scholarly journals Research on the classification of lymphoma pathological images based on deep residual neural network

2021 ◽  
Vol 29 ◽  
pp. 335-344
Author(s):  
Xiaoli Zhang ◽  
Kuixing Zhang ◽  
Mei Jiang ◽  
Lin Yang
Keyword(s):  
Neural Network ◽  
Experimental Data ◽  
Network Model ◽  
Bp Neural Network ◽  
Classification Accuracy ◽  
Data Set ◽  
Color Transformation ◽  
Objective Basis ◽  
Time And Energy

BACKGROUND: Malignant lymphoma is a type of tumor that originated from the lymphohematopoietic system, with complex etiology, diverse pathological morphology, and classification. It takes a lot of time and energy for doctors to accurately determine the type of lymphoma by observing pathological images. OBJECTIVE: At present, an automatic classification technology is urgently needed to assist doctors in analyzing the type of lymphoma. METHODS: In this paper, by comparing the training results of the BP neural network and BP neural network optimized by genetic algorithm (GA-BP), adopts a deep residual neural network model (ResNet-50), with 374 lymphoma pathology images as the experimental data set. After preprocessing the dataset by image flipping, color transformation, and other data enhancement methods, the data set is input into the ResNet-50 network model, and finally classified by the softmax layer. RESULTS: The training results showed that the classification accuracy was 98.63%. By comparing the classification effect of GA-BP and BP neural network, the accuracy of the network model proposed in this paper is improved. CONCLUSIONS: The network model can provide an objective basis for doctors to diagnose lymphoma types.

scholarly journals Clinicopathological features of fibrosarcomatous dermatofibrosarcoma protuberans and the construction of a back-propagation neural network recognition model

2021 ◽  
Vol 16 (1) ◽  
Author(s):  
Yanan Li ◽  
Jiaqi Liang ◽  
Xuewen Xu ◽  
Xian Jiang ◽  
Chuan Wang ◽  
...  
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Bp Neural Network ◽  
Classification Accuracy ◽  
Back Propagation ◽  
Dermatofibrosarcoma Protuberans ◽  
Clinicopathological Features ◽  
Recognition Model ◽  
Bp Neural Network Model

Abstract Background Fibrosarcomatous dermatofibrosarcoma protuberans (FS-DFSP) is a form of tumor progression of dermatofibrosarcoma protuberans (DFSP) with an increased risk of metastasis and recurrence. Few studies have compared the clinicopathological features of FS-DFSP and conventional DFSP (C-DFSP). Objectives To better understand the epidemiological and clinicopathological characteristics of FS-DFSP. Methods We conducted a cohort study of 221 patients diagnosed with DFSP and built a recognition model with a back-propagation (BP) neural network for FS-DFSP. Results Twenty-six patients with FS-DFSP and 195 patients with C-DFSP were included. There were no differences between FS-DFSP and C-DFSP regarding age at presentation, age at diagnosis, sex, size at diagnosis, size at presentation, and tumor growth. The negative ratio of CD34 in FS-DFSP (11.5%) was significantly lower than that in C-DFSP (5.1%) (P = 0.005). The average Ki-67 index of FS-DFSP (18.1%) cases was significantly higher than that of C-DFSP (8.1%) cases (P < 0.001). The classification accuracy of the BP neural network model training samples was 100%. The correct rates of classification and misdiagnosis were 84.1% and 15.9%. Conclusions The clinical manifestations of FS-DFSP and C-DFSP are similar but have large differences in immunohistochemistry. The classification accuracy and feasibility of the BP neural network model are high in FS-DFSP.

Research of Orange Quality Classification Technology Based on BP Neural Network Algorithm

2015 ◽  
Vol 713-715 ◽  
pp. 1821-1824
Author(s):  
Chun Hua Qian ◽  
He Qun Qiang ◽  
Sheng Rong Gong
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
Classification Accuracy ◽  
Bp Algorithm ◽  
Shape Features ◽  
Accuracy Rate ◽  
Network Algorithm ◽  
Quality Classification ◽  
Neural Network Algorithm

BP algorithm is a classical neural network algorithm. We analyzed the deficiency of traditional BP neural network algorithm, designed new S function and momentum method strategy, optimized the algorithm parameters. We use the new algorithm in the classification of orange images, take color and shape features as input value, the experimental results proved that our algorithm is faster and the classification accuracy rate reaches to 90%

scholarly journals Clinicopathological Features of Fibrosarcomatous Dermatofibrosarcoma Protuberans and the Construction of a Back-Propagation Neural Network Recognition Model

