Atjaunināt sīkdatņu piekrišanu

Radiomics and Its Clinical Application: Artificial Intelligence and Medical Big Data [Mīkstie vāki]

(Professor, CAS Key Laborato), (Associate Professor, CAS Key Laboratory of Molecular Imaging, Chinese Academy of Sciences, Beijing, China), (Director, CAS Key Laboratory of Molecular Imaging, Chinese Academy of Sciences, Beijing, China),
  • Formāts: Paperback / softback, 300 pages, height x width: 235x191 mm, weight: 630 g
  • Sērija : The MICCAI Society book Series
  • Izdošanas datums: 09-Jun-2021
  • Izdevniecība: Academic Press Inc
  • ISBN-10: 012818101X
  • ISBN-13: 9780128181010
Citas grāmatas par šo tēmu:
  • Mīkstie vāki
  • Cena: 130,13 €
  • Grāmatu piegādes laiks ir 3-4 nedēļas, ja grāmata ir uz vietas izdevniecības noliktavā. Ja izdevējam nepieciešams publicēt jaunu tirāžu, grāmatas piegāde var aizkavēties.
  • Daudzums:
  • Ielikt grozā
  • Piegādes laiks - 4-6 nedēļas
  • Pievienot vēlmju sarakstam
Radiomics and Its Clinical Application: Artificial Intelligence and Medical Big DataPalielināt
  • Formāts: Paperback / softback, 300 pages, height x width: 235x191 mm, weight: 630 g
  • Sērija : The MICCAI Society book Series
  • Izdošanas datums: 09-Jun-2021
  • Izdevniecība: Academic Press Inc
  • ISBN-10: 012818101X
  • ISBN-13: 9780128181010
Citas grāmatas par šo tēmu:
Permanent link: https://www.kriso.lv/db/9780128181010.html
Keywords:
Radiomics and its Clinical Application: Artificial Intelligence and Medical Big Data describes the two key aspects of radiomic clinical practice, including precision diagnosis and the therapeutic effect and prognostic evaluation that make radiomics a powerful tool in the clinical setting. This book is a very useful resource for scientists and computer engineers in machine learning and medical image analysis, scientists focusing on antineoplastic drugs, radiologists, pathologists, oncologists and surgeons wanting to understand radiomics and its potential in clinical practice.
  • Provides an introduction to the concepts of radiomics
  • Presents an in-depth discussion on core technologies and methods
  • Summarizes current radiomics research, perspectives on the future of radiomics, and the challenges ahead
  • Includes an introduction to several platforms that are planned to be built, including cooperation, data sharing, software and application platforms
Biographies ix
Preface xi
Chapter 1 Introduction
1(18)
1.1 Background of medical image analysis in cancer
2(2)
1.2 Multidimensional complexity of biomedical research
4(2)
1.3 Concept of radiomics
6(1)
1.4 Value of radiomics
7(1)
1.5 Workflow of radiomics
7(9)
1.5.1 Image acquisition and reconstruction
8(1)
1.5.2 Image segmentation
8(1)
1.5.3 Feature extraction and selection
8(1)
1.5.4 Database and data sharing
9(1)
1.5.5 Informatics analysis
9(1)
1.5.6 Medical image acquisition
9(2)
1.5.7 Segmentation of the tumor
11(1)
1.5.8 Tumor image phenotype
12(1)
1.5.9 Clinical prediction for tumor
13(2)
1.5.10 New technology of artificial intelligence
15(1)
1.6 Prospect of clinical application of radiomics
16(3)
References
16(3)
Chapter 2 Key technologies and software platforms for radiomics
19(80)
2.1 Tumor detection
20(4)
2.1.1 Data preprocessing
20(2)
2.1.2 Detection of candidate nodules
22(2)
2.2 Tumor segmentation
24(15)
2.2.1 Segmentation of pulmonary nodules based on the central-focused convolutional neural network
25(8)
2.2.2 Segmentation of brain tumor based on the convolutional neural network
33(1)
2.2.3 Fully convolutional networks
34(1)
2.2.4 Voxel segmentation algorithm based on MV-CNN
35(4)
2.3 Feature extraction
39(4)
2.3.1 The features of artificial design
40(1)
2.3.2 Deep learning features
41(2)
2.4 Feature selection and dimension reduction
43(9)
2.4.1 Classical linear dimension reduction
43(1)
2.4.2 Dimension reduction method based on feature selection
43(3)
2.4.3 Feature selection based on the linear model and regularization
46(6)
2.5 Model building
52(31)
2.5.1 Linear regression model
52(5)
2.5.2 Linear classification model
