Brain MRI-Based Artificial Intelligence Software in Patients with Neurodegenerative Diseases: Current Status

and reliable assessment and precise detection are important for the early diagnosis of neurodegenerative diseases. Artificial intelligence (AI) using brain MRI applied to the study of neurodegenerative diseases could promote early diagnosis and optimal decisions for treatment plans. MRI-based AI software have been developed and studied worldwide. Representatively, there are MRI-based volumetry and segmentation software. In this review, we present the development process of brain volumetry analysis software in neurodegenerative diseases, currently used and developed AI software for neurodegenerative disease in the Republic of Korea, probable uses of AI in the future, and AI software limitations.

Current Updates and Unmet Needs of Brain MRI-Based Artificial Intelligence Software for Patients With Neurodegenerative Diseases in the Republic of Korea

In aging societies, incidences of neurodegenerative diseases such as Alzheimer’s disease and Parkinson’s disease are increasing. Neurodegenerative diseases are bringing main challenges to the healthcare system in today’s world. Analyzing characteristic imaging patterns of patients with neurodegenerative diseases is important. Since objective and reliable imaging assessments and precise analyses can lead to early diagnosis of neurodegenerative diseases, imaging patterns are being increasingly investigated. Artificial intelligence (AI) analyzing brain MRI has been applied to neurodegenerative diseases, providing added value in early diagnosis. MRI-based AI software has been developed and studied worldwide, with some AI-based software already being used in actual clinical care. Currently, there are MRI-based volumetry and segmentation software available. There is also an unmet demand for the application of AI in neurodegenerative diseases. Here, we review current status and unmet needs for application of AI in neurodegenerative diseases. We also discuss current limitations of AI, suggestion for AI-based software, and how it can be clinically applied in the future.

Behavior, PET and Histology in Novel Regimen of MPTP Marmoset Model of Parkinson's Disease for Long-Term Stem Cell Therapy

Stem cell technologies are particularly attractive in Parkinson's disease (PD) research although they occasionally need long-term treatment for anti-parkinsonian activity. Unfortunately, 1-methyl-4-phenyl-1,2,3,6-tetrahydropyridine (MPTP) widely used as a model for PD has several limitations, including the risk of dose-dependent mortality and the difficulty of maintenance of PD symptoms during the whole experiment period. Therefore, we tested if our novel MPTP regimen protocol (2 mg/kg for 2 consecutive days and 1 mg/kg for next 3 consecutive days) can be maintained stable parkinsonism without mortality for long-term stem cell therapy. For this, we used small-bodied common marmoset monkeys (Callithrix jacchus) among several nonhuman primates showing high anatomical, functional, and behavioral similarities to humans. Along with no mortality, the behavioral changes involved in PD symptoms were maintained for 32 weeks. Also, the loss of jumping ability of the MPTP-treated marmosets in the Tower test was not recovered by 32 weeks. Positron emission tomography (PET) analysis revealed that remarkable decreases of bindings of ¹⁸F-FP-CIT were observed at the striatum of the brains of the marmosets received MPTP during the full period of the experiment for 32 weeks. In the substantia nigra of the marmosets, the loss of tyrosine hydroxylase (TH) immunoreactivity was also observed at 32 weeks following the MPTP treatment. In conclusion, our low-dose MPTP regimen protocol was found to be stable parkinsonism without mortality as evidenced by behavior, PET, and TH immunohistochemistry. This result will be useful for evaluation of possible long-term stem cell therapy for anti-parkinsonian activity.

In-Vivo Proton Magnetic Resonance Spectroscopy of 2-Hydroxyglutarate in Isocitrate Dehydrogenase-Mutated Gliomas: A Technical Review for Neuroradiologists

The diagnostic and prognostic potential of an onco-metabolite, 2-hydroxyglutarate (2HG) as a proton magnetic resonance spectroscopy (1H-MRS) detectable biomarker of the isocitrate dehydrogenase (IDH)-mutated (IDH-MT) gliomas has drawn attention of neuroradiologists recently. However, due to severe spectral overlap with background signals, quantification of 2HG can be very challenging. In this technical review for neuroradiologists, first, the biochemistry of 2HG and its significance in the diagnosis of IDH-MT gliomas are summarized. Secondly, various 1H-MRS methods used in the previous studies are outlined. Finally, wereview previous in vivo studies, and discuss the current status of 1H-MRS in the diagnosis of IDH-MT gliomas.

Effect of Berberine on Cell Survival in the Developing Rat Brain Damaged by MK-801

Berberine is an isoquinoline alkaloid isolated from goldenthread, Coptidis Rhizoma and shown to have many biological and pharmacological effects. We previously reported that berberine promotes cell survival and differentiation of neural stem cells. To examine whether berberine has survival promoting effect on damaged neuronal cells, we generated a cellular model under oxidative stress and an neonatal animal model of degenerating brain disease by injecting MK-801. MK801, a noncompetitive antagonist of N-methyl-d-aspartate (NMDA) receptors, acts as a neurotoxin in developing rats by inhibiting NMDA receptors and induce neuronal cell death. We found that the survival rate of the SH-SY5Y cells under oxidative stress was increased by 287% and 344%, when treated with 1.5 and 3.0microg/ml berberine, respectively. In the developing rats injected by MK801, we observed that TUNEL positive apoptotic cells were outspread in entire brain. The cell death was decreased more than 3 fold in the brains of the MK-801-induced neurodegenerative animal model when berberine was treated to the model animals. This suggests that berberine promotes activity dependent cell survival mediated by NMDA receptor because berberine is known to activate neurons by blocking K+ current or lowering the threshold of the action potential. Taken together, berberine has neuroprotective effect on damaged neurons and neurodegenerating brains of neonatal animal model induced by MK-801 administration.