Disease Classification of Macular Optical Coherence Tomography Scans Using Deep Learning Software

Bhatia, Kanwal K.; Graham, Mark S.; Terry, Louise; Wood, Ashley; Tranos, Paris; Trikha, Sameer; Jaccard, Nicolas

doi:10.1097/iae.0000000000002640

Cited by 27 publications

(16 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Pegasus primarily uses deep learning technologies to identify images with anomalous features that may be indicative of disease to enable classification into disease groups. 12 Additionally, Pegasus-OCT incorporates automated multiclass fluid segmentation algorithms designed to detect and segment three clinical subtypes of fluid: intraretinal fluid (IRF), subretinal fluid (SRF), and pigment epithelial detachment (PED). IRF is characterized as a hyporeflective space (cystoid fluid) located within the neural retinal tissue, SRF as a hyporeflective space located between the hyperreflective retinal pigment epithelium (RPE) and the overlying neural retina, and PED as a hyporeflective space located between the RPE and underlying Bruch's membrane, visible on the OCT as the anterior of the choroidal vascular layer.…”

Section: Introductionmentioning

confidence: 99%

Evaluation of Automated Multiclass Fluid Segmentation in Optical Coherence Tomography Images Using the Pegasus Fluid Segmentation Algorithms

Terry

Trikha

Bhatia³

et al. 2021

Trans. Vis. Sci. Tech.

Self Cite

View full text Add to dashboard Cite

To evaluate the performance of the Pegasus-OCT (Visulytix Ltd) multiclass automated fluid segmentation algorithms on independent spectral domain optical coherence tomography data sets. Methods:The Pegasus automated fluid segmentation algorithms were applied to three data sets with edematous pathology, comprising 750, 600, and 110 b-scans, respectively. Intraretinal fluid (IRF), sub-retinal fluid (SRF), and pigment epithelial detachment (PED) were automatically segmented by Pegasus-OCT for each b-scan where ground truth from data set owners was available. Detection performance was assessed by calculating sensitivities and specificities, while Dice coefficients were used to assess agreement between the segmentation methods.Results: For two data sets, IRF detection yielded promising sensitivities (0.98 and 0.94, respectively) and specificities (1.00 and 0.98) but less consistent agreement with the ground truth (dice coefficients 0.81 and 0.59); likewise, SRF detection showed high sensitivity (0.86 and 0.98) and specificity (0.83 and 0.89) but less consistent agreement (0.59 and 0.78). PED detection on the first data set showed moderate agreement (0.66) with high sensitivity (0.97) and specificity (0.98). IRF detection in a third data set yielded less favorable agreement (0.46-0.57) and sensitivity (0.59-0.68), attributed to image quality and ground truth grader discordance. Conclusions:The Pegasus automated fluid segmentation algorithms were able to detect IRF, SRF, and PED in SD-OCT b-scans acquired across multiple independent data sets. Dice coefficients and sensitivity and specificity values indicate the potential for application to automated detection and monitoring of retinal diseases such as agerelated macular degeneration and diabetic macular edema.Translational Relevance: The potential of Pegasus-OCT for automated fluid quantification and differentiation of IRF, SRF, and PED in OCT images has application to both clinical practice and research.

show abstract

Section: Introductionmentioning

confidence: 99%

Evaluation of Automated Multiclass Fluid Segmentation in Optical Coherence Tomography Images Using the Pegasus Fluid Segmentation Algorithms

Terry

Trikha

Bhatia³

et al. 2021

Trans. Vis. Sci. Tech.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Nesta tarefa, softwares de auxílio ao diagnóstico, que funcionam de forma automática e inteligente, podem favorecer no diagnóstico mais eficaz das doenças, melhorando o prognóstico do paciente. Noâmbito do desenvolvimento de sistemas de auxílio ao diagnóstico (Computer-Aided Diagnosis -CAD), sistemas inteligentes que integram técnicas de Análise e Processamento de Imagensà ferramenta de aprendizado de máquina, tem tido ampla utilização na detecção de diagnósticos complexos, como o auxílio ao diagnóstico do Edema Macular [Bhatia et al 2020] e da Retinopatia Diabética [Gama et al 2020].…”

Section: Introductionunclassified

Detecção Automática de Anomalias Oculares Utilizando Redes Neurais Convolucionais

