Computational Methodologies for Solid Tumor Characterization and Outcome Prediction in Volumetric Medical Images PDF Download
Are you looking for read ebook online? Search for your book and save it on your Kindle device, PC, phones or tablets. Download Computational Methodologies for Solid Tumor Characterization and Outcome Prediction in Volumetric Medical Images PDF full book. Access full book title Computational Methodologies for Solid Tumor Characterization and Outcome Prediction in Volumetric Medical Images by Thierry Lefebvre. Download full books in PDF and EPUB format.
Author: Thierry Lefebvre Publisher: ISBN: Category : Languages : en Pages :
Book Description
"Imaging-based quantification and characterization of tumor phenotypes has been the main goal of numerous efforts in recent years for developing and integrating precision oncology in clinical practice. Identifying optimal quantitative image features and machine learning pipelines for computer-aided diagnosis constitute crucial steps towards the development of reproducible, standardized, and clinically relevant imaging biomarkers of cancer phenotypic characteristics. An “image feature” can be understood as an image-derived descriptor of intensity, shape, texture, etc. In radiomics studies, the main hypothesis is that combining many of these quantitative features extracted from tumor regions in medical images can predict underlying genetic or pathological changes occurring in response to disease activity. Given the high variability of processing pipelines in radiomics studies, we first aimed to develop and validate a standardized, IBSI-compliant, and evidence-based processing pipeline for radiomics studies. Second, we aimed to evaluate the diagnostic performance of the well-established robust set of rotationally invariant features from spherical harmonics (SPHARM) decompositions in predicting outcomes from volumetric medical images and compare it to radiomics. Pipelines for these two methods were built and validated on synthetic 3D texture datasets and in two distinct dual-centre diagnostic retrospective studies: i) a study on identifying renal cysts malignancy on contrast-enhanced CT, and ii) a study on identifying histopathological features of endometrial cancer on multi-parametric MRI.For distinguishing benign from malignant renal cysts, a random forest model based on a set of five most discriminative and reproducible radiomics features resulted in high diagnostic performance (testing area under the receiver operating characteristic curve [AUC] = 0.91). Similarly, for SPHARM decomposition coefficients, a tensor logistic regressor resulted in good diagnostic performance for predicting malignancy of renal cysts (testing AUC = 0.83). For detecting histopathological deep myometrial invasion in endometrial cancer on multi-parametric MRI, a random forest model based on our set of five most discriminative and reproducible radiomics features resulted in good diagnostic performance (testing AUC = 0.81). For SPHARM decomposition coefficients, a tensor logistic regressor resulted in higher diagnostic performance using only dynamic-contrast-enhanced MRI images (testing AUC = 0.86). Furthermore, we show that in specific situations, approximate spherical tumor segmentations can rival or even outperform painstakingly obtained but accurate tumor segmentations. Both radiomics features and SPHARM descriptors show promise as reproducible surrogate biomarkers of histopathological features of cancer activity on CT and MRI. Implementing such computational pipelines in clinical practice could improve and accelerate patients’ stratification and decision-making for radiologists and radio-oncologists in cancer diagnosis or treatment"--
Author: Thierry Lefebvre Publisher: ISBN: Category : Languages : en Pages :
Book Description
"Imaging-based quantification and characterization of tumor phenotypes has been the main goal of numerous efforts in recent years for developing and integrating precision oncology in clinical practice. Identifying optimal quantitative image features and machine learning pipelines for computer-aided diagnosis constitute crucial steps towards the development of reproducible, standardized, and clinically relevant imaging biomarkers of cancer phenotypic characteristics. An “image feature” can be understood as an image-derived descriptor of intensity, shape, texture, etc. In radiomics studies, the main hypothesis is that combining many of these quantitative features extracted from tumor regions in medical images can predict underlying genetic or pathological changes occurring in response to disease activity. Given the high variability of processing pipelines in radiomics studies, we first aimed to develop and validate a standardized, IBSI-compliant, and evidence-based processing pipeline for radiomics studies. Second, we aimed to evaluate the diagnostic performance of the well-established robust set of rotationally invariant features from spherical harmonics (SPHARM) decompositions