Tongue colour and coating prediction in traditional Chinese medicine based on visible hyperspectral imaging

Zhang, Dong; Zhang, Junhua; Wang, Zheng; Sun, Meijun

doi:10.1049/iet-ipr.2018.5398

Cited by 10 publications

(7 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The critical idea in the independent component analysis is to assume that the data are amalgamated linearly across a set of individual sources and decompose them in terms of the statistical independence of the cross-information measures. Normalized reflectance spectra PCA [39] Normalized reflectance spectra PCA [84] Shannon entropy [40] Machine learning pre-processing [85] Normalized reflectance spectra PCA Singular Spectrum Analysis (SSA) [41] Normalized reflectance spectra Smoothing filter noise processing [86] PCA [31] Normalized reflectance spectra [42] Normalized reflectance spectra [87] Normalized reflectance spectra Smoothing filter noise processing [88] ICA K-means [43] Normalized reflectance spectra [44] Normalized reflectance spectra [45] Normalized reflectance spectra [89] Normalized reflectance spectra [90] Normalized reflectance spectra ACO Band Selection for Ant Colony Optimization (ACO) [91] PCA [46] Normalized reflectance spectra PCA [47] Ratio between original Image and reference image [48] Normalized reflectance spectra…”

Section: Wave Selectionmentioning

confidence: 99%

“…The experimental outcomes demonstrated the highest accuracy by placing the attention module at the final layer of the network to classify. Besides the categorization of cells, there are so many medical image classification applications using deep learning in the case of some cancer diagnoses, and most studies have used hyperspectral imaging with convolutional neural network (CNN) classifiers for cancer cell classification [31,33,35,42,85,91,94]. For example, Sommer et al [34] classified nephrons by using CNNs based on HSI data, specifically by residual neural networks (ResNet).…”

Section: Classificationmentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning in Medical Hyperspectral Images: A Review

Chen

Yu²,

Xu³

et al. 2022

Sensors

View full text Add to dashboard Cite

With the continuous progress of development, deep learning has made good progress in the analysis and recognition of images, which has also triggered some researchers to explore the area of combining deep learning with hyperspectral medical images and achieve some progress. This paper introduces the principles and techniques of hyperspectral imaging systems, summarizes the common medical hyperspectral imaging systems, and summarizes the progress of some emerging spectral imaging systems through analyzing the literature. In particular, this article introduces the more frequently used medical hyperspectral images and the pre-processing techniques of the spectra, and in other sections, it discusses the main developments of medical hyperspectral combined with deep learning for disease diagnosis. On the basis of the previous review, tne limited factors in the study on the application of deep learning to hyperspectral medical images are outlined, promising research directions are summarized, and the future research prospects are provided for subsequent scholars.

show abstract

Section: Wave Selectionmentioning

confidence: 99%

Section: Classificationmentioning

confidence: 99%

Deep Learning in Medical Hyperspectral Images: A Review

Chen

Yu²,

Xu³

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…C in Figure 1). The size of the convolution kernel is 1 × 1 × 3 (i.e.K 3 1 = 1,K 3 2 = 1, and K 3 3 = 3 in Figure 1). In order to extract spatial features without losing spectral information, the 3D convolution with spatial dimension of 3 × 3 is applied in the first two layers, spatial information and spectral information are potentially retained in the generated feature maps.…”

Section: D-mmentioning

confidence: 99%

“…Generally, HSIs are composed of hundreds of spectral bands and contain a wealth of spectral information, which is crucial for HSIs’ classification. In recent years, HSIs’ classification has been widely used in agriculture [2], medical [3], environmental science [4], and other applications, and has achieved remarkable results.…”

Section: Introductionmentioning

confidence: 99%

Hybrid network model based on 3D convolutional neural network and scalable graph convolutional network for hyperspectral image classification

