Foreword xxi
Preface xxiii
1 Assessing Predictive Accuracy: Model Validation in Cancer Diagnostics 1
M. Sudha, Arun Elias, G. Gurumoorthy, S. Rajalakshmi and S. K. Muthusundar
1.1 Introduction 2
1.1.1 Conventional Cancer Diagnosis 3
1.1.2 Machine Learning in Cancer Diagnosis 3
1.1.3 Types of Cancer in Focus 4
1.1.3.1 Breast Cancer 4
1.1.3.2 Lung Cancer 4
1.1.3.3 Skin Cancer 4
1.1.4 Objectives of Study 4
1.1.5 Study Scope 5
1.1.6 Performance Metrics 6
1.1.7 Limitations and Future Directions 6
1.2 Literature Review 7
1.3 Methodology 9
1.3.1 Data Acquisition 9
1.3.2 Data Preprocessing 10
1.3.2.1 Dealing with Missing Data 10
1.3.2.2 Normalization and Standardization 10
1.3.2.3 Feature Selection and Dimensionality Reduction 11
1.3.3 Machine Learning Models 11
1.3.3.1 Support Vector Machine (SVM) 11
1.3.3.2 Random Forest (RF) 12
1.3.3.3 k-Nearest Neighbors (k-NN) 12
1.3.3.4 Logistic Regression (LR) 12
1.3.3.5 Hyperparameter Tuning 13
1.3.4 Performance Metrics 13
1.4 Analysis of Results 14
1.4.1 The Overall Performance of Each Model on the Breast Cancer Dataset 14
1.4.2 Models’ Performance for Lung Cancer Dataset 16
1.4.3 Model Performance on Skin Cancer Dataset 17
1.4.4 Analysis of Inter-Cancer Type Performance Comparison 18
1.5 Discussion of Results 19
1.6 Conclusion 20
References 21
2 Applying Transfer Learning to Accelerate Cancer Classification and Prediction 23
T. Ravi, Shashidhar Gurav, Nandhini, Vijayaraj and S. K. Muthusundar
2.1 Introduction 24
2.1.1 Background on Cancer Classification 24
2.1.2 Transfer Learning in Medical Imaging 25
2.1.3 Model Development 26
2.2 Literature Review 27
2.2.1 Application of Transfer Learning in Breast Cancer Diagnosis 27
2.3 Methodology 30
2.3.1 Introduction 30
2.3.2 Data Preparation 31
2.3.2.1 Data Source 31
2.3.2.2 Data Collection 31
2.3.2.3 Data Preprocessing 31
2.3.2.4 Normalization 31
2.3.2.5 Handling Missing Values 32
2.3.2.6 Feature Selection 32
2.3.2.7 Data Partitioning 32
2.3.3 Model Design 33
2.3.3.1 Transfer Learning Approach 33
2.3.4 Implementation Tools 35
2.4 Results 36
2.4.1 Data Distribution 36
2.4.2 Accuracy, Precision, Recall, and F1-Score 37
2.4.3 Confusion Matrix 37
2.4.4 ROC Curve Analysis 39
2.4.5 Comparison on Traditional Machine Learning Models 39
2.5 Discussion of Results 40
2.5.1 Model Strengths 40
2.5.2 Areas for Improvement 40
2.6 Conclusion 41
References 43
3 Artificial Intelligence in Cancer Screening: Innovations in Early Detection 45
Arun Elias, V. Vaithianathan, S.K. Rajesh Kanna, G.M. Raja and S.K. Muthusundar
3.1 Introduction 46
3.1.1 Background on Cancer Screening 46
3.1.2 Role of Artificial Intelligence 47
3.1.3 Research Methodology 47
3.1.4 AI in Medical Imaging 48
3.1.5 Challenges and Ethical Considerations 48
3.2 Literature Review 50
3.3 Methodology 53
3.3.1 Dataset Collection 53
3.3.2 Data Preprocessing 54
3.3.3 Architecture Model Design 55
3.3.4 Training and Validation 56
3.3.5 Metrics to Measure 57
3.4 Results 58
3.4.1 Model Performance Metrics 58
3.4.2 Confusion Matrix Analysis 59
3.4.3 Receiver Operating Characteristic Curve 60
3.4.4 Comparison with Existing Models 61
3.4.5 Error Analysis 62
3.5 Future Directions 62
3.6 Conclusion 63
References 64
