Validation of a Deep Learning-Based Algorithm for Segmentation of the Ellipsoid Zone on Optical Coherence Tomography Images of an Ush2a-Related Retinal Degeneration Clinical Trial

Loo, Jessica; Jaffe, Glenn J.; Duncan, Jacque L.; Birch, David G.; Farsiu, Sina

doi:10.1097/iae.0000000000003448

Cited by 8 publications

(5 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results of this study demonstrate that automatic EZ area measurements generated from our DL models were in excellent agreement with those by the manual grading of the reading center, with a correlation coefficient >0.99 for both U-Net model and hybrid models as well as with a mean difference ± SD of -0.137 ± 1.131 mm 2 and -0.082 ± 0.825 mm 2 for the original (RP240) and the improved (RP340) hybrid model, respectively. Our findings are consistent with a recent study by Loo et al ( 26 ) showing a close agreement of EZ area estimates between a deep learning-based algorithm and experienced human graders (a mean DSC ± SD of 0.79 ± 0.27, a mean absolute different ± SD of 0.62 ± 1.41 mm 2 with a correlation of 0.97). The similarity between the performances of deep learning models and the manual grading for EZ area measurements suggests that deep learning may provide effective tools to significantly reduce the burden of reading centers to analyze OCT scan images in RP.…”

Section: Discussionsupporting

confidence: 92%

“…Previously, image processing–based methods have been employed for automatic segmentation of outer retinal layers in RP ( 23 – 25 ). A more recent study by Loo et al ( 26 ) evaluated a deep learning-based algorithm originally developed for macular telangiectasia ( 27 ) for the segmentation of EZ in RP. While they showed that the DL algorithm performed well in segmenting EZ area, it doesn’t provide a measure of other photoreceptor outer segment metrics, such as volume, from OCT volume scans.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Performance of Deep Learning Models in Automatic Measurement of Ellipsoid Zone Area on Baseline Optical Coherence Tomography (OCT) Images From the Rate of Progression of USH2A-Related Retinal Degeneration (RUSH2A) Study

Wang

Birch

2022

Front. Med.

Self Cite

View full text Add to dashboard Cite

PurposePreviously, we have shown the capability of a hybrid deep learning (DL) model that combines a U-Net and a sliding-window (SW) convolutional neural network (CNN) for automatic segmentation of retinal layers from OCT scan images in retinitis pigmentosa (RP). We found that one of the shortcomings of the hybrid model is that it tends to underestimate ellipsoid zone (EZ) width or area, especially when EZ extends toward or beyond the edge of the macula. In this study, we trained the model with additional data which included more OCT scans having extended EZ. We evaluated its performance in automatic measurement of EZ area on SD-OCT volume scans obtained from the participants of the RUSH2A natural history study by comparing the model’s performance to the reading center’s manual grading.Materials and MethodsDe-identified Spectralis high-resolution 9-mm 121-line macular volume scans as well as their EZ area measurements by a reading center were transferred from the management center of the RUSH2A study under the data transfer and processing agreement. A total of 86 baseline volume scans from 86 participants of the RUSH2A study were included to evaluate two hybrid models: the original RP240 model trained on 480 mid-line B-scans from 220 patients with retinitis pigmentosa (RP) and 20 participants with normal vision from a single site, and the new RP340 model trained on a revised RP340 dataset which included RP240 dataset plus an additional 200 mid-line B-scans from another 100 patients with RP. There was no overlap of patients between training and evaluation datasets. EZ and apical RPE in each B-scan image were automatically segmented by the hybrid model. EZ areas were determined by interpolating the discrete 2-dimensional B-scan EZ-RPE layer over the scan area. Dice similarity, correlation, linear regression, and Bland-Altman analyses were conducted to assess the agreement between the EZ areas measured by the hybrid model and by the reading center.ResultsFor EZ area > 1 mm2, average dice coefficients ± SD between the EZ band segmentations determined by the DL model and the manual grading were 0.835 ± 0.132 and 0.867 ± 0.105 for RP240 and RP340 hybrid models, respectively (p < 0.0005; n = 51). When compared to the manual grading, correlation coefficients (95% CI) were 0.991 (0.987–0.994) and 0.994 (0.991–0.996) for RP240 and RP340 hybrid models, respectively. Linear regression slopes (95% CI) were 0.918 (0.896–0.940) and 0.995 (0.975–1.014), respectively. Bland-Altman analysis revealed a mean difference ± SD of -0.137 ± 1.131 mm2 and 0.082 ± 0.825 mm2, respectively.ConclusionAdditional training data improved the hybrid model’s performance, especially reducing the bias and narrowing the range of the 95% limit of agreement when compared to manual grading. The close agreement of DL models to manual grading suggests that DL may provide effective tools to significantly reduce the burden of reading centers to analyze OCT scan images. In addition to EZ area, our DL models can also provide the measurements of photoreceptor outer segment volume and thickness to further help assess disease progression and to facilitate the study of structure and function relationship in RP.