Wang

Liang

2022

IET Image Processing

View full text Add to dashboard Cite

Hyperspectral images (HSIs) contain hundreds of continuous spectral bands and are rich in spectral-spatial information. In terms of HSIs' classification, traditional convolutional neural networks (CNNs) extract features based on HSI's spectral-spatial information through 2D convolution. However, 2D convolution extracts features in 2D plane without considering the relationships between spectral bands, which inevitably leads to insufficient feature extraction. 3D convolutional neural networks (3DCNNs) take account of the correlations among spectral bands and outperform 2D convolutional networks in feature extraction, but the computational cost is rather expensive. To address the above problem, a light-weight three-layer 3D convolutional network Module (3D-M) for HSIs' spectral-spatial feature extraction is proposed. Another challenge is that neither 2D convolution nor 3D convolution utilizes the structural information inherent in the data. Graph convolution networks (GCNs) can model and utilize such information through the similarity matrix, also known as adjacency matrix. However, traditional GCNs cannot handle large-scale data because they construct adjacency matrix on all data, which results in high computational complexity and large storage requirement. To conquer this challenge, this article proposes a batch-graph strategy on which a scalable GCN is developed. Finally, a hybrid network model (HNM) based on the proposed light-weight 3D-M and scalable GCN is presented. HNM extracts spectral-spatial features of HSIs with low computational complexity through the light-weight 3D convolution network and leverages the structural information in data via the scalable GCN. The experimental results on three public datasets with different sizes demonstrate that the proposed HNM produces better classification results than other state-of-the-art hyperspectral images classification models in terms of overall accuracy (OA), average accuracy (AA) and kappa coefficient (Kappa).

show abstract

“…Thus, the images acquired using the HS imaging technology contain not only abundant spatial structures but also detailed spectral signature and well suited to the substantial and high-performance analysis of imaged scenes. Having the advantages of detailed spectral distribution, the HS images were successfully used in various applications, such as remote sensing [ 1 ], food inspection [ 2 , 3 , 4 ], image classification [ 5 , 6 , 7 ] and object detection [ 8 , 9 , 10 ], and medicine [ 11 , 12 , 13 ], and are capable of achieving high-performance gain compared with other common RGB images. However, due to the radiant collection for each narrow-spectrum band in HS imaging sensors, less radiant energy per pixel and per spectral band measurement of an image scene is anticipated compared with the RGB imaging sensors.…”

Section: Introductionmentioning

confidence: 99%

Deep Unsupervised Fusion Learning for Hyperspectral Image Super Resolution

Liu

Zheng

Han

2021

Sensors

View full text Add to dashboard Cite

Hyperspectral image (HSI) super-resolution (SR) is a challenging task due to its ill-posed nature, and has attracted extensive attention by the research community. Previous methods concentrated on leveraging various hand-crafted image priors of a latent high-resolution hyperspectral (HR-HS) image to regularize the degradation model of the observed low-resolution hyperspectral (LR-HS) and HR-RGB images. Different optimization strategies for searching a plausible solution, which usually leads to a limited reconstruction performance, were also exploited. Recently, deep-learning-based methods evolved for automatically learning the abundant image priors in a latent HR-HS image. These methods have made great progress for HS image super resolution. Current deep-learning methods have faced difficulties in designing more complicated and deeper neural network architectures for boosting the performance. They also require large-scale training triplets, such as the LR-HS, HR-RGB, and their corresponding HR-HS images for neural network training. These training triplets significantly limit their applicability to real scenarios. In this work, a deep unsupervised fusion-learning framework for generating a latent HR-HS image using only the observed LR-HS and HR-RGB images without previous preparation of any other training triplets is proposed. Based on the fact that a convolutional neural network architecture is capable of capturing a large number of low-level statistics (priors) of images, the automatic learning of underlying priors of spatial structures and spectral attributes in a latent HR-HS image using only its corresponding degraded observations is promoted. Specifically, the parameter space of a generative neural network used for learning the required HR-HS image to minimize the reconstruction errors of the observations using mathematical relations between data is investigated. Moreover, special convolutional layers for approximating the degradation operations between observations and the latent HR-HS image are specifically to construct an end-to-end unsupervised learning framework for HS image super-resolution. Experiments on two benchmark HS datasets, including the CAVE and Harvard, demonstrate that the proposed method can is capable of producing very promising results, even under a large upscaling factor. Furthermore, it can outperform other unsupervised state-of-the-art methods by a large margin, and manifests its superiority and efficiency.

show abstract

Tongue colour and coating prediction in traditional Chinese medicine based on visible hyperspectral imaging

Cited by 10 publications

References 38 publications

Deep Learning in Medical Hyperspectral Images: A Review

Deep Learning in Medical Hyperspectral Images: A Review

Hybrid network model based on 3D convolutional neural network and scalable graph convolutional network for hyperspectral image classification

Deep Unsupervised Fusion Learning for Hyperspectral Image Super Resolution

Contact Info

Product

Resources

About