4 Comprehensive Approaches to Survival Analysis and Prognostic Modeling in Cancer Research: Integrating Statistical Techniques, and Clinical Variables 67
B. Sriman, J. Maria Arockia Dass, R. Seetha and Ashish Kumar
4.1 Introduction 68
4.1.1 Objectives 70
4.2 Literature Review 71
4.3 Methodology 74
4.3.1 Collection and Preprocessing 75
4.3.2 Cox Proportional Hazards Model 76
4.3.3 Random Survival Forest (RSF) 76
4.3.4 DeepSurv: Neural Network-Based Survival Model 77
4.3.5 Model Evaluation and Comparison 78
4.4 Results 79
4.4.1 General Comparison of Ability 79
4.4.2 Results of Cox Proportional Hazards (CPH) Model 79
4.4.3 RSF Results 82
4.4.4 Results on DeepSurv 82
4.4.5 Model Comparison and Discussion 84
4.4.6 Impact on Personalized Medicine 86
4.5 Conclusion 86
References 87
5 Exploring Cancer Therapeutics: A Collection of Case Studies 89
L. Selvam, Annie Silviya S. H., Singaravelan M. and Ira Aditi
5.1 Introduction 90
5.1.1 Conventional Cancer Therapies: Limitations and Challenges 90
5.1.2 The New Era of Targeted Therapies 91
5.1.3 Immunotherapy 91
5.1.4 Case Study: Targeted Therapy in HER2-Positive Breast Cancer 92
5.1.5 Case Study: Immunotherapy in Advanced Melanoma 93
5.2 Literature Review 93
5.3 Methodology 96
5.3.1 Research Design 97
5.3.2 Patient Selection 97
5.3.2.1 Case Study: HER2-Positive Breast Cancer (Trastuzumab) 98
5.3.2.2 Advanced Melanoma Case Study (Pembrolizumab) 98
5.3.3 Treatment Protocols 98
5.3.3.1 Trastuzumab Protocol for HER2-Positive Breast Cancer 99
5.3.4 Data Collection 99
5.3.4.1 Clinical and Imaging Data 100
5.3.4.2 Immune and Genetic Markers 100
5.3.5 Statistical Analysis 100
5.4 Results 101
5.4.1 Tumor Response 101
5.4.2 Survival Analysis 103
5.4.3 Recurrence Rate and Disease Control 105
5.4.4 Immune-Related Adverse Events and Safety Profile 106
5.5 Conclusion 109
References 109
6 Predicting Cancer Outcomes Using Transfer Learning: Harnessing Pre-Trained Models and Cross-Domain Knowledge for Enhanced Prognosis and Personalized Treatment Strategies 111
R. Ramachandran, V. Vaissnave, Vijayaraj and S. K. Muthusundar
6.1 Introduction 112
6.1.1 Background 112
6.1.2 Objectives 113
6.2 Literature Review 114
6.3 Methodology 119
6.3.1 Data Collection 119
6.3.2 Preprocessing the Data 120
6.3.3 Modeling 121
6.3.4 Model Assessment 122
6.3.5 Implementation of the Integrated Model 122
6.4 Results 123
6.4.1 Model Performance Metrics 123
6.4.2 Baseline Model Comparisons 125
6.4.3 Feature Importance Analysis 125
6.4.4 Clinical Validation Results 127
6.5 Conclusion 128
References 129
7 Predicting Cancer Outcomes with RNNs: A Time Series Approach 133
M. Mahalakshmi, Annie Silviya S. H., Kumud Sachdeva and Rajan Sachdeva
7.1 Introduction 134
7.1.1 Background 134
7.1.2 Significance of Ensemble Learning 134
7.1.3 Objectives 135
7.1.4 Significance of the Study 136
7.2 Literature Review 136
7.3 Methodology 137
7.3.1 Objective 137
7.3.2 Data Collection 137
7.3.2.1 Dataset 137
7.3.3 Preprocessing 138
7.3.3.1 Data Drawing 138
7.3.3.2 Normalization Numerical Features 138
7.3.3.3 Point Selection 139
7.3.4 Feature Selection 139
7.3.5 Ensemble Learning Techniques 140
7.3.6 Model Evaluation Metrics 142
7.3.7 Cross-Validation 143
7.4 Results 143
7.4.1 Model Performance 143