show abstract

Section: Discussionsupporting

confidence: 92%

Section: Introductionmentioning

confidence: 99%

Performance of Deep Learning Models in Automatic Measurement of Ellipsoid Zone Area on Baseline Optical Coherence Tomography (OCT) Images From the Rate of Progression of USH2A-Related Retinal Degeneration (RUSH2A) Study

Wang

Birch

2022

Front. Med.

Self Cite

View full text Add to dashboard Cite

show abstract

“…This tool reached 0.894 ± 0.102 similarity between automatic and manual grading for RP and 0.912 ± 0.055 for CHM. Loo et al also targeted EZ segmentation and validated their algorithm for macular telangiectasia in patients with USH2A -related RP, with excellent applicability (dice score 0.79 ± 0.27) [ 91 ]. Similarly, Wang et al also tested an EZ segmentation CNN in USH2A -RP and obtained a Dice score of 0.867 ± 0.105 [ 92 ].…”

Section: Selected Retinal Diseases For Which Ai-based Tools Have Been...mentioning

confidence: 99%

Artificial intelligence in retinal disease: clinical application, challenges, and future directions

Varela

Sen

Guimarães

et al. 2023

Graefes Arch Clin Exp Ophthalmol

View full text Add to dashboard Cite

Retinal diseases are a leading cause of blindness in developed countries, accounting for the largest share of visually impaired children, working-age adults (inherited retinal disease), and elderly individuals (age-related macular degeneration). These conditions need specialised clinicians to interpret multimodal retinal imaging, with diagnosis and intervention potentially delayed. With an increasing and ageing population, this is becoming a global health priority. One solution is the development of artificial intelligence (AI) software to facilitate rapid data processing. Herein, we review research offering decision support for the diagnosis, classification, monitoring, and treatment of retinal disease using AI. We have prioritised diabetic retinopathy, age-related macular degeneration, inherited retinal disease, and retinopathy of prematurity. There is cautious optimism that these algorithms will be integrated into routine clinical practice to facilitate access to vision-saving treatments, improve efficiency of healthcare systems, and assist clinicians in processing the ever-increasing volume of multimodal data, thereby also liberating time for doctor-patient interaction and co-development of personalised management plans.

show abstract

“…Recent advances in machine learning have provided new tools for clinical applications in ophthalmology, especially in retinal diseases [8][9][10][11][12][13][14][15]. One such application is the automated layer segmentation in OCT scan images [16][17][18][19][20][21][22][23][24], in particular automatic measurements of EZ width or area from the retinal layer segmentation of OCT scan images in patients with inherited retinal degeneration [7,[25][26][27][28]. For instance, Camino et al implemented a method based on a convolutional neural network (CNN) for the segmentation of a preserved EZ area on en face OCT in choroideremia and RP and achieved 90% accuracy [25].…”

Section: Introductionmentioning

confidence: 99%

“…For instance, Camino et al implemented a method based on a convolutional neural network (CNN) for the segmentation of a preserved EZ area on en face OCT in choroideremia and RP and achieved 90% accuracy [25]. Loo et al evaluated a deep learning-based algorithm originally developed for macular telangiectasia [29] for the segmentation of the EZ area in USH2A-related RP [26], and they showed that the deep learning algorithm performed well in segmenting the EZ area, with a dice similarity score (SD) of 0.79 (0.27). Wang et al developed a machine learning method based on random forests for the automatic detection of continuous areas of a preserved EZ in choroideremia [28].…”

