Login Register Cart 0
Generic placeholder image

Current Pharmaceutical Design

Editor-in-Chief

ISSN (Print): 1381-6128
ISSN (Online): 1873-4286

Back
Journal Home About Journal Editorial Board Journal Insight Current Issue Volumes/Issues
Subscribe
Research Article

Transfer Learning of the ResNet-18 and DenseNet-121 Model Used to Diagnose Intracranial Hemorrhage in CT Scanning

Author(s): Qi Zhou, Wenjie Zhu, Fuchen Li, Mingqing Yuan, Linfeng Zheng* and Xu Liu*

Volume 28, Issue 4, 2022

Published on: 31 December, 2021

Page: [287 - 295] Pages: 9

DOI: 10.2174/1381612827666211213143357

Price: $65

conference banner
Abstract

Objective: The aim of the study was to verify the ability of the deep learning model to identify five subtypes and normal images in non-contrast enhancement CT of intracranial hemorrhage.

Methods: A total of 351 patients (39 patients in the normal group, 312 patients in the intracranial hemorrhage group) who underwent intracranial hemorrhage noncontrast enhanced CT were selected, obtaining 2768 images in total (514 images for the normal group, 398 images for the epidural hemorrhage group, 501 images for the subdural hemorrhage group, 497 images for the intraventricular hemorrhage group, 415 images for the cerebral parenchymal hemorrhage group, and 443 images for the subarachnoid hemorrhage group). Based on the diagnostic reports of two radiologists with more than 10 years of experience, the ResNet-18 and DenseNet-121 deep learning models were selected. Transfer learning was used. 80% of the data was used for training models, 10% was used for validating model performance against overfitting, and the last 10% was used for the final evaluation of the model. Assessment indicators included accuracy, sensitivity, specificity, and AUC values.

Results: The overall accuracy of ResNet-18 and DenseNet-121 models was obtained as 89.64% and 82.5%, respectively. The sensitivity and specificity of identifying five subtypes and normal images were above 0.80. The sensitivity of the DenseNet-121 model to recognize intraventricular hemorrhage and cerebral parenchymal hemorrhage was lower than 0.80, 0.73, and 0.76, respectively. The AUC values of the two deep learning models were found to be above 0.9.

Conclusion: The deep learning model can accurately identify the five subtypes of intracranial hemorrhage and normal images, and it can be used as a new tool for clinical diagnosis in the future.

Keywords: Deep learning, transfer learning, intracranial hemorrhage, ResNet, DenseNet diagnosis, CT scanning.

