Linked e-resources
Details
Table of Contents
Intro; Foreword; Preface; Acknowledgements; Contents; Advanced Machine Learning in Computer-Aided Systems; Multi-modality Feature Learning in Diagnoses of Alzheimer's Disease; 1 Introduction; 2 Subjects; 2.1 Data Acquisition; 2.2 Image Analysis; 3 Multi-task Feature Selection (MTFS); 3.1 Method; 3.2 Multimodal Data Fusion and Classification; 3.3 Validation; 3.4 Results; 4 Manifold Regularized Multi-task Feature Selection (M2TFS); 4.1 Manifold Regularized MTFS (M2TFS); 4.2 Classification; 4.3 Results; 5 Label-Aligned Multi-task Feature Selection (LAMTFS); 5.1 Method.
5.2 Experiments and Results6 Discriminative Multi-task Feature Selection (DMTFS); 6.1 Method; 6.2 Experimental Results; 7 Conclusion; References; A Comparative Study of Modern Machine Learning Approaches for Focal Lesion Detection and Classification in Medical Images: BoVW, CNN and MTANN; 1 Introduction; 2 Methods; 2.1 Massive-Training Artificial Neural Networks (MTANNs); 2.2 Convolutional Neural Networks (CNNs); 2.3 Bag of Visual Words with Fisher Encoding; 3 Datasets; 3.1 Database for Lung Nodule Detection; 3.2 Database for Colorectal Polyp Detection.
3.3 Database for Lung Nodule Classification4 Candidate Generation and Data Augmentation; 5 Experiments; 5.1 CNNs Versus Fisher Vectors; 5.2 CNNs Versus MTANNs; 6 Discussion; 7 Conclusion; References; 3 Introduction to Binary Coordinate Ascent: New Insights into Efficient Feature Subset Selection for Machine Learning; Abstract; 1 Introduction; 2 Methods; 2.1 Coordinate Descent Algorithm; 2.2 Binary Coordinate Ascent Algorithm; 2.3 BCA-Based Wrapper FS; 3 Experimental Results; 4 Discussion; 5 Conclusion; Acknowledgements; References; Computer-Aided Detection.
4 Automated Lung Nodule Detection Using Positron Emission Tomography/Computed TomographyAbstract; 1 Introduction; 1.1 Related Works; 1.2 Objectives; 2 Methods; 2.1 Method Overview; 2.2 Nodule Detection Using CT Images; 2.2.1 Lung Segmentation; 2.2.2 Nodule Enhancement and Segmentation; 2.3 Nodule Detection in PET Images; 2.3.1 SUV Transformation; 2.3.2 Detection of Initial Candidates; 2.3.3 Initial FP Reduction; 2.4 Integration and False Positive Reduction; 2.4.1 Calculation of Characteristic Features; 2.4.2 Rule-Based Classifier; 2.4.3 SVM Classifiers; 3 Experiments; 3.1 Materials.
3.2 Evaluation Methods3.3 Results; 4 Discussions; 5 Conclusion; Acknowledgements; References; Detecting Mammographic Masses via Image Retrieval and Discriminative Learning; 1 Introduction; 2 Related Work; 2.1 Learning-Based CAD Methods; 2.2 CBIR-Based CAD Methods; 3 Mass Detection via Retrieval and Learning; 3.1 Local Feature Voting-Based Mass Retrieval; 3.2 Learning Similarity Thresholds; 3.3 Detection of Masses; 4 Experiments; 4.1 Dataset; 4.2 Mass Detection Performance; 4.3 Mass Retrieval Performance; 5 Conclusions and Discussions; References; Computer-Aided Diagnosis.
5.2 Experiments and Results6 Discriminative Multi-task Feature Selection (DMTFS); 6.1 Method; 6.2 Experimental Results; 7 Conclusion; References; A Comparative Study of Modern Machine Learning Approaches for Focal Lesion Detection and Classification in Medical Images: BoVW, CNN and MTANN; 1 Introduction; 2 Methods; 2.1 Massive-Training Artificial Neural Networks (MTANNs); 2.2 Convolutional Neural Networks (CNNs); 2.3 Bag of Visual Words with Fisher Encoding; 3 Datasets; 3.1 Database for Lung Nodule Detection; 3.2 Database for Colorectal Polyp Detection.
3.3 Database for Lung Nodule Classification4 Candidate Generation and Data Augmentation; 5 Experiments; 5.1 CNNs Versus Fisher Vectors; 5.2 CNNs Versus MTANNs; 6 Discussion; 7 Conclusion; References; 3 Introduction to Binary Coordinate Ascent: New Insights into Efficient Feature Subset Selection for Machine Learning; Abstract; 1 Introduction; 2 Methods; 2.1 Coordinate Descent Algorithm; 2.2 Binary Coordinate Ascent Algorithm; 2.3 BCA-Based Wrapper FS; 3 Experimental Results; 4 Discussion; 5 Conclusion; Acknowledgements; References; Computer-Aided Detection.
4 Automated Lung Nodule Detection Using Positron Emission Tomography/Computed TomographyAbstract; 1 Introduction; 1.1 Related Works; 1.2 Objectives; 2 Methods; 2.1 Method Overview; 2.2 Nodule Detection Using CT Images; 2.2.1 Lung Segmentation; 2.2.2 Nodule Enhancement and Segmentation; 2.3 Nodule Detection in PET Images; 2.3.1 SUV Transformation; 2.3.2 Detection of Initial Candidates; 2.3.3 Initial FP Reduction; 2.4 Integration and False Positive Reduction; 2.4.1 Calculation of Characteristic Features; 2.4.2 Rule-Based Classifier; 2.4.3 SVM Classifiers; 3 Experiments; 3.1 Materials.
3.2 Evaluation Methods3.3 Results; 4 Discussions; 5 Conclusion; Acknowledgements; References; Detecting Mammographic Masses via Image Retrieval and Discriminative Learning; 1 Introduction; 2 Related Work; 2.1 Learning-Based CAD Methods; 2.2 CBIR-Based CAD Methods; 3 Mass Detection via Retrieval and Learning; 3.1 Local Feature Voting-Based Mass Retrieval; 3.2 Learning Similarity Thresholds; 3.3 Detection of Masses; 4 Experiments; 4.1 Dataset; 4.2 Mass Detection Performance; 4.3 Mass Retrieval Performance; 5 Conclusions and Discussions; References; Computer-Aided Diagnosis.