Full Field Optical Coherence Tomography Image Denoising Using Deep Learning with Spatial Compounding

Chen, I‐Ling; Ho, Tuan-Shu; Lu, Chih-Wei

doi:10.1109/isbi45749.2020.9098452

Cited by 5 publications

(8 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With reference to previous related studies [17,23], for the training dataset of the denoising model, only about 300-400 images are needed to achieve the outstanding effect, and increasing the amount of training data has a small improvement in performance [17]. In our research, the model was trained and verified via 335 B-scan OCT images collected from 10 patients [16]. The specifications of all B-scan data captured with the whole FF-OCT scan were 1024 × 715 pixels, about 0.5 µm/pixel image resolution, and storage in 8-bit pixel depth.…”

Section: Sc-dncnnmentioning

confidence: 92%

“…However, the tradeoffs are greater time consumed, motion blur, and potential reduction of spatial resolution. To address the difficulties, preliminary research [16] combined SC and deep learning to provide effective noise reduction while maintaining the details of the OCT image. An SC-based denoising convolutional neural network (SC-DnCNN) is used in the presented CADe system to improve image quality.…”

Section: Methodsmentioning

confidence: 99%

“…The training and implementation structure of the SC-DnCNN model are shown in Figure 4. According to the successful demonstration of B-scan image denoising in the previous study [16], we chose a model trained with noisy images compounded by 5-pixel lines to improve the en face scan (E-scan) image quality in this work. To train the SC-DnCNN model, 512 paired patches with a size of 50 × 50 were randomly cropped in each pair of images (noisy image and noise map).…”

Section: Sc-dncnnmentioning

confidence: 99%

See 2 more Smart Citations

Computer-Aided Detection (CADe) System with Optical Coherent Tomography for Melanin Morphology Quantification in Melasma Patients

Chen¹,

Wang

Chang

et al. 2021

Diagnostics

Self Cite

View full text Add to dashboard Cite

Dark skin-type individuals have a greater tendency to have pigmentary disorders, among which melasma is especially refractory to treat and often recurs. Objective measurement of melanin amount helps evaluate the treatment response of pigmentary disorders. However, naked-eye evaluation is subjective to weariness and bias. We used a cellular resolution full-field optical coherence tomography (FF-OCT) to assess melanin features of melasma lesions and perilesional skin on the cheeks of eight Asian patients. A computer-aided detection (CADe) system is proposed to mark and quantify melanin. This system combines spatial compounding-based denoising convolutional neural networks (SC-DnCNN), and through image processing techniques, various types of melanin features, including area, distribution, intensity, and shape, can be extracted. Through evaluations of the image differences between the lesion and perilesional skin, a distribution-based feature of confetti melanin without layering, two distribution-based features of confetti melanin in stratum spinosum, and a distribution-based feature of grain melanin at the dermal–epidermal junction, statistically significant findings were achieved (p-values = 0.0402, 0.0032, 0.0312, and 0.0426, respectively). FF-OCT enables the real-time observation of melanin features, and the CADe system with SC-DnCNN was a precise and objective tool with which to interpret the area, distribution, intensity, and shape of melanin on FF-OCT images.

show abstract

Section: Sc-dncnnmentioning

confidence: 92%

Section: Methodsmentioning

confidence: 99%

Section: Sc-dncnnmentioning

confidence: 99%

See 1 more Smart Citation

Computer-Aided Detection (CADe) System with Optical Coherent Tomography for Melanin Morphology Quantification in Melasma Patients

Chen¹,

Wang

Chang

et al. 2021

Diagnostics

Self Cite

View full text Add to dashboard Cite

show abstract

“…Adapted from Ref. 57 . (d) Comparison of FF-OCT images of a Ficus leaf before and after sample self-induced aberration was corrected when imaging at a depth of

.…”

Section: Ff-oct Performance Optimization Methodsmentioning

confidence: 99%

“…The fundamental approach for noise elimination based on deep learning is to distinguish noise from signals by combining spatial mixing and noise spectrum prediction technology. 57 As shown in Fig. 5(c) , a neural network of two-phase image-spectrum conversion is adopted to reduce the noise of the FF-OCT image.…”

Section: Ff-oct Performance Optimization Methodsmentioning

confidence: 99%

Methods and applications of full-filed optical coherence tomography: a review

2022

J. Biomed. Opt.

View full text Add to dashboard Cite

Analysis of Noise Removal Techniques on Retinal Optical Coherence Tomography Images

Sheeba¹,

Raj²

2022

IJACSA

View full text Add to dashboard Cite

In the biomedical field, automatic disease detection by image processing has become the norm in the current days. For early illness detection, ophthalmologists have explored a variety of invasive and noninvasive procedures. Optical Coherence Tomography (OCT) is a noninvasive imaging technique for obtaining high resolution tomographic images of biological systems. The image quality is degraded by noise, which degrades the performance of noisy image processing algorithms. The OCT images captured with speckle noise and prior to further processing, it is critical to use an effective approach for denoising the image. In this paper, we used Median filter, Average filter or Mean filter, Wiener filter, Gaussian filter and Bilateral filter on OCT images in this paper, and discussed the advantages and drawbacks of each approach. The effectiveness of these filters are compared using the Peak Signal to Noise Ratio (PSNR), Mean Square Error (MSE) and Contrast to Noise Ratio (CNR).

show abstract

Full Field Optical Coherence Tomography Image Denoising Using Deep Learning with Spatial Compounding

Cited by 5 publications

References 16 publications

Computer-Aided Detection (CADe) System with Optical Coherent Tomography for Melanin Morphology Quantification in Melasma Patients

Computer-Aided Detection (CADe) System with Optical Coherent Tomography for Melanin Morphology Quantification in Melasma Patients

Methods and applications of full-filed optical coherence tomography: a review

Analysis of Noise Removal Techniques on Retinal Optical Coherence Tomography Images

Contact Info

Product

Resources

About