An intelligent decision-making system for early diagnosis of macular pathology
Purpose: to develop a software technology based on artificial intelligence methods aimed at analyzing large volumes of optical coherent tomography (OCT) data in order to identify early symptoms of age-related macular degeneration (AMD) and the transition from dry AMD to neovascular AMD (nAMD).Materi...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | Russian |
| Published: |
Real Time Ltd
2022-06-01
|
| Series: | Российский офтальмологический журнал |
| Subjects: | |
| Online Access: | https://roj.igb.ru/jour/article/view/963 |
| _version_ | 1826569898103406592 |
|---|---|
| author | T. G. Kamenskikh O. N. Dolinina I. O. Kolbenev E. V. Veselova |
| author_facet | T. G. Kamenskikh O. N. Dolinina I. O. Kolbenev E. V. Veselova |
| author_sort | T. G. Kamenskikh |
| collection | DOAJ |
| description | Purpose: to develop a software technology based on artificial intelligence methods aimed at analyzing large volumes of optical coherent tomography (OCT) data in order to identify early symptoms of age-related macular degeneration (AMD) and the transition from dry AMD to neovascular AMD (nAMD).Material and methods. Patients with dry AMD (1125 eyes), wet nAMD (1200 eyes) and subjects without ophthalmic pathology (1205 eyes) underwent a standard ophthalmological examination and macular OCT (Cirrus HD-OCT 4000, Carl Zeiss Meditec AG, Germany) according to the MacularCube scanning protocol with a standard ETDRS macular map. The thickness of the retina from the inner limiting membrane to the retinal pigment epithelium and the presence and location of fovea configuration changes were determined.Results. Two ultra-precise artificial neural networks (ANN) were created: one intended to identify patients with early signs of dry AMD and the other to identify those with signs of nAMD. By the time when 1000 training images were processed, the image interpretation decision-making accuracy in the first ANN increased to reach 97.6%, in the second ANN, to 96.8%, which shows the high efficiency of this technology. The deep learning processes were run on an Amazon Web Service EC2 GPU. The trained ANN model was also tested on healthy eyes at each estimated probability value. The correspondence between the doctor's diagnosis and the decision taken by the ANN was assessed.Conclusions. A software technology based on artificial intelligence methods has been developed, which answered the need to process a large amount of OCT data. The technology proved effective in identifying early symptoms of dry and wet forms of AMD and in early diagnosis of the transition of the dry form of AMD into neovascular form, the latter requiring immediate treatment. |
| first_indexed | 2024-04-10T02:30:53Z |
| format | Article |
| id | doaj.art-dcd247f2d92a4dc58125d2504696b500 |
| institution | Directory Open Access Journal |
| issn | 2072-0076 2587-5760 |
| language | Russian |
| last_indexed | 2025-03-14T11:46:38Z |
| publishDate | 2022-06-01 |
| publisher | Real Time Ltd |
| record_format | Article |
| series | Российский офтальмологический журнал |
| spelling | doaj.art-dcd247f2d92a4dc58125d2504696b5002025-03-02T09:51:28ZrusReal Time LtdРоссийский офтальмологический журнал2072-00762587-57602022-06-01152 (Прил)697410.21516/2072-0076-2022-15-2-supplement-69-74452An intelligent decision-making system for early diagnosis of macular pathologyT. G. Kamenskikh0O. N. Dolinina1I. O. Kolbenev2E. V. Veselova3V.I. Razumovsky Saratov State Medical UniversityInstitute of Applied Technologies and Communications, Yuri Gagarin Saratov State Technical UniversityV.I. Razumovsky Saratov State Medical UniversityV.I. Razumovsky Saratov State Medical UniversityPurpose: to develop a software technology based on artificial intelligence methods aimed at analyzing large volumes of optical coherent tomography (OCT) data in order to identify early symptoms of age-related macular degeneration (AMD) and the transition from dry AMD to neovascular AMD (nAMD).Material and methods. Patients with dry AMD (1125 eyes), wet nAMD (1200 eyes) and subjects without ophthalmic pathology (1205 eyes) underwent a standard ophthalmological examination and macular OCT (Cirrus HD-OCT 4000, Carl Zeiss Meditec AG, Germany) according to the MacularCube scanning protocol with a standard ETDRS macular map. The thickness of the retina from the inner limiting membrane to the retinal pigment epithelium and the presence and location of fovea configuration changes were determined.Results. Two ultra-precise artificial neural networks (ANN) were created: one intended to identify patients with early signs of dry AMD and the other to identify those with signs of nAMD. By the time when 1000 training images were processed, the image interpretation decision-making accuracy in the first ANN increased to reach 97.6%, in the second ANN, to 96.8%, which shows the high efficiency of this technology. The deep learning processes were run on an Amazon Web Service EC2 GPU. The trained ANN model was also tested on healthy eyes at each estimated probability value. The correspondence between the doctor's diagnosis and the decision taken by the ANN was assessed.Conclusions. A software technology based on artificial intelligence methods has been developed, which answered the need to process a large amount of OCT data. The technology proved effective in identifying early symptoms of dry and wet forms of AMD and in early diagnosis of the transition of the dry form of AMD into neovascular form, the latter requiring immediate treatment.https://roj.igb.ru/jour/article/view/963amddry formneovascular formartificial neural network |
| spellingShingle | T. G. Kamenskikh O. N. Dolinina I. O. Kolbenev E. V. Veselova An intelligent decision-making system for early diagnosis of macular pathology Российский офтальмологический журнал amd dry form neovascular form artificial neural network |
| title | An intelligent decision-making system for early diagnosis of macular pathology |
| title_full | An intelligent decision-making system for early diagnosis of macular pathology |
| title_fullStr | An intelligent decision-making system for early diagnosis of macular pathology |
| title_full_unstemmed | An intelligent decision-making system for early diagnosis of macular pathology |
| title_short | An intelligent decision-making system for early diagnosis of macular pathology |
| title_sort | intelligent decision making system for early diagnosis of macular pathology |
| topic | amd dry form neovascular form artificial neural network |
| url | https://roj.igb.ru/jour/article/view/963 |
| work_keys_str_mv | AT tgkamenskikh anintelligentdecisionmakingsystemforearlydiagnosisofmacularpathology AT ondolinina anintelligentdecisionmakingsystemforearlydiagnosisofmacularpathology AT iokolbenev anintelligentdecisionmakingsystemforearlydiagnosisofmacularpathology AT evveselova anintelligentdecisionmakingsystemforearlydiagnosisofmacularpathology AT tgkamenskikh intelligentdecisionmakingsystemforearlydiagnosisofmacularpathology AT ondolinina intelligentdecisionmakingsystemforearlydiagnosisofmacularpathology AT iokolbenev intelligentdecisionmakingsystemforearlydiagnosisofmacularpathology AT evveselova intelligentdecisionmakingsystemforearlydiagnosisofmacularpathology |