in predicting outcomes from volumetric medical images and compare it to radiomics. Pipelines for these two methods were built and validated on synthetic 3D texture datasets and in two distinct dual-centre diagnostic retrospective studies: i) a study on identifying renal cysts malignancy on contrast-enhanced CT, and ii) a study on identifying histopathological features of endometrial cancer on multi-parametric MRI.For distinguishing benign from malignant renal cysts, a random forest model based on a set of five most discriminative and reproducible radiomics features resulted in high diagnostic performance (testing area under the receiver operating characteristic curve [AUC] = 0.91). Similarly, for SPHARM decomposition coefficients, a tensor logistic regressor resulted in good diagnostic performance for predicting malignancy of renal cysts (testing AUC = 0.83). For detecting histopathological deep myometrial invasion in endometrial cancer on multi-parametric MRI, a random forest model based on our set of five most discriminative and reproducible radiomics features resulted in good diagnostic performance (testing AUC = 0.81). For SPHARM decomposition coefficients, a tensor logistic regressor resulted in higher diagnostic performance using only dynamic-contrast-enhanced MRI images (testing AUC = 0.86). Furthermore, we show that in specific situations, approximate spherical tumor segmentations can rival or even outperform painstakingly obtained but accurate tumor segmentations. Both radiomics features and SPHARM descriptors show promise as reproducible surrogate biomarkers of histopathological features of cancer activity on CT and MRI. Implementing such computational pipelines in clinical practice could improve and accelerate patients’ stratification and decision-making for radiologists and radio-oncologists in cancer diagnosis or treatment"--
Author: Leonardo Rundo Publisher: Mdpi AG ISBN: 9783036525549 Category : Science Languages : en Pages : 262
Book Description
Cancer is the second most common cause of death worldwide and encompasses highly variable clinical and biological scenarios. Some of the current clinical challenges are (i) early diagnosis of the disease and (ii) precision medicine, which allows for treatments targeted to specific clinical cases. The ultimate goal is to optimize the clinical workflow by combining accurate diagnosis with the most suitable therapies. Toward this, large-scale machine learning research can define associations among clinical, imaging, and multi-omics studies, making it possible to provide reliable diagnostic and prognostic biomarkers for precision oncology. Such reliable computer-assisted methods (i.e., artificial intelligence) together with clinicians' unique knowledge can be used to properly handle typical issues in evaluation/quantification procedures (i.e., operator dependence and time-consuming tasks). These technical advances can significantly improve result repeatability in disease diagnosis and guide toward appropriate cancer care. Indeed, the need to apply machine learning and computational intelligence techniques has steadily increased to effectively perform image processing operations-such as segmentation, co-registration, classification, and dimensionality reduction-and multi-omics data integration.
Author: National Research Council Publisher: National Academies Press ISBN: 0309222222 Category : Medical Languages : en Pages : 142
Book Description
Motivated by the explosion of molecular data on humans-particularly data associated with individual patients-and the sense that there are large, as-yet-untapped opportunities to use this data to improve health outcomes, Toward Precision Medicine explores the feasibility and need for "a new taxonomy of human disease based on molecular biology" and develops a potential framework for creating one. The book says that a new data network that integrates emerging research on the molecular makeup of diseases with clinical data on individual patients could drive the development of a more accurate classification of diseases and ultimately enhance diagnosis and treatment. The "new taxonomy" that emerges would define diseases by their underlying molecular causes and other factors in addition to their traditional physical signs and symptoms. The book adds that the new data network could also improve biomedical research by enabling scientists to access patients' information during treatment while still protecting their rights. This would allow the marriage of molecular research and clinical data at the point of care, as opposed to research information continuing to reside primarily in academia. Toward Precision Medicine notes that moving toward individualized medicine requires that researchers and health care providers have access to very large sets of health- and disease-related data linked to individual patients. These data are also critical for developing the information commons, the knowledge network of disease, and ultimately the new taxonomy.