2020 ◽  
Author(s):  
Yanan Li ◽  
Jiaqi Liang ◽  
Xuewen Xu ◽  
Xian Jiang ◽  
Chuan Wang ◽  
...  
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Bp Neural Network ◽  
Classification Accuracy ◽  
Back Propagation ◽  
Dermatofibrosarcoma Protuberans ◽  
Clinicopathological Features ◽  
Recognition Model ◽  
Bp Neural Network Model

Abstract BackgroundFibrosarcomatous dermatofibrosarcoma protuberans (FS-DFSP) is a form of tumor progression of dermatofibrosarcoma protuberans (DFSP) with an increased risk of metastasis and recurrence. Few studies have compared the clinicopathological features of FS-DFSP and conventional DFSP (C-DFSP).ObjectivesTo better understand the epidemiological and clinicopathological characteristics of FS-DFSP.MethodsWe conducted a cohort study of 221 patients diagnosed with DFSP and built a recognition model with a back-propagation (BP) neural network for FS-DFSP.ResultsTwenty-six patients with FS-DFSP and 195 patients with C-DFSP were included. There were no differences between FS-DFSP and C-DFSP regarding age at presentation, age at diagnosis, sex, size at diagnosis, size at presentation, and the size interval. The negative ratio of CD34 in FS-DFSP (11.5%) was significantly lower than that in C-DFSP (5.1%) (P=0.005). The average Ki-67 index of FS-DFSP (18.1%) cases was significantly higher than that of C-DFSP (8.1%) cases (P<0.001). The classification accuracy of the BP neural network model training samples was 100%. The correct rates of classification and misdiagnosis were 84.1% and 15.9%.ConclusionsThe clinical manifestations of FS-DFSP and C-DFSP are similar but have large differences in immunohistochemistry. The classification accuracy and feasibility of the BP neural network model are high in FS-DFSP.

Estimating nitrogen contents of apple leaves based on hyperspectral parameter models at different phenophases

2016 ◽  
Vol 6 (2) ◽  
pp. 942-952
Author(s):  
Xicun ZHU ◽  
Zhuoyuan WANG ◽  
Lulu GAO ◽  
Gengxing ZHAO ◽  
Ling WANG
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Bp Neural Network ◽  
Shoot Growth ◽  
Hyperspectral Data ◽  
Estimation Model ◽  
Apple Leaves ◽  
Bp Neural Network Model ◽  
Nitrogen Contents

The objective of the paper is to explore the best phenophase for estimating the nitrogen contents of apple leaves, to establish the best estimation model of the hyperspectral data at different phenophases. It is to improve the apple trees precise fertilization and production management. The experiments were done in 20 orchards in the field, measured hyperspectral data and nitrogen contents of apple leaves at three phenophases in two years, which were shoot growth phenophase, spring shoots pause growth phenophase, autumn shoots pause growth phenophase. The study analyzed the nitrogen contents of apple leaves with its original spectral and first derivative, screened sensitive wavelengths of each phenophase. The hyperspectral parameters were built with the sensitive wavelengths. Multiple stepwise regressions, partial least squares and BP neural network model were adopted in the study. The results showed that 551 nm, 716 nm, 530 nm, 703 nm; 543 nm, 705 nm, 699 nm, 756 nm and 545 nm, 702 nm, 695 nm, 746 nm were sensitive wavelengths of three phenophases. R551+R716, R551*R716, FDR530+FDR703, FDR530*FDR703; R543+R705, R543*R705, FDR699+FDR756, FDR699*FDR756and R545+R702, R545*R702, FDR695+FDR746, FDR695*FDR746 were the best hyperspectral parameters of each phenophase. Of all the estimation models, the estimated effect of shoot growth phenophase was better than other two phenophases, so shoot growth phenophase was the best phenophase to estimate the nitrogen contents of apple leaves based on hyperspectral models. In the three models, the 4-3-1 BP neural network model of shoot growth phenophase was the best estimation model. The R2 of estimated value and measured value was 0.6307, RE% was 23.37, RMSE was 0.6274.

scholarly journals Regional logistics demand forecasting: a BP neural network approach

2021 ◽  
Author(s):  
Lijuan Huang ◽  
Guojie Xie ◽  
Wende Zhao ◽  
Yan Gu ◽  
Yi Huang
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Bp Neural Network ◽  
Demand Forecasting ◽  
Indicator System ◽  
Regional Logistics ◽  
Logistics Enterprises ◽  
Logistics Demand ◽  
Bp Neural Network Model

