Grad-CAM helps interpret the deep learning models trained to classify multiple sclerosis types using clinical brain magnetic resonance imaging

2021 ◽  
Vol 353 ◽  
pp. 109098
Author(s):  
Yunyan Zhang ◽  
Daphne Hong ◽  
Daniel McClement ◽  
Olayinka Oladosu ◽  
Glen Pridham ◽  
...  
2021 ◽  
Vol 15 ◽  
Author(s):  
Yudan Ren ◽  
Shuhan Xu ◽  
Zeyang Tao ◽  
Limei Song ◽  
Xiaowei He

Naturalistic functional magnetic resonance imaging (NfMRI) has become an effective tool to study brain functional activities in real-life context, which reduces the anxiety or boredom due to difficult or repetitive tasks and avoids the problem of unreliable collection of brain activity caused by the subjects’ microsleeps during resting state. Recent studies have made efforts on characterizing the brain’s hierarchical organizations from fMRI data by various deep learning models. However, most of those models have ignored the properties of group-wise consistency and inter-subject difference in brain function under naturalistic paradigm. Another critical issue is how to determine the optimal neural architecture of deep learning models, as manual design of neural architecture is time-consuming and less reliable. To tackle these problems, we proposed a two-stage deep belief network (DBN) with neural architecture search (NAS) combined framework (two-stage NAS-DBN) to model both the group-consistent and individual-specific naturalistic functional brain networks (FBNs), which reflected the hierarchical organization of brain function and the nature of brain functional activities under naturalistic paradigm. Moreover, the test-retest reliability and spatial overlap rate of the FBNs identified by our model reveal better performance than that of widely used traditional methods. In general, our model provides a promising method for characterizing hierarchical spatiotemporal features under the natural paradigm.


2019 ◽  
Vol 27 (2) ◽  
pp. 235-243 ◽  
Author(s):  
N. Ziliotto ◽  
R. Zivadinov ◽  
M. Baroni ◽  
G. Marchetti ◽  
D. Jakimovski ◽  
...  

2021 ◽  
pp. 69-72
Author(s):  
Andrew McKeon

A 60-year-old woman with a history of Sjögren syndrome had an episode of painful left eye vision loss. Brain magnetic resonance imaging showed an arteriovenous malformation adjacent to the left ventricular atrium. Although this was considered an asymptomatic lesion, the patient underwent stereotactic radiosurgery to reduce the risk of future growth and hemorrhage. Within days of the surgery, speech disturbance and weakness of the right arm and leg developed. Examination indicated a subcortical language deficit and an upper motor pattern of paresis of right-sided limbs. Considered in the differential diagnosis were new hemorrhage from the arteriovenous malformation, ischemic stroke, radiation-induced necrosis, abscess, and demyelinating disease. Magnetic resonance imaging of the head with and without gadolinium contrast was used to evaluate for these possibilities. Brain magnetic resonance imaging after onset of speech and motor symptoms demonstrated new areas of confluent T2 signal abnormality in the brainstem and deep white matter of the left hemisphere, with some accompanying enhancement but without evidence of hemorrhage or acute stroke. Slow conduction was noted in the left optic nerve on visual evoked potentials. The patient was diagnosed with optic neuritis, with subsequent evolution to multiple sclerosis in the setting of radiosurgery. The patient received intravenous methylprednisolone with full recovery of language function and partial recovery of the hemiparesis, which improved with rehabilitation such that she could walk without a gait aid. Because the patient had more than 1 episode, she was treated with interferon beta-1a for further prevention of multiple sclerosis relapse. Chronic neurotoxicity leading to subcortical dementia occurs in approximately 25% of patients undergoing whole-brain radiotherapy. Histologically, demyelination, as well as necrosis, can be a prominent feature. Among patients with multiple sclerosis or a clinically isolated syndrome, the risk of demyelinating events appears to increase after brain radiotherapy, within the field of treatment.


Sign in / Sign up

Export Citation Format

Share Document