Accuracy of a Deep Learning System for Classification of Papilledema Severity on Ocular Fundus Photographs
Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Standard
Accuracy of a Deep Learning System for Classification of Papilledema Severity on Ocular Fundus Photographs. / Vasseneix, Caroline; Najjar, Raymond P.; Xu, Xinxing; Tang, Zhiqun; Loo, Jing Liang; Singhal, Shweta; Tow, Sharon; Milea, Leonard; Ting, Daniel Shu Wei; Liu, Yong; Wong, Tien Y.; Newman, Nancy J.; Biousse, Valerie; Milea, Dan; BONSAI Group.
I: Neurology, Bind 97, Nr. 4, 2021, s. e369-e377.Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Accuracy of a Deep Learning System for Classification of Papilledema Severity on Ocular Fundus Photographs
AU - Vasseneix, Caroline
AU - Najjar, Raymond P.
AU - Xu, Xinxing
AU - Tang, Zhiqun
AU - Loo, Jing Liang
AU - Singhal, Shweta
AU - Tow, Sharon
AU - Milea, Leonard
AU - Ting, Daniel Shu Wei
AU - Liu, Yong
AU - Wong, Tien Y.
AU - Newman, Nancy J.
AU - Biousse, Valerie
AU - Milea, Dan
AU - BONSAI Group
N1 - Publisher Copyright: © 2021 American Academy of Neurology.
PY - 2021
Y1 - 2021
N2 - OBJECTIVE: To evaluate the performance of a deep learning system (DLS) in classifying the severity of papilledema associated with increased intracranial pressure on standard retinal fundus photographs. METHODS: A DLS was trained to automatically classify papilledema severity in 965 patients (2,103 mydriatic fundus photographs), representing a multiethnic cohort of patients with confirmed elevated intracranial pressure. Training was performed on 1,052 photographs with mild/moderate papilledema (MP) and 1,051 photographs with severe papilledema (SP) classified by a panel of experts. The performance of the DLS and that of 3 independent neuro-ophthalmologists were tested in 111 patients (214 photographs, 92 with MP and 122 with SP) by calculating the area under the receiver operating characteristics curve (AUC), accuracy, sensitivity, and specificity. Kappa agreement scores between the DLS and each of the 3 graders and among the 3 graders were calculated. RESULTS: The DLS successfully discriminated between photographs of MP and SP, with an AUC of 0.93 (95% confidence interval [CI] 0.89-0.96) and an accuracy, sensitivity, and specificity of 87.9%, 91.8%, and 86.2%, respectively. This performance was comparable with that of the 3 neuro-ophthalmologists (84.1%, 91.8%, and 73.9%, p = 0.19, p = 1, p = 0.09, respectively). Misclassification by the DLS was mainly observed for moderate papilledema (Frisén grade 3). Agreement scores between the DLS and the neuro-ophthalmologists' evaluation was 0.62 (95% CI 0.57-0.68), whereas the intergrader agreement among the 3 neuro-ophthalmologists was 0.54 (95% CI 0.47-0.62). CONCLUSIONS: Our DLS accurately classified the severity of papilledema on an independent set of mydriatic fundus photographs, achieving a comparable performance with that of independent neuro-ophthalmologists. CLASSIFICATION OF EVIDENCE: This study provides Class II evidence that a DLS using mydriatic retinal fundus photographs accurately classified the severity of papilledema associated in patients with a diagnosis of increased intracranial pressure.
AB - OBJECTIVE: To evaluate the performance of a deep learning system (DLS) in classifying the severity of papilledema associated with increased intracranial pressure on standard retinal fundus photographs. METHODS: A DLS was trained to automatically classify papilledema severity in 965 patients (2,103 mydriatic fundus photographs), representing a multiethnic cohort of patients with confirmed elevated intracranial pressure. Training was performed on 1,052 photographs with mild/moderate papilledema (MP) and 1,051 photographs with severe papilledema (SP) classified by a panel of experts. The performance of the DLS and that of 3 independent neuro-ophthalmologists were tested in 111 patients (214 photographs, 92 with MP and 122 with SP) by calculating the area under the receiver operating characteristics curve (AUC), accuracy, sensitivity, and specificity. Kappa agreement scores between the DLS and each of the 3 graders and among the 3 graders were calculated. RESULTS: The DLS successfully discriminated between photographs of MP and SP, with an AUC of 0.93 (95% confidence interval [CI] 0.89-0.96) and an accuracy, sensitivity, and specificity of 87.9%, 91.8%, and 86.2%, respectively. This performance was comparable with that of the 3 neuro-ophthalmologists (84.1%, 91.8%, and 73.9%, p = 0.19, p = 1, p = 0.09, respectively). Misclassification by the DLS was mainly observed for moderate papilledema (Frisén grade 3). Agreement scores between the DLS and the neuro-ophthalmologists' evaluation was 0.62 (95% CI 0.57-0.68), whereas the intergrader agreement among the 3 neuro-ophthalmologists was 0.54 (95% CI 0.47-0.62). CONCLUSIONS: Our DLS accurately classified the severity of papilledema on an independent set of mydriatic fundus photographs, achieving a comparable performance with that of independent neuro-ophthalmologists. CLASSIFICATION OF EVIDENCE: This study provides Class II evidence that a DLS using mydriatic retinal fundus photographs accurately classified the severity of papilledema associated in patients with a diagnosis of increased intracranial pressure.
U2 - 10.1212/WNL.0000000000012226
DO - 10.1212/WNL.0000000000012226
M3 - Journal article
C2 - 34011570
AN - SCOPUS:85112489324
VL - 97
SP - e369-e377
JO - Neurology
JF - Neurology
SN - 0028-3878
IS - 4
ER -
ID: 304283930