1
|
Feng Q, Ding Z. MRI Radiomics Classification and Prediction in Alzheimer's Disease and Mild Cognitive Impairment: A Review. Curr Alzheimer Res 2021; 17:297-309. [PMID: 32124697 DOI: 10.2174/1567205017666200303105016] [Citation(s) in RCA: 29] [Impact Index Per Article: 9.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/08/2019] [Revised: 02/03/2020] [Accepted: 03/01/2020] [Indexed: 01/18/2023]
Abstract
BACKGROUND Alzheimer's Disease (AD) is a progressive neurodegenerative disease that threatens the health of the elderly. Mild Cognitive Impairment (MCI) is considered to be the prodromal stage of AD. To date, AD or MCI diagnosis is established after irreversible brain structure alterations. Therefore, the development of new biomarkers is crucial to the early detection and treatment of this disease. At present, there exist some research studies showing that radiomics analysis can be a good diagnosis and classification method in AD and MCI. OBJECTIVE An extensive review of the literature was carried out to explore the application of radiomics analysis in the diagnosis and classification among AD patients, MCI patients, and Normal Controls (NCs). RESULTS Thirty completed MRI radiomics studies were finally selected for inclusion. The process of radiomics analysis usually includes the acquisition of image data, Region of Interest (ROI) segmentation, feature extracting, feature selection, and classification or prediction. From those radiomics methods, texture analysis occupied a large part. In addition, the extracted features include histogram, shapebased features, texture-based features, wavelet features, Gray Level Co-Occurrence Matrix (GLCM), and Run-Length Matrix (RLM). CONCLUSION Although radiomics analysis is already applied to AD and MCI diagnosis and classification, there still is a long way to go from these computer-aided diagnostic methods to the clinical application.
Collapse
Affiliation(s)
- Qi Feng
- Department of Radiology, Affiliated Hangzhou First People's Hospital, Zhejiang University School of Medicine, Hangzhou, China
| | - Zhongxiang Ding
- Department of Radiology, Affiliated Hangzhou First People's Hospital, Zhejiang University School of Medicine, Hangzhou, China.,Translational Medicine Research Center, Key Laboratory of Clinical Cancer Pharmacology and Toxicology Research of Zhejiang Province, Affiliated Hangzhou First People's Hospital, Zhejiang University School of Medicine, Hangzhou, China
| |
Collapse
|
2
|
Huang J, Milchenko M, Rao YJ, LaMontagne P, Abraham C, Robinson CG, Huang Y, Shimony JS, Rich KM, Benzinger T. A feasibility study to evaluate early treatment response of brain metastases one week after stereotactic radiosurgery using perfusion weighted imaging. PLoS One 2020; 15:e0241835. [PMID: 33141861 PMCID: PMC7608872 DOI: 10.1371/journal.pone.0241835] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/17/2020] [Accepted: 10/20/2020] [Indexed: 01/06/2023] Open
Abstract
Background To explore if early perfusion-weighted magnetic resonance imaging (PWI) may be a promising imaging biomarker to predict local recurrence (LR) of brain metastases after stereotactic radiosurgery (SRS). Methods This is a prospective pilot study of adult brain metastasis patients who were treated with SRS and imaged with PWI before and 1 week later. Relative cerebral blood volume (rCBV) parameter maps were calculated by normalizing to the mean value of the contralateral white matter on PWI. Cox regression was conducted to explore factors associated with time to LR, with Bonferroni adjusted p<0.0006 for multiple testing correction. LR rates were estimated with the Kaplan-Meier method and compared using the log-rank test. Results Twenty-three patients were enrolled from 2013 through 2016, with 22 evaluable lesions from 16 patients. After a median follow-up of 13.1 months (range: 3.0–53.7), 5 lesions (21%) developed LR after a median of 3.4 months (range: 2.3–5.7). On univariable analysis, larger tumor volume (HR 1.48, 95% CI 1.02–2.15, p = 0.04), lower SRS dose (HR 0.45, 95% CI 0.21–0.97, p = 0.04), and higher rCBV at week 1 (HR 1.07, 95% CI 1.003–1.14, p = 0.04) had borderline association with shorter time to LR. Tumors >2.0cm3 had significantly higher LR than if ≤2.0cm3: 54% vs 0% at 1 year, respectively, p = 0.008. A future study to confirm the association of early PWI and LR of the high-risk cohort of lesions >2.0cm3 is estimated to require 258 patients. Conclusions PWI at week 1 after SRS may have borderline association with LR. Tumors <2.0cm3 have low risk of LR after SRS and may be low-yield for predictive biomarker studies. Information regarding sample size and potential challenges for future imaging biomarker studies may be gleaned from this pilot study.
