Early diagnosis of gastric cancer based on deep learning combined with the spectral-spatial classification method

Li, Yuanpeng; Deng, Liangyu; Yang, Xinhao; Liu, Zhao; Zhao, Xiaoping; Huang, Furong; Zhu, Siqi; Chen, Xingdan; Chen, Zhenqiang; Zhang, Weimin

doi:10.1364/boe.10.004999

Cited by 29 publications

(36 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It was necessary to preprocess the original spectra due to the uneven intensity of light sources at different wavelengths and the influence of instrument noise. In this paper, the spectra were processed using ten preprocessing methods, including multiplicative scatter correction (MSC) [ 23 ], standardized normal variate (SNV) [ 24 ], normalization [ 25 ], autoscales [ 26 ], mean centering (MC) [ 27 ], moving average method (MA) [ 28 ], detrend fluctuation analysis (Detrend) [ 29 ], Savitsky–Golay smoothing (SG) [ 30 ], Savitsky–Golay first derivative (SG-FD) [ 31 ], and Savitsky–Golay second derivative (SG-SD) [ 32 ]. To reduce calculation and increase calculation speed, competitive adaptive reweighted sampling (CARS) [ 33 ], principal components analysis (PCA) [ 34 ], and successive projections algorithm (SPA) [ 35 ] are preferable to extract feature wavelengths to reduce the dimensionality.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Nondestructive Detection for Egg Freshness Based on Hyperspectral Scattering Image Combined with Ensemble Learning

Dai

Jiang

Lü

et al. 2020

Sensors

View full text Add to dashboard Cite

Scattering hyperspectral technology is a nondestructive testing method with many advantages. Here, we propose a method to improve the accuracy of egg freshness, research the influence of incident angles of light source on the accuracy, and explain its mechanism. A variety of weak classifiers classify eggs based on the spectra after preprocessing and feature wavelength extraction to obtain three classifiers with the highest accuracy. The three classifiers are used as metamodels of stacking ensemble learning to improve the highest accuracy from 96.25% to 100%. Moreover, the highest accuracy of scattering, reflection, transmission, and mixed hyperspectral of eggs are 100.00%, 88.75%, 95.00%, and 96.25%, respectively, indicating that the scattering hyperspectral for egg freshness detection is better than that of the others. In addition, the accuracy is inversely proportional to the angle of incidence, i.e., the smaller the incident angle, the camera collects a larger proportion of scattering light, which contains more biochemical parameters of an egg than that of reflection and transmission. These results are very important for improving the accuracy of non-destructive testing and for selecting the incident angle of a light source, and they have potential applications for online non-destructive testing.

show abstract

Section: Methodsmentioning

confidence: 99%

“…To further improve the accuracy of the model, several weak classifiers are combined into a strong classifier, and stacking ensemble learning (SEL) [ 32 ] is performed to improve the generalization ability of the classification model. A two-layer training structure of SEL is used to improve the accuracy and speed of model.…”

Section: Guided Filteringmentioning

confidence: 99%

Nondestructive Detection for Egg Freshness Based on Hyperspectral Scattering Image Combined with Ensemble Learning

Dai

Jiang

Lü

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…It is necessary to preprocess the original spectra due to the uneven intensity of light sources at different wavelengths and the influence of instrument noise. In this paper, the spectra are processed by ten pre-processing methods, including Multiplicative Scatter Correction (MSC) [18], Standardized Normal Variate (SNV) [19], Normalization [20], Autoscales [21], Mean Centering (MC) [22], Moving-Average Method (MA) [23], Detrend Fluctuation Analysis (Detrend) [24], Savitsky-Golay Smoothing (SG) [25], Savitsky-Golay-First Derivative (SG-FD) [26] and Savitsky-Golay-Second Derivative (SG-SD) [27]. to distinguish due to their obvious spoilage and unpleasant smell deterioration, so they will not be discussed in this article.…”

Section: Spectrum Processing Methodsmentioning

confidence: 99%

“…To further improve the accuracy of the model, several weak classifiers are combined into a strong classifier, and stacking ensemble learning (SEL) [27] is performed to improve the generalization ability of the classification model. A two-layer training structure of SEL is used to improve the accuracy and speed of model.…”

