The role of artificial intelligence and machine learning in harmonization of high-resolution post-mortem MRI (virtopsy) with respect to brain microstructure

被引：18
作者：
O’Sullivan S. [1 ]
Heinsen H. [1 ,2 ,3 ]
Grinberg L.T. [1 ,2 ,4 ,5 ]
Chimelli L. [6 ]
Amaro E., Jr. [3 ]
do Nascimento Saldiva P.H. [1 ,7 ]
Jeanquartier F. [8 ]
Jean-Quartier C. [8 ]
da Graça Morais Martin M. [3 ]
Sajid M.I. [9 ]
Holzinger A. [8 ]
机构：
[1] Department of Pathology, Faculdade de Medicina, Universidade de Sao Paulo, São Paulo
[2] Morphological Brain Research Unit, University of Würzburg, Würzburg
[3] Institute of Radiology, Faculdade de Medicina, Universidade de Sao Paulo, São Paulo
[4] Aging Brain Project, Department of Pathology, Faculdade de Medicina, Universidade de Sao Paulo, São Paulo
[5] Albert Einstein Instituto Israelita de Ensino e Pesquisa, São Paulo
[6] Laboratory of Neuropathology, State Institute of Brain, Rio de Janeiro
[7] Institute of Advanced Studies, Universidade de Sao Paulo, São Paulo
[8] Holzinger Group, Institute for Medical Informatics and Statistics, Medical University of Graz, Graz
[9] Department of Upper GI Surgery, Wirral University Teaching Hospital, Birkenhead
来源：
Brain Informatics | 2019年 / 6卷 / 1期
基金：
美国国家卫生研究院;
关键词：
7 T post-mortem MRI; Brain mapping; Disector; Neurodegenerative diseases; Neuroimaging; Stereology;
D O I：
10.1186/s40708-019-0096-3
中图分类号：
学科分类号：
摘要：
Enhanced resolution of 7 T magnetic resonance imaging (MRI) scanners has considerably advanced our knowledge of structure and function in human and animal brains. Post-industrialized countries are particularly prone to an ever-increasing number of ageing individuals and ageing-associated neurodegenerative diseases. Neurodegenerative diseases are associated with volume loss in the affected brain. MRI diagnoses and monitoring of subtle volume changes in the ageing/diseased brains have the potential to become standard diagnostic tools. Even with the superior resolution of 7 T MRI scanners, the microstructural changes comprising cell types, cell numbers, and cellular processes, are still undetectable. Knowledge of origin, nature, and progression for microstructural changes are necessary to understand pathogenetic stages in the relentless neurodegenerative diseases, as well as to develop therapeutic tools that delay or stop neurodegenerative processes at their earliest stage. We illustrate the gap in resolution by comparing the identical regions of the post-mortem in situ 7 T MR images (virtual autopsy or virtopsy) with the histological observations in serial sections through the same brain. We also described the protocols and limitations associated with these comparisons, as well as the necessity of supercomputers and data management for “Big data”. Analysis of neuron and/or glial number by using a body of mathematical tools and guidelines (stereology) is time-consuming, cumbersome, and still restricted to trained human investigators. Development of tools based on machine learning (ML) and artificial intelligence (AI) could considerably accelerate studies on localization, onset, and progression of neuron loss. Finally, these observations could disentangle the mechanisms of volume loss into stages of reversible atrophy and/or irreversible fatal cell death. This AI- and ML-based cooperation between virtopsy and histology could bridge the present gap between virtual reality and neuropathology. It could also culminate in the creation of an imaging-associated comprehensive database. This database would include genetic, clinical, epidemiological, and technical aspects that could help to alleviate or even stop the adverse effects of neurodegenerative diseases on affected individuals, their families, and society. © 2019, The Author(s).
引用
收藏
相关论文
共 97 条
[1]  
Roberts L.W., Nolte K.B., Warner T.D., McCarty T., Rosenbaum L.S., Zumwalt R., Perceptions of the ethical acceptability of using medical examiner autopsies for research and education: a survey of forensic pathologists, Arch Pathol Lab Med, 124, 10, pp. 1485-1495, (2000)
[2]  
Clark M.J., Autopsy, The Lancet, 366, 9499, (2005)
[3]  
Hamza A., Declining rate of autopsies: implications for anatomic pathology residents, Autops Case Rep, 7, 4, pp. 1-2, (2017)
[4]  
Baumgartner A., The decline of the autopsy in rhode island and nationwide: past trends and future directions, R I Med J, 99, 10, pp. 36-38, (2016)
[5]  
Nemetz P.N., Tangalos E., Sands L.P., Fisher W.P., Newman W.P., Ec B., Attitudes toward the autopsy—an 8-state survey, Medscape Gen Med, 8, (2006)
[6]  
Kj D., The changing role of the autopsy: a social environmental perspective, Hum Pathol, 21, pp. 145-153, (1990)
[7]  
Jh S., Accounting for the professional work of pathologists performing autopsies, Arch Pathol Lab Med, 137, pp. 228-232, (2013)
[8]  
Bassat Q., Castillo P., Alonso P.L., Ordi J., Menendez C., Resuscitating the dying autopsy, PLoS Med, 13, (2016)
[9]  
Katz P.R., Seidel G., Home autopsies. Survey of physician attitudes and practice patterns, Arch Pathol Lab Med, 114, 2, pp. 145-147, (1990)
[10]  
Oluwasola A., Fawole O., Otegbayo J., Ogun G., Adebamowo C., Knowledge E.B.A.T.A., Attitude, and perceptions of doctors and relatives of the deceased, Arch Pathol Lab Med, 133, 78-82, pp. 1543-2165, (2009)
12345678910