Automatic quality evaluation as assessment standard for optical coherence tomography

Kauer, Josef; Gawlik, K.; Zimmermann, Hanna; Kadas, Ella Maria; Bereuter, Charlotte; Paul, Friedemann; Brandt, Alexander U.; Haußer, Frank; Darvin, Maxim E.

doi:10.1117/12.2510393

Cited by 7 publications

(8 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Few studies have investigated the use of blind IQA methods based on OCT until 2019. Kauer et al proposed an AQuANet to classify OCT B-scans into 'good,' 'bad,' 'upper,' and 'lower' categories using A-scans [22]. However, this study only investigated the position of the signal.…”

Section: Introductionmentioning

confidence: 99%

Deep learning for quality assessment of retinal OCT images

Wang

Deng

et al. 2019

Biomed. Opt. Express

View full text Add to dashboard Cite

Optical coherence tomography (OCT) is a promising high-speed, non-invasive imaging modality providing high-resolution retinal scans. However, a variety of external factors such as light occlusion and patient movement can seriously degrade OCT image quality, which complicates manual retinopathy detection and computer-aided diagnosis. As such, this study first presents an OCT image quality assessment (OCT-IQA) system, capable of automatic classification based on signal completeness, location, and effectiveness. Four CNN architectures (VGG-16, Inception-V3, ResNet-18, and ResNet-50) from the ImageNet classification task were used to train the proposed OCT-IQA system via transfer learning. The ResNet-50 with the best performance was then integrated into the final OCT-IQA network. The usefulness of this approach was evaluated using retinopathy detection results. A retinopathy classification network was first trained by fine-tuning Inception-V3 model. The model was then applied to two test datasets, created randomly from the original dataset, one of which was screened by the OCT-IQA system and only included high quality images while the other was mixed by high and low quality images. Results showed that retinopathy detection accuracy and area under curve (AUC) were 3.75% and 1.56% higher, respectively, for the filtered data (compared with the unfiltered data). These experimental results demonstrate the effectiveness of the proposed OCT-IQA system and suggest that deep learning could be applied to the design of computer-aided systems (CADSs) for automatic retinopathy detection.

show abstract

Section: Introductionmentioning

confidence: 99%

Deep learning for quality assessment of retinal OCT images

Wang

Deng

et al. 2019

Biomed. Opt. Express

View full text Add to dashboard Cite

show abstract

“…To automatically detect and remove these artefacts, we employ a deep learning-based quality control method described and validated in detail previously [ 39 , 40 ]. Briefly, the automatic quality analysis (AQuA) method combines the detection of center, signal quality and image completeness artifacts.…”

Section: Methodsmentioning

confidence: 99%

“…All scans underwent automatic quality control to avoid data with insufficient quality for training and validation purposes [ 39 , 40 ]. In the end, we selected 17,458 B-scans for training, 3081 for validation and 208 for testing.…”

Section: Methodsmentioning

confidence: 99%

Intraretinal Layer Segmentation Using Cascaded Compressed U-Nets

et al. 2022

Self Cite

View full text Add to dashboard Cite

Reliable biomarkers quantifying neurodegeneration and neuroinflammation in central nervous system disorders such as Multiple Sclerosis, Alzheimer’s dementia or Parkinson’s disease are an unmet clinical need. Intraretinal layer thicknesses on macular optical coherence tomography (OCT) images are promising noninvasive biomarkers querying neuroretinal structures with near cellular resolution. However, changes are typically subtle, while tissue gradients can be weak, making intraretinal segmentation a challenging task. A robust and efficient method that requires no or minimal manual correction is an unmet need to foster reliable and reproducible research as well as clinical application. Here, we propose and validate a cascaded two-stage network for intraretinal layer segmentation, with both networks being compressed versions of U-Net (CCU-INSEG). The first network is responsible for retinal tissue segmentation from OCT B-scans. The second network segments eight intraretinal layers with high fidelity. At the post-processing stage, we introduce Laplacian-based outlier detection with layer surface hole filling by adaptive non-linear interpolation. Additionally, we propose a weighted version of focal loss to minimize the foreground–background pixel imbalance in the training data. We train our method using 17,458 B-scans from patients with autoimmune optic neuropathies, i.e., multiple sclerosis, and healthy controls. Voxel-wise comparison against manual segmentation produces a mean absolute error of 2.3 μm, outperforming current state-of-the-art methods on the same data set. Voxel-wise comparison against external glaucoma data leads to a mean absolute error of 2.6 μm when using the same gold standard segmentation approach, and 3.7 μm mean absolute error in an externally segmented data set. In scans from patients with severe optic atrophy, 3.5% of B-scan segmentation results were rejected by an experienced grader, whereas this was the case in 41.4% of B-scans segmented with a graph-based reference method. The validation results suggest that the proposed method can robustly segment macular scans from eyes with even severe neuroretinal changes.

show abstract

“…To remove these artefacts from the OCT volumes, we employ a deep learning-based quality check method introduced and described in detail by Kauer et al (2019). The output of the quality analysis is combined into three key features; centering, signal quality and image completeness.…”

Section: Methodsmentioning

confidence: 99%

“…All scans underwent automatic quality control to avoid data with insufficient quality for training and validation purposes (Kauer et al (2019)). To delineate different OCT layers in these data, the initial segmentation was performed using the SAMIRIX toolbox (Motamedi et al (2019)), which uses AURA developed by Lang et al (2013), and then manually corrected by experts using the same toolbox.…”

Section: Methodsmentioning

confidence: 99%

Deep Learning based Intraretinal Layer Segmentation using Cascaded Compressed U-Net

Yadav

Kafieh

Zimmermann

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Intraretinal layer segmentation on macular optical coherence tomography (OCT) images generates non invasive biomarkers querying neuronal structures with near cellular resolution. While first deep learning methods have delivered promising results with high computing power demands, a reliable, power efficient and reproducible intraretinal layer segmentation is still an unmet need. We propose a cascaded two-stage network for intraretinal layer segmentation, with both networks being compressed versions of U-Net (CCU-INSEG). The first network is responsible for retinal tissue segmentation from OCT B-scans. The second network segments 8 intraretinal layers with high fidelity. By compressing U-Net, we achieve 392- and 26-time reductions in model size and parameters in the first and second network, respectively. Still, our method delivers almost similar accuracy compared to U-Net without additional constraints of computation and memory resources. At the post-processing stage, we introduce Laplacian-based outlier detection with layer surface hole filling by adaptive non-linear interpolation. We trained our method using 17,458 B-scans from patients with autoimmune optic neuropathies, i.e. multiple sclerosis, and healthy controls. Voxel-wise comparison against manual segmentation produces a mean absolute error of 2.3μm, which is 2.5x better than the device’s own segmentation. Voxel-wise comparison against external multicenter data leads to a mean absolute error of 2.6μm for glaucoma data using the same gold standard segmentation approach, and 3.7μm mean absolute error compared against an externally segmented reference data set. In 20 macular volume scans from patients with severe disease, 3.5% of B-scan segmentation results were rejected by an experienced grader, whereas this was the case in 41.4% of B-scans segmented with a graph-based reference method.

show abstract

Automatic quality evaluation as assessment standard for optical coherence tomography

Cited by 7 publications

References 15 publications

Deep learning for quality assessment of retinal OCT images

Deep learning for quality assessment of retinal OCT images

Intraretinal Layer Segmentation Using Cascaded Compressed U-Nets

Deep Learning based Intraretinal Layer Segmentation using Cascaded Compressed U-Net

Contact Info

Product

Resources

About