Back

Enhancing Radiographic Diagnosis: CycleGAN-based methods for reducing cast shadow artifacts in wrist radiographs

2024-10-17 radiology and imaging Title + abstract only
View on medRxiv
Show abstract

ObjectiveWe extend existing techniques by using generative adversarial network (GAN) models to reduce the appearance of cast shadows in radiographs across various age groups. Materials and MethodsWe retrospectively collected 12000 adult and pediatric wrist radiographs, evenly divided between those with and without casts. The test subset consisted of 100 radiographs with cast and 100 without cast. We extended the results from a previous study that employed CycleGAN by enhancing the model using a...

Predicted journal destinations

1
Scientific Reports
701 training papers
Top 0.9% 24.2%
2
PLOS ONE
1737 training papers
Top 35% 19.3%
3
Computers in Biology and Medicine
39 training papers
#1 10.2%
4
PLOS Digital Health
88 training papers
Top 5% 5.5%
5
npj Digital Medicine
85 training papers
Top 6% 4.2%
6
Scientific Data
30 training papers
Top 0.5% 2.1%
7
NeuroImage
36 training papers
Top 2% 2.1%
8
Diagnostics
36 training papers
Top 0.9% 2.1%
9
Sensors
18 training papers
Top 0.6% 1.7%
10
Nature Communications
483 training papers
Top 41% 1.7%
11
Human Brain Mapping
53 training papers
Top 5% 1.7%
12
Archives of Clinical and Biomedical Research
18 training papers
#1 1.5%
13
Imaging Neuroscience
18 training papers
Top 1% 1.5%
14
NeuroImage: Clinical
77 training papers
Top 9% 1.3%
15
BMJ Open
553 training papers
Top 58% 1.3%
16
eLife
262 training papers
Top 43% 1.0%
17
Frontiers in Oncology
34 training papers
Top 6% 0.8%
18
Heliyon
57 training papers
Top 12% 0.8%
19
Journal of Clinical Medicine
77 training papers
Top 21% 0.8%
20
Cureus
64 training papers
Top 20% 0.8%
21
Brain and Behavior
19 training papers
Top 4% 0.5%
22
Cancers
57 training papers
Top 9% 0.5%
23
Alzheimer's Research & Therapy
31 training papers
Top 7% 0.5%
24
Frontiers in Neuroscience
29 training papers
Top 8% 0.5%
25
BMC Cancer
21 training papers
Top 7% 0.5%
26
PLOS Computational Biology
141 training papers
Top 17% 0.5%