Robust and Efficient Computation of Retinal Fractal Dimension Through Deep Approximation

Engelmann, Justin; Villaplana-Velasco, Ana; Storkey, Amos; Bernabéu, Miguel O.

doi:10.1007/978-3-031-16525-2_9

Cited by 7 publications

(5 citation statements)

References 20 publications

(25 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First, only a single quality annotator was used, although they were very experienced, and comparable quality taxonomies for color fundus imaging have good repeatability according to the literature. Future work ideally should use fully automated methods such as the recently proposed QuickQual 21 that avoid introducing subjectivity and allow better comparison of quality annotations across different works. Second, although DART is more robust to image quality than traditional approaches, some images might still be too poor in quality.…”

Section: Discussionmentioning

confidence: 99%

“…To compute the FD of the images, we used DART, 13 which is based on the multifractal FD of VAMPIRE. 2 , 14 , 15 All images could be successfully processed in less than a minute on a consumer-grade, desktop central processing unit (CPU), and no images were excluded from analysis.…”

Section: Methodsmentioning

confidence: 99%

“…Recently, a novel artificial intelligence–based method for computing FD has been proposed: Deep Approximation of Retinal Traits (DART). 13 Traditional methods such as VAMPIRE 14 calculate FD from binary segmentations of the blood vessels, and even small imperfections in those segmentations can affect the calculations, resulting in a high bar for minimum image quality. DART uses a deep learning model that was trained to output the same FD as VAMPIRE but during training received original high-quality images and degraded versions of those, such as with altered brightness or contrast to simulate lighting issues, blur, or simulated artifacts.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Retinal Fractal Dimension Is a Potential Biomarker for Systemic Health—Evidence From a Mixed-Age, Primary-Care Population

Engelmann,

Kearney,

McTrusty

et al. 2024

Trans. Vis. Sci. Tech.

Self Cite

View full text Add to dashboard Cite

Purpose To investigate whether fractal dimension (FD), a retinal trait relating to vascular complexity and a potential “oculomics” biomarker for systemic disease, is applicable to a mixed-age, primary-care population. Methods We used cross-sectional data (96 individuals; 183 eyes; ages 18–81 years) from a university-based optometry clinic in Glasgow, Scotland, to study the association between FD and systemic health. We computed FD from color fundus images using Deep Approximation of Retinal Traits (DART), an artificial intelligence–based method designed to be more robust to poor image quality. Results Despite DART being designed to be more robust, a significant association ( P < 0.001) between image quality and FD remained. Consistent with previous literature, age was associated with lower FD ( P < 0.001 univariate and when adjusting for image quality). However, FD variance was higher in older patients, and some patients over 60 had FD comparable to those of patients in their 20s. Prevalent systemic conditions were significantly ( P = 0.037) associated with lower FD when adjusting for image quality and age. Conclusions Our work suggests that FD as a biomarker for systemic health extends to mixed-age, primary-care populations. FD decreases with age but might not substantially decrease in everyone. This should be further investigated using longitudinal data. Finally, image quality was associated with FD, but it is unclear whether this finding is measurement error caused by image quality or confounded by age and health. Future work should investigate this to clarify whether adjusting for image quality is appropriate. Translational Relevance FD could potentially be used in regular screening settings, but questions around image quality remain.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Retinal Fractal Dimension Is a Potential Biomarker for Systemic Health—Evidence From a Mixed-Age, Primary-Care Population

Engelmann,

Kearney,

McTrusty

et al. 2024

Trans. Vis. Sci. Tech.

Self Cite

View full text Add to dashboard Cite

show abstract

“…25 We also used progressive erasing plus progressive restoration to validate whether the global attention map was faithful to the method of the model to make predictions and investigate how the performance of the model degraded upon removing either the most or the least important regions. 26…”

Section: Methodsmentioning

confidence: 99%

Screening of Moyamoya Disease From Retinal Photographs: Development and Validation of Deep Learning Algorithms