57(4)
2.5.3 Tree models
61(1)
2.5.4 AdaBoost
62(2)
2.5.5 Model selection
64(1)
2.5.6 Convolutional neural network
65(6)
2.5.7 Migration learning
71(5)
2.5.8 Semisupervised learning
76(7)
2.6 Radiomics quality assessment system
83(2)
2.7 Radiomics software platform
85(14)
2.7.1 Radiomics software
85(1)
2.7.2 Pyradiomics---radiomics algorithm library
86(11)
References
97(2)
Chapter 3 Precision diagnosis based on radiomics
99(76)
3.1 Application of radiomics in cancer screening
101(11)
3.1.1 Lung cancer screening
101(6)
3.1.2 Gastrointestinal cancer screening
107(2)
3.1.3 Breast cancer screening
109(2)
3.1.4 Prostate cancer screening
111(1)
3.2 Application of radiomics in cancer staging
112(24)
3.2.1 Prediction of parametrial invasion in cervical cancer
113(2)
3.2.2 Correlation between PET and CT features in lymph node metastasis
115(3)
3.2.3 Prediction of lymph node metastasis in colorectal cancer
118(3)
3.2.4 Prediction of axillary lymph node status in breast cancer
121(4)
3.2.5 Prediction of lymph node metastases in gastric cancer
125(3)
3.2.6 Prediction of distant metastasis in lung adenocarcinoma
128(1)
3.2.7 Prediction of distant metastasis in oropharyngeal cancer
129(2)
3.2.8 Prediction of distant metastasis in nasopharyngeal carcinoma
131(2)
3.2.9 Prediction of occult peritoneal metastasis in gastric cancer
133(3)
3.3 Application of radiomics in histopathological diagnosis of cancer
136(8)
3.3.1 Prediction of Gleason score in prostate cancer
137(1)
3.3.2 Prediction of histopathological grade in bladder cancer
138(1)
3.3.3 Prediction of histopathological grade in cervical cancer
138(3)
3.3.4 Identification of pathological subtype of lung ground-glass nodules
141(2)
3.3.5 Identification of histologic subtype in non-small cell lung cancer
143(1)
3.4 Application of radiomics in prediction of cancer gene mutation and molecular subtype
144(11)
3.4.1 Prediction of somatic mutations in lung cancer
144(2)
3.4.2 Prediction of gene mutations in gliomas
146(4)
3.4.3 Prediction of KRAS/NRAS/BRAF mutations in colorectal cancer
150(4)
3.4.4 Prediction of molecular subtypes in breast cancer
154(1)
3.5 Application of radiomics in other diseases
155(20)
3.5.1 Diagnosis of COVID-19
155(6)
3.5.2 Staging of liver fibrosis
161(1)
3.5.3 Diagnosis of portal hypertension
162(2)
3.5.4 Diagnosis of cardiovascular plaques
164(2)
3.5.5 Identification of coronary plaques with napkin-ring sign
166(1)
References
167(8)
Chapter 4 Treatment evaluation and prognosis prediction using radiomics in clinical practice
175(90)
4.1 Radiomics and its application in treatment evaluation
177(27)
4.1.1 Evaluation of radiotherapy
177(5)
4.1.2 Evaluation of response to targeted therapy
182(12)
4.1.3 Application of radiogenomics in efficacy evaluation
194(10)
4.2 Radiomics-based prognosis analysis
204(61)
4.2.1 Lung cancer
205(27)
4.2.2 Breast cancer
232(1)
4.2.3 Prostate cancer
233(1)
4.2.4 Colorectal cancer
234(1)
4.2.5 Esophageal and gastric cancers
235(2)
4.2.6 Liver cancer
237(2)
4.2.7 Pancreatic cancer
239(2)
4.2.8 Cervix cancer
241(2)
4.2.9 Central nervous system cancers
243(2)
4.2.10 Other solid cancers
245(4)
References
249(16)
Chapter 5 Summary and prospects
265(18)
5.1 Summary
265(1)
5.2 Prospect
266(11)
5.2.1 Prospective clinical application of radiomics
267(1)
5.2.2 Formulate the research norms
268(1)
5.2.3 Fundamentals of medical big data
268(1)
5.2.4 Lesion segmentation algorithms
269(1)
5.2.5 Reproducibility of the experiment
269(1)
5.2.6 Influence of machine parameters
270(2)
5.2.7 Integration of radiomics and multi-omics
272(1)
5.2.8 Prospective study
273(1)
5.2.9 Distributed learning in medical research
274(1)
5.2.10 Interpretability of radiomics
275(1)
5.2.11 Advancement in clinical guidelines
276(1)
5.3 Conclusion
277(6)
References
278(5)
Index 283
