Artificial Intelligence in Cancer Diagnosis and Prognosis

Description

PRELIMS.pdf Preface Acknowledgements Editor biographies Ayman El-Baz Jasjit S Suri List of contributors CH001.pdf Chapter 1 American Joint Committee on Cancer staging of lung and renal cancers using a recurrent deep neural network model 1.1 Introduction 1.2 Background 1.2.1 Lung cancer 1.2.2 Renal cancer 1.2.3 Research scope 1.3 Methodology 1.3.1 AJCC staging 1.3.2 Database 1.3.3 The deep learning model 1.4 The experiment 1.5 Results and discussion 1.6 Conclusions References CH002.pdf Chapter 2 Neural-ensemble-based detection: a modern way to diagnose lung cancer 2.1 Introduction 2.1.1 Lung cancer epidemiology 2.1.2 Signs and symptoms of lung cancer 2.1.3 Staging of lung cancer 2.1.4 Classification of lung cancer 2.2 Different methods of lung cancer detection 2.2.1 Invasive methods 2.2.2 Non-invasive methods 2.3 Neural-ensemble-based detection 2.4 Conclusions References and further reading CH003.pdf Chapter 3 Computed tomography and magnetic resonance imaging machine learning applications for renal cell carcinoma 3.1 Background 3.2 Applications 3.2.1 Malignant versus benign discrimination 3.2.2 Malignancy subtyping 3.2.3 Biologic aggressiveness 3.2.4 Correlation with overall and progression-free survival under treatment 3.2.5 Prediction of perioperative complications 3.3 Conclusions References CH004.pdf Chapter 4 Pulmonary nodule-based feature learning for automated lung tumor grading using convolutional neural networks 4.1 Introduction 4.2 Literature review 4.2.1 Preprocessing 4.2.2 Candidate nodule segmentation 4.2.3 Feature extraction and classification 4.3 Methodology 4.3.1 Data acquisition 4.3.2 Preprocessing 4.3.3 NROI segmentation 4.3.4 GAN 4.3.5 Feature extraction 4.3.6 Classification 4.4 Results and discussion 4.5 Conclusions References CH005.pdf Chapter 5 Detection of lung contours using closed principal curves and machine learning 5.1 Introduction 5.2 Materials and methods 5.2.1 Principal curve 5.2.2 Machine learning 5.2.3 Proposed algorithm 5.2.4 Quantitative evaluation 5.3 Results and discussion 5.3.1 Detecting contours in the private dataset using different learning rates 5.3.2 Detecting contours in the private dataset using different numbers of neurons in the hidden layer 5.3.3 Detecting contours in the private dataset using different numbers of epochs 5.3.4 Detecting contours in the private dataset using different algorithms 5.3.5 Detecting contours in the public LIDC–IDRI dataset using different algorithms 5.4 Conclusions Acknowledgments References CH006.pdf Chapter 6 Bytes, pixels, and bases: machine learning in imaging–omics for renal cell carcinoma 6.1 Introduction 6.1.1 The convergence of computers and cancer care 6.2 Imaging in renal cell carcinoma 6.2.1 Radiology 6.2.2 Pathology 6.3 Omics in renal cell carcinoma 6.3.1 Multiomics 6.4 Imaging–omics for kidney carcinoma 6.4.1 Radiomics 6.4.2 Pathomics 6.5 Opportunities and obstacles 6.5.1 Data 6.5.2 Interpretability 6.5.3 Privacy 6.5.4 Adversarial attacks 6.5.5 Regulatory roadblocks 6.6 Future directions 6.7 Conclusions References CH007.pdf Chapter 7 Detection, growth quantification, and malignancy prediction of pulmonary nodules using deep convolutional networks in follow-up CT scans 7.1 Introduction 7.2 Background 7.2.1 Nodule detection 7.2.2 Nodule quantification 7.2.3 Lung cancer prediction 7.3 Temporal lung nodule assessment 7.3.1 Preprocessing 7.3.2 Nodule detection 7.3.3 Nodule reidentification 7.3.4 Nodule growth quantification 7.3.5 Nodule malignancy classification 7.4 Data cohort 7.4.1 Scanners and protocols 7.4.2 Data 7.5 Results 7.5.1 Nodule detection 7.5.2 Nodule reidentification 7.5.3 Nodule growth quantification 7.5.4 Nodule malignancy classification 7.6 Discussion 7.7 Conclusions References and further reading CH008.pdf Chapter 8 Training a deep multiview model using small samples of medical data 8.1 Introduction 8.2 Related work 8.2.1 Cox proportional hazard model 8.2.2 Deep survival models 8.3 Methodology 8.3.1 Training the deep multiview model on small numbers of data samples 8.3.2 Training the network using a divide-and-conquer strategy 8.3.3 Training the model as a multitask model (MM) 8.4 Experiments and discussion 8.4.1 Data set descriptions 8.4.2 Data preprocessing 8.4.3 Experimental setup 8.4.4 Results 8.4.5 Discussion 8.5 Conclusions References CH009.pdf Chapter 9 Overview of deep learning for lung cancer diagnosis 9.1 Introduction 9.2 Deep learning 9.2.1 Convolutional neural networks 9.2.2 Transfer learning models 9.2.3 The U-Net 9.3 Evaluation criteria 9.3.1 Evaluation metrics used in classification applications 9.3.2 Evaluation metrics used in segmentation applications 9.4 Datasets 9.4.1 The LIDC–IDRI data set 9.4.2 The LungCT-Diagnosis data set 9.4.3 The NSCLC-Radiomics data set 9.5 Overview of recent research 9.6 Discussion 9.7 Conclusions References CH010.pdf Chapter 10 Artificial intelligence for cancer diagnosis 10.1 Introduction 10.2 Background of cancer 10.3 The basics of artificial intelligence 10.4 AI impacts on cancer-based clinical analysis 10.5 Visualization tools for AI-assisted cancer recognition systems 10.6 Multi-platform deployment for cancer prognosis systems 10.7 Case studies of cancer recognition systems that use artificial intelligence techniques 10.8 Conclusions References and further reading CH011.pdf Chapter 11 Lung cancer diagnosis using 3D-CNN and spherical harmonics expansions 11.1 Introduction 11.2 Methodology 11.2.1 Feature extraction utilizing convolutional neural networks 11.2.2 Explanation of feature extraction utilizing spherical harmonics 11.3 Results 11.3.1 Experimental setup 11.3.2 Experimental evaluation 11.4 Conclusions References