT images. This approach establishes a robust model even when confronted with limited labeled data, eliminating the need for an extensive array of parameters, as required in learning from scratch. Comprehensive experimentation on real-world datasets demonstrates that the ensemble models constructed by the proposed ensemble method show superior performance over the baseline models under sparse labeled data, especially the triple ensemble model, which achieves the accuracy of 92.06%, which is 8.27%, 7.99%, and 11.14% better than the three baseline models, respectively. In addition, compared with the three baseline models learned from scratch, the triple ensemble model has fewer trainable parameters, only 3.677M, which is lower than the three baseline models of 8.013M, 4.302M, and 20.158M, respectively.
Collapse
Affiliation(s)
- Jiahao Wang
- School of Information and Communication Engineering, Hainan University, Haikou, 570228, China
| | - Hong Peng
- School of Information and Communication Engineering, Hainan University, Haikou, 570228, China
| | - Shengchao Chen
- Australian AI Institute, School of Computer Science, FEIT, University of Technology Sydney, Sydney, 2008, NSW, Australia.
| | - Sufen Ren
- School of Information and Communication Engineering, Hainan University, Haikou, 570228, China.
| |
Collapse
|
3
|
Ieracitano C, Mahmud M, Doborjeh M, Lay-Ekuakille A. Editorial Topical Collection: "Explainable and Augmented Machine Learning for Biosignals and Biomedical Images". SENSORS (BASEL, SWITZERLAND) 2023; 23:9722. [PMID: 38139568 PMCID: PMC10747000 DOI: 10.3390/s23249722] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/15/2023] [Accepted: 11/28/2023] [Indexed: 12/24/2023]
Abstract
Machine learning (ML) is a well-known subfield of artificial intelligence (AI) that aims at developing algorithms and statistical models able to empower computer systems to automatically adapt to a specific task through experience or learning from data [...].
Collapse
Affiliation(s)
- Cosimo Ieracitano
- DICEAM Department, University Mediterranea of Reggio Calabria, Via Zehender, Feo di Vito, 89122 Reggio Calabria, Italy
| | - Mufti Mahmud
- Department of Computer Science, Nottingham Trent University, Nottingham NG11 8NS, UK;
- Computing and Informatics Research Centre, Nottingham Trent University, Nottingham NG11 8NS, UK
- Medical Technologies Innovation Facility, Nottingham Trent University, Nottingham NG11 8NS, UK
| | - Maryam Doborjeh
- Computer Science and Software Engineering, Auckland University of Technology, Auckland 1010, New Zealand;
| | - Aimé Lay-Ekuakille
- Department of Innovation Engineering, University of Salento, 73100 Lecce, Italy;
| |
Collapse
|