| Autor: |
Sudeshna Sil Kar, Hasan Cetin, Joseph Abraham, Sunil K. Srivastava, Anant Madabhushi, Justis P. Ehlers |
| Jazyk: |
angličtina |
| Rok vydání: |
2024 |
| Předmět: |
|
| Zdroj: |
Scientific Reports, Vol 14, Iss 1, Pp 1-13 (2024) |
| Druh dokumentu: |
article |
| ISSN: |
2045-2322 |
| DOI: |
10.1038/s41598-024-68259-0 |
| Popis: |
Abstract Geographic atrophy (GA) is an advanced form of dry age-related macular degeneration (AMD) that leads to progressive and irreversible vision loss. Identifying patients with greatest risk of GA progression is important for targeted utilization of emerging therapies. This study aimed to comprehensively evaluate the role of shape-based fractal dimension features ( $${F}_{fd}$$ F fd ) of sub-retinal pigment epithelium (sub-RPE) compartment and texture-based radiomics features ( $${F}_{t}$$ F t ) of Ellipsoid Zone (EZ)-RPE and sub-RPE compartments for risk stratification for subfoveal GA (sfGA) progression. This was a retrospective study of 137 dry AMD subjects with a 5-year follow-up. Based on sfGA status at year 5, eyes were categorized as Progressors and Non-progressors. A total of 15 shape-based $${F}_{fd}$$ F fd of sub-RPE surface and 494 $${F}_{t}$$ F t from each of sub-RPE and EZ-RPE compartments were extracted from baseline spectral domain-optical coherence tomography scans. The top nine features were identified from $${F}_{fd}$$ F fd and $${F}_{t}$$ F t feature pool separately using minimum Redundancy maximum Relevance feature selection and used to train a Random Forest (RF) classifier independently using three-fold cross validation on the training set ( $${S}_{t}$$ S t , N = 90) to distinguish between sfGA Progressors and Non-progressors. Combined $${F}_{fd}$$ F fd and $${F}_{t}$$ F t was also evaluated in predicting risk of sfGA progression. The RF classifier yielded AUC of 0.85, 0.79 and 0.89 on independent test set ( $${S}_{v}$$ S v , N = 47) using $${F}_{fd}$$ F fd , $${F}_{t}$$ F t , and their combination, respectively. Using combined $${F}_{fd}$$ F fd and $${F}_{t}$$ F t , the improvement in AUC was statistically significant on $${S}_{v}$$ S v with p-values of 0.032 and 0.04 compared to using only $${F}_{fd}$$ F fd and only $${F}_{t}$$ F t , respectively. Combined $${F}_{fd}$$ F fd and $${F}_{t}$$ F t appears to identify high-risk patients. Our results show that FD and texture features could be potentially used for predicting risk of sfGA progression and future therapeutic response. |
| Databáze: |
Directory of Open Access Journals |
| Externí odkaz: |
|
