Spatial attention-based CSR-Unet framework for subdural and epidural hemorrhage segmentation and classification using CT images.
Classification
Deep Learning
Epidural hemorrhage
Intracranial hemorrhage
Segmentation
Subdural hemorrhage
Journal
BMC medical imaging
ISSN: 1471-2342
Titre abrégé: BMC Med Imaging
Pays: England
ID NLM: 100968553
Informations de publication
Date de publication:
22 Oct 2024
22 Oct 2024
Historique:
received:
06
08
2024
accepted:
07
10
2024
medline:
23
10
2024
pubmed:
23
10
2024
entrez:
22
10
2024
Statut:
epublish
Résumé
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. 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. 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. 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.
Sections du résumé
BACKGROUND
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
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
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
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.
Identifiants
pubmed: 39438833
doi: 10.1186/s12880-024-01455-6
pii: 10.1186/s12880-024-01455-6
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
285Informations de copyright
© 2024. The Author(s).
Références
Xi G, Keep RF, Hoff JT. Mechanisms of brain injury after intracerebral haemorrhage. Lancet Neurol. 2006;5(1):53–63.
pubmed: 16361023
doi: 10.1016/S1474-4422(05)70283-0
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.
pubmed: 23726393
pmcid: 3906609
doi: 10.1016/S0140-6736(13)60986-1
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.
pubmed: 30340847
pmcid: 6227505
doi: 10.1016/S0140-6736(18)31694-5
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.
Skalski M. Diagram - intracranial hemorrhage. Case study, Radiopaedia.org. https://doi.org/10.53347/rID-21542 . Accessed 25 May 2024.
Sun T, Yuan Y, Wu K, Zhou Y, You C, Guan J. Trends and patterns in the global burden of intracerebralhemorrhage: a comprehensive analysis from 1990 to 2019. Front Neurol. 2023;14:1241158.
pubmed: 38073625
pmcid: 10699537
doi: 10.3389/fneur.2023.1241158
Ahmed SN, Prakasam P. A systematic review on intracranial aneurysm and hemorrhage detection using machine learning and deep learning techniques. Progress Biophys Mol Biol. 2023;183:1–16.
doi: 10.1016/j.pbiomolbio.2023.07.001
Currie S, Saleem N, Straiton JA, Macmullen-Price J, Warren DJ, Craven IJ. Imaging assessment of traumatic brain injury. Postgrad Med J. 2016;92(1083):41–50.
pubmed: 26621823
doi: 10.1136/postgradmedj-2014-133211
Phan K, Moore JM, Griessenauer C, Dmytriw AA, Scherman DB, Sheik-Ali S, Adeeb N, Ogilvy CS, Thomas A, Rosenfeld JV. Craniotomy versus decompressivecraniectomy for acute subdural hematoma: systematic review and meta-analysis. World Neurosurg. 2017;101:677–85.
pubmed: 28315797
doi: 10.1016/j.wneu.2017.03.024
Gudigar A, Raghavendra U, Hegde A, Kalyani M, Ciaccio EJ, Acharya UR. Brain pathology identification using computer aided diagnostic tool: a systematic review. Comput Methods Programs Biomed. 2020;187:105205.
pubmed: 31786457
doi: 10.1016/j.cmpb.2019.105205
Lal NR, Murray UM, Eldevik OP, Desmond JS. Clinical consequences of misinterpretations of neuroradiologic CT scans by on-callradiology residents. Am J Neuroradiol. 2000;21(1):124–9.
pubmed: 10669236
pmcid: 7976358
Cho J, Park KS, Karki M, Lee E, Ko S, Kim JK, Lee D, Choe J, Son J, Kim M, Lee S. Improving sensitivity on identification and delineation of intracranial hemorrhage lesion using cascaded deep learning models. J Digit Imaging. 2019;32:450–61.
pubmed: 30680471
pmcid: 6499861
doi: 10.1007/s10278-018-00172-1
Tarnutzer AA, Lee SH, Robinson KA, Wang Z, Edlow JA, Newman-Toker DE, editors. ED misdiagnosis of cerebrovascular events in the era of modern neuroimaging: a meta-analysis. Neurology. 2017;88(15):1468-77.