Section: Introductionmentioning

confidence: 99%

Deep Learning-Assisted Measurements of Photoreceptor Ellipsoid Zone Area and Outer Segment Volume as Biomarkers for Retinitis Pigmentosa

Wang,

Juroch,

Birch

2023

Bioengineering

View full text Add to dashboard Cite

The manual segmentation of retinal layers from OCT scan images is time-consuming and costly. The deep learning approach has potential for the automatic delineation of retinal layers to significantly reduce the burden of human graders. In this study, we compared deep learning model (DLM) segmentation with manual correction (DLM-MC) to conventional manual grading (MG) for the measurements of the photoreceptor ellipsoid zone (EZ) area and outer segment (OS) volume in retinitis pigmentosa (RP) to assess whether DLM-MC can be a new gold standard for retinal layer segmentation and for the measurement of retinal layer metrics. Ninety-six high-speed 9 mm 31-line volume scans obtained from 48 patients with RPGR-associated XLRP were selected based on the following criteria: the presence of an EZ band within the scan limit and a detectable EZ in at least three B-scans in a volume scan. All the B-scan images in each volume scan were manually segmented for the EZ and proximal retinal pigment epithelium (pRPE) by two experienced human graders to serve as the ground truth for comparison. The test volume scans were also segmented by a DLM and then manually corrected for EZ and pRPE by the same two graders to obtain DLM-MC segmentation. The EZ area and OS volume were determined by interpolating the discrete two-dimensional B-scan EZ-pRPE layer over the scan area. Dice similarity, Bland–Altman analysis, correlation, and linear regression analyses were conducted to assess the agreement between DLM-MC and MG for the EZ area and OS volume measurements. For the EZ area, the overall mean dice score (SD) between DLM-MC and MG was 0.8524 (0.0821), which was comparable to 0.8417 (0.1111) between two MGs. For the EZ area > 1 mm2, the average dice score increased to 0.8799 (0.0614). When comparing DLM-MC to MG, the Bland–Altman plots revealed a mean difference (SE) of 0.0132 (0.0953) mm2 and a coefficient of repeatability (CoR) of 1.8303 mm2 for the EZ area and a mean difference (SE) of 0.0080 (0.0020) mm3 and a CoR of 0.0381 mm3 for the OS volume. The correlation coefficients (95% CI) were 0.9928 (0.9892–0.9952) and 0.9938 (0.9906–0.9958) for the EZ area and OS volume, respectively. The linear regression slopes (95% CI) were 0.9598 (0.9399–0.9797) and 1.0104 (0.9909–1.0298), respectively. The results from this study suggest that the manual correction of deep learning model segmentation can generate EZ area and OS volume measurements in excellent agreement with those of conventional manual grading in RP. Because DLM-MC is more efficient for retinal layer segmentation from OCT scan images, it has the potential to reduce the burden of human graders in obtaining quantitative measurements of biomarkers for assessing disease progression and treatment outcomes in RP.

show abstract

Validation of a Deep Learning-Based Algorithm for Segmentation of the Ellipsoid Zone on Optical Coherence Tomography Images of an Ush2a-Related Retinal Degeneration Clinical Trial

Cited by 8 publications

References 22 publications

Performance of Deep Learning Models in Automatic Measurement of Ellipsoid Zone Area on Baseline Optical Coherence Tomography (OCT) Images From the Rate of Progression of USH2A-Related Retinal Degeneration (RUSH2A) Study

Performance of Deep Learning Models in Automatic Measurement of Ellipsoid Zone Area on Baseline Optical Coherence Tomography (OCT) Images From the Rate of Progression of USH2A-Related Retinal Degeneration (RUSH2A) Study

Artificial intelligence in retinal disease: clinical application, challenges, and future directions

Deep Learning-Assisted Measurements of Photoreceptor Ellipsoid Zone Area and Outer Segment Volume as Biomarkers for Retinitis Pigmentosa

Contact Info

Product

Resources

About