Machine learning based detection of age-related macular degeneration (AMD) and diabetic macular edema (DME) from optical coherence tomography (OCT) images

Wang, Yu; Zhang, Yaonan; Yao, Zhaomin; Zhao, Ruxing; Zhou, Fengfeng

doi:10.1364/boe.7.004928

Cited by 122 publications

(69 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Information about the segmented layer is utilized to quantify layer deformations to identify the pathology [2,7,19,20]. Another stream of algorithms includes the quantification of textural and morphological features to train a classifier to identify the pathology [21][22][23][24][25][26]. The evolution of salient feature quantification has reduced the dependency of image classification approaches on retinal segmentation; for example, in recent OCT image classification techniques [24] utilizes only segmented retinal pigment epithelium (RPE) layer information for retinal flattening and this has also been considered as a common practice.…”

Section: Introductionmentioning

confidence: 99%

Transfer learning based classification of optical coherence tomography images with diabetic macular edema and dry age-related macular degeneration

Karri

Chakraborty

Chatterjee

2017

Biomed. Opt. Express

251

146

View full text Add to dashboard Cite

We present an algorithm for identifying retinal pathologies given retinal optical coherence tomography (OCT) images. Our approach fine-tunes a pre-trained convolutional neural network (CNN), GoogLeNet, to improve its prediction capability (compared to random initialization training) and identifies salient responses during prediction to understand learned filter characteristics. We considered a data set containing subjects with diabetic macular edema, or dry age-related macular degeneration, or no pathology. The fine-tuned CNN could effectively identify pathologies in comparison to classical learning. Our algorithm aims to demonstrate that models trained on non-medical images can be fine-tuned for classifying OCT images with limited training data.

show abstract

Section: Introductionmentioning

confidence: 99%

Transfer learning based classification of optical coherence tomography images with diabetic macular edema and dry age-related macular degeneration

Karri

Chakraborty

Chatterjee

2017

Biomed. Opt. Express

251

146

View full text Add to dashboard Cite

show abstract

“…All in all, these insights emphasize once more, that OCT's capability of producing volumetric information is very exploitable by 3D CNNs. We provide strong evidence that OCT based 2D slicing and projection methods (Roth et al, 2016;Wang et al, 2016;Venhuizen et al, 2015) could significantly benefit from 3D data usage and volumetric feature exploitation.…”

Section: Discussionmentioning

confidence: 60%

A deep learning approach for pose estimation from volumetric OCT data

Gessert

Schlüter

Schlaefer

2018

Medical Image Analysis

View full text Add to dashboard Cite

Tracking the pose of instruments is a central problem in image-guided surgery. For microscopic scenarios, optical coherence tomography (OCT) is increasingly used as an imaging modality. OCT is suitable for accurate pose estimation due to its micrometer range resolution and volumetric field of view. However, OCT image processing is challenging due to speckle noise and reflection artifacts in addition to the images' 3D nature. We address pose estimation from OCT volume data with a new deep learning-based tracking framework. For this purpose, we design a new 3D convolutional neural network (CNN) architecture to directly predict the 6D pose of a small marker geometry from OCT volumes. We use a hexapod robot to automatically acquire labeled data points which we use to train 3D CNN architectures for multi-output regression. We use this setup to provide an in-depth analysis on deep learning-based pose estimation from volumes. Specifically, we demonstrate that exploiting volume information for pose estimation yields higher accuracy than relying on 2D representations with depth information. Supporting this observation, we provide quantitative and qualitative results that 3D CNNs effectively exploit the depth structure of marker objects. Regarding the deep learning aspect, we present efficient design principles for 3D CNNs, making use of insights from the 2D deep learning community. In particular, we present Inception3D as a new architecture which performs best for our application. We show that our deep learning approach reaches errors at our ground-truth label's resolution. We achieve a mean average error of 14.89 ± 9.3 µm and 0.096 ± 0.072° for position and orientation learning, respectively.

show abstract

“…A classifier was evaluated for optimizing its parameters by the 5-fold cross-validation strategy, and its classification performance was calculated by the leave-one-out validation strategy for the comparison with the existing studies. The k-fold cross validation strategy randomly split both the positive and negative datasets into k equally-sized bins and iteratively tested each pair of one positive and one negative bin with the model trained over the other samples (Wang, et al, 2018;Wang, et al, 2016;Zhao, et al, 2018). The final performance metrics were averaged over all the samples.…”

Section: Evaluation Methods Of Performancementioning

confidence: 99%

sefOri: selecting the best-engineered sequence features to predict DNA replication origins

et al. 2019

Self Cite

View full text Add to dashboard Cite

Motivation Cell divisions start from replicating the double-stranded DNA, and the DNA replication process needs to be precisely regulated both spatially and temporally. The DNA is replicated starting from the DNA replication origins. A few successful prediction models were generated based on the assumption that the DNA replication origin regions have sequence level features like physicochemical properties significantly different from the other DNA regions. Results This study proposed a feature selection procedure to further refine the classification model of the DNA replication origins. The experimental data demonstrated that as large as 26% improvement in the prediction accuracy may be achieved on the yeast Saccharomyces cerevisiae. Moreover, the prediction accuracies of the DNA replication origins were improved for all the four yeast genomes investigated in this study. Availability and implementation The software sefOri version 1.0 was available at http://www.healthinformaticslab.org/supp/resources.php. An online server was also provided for the convenience of the users, and its web link may be found in the above-mentioned web page. Supplementary information Supplementary data are available at Bioinformatics online.

show abstract

Machine learning based detection of age-related macular degeneration (AMD) and diabetic macular edema (DME) from optical coherence tomography (OCT) images

Cited by 122 publications

References 36 publications

Transfer learning based classification of optical coherence tomography images with diabetic macular edema and dry age-related macular degeneration

Transfer learning based classification of optical coherence tomography images with diabetic macular edema and dry age-related macular degeneration

A deep learning approach for pose estimation from volumetric OCT data

sefOri: selecting the best-engineered sequence features to predict DNA replication origins

Contact Info

Product

Resources

About