Chandrasekar V, Ansari MY, Singh AV, Uddin S, Prabhu KS, Dash S, Al Khodor S, Terranegra A, Avella M, Dakua SP. Investigating the use of machine learning models to understand the drugs permeability across placenta. IEEE Access. 2023;11:52726–39.
doi: 10.1109/ACCESS.2023.3272987
Ansari MY, Chandrasekar V, Singh AV, Dakua SP. Re-routing drugs to blood brain barrier: a comprehensive analysis of machine learning approaches with fingerprint amalgamation and data balancing. IEEE Access. 2022;11:9890–906.
doi: 10.1109/ACCESS.2022.3233110
Ansari MY, Mangalote IA, Meher PK, Aboumarzouk O, Al-Ansari A, Halabi O, Dakua SP. Advancements in deep learning for B-mode ultrasound segmentation: a comprehensive review. In: IEEE Transactions on emerging topics in computational intelligence. 2024.
Ansari MY, Qaraqe M, Righetti R, Serpedin E, Qaraqe K. Unveiling the future of breast cancer assessment: a critical review on generative adversarial networks in elastography ultrasound. Front Oncol. 2023;13:1282536.
pubmed: 38125949
pmcid: 10731303
doi: 10.3389/fonc.2023.1282536
Ansari MY, Mangalote IA, Masri D, Dakua SP. Neural network-based fast liver ultrasound image segmentation. In: 2023 international joint conference on neural networks (IJCNN). USA: IEEE; 2023. p. 1–8.
Ansari MY, Qaraqe M, Charafeddine F, Serpedin E, Righetti R, Qaraqe K. Estimating age and gender from electrocardiogram signals: a comprehensive review of the past decade. Artif Intell Med. 2023;21:102690.
doi: 10.1016/j.artmed.2023.102690
Ansari MY, Qaraqe M, Righetti R, Serpedin E, Qaraqe K. Enhancing ECG-based heart age: impact of acquisition parameters and generalization strategies for varying signal morphologies and corruptions. Front Cardiovasc Med. 2024;11:1424585.
pubmed: 39027006
pmcid: 11254851
doi: 10.3389/fcvm.2024.1424585
McCulloch WS, Pitts W. A logical calculus of the ideas immanent in nervous activity. Bull Math Biophys. 1943;5:115–33.
doi: 10.1007/BF02478259
Yuh EL, Gean AD, Manley GT, Callen AL, Wintermark M. Computer-aided assessment of head computed tomography (CT) studies in patients with suspected traumatic brain injury. J Neurotrauma. 2008;25(10):1163–72.
pubmed: 18986221
doi: 10.1089/neu.2008.0590
Shahangian B, Pourghassem H. Automatic brain hemorrhage segmentation and classification algorithm based on weighted grayscale histogram feature in a hierarchical classification structure. Biocybern Biomed Eng. 2016;36(1):217–32.
doi: 10.1016/j.bbe.2015.12.001
Murugappan M, Bourisly AK, Prakash NB, Sumithra MG, Acharya UR. Automated semantic lung segmentation in chest CT images using deep neural network. Neural Comput Appl. 2023;35(21):15343–64.
pubmed: 37273912
pmcid: 10088735
doi: 10.1007/s00521-023-08407-1
Murugappan M, Prakash NB, Jeya R, Mohanarathinam A, Hemalakshmi GR, Mahmud M. A novel few-shot classification framework for diabetic retinopathy detection and grading. Measurement. 2022;200:111485.
doi: 10.1016/j.measurement.2022.111485
Prakash NB, Murugappan M, Hemalakshmi GR, Jayalakshmi M, Mahmud M. Deep transfer learning for COVID-19 detection and infection localization with superpixel based segmentation. Sustainable Cities Soc. 2021;75:103252.
doi: 10.1016/j.scs.2021.103252
Wang X, Shen T, Yang S, Lan J, Xu Y, Wang M, Zhang J, Han X. A deep learning algorithm for automatic detection and classification of acute intracranial hemorrhages in head CT scans. NeuroImage: Clin. 2021;32:102785.
