Artificial Intelligence Based Analysis of Corneal Confocal Microscopy Images for Diagnosing Peripheral Neuropathy: A Binary Classification Model
Diabetic peripheral neuropathy (DPN) is the leading cause of neuropathy worldwide resulting in excess morbidity and mortality. We aimed to develop an artificial intelligence deep learning algorithm to classify the presence or absence of peripheral neuropathy (PN) in participants with diabetes or pre...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Journal of Clinical Medicine |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-0383/12/4/1284 |
| _version_ | 1797620298986553344 |
|---|---|
| author | Yanda Meng Frank George Preston Maryam Ferdousi Shazli Azmi Ioannis Nikolaos Petropoulos Stephen Kaye Rayaz Ahmed Malik Uazman Alam Yalin Zheng |
| author_facet | Yanda Meng Frank George Preston Maryam Ferdousi Shazli Azmi Ioannis Nikolaos Petropoulos Stephen Kaye Rayaz Ahmed Malik Uazman Alam Yalin Zheng |
| author_sort | Yanda Meng |
| collection | DOAJ |
| description | Diabetic peripheral neuropathy (DPN) is the leading cause of neuropathy worldwide resulting in excess morbidity and mortality. We aimed to develop an artificial intelligence deep learning algorithm to classify the presence or absence of peripheral neuropathy (PN) in participants with diabetes or pre-diabetes using corneal confocal microscopy (CCM) images of the sub-basal nerve plexus. A modified ResNet-50 model was trained to perform the binary classification of PN (PN+) versus no PN (PN−) based on the Toronto consensus criteria. A dataset of 279 participants (149 PN−, 130 PN+) was used to train (<i>n</i> = 200), validate (<i>n</i> = 18), and test (<i>n</i> = 61) the algorithm, utilizing one image per participant. The dataset consisted of participants with type 1 diabetes (<i>n</i> = 88), type 2 diabetes (<i>n</i> = 141), and pre-diabetes (<i>n</i> = 50). The algorithm was evaluated using diagnostic performance metrics and attribution-based methods (gradient-weighted class activation mapping (Grad-CAM) and Guided Grad-CAM). In detecting PN+, the AI-based DLA achieved a sensitivity of 0.91 (95%CI: 0.79–1.0), a specificity of 0.93 (95%CI: 0.83–1.0), and an area under the curve (AUC) of 0.95 (95%CI: 0.83–0.99). Our deep learning algorithm demonstrates excellent results for the diagnosis of PN using CCM. A large-scale prospective real-world study is required to validate its diagnostic efficacy prior to implementation in screening and diagnostic programmes. |
| first_indexed | 2024-03-11T08:39:11Z |
| format | Article |
| id | doaj.art-eb54b39cfa9441888bb49efe3b444afd |
| institution | Directory Open Access Journal |
| issn | 2077-0383 |
| language | English |
| last_indexed | 2024-03-11T08:39:11Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Clinical Medicine |
| spelling | doaj.art-eb54b39cfa9441888bb49efe3b444afd2023-11-16T21:17:24ZengMDPI AGJournal of Clinical Medicine2077-03832023-02-01124128410.3390/jcm12041284Artificial Intelligence Based Analysis of Corneal Confocal Microscopy Images for Diagnosing Peripheral Neuropathy: A Binary Classification ModelYanda Meng0Frank George Preston1Maryam Ferdousi2Shazli Azmi3Ioannis Nikolaos Petropoulos4Stephen Kaye5Rayaz Ahmed Malik6Uazman Alam7Yalin Zheng8Department of Eye and Vision Science, Institute of Life Course and Medical Sciences, University of Liverpool, Liverpool L7 8TX, UKDepartment of Cardiovascular & Metabolic Medicine, Institute of Life Course and Medical Sciences, University of Liverpool, Liverpool L7 8TX, UKInstitute of Cardiovascular Science, University of Manchester, Manchester M13 9PL, UKInstitute of Cardiovascular Science, University of Manchester, Manchester M13 9PL, UKDepartment of Medicine, Weill Cornell Medicine-Qatar, Doha 24144, QatarDepartment of Eye and Vision Science, Institute of Life Course and Medical Sciences, University of Liverpool, Liverpool L7 8TX, UKDepartment of Medicine, Weill Cornell Medicine-Qatar, Doha 24144, QatarDepartment of Cardiovascular & Metabolic Medicine, Institute of Life Course and Medical Sciences, University of Liverpool, Liverpool L7 8TX, UKDepartment of Eye and Vision Science, Institute of Life Course and Medical Sciences, University of Liverpool, Liverpool L7 8TX, UKDiabetic peripheral neuropathy (DPN) is the leading cause of neuropathy worldwide resulting in excess morbidity