Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Oct 22;24(1):285.
doi: 10.1186/s12880-024-01455-6.

Spatial attention-based CSR-Unet framework for subdural and epidural hemorrhage segmentation and classification using CT images

Nafees Ahmed S  1 , Prakasam P  2
Affiliations

Spatial attention-based CSR-Unet framework for subdural and epidural hemorrhage segmentation and classification using CT images

Nafees Ahmed S et al. BMC Med Imaging. .

Abstract

Background: Automatic diagnosis and brain hemorrhage segmentation in Computed Tomography (CT) may be helpful in assisting the neurosurgeon in developing treatment plans that improve the patient's chances of survival. Because medical segmentation of images is important and performing operations manually is challenging, many automated algorithms have been developed for this purpose, primarily focusing on certain image modalities. Whenever a blood vessel bursts, a dangerous medical condition known as intracranial hemorrhage (ICH) occurs. For best results, quick action is required. That being said, identifying subdural (SDH) and epidural haemorrhages (EDH) is a difficult task in this field and calls for a new, more precise detection method.

Methods: This work uses a head CT scan to detect cerebral bleeding and distinguish between two types of dural hemorrhages using deep learning techniques. This paper proposes a rich segmentation approach to segment both SDH and EDH by enhancing segmentation efficiency with a better feature extraction procedure. This method incorporates Spatial attention- based CSR (convolution-SE-residual) Unet, for rich segmentation and precise feature extraction.

Results: According to the study's findings, the CSR based Spatial network performs better than the other models, exhibiting impressive metrics for all assessed parameters with a mean dice coefficient of 0.970 and mean IoU of 0.718, while EDH and SDH dice scores are 0.983 and 0.969 respectively.

Conclusions: The CSR Spatial network experiment results show that it can perform well regarding dice coefficient. Furthermore, Spatial Unet based on CSR may effectively model the complicated in segmentations and rich feature extraction and improve the representation learning compared to alternative deep learning techniques, of illness and medical treatment, to enhance the meticulousness in predicting the fatality.

Keywords: Classification; Deep Learning; Epidural hemorrhage; Intracranial hemorrhage; Segmentation; Subdural hemorrhage.

PubMed Disclaimer

Conflict of interest statement

The authors declare no competing interests.

Figures

Fig. 1
Fig. 1
Subdural and Epidural Hemorrhage [5]
Fig. 2
Fig. 2
Framework of the proposed model CSR-SAM-UNet
Fig. 3
Fig. 3
Comparison with enhancement (CLAHE) (a) Images before using CLAHE (b)Images after using CLAHE
Fig. 4
Fig. 4
Balancing based on SMOTE
Fig. 5
Fig. 5
Comparison with SMOTE (a) Images before using SMOTE (b)Images after using SMOTE
Fig. 6
Fig. 6
Spatial attention- based CSR-Unet architecture
Fig. 7
Fig. 7
CSR module
Fig. 8
Fig. 8
Spatial attention module
None
Algorithm 1. Spatial Attention- based CSR Unet training process
Fig. 9
Fig. 9
Model training, testing graph in loss & accuracy
Fig. 10
Fig. 10
(a) Actual image comparison with a resized image (b) Actual mask comparison with a resized mask (c) Actual image comparison with CLAHE & Gamma applied image
Fig. 11
Fig. 11
Depicts the segmented instances of EDH represented with input, ground truth, and prediction along with an overlaid image are given as (a)input image of EDH (b) ground truth (c) prediction (d) overlaid image
Fig. 12
Fig. 12
Depicts the segmented instances of SDH represented with input, ground truth, and prediction along with an overlaid image are given as (a) input image of SDH (b) ground truth (c) prediction (d) overlaid image
Fig. 13
Fig. 13
Confusion matrix for dural hemorrhage classification
Fig. 14
Fig. 14
Precision, F1 -score, recall chart
Fig. 15
Fig. 15
Binary ROC curve on the testing dataset
See this image and copyright information in PMC

References

    1. Xi G, Keep RF, Hoff JT. Mechanisms of brain injury after intracerebral haemorrhage. Lancet Neurol. 2006;5(1):53–63. - PubMed
    1. Mendelow AD, Gregson BA, Rowan EN, Murray GD, Gholkar A, Mitchell PM. Early surgery versus initial conservative treatment in patients with spontaneous supratentorial lobar intracerebral haematomas (STICH II): a randomised trial. Lancet. 2013;382(9890):397–408. - PMC - PubMed
    1. Foreman KJ, Marquez N, Dolgert A, Fukutaki K, Fullman N, McGaughey M, Pletcher MA, Smith AE, Tang K, Yuan CW, Brown JC. Forecasting life expectancy, years of life lost, and all-cause and cause-specific mortality for 250 causes of death: reference and alternative scenarios for 2016–40 for 195 countries and territories. Lancet. 2018;392(10159):2052–90. - PMC - PubMed
    1. Chang CS, Chang TS, Yan JL, Ko L. All attention U-NET for semantic segmentation of intracranial hemorrhages in head CT images. In: 2022 IEEE Biomedical Circuits and Systems Conference (BioCAS). USA: IEEE; 2022. p. 600–4.
    1. Skalski M. Diagram - intracranial hemorrhage. Case study, Radiopaedia.org. 10.53347/rID-21542. Accessed 25 May 2024.

MeSH terms