Identifying "Preperimetric" Glaucoma in Standard Automated Perimetry Visual Fields

Asaoka, Ryo; Iwase, Aiko; Hirasawa, Kazunori; Murata, Hiroshi; Araie, Makoto

doi:10.1167/iovs.14-15120

Cited by 25 publications

(17 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For example, a study that classified between glaucomatous and healthy eyes using random forest performed with an AROC of 0.79. 20 This result was slightly underwhelming when taking into account that over 60% of the data was glaucomatous. This means that a classifier performing by chance would produce an AROC of ~0.60.…”

Section: Discussionmentioning

confidence: 96%

Hybrid Deep Learning on Single Wide-field Optical Coherence tomography Scans Accurately Classifies Glaucoma Suspects

Hassan

Fuchs

Cuir³

et al. 2017

Journal of Glaucoma

199

111

View full text Add to dashboard Cite

Purpose Existing summary statistics based upon optical coherence tomography (OCT) scans and/or visual fields (VF) are suboptimal for distinguishing between healthy and glaucomatous eyes in the clinic. This study evaluates the extent to which a hybrid deep learning method (HDLM), combined with a single wide-field OCT protocol, can distinguish eyes previously classified as either healthy suspects or mild glaucoma. Patients and Methods 102 eyes from 102 patients, with or suspected open-angle glaucoma, had previously been classified by two glaucoma experts as either glaucomatous (57 eyes) or healthy/suspects (45 eyes). The HDLM had access only to information from a single, wide-field (9×12mm) swept-source OCT scan per patient. Convolutional neural networks were used to extract rich features from maps derived from these scans. Random forest classifier was used to train a model based on these features to predict the existence of glaucomatous damage. The algorithm was compared against traditional OCT and VF metrics. Results The accuracy of the HDLM ranged from 63.7% to 93.1% depending upon the input map. The RNFL probability map had the best accuracy (93.1%), with 4 false positives, and 3 false negatives. In comparison, the accuracy of the OCT and 24-2 and 10-2 VF metrics ranged from 66.7% to 87.3%. The OCT quadrants analysis had the best accuracy (87.3%) of the metrics, with 4 FP and 9 FN. Conclusion The HDLM protocol outperforms standard OCT and VF clinical metrics in distinguishing healthy suspect eyes from eyes with early glaucoma. It should be possible to further improve this algorithm and with improvement it might be useful for screening

show abstract

Section: Discussionmentioning

confidence: 96%

Hybrid Deep Learning on Single Wide-field Optical Coherence tomography Scans Accurately Classifies Glaucoma Suspects

Hassan

Fuchs

Cuir³

et al. 2017

Journal of Glaucoma

199

111

View full text Add to dashboard Cite

show abstract

“…Thus, to evaluate the relationships between VRQoL-related parameters and BCVA, as well as between VRQoL-related parameters and VF damage in various subfields, it is important to control for such inter-correlations. The advantage of the Random Forest algorithm 21 , used in the current study, is that it can control for inter-correlation of multiple explanatory variables; thus, it is particularly useful in analysing data that include test results obtained from various subfields of the VF 17,25,26 .…”

Section: Discussionmentioning

confidence: 99%

Relationship between Vision-Related Quality of Life and Central 10° of the Binocular Integrated Visual Field in Advanced Glaucoma

Yamazaki

Sugisaki

Araie

et al. 2019

Sci Rep

View full text Add to dashboard Cite

To investigate the relationships between sensitivity loss in various subfields of the central 10° of the binocular integrated visual field (IVF) and vision-related quality of life (VRQoL) in 172 patients with advanced glaucoma. Using the Random Forest algorithm, which controls for inter-correlations among various subfields of the IVF, we analysed the relationships among the Rasch analysis-derived person ability index (RADPAI), age, best-corrected visual acuity (BCVA), mean total deviations (mTDs) of eight quadrant subfields in the IVF measured with the Humphrey Field Analyzer (HFA) 10-2 program (10-2 IVF), and mTDs of the upper/lower hemifields in the IVF measured with the HFA 24-2 program (24-2 IVF). Significant contributors to RADPAIs were as follows: the inner and outer lower-right quadrants of the 10-2 IVF contributed to the dining and total tasks; the lower-left quadrant of the 10-2 IVF contributed to the walking, going out and total tasks; the lower hemifield of the 24-2 IVF contributed to the walking, going out, dining, miscellaneous and total tasks; and BCVA contributed more to the letter, sentence, dressing and miscellaneous tasks than to others. The impact of damage in different 10-2 IVF subfields differed significantly across daily tasks in patients with advanced glaucoma.

show abstract

“…A minimum 2 tests were performed to minimize the learning effect; if any 2 tests failed to satisfy the reliability criteria defined by the perimeter (false positive, false negative, and loss of fixation), the test was repeated. The Anderson-Patella criteria was used with 3 non edge points depressed to an extent of what is present in <5% of normal population with at least 1 point of these 3 depressed to an extent found in less than 1% of normal population, pattern standard deviation and corrected pattern standard deviation (PSD/CPSD) should be that found in <5% population and glaucoma hemifield test (GHT) should be "OUTSIDE NORMAL LIMITS" [13].…”

Section: Discussionmentioning

confidence: 99%

Vision-Related Quality of Life in Ocular Hypertension Patients: Effects of Treatment

Kazaki¹,

Georgalas²,

Damanakis³

et al. 2015

OJOph

View full text Add to dashboard Cite

Purpose: To evaluate the quality of life related to vision (QoL) in patients with ocular hypertension under treatment. Methods: The study included two groups. The first one consisted of 60 ocular hypertension patients under topical hypotensive medications and the second one of 60 healthy persons. The Greek language version of the National Eye Institute Visual Function Questionnaire 25 (NEI VFQ-25) was completed by all patients. Results: The median scores of the total score and also for almost all the NEI VFQ-25 subscales were significantly decreased for the first group of ocular hypertension patients (OHT) under topical therapy. Females presented higher QoL than that of males. The patients who used one medication presented higher QoL than that of the patients who used more than one. The best corrected visual acuity (BCVA) and the intraocular pressure (IOP) were significantly correlated with QoL. The index of the visual fields, pattern standard deviation (PSD), was significantly related to the quality of life of OHT. The age, the cup to disk ratio and the central corneal thickness had also significant correlations with subscales of the QoL. Conclusions: The quality of life OHT patients under topical treatment is significantly decreased than healthy persons. Male sex and the number of medications affect QoL more. BCVA and IOP represent the clinical findings that best correlate with several subscales of QoL. PSD is a significant index that correlates well with the quality of life of OHT patients.

show abstract

Identifying "Preperimetric" Glaucoma in Standard Automated Perimetry Visual Fields

Abstract: Differences exist between healthy VFs and VFs of preperimetric glaucoma eyes, which go on to develop manifest glaucoma; these two groups of VFs could be well distinguished by using the Random Forests classifier.

Cited by 25 publications

References 44 publications

Hybrid Deep Learning on Single Wide-field Optical Coherence tomography Scans Accurately Classifies Glaucoma Suspects

Hybrid Deep Learning on Single Wide-field Optical Coherence tomography Scans Accurately Classifies Glaucoma Suspects

Relationship between Vision-Related Quality of Life and Central 10° of the Binocular Integrated Visual Field in Advanced Glaucoma

Vision-Related Quality of Life in Ocular Hypertension Patients: Effects of Treatment

Contact Info

Product

Resources

About