Hong,

Yoon,

Shim

et al. 2024

Stroke

View full text Add to dashboard Cite

BACKGROUND: Moyamoya disease (MMD) is a rare and complex pathological condition characterized by an abnormal collateral circulation network in the basal brain. The diagnosis of MMD and its progression is unpredictable and influenced by many factors. MMD can affect the blood vessels supplying the eyes, resulting in a range of ocular symptoms. In this study, we developed a deep learning model using real-world data to assist a diagnosis and determine the stage of the disease using retinal photographs. METHODS: This retrospective observational study conducted from August 2006 to March 2022 included 498 retinal photographs from 78 patients with MMD and 3835 photographs from 1649 healthy participants. Photographs were preprocessed, and an ResNeXt50 model was developed. Model performance was measured using receiver operating curves and their area under the receiver operating characteristic curve, accuracy, sensitivity, and F1-score. Heatmaps and progressive erasing plus progressive restoration were performed to validate the faithfulness. RESULTS: Overall, 322 retinal photographs from 67 patients with MMD and 3752 retinal photographs from 1616 healthy participants were used to develop a screening and stage prediction model for MMD. The average age of the patients with MMD was 44.1 years, and the average follow-up time was 115 months. Stage 3 photographs were the most prevalent, followed by stages 4, 5, 2, 1, and 6 and healthy. The MMD screening model had an average area under the receiver operating characteristic curve of 94.6%, with 89.8% sensitivity and 90.4% specificity at the best cutoff point. MMD stage prediction models had an area under the receiver operating characteristic curve of 78% or higher, with stage 3 performing the best at 93.6%. Heatmap identified the vascular region of the fundus as important for prediction, and progressive erasing plus progressive restoration result shows an area under the receiver operating characteristic curve of 70% only with 50% of the important regions. CONCLUSIONS: This study demonstrated that retinal photographs could be used as potential biomarkers for screening and staging of MMD and the disease stage could be classified by a deep learning algorithm.

show abstract

“…Subsequently, we used a progressive erasing technique to quantitatively validate the explainability of the heat map. 27,28 Model performance was sequentially evaluated by gradually removing 5% of the least important parts based on the averaged heat map. The eliminated parts of the image were filled with zeros, which were equivalent to black.…”

Section: Model Visualization and Quantitative Validationmentioning

confidence: 99%

Development of Deep Ensembles to Screen for Autism and Symptom Severity Using Retinal Photographs

Kim,

Hong,

Choi

et al. 2023

JAMA Netw Open

View full text Add to dashboard Cite

ImportanceScreening for autism spectrum disorder (ASD) is constrained by limited resources, particularly trained professionals to conduct evaluations. Individuals with ASD have structural retinal changes that potentially reflect brain alterations, including visual pathway abnormalities through embryonic and anatomic connections. Whether deep learning algorithms can aid in objective screening for ASD and symptom severity using retinal photographs is unknown.ObjectiveTo develop deep ensemble models to differentiate between retinal photographs of individuals with ASD vs typical development (TD) and between individuals with severe ASD vs mild to moderate ASD.Design, Setting, and ParticipantsThis diagnostic study was conducted at a single tertiary-care hospital (Severance Hospital, Yonsei University College of Medicine) in Seoul, Republic of Korea. Retinal photographs of individuals with ASD were prospectively collected between April and October 2022, and those of age- and sex-matched individuals with TD were retrospectively collected between December 2007 and February 2023. Deep ensembles of 5 models were built with 10-fold cross-validation using the pretrained ResNeXt-50 (32×4d) network. Score-weighted visual explanations for convolutional neural networks, with a progressive erasing technique, were used for model visualization and quantitative validation. Data analysis was performed between December 2022 and October 2023.ExposuresAutism Diagnostic Observation Schedule–Second Edition calibrated severity scores (cutoff of 8) and Social Responsiveness Scale–Second Edition T scores (cutoff of 76) were used to assess symptom severity.Main Outcomes and MeasuresThe main outcomes were participant-level area under the receiver operating characteristic curve (AUROC), sensitivity, and specificity. The 95% CI was estimated through the bootstrapping method with 1000 resamples.ResultsThis study included 1890 eyes of 958 participants. The ASD and TD groups each included 479 participants (945 eyes), had a mean (SD) age of 7.8 (3.2) years, and comprised mostly boys (392 [81.8%]). For ASD screening, the models had a mean AUROC, sensitivity, and specificity of 1.00 (95% CI, 1.00-1.00) on the test set. These models retained a mean AUROC of 1.00 using only 10% of the image containing the optic disc. For symptom severity screening, the models had a mean AUROC of 0.74 (95% CI, 0.67-0.80), sensitivity of 0.58 (95% CI, 0.49-0.66), and specificity of 0.74 (95% CI, 0.67-0.82) on the test set.Conclusions and RelevanceThese findings suggest that retinal photographs may be a viable objective screening tool for ASD and possibly for symptom severity. Retinal photograph use may speed the ASD screening process, which may help improve accessibility to specialized child psychiatry assessments currently strained by limited resources.

show abstract

Robust and Efficient Computation of Retinal Fractal Dimension Through Deep Approximation

Cited by 7 publications

References 20 publications

Retinal Fractal Dimension Is a Potential Biomarker for Systemic Health—Evidence From a Mixed-Age, Primary-Care Population

Retinal Fractal Dimension Is a Potential Biomarker for Systemic Health—Evidence From a Mixed-Age, Primary-Care Population

Screening of Moyamoya Disease From Retinal Photographs: Development and Validation of Deep Learning Algorithms

Development of Deep Ensembles to Screen for Autism and Symptom Severity Using Retinal Photographs

Contact Info

Product

Resources

About