7.5 Results 149
7.5.1 Cross-Validation Results 149
7.5.2 Model Comparison 149
7.6 Conclusion 151
References 151
8 AI in Cancer Screening and Early Detection 153
Priya Batta and Soumen Sardar
8.1 Introduction 153
8.2 Literature Review 157
8.3 Methodology 160
8.4 Results 162
8.5 Conclusion and Future Scope 163
References 164
9 Challenges and Limitations of AI in Oncology 167
Priya Batta
9.1 Introduction 167
9.2 Literature Review 170
9.3 Methodology 172
9.4 Results 174
9.5 Conclusion and Future Scope 174
References 175
10 Predictive Models for Cancer-Related Lymphedema: Enhancing Telerehabilitation and Physiotherapy Management 177
Madhusmita Jena, Charu Chhabra, Huma Parveen, Sahar Zaidi, Noor Fatima and Habiba Sundus
10.1 Introduction 178
10.1.1 Prevalence of Lymphedema 179
10.1.2 Diagnostic Technique for Lymphedema 180
10.1.3 Commonly Used Scales for Diagnosis of Lymphedema 181
10.2 Lymphedema’s Impact on Cancer Survivors 181
10.3 Current Challenges in Lymphedema Management 182
10.4 Role of AI in Lymphedema Management 183
10.4.1 Customizing Physiotherapy Regimens Based on AI Predictions 184
10.4.2 Integrating Telerehabilitation for Effective Lymphedema Management 185
10.5 Conclusion 186
References 186
11 Role of AI in the Prediction of Leukemia and AI-Driven Predictive Models for Rehabilitation Outcomes in Acute Lymphoblastic Leukemia 189
Huma Parveen, Charu Chhabra, Sahar Zaidi, Noor Fatima, Madhusmita Jena and Amaan Ali Khan
11.1 Acute Lymphoblastic Leukemia 190
11.2 Importance of Early Prediction and Rehabilitation in ALL 191
11.3 Role of AI in Healthcare 193
11.4 AI in Leukemia Prediction 194
11.5 AI-Driven Predictive Rehabilitation Outcomes in ALL 196
11.6 Data Privacy and Security in Healthcare Models 199
11.7 Framework for Protecting Data Privacy 200
11.7.1 Acts and Policies 200
11.7.2 National Policies 200
11.7.3 AI Models-Based Privacy Protection 201
11.8 Ethical Concerns in AI Healthcare 202
References 203
12 Data Privacy and Ethical Challenges in AI-Driven Cancer Care 207
Firdaus Jawed, Rabia Aziz, Sumbul Ansari, Shahnawaz Anwar and Sohrab Ahmad Khan
12.1 Introduction to Data Privacy and Ethics in AI-Driven Cancer Care 208
12.2 Types of Sensitive Data in AI-Driven Cancer Care 209
12.3 Ethical Frameworks and Guidelines for Data Privacy 212
12.4 Data Security and Protection Techniques 214
12.5 Bias, Fairness, and Algorithmic Transparency in AI-Driven Cancer Care 216
12.6 Regulatory and Compliance Challenges 219
12.7 Emerging Technologies and Innovations in Privacy 221
12.8 Future Directions in Ethical AI for Cancer Care 222
12.9 Conclusions 224
References 224
13 Cancer Rehabilitation in the Era of Targeted Chemotherapy and Personalized Immunotherapy 229
Rabia Aziz, Firdaus Jawed, Sumbul Ansari, Shahnawaz Anwar and Sohrab Ahmad Khan
13.1 Evolving Landscape of Cancer Treatment 230
13.2 Importance of Cancer Rehabilitation 231
13.3 Integrating Rehabilitation Into AI-Powered Cancer Rehabilitation 232
13.3.1 The Role of Data in Rehabilitation 238
13.3.2 Machine Learning and Predictive Analytics 239
13.3.3 Real-Time Monitoring and Feedback 239
13.3.4 Outcomes Measurement and Continuous Improvement 240
13.3.5 The Rationale for Integration 241
