Forskning
Udskriv Udskriv
Switch language
Region Hovedstaden - en del af Københavns Universitetshospital
Udgivet

Optic Disc Classification by Deep Learning versus Expert Neuro-Ophthalmologists

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

DOI

  1. Amylin Analog Pramlintide Induces Migraine-like Attacks in Patients

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  2. A New Glycogen Storage Disease Caused by a Dominant PYGM Mutation

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  3. Neurophysiological signatures of motor impairment in patients with Rett syndrome

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  1. Ipsilateral Recurrence of Optic Disc Drusen-Associated Anterior Ischemic Optic Neuropathy in a 15-Year-Old Boy

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  2. Optic disc drusen diagnosed by optical coherence tomography in a 3-year-old child

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  3. Multiplexed optical coherence tomography imaging of optic disc drusen

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  4. Optic Disc Drusen Associated Anterior Ischemic Optic Neuropathy: Prevalence of Comorbidities and Vascular Risk Factors

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  • BONSAI (Brain and Optic Nerve Study with Artificial Intelligence) Study Group
  • Anna Isabelle Karlesand (Medlem af forfattergruppering)
Vis graf over relationer

OBJECTIVE: To compare the diagnostic performance of an artificial intelligence deep learning system with that of expert neuro-ophthalmologists in classifying optic disc appearance.

METHODS: The deep learning system was previously trained and validated on 14,341 ocular fundus photographs from 19 international centers. The performance of the system was evaluated on 800 new fundus photographs (400 normal optic discs, 201 papilledema [disc edema from elevated intracranial pressure], 199 other optic disc abnormalities) and compared with that of 2 expert neuro-ophthalmologists who independently reviewed the same randomly presented images without clinical information. Area under the receiver operating characteristic curve, accuracy, sensitivity, and specificity were calculated.

RESULTS: The system correctly classified 678 of 800 (84.7%) photographs, compared with 675 of 800 (84.4%) for Expert 1 and 641 of 800 (80.1%) for Expert 2. The system yielded areas under the receiver operating characteristic curve of 0.97 (95% confidence interval [CI] = 0.96-0.98), 0.96 (95% CI = 0.94-0.97), and 0.89 (95% CI = 0.87-0.92) for the detection of normal discs, papilledema, and other disc abnormalities, respectively. The accuracy, sensitivity, and specificity of the system's classification of optic discs were similar to or better than the 2 experts. Intergrader agreement at the eye level was 0.71 (95% CI = 0.67-0.76) between Expert 1 and Expert 2, 0.72 (95% CI = 0.68-0.76) between the system and Expert 1, and 0.65 (95% CI = 0.61-0.70) between the system and Expert 2.

INTERPRETATION: The performance of this deep learning system at classifying optic disc abnormalities was at least as good as 2 expert neuro-ophthalmologists. Future prospective studies are needed to validate this system as a diagnostic aid in relevant clinical settings. ANN NEUROL 2020;88:785-795.

OriginalsprogEngelsk
TidsskriftAnnals of Neurology
Vol/bind88
Udgave nummer4
Sider (fra-til)785-795
Antal sider11
ISSN0364-5134
DOI
StatusUdgivet - okt. 2020

Bibliografisk note

© 2020 American Neurological Association.

ID: 61987275