Sampling Time Adaptive Single-Photon Compressive Imaging

Wang, Hui; Yan, Qiurong; Li, Bing; Yuan, Chenglong; Wang, Yuhao

doi:10.1109/jphot.2019.2912326

Cited by 7 publications

(3 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For fair comparison, all domain adaptation methods use VGG‐16 for feature extraction. To quantify the performance of different methods, we used the evaluation metrics of classification accuracy, precision, recall, and AUC (areas under ROC curve) values, which are widely adopted in the literature [5, 11]. The definition of classification accuracy can be expressed as:

Accuracy = \frac{Number of correctly classified samples}{Total number of samples} .

…”

Section: Discussionmentioning

confidence: 99%

“…It has also been widely adopted for automatic retinopathy classification with OCT images. The authors in [5] applied five deep learning algorithms, that is, CliqueNet, DPN, DenseNet, ResNet, and ResNext, to classify OCT images with different retinopathies. Lee et al leveraged the popular VGG‐16 deep learning method for retinopathy classification [6].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Cross‐domain retinopathy classification with optical coherence tomography images via a novel deep domain adaptation method

Luo

Hou

et al. 2021

Journal of Biophotonics

View full text Add to dashboard Cite

Deep learning based retinopathy classification with optical coherence tomography (OCT) images has recently attracted great attention. However, existing deep learning methods fail to work well when training and testing datasets are different due to the general issue of domain shift between datasets caused by different collection devices, subjects, imaging parameters, etc. To address this practical and challenging issue, we propose a novel deep domain adaptation (DDA) method to train a model on a labeled dataset and adapt it to an unlabelled dataset (collected under different conditions). It consists of two modules for domain alignment, that is, adversarial learning and entropy minimization. We conduct extensive experiments on three public datasets to evaluate the performance of the proposed method. The results indicate that there are large domain shifts between datasets, resulting a poor performance for conventional deep learning methods. The proposed DDA method can significantly outperform existing methods for retinopathy classification with OCT images. It achieves retinopathy classification accuracies of 0.915, 0.959 and 0.990 under three cross‐domain (cross‐dataset) scenarios. Moreover, it obtains a comparable performance with human experts on a dataset where no labeled data in this dataset have been used to train the proposed DDA method. We have also visualized the learnt features by using the t‐distributed stochastic neighbor embedding (t‐SNE) technique. The results demonstrate that the proposed method can learn discriminative features for retinopathy classification.

show abstract

Accuracy = \frac{Number of correctly classified samples}{Total number of samples} .

…”

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Cross‐domain retinopathy classification with optical coherence tomography images via a novel deep domain adaptation method

Luo

Hou

et al. 2021

Journal of Biophotonics

View full text Add to dashboard Cite

show abstract

“…In recent years, deep learning technology has been developed and achieved significant success in many applications. Deep learning has been extended to the field of OCT, and many breakthroughs have been made for retinal layer segmentation [19][20][21], avascular area detection [22], and retinal disease classification [23][24][25]. In addition, Gour and Khanna [26] used residual deep convolutional neural network for speckle denoising in retinal OCT structural images, where the image quality was significantly improved in terms of peak signal-tonoise ratio (PSNR) and structural similarity (SSIM) compared with traditional denoising methods.…”

Section: Introductionmentioning

confidence: 99%

Deep‐learning visualization enhancement method for optical coherence tomography angiography in dermatology

Yuan

Qin

et al. 2023

Journal of Biophotonics

View full text Add to dashboard Cite

Optical coherence tomography angiography (OCTA) in dermatology usually suffers from low image quality due to the highly scattering property of the skin, the complexity of cutaneous vasculature, and limited acquisition time. Deep‐learning methods have achieved great success in many applications. However, the deep learning approach to improve dermatological OCTA images has not been investigated due to the requirement of high‐performance OCTA systems and difficulty of obtaining high‐quality images as ground truth. This study aims to generate proper datasets and develop a robust deep learning method to enhance the skin OCTA images. A swept‐source skin OCTA system was employed to create low‐quality and high‐quality OCTA images with different scanning protocols. We propose a model named vascular visualization enhancement generative adversarial network and adopt an optimized data augmentation strategy and perceptual content loss function to achieve better image enhancement effect with small amount of training data. We demonstrate the superiority of the proposed method in skin OCTA image enhancement by quantitative and qualitative comparisons.

show abstract

Deep-learning-based single-photon-counting compressive imaging via jointly trained subpixel convolution sampling

Yan

Guan

et al. 2020

Appl. Opt.

View full text Add to dashboard Cite

The combination of single-pixel-imaging and single-photon-counting technology can achieve ultrahigh-sensitivity photon-counting imaging. However, its applications in high-resolution and real-time scenarios are limited by the long sampling and reconstruction time. Deep-learning-based compressive sensing provides an effective solution due to its ability to achieve fast and high-quality reconstruction. This paper proposes a sampling and reconstruction integrated neural network for single-photon-counting compressive imaging. To effectively remove the blocking artefact, a subpixel convolutional layer is jointly trained with a deep reconstruction network to imitate compressed sampling. By modifying the forward and backward propagation of the network, the first layer is trained into a binary matrix, which can be applied to the imaging system. An improved deep-reconstruction network based on the traditional Inception network is proposed, and the experimental results show that its reconstruction quality is better than existing deep-learning-based compressive sensing reconstruction algorithms.

show abstract

Sampling Time Adaptive Single-Photon Compressive Imaging

Cited by 7 publications

References 32 publications

Cross‐domain retinopathy classification with optical coherence tomography images via a novel deep domain adaptation method

Cross‐domain retinopathy classification with optical coherence tomography images via a novel deep domain adaptation method

Deep‐learning visualization enhancement method for optical coherence tomography angiography in dermatology

Deep-learning-based single-photon-counting compressive imaging via jointly trained subpixel convolution sampling

Contact Info

Product

Resources

About