pubmed: 34411910
doi: 10.1016/j.nicl.2021.102785
Umapathy S, Murugappan M, Bharathi D, Thakur M. Automated computer-aided detection and classification of intracranial hemorrhage using ensemble deep learning techniques. Diagnostics. 2023;13(18):2987.
pubmed: 37761354
pmcid: 10527774
doi: 10.3390/diagnostics13182987
Gençtürk TH, GülağIz FK, Kaya İ. Detection and segmentation of subdural hemorrhage on head CT images. IEEE Access. 2024;2:82235–46.
doi: 10.1109/ACCESS.2024.3411932
Lee JY, Kim JS, Kim TY, Kim YS. Detection and classification of intracranial haemorrhage on CT images using a novel deep-learning algorithm. Sci Rep. 2020;10(1):20546.
pubmed: 33239711
pmcid: 7689498
doi: 10.1038/s41598-020-77441-z
Chang PD, Kuoy E, Grinband J, Weinberg BD, Thompson M, Homo R, Chen J, Abcede H, Shafie M, Sugrue L, Filippi CG. Hybrid 3D/2D convolutional neural network for hemorrhage evaluation on head CT. Am J Neuroradiol. 2018;39(9):1609–16.
pubmed: 30049723
pmcid: 6128745
doi: 10.3174/ajnr.A5742
Deng B, Zhou Y, Guan J, Yuan L, Han J, Yang B. Convolutional neural networks for the distinction of subdural and epidural hematoma. J Innov Social Sci Res. 2022;9(4):193–143.
doi: 10.53469/jissr.2022.09(04).28
Maya BS, Asha T. Segmentation and classification of brain hemorrhage using U-net and CapsNet. J Seybold Rep. 2017;42(1):60–88.
Grewal M, Srivastava MM, Kumar P, Varadarajan S. Radnet: Radiologist level accuracy using deep learning for hemorrhage detection in ct scans. In 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018). USA: IEEE; 2018. p. 281–4.
Ronneberger O, Fischer P, Brox T. U-net: convolutional networks for biomedical image segmentation. In: Medical image computing and computer-assisted intervention–MICCAI 2015: 18th international conference, Munich, Germany, October 5–9, 2015, proceedings, part III 18. Cham: Springer International Publishing; 2015. p. 234–41.
Xu J, Zhang R, Zhou Z, Wu C, Gong Q, Zhang H, Wu S, Wu G, Deng Y, Xia C, Ma J. Deep network for the automatic segmentation and quantification of intracranial hemorrhage on CT. Front NeuroSci. 2021;14:541817.
pubmed: 33505231
pmcid: 7832216
doi: 10.3389/fnins.2020.541817
Mazhari A, Allahgholi A, Shafieian M. Automated Detection of SDH and EDH due to TBI from CT-scan images using CNN. In 2023 30th National and 8th International Iranian Conference on Biomedical Engineering (ICBME). USA: IEEE; 2023. p. 164–70.
Phaphuangwittayakul A, Guo Y, Ying F, Dawod AY, Angkurawaranon S, Angkurawaranon C. An optimal deep learning framework for multi-type hemorrhagic lesions detection and quantification in head CT images for traumatic brain injury. Appl Intell. 2022;1:1–9.
Angkurawaranon S, Sanorsieng N, Unsrisong K, Inkeaw P, Sripan P, Khumrin P, Angkurawaranon C, Vaniyapong T, Chitapanarux I. A comparison of performance between a deep learning model with residents for localization and classification of intracranial hemorrhage. Sci Rep. 2023;13(1):9975.
pubmed: 37340038
pmcid: 10282020
doi: 10.1038/s41598-023-37114-z
Huang H, Lin L, Tong R, Hu H, Zhang Q, Iwamoto Y, Han X, Chen YW, Wu J. Unet 3+: A full-scale connected unet for medical image segmentation. InICASSP 2020–2020 IEEE international conference on acoustics, speech and signal processing (ICASSP). USA: IEEE; 2020. p. 1055–9.
