Back

Detecting orientation of Brain MR scans using deep learning

Singhal, C.; Gupta, N.; Stein, A.; Zhou, Q.; Chen, L.; Shih, G.

2021-08-24 neurology
10.1101/2021.08.17.21262189
Show abstract

AO_SCPLOWBSTRACTC_SCPLOWThere has been a steady escalation in the impact of Artificial Intelligence (AI) on Healthcare along with an increasing amount of progress being made in this field. While many entities are working on the development of significant deep learning models for the diagnosis of brain-related diseases, identifying precise images needed for model training and inference tasks is limited due to variation in DICOM fields which use free text to define things like series description, sequence and orientation [1]. Detecting the orientation of brain MR scans (Axial/Sagittal/Coronal) remains a challenge due to these variations caused by linguistic barriers, human errors and de-identification - essentially rendering the tags unreliable [2, 3, 4]. In this work, we propose a deep learning model that identifies the orientation of brain MR scans with near perfect accuracy.

Matching journals

The top 7 journals account for 50% of the predicted probability mass.

1
IEEE Access
based on 11 papers
Top 0.1%
12.3%
2
Scientific Reports
based on 701 papers
Top 17%
9.9%
3
PLOS ONE
based on 1737 papers
Top 52%
9.9%
4
NeuroImage
based on 36 papers
Top 0.7%
6.2%
5
Human Brain Mapping
based on 53 papers
Top 2%
5.2%
6
Frontiers in Artificial Intelligence
based on 11 papers
Top 0.3%
4.4%
7
PLOS Digital Health
based on 88 papers
Top 5%
2.9%
50% of probability mass above
8
NeuroImage: Clinical
based on 77 papers
Top 4%
2.5%
9
Frontiers in Neuroscience
based on 29 papers
Top 1%
2.4%
10
Computers in Biology and Medicine
based on 39 papers
Top 3%
2.4%
11
Frontiers in Neurology
based on 74 papers
Top 7%
2.4%
12
Scientific Data
based on 30 papers
Top 1.0%
2.4%
13
Epilepsia
based on 27 papers
Top 1.0%
2.3%
14
Informatics in Medicine Unlocked
based on 11 papers
Top 0.8%
2.3%
15
Journal of Alzheimer's Disease
based on 31 papers
Top 3%
1.7%
16
Sensors
based on 18 papers
Top 2%
1.5%
17
Diagnostics
based on 36 papers
Top 4%
1.3%
18
BMC Medical Informatics and Decision Making
based on 36 papers
Top 6%
1.3%
19
Journal of NeuroEngineering and Rehabilitation
based on 14 papers
Top 2%
1.2%
20
npj Digital Medicine
based on 85 papers
Top 11%
1.2%
21
Neuro-Oncology Advances
based on 14 papers
Top 2%
1.2%
22
Brain and Behavior
based on 19 papers
Top 3%
1.2%
23
Brain Sciences
based on 19 papers
Top 2%
0.8%
24
International Journal of Medical Informatics
based on 25 papers
Top 6%
0.8%
25
Journal of Neural Engineering
based on 19 papers
Top 2%
0.8%
26
Brain Communications
based on 79 papers
Top 7%
0.8%
27
European Radiology
based on 11 papers
Top 3%
0.7%
28
Journal of Biomedical Informatics
based on 37 papers
Top 6%
0.7%
29
Heliyon
based on 57 papers
Top 14%
0.7%