1
|
Nakayama LF, Matos J, Quion J, Novaes F, Mitchell WG, Mwavu R, Hung CJYJ, Santiago APD, Phanphruk W, Cardoso JS, Celi LA. Unmasking biases and navigating pitfalls in the ophthalmic artificial intelligence lifecycle: A narrative review. PLOS DIGITAL HEALTH 2024; 3:e0000618. [PMID: 39378192 PMCID: PMC11460710 DOI: 10.1371/journal.pdig.0000618] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 10/10/2024]
Abstract
Over the past 2 decades, exponential growth in data availability, computational power, and newly available modeling techniques has led to an expansion in interest, investment, and research in Artificial Intelligence (AI) applications. Ophthalmology is one of many fields that seek to benefit from AI given the advent of telemedicine screening programs and the use of ancillary imaging. However, before AI can be widely deployed, further work must be done to avoid the pitfalls within the AI lifecycle. This review article breaks down the AI lifecycle into seven steps-data collection; defining the model task; data preprocessing and labeling; model development; model evaluation and validation; deployment; and finally, post-deployment evaluation, monitoring, and system recalibration-and delves into the risks for harm at each step and strategies for mitigating them.
Collapse
Affiliation(s)
- Luis Filipe Nakayama
- Department of Ophthalmology, Sao Paulo Federal University, Sao Paulo, Sao Paulo, Brazil
- Laboratory for Computational Physiology, Massachusetts Institute of Technology, Cambridge, Massachusetts, United States of America
| | - João Matos
- Laboratory for Computational Physiology, Massachusetts Institute of Technology, Cambridge, Massachusetts, United States of America
- Faculty of Engineering (FEUP), University of Porto, Porto, Portugal
- Institute for Systems and Computer Engineering (INESC TEC), Technology and Science, Porto, Portugal
| | - Justin Quion
- Laboratory for Computational Physiology, Massachusetts Institute of Technology, Cambridge, Massachusetts, United States of America
| | - Frederico Novaes
- Department of Ophthalmology, Sao Paulo Federal University, Sao Paulo, Sao Paulo, Brazil
| | | | - Rogers Mwavu
- Department of Information Technology, Mbarara University of Science and Technology, Mbarara, Uganda
| | - Claudia Ju-Yi Ji Hung
- Department of Ophthalmology, Byers Eye Institute at Stanford, California, United States of America
- Department of Computer Science and Information Engineering, National Taiwan University, Taiwan
| | - Alvina Pauline Dy Santiago
- University of the Philippines Manila College of Medicine, Manila, Philippines
- Division of Pediatric Ophthalmology, Department of Ophthalmology & Visual Sciences, Philippine General Hospital, Manila, Philippines
- Section of Pediatric Ophthalmology, Eye and Vision Institute, The Medical City, Pasig, Philippines
- Section of Pediatric Ophthalmology, International Eye and Institute, St. Luke’s Medical Center, Quezon City, Philippines
| | - Warachaya Phanphruk
- Department of Ophthalmology, Faculty of Medicine, Khon Kaen University, Khon Kaen, Thailand
| | - Jaime S. Cardoso
- Faculty of Engineering (FEUP), University of Porto, Porto, Portugal
- Institute for Systems and Computer Engineering (INESC TEC), Technology and Science, Porto, Portugal
| | - Leo Anthony Celi
- Laboratory for Computational Physiology, Massachusetts Institute of Technology, Cambridge, Massachusetts, United States of America
- Department of Biostatistics, Harvard TH Chan School of Public Health, Boston, Massachusetts, United States of America
- Department of Medicine, Beth Israel Deaconess Medical Center, Boston, Massachusetts, United States of America
| |
Collapse
|
2
|
Horry MJ, Chakraborty S, Pradhan B, Paul M, Zhu J, Loh HW, Barua PD, Acharya UR. Development of Debiasing Technique for Lung Nodule Chest X-ray Datasets to Generalize Deep Learning Models. SENSORS (BASEL, SWITZERLAND) 2023; 23:6585. [PMID: 37514877 PMCID: PMC10385599 DOI: 10.3390/s23146585] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/14/2023] [Revised: 07/16/2023] [Accepted: 07/20/2023] [Indexed: 07/30/2023]
Abstract
Screening programs for early lung cancer diagnosis are uncommon, primarily due to the challenge of reaching at-risk patients located in rural areas far from medical facilities. To overcome this obstacle, a comprehensive approach is needed that combines mobility, low cost, speed, accuracy, and privacy. One potential solution lies in combining the chest X-ray imaging mode with federated deep learning, ensuring that no single data source can bias the model adversely. This study presents a pre-processing pipeline designed to debias chest X-ray images, thereby enhancing internal classification and external generalization. The pipeline employs a pruning mechanism to train a deep learning model for nodule detection, utilizing the most informative images from a publicly available lung nodule X-ray dataset. Histogram equalization is used to remove systematic differences in image brightness and contrast. Model training is then performed using combinations of lung field segmentation, close cropping, and rib/bone suppression. The resulting deep learning models, generated through this pre-processing pipeline, demonstrate successful generalization on an independent lung nodule dataset. By eliminating confounding variables in chest X-ray images and suppressing signal noise from the bone structures, the proposed deep learning lung nodule detection algorithm achieves an external generalization accuracy of 89%. This approach paves the way for the development of a low-cost and accessible deep learning-based clinical system for lung cancer screening.
Collapse
Affiliation(s)
- Michael J Horry
- Centre for Advanced Modelling and Geospatial Information Systems (CAMGIS), Faculty of Engineering and Information Technology, University of Technology Sydney, Ultimo, NSW 2007, Australia
- IBM Australia Limited, Sydney, NSW 2000, Australia
| | - Subrata Chakraborty
- Centre for Advanced Modelling and Geospatial Information Systems (CAMGIS), Faculty of Engineering and Information Technology, University of Technology Sydney, Ultimo, NSW 2007, Australia
- Faculty of Science, Agriculture, Business and Law, University of New England, Armidale, NSW 2351, Australia
| | - Biswajeet Pradhan
- Centre for Advanced Modelling and Geospatial Information Systems (CAMGIS), Faculty of Engineering and Information Technology, University of Technology Sydney, Ultimo, NSW 2007, Australia
- Earth Observation Center, Institute of Climate Change, Universiti Kebangsaan Malaysia, Bangi 43600, Malaysia
| | - Manoranjan Paul
- Machine Vision and Digital Health (MaViDH), School of Computing and Mathematics, Charles Sturt University, Bathurst, NSW 2795, Australia
| | - Jing Zhu
- Department of Radiology, Westmead Hospital, Westmead, NSW 2145, Australia
| | - Hui Wen Loh
- School of Science and Technology, Singapore University of Social Sciences, Singapore 599494, Singapore
| | - Prabal Datta Barua
- Centre for Advanced Modelling and Geospatial Information Systems (CAMGIS), Faculty of Engineering and Information Technology, University of Technology Sydney, Ultimo, NSW 2007, Australia
- Faculty of Science, Agriculture, Business and Law, University of New England, Armidale, NSW 2351, Australia
- Cogninet Brain Team, Cogninet Australia, Sydney, NSW 2010, Australia
- School of Business (Information Systems), Faculty of Business, Education, Law & Arts, University of Southern Queensland, Toowoomba, QLD 4350, Australia
| | - U Rajendra Acharya
- School of Mathematics, Physics and Computing, University of Southern Queensland, Springfield, QLD 4300, Australia
| |
Collapse
|