Collapse
Affiliation(s)
- Jiayi Huang
- Department of Radiation Oncology, Washington University School of Medicine, Saint Louis, Missouri, United States of America
| | - Mikhail Milchenko
- Mallinckrodt Institute of Radiology, Washington University School of Medicine, Saint Louis, Missouri, United States of America
| | - Yuan J Rao
- Department of Radiation Oncology, Washington University School of Medicine, Saint Louis, Missouri, United States of America
| | - Pamela LaMontagne
- Mallinckrodt Institute of Radiology, Washington University School of Medicine, Saint Louis, Missouri, United States of America
| | - Christopher Abraham
- Department of Radiation Oncology, Washington University School of Medicine, Saint Louis, Missouri, United States of America
| | - Clifford G Robinson
- Department of Radiation Oncology, Washington University School of Medicine, Saint Louis, Missouri, United States of America
| | - Yi Huang
- Department of Radiation Oncology, Washington University School of Medicine, Saint Louis, Missouri, United States of America
| | - Joshua S Shimony
- Mallinckrodt Institute of Radiology, Washington University School of Medicine, Saint Louis, Missouri, United States of America
| | - Keith M Rich
- Department of Neurosurgery, Washington University School of Medicine, Saint Louis, Missouri, United States of America
| | - Tammie Benzinger
- Mallinckrodt Institute of Radiology, Washington University School of Medicine, Saint Louis, Missouri, United States of America
| |
Collapse
|
3
|
Wang Q, Pérez-Carrillo GJG, Ponisio MR, LaMontagne P, Dahiya S, Marcus DS, Milchenko M, Shimony J, Liu J, Chen G, Salter A, Massoumzadeh P, Miller-Thomas MM, Rich KM, McConathy J, Benzinger TLS, Wang Y. Heterogeneity Diffusion Imaging of gliomas: Initial experience and validation. PLoS One 2019; 14:e0225093. [PMID: 31725772 PMCID: PMC6855653 DOI: 10.1371/journal.pone.0225093] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/03/2019] [Accepted: 10/29/2019] [Indexed: 12/05/2022] Open
Abstract
Objectives Primary brain tumors are composed of tumor cells, neural/glial tissues, edema, and vasculature tissue. Conventional MRI has a limited ability to evaluate heterogeneous tumor pathologies. We developed a novel diffusion MRI-based method—Heterogeneity Diffusion Imaging (HDI)—to simultaneously detect and characterize multiple tumor pathologies and capillary blood perfusion using a single diffusion MRI scan. Methods Seven adult patients with primary brain tumors underwent standard-of-care MRI protocols and HDI protocol before planned surgical resection and/or stereotactic biopsy. Twelve tumor sampling sites were identified using a neuronavigational system and recorded for imaging data quantification. Metrics from both protocols were compared between World Health Organization (WHO) II and III tumor groups. Cerebral blood volume (CBV) derived from dynamic susceptibility contrast (DSC) perfusion imaging was also compared with the HDI-derived perfusion fraction. Results The conventional apparent diffusion coefficient did not identify differences between WHO II and III tumor groups. HDI-derived slow hindered diffusion fraction was significantly elevated in the WHO III group as compared with the WHO II group. There was a non-significantly increasing trend of HDI-derived tumor cellularity fraction in the WHO III group, and both HDI-derived perfusion fraction and DSC-derived CBV were found to be significantly higher in the WHO III group. Both HDI-derived perfusion fraction and slow hindered diffusion fraction strongly correlated with DSC-derived CBV. Neither HDI-derived cellularity fraction nor HDI-derived fast hindered diffusion fraction correlated with DSC-derived CBV. Conclusions Conventional apparent diffusion coefficient, which measures averaged pathology properties of brain tumors, has compromised accuracy and specificity. HDI holds great promise to accurately separate and quantify the tumor cell fraction, the tumor cell packing density, edema, and capillary blood perfusion, thereby leading to an improved microenvironment characterization of primary brain tumors. Larger studies will further establish HDI’s clinical value and use for facilitating biopsy planning, treatment evaluation, and noninvasive tumor grading.
