Developing a Continuous Severity Scale for Macular Telangiectasia Type 2 Using Deep Learning and Implications for Disease Grading
Copyright © 2023 American Academy of Ophthalmology. Published by Elsevier Inc. All rights reserved..
PURPOSE: Deep learning (DL) models have achieved state-of-the-art medical diagnosis classification accuracy. Current models are limited by discrete diagnosis labels, but could yield more information with diagnosis in a continuous scale. We developed a novel continuous severity scaling system for macular telangiectasia (MacTel) type 2 by combining a DL classification model with uniform manifold approximation and projection (UMAP).
DESIGN: We used a DL network to learn a feature representation of MacTel severity from discrete severity labels and applied UMAP to embed this feature representation into 2 dimensions, thereby creating a continuous MacTel severity scale.
PARTICIPANTS: A total of 2003 OCT volumes were analyzed from 1089 MacTel Project participants.
METHODS: We trained a multiview DL classifier using multiple B-scans from OCT volumes to learn a previously published discrete 7-step MacTel severity scale. The classifiers' last feature layer was extracted as input for UMAP, which embedded these features into a continuous 2-dimensional manifold. The DL classifier was assessed in terms of test accuracy. Rank correlation for the continuous UMAP scale against the previously published scale was calculated. Additionally, the UMAP scale was assessed in the κ agreement against 5 clinical experts on 100 pairs of patient volumes. For each pair of patient volumes, clinical experts were asked to select the volume with more severe MacTel disease and to compare them against the UMAP scale.
MAIN OUTCOME MEASURES: Classification accuracy for the DL classifier and κ agreement versus clinical experts for UMAP.
RESULTS: The multiview DL classifier achieved top 1 accuracy of 63.3% (186/294) on held-out test OCT volumes. The UMAP metric showed a clear continuous gradation of MacTel severity with a Spearman rank correlation of 0.84 with the previously published scale. Furthermore, the continuous UMAP metric achieved κ agreements of 0.56 to 0.63 with 5 clinical experts, which was comparable with interobserver κ values.
CONCLUSIONS: Our UMAP embedding generated a continuous MacTel severity scale, without requiring continuous training labels. This technique can be applied to other diseases and may lead to more accurate diagnosis, improved understanding of disease progression, and key imaging features for pathologic characteristics.
FINANCIAL DISCLOSURE(S): Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2024 |
|---|---|
| Erschienen: |
2024 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:131 |
|---|---|
| Enthalten in: |
Ophthalmology - 131(2024), 2 vom: 29. Feb., Seite 219-226 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Wu, Yue [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Continuous scale |
|---|
| Anmerkungen: |
Date Completed 23.01.2024 Date Revised 07.02.2024 published: Print-Electronic Citation Status MEDLINE |
|---|
| doi: |
10.1016/j.ophtha.2023.09.016 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM362357463 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM362357463 | ||
| 003 | DE-627 | ||
| 005 | 20240207232043.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231226s2024 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1016/j.ophtha.2023.09.016 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1283.xml |
| 035 | |a (DE-627)NLM362357463 | ||
| 035 | |a (NLM)37739233 | ||
| 035 | |a (PII)S0161-6420(23)00675-9 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Wu, Yue |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Developing a Continuous Severity Scale for Macular Telangiectasia Type 2 Using Deep Learning and Implications for Disease Grading |
| 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 23.01.2024 | ||
| 500 | |a Date Revised 07.02.2024 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a Copyright © 2023 American Academy of Ophthalmology. Published by Elsevier Inc. All rights reserved. | ||
| 520 | |a PURPOSE: Deep learning (DL) models have achieved state-of-the-art medical diagnosis classification accuracy. Current models are limited by discrete diagnosis labels, but could yield more information with diagnosis in a continuous scale. We developed a novel continuous severity scaling system for macular telangiectasia (MacTel) type 2 by combining a DL classification model with uniform manifold approximation and projection (UMAP) | ||
| 520 | |a DESIGN: We used a DL network to learn a feature representation of MacTel severity from discrete severity labels and applied UMAP to embed this feature representation into 2 dimensions, thereby creating a continuous MacTel severity scale | ||
| 520 | |a PARTICIPANTS: A total of 2003 OCT volumes were analyzed from 1089 MacTel Project participants | ||
| 520 | |a METHODS: We trained a multiview DL classifier using multiple B-scans from OCT volumes to learn a previously published discrete 7-step MacTel severity scale. The classifiers' last feature layer was extracted as input for UMAP, which embedded these features into a continuous 2-dimensional manifold. The DL classifier was assessed in terms of test accuracy. Rank correlation for the continuous UMAP scale against the previously published scale was calculated. Additionally, the UMAP scale was assessed in the κ agreement against 5 clinical experts on 100 pairs of patient volumes. For each pair of patient volumes, clinical experts were asked to select the volume with more severe MacTel disease and to compare them against the UMAP scale | ||
| 520 | |a MAIN OUTCOME MEASURES: Classification accuracy for the DL classifier and κ agreement versus clinical experts for UMAP | ||
| 520 | |a RESULTS: The multiview DL classifier achieved top 1 accuracy of 63.3% (186/294) on held-out test OCT volumes. The UMAP metric showed a clear continuous gradation of MacTel severity with a Spearman rank correlation of 0.84 with the previously published scale. Furthermore, the continuous UMAP metric achieved κ agreements of 0.56 to 0.63 with 5 clinical experts, which was comparable with interobserver κ values | ||
| 520 | |a CONCLUSIONS: Our UMAP embedding generated a continuous MacTel severity scale, without requiring continuous training labels. This technique can be applied to other diseases and may lead to more accurate diagnosis, improved understanding of disease progression, and key imaging features for pathologic characteristics | ||
| 520 | |a FINANCIAL DISCLOSURE(S): Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a Continuous scale | |
| 650 | 4 | |a Deep learning | |
| 650 | 4 | |a Feature embedding | |
| 650 | 4 | |a MacTel | |
| 650 | 4 | |a OCT | |
| 700 | 1 | |a Egan, Catherine |e verfasserin |4 aut | |
| 700 | 1 | |a Olvera-Barrios, Abraham |e verfasserin |4 aut | |
| 700 | 1 | |a Scheppke, Lea |e verfasserin |4 aut | |
| 700 | 1 | |a Peto, Tunde |e verfasserin |4 aut | |
| 700 | 1 | |a Charbel Issa, Peter |e verfasserin |4 aut | |
| 700 | 1 | |a Heeren, Tjebo F C |e verfasserin |4 aut | |
| 700 | 1 | |a Leung, Irene |e verfasserin |4 aut | |
| 700 | 1 | |a Rajesh, Anand E |e verfasserin |4 aut | |
| 700 | 1 | |a Tufail, Adnan |e verfasserin |4 aut | |
| 700 | 1 | |a Lee, Cecilia S |e verfasserin |4 aut | |
| 700 | 1 | |a Chew, Emily Y |e verfasserin |4 aut | |
| 700 | 1 | |a Friedlander, Martin |e verfasserin |4 aut | |
| 700 | 1 | |a Lee, Aaron Y |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Ophthalmology |d 1993 |g 131(2024), 2 vom: 29. Feb., Seite 219-226 |w (DE-627)NLM000457019 |x 1549-4713 |7 nnns |
| 773 | 1 | 8 | |g volume:131 |g year:2024 |g number:2 |g day:29 |g month:02 |g pages:219-226 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1016/j.ophtha.2023.09.016 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 131 |j 2024 |e 2 |b 29 |c 02 |h 219-226 | ||