Moura¹,

Coelho²,

Baffa³

2021

Anais Do VIII Encontro Nacional De Computação Dos Institutos Federais (EnCompIF 2021)

View full text Add to dashboard Cite

Analisando a importância do cuidado com a visão, o trabalho proposto tem como objetivo desenvolver um método de auxílio ao diagnostico de diferentes anomalias que acometem a região externa do olho. A Rede Neural Convolucional foi então utilizada para detectar padroes visuais das imagens da base de dados Warsaw BioBase Disease Iris v2.1, que posteriormente foram classificadas entre doentes e saudáveis. O classificador construído foi avaliado seguindo o protocolo de experimentação Holdout, obtendo uma taxa de acerto de 94%. Mediante tal resultado, é possível concluir que o modelo desenvolvido tem potencial para se tornar uma ferramenta para o auxílio ao diagnostico.

show abstract

“…. 11] and max_f eatures ∈ [2,3,4]. Model estimation and grid-search for C r was performed using scikit-learn.…”

Section: Evaluation Methodologymentioning

confidence: 99%

“…The CNN architecture shown in figure 2 differs to the typical Deep Learning architectures used in Ophthalmology for prediction. Usually, 2D CNNs are used in which the model input is a single b-scan from a subject [3,23,16,17]. Such approaches require a way of pooling the model predictions from each b-scan to give a volume-level prediction.…”

Section: Fully Trained Deep Learning Modelsmentioning

confidence: 99%

“…An alternative to using biomarkers for predictive modelling is to use Deep Learning methods, whereby image features are extracted by training a Convolutional Neural Network (CNN). Deep Learning has been used in a number of prediction tasks involving OCT, such as disease classification [14,3], prediction of conversion to nAMD [24], and treatment referral [16,11]. In [23], Deep Learning was used to predict treatment response of patients with nAMD from OCT and clinical/demographic variables.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Rao, Anil; Chandra, Shruti; Sivaprasad, Sobha; (2022) Prediction of treatment response in patients with neovascular age-related macular degeneration

View full text Add to dashboard Cite

Neovascular age-related macular degeneration (nAMD) is a common cause of visual impairment, and is currently treated with intravitreal anti-vascular endothelial growth factor agents such as aflibercept. While these treatments may improve visual acuity (VA) in some patients, clinicians cannot currently predict who is likely to benefit before treatment starts. The aim of this study is to explore the effectiveness of using Deep Learning approaches to train models for predicting whether a patient's VA will respond favourably to three months of aflibercept therapy, using pre-treatment OCT images and clinical/demographic variables. We train a number of models using standard machine learning, Deep Learning transfer learning, and fully trained Deep Learning approaches in two experiments using outcomes based on the VA at 4-10 weeks after the final dose. In experiment one, we trained models to predict whether the VA will be at least 54 Early Treatment Diabetic Retinopathy Study (ETDRS) letters, while in experiment two we trained them to predict whether the VA will have increased by 10 or more letters. Model prediction quality was assessed using the Area Under the Curve (AUC) of the Receiver-Operating-Characteristic (ROC) curves. We found that all models performed significantly better than chance in both experiments, except for the fully trained Deep Learning model using just images in experiment two. The best performing model for experiment one was the Deep Learning transfer model using images and clinical/demographic variables (AUC=0.901), while in experiment two, none of the Deep Learning approaches performed better than a random forest using only clinical/demographic variables (AUC=0.751). Our experiments suggest that different Deep Learning approaches are required for predicting the second outcome if we want the models to perform better than those that use clinical/demographic variables alone.

show abstract

Disease Classification of Macular Optical Coherence Tomography Scans Using Deep Learning Software

Cited by 27 publications

References 30 publications

Evaluation of Automated Multiclass Fluid Segmentation in Optical Coherence Tomography Images Using the Pegasus Fluid Segmentation Algorithms

Evaluation of Automated Multiclass Fluid Segmentation in Optical Coherence Tomography Images Using the Pegasus Fluid Segmentation Algorithms

Detecção Automática de Anomalias Oculares Utilizando Redes Neurais Convolucionais

Rao, Anil; Chandra, Shruti; Sivaprasad, Sobha; (2022) Prediction of treatment response in patients with neovascular age-related macular degeneration

Contact Info

Product

Resources

About