Computational Intelligence in Cancer Diagnosis Progress and Challenges

• Main Authors: Nayak, Janmenjoy, Pelusi, Danilo, Naik, Bighnaraj, Mishra, Manohar, Muhammad, Khan, Al-Dabass, David
• Format: eBook
• Language: English
• Published: Chantilly Elsevier Science & Technology 2023; Academic Press
• Edition: 1
• Subjects: Cancer; Computational intelligence
• ISBN: 9780323852401; 0323852408
• DOI: 10.1016/C2020-0-02257-7

Computational Intelligence in Cancer Diagnosis: Progress and Challenges provides insights into the current strength and weaknesses of different applications and research findings on computational intelligence in cancer research.

Table of Contents:

• 3D CNN -- Neural network for detection of lung nodules -- Target detection based on deep learning -- Detection of lung cancer based on 2D convolutional neural network -- Lung cancer detection based on 3D convolutional neural network -- Application of neural network to medical image segmentation in diagnosis of lung cancer -- FCN -- U-Net -- GAN -- Neural network for classification of lung cancer diagnosis -- Use logistic regression analysis to classify benign and malignant -- Lung cancer pathological image classification based on a CNN -- Classification of lung nodules based on a 3D dense convolutional neural network -- Classification of lung nodules based on different feature extraction -- Conclusion and future directions -- Conclusion -- Challenges and opportunities in the clinical research of lung cancer -- References -- Chapter 6: Machine learning for thyroid cancer diagnosis -- Introduction -- Literature survey -- Thyroid cancer detection by ultrasound imaging and machine learning/deep learning -- Machine learning/deep learning based thyroid cancer prediction using cytopathology whole-slide images and histopathology images -- Thyroid gland disorders and machine learning approaches -- Methods -- Linear Discriminant Analysis -- Principal Component Analysis -- K-Nearest Neighbor -- Decision Tree -- Random Forest -- Support Vector Machine -- Multilayer Neural Network -- Probabilistic Neural Network -- Performance evaluation metrics -- Autoencoders -- Convolutional Neural Networks -- Convolutional layer -- Pooling layer -- Fully-connected layer -- Long short-term memory network -- Results -- Conclusion -- References -- Part 2: Prediction of cancer susceptibility -- Chapter 7: Machine learning-based detection and classification of lung cancer -- Introduction -- Related work -- Problem definition -- Proposed methodology -- Overview -- Dataset
• Chapter 12: Convolutional neural networks and stacked generalization ensemble method in breast cancer prognosis
• Deep learning techniques -- Interpretability and visualization -- Software used -- Critical analysis -- Conclusion -- References -- Further reading -- Chapter 3: Integrative data analysis and automated deep learning technique for ovary cancer detection -- Introduction -- Related work -- Methodology -- Proposed methodology -- CNN architecture -- Input layer -- Convolutional layer -- Activation function -- Pooling -- Fully connected layer -- Overall process of the proposed framework -- Result analysis -- Conclusion -- References -- Chapter 4: Learning from multiple modalities of imaging data for cancer diagnosis -- Introduction -- Diagnosis in CT -- Imaging characteristics of CT -- Diagnosis of cancer in CT -- Liver cancer detection based on CT -- Lung cancer detection based on CT -- Diagnosis in MRI -- Imaging characteristics of MRI -- Diagnosis of cancer in MRI -- Breast cancer detection based on MRI -- Brain tumor detection based on MRI -- Gastric cancer detection based on MRI -- Diagnosis in X-ray -- Imaging characteristics of X -ray -- Diagnosis of cancer in X -ray -- Breast cancer detection based on X -ray -- Lung cancer detection based on X -ray -- Diagnosis in UI -- Imaging characteristics of UI -- Diagnosis of cancer in UI -- Breast cancer detection based on UI -- Liver cancer detection based on UI -- Diagnosis in PET -- Imaging characteristics of PET -- Diagnosis of cancer in PET -- Lymph cancer detection based on PET -CT -- Thyroid cancer detection based on PET -CT -- Lung cancer detection based on PET -- Medical imaging and artificial intelligence -- Conclusion -- Future directions -- Critical analysis -- References -- Chapter 5: Neural network for lung cancer diagnosis -- Introduction -- The basics knowledge of neural network -- The structure of the neural network -- Feedforward neural network -- Feedback neural network -- CNN -- 2D CNN
