An explainable deep-learning algorithm for the detection of acute intracranial haemorrhage from small datasets
By Hyunkwang Lee, Sehyo Yune, Mohammad Mansouri, Myeongchan Kim, Shahein H. Tajmir, Claude E. Guerrier, Sarah A. Ebert, Stuart R. Pomerantz, J. Romero, S. Kamalian and 3 more. Nature Biomedical Engineering, 2018
384 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Epidemiology, Neurology
View Paper: https://www.semanticscholar.org/paper/027b9a21d6ee849b3268c45df10a44cc3d7b7c24
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Hayit Greenspan
- Jianfeng Zhan
- Marinka Zitnik
- Gregor Stiglic
- Katrien Verbert
- Nino Fijacko
- Leona Cilar
- Primož Kocbek
Citations in the corpus
- RadImageNet: An Open Radiologic Deep Learning Research Dataset for Effective Transfer Learning (2022, methodology): “All images were resized to 224 3 224 pixels and used as the fibrotic lung disease (16), classification of skin cancer (17), and detection of acute intracranial hemorrhage (18).”
- Annotation-efficient deep learning for automatic medical image segmentation (2020, background): “…the reported successful applications, the performance of DNNs depends heavily on the Recent deep learning works have presented encouraging performance in handling certain types of imperfect datasets in isolation 41–45 but have not yet shown general applicability by addressing all three types.”
- Interpretability of machine learning‐based prediction models in healthcare (2020, background): “uring surgery (Lundberg, et al., 2018), which increased the anaesthesiologists anticipation of hypoxaemia events by 15%, or in the detection of acute intracranial haemorrhage from images of CT scans (Lee, et al., 2019), which was achieved via attention maps visualization, where areas were highlighte”
- A new direction to promote the implementation of artificial intelligence in natural clinical settings (2019, background): “Among them, the issues of reproducibility and interpretability attracted intensive attention from the AI researchers 31 , with many significant achievements 17,32 .”