Artificial Neural Networks in Cancer Diagnosis, Prognosis, and Patient Management

Name: Artificial Neural Networks in Cancer Diagnosis, Prognosis, and Patient Management
Rating: 0 (0 reviews)
ISBN: 9780849396922

Biomedical Engineering Series

By: R. N. G. Naguib (Editor), G. V. Sherbet (Editor)

Be the first to write a review

Hardcover Published: 22nd June 2001
ISBN: 9780849396922
Number Of Pages: 216

Hardcover

RRP $477.99

$330.50

31%
OFF

or 4 easy payments of $82.63 with

Learn more

BUY NOW

Add to Wishlist

Ships in 10 to 15 business days

Earn 661 Qantas Points
on this Book

Description
Table of Contents
Product Details

The potential value of artificial neural networks (ANN) as a predictor of malignancy has begun to receive increased recognition. Research and case studies can be found scattered throughout a multitude of journals. Artificial Neural Networks in Cancer Diagnosis, Prognosis, and Patient Management brings together the work of top researchers - primarily clinicians - who present the results of their state-of-the-art work with ANNs as applied to nearly all major areas of cancer for diagnosis, prognosis, and management of the disease.
The book introduces the theory of neural networks and the method of their application in oncology. It is not an exercise in ANN research, but the presentation of a new technique for diagnosing and determining the treatment of cancers. The authors have included almost all cancers for which there exist ANN applications. When the data available is ill-defined and the development of an algorithmic solution difficult, neural networks provide a non-linear approach which helps sift through the maze of information and arrive at a reasonable solution.
Highly interdisciplinary in nature, this book provides comprehensive coverage of the most important materials relating to the applications of ANNs in the cancer field. With contributions from prominent research centers worldwide, it serves as an introduction to how neural networks can be used for accurate prediction or diagnosis and shows why neural networks are more accurate. Artificial Neural Networks in Cancer Diagnosis, Prognosis, and Patient Management gives you an understanding of this new tool, its applications, and when it should be used.

Industry Reviews

"This book concentrates on the application of ANNs in human cancer research including feature extraction, prognostic studies, survival analyses, and outcome prediction. . . This book presents an exciting alternative to traditional statistical techniques for use in outcome prediction and disease management for cancer patients. . . most readers will be able to use the book immediately." -Kemi Ladeji-Osias, Morgan State University

