Robust and Interpretable Convolutional Neural Networks to Detect Glaucoma in Optical Coherence Tomography Images

Thakoor, Kaveri A.; Koorathota, Sharath; Hood, Donald C.; Sajda, Paul

doi:10.1109/tbme.2020.3043215

Cited by 48 publications

(23 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition to available cross-sectional and longitudinal studies that support the use of RNFL probability map, heat maps generated following artificial intelligence assessment of large patient data sets also point to the parapapillary optic nerve as the key regions that these machine methods rely upon. 48,[50][51][52] All told, there is considerable evidence to support the use of the RNFL and macular probability plots as the first steps in our method and key components of our OCT-based glaucoma definition. The GCL and RNFL maps provide complementary and corroborative information of structural glaucomatous damage.…”

Section: Key Elements Of Our Methodsmentioning

confidence: 89%

Rationale and Development of an OCT-Based Method for Detection of Glaucomatous Optic Neuropathy

Liebmann

Hood

Moraes

et al. 2022

Journal of Glaucoma

Self Cite

View full text Add to dashboard Cite

A specific, sensitive, and intersubjectively verifiable definition of disease for clinical care and research remains an important unmet need in the field of glaucoma. Using an iterative, consensus-building approach and employing pilot data, an optical coherence tomography (OCT)-based method to aid in the detection of glaucomatous optic neuropathy was sought to address this challenge. To maximize the chance of success, we utilized all available information from the OCT circle and cube scans, applied both quantitative and semiquantitative data analysis methods, and aimed to limit the use of perimetry to cases where it is absolutely necessary. The outcome of this approach was an OCT-based method for the diagnosis of glaucomatous optic neuropathy that did not require the use of perimetry for initial diagnosis. A decision tree was devised for testing and implementation in clinical practice and research that can be used by reading centers, researchers, and clinicians. While initial pilot data were encouraging, future testing and validation will be needed to establish its utility in clinical practice, as well as for research.

show abstract

Section: Key Elements Of Our Methodsmentioning

confidence: 89%

Rationale and Development of an OCT-Based Method for Detection of Glaucomatous Optic Neuropathy

Liebmann

Hood

Moraes

et al. 2022

Journal of Glaucoma

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, there is an overlap in appearance that will make it difficult for a clinician to reliably use this information. It is possible, however, that an AI program based upon RNFL p-maps, such as that developed by Thakoor and colleagues, 40 , 70 , 71 may be able to use this information.…”

Section: Discussionmentioning

confidence: 99%

The OCT RNFL Probability Map and Artifacts Resembling Glaucomatous Damage

Bruna

Rai

Mao

et al. 2022

Trans. Vis. Sci. Tech.

Self Cite

View full text Add to dashboard Cite

Purpose The purpose of this study was to improve the diagnostic ability of the optical coherence tomography (OCT) retinal nerve fiber layer (RNFL) probability (p-) map by understanding the frequency and pattern of artifacts seen on the p-maps of healthy control (HC) eyes resembling glaucomatous damage. Methods RNFL p-maps were generated from wide-field OCT cube scans of 2 groups of HC eyes, 200 from a commercial normative group (HC-norm) and 54 from a prospective study group, as well as from 62 patient eyes, which included 32 with early glaucoma (EG). These 32 EG eyes had 24-2 mean deviation (MD) better than −6 dB and perimetric glaucoma as defined by 24-2 and 10-2 criteria. For the HC groups, “glaucoma-like” arcuates were defined as any red region near the temporal half of the disc. Results Seven percent of the 200 HC-norm and 11% of the 54 HC RNFL p-maps satisfied the definition of “glaucoma-like,” as did all the patients’ p-maps. The HC p-maps showed two general patterns of abnormal regions, “arcuate” and “temporal quadrant,” and these patterns resembled those seen on some of the RNFL p-maps of the EG eyes. A “vertical midline” rule, which required the abnormal region to cross the vertical midline through the fovea, had a specificity of >99%, and a sensitivity of 75% for EG and 93% for moderate to advanced eyes. Conclusions Glaucoma-like artifacts on RNFL p-maps are relatively common and can masquerade as arcuate and/or widespread/temporal damage. Translational Relevance A vertical midline rule had excellent specificity. However, other OCT information is necessary to obtain high sensitivity, especially in eyes with early glaucoma.

show abstract

“…Thus, several recent studies have focused on the development of DL models that are capable of performing well in external datasets acquired in different cameras and in field data, where imaging may be affected by variability in quality. For example, Thakoor et al created four different end-to-end DL models by employing fine-tuned transfer learning and also created a final CNN ensemble model (48). The accuracy of each of these DL models compared to earlier hybrid DL/MLCs was more robust in both laboratory and field test datasets, with smaller declines in performance when applied to field-collected datasets.…”

Section: Discussionmentioning

confidence: 99%

Deep learning and optical coherence tomography in glaucoma: Bridging the diagnostic gap on structural imaging

Falconi¹,

Sappington²

2022

Front. Ophthalmol.

View full text Add to dashboard Cite

Glaucoma is a leading cause of progressive blindness and visual impairment worldwide. Microstructural evidence of glaucomatous damage to the optic nerve head and associated tissues can be visualized using optical coherence tomography (OCT). In recent years, development of novel deep learning (DL) algorithms has led to innovative advances and improvements in automated detection of glaucomatous damage and progression on OCT imaging. DL algorithms have also been trained utilizing OCT data to improve detection of glaucomatous damage on fundus photography, thus improving the potential utility of color photos which can be more easily collected in a wider range of clinical and screening settings. This review highlights ten years of contributions to glaucoma detection through advances in deep learning models trained utilizing OCT structural data and posits future directions for translation of these discoveries into the field of aging and the basic sciences.

show abstract

Robust and Interpretable Convolutional Neural Networks to Detect Glaucoma in Optical Coherence Tomography Images

Cited by 48 publications

References 24 publications

Rationale and Development of an OCT-Based Method for Detection of Glaucomatous Optic Neuropathy

Rationale and Development of an OCT-Based Method for Detection of Glaucomatous Optic Neuropathy

The OCT RNFL Probability Map and Artifacts Resembling Glaucomatous Damage

Deep learning and optical coherence tomography in glaucoma: Bridging the diagnostic gap on structural imaging

Contact Info

Product

Resources

About