• Dataset preparation -- Simulation environment -- Performance measures -- Accuracy -- True positive rate (TPR) -- False positive rate (FPR) -- True negative rate (TNR) -- Precision -- F1-score -- AUC -- Result analysis -- Conclusion -- References -- Chapter 10: Effect of COVID-19 on cancer patients: Issues and future challenges -- Introduction -- Effect of COVID-19 on various types of cancer -- Impact of COVID-19 on lung cancer -- Impact of COVID-19 on colorectal cancer -- Impact of COVID-19 on breast cancer -- Impact of COVID-19 on head and neck cancer -- Impact of COVID-19 on thyroid cancer -- Scenario of the impact of COVID-19 on cancer patients in various countries -- Case study 1: Assessment of mortality rate of COVID-19 in cancer patients of the United Kingdom undergoing chemotherapy or ... -- Case study 2: Assessment of the clinical impact of COVID-19 infection on cancer patients -- Case study 3: Investigating the risk of COVID-19 in cancer patients in the United Kingdom based on the tumor subtype and pa ... -- Major challenges of oncology community and cancer patients during the COVID-19 pandemic -- Healthcare practitioners -- Patients -- Health systems -- Discussion and future directions -- Telemedicine -- Enhancement of cancer screening through social media campaigns -- Conclusion -- References -- Chapter 11: Empirical wavelet transform-based fast deep convolutional neural network for detection and classification of me -- Introduction -- Dataset -- Continuous wavelet transform (CWT) -- Discrete wavelet transform (DWT) -- Empirical wavelet transform (EWT) -- Fast deep convolutional neural network (fast-DCNN) -- Convolutional layer -- Rectified liner unit (ReLU) layer -- Pooling layer -- Fully connected layer -- Softmax layer -- Result and discussion -- Conclusion -- References -- Part 3: Advance computational intelligence paradigms
• Intro -- Computational Intelligence in Cancer Diagnosis: Progress and Challenges -- Copyright -- Contents -- Contributors -- About the editors -- Foreword -- Preface -- Part 1: Introduction to computational intelligence approaches -- Part 2: Prediction of cancer susceptibility -- Part 3: Advance computational intelligence paradigms -- Part 1: Introduction to computational intelligence approaches -- Chapter 1: The roadmap to the adoption of computational intelligence in cancer diagnosis: The clinical-radiological -- Introduction -- Radiomics and artificial intelligence for cancer diagnosis and treatment -- Challenges and perspectives -- Conclusion -- References -- Chapter 2: Deep learning approaches for high dimension cancer microarray data feature prediction: A review -- Introduction -- Background -- Microarray data -- Microarray technology -- Microarray gene expression profile -- Microarray dataset -- Microarray feature selection technique -- Filter method -- Wrapper method -- Embedded method -- Hybrid method -- Ensemble method -- Microarray feature extraction techniques -- Correlation-based feature selection (CFS) -- Fast correlation-based filter (FCBF) -- INTERACT -- Information gain -- ReliefF -- Minimum redundancy maximum relevance (mRMR) -- Machine learning -- Introduction -- Principal component analysis (PCA) -- Independent component analysis (ICA) -- Partial least squares (PLS) -- Local linear embedding (LLE) -- Related work -- The effectiveness of feature selection -- Feature selection from the leukemia dataset -- Leukemia dataset result analysis -- Disadvantage -- Deep learning -- Introduction -- Related work -- Advantage of DL over ML -- Critical analysis: Challenges and future trends -- Microarray data analysis: Challenges -- Microarray data analysis: Future trends -- Number of samples -- Feature selection methods
• Preprocessing -- Gabor filter -- Gaussian filter -- Hessian filter -- Laplace filter -- Median filter -- Sobel operator -- Feature extraction -- LBP -- HOG -- SIFT -- Morphological gradient -- Statistical features -- Mean -- Median -- Variance -- Standard deviation -- Range -- Skewness -- Kurtosis -- Feature selection -- Principal component analysis (PCA) -- SelectKBest -- Recursive feature elimination (RFE) -- Classification -- Support vector machine (SVM) -- K-nearest neighbor (KNN) -- XGBoost -- Multilayer perceptron (MLP) -- Logistic regression -- ExtraTrees -- Decision tree -- Gaussian Naive Bayes -- Linear discriminant analysis (LDA) -- Extreme learning machine (ELM) -- Result analysis and discussion -- Nodule detection -- Nodule classification -- Confusion matrices for nodule detection and classification -- Performance of the nodule detection and classification task using various evaluation metrics -- Performance comparison of the proposed method with other CAD systems -- Conclusion -- References -- Chapter 8: Deep learning techniques for oral cancer diagnosis -- Introduction -- Deep neural networks (DNNs) -- Convolution neural networks (CNNs) -- 3D convolution neural networks (3D CNNs) -- CNN-based methods for oral cancer diagnosis -- Results and discussion -- Current challenges and future research direction -- Lack of oral cancer staging/classification methods -- Lack of common large-scale datasets for oral cancer diagnosis -- Active and incremental learning for newly added samples and classes -- Use of explainable artificial intelligence (XAI) for understanding data -- Conclusion -- Acknowledgment -- References -- Chapter 9: An intelligent deep learning approach for colon cancer diagnosis -- Introduction -- Literature study -- Materials and methods -- Deep neural network -- Genetic algorithm -- Proposed method -- Experimental setup