Literature DB >> 34011570

Accuracy of a Deep Learning System for Classification of Papilledema Severity on Ocular Fundus Photographs.

Caroline Vasseneix1, Raymond P Najjar1, Xinxing Xu1, Zhiqun Tang1, Jing Liang Loo1, Shweta Singhal1, Sharon Tow1, Leonard Milea2, Daniel Shu Wei Ting1, Yong Liu1, Tien Y Wong1, Nancy J Newman1, Valerie Biousse1, Dan Milea2.   

Abstract

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.
© 2021 American Academy of Neurology.

Entities:  

Mesh:

Year:  2021        PMID: 34011570      PMCID: PMC8362357          DOI: 10.1212/WNL.0000000000012226

Source DB:  PubMed          Journal:  Neurology        ISSN: 0028-3878            Impact factor:   9.910


  42 in total

1.  Swelling of the optic nerve head: a staging scheme.

Authors:  L Frisén
Journal:  J Neurol Neurosurg Psychiatry       Date:  1982-01       Impact factor: 10.154

2.  Nonmydriatic ocular fundus photography in the emergency department.

Authors:  Beau B Bruce; Cédric Lamirel; David W Wright; Antoinette Ward; Katherine L Heilpern; Valérie Biousse; Nancy J Newman
Journal:  N Engl J Med       Date:  2011-01-27       Impact factor: 91.245

Review 3.  Optical coherence tomography in papilledema: what am I missing?

Authors:  Randy Kardon
Journal:  J Neuroophthalmol       Date:  2014-09       Impact factor: 3.042

4.  Visual loss in pseudotumor cerebri. Follow-up of 57 patients from five to 41 years and a profile of 14 patients with permanent severe visual loss.

Authors:  J J Corbett; P J Savino; H S Thompson; T Kansu; N J Schatz; L S Orr; D Hopson
Journal:  Arch Neurol       Date:  1982-08

5.  Factors affecting visual loss in benign intracranial hypertension.

Authors:  J C Orcutt; N G Page; M D Sanders
Journal:  Ophthalmology       Date:  1984-11       Impact factor: 12.079

6.  Clinical and Neuro-ophthalmologic Predictors of Visual Outcome in Idiopathic Intracranial Hypertension.

Authors:  Aastha Takkar; Manoj Kumar Goyal; Reema Bansal; Vivek Lal
Journal:  Neuroophthalmology       Date:  2018-01-09

7.  U-Net: deep learning for cell counting, detection, and morphometry.

Authors:  Thorsten Falk; Dominic Mai; Robert Bensch; Özgün Çiçek; Ahmed Abdulkadir; Yassine Marrakchi; Anton Böhm; Jan Deubner; Zoe Jäckel; Katharina Seiwald; Alexander Dovzhenko; Olaf Tietz; Cristina Dal Bosco; Sean Walsh; Deniz Saltukoglu; Tuan Leng Tay; Marco Prinz; Klaus Palme; Matias Simons; Ilka Diester; Thomas Brox; Olaf Ronneberger
Journal:  Nat Methods       Date:  2018-12-17       Impact factor: 28.547

8.  Pivotal trial of an autonomous AI-based diagnostic system for detection of diabetic retinopathy in primary care offices.

Authors:  Michael D Abràmoff; Philip T Lavin; Michele Birch; Nilay Shah; James C Folk
Journal:  NPJ Digit Med       Date:  2018-08-28

Review 9.  Artificial intelligence and deep learning in ophthalmology.

Authors:  Daniel Shu Wei Ting; Louis R Pasquale; Lily Peng; John Peter Campbell; Aaron Y Lee; Rajiv Raman; Gavin Siew Wei Tan; Leopold Schmetterer; Pearse A Keane; Tien Yin Wong
Journal:  Br J Ophthalmol       Date:  2018-10-25       Impact factor: 4.638

10.  The expanding burden of idiopathic intracranial hypertension.

Authors:  Susan P Mollan; Magda Aguiar; Felicity Evison; Emma Frew; Alexandra J Sinclair
Journal:  Eye (Lond)       Date:  2018-10-24       Impact factor: 3.775

View more
  3 in total

Review 1.  The use of deep learning technology for the detection of optic neuropathy.

Authors:  Mei Li; Chao Wan
Journal:  Quant Imaging Med Surg       Date:  2022-03

2.  A recurrent machine learning model predicts intracranial hypertension in neurointensive care patients.

Authors:  Nils Schweingruber; Marius Marc Daniel Mader; Anton Wiehe; Frank Röder; Jennifer Göttsche; Stefan Kluge; Manfred Westphal; Patrick Czorlich; Christian Gerloff
Journal:  Brain       Date:  2022-08-27       Impact factor: 15.255

Review 3.  Diagnostic Error in Neuro-ophthalmology: Avenues to Improve.

Authors:  Elena A Muro-Fuentes; Leanne Stunkel
Journal:  Curr Neurol Neurosci Rep       Date:  2022-03-23       Impact factor: 6.030

  3 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.