Author: Ke-Lin Du Publisher: Springer Science & Business Media ISBN: 1447155718 Category : Technology & Engineering Languages : en Pages : 834
Book Description
Providing a broad but in-depth introduction to neural network and machine learning in a statistical framework, this book provides a single, comprehensive resource for study and further research. All the major popular neural network models and statistical learning approaches are covered with examples and exercises in every chapter to develop a practical working understanding of the content. Each of the twenty-five chapters includes state-of-the-art descriptions and important research results on the respective topics. The broad coverage includes the multilayer perceptron, the Hopfield network, associative memory models, clustering models and algorithms, the radial basis function network, recurrent neural networks, principal component analysis, nonnegative matrix factorization, independent component analysis, discriminant analysis, support vector machines, kernel methods, reinforcement learning, probabilistic and Bayesian networks, data fusion and ensemble learning, fuzzy sets and logic, neurofuzzy models, hardware implementations, and some machine learning topics. Applications to biometric/bioinformatics and data mining are also included. Focusing on the prominent accomplishments and their practical aspects, academic and technical staff, graduate students and researchers will find that this provides a solid foundation and encompassing reference for the fields of neural networks, pattern recognition, signal processing, machine learning, computational intelligence, and data mining.
Author: Ruijiang Li Publisher: CRC Press ISBN: 1351208268 Category : Science Languages : en Pages : 420
Book Description
Radiomics and Radiogenomics: Technical Basis and Clinical Applications provides a first summary of the overlapping fields of radiomics and radiogenomics, showcasing how they are being used to evaluate disease characteristics and correlate with treatment response and patient prognosis. It explains the fundamental principles, technical bases, and clinical applications with a focus on oncology. The book’s expert authors present computational approaches for extracting imaging features that help to detect and characterize disease tissues for improving diagnosis, prognosis, and evaluation of therapy response. This book is intended for audiences including imaging scientists, medical physicists, as well as medical professionals and specialists such as diagnostic radiologists, radiation oncologists, and medical oncologists. Features Provides a first complete overview of the technical underpinnings and clinical applications of radiomics and radiogenomics Shows how they are improving diagnostic and prognostic decisions with greater efficacy Discusses the image informatics, quantitative imaging, feature extraction, predictive modeling, software tools, and other key areas Covers applications in oncology and beyond, covering all major disease sites in separate chapters Includes an introduction to basic principles and discussion of emerging research directions with a roadmap to clinical translation
Author: Nikos Paragios Publisher: Springer ISBN: 9781489977755 Category : Computers Languages : en Pages : 0
Book Description
This book offers a unique guide to the entire chain of biomedical imaging, explaining how image formation is done, and how the most appropriate algorithms are used to address demands and diagnoses. It is an exceptional tool for radiologists, research scientists, senior undergraduate and graduate students in health sciences and engineering, and university professors.
Author: Alex A.T. Bui Publisher: Springer Science & Business Media ISBN: 1441903852 Category : Technology & Engineering Languages : en Pages : 454
Book Description
Medical Imaging Informatics provides an overview of this growing discipline, which stems from an intersection of biomedical informatics, medical imaging, computer science and medicine. Supporting two complementary views, this volume explores the fundamental technologies and algorithms that comprise this field, as well as the application of medical imaging informatics to subsequently improve healthcare research. Clearly written in a four part structure, this introduction follows natural healthcare processes, illustrating the roles of data collection and standardization, context extraction and modeling, and medical decision making tools and applications. Medical Imaging Informatics identifies core concepts within the field, explores research challenges that drive development, and includes current state-of-the-art methods and strategies.
Author: S. Kevin Zhou Publisher: Academic Press ISBN: 0323858880 Category : Computers Languages : en Pages : 544
Book Description
Deep Learning for Medical Image Analysis, Second Edition is a great learning resource for academic and industry researchers and graduate students taking courses on machine learning and deep learning for computer vision and medical image computing and analysis. Deep learning provides exciting solutions for medical image analysis problems and is a key method for future applications. This book gives a clear understanding of the principles and methods of neural network and deep learning concepts, showing how the algorithms that integrate deep learning as a core component are applied to medical image detection, segmentation, registration, and computer-aided analysis. · Covers common research problems in medical image analysis and their challenges · Describes the latest deep learning methods and the theories behind approaches for medical image analysis · Teaches how algorithms are applied to a broad range of application areas including cardiac, neural and functional, colonoscopy, OCTA applications and model assessment · Includes a Foreword written by Nicholas Ayache
Author: Thierry Lefebvre
Author: Thierry Lefebvre
Author: Leonardo Rundo
Author: National Research Council
Author: Ke-Lin Du
Author: Omar Sultan Al-Kadi
Author: Ruijiang Li
Author: Nikos Paragios
Author: Alex A.T. Bui
Author: S. Kevin Zhou
Author: