Authors: Qingqiu Li, Runtian Yuan, Junlin Hou, Jilan Xu, Yuejie Zhang, Rui Feng, Hao Chen
Published on: March 18, 2024
Impact Score: 8.0
Arxiv code: Arxiv:2403.11953
Summary
- What is new: The use of a straightforward model focusing solely on lesion-related areas in 3D CT scans for COVID-19 diagnosis.
- Why this is important: The need for more accurate diagnosis of COVID-19.
- What the research proposes: A model that analyzes 3D CT scans to remove non-lung parts and employs ResNeSt50 with pretrained weights for strong feature extraction.
- Results: Achieved a Macro F1 Score of 0.94 on the validation set, surpassing the baseline by 16%.
Technical Details
Technological frameworks used: ResNeSt50
Models used: 3D CT scan analysis model with COVID-19-specific prior knowledge
Data used: 3D CT scans
Potential Impact
Healthcare diagnostics, Medical Imaging, AI-driven diagnostic solutions
Want to implement this idea in a business?
We have generated a startup concept here: LungVision.
Leave a Reply