Multi-Method Diagnosis of CT Images for Rapid Detection of Intracranial Hemorrhages Based on Deep and Hybrid Learning
Problem
Intracranial hemorrhage is dangerous with high mortality without rapid diagnosis, and CT images take long and require much expertise to analyze.
Why it matters
Delayed diagnosis and treatment of intracranial hemorrhage can be fatal.
What the AI did
Three proposed systems using pretrained deep learning models (GoogLeNet, ResNet-50, AlexNet) and hybrid networks automatically evaluate CT images to detect intracranial hemorrhages and support radiologists' decisions.
Results
not stated in source (abstract truncated before any accuracy figures)
Impact
Proposes automated CT-based hemorrhage detection systems to help radiologists, per abstract; metrics not shown.
Record
| Venue | Electronics |
|---|---|
| Published | 2022 |
| Work type | article |
| Authors | Badiea Abdulkarem Mohammed, Ebrahim Mohammed Senan, Zeyad Ghaleb Al-Mekhlafi, Taha Hussein Rassem, Nasrin M. Makbol, Adwan Alanazi, Tariq S. Almurayziq, Fuad Abdulgaleel Abdoh Ghaleb et al. |
| Citations | 41 (OpenAlex, at import time) |
| References | 49 |
| Model or method | GoogLeNet, ResNet-50, AlexNet, plus hybrid deep learning networks |
| Organization | not stated in source |
| Primary source | https://doi.org/10.3390/electronics11152460 |
| Open access | gold |
| Keywords | intracranial hemorrhage, CT imaging, deep learning, GoogLeNet, ResNet-50, AlexNet |
Importance rating
significant — thousands to millions affected
Abstract states intracranial hemorrhage is very dangerous with high mortality without rapid diagnosis; automated CT analysis addresses a serious, widespread medical need.