13.3.6 Utilizing Biomarkers in Rehabilitation 241
13.3.7 Multidisciplinary Collaboration 242
13.3.8 Early Intervention Strategies 242
13.3.9 Leveraging Technology for Monitoring and Feedback 243
13.4 Leveraging Data Analytics and AI for Adaptive Rehabilitation 243
13.4.1 The Role of Data Analytics in Rehabilitation 244
13.4.2 AI-Driven Personalization of Rehabilitation Programs 244
13.4.3 Integration of Wearable Technology and Telehealth 245
13.4.4 Virtual Reality (VR) and Augmented Reality (AR) Applications 245
13.5 Tailoring Rehabilitation Strategies for Targeted Therapies 246
13.5.1 Understanding Targeted Therapies and Their Implications 246
13.5.2 Personalized Assessment and Planning 247
13.5.3 Integrating Evidence-Based Interventions 247
13.5.3.1 Physical Therapy 247
13.5.3.2 Occupational Therapy 248
13.5.3.3 Psychosocial Support 249
13.5.3.4 Nutritional Counseling 249
13.5.4 Utilizing Technology for Enhanced Rehabilitation 250
13.6 Future Directions and Emerging Trends 251
13.7 Summary 251
References 252
14 Role of AI in Cancer Screening and Its Detection 257
Muskan, Shweta Sharma, Parul Sharma, Manoj Malik and Jaspreet Kaur
14.1 Introduction 258
14.2 Cancer Mechanisms and Various Pathologies 258
14.3 Conventional Methods of Cancer Screening 260
14.3.1 Mammography 260
14.3.2 Ultrasound 262
14.3.3 Magnetic Resonance Imaging 262
14.3.4 Liquid Biopsies 262
14.3.5 Pap Smear (Papanicolaou Test) 263
14.3.6 Barium X-Ray (Barium Swallow or Enema) 263
14.3.7 Photoacoustic Tomography (PAT) 263
14.3.8 SPECT (Single-Photon Emission Computed Tomography) and PET (Positron Emission Tomography) 263
14.4 Overview of AI (Artificial Intelligence) in Cancer Detection 264
14.5 AI Applications in Cancer Screening Using Deep Learning and Machine Learning 266
14.5.1 AI Models for Breast Cancer 266
14.5.2 AI Models for Lung Cancer 266
14.5.3 AI Models for Skin Cancer 267
14.5.4 AI Models for Gastric Cancers 267
14.5.5 AI Models for Prostate Cancers 269
14.6 Challenges in AI Adoption for Cancer Screening 270
14.7 Proposed Strategies for AI Implementation for Cancer Detection 271
14.8 Conclusion 272
14.9 Future Directions 273
References 274
15 Automated 3D U-Net Framework for Brain Tumor Segmentation and Classification with Insights Into AI-Driven Cancer Research Applications 279
S. Usharani, P. Manju Bala, T. Ananth kumar and G. Glorindal Selvam
15.1 Introduction 280
15.2 Literature Review 283
15.2.1 Brain Tumor MRI Image Segmentation 283
15.2.1.1 Methods for Manual Segmentation 283
15.2.1.2 Methods for Partly-Automated Segmentation 283
15.2.1.3 Methods for Absolutely Automated Segmentation 284
15.2.2 Brain Tumor MRI Classification 285
15.3 Materials and Methods 290
15.3.1 Materials 290
15.3.2 Methods 291
15.3.2.1 System Model 291
15.3.2.2 Multi Scale Feature Extraction Network 293
15.3.2.3 Incremental Feature Improvement 294
15.3.2.4 Loss Function 295
15.4 Experimental Setup 296
15.4.1 Experimental Analysis 296
15.5 Conclusion 301
References 302
16 Early Prediction of Bone Cancer: Integrating Deep Learning Models 309
R. Dhinesh, T. Ananth kumar, P. Kanimozhi and Sunday Adeola Ajagbe
16.1 Introduction 310
16.2 Related Works 311
16.3 Proposed Methodology 313