Introduction to Artificial Neural Networks and Their Use in Cancer Diagnosis, Prognosis, and Patient Management	p. 1
Preamble	p. 1
Artificial Neural Networks	p. 2
Discussion	p. 5
References	p. 6
Analysis of Molecular Prognostic Factors in Breast Cancer by Artificial Neural Networks	p. 9
Introduction	p. 9
Prognostic Factors in Breast Cancer	p. 10
Established Prognostic Factors in Clinical Use: Stage, Grade, and Size	p. 10
Hormone Receptors and Oestrogen Regulated Proteins	p. 11
Markers of Cellular Proliferation and Cell Cycle Regulators	p. 12
p53 and Related Proteins	p. 12
Type 1 Growth Factor Receptors	p. 12
Prediction of Nodal Metastasis by Neural Analysis	p. 13
Proteins Associated with Metastatic Potential	p. 14
h-mts1 and not nm23 Expression Correlates with Nodal Sread of Cancer	p. 15
h-mts1 Expression and ER/PgR Status	p. 16
Anaylsis of h-mts1 and nm23 Expression by Artificial Neural Networks	p. 16
Concluding Remarks	p. 17
References	p. 17
Artificial Neural Approach to Analysing the Prognostic Significance of DNA Ploidy and Cell Cycle Distribution of Breast Cancer Aspirate Cells	p. 23
Introduction	p. 23
Breast Cancer Fine-Needle Aspirates	p. 23
Analysis of Image Cytometric Data Using Artificial Neural Networks	p. 24
Conclusions	p. 25
References	p. 26
Neural Networks for the Estimation of Prognosis in Lung Cancer	p. 29
Introduction	p. 29
Carcinoma of the Lung	p. 29
Medical Applications of Artificial Neural Networks	p. 30
Artificial Neural Networks	p. 31
Architecture	p. 31
Training Artificial Neural Network Systems	p. 31
Estimating the Reliability of Artificial Neural Networks	p. 32
Practical Application of Neural Networks in the Prognosis of Lung Cancer Patients	p. 32
Tumour Type	p. 33
Ploidy Levels	p. 33
Immunohistochemical Proliferation Markers	p. 33
Neural Processing	p. 34
Conclusions	p. 35
References	p. 35
The Use of a Genetic Algorithm Neural Network (GANN) for Prognosis in Surgically Treated Nonsmall Cell Lung Cancer (NSCLC)	p. 39
Introduction	p. 39
Method	p. 40
The NSCLC Data	p. 40
Mathematical Method: The Genetic Algorithm Neural Network	p. 40
Selection of Predictors by Genetic Algorithm	p. 40
Classification	p. 41
Choosing the Optimal Genome for Use with a Neural Network	p. 41
Updating the Optimal Information Genome	p. 41
Defining the Neural Network Architecture	p. 41
Training the Neural Network	p. 41
Stopping Rule for the Training Process	p. 41
Classification Solution	p. 42
Application of Bayes' Theorem	p. 42
Computational Method	p. 42
Statistical Methods	p. 42
Predictive Statistics	p. 42
Comparison of Predictive Statistics	p. 42
Survival	p. 43
Survival by Logistic Regression	p. 44
Survival Classification by GANN	p. 44
Comparison of Logistic Regression and GANN for Classification of Survival	p. 45
Discussion	p. 48
Interpretation of Clinical Findings	p. 48
Methodological Considerations	p. 49
Classification of Survival Outcome	p. 49
Losses and Gains in Information	p. 50
Adaptability and Retraining	p. 51
Variable Selection by the GA	p. 52
Performance of Genetic Algorithm Neural Network Compared with Logistic Regression	p. 52
Adaptations in the Genetic Algorithm Neural Network Method: Simulating Preprocessing in Basic Neural Systems	p. 52
Components of Methodological Performance	p. 52
Conclusions	p. 53
References	p. 53
The Use of Machine Learning in Screening for Oral Cancer	p. 55
Epidemiology	p. 55
Clinical Features and Diagnosis	p. 55
Screening for Oral Cancer	p. 56
Selection of High-Risk Groups Using a Neural Network	p. 57
Training and Testing the Neural Network	p. 57
Comparison of Neural Networks and Other Machine Learning Techniques	p. 60
Data Visualisation in Clementine	p. 60
Inducing Models in Clementine	p. 64
Evaluating the Potential Performance of Machine Learning for Detection of High-Risk Individuals	p. 68
Summary and Conclusions	p. 70
References	p. 70
Outcome Prediction of Oesophago-Gastric Cancer Using Neural Analysis of Pre- and Postoperative Parameters	p. 73
Introduction	p. 73
Artificial Neural Networks for the Prediction of Outcome of Oesophago-Gastric Cancer	p. 74
Reference	p. 90
Artifical Neural Networks in Urologic Oncology	p. 93
Introduction	p. 93
Kidney Cancer	p. 94
Bladder Cancer	p. 95
Prostate Cancer	p. 95
Testicular Cancer	p. 98
Discussion	p. 98
References	p. 100
Neural Networks in Urologic Oncology	p. 103
Introduction	p. 103
Renal Cell Carcinoma	p. 103
Prostate Cancer	p. 107
Bladder Cancer	p. 110
Testicular Carcinoma	p. 111
Conclusion	p. 111
References	p. 112
Comparison of a Neural Network with High Sensitivity and Specificity of Free/Total Serum PSA for Diagnosing Prostate Cancer in Men with a PSA [ 4.0 ng/mL	p. 115
Introduction	p. 115
Material and Methods	p. 116
Patient Selection	p. 116
Laboratory Analysis	p. 116
Neural Network Inputs and Derivation of the PI	p. 116
Results	p. 116
Comment	p. 122
References	p. 124
Artificial Neural Networks and Prognosis in Prostate Cancer	p. 125
Introduction	p. 125
Prostate Cancer	p. 126
Patients and Methods	p. 126
Patients	p. 126
Methods	p. 126
Immunohistochemistry	p. 126
Artificial Neural Networks	p. 127
Statistical Analysis	p. 127
Results	p. 127
Immunohistochemistry	p. 127
Neural Network Analysis	p. 127
Comparison of ANNs with Statistical Analysis	p. 129
Summary	p. 130
References	p. 131
Comparison between Urologists and Artificial Neural Networks in Bladder Cancer Outcome Prediction	p. 133
Introduction	p. 133
Materials and Methods	p. 135
Results	p. 136
Clinical Outcome: Recurrence, Progression, and Survival	p. 136
Predictions by the ANN and Clinicians	p. 136
Discussion	p. 138
References	p. 139
A Probabilistic Neural Network Framework for the Detection of Malignant Melanoma	p. 141
Introduction	p. 141
Malignant Melanoma	p. 141
Evolution of Malignant Melanoma	p. 142
Image Acquistion Techniques	p. 142
Traditional Imaging	p. 142
Dermatoscopic Imaging	p. 142
Dermatoscopic Features	p. 143
Feature Extraction in Dermatoscopic Images	p. 145
Image Acquisition	p. 145
Image Preprocessing	p. 146
Median Filtering	p. 147
Karhunen-Loeve Transform	p. 148
Image Segmentation	p. 149
Optimal Thresholding	p. 149
Dermatoscopic Feature Description	p. 152
Asymmetry	p. 152
Edge Abruptness	p. 154
Colour	p. 156
A Probabalistic Framework for Classification	p. 160
Bayes' Decision Theory	p. 160
Measuring Model Preformance	p. 161
Cross-Entropy Error Function for Multiple Classes	p. 163
Measuring Generalisation Performance	p. 163
Empirical Estimates	p. 164
Algebraic Estimates	p. 165
Controlling Model Complexity	p. 165
Weight Decay Regularisation	p. 166
Optimal Brain Damage Pruning	p. 166
Neural Classifier Modelling	p. 167
Multilayer Perception Architecture	p. 168
Softmax Normalisation	p. 168
Modified Softmax Normalisation	p. 169
Estimating Model Parameters	p. 170
Gradient Descent Optimisation	p. 172
Newton Optimisation	p. 172
Overview of Design Algorithm	p. 173
Experiments	p. 173
Experimental Setup	p. 173
Results	p. 174
Classifier Results	p. 174
Dermatoscopic Feature Importance	p. 178
Conclusions	p. 180
Dermatoscopic Feature Extraction	p. 180
Probabilistic Framework for Classification	p. 180
Neural Classifier Modelling	p. 180
The Malignant Melanoma Classification Problem	p. 181
References	p. 181
Index	p. 185
Table of Contents provided by Syndetics. All Rights Reserved.

ISBN: 9780849396922
ISBN-10: 0849396921
Series: Biomedical Engineering Series
Audience: Professional
Format: Hardcover
Language: English
Number Of Pages: 216
Published: 22nd June 2001
Publisher: CRC PR INC
Country of Publication: US
Dimensions (cm): 25.4 x 18.42 x 1.91
Weight (kg): 0.6
Edition Number: 1