Chang JR, Chen YS. Pyramid stereo matching network. In: In Proceedings of the IEEE conference on computer vision and pattern recognition. 2018. p. 5410–8.
Rifai AM, Raharjo S, Utami E, Ariatmanto D. Analysis for diagnosis of pneumonia symptoms using chest X-ray based on MobileNetV2 models with image enhancement using white balance and contrast limited adaptive histogram equalization (CLAHE). Biomed Signal Process Control. 2024;90:105857.
doi: 10.1016/j.bspc.2023.105857
Ansari MY, Yang Y, Meher PK, Dakua SP. Dense-PSP-UNet: a neural network for fast inference liver ultrasound segmentation. Comput Biol Med. 2023;153:106478.
pubmed: 36603437
doi: 10.1016/j.compbiomed.2022.106478
Ansari MY, Yang Y, Balakrishnan S, Abinahed J, Al-Ansari A, Warfa M, Almokdad O, Barah A, Omer A, Singh AV, Meher PK. A lightweight neural network with multiscale feature enhancement for liver CT segmentation. Sci Rep. 2022;12(1):14153.
pubmed: 35986015
pmcid: 9391485
doi: 10.1038/s41598-022-16828-6
Albahra S, Gorbett T, Robertson S, D’Aleo G, Kumar SV, Ockunzzi S, Lallo D, Hu B, Rashidi HH. Artificial intelligence and machine learning overview in pathology & laboratory medicine: a general review of data preprocessing and basic supervised concepts. Semin Diagn Pathol 2023;40(2):71–87. WB Saunders.
pubmed: 36870825
doi: 10.1053/j.semdp.2023.02.002
Hayati M, Muchtar K, Maulina N, Syamsuddin I, Elwirehardja GN, Pardamean B. Impact of CLAHE-based image enhancement for diabetic retinopathy classification through deep learning. Procedia Comput Sci. 2023;216:57–66.
doi: 10.1016/j.procs.2022.12.111
Haddadi YR, Mansouri B, Khodja FZ. A novel medical image enhancement algorithm based on CLAHE and pelican optimization. Multimedia Tools Appl. 2024;5:1–20.
Gholampour S. Impact of nature of Medical Data on Machine and Deep Learning for Imbalanced datasets: clinical validity of SMOTE is questionable. Mach Learn Knowl Extr. 2024;6(2):827–41.
doi: 10.3390/make6020039
Moghtaderi S, Yaghoobian O, Wahid KA, Lukong KE. Endoscopic image enhancement: Wavelet transform and guided Filter decomposition-based Fusion Approach. J Imaging. 2024;10(1):28.
pubmed: 38276320
pmcid: 10816908
doi: 10.3390/jimaging10010028
Ahmad I, Farooque G, Liu Q, Hadi F, Xiao L. MSTSENet: Multiscale spectral–spatial transformer with squeeze and excitation network for hyperspectral image classification. Eng Appl Artif Intell. 2024;134:108669.
doi: 10.1016/j.engappai.2024.108669
Roy AG, Navab N, Wachinger C. Concurrent spatial and channel ‘squeeze & excitation’ in fully convolutional networks. In Medical Image Computing and Computer Assisted Intervention–MICCAI. 2018: 21st International Conference, Granada, Spain, September 16–20, 2018, Proceedings, Part I 2018. Cham: Springer International Publishing; 2018. p. 421–9.
Wu S, Yu H, Li C, Zheng R, Xia X, Wang C, Wang H. A coarse-to-fine fusion network for small liver tumor detection and segmentation: a real-world study. Diagnostics. 2023;13(15):2504.
pubmed: 37568868
pmcid: 10417427
doi: 10.3390/diagnostics13152504
He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: InProceedings of the IEEE conference on computer vision and pattern recognition. 2016. p. 770–8.