16.4 Results and Discussion 318
16.5 Conclusion 321
References 322
17 Machine Learning Techniques for Predicting Epileptic Seizures: A Data-Driven Analysis Using EEG Signals 325
Preeti Narooka, Ankit Vishnoi and Jatin Verma
17.1 Introduction 326
17.1.1 Background 326
17.1.2 Objective 326
17.2 Literature Survey 327
17.2.1 Study 1: Feature Extraction Techniques in EEG-Based Seizure Detection 327
17.2.2 Study 2: Application of Deep Learning in Neurological Disorders 327
17.2.3 Study 3: Comparative Analysis of ML Algorithms 328
17.2.4 Study 4: Transfer Learning in EEG Analysis 328
17.2.5 Study 5: Real-Time Seizure Prediction Systems 328
17.2.6 Study 6: Explainable Artificial Intelligence in Seizure Detection 328
17.2.7 Study 7: Challenges in EEG-Based Seizure Detection 329
17.2.8 Study 8: Multimodal Learning Approaches 329
17.3 Methodology 329
17.3.1 Dataset 329
17.3.2 Preprocessing 330
17.3.3 Feature Extraction 330
17.3.4 Model Architecture 331
17.4 Results and Discussion 332
17.4.1 Model Performance 332
17.4.2 Discussion 333
17.4.3 Implications for Healthcare Applications 334
17.5 Conclusion 334
References 334
18 Transfer Learning in Cancer Research 337
Mamta and Nitin
18.1 Definition and Overview of Transfer Learning 338
18.1.1 Transfer Learning Typically Involves the Following Components 338
18.1.2 Importance of Transfer Learning in Cancer Research 339
18.1.3 Challenges in Traditional Cancer Research Approaches 341
18.2 How Transfer Learning Works 344
18.2.1 Types of Transfer Learning 345
18.2.2 Transductive Transfer Learning 346
18.3 Applications of Transfer Learning in Cancer Research 346
18.4 Challenges in Transfer Learning for Cancer 348
18.4.1 Data Scarcity and Domain Adaptation 348
18.4.2 Model Interpretability 349
18.5 Future Directions: Personalized Medicine and Drug Discovery 351
18.5.1 Personalized Medicine: Tailoring Treatment to the Individual 352
18.6 Drug Discovery: Accelerating the Path to New Therapies 353
18.7 Challenges and Ethical Considerations 354
18.8 Conclusion 354
References 355
19 Machine Learning Approaches for Early Detection of Cervical Cancer: A Comparative Study of Classification Models 359
Inam Ul Haq, Janvi Malhotra, Vanshika Rawat, Jyoti Kumari and Gagandeep Kaur
19.1 Introduction 360
19.2 Literature Review of Some Research Papers 364
19.3 Methodology 368
19.4 Results 369
19.5 Conclusion and Future Scope 370
References 370
20 Interactive Data Management for Cancer Care: Leveraging Electronic Health Records and Proteomic Data 375
M. Rohini, S. Oswalt Manoj, J. P. Ananth and D. Surendran
20.1 Introduction 376
20.1.1 Need of Electronic Health Record Maintenance 376
20.1.2 Message Passing Protocol for Cancer EHR Updates 377
20.1.3 Reliable Messaging for Critical Data 379
20.1.4 Microservice-Oriented Cancer Data Staging and Deployment 380
20.2 HER Data Processing 382
20.2.1 Staging Service 382
20.2.1.1 Autoscaling Based on Criticality of EHR System 382
20.2.2 Internal Working of the Staging Service 383
20.2.2.1 Validate and Fetch Dashboard Details 383
20.2.2.2 Execute Stored Procedure 385
20.2.2.3 High-Availability Deployment Phase 386
20.3 Conclusion 388
References 389
21 Artificial Intelligence–Driven Personalized Cancer Treatment 391