AbstractWith the rapid development of e-commerce, the backlog of distribution orders, insufficient logistics capacity and other issues are becoming more and more serious. It is very significant for e-commerce platforms and logistics enterprises to clarify the demand of logistics. To meet this need, a forecasting indicator system of Guangdong logistics demand was constructed from the perspective of e-commerce. The GM (1, 1) model and Back Propagation (BP) neural network model were used to simulate and forecast the logistics demand of Guangdong province from 2000 to 2019. The results show that the Guangdong logistics demand forecasting indicator system has good applicability. Compared with the GM (1, 1) model, the BP neural network model has smaller prediction error and more stable prediction results. Based on the results of the study, it is the recommendation of the authors that e-commerce platforms and logistics enterprises should pay attention to the prediction of regional logistics demand, choose scientific forecasting methods, and encourage the implementation of new distribution modes.

scholarly journals ResCaps: an improved capsule network and its application in ultrasonic image classification of thyroid papillary carcinoma

2021 ◽  
Author(s):  
Xiongzhi Ai ◽  
Jiawei Zhuang ◽  
Yonghua Wang ◽  
Pin Wan ◽  
Yu Fu
Keyword(s):  
Papillary Carcinoma ◽  
Network Model ◽  
Reliability And Validity ◽  
Thyroid Papillary Carcinoma ◽  
Data Set ◽  
Ultrasonic Image ◽  
First Choice ◽  
Thyroid Papillary ◽  
Ultrasonic Images

AbstractUltrasonic image examination is the first choice for the diagnosis of thyroid papillary carcinoma. However, there are some problems in the ultrasonic image of thyroid papillary carcinoma, such as poor definition, tissue overlap and low resolution, which make the ultrasonic image difficult to be diagnosed. Capsule network (CapsNet) can effectively address tissue overlap and other problems. This paper investigates a new network model based on capsule network, which is named as ResCaps network. ResCaps network uses residual modules and enhances the abstract expression of the model. The experimental results reveal that the characteristic classification accuracy of ResCaps3 network model for self-made data set of thyroid papillary carcinoma was $$81.06\%$$ 81.06 % . Furthermore, Fashion-MNIST data set is also tested to show the reliability and validity of ResCaps network model. Notably, the ResCaps network model not only improves the accuracy of CapsNet significantly, but also provides an effective method for the classification of lesion characteristics of thyroid papillary carcinoma ultrasonic images.

scholarly journals Vibration-based classification of road damages: gyroscope data and a simple neural network model

2018 ◽  
Vol 195 ◽  
pp. 012068
Author(s):  
Fergyanto E. Gunawan ◽  
Herriyandi ◽  
Benfano Soewito ◽  
Tuga Mauritsius ◽  
Nico Surantha
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Simple Neural Network

scholarly journals RISC-V Virtual Platform-Based Convolutional Neural Network Accelerator Implemented in SystemC

Electronics ◽  
2021 ◽  
Vol 10 (13) ◽  
pp. 1514
Author(s):  
Seung-Ho Lim ◽  
WoonSik William Suh ◽  
Jin-Young Kim ◽  
Sang-Young Cho
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Network Model ◽  
Neural Network Model ◽  
Deep Neural Network ◽  
System Level ◽  
Neural Network Models ◽  
Data Set ◽  
Embedded Device ◽  
Virtual Platform

The optimization for hardware processor and system for performing deep learning operations such as Convolutional Neural Networks (CNN) in resource limited embedded devices are recent active research area. In order to perform an optimized deep neural network model using the limited computational unit and memory of an embedded device, it is necessary to quickly apply various configurations of hardware modules to various deep neural network models and find the optimal combination. The Electronic System Level (ESL) Simulator based on SystemC is very useful for rapid hardware modeling and verification. In this paper, we designed and implemented a Deep Learning Accelerator (DLA) that performs Deep Neural Network (DNN) operation based on the RISC-V Virtual Platform implemented in SystemC in order to enable rapid and diverse analysis of deep learning operations in an embedded device based on the RISC-V processor, which is a recently emerging embedded processor. The developed RISC-V based DLA prototype can analyze the hardware requirements according to the CNN data set through the configuration of the CNN DLA architecture, and it is possible to run RISC-V compiled software on the platform, can perform a real neural network model like Darknet. We performed the Darknet CNN model on the developed DLA prototype, and confirmed that computational overhead and inference errors can be analyzed with the DLA prototype developed by analyzing the DLA architecture for various data sets.

Sign in / Sign up

Export Citation Format

Share Document