A Novel Fusion Approach for Early Lung Cancer Detection Using Computer Aided Diagnosis Techniques

Fernandes, Steven Lawrence; Gurupur, Varadraj P.; Lin, Hong; Martis, Roshan Joy

doi:10.1166/jmihi.2017.2280

Cited by 39 publications

(12 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The research work is motivated by the Content Supported Medical Image Retrieval (CSMIR) proposed by Fernandes et al [42]. Their approach was able to analyze the tumor or lesion from 2D and 3D radiology images.…”

Section: Motivationmentioning

confidence: 99%

Deep-learning framework to detect lung abnormality – A study with chest X-Ray and lung CT scan images

Bhandary¹,

Prabhu

Rajinikanth

et al. 2020

Pattern Recognition Letters

349

150

View full text Add to dashboard Cite

Lung abnormalities are highly risky conditions in humans. The early diagnosis of lung abnormalities is essential to reduce the risk by enabling quick and efficient treatment. This research work aims to propose a Deep-Learning (DL) framework to examine lung pneumonia and the cancer. This work proposes two different DL practices to evaluate the considered problem: (i) The initial DL method, named a modified AlexNet (MAN), is implemented to classify chest X-Ray images into normal and pneumonia class. In the MAN, the classification is implemented using with Support Vector Machine (SVM), and its performance is compared against Softmax. Further, its performance is validated with other pre-trained DL techniques, such as AlexNet, VGG16, VGG19 and ResNet50. (ii) The second DL work implements a fusion of handcrafted and learned features in the MAN to improve the classification accuracy during lung cancer assessment. This work employs serial fusion and Principal Component Analysis (PCA) based features selection to enhance the feature vector. The performance of this DL structure is tested by the benchmark lung cancer CT images of LIDC-IDRI and superior classification accuracy of >97.27% is achieved.

show abstract

Section: Motivationmentioning

confidence: 99%

Deep-learning framework to detect lung abnormality – A study with chest X-Ray and lung CT scan images

Bhandary¹,

Prabhu

Rajinikanth

et al. 2020

Pattern Recognition Letters

349

150

View full text Add to dashboard Cite

show abstract

“…The classification accuracy of this method was 99.86%, and the classification accuracy rate was the highest among all methods, which is close to all accurate classifications, which fully verifies that the proposed method can improve the accuracy of image classification and has better stability and robustness. This is mainly because the method proposed in this paper compared the method proposed in [43][44][45][46][47], and not only introduced the visual aid mechanism to the deep learning model but also improved the network structure and loss function in the deep learning model. Through the optimization and improvement of the two, the modeling ability and nonlinear classification ability of the deep learning model improved, and the highest classification effect was achieved.…”

Section: Example Analysismentioning

confidence: 99%

Medical Image Classification Algorithm Based on Visual Attention Mechanism‐MCNN

2021

Oxidative Medicine and Cellular Longevity

View full text Add to dashboard Cite

Due to the complexity of medical images, traditional medical image classification methods have been unable to meet the actual application needs. In recent years, the rapid development of deep learning theory has provided a technical approach for solving medical image classification. However, deep learning has the following problems in the application of medical image classification. First, it is impossible to construct a deep learning model with excellent performance according to the characteristics of medical images. Second, the current deep learning network structure and training strategies are less adaptable to medical images. Therefore, this paper first introduces the visual attention mechanism into the deep learning model so that the information can be extracted more effectively according to the problem of medical images, and the reasoning is realized at a finer granularity. It can increase the interpretability of the model. Additionally, to solve the problem of matching the deep learning network structure and training strategy to medical images, this paper will construct a novel multiscale convolutional neural network model that can automatically extract high-level discriminative appearance features from the original image, and the loss function uses the Mahalanobis distance optimization model to obtain a better training strategy, which can improve the robust performance of the network model. The medical image classification task is completed by the above method. Based on the above ideas, this paper proposes a medical classification algorithm based on a visual attention mechanism-multiscale convolutional neural network. The lung nodules and breast cancer images were classified by the method in this paper. The experimental results show that the accuracy of medical image classification in this paper is not only higher than that of traditional machine learning methods but also improved compared with other deep learning methods, and the method has good stability and robustness.

