06464nam 22007455 450 991043791830332120200630055603.01-283-63443-0978661394688194-007-5389-610.1007/978-94-007-5389-1(CKB)2670000000256415(EBL)1030695(OCoLC)810931914(SSID)ssj0000766962(PQKBManifestationID)11511278(PQKBTitleCode)TC0000766962(PQKBWorkID)10732094(PQKB)11235607(DE-He213)978-94-007-5389-1(MiAaPQ)EBC1030695(PPN)168340763(EXLCZ)99267000000025641520120915d2013 u| 0engur|n|---|||||txtccrColor Medical Image Analysis[electronic resource] /edited by M. Emre Celebi, Gerald Schaefer1st ed. 2013.Dordrecht :Springer Netherlands :Imprint: Springer,2013.1 online resource (207 p.)Lecture Notes in Computational Vision and Biomechanics,2212-9391 ;6Description based upon print version of record.94-017-8129-X 94-007-5388-8 Includes bibliographical references and index.Color Medical Image Analysis; Preface; Contents; A Data Driven Approach to Cervigram Image Analysis and Classification; 1 Introduction; 2 Related Work; 3 Methodology; 3.1 Visual Feature Extraction and Representation; Color Features; Texture Features; Image Similarity Measurement; 3.2 Finding the Region of Interest; 3.3 Cervigram Classification; 3.4 Support Vector Machine Classification; 3.5 Majority Vote Classification; 4 Results; 4.1 Isolating the Region of Interest; 4.2 Accuracy of Our Disease Classification; 4.3 Weighted Effect of Color and Texture; 5 Discussion and Conclusion; ReferencesMacroscopic Pigmented Skin Lesion Segmentation and Its Influence on Lesion Classification and Diagnosis1 Introduction; 2 Pre-processing; 2.1 Shading Attenuation; 3 Segmentation; 3.1 Grayscale-Based Methods; 3.1.1 Thresholding-Based Methods; 3.1.2 Multi-Direction GVF Snake Method; 3.2 Multichannel-Based Methods; 3.2.1 Thresholding-Based Methods; 3.2.2 ICA-Based Active-Contours Method; 3.3 Comparison of Segmentation Methods Based on Experimental Results; 4 Feature Extraction for Skin Lesion Discrimination; 4.1 Features Used for Lesion Asymmetry Characterization4.2 Features Used for Lesion Boundary Irregularity Characterization4.3 Features Used for Lesion Color Variation Characterization; 4.4 Features Used for Lesion Differential Structures Characterization; 4.5 Feature Extraction Summary; 5 Classification of Pigmented Skin Lesion Images; 5.1 Feature Normalization; 5.2 Defining Training Sets; 5.3 Classification Methods; 6 Discussion of Experimental Evidences: Pigmented Skin Lesion Segmentation and Its Influence on the Lesion Classification and Diagnosis; 7 Summary and Future Trends; ReferencesColor and Spatial Features Integrated Normalized Distance for Density Based Border Detection in Dermoscopy Images1 Introduction; 2 Dermoscopy Image Analysis; 2.1 The ABCDE Rule; 3 Density Based Clustering; 3.1 DBSCAN; 3.2 Boundary Driven Density Clustering; 3.3 Expanding Cluster in FDBLD; 3.4 Selecting Leading Points; 3.5 FDBLD Algorithm; 4 Normalized Distance; 4.1 Effect of Color Spaces; 5 Experiments and Results on Dermoscopy Images; 6 Conclusion; References; A Color and Texture Based Hierarchical K-NN Approach to the Classification of Non-melanoma Skin Lesions; 1 Introduction2 Skin Class Hierarchy3 Hierarchical K-NN Classifier; 3.1 K-NN Classifier; 3.2 Learning Phase; 3.3 Classification Phase; 4 Feature Description; 4.1 Color Features; 4.2 Texture Features; 4.3 Ad Hoc Color Ratio Features; 4.4 Distance Measure; 5 Methods; 5.1 Acquisition and Preprocessing; 5.2 Highlight Removal; 5.3 Feature Normalization; 5.4 Evaluation; 5.4.1 Influence of the K Parameter; 5.4.2 Influence of Color Features; 5.4.3 Influence of Texture Features; 5.4.4 Influence of Feature Number and Selection Algorithm; 5.5 Comparison with Other Methods; 6 Overall Results; 7 Conclusions; AppendixReferencesSince the early 20th century, medical imaging has been dominated by monochrome imaging modalities such as x-ray, computed tomography, ultrasound, and magnetic resonance imaging. As a result, color information has been overlooked in medical image analysis applications. Recently, various medical imaging modalities that involve color information have been introduced. These include cervicography, dermoscopy, fundus photography, gastrointestinal endoscopy, microscopy, and wound photography. However, in comparison to monochrome images, the analysis of color images is a relatively unexplored area. The multivariate nature of color image data presents new challenges for researchers and practitioners as the numerous methods developed for monochrome images are often not directly applicable to multichannel images. The goal of this volume is to summarize the state-of-the-art in the utilization of color information in medical image analysis.Lecture Notes in Computational Vision and Biomechanics,2212-9391 ;6Biomedical engineeringOptical data processingRadiologyBiomedical Engineering and Bioengineeringhttps://scigraph.springernature.com/ontologies/product-market-codes/T2700XImage Processing and Computer Visionhttps://scigraph.springernature.com/ontologies/product-market-codes/I22021Imaging / Radiologyhttps://scigraph.springernature.com/ontologies/product-market-codes/H29005Biomedical engineering.Optical data processing.Radiology.Biomedical Engineering and Bioengineering.Image Processing and Computer Vision.Imaging / Radiology.621.36/7Celebi M. Emreedthttp://id.loc.gov/vocabulary/relators/edtSchaefer Geraldedthttp://id.loc.gov/vocabulary/relators/edtBOOK9910437918303321Color Medical Image Analysis2525738UNINA