Section: Egg Freshness Classification Based On Stacking Ensemble Learmentioning

confidence: 99%

Nondestructive Detection for Egg Freshness based on Hyperspectral Scattering Image combined with Ensemble Learning

Dai¹,

Jiang²,

Lu³

et al. 2020

Preprint

View full text Add to dashboard Cite

Scattering hyperspectral technology is a nondestructive testing method with many advantages. Here, we propose a method to improve the accuracy of egg freshness, research the influence of incident angles of light source on the accuracy and explain its mechanism. A variety of weak classifiers classify eggs based on the spectra after preprocessing and feature wavelength extraction to obtain three classifiers with the highest accuracy. The three classifiers are used as metamodels of stacking ensemble learning to improve the highest accuracy from 96.25% to 100%. Moreover, the highest accuracy of scattering, reflection, transmission and mixed hyperspectral of eggs are 100.00%, 88.75%, 95.00% and 96.25%, respectively, indicating that the scattering hyperspectral for egg freshness detection is better than that of the others. In addition, the accuracy is inversely proportional to the angle of incidence due that the smaller the incident angle, the camera collects a larger proportion of scattering light, which contains more biochemical parameters of an egg than that of reflection and transmission. These results are very important for improving the accuracy of non-destructive testing and selecting the incident angle of the light source, and have potential applications in online non-destructive testing.

show abstract

“…to detect various kind of cancers and tumors. Some automatic detection systems (Rahmawaty et al 2016;Solmaz and Tareripour 2016;Bakheey 2017;Khan et al 2019) classify medical images based on the features extracted using traditional handcrafted techniques whereas, others (Liu et al 2015;Li et al 2019;Bisla et al 2019;Cao et al 2019) use DLM to perform feature extraction and classification of medical images. Recently, it has been observed that researchers have proposed automatic detection systems (Yadav et al 2018;Hasan et al 2019;Almaraz-Damian 2020;Shankar and Perumal 2020) that use an amalgamation of both the techniques and these systems exhibit good performance as compared to their counter-parts.…”

Section: Related Workmentioning

confidence: 99%

Automatic Detection of Osteosarcoma Based on Integrated Features and Feature Selection Using Binary Arithmetic Optimization Algorithm

Bansal

Gehlot

Singhal

2021

Preprint

View full text Add to dashboard Cite

Osteosarcoma is one of the most common malignant bone tumor mostly found in children and teenagers. Manual detection of osteosarcoma requires expertise and is a labour-intensive process. If detected on time, the mortality rate can be reduced. With the advent of new technologies, automatic detection systems are used to analyse and classify images obtained from different sources. Here, we propose an automatic detection system Integrated Features-Feature Selection Model for Classification (IF-FSM-C) that detect osteosarcoma from the high-resolution whole slide images (WSIs). The novelty of the proposed approach is the use of integrated features obtained by fusion of features extracted using traditional handcrafted feature extraction techniques and deep learning models. It is quite possible that the integrated features may contain some redundant and irrelevant features which may unnecessarily increases the computation time and leads to wastage of resources. To avoid this, we perform feature selection (FS) before giving the integrated features to the classifier. To perform feature selection, we propose two binary variants of recently proposed Arithmetic Optimization Algorithm (AOA) known as BAOA-S and BAOA-V. The selected features are given to a classifier that classifies the WSIs into Viable tumor (VT), Non-viable tumor (NVT) and non-tumor (NT). Experiments are performed and the results prove the superiority of the proposed IF-FSM-C that uses integrated features and feature selection in classifying WSIs as compared to the classifiers which use handcrafted or deep learning features alone as well as state-of-the-art methods for osteosarcoma detection.

show abstract

Early diagnosis of gastric cancer based on deep learning combined with the spectral-spatial classification method

Cited by 29 publications

References 39 publications

Nondestructive Detection for Egg Freshness Based on Hyperspectral Scattering Image Combined with Ensemble Learning

Nondestructive Detection for Egg Freshness Based on Hyperspectral Scattering Image Combined with Ensemble Learning

Nondestructive Detection for Egg Freshness based on Hyperspectral Scattering Image combined with Ensemble Learning

Automatic Detection of Osteosarcoma Based on Integrated Features and Feature Selection Using Binary Arithmetic Optimization Algorithm

Contact Info

Product

Resources

About