Dr. Jie Tian received his PhD (with honors) in Artificial Intelligence from the Chinese Academy of Sciences in 1993. Since 1997, he has been a Professor at the Chinese Academy of Sciences. Dr. Tian has been elected as a Fellow of ISMRM, AIMBE, IAMBE, IEEE, OSA, SPIE, and IAPR. He serves as an editorial board member of Molecular Imaging and Biology, European Radiology, IEEE Transactions on Medical Imaging, IEEE Transactions on Biomedical Engineering, IEEE Journal of Biomedical and Health Informatics, and Photoacoustics. He is the author of over 400 peer-reviewed journal articles, including publication in Nature Biomedical Engineering, Science Advances, Journal of Clinical Oncology, Nature Communications, Radiology, IEEE Transactions on Medical Imaging, and many other journals, and these articles have received over 25,000 Google Scholar citations (H-index 79). Dr. Tian is recognized as a pioneer and leader in the field of molecular imaging in China. In the last two decades, he has developed a series of new optical imaging models and reconstruction algorithms for in vivo optical tomographic imaging, including bioluminescence tomography, fluorescence molecular tomography, and Cerenkov luminescence tomography. He has developed new artificial intelligence strategies for medical imaging big data analysis in the field of radiomics and played a major role in establishing a standardized radiomics database with more than 100,000 cancer patients data collected from over 50 hospitals all over China. He has received numerous awards, including 5 national top awards for his outstanding work in medical imaging and biometrics recognition. Dr. Di Dong is currently an Associate Professor at the Institute of Automation, Chinese Academy of Sciences. He received his PhD in Pattern Recognition and Intelligent Systems from the Institute of Automation, Chinese Academy of Sciences, China, in 2013. Dr. Dong is a member of the Youth Innovation Promotion Association of the Chinese Academy of Sciences, an active member of the American Association for Cancer Research (AACR), and a corresponding member of the European Society of Radiology (ESR). Dr. Dong has carried out long-term research work in the field of tumor radiomics and medical big data analysis. In recent years, Dr. Dong has published nearly 50 peer-reviewed papers in SCI journals, e.g., in Annals of Oncology, European Respiratory Journal, Clinical Cancer Research (3 publications), BMC Medicine, etc. These articles received over 1,600 Google Scholar citations (H-index 24). He has 6 ESI highly cited papers. He has applied for more than 20 patents and 10 software copyright licences in China. Dr. Zhenyu Liu is currently a Professor at CAS Key Laboratory of Molecular Imaging, Institute of Automation. He received his PhD in Pattern Recognition and Intelligent Systems from the Institute of Automation, Chinese Academy of Sciences, China, in 2014. Dr. Liu got the outstanding youth fund of the Natural Science Foundation of China (NSFC) and is a member of the Youth Innovation Promotion Association of the Chinese Academy of Sciences. His research focuses on medical imaging analysis, especially radiomics and its application in oncology research. In recent years, Dr. Liu has published nearly 30 papers in peer-reviewed journals, e.g., in Clinical Cancer Research, Theranostics, EBioMedicine, Radiotherapy and Oncology, etc. These articles received over 1,300 Google Scholar citations. He also holds more than 10 patents in China. Dr. Jingwei Wei is currently an Assistant Professor at the Institute of Automation, Chinese Academy of Sciences. Her research focuses on radiomics and its clinical application on liver diseases, liver-specific feature engineering, traditional pattern recognition classifiers, and deep learning methods implemented towards liver disease-oriented research. Her primary main work includes pre-operative prediction of microvascular invasion in hepatocellular carcinoma (HCC), prognosis prediction in HCC, and non-invasive imaging biomarker development for pathological factors prediction in liver diseases. Dr. Wei has published over 20 peer-reviewed papers in SCI journals, e.g., in Liver Cancer, Liver International, Clinical and Translational Gastroenterology, etc.