Gurwinder Singh, Sarthak Sharma and Aastha Anand
21.1 Introduction: The Dawn of Artificial Intelligence–Powered Cancer Screening 392
21.2 Role of AI in Cancer Screening 395
21.3 Role of AI in Early Detection 399
21.4 Case Studies and Real-World Implementation 401
21.5 Benefits and Opportunities 404
21.6 Conclusion 406
21.7 Future Scope 407
References 408
22 Revolutionizing Breast Cancer Detection: Emerging Trends and Future Technologies 411
Gurmeet Kaur Saini, Inderdeep Kaur and Kanwaldeep Kaur
22.1 Overview 412
22.2 Risk Assessment Types 413
22.3 Risk Elements 413
22.4 Risk Factors for Hormones and Reproduction 413
22.5 Additional Risk Factors 414
22.6 Risk of Breast Cancer Over Time 414
22.6.1 Risk Assessment by Family History 414
22.7 Models for Risk Estimate 415
22.7.1 The Gail Model 415
22.7.2 Claus–Mammary Carcinoma Risk Assessment Model 416
22.7.3 The BRCAPRO Model 418
22.7.4 Tools for Risk Calculation 418
22.8 Clinical Breast Imaging Techniques 418
22.8.1 Mammography 418
22.8.2 Ultrasonic 420
22.8.3 Magnetic Resonance Imaging 420
22.9 Measurement Systems and Techniques for Microwave Breast Imaging 421
22.9.1 Tomography Using Microwaves 421
22.9.2 Microwave Imaging Using Radar Technology 421
22.9.3 Breast Cancer Detection Using Biosensors 422
22.9.4 Use of Thermography to Find Breast Cancer 422
22.10 Discussion 423
22.11 Present Developments and Prospects for Breast Cancer Screening Methods 423
22.12 Conclusion 426
References 426
23 Future of Neurological Research: Leveraging Artificial Intelligence for Precision and Discovery 431
Hemlata and Utsav Krishan Murari
23.1 Introduction 431
23.2 AI in Neuroimaging: A Revolution in Neurological Research 435
23.3 Computational Neuroscience and Modeling: Transforming Understanding of Neural Mechanisms through AI 438
23.4 AI and BCIs: Transforming Accessibility and Real-Time Neural Interaction 441
23.5 Ethics in the Integration of AI Into Neurological Research 445
23.6 Conclusion 448
References 449
24 Cervical Cancer Detection Using Machine Learning 451
Saranya. A., S. Ravi, Harsha Latha. P., T. Kalaichelvi and A. Anbarasi
24.1 Introduction 452
24.1.1 Overview of Medical Image Analysis 454
24.2 ml Techniques for Cervical Cancer Diagnosis 459
24.2.1 ml Algorithms 459
24.2.2 Methodology of ML Classification of Images 460
24.2.3 Cervical Cancer Image Dataset 462
24.3 Related Work 462
24.3.1 Cervical Cancer Detection Using ml 463
24.4 Findings 466
24.5 Performance Metrics in ml 470
24.6 Conclusion 471
References 472
25 Deep Learning Techniques–Based Medical Image Segmentation in Cervical Cancer 477
Saranya. A., S. Ravi, Harsha Latha. P. and T. Kalaichelvi
25.1 Introduction 478
25.2 Motivation of Computer-Aided Diagnosis 480
25.3 History of DL in Medical Imaging 482
25.4 Deep Learning Application of Cervical Cancer 482
25.5 Cervical Cancer Detection Based on DL Techniques for Medical Image Segmentation 483
25.5.1 Deep Learning in Image Segmentation 483
25.5.2 Deep Learning in Classification Task 487
25.6 Frameworks Used in Detecting Cervical Cancer 488
25.6.1 Comparison Between DL Segmentation and Classification 489
25.7 Performance Metrics 494
25.8 Conclusion 495
References 495
Index 499