show abstract

“…Such an approach improves uncertainty of the sequence generated since it integrates both good statistical properties of Pseudo Random Number Generator based on an Elliptic Curve and Pseudo Random Number Generator based on chaotic map. [20][21][22][23][24][25][26][27][28][29][30][31][32][33][34][35][36][37][38][39] This work proposes a new Pseudo Random Number Generator. In this scheme, double rounds of diffusion and substitution operations are performed.…”

Section: Literature Survey On Pseudo Random Number Generatormentioning

confidence: 99%

Generation of pseudo random number sequence from discrete oscillating samples of equally spread objects and application for stream cipher system

Sudeepa¹,

Aithal

2019

Concurrency and Computation

View full text Add to dashboard Cite

The demand on security privileged information has widely increased due to the sensitivity of the exchanged information over public communication channels. Nowadays, almost all organizations, mainly, business, financial, and government related areas, and also other regions are computerized, and sometimes, the data will be highly confidential. Since some areas dealing with confidential data, it is very much essential to provide the security for the data to avoid unauthorized access. Multimedia data security and security related issues have attracted many researchers towards it. Cryptography is necessary to protect the confidential information transmitting over the network. The strength of the cryptographic system, especially, stream cipher, is not only depending upon its encryption/decryption algorithm but also depends upon the randomness properties of the key sequence such as length, uniformity, independence, etc. In this work, a novel method of generating the pseudo random number that is based on the discrete equally spread oscillating points viewed orthogonally as an envelope has been considered for the generation. Depending on the number of samples, it is possible to get the higher length of the sequence. The random patterns generated by the discrete points of a moving wave are used to generate non binary random numbers. These numbers are used as key in stream cipher system. These are having greater advantages like one time padding to achieve perfect security in cryptographic application. The same non binary key sequence generated is applied for the cryptographic application, and the security parameters of the result obtained from cryptographic applications are also evaluated to observe the strength of security level. KEYWORDS discrete oscillating samples, Pseudo Random Number Generator, stream cipher system INTRODUCTIONData can be hacked during transmission through network channel. Hence, it is very essential to be transmitted in a secured manner. Cryptography is one of the major techniques to ensure security of data. Cryptography is a technique of transforming an original data into a particular form so that only those who know the key can read and process it. In cryptosystem, original message or data referred to as plain text. This could be transformed into non readable or scrambled form referred to as cipher text. This is done based on encryption algorithm. The encryption algorithm uses a key for changing the plain text into a cipher text. The cipher text can be recovered into its original form by an algorithm using a key known as decryption. The main goal of cryptography is data privacy (confidentiality), data authenticity, and data integrity (it cannot be modified in any way) in the digital world. Based on the type of key used for encryption/decryption, cryptography systems are categorized as symmetric key system and asymmetric key system. 1 The symmetric system can be categorized as stream and block cipher.Concurrency Computat Pract Exper. 2020;32:e5181. wileyonlinelibrary.com/journal/cpe Decryption Algor...

show abstract

A Novel Fusion Approach for Early Lung Cancer Detection Using Computer Aided Diagnosis Techniques

Cited by 39 publications

References 0 publications

Deep-learning framework to detect lung abnormality – A study with chest X-Ray and lung CT scan images

Deep-learning framework to detect lung abnormality – A study with chest X-Ray and lung CT scan images

Medical Image Classification Algorithm Based on Visual Attention Mechanism‐MCNN

Generation of pseudo random number sequence from discrete oscillating samples of equally spread objects and application for stream cipher system

Contact Info

Product

Resources

About