Collapse
Affiliation(s)
- Qing Wang
- Department of Radiology, Washington University in St. Louis, St. Louis, Missouri, United States of America
| | | | - Maria Rosana Ponisio
- Department of Radiology, Washington University in St. Louis, St. Louis, Missouri, United States of America
| | - Pamela LaMontagne
- Department of Radiology, Washington University in St. Louis, St. Louis, Missouri, United States of America
| | - Sonika Dahiya
- Department of Pathology and Immunology, Washington University in St. Louis, St. Louis, Missouri, United States of America
| | - Daniel S. Marcus
- Department of Radiology, Washington University in St. Louis, St. Louis, Missouri, United States of America
| | - Mikhail Milchenko
- Department of Radiology, Washington University in St. Louis, St. Louis, Missouri, United States of America
| | - Joshua Shimony
- Department of Radiology, Washington University in St. Louis, St. Louis, Missouri, United States of America
| | - Jingxia Liu
- Department of Surgery, Washington University in St. Louis, St. Louis, Missouri, United States of America
| | - Gengsheng Chen
- Department of Radiology, Washington University in St. Louis, St. Louis, Missouri, United States of America
| | - Amber Salter
- Department of Biostatistics, Washington University in St. Louis, St. Louis, Missouri, United States of America
| | - Parinaz Massoumzadeh
- Department of Radiology, Washington University in St. Louis, St. Louis, Missouri, United States of America
| | - Michelle M. Miller-Thomas
- Department of Radiology, Washington University in St. Louis, St. Louis, Missouri, United States of America
| | - Keith M. Rich
- Department of Neurosurgery, Washington University in St. Louis, St. Louis, Missouri, United States of America
| | - Jonathan McConathy
- Department of Radiology, Division of Molecular Imaging and Therapeutics, University of Alabama at Birmingham, Birmingham, Alabama, United States of America
| | - Tammie L. S. Benzinger
- Department of Radiology, Washington University in St. Louis, St. Louis, Missouri, United States of America
| | - Yong Wang
- Department of Radiology, Washington University in St. Louis, St. Louis, Missouri, United States of America
- Department of Obstetrics and Gynecology, Washington University in St. Louis, St. Louis, Missouri, United States of America
- * E-mail:
| |
Collapse
|
4
|
Hsu W, Park S, Kahn CE. Sensor, Signal, and Imaging Informatics. Yearb Med Inform 2017; 26:120-124. [PMID: 29063550 DOI: 10.15265/iy-2017-019] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/24/2022] Open
Abstract
Objective: To summarize significant contributions to sensor, signal, and imaging informatics published in 2016. Methods: We conducted an extensive search using PubMed® and Web of Science® to identify the scientific contributions published in 2016 that addressed sensors, signals, and imaging in medical informatics. The three section editors selected 15 candidate best papers by consensus. Each candidate article was reviewed by the section editors and at least two other external reviewers. The final selection of the six best papers was conducted by the editorial board of the Yearbook. Results: The selected papers of 2016 demonstrate the important scientific advances in management and analysis of sensor, signal, and imaging information. Conclusion: The growing volume of signal and imaging data provides exciting new challenges and opportunities for research in medical informatics. Evolving technologies provide faster and more effective approaches for pattern recognition and diagnostic evaluation. The papers selected here offer a small glimpse of the high-quality scientific work published in 2016 in the domain of sensor, signal, and imaging informatics.
Collapse
|