Siuly S, Guo Y, Alcin OF, Li Y, Wen P, Wang H. Exploring deep residual network based features for automatic schizophrenia detection from EEG. Phys Eng Sci Med. 2023;46(2):561–74.
pubmed: 36947384
pmcid: 10209282
doi: 10.1007/s13246-023-01225-8
He K, Zhang X, Ren S, Sun J. Identity mappings in deep residual networks. In: Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part IV 14. Cham: Springer International Publishing; 2016. p. 630–45.
Liu H, Huang J, Li Q, Guan X, Tseng M. A deep convolutional neural network for the automatic segmentation of glioblastoma brain tumor: joint spatial pyramid module and attention mechanism network. Artif Intell Med. 2024;148: 102776.
pubmed: 38325925
doi: 10.1016/j.artmed.2024.102776
Guo C, Szemenyei M, Yi Y, Wang W, Chen B, Fan C. Sa-unet: spatial attention u-net for retinal vessel segmentation. In: 2020 25th international conference on pattern recognition (ICPR). USA: IEEE; 2021. p. 1236–42.
Zhai X, Chen M, Esfahani SS, Amira A, Bensaali F, Abinahed J, Dakua S, Richardson RA, Coveney PV. Heterogeneous system-on-chip-based Lattice-Boltzmann visual simulation system. IEEE Syst J. 2019;14(2):1592–601.
doi: 10.1109/JSYST.2019.2952459
Zhai X, Amira A, Bensaali F, Al-Shibani A, Al‐Nassr A, El‐Sayed A, Eslami M, Dakua SP, Abinahed J. ZynqSoC based acceleration of the lattice boltzmann method. Concurr Comput. 2019;31(17):e5184.
doi: 10.1002/cpe.5184
Zhai X, Eslami M, Hussein ES, Filali MS, Shalaby ST, Amira A, Bensaali F, Dakua S, Abinahed J, Al-Ansari A, Ahmed AZ. Real-time automated image segmentation technique for cerebral aneurysm on reconfigurable system-on-chip. J Comput Sci. 2018;27:35–45.
doi: 10.1016/j.jocs.2018.05.002
Duchi J, Hazan E, Singer Y. Adaptive subgradient methods for online learning and stochastic optimization. J Mach Learn Res. 2011;12:2121–59.
Nizarudeen S, Shunmugavel GR. Multi-layer ResNet-DenseNet architecture in consort with the XgBoost classifier for intracranial hemorrhage (ICH) subtype detection and classification. J Intell Fuzzy Syst. 2023;44(2):2351–66.
doi: 10.3233/JIFS-221177
Hilal AM, Alabdan R, Othman MT, Hassine SB, Al-Wesabi FN, Rizwanullah M, Yaseen I, Motwakel A. Modelling of biosignal based decision making model for intracranial haemorrhage diagnosis in IoT environment. Expert Syst. 2022;39(7):e12964.
doi: 10.1111/exsy.12964
Venugopal D, Jayasankar T, Sikkandar MY, Waly MI, Pustokhina IV, Pustokhin DA, Shankar K. Computers Mater Continua. 2021;68:3.
Xiao Y, Hou Y, Wang Z, Zhang Y, Li X, Hu K, Gao X. Multi-scale perception and feature refinement network for multi-class segmentation of intracerebral hemorrhage in CT images. Biomed Signal Process Control. 2024;88:105614.
doi: 10.1016/j.bspc.2023.105614
Ma Y, Ren F, Li W, Yu N, Zhang D, Li Y, Ke M. IHA-Net: an automatic segmentation framework for computer-tomography of tiny intracerebral hemorrhage based on improved attention U-net. Biomed Signal Process Control. 2023;80:104320.
doi: 10.1016/j.bspc.2022.104320
Wang H, Wang X. MSRL-Net: an automatic segmentation of intracranial hemorrhage for CT images based on the U-Net framework. Appl Sci. 2023;13(21):11781.
doi: 10.3390/app132111781
Mehendale DN, Gupta P, Rajadhyaksha N, Dagha A, Hundiwala M, Paretkar A, Chavan S, Mishra T. A graphical approach for brain haemorrhage segmentation. arXiv preprint arXiv:2202.06876. 2022.