CorNet : Autonomous feature learning in raw Corvis ST data for keratoconus diagnosis via residual CNN approach
Copyright © 2024 Elsevier Ltd. All rights reserved..
PURPOSE: To ascertain whether the integration of raw Corvis ST data with an end-to-end CNN can enhance the diagnosis of keratoconus (KC).
METHOD: The Corvis ST is a non-contact device for in vivo measurement of corneal biomechanics. The CorNet was trained and validated on a dataset consisting of 1786 Corvis ST raw data from 1112 normal eyes and 674 KC eyes. Each raw data consists of the anterior and posterior corneal surface elevation during air-puff induced dynamic deformation. The architecture of CorNet utilizes four ResNet-inspired convolutional structures that employ 1 × 1 convolution in identity mapping. Gradient-weighted Class Activation Mapping (Grad-CAM) was adopted to visualize the attention allocation to diagnostic areas. Discriminative performance was assessed using metrics including the AUC of ROC curve, sensitivity, specificity, precision, accuracy, and F1 score.
RESULTS: CorNet demonstrated outstanding performance in distinguishing KC from normal eyes, achieving an AUC of 0.971 (sensitivity: 92.49%, specificity: 91.54%) in the validation set, outperforming the best existing Corvis ST parameters, namely the Corvis Biomechanical Index (CBI) with an AUC of 0.947, and its updated version for Chinese populations (cCBI) with an AUC of 0.963. Though the ROC curve analysis showed no significant difference between CorNet and cCBI (p = 0.295), it indicated a notable difference between CorNet and CBI (p = 0.011). The Grad-CAM visualizations highlighted the significance of corneal deformation data during the loading phase rather than the unloading phase for KC diagnosis.
CONCLUSION: This study proposed an end-to-end CNN approach utilizing raw biomechanical data by Corvis ST for KC detection, showing effectiveness comparable to or surpassing existing parameters provided by Corvis ST. The CorNet, autonomously learning comprehensive temporal and spatial features, demonstrated a promising performance for advancing KC diagnosis in ophthalmology.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2024 |
|---|---|
| Erschienen: |
2024 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:172 |
|---|---|
| Enthalten in: |
Computers in biology and medicine - 172(2024) vom: 26. März, Seite 108286 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Zhang, PeiPei [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Convolutional neural network |
|---|
| Anmerkungen: |
Date Completed 26.03.2024 Date Revised 26.03.2024 published: Print-Electronic Citation Status MEDLINE |
|---|
| doi: |
10.1016/j.compbiomed.2024.108286 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM369832922 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM369832922 | ||
| 003 | DE-627 | ||
| 005 | 20240326235907.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 240318s2024 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1016/j.compbiomed.2024.108286 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1349.xml |
| 035 | |a (DE-627)NLM369832922 | ||
| 035 | |a (NLM)38493602 | ||
| 035 | |a (PII)S0010-4825(24)00370-6 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Zhang, PeiPei |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a CorNet |b Autonomous feature learning in raw Corvis ST data for keratoconus diagnosis via residual CNN approach |
| 264 | 1 | |c 2024 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Completed 26.03.2024 | ||
| 500 | |a Date Revised 26.03.2024 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a Copyright © 2024 Elsevier Ltd. All rights reserved. | ||
| 520 | |a PURPOSE: To ascertain whether the integration of raw Corvis ST data with an end-to-end CNN can enhance the diagnosis of keratoconus (KC) | ||
| 520 | |a METHOD: The Corvis ST is a non-contact device for in vivo measurement of corneal biomechanics. The CorNet was trained and validated on a dataset consisting of 1786 Corvis ST raw data from 1112 normal eyes and 674 KC eyes. Each raw data consists of the anterior and posterior corneal surface elevation during air-puff induced dynamic deformation. The architecture of CorNet utilizes four ResNet-inspired convolutional structures that employ 1 × 1 convolution in identity mapping. Gradient-weighted Class Activation Mapping (Grad-CAM) was adopted to visualize the attention allocation to diagnostic areas. Discriminative performance was assessed using metrics including the AUC of ROC curve, sensitivity, specificity, precision, accuracy, and F1 score | ||
| 520 | |a RESULTS: CorNet demonstrated outstanding performance in distinguishing KC from normal eyes, achieving an AUC of 0.971 (sensitivity: 92.49%, specificity: 91.54%) in the validation set, outperforming the best existing Corvis ST parameters, namely the Corvis Biomechanical Index (CBI) with an AUC of 0.947, and its updated version for Chinese populations (cCBI) with an AUC of 0.963. Though the ROC curve analysis showed no significant difference between CorNet and cCBI (p = 0.295), it indicated a notable difference between CorNet and CBI (p = 0.011). The Grad-CAM visualizations highlighted the significance of corneal deformation data during the loading phase rather than the unloading phase for KC diagnosis | ||
| 520 | |a CONCLUSION: This study proposed an end-to-end CNN approach utilizing raw biomechanical data by Corvis ST for KC detection, showing effectiveness comparable to or surpassing existing parameters provided by Corvis ST. The CorNet, autonomously learning comprehensive temporal and spatial features, demonstrated a promising performance for advancing KC diagnosis in ophthalmology | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a Convolutional neural network | |
| 650 | 4 | |a Corneal biomechanics | |
| 650 | 4 | |a Corvis ST | |
| 650 | 4 | |a Keratoconus | |
| 700 | 1 | |a Yang, LanTing |e verfasserin |4 aut | |
| 700 | 1 | |a Mao, YiCheng |e verfasserin |4 aut | |
| 700 | 1 | |a Zhang, XinYu |e verfasserin |4 aut | |
| 700 | 1 | |a Cheng, JiaXuan |e verfasserin |4 aut | |
| 700 | 1 | |a Miao, YuanYuan |e verfasserin |4 aut | |
| 700 | 1 | |a Bao, FangJun |e verfasserin |4 aut | |
| 700 | 1 | |a Chen, ShiHao |e verfasserin |4 aut | |
| 700 | 1 | |a Zheng, QinXiang |e verfasserin |4 aut | |
| 700 | 1 | |a Wang, JunJie |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Computers in biology and medicine |d 1970 |g 172(2024) vom: 26. März, Seite 108286 |w (DE-627)NLM000382272 |x 1879-0534 |7 nnns |
| 773 | 1 | 8 | |g volume:172 |g year:2024 |g day:26 |g month:03 |g pages:108286 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1016/j.compbiomed.2024.108286 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 172 |j 2024 |b 26 |c 03 |h 108286 | ||