and mortality. We aimed to develop an artificial intelligence deep learning algorithm to classify the presence or absence of peripheral neuropathy (PN) in participants with diabetes or pre-diabetes using corneal confocal microscopy (CCM) images of the sub-basal nerve plexus. A modified ResNet-50 model was trained to perform the binary classification of PN (PN+) versus no PN (PN−) based on the Toronto consensus criteria. A dataset of 279 participants (149 PN−, 130 PN+) was used to train (<i>n</i> = 200), validate (<i>n</i> = 18), and test (<i>n</i> = 61) the algorithm, utilizing one image per participant. The dataset consisted of participants with type 1 diabetes (<i>n</i> = 88), type 2 diabetes (<i>n</i> = 141), and pre-diabetes (<i>n</i> = 50). The algorithm was evaluated using diagnostic performance metrics and attribution-based methods (gradient-weighted class activation mapping (Grad-CAM) and Guided Grad-CAM). In detecting PN+, the AI-based DLA achieved a sensitivity of 0.91 (95%CI: 0.79–1.0), a specificity of 0.93 (95%CI: 0.83–1.0), and an area under the curve (AUC) of 0.95 (95%CI: 0.83–0.99). Our deep learning algorithm demonstrates excellent results for the diagnosis of PN using CCM. A large-scale prospective real-world study is required to validate its diagnostic efficacy prior to implementation in screening and diagnostic programmes.https://www.mdpi.com/2077-0383/12/4/1284artificial intelligencecorneal confocal microscopydiabetic peripheral neuropathy |
| spellingShingle | Yanda Meng Frank George Preston Maryam Ferdousi Shazli Azmi Ioannis Nikolaos Petropoulos Stephen Kaye Rayaz Ahmed Malik Uazman Alam Yalin Zheng Artificial Intelligence Based Analysis of Corneal Confocal Microscopy Images for Diagnosing Peripheral Neuropathy: A Binary Classification Model Journal of Clinical Medicine artificial intelligence corneal confocal microscopy diabetic peripheral neuropathy |
| title | Artificial Intelligence Based Analysis of Corneal Confocal Microscopy Images for Diagnosing Peripheral Neuropathy: A Binary Classification Model |
| title_full | Artificial Intelligence Based Analysis of Corneal Confocal Microscopy Images for Diagnosing Peripheral Neuropathy: A Binary Classification Model |
| title_fullStr | Artificial Intelligence Based Analysis of Corneal Confocal Microscopy Images for Diagnosing Peripheral Neuropathy: A Binary Classification Model |
| title_full_unstemmed | Artificial Intelligence Based Analysis of Corneal Confocal Microscopy Images for Diagnosing Peripheral Neuropathy: A Binary Classification Model |
| title_short | Artificial Intelligence Based Analysis of Corneal Confocal Microscopy Images for Diagnosing Peripheral Neuropathy: A Binary Classification Model |
| title_sort | artificial intelligence based analysis of corneal confocal microscopy images for diagnosing peripheral neuropathy a binary classification model |
| topic | artificial intelligence corneal confocal microscopy diabetic peripheral neuropathy |
| url | https://www.mdpi.com/2077-0383/12/4/1284 |
| work_keys_str_mv | AT yandameng artificialintelligencebasedanalysisofcornealconfocalmicroscopyimagesfordiagnosingperipheralneuropathyabinaryclassificationmodel AT frankgeorgepreston artificialintelligencebasedanalysisofcornealconfocalmicroscopyimagesfordiagnosingperipheralneuropathyabinaryclassificationmodel AT maryamferdousi artificialintelligencebasedanalysisofcornealconfocalmicroscopyimagesfordiagnosingperipheralneuropathyabinaryclassificationmodel AT shazliazmi artificialintelligencebasedanalysisofcornealconfocalmicroscopyimagesfordiagnosingperipheralneuropathyabinaryclassificationmodel AT ioannisnikolaospetropoulos artificialintelligencebasedanalysisofcornealconfocalmicroscopyimagesfordiagnosingperipheralneuropathyabinaryclassificationmodel AT stephenkaye artificialintelligencebasedanalysisofcornealconfocalmicroscopyimagesfordiagnosingperipheralneuropathyabinaryclassificationmodel AT rayazahmedmalik artificialintelligencebasedanalysisofcornealconfocalmicroscopyimagesfordiagnosingperipheralneuropathyabinaryclassificationmodel AT uazmanalam artificialintelligencebasedanalysisofcornealconfocalmicroscopyimagesfordiagnosingperipheralneuropathyabinaryclassificationmodel AT yalinzheng artificialintelligencebasedanalysisofcornealconfocalmicroscopyimagesfordiagnosingperipheralneuropathyabinaryclassificationmodel |