« Previous Next »
[1]
Heit JJ, Iv M, Wintermark M. Imaging of intracranial hemorrhage. J Stroke 2017; 19(1): 11-27.
[http://dx.doi.org/10.5853/jos.2016.00563] [PMID: 28030895]
[2]
Qureshi AI, Tuhrim S, Broderick JP, Batjer HH, Hondo H, Hanley DF. Spontaneous intracerebral hemorrhage. N Engl J Med 2001; 344(19): 1450-60.
[http://dx.doi.org/10.1056/NEJM200105103441907] [PMID: 11346811]
[3]
Elliott J, Smith M. The acute management of intracerebral hemorrhage: a clinical review. Anesth Analg 2010; 110(5): 1419-27.
[http://dx.doi.org/10.1213/ANE.0b013e3181d568c8] [PMID: 20332192]
[4]
Carney N, Totten AM, O’Reilly C. Guidelines for the management of severe traumatic brain injury, Fourth Edition. Neurosurgery 2017; 80(1): 6-15.
[5]
Strub WM, Leach JL, Tomsick T. Vagal. (2017) A Overnight preliminary head CT interpretations provided by residents: locations of misidentified intracranial hemorrhage. AJNR Am. J. Neuroradiol. 2007; 28(9): 1679-82.
[6]
LeCun Y, Bengio Y, Hinton G. Deep learning. Nature 2015; 521(7553): 436-44.
[7]
LeCun Y, Boser B, Denker JS, et al. Backpropagation applied to handwritten zip code recognition. Neural Comput 1989; 1(4): 541-51.
[http://dx.doi.org/10.1162/neco.1989.1.4.541]
[8]
Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv:14091556 2014.
[9]
He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. arXiv:151203385 2015.
[10]
Huang G, Liu Z. Laurens van der Maaten, Kilian Q. Deeply connected convolutional networks. Weinberger arXiv:160806993 2016.
[11]
Havaei M, Davy A, Warde-Farley D, et al. Brain tumor segmentation with deep neural networks. Med Image Anal 2017; 35: 18-31.
[http://dx.doi.org/10.1016/j.media.2016.05.004] [PMID: 27310171]
[12]
Kamnitsas K, Ledig C, Newcombe VFJ, et al. Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation. Med Image Anal 2017; 36: 61-78.
[http://dx.doi.org/10.1016/j.media.2016.10.004] [PMID: 27865153]
[13]
Avendi MR, Kheradvar A, Jafarkhani H. A combined deep-learning and deformable-model approach to fully automatic segmentation of the left ventricle in cardiac MRI. Med Image Anal 2016; 30: 108-19.
[http://dx.doi.org/10.1016/j.media.2016.01.005] [PMID: 26917105]
[14]
Shin HC, Roth HR, Gao M, et al. Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning. IEEE Trans Med Imaging 2016; 35(5): 1285-98.
[http://dx.doi.org/10.1109/TMI.2016.2528162] [PMID: 26886976]
[15]
Cheng PM, Malhi HS. Transfer learning with convolutional neural networks for classifcation of abdominal ultrasound images. J Digit Imaging 2017; 30(2): 234-43.
[http://dx.doi.org/10.1007/s10278-016-9929-2] [PMID: 27896451]
[16]
Du X, Tang R, Yin S, Zhang Y, Li S. Direct segmentation-based full quantification for left ventricle via deep multi-task regression learning network. IEEE J Biomed Health Inform 2019; 23(3): 942-8.
[http://dx.doi.org/10.1109/JBHI.2018.2879188] [PMID: 30387757]
[17]
Gulshan V, Peng L, Coram M, et al. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA 2016; 316(22): 2402-10.
[http://dx.doi.org/10.1001/jama.2016.17216] [PMID: 27898976]
[18]
Litjens G, Kooi T, Bejnordi BE, et al. A survey on deep learning in medical image analysis. Med Image Anal 2017; 42: 60-88.
[http://dx.doi.org/10.1016/j.media.2017.07.005] [PMID: 28778026]
[19]
Majkowska A, Mittal S, Steiner DF, et al. Chest radiograph interpretation with deep learning models: assessment with radiologist-adjudicated reference standards and population-adjusted evaluation. Radiology 2020; 294(2): 421-31.
[http://dx.doi.org/10.1148/radiol.2019191293] [PMID: 31793848]
[20]
Ye H, Gao F, Yin Y, et al. Precise diagnosis of intracranial hemorrhage and subtypes using a three-dimensional joint convolutional and recurrent neural network. Eur Radiol 2019; 29(11): 6191-201.
[http://dx.doi.org/10.1007/s00330-019-06163-2] [PMID: 31041565]
[21]
Kuo W, Hӓne C, Mukherjee P, Malik J, Yuh EL. Expert-level detection of acute intracranial hemorrhage on head computed tomography using deep learning. Proc Natl Acad Sci USA 2019; 116(45): 22737-45.
[http://dx.doi.org/10.1073/pnas.1908021116] [PMID: 31636195]
[22]
Chilamkurthy S, Ghosh R, Tanamala S. Development and validation of deep learning algorithms for detection of critical findings in head CT scans arXiv preprint arXiv:180305854 2018.
[23]
Ironside N, Chen CJ, Mutasa S, et al. Fully automated segmentation algorithm for hematoma volumetric analysis in spontaneous intracerebral hemorrhage. Stroke 2019; 50(12): 3416-23.
[http://dx.doi.org/10.1161/STROKEAHA.119.026561] [PMID: 31735138]
[24]
Kong Z, Li T, Luo J, Xu S. Automatic tissue image segmentation based on image processing and deep learning. J Healthc Eng 2019; 2912458.
[http://dx.doi.org/10.1155/2019/2912458] [PMID: 30838122]
[25]
Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, et al. ImageNet large scale visual recognition challenge. Int J Comput Vis 2015; 115(3): 211-52.
[http://dx.doi.org/10.1007/s11263-015-0816-y]
[26]
Alfaro D, Levitt MA, English DK, Williams V, Eisenberg R. Accuracy of interpretation of cranial computed tomography scans in an emergency medicine residency program. Ann Emerg Med 1995; 25(2): 169-74.
[http://dx.doi.org/10.1016/S0196-0644(95)70319-5] [PMID: 7832342]
[27]
Lal NR, Murray UM, Eldevik OP, Desmond JS. Clinical consequences of misinterpretations of neuroradiologic CT scans by on-call radiology residents. AJNR Am J Neuroradiol 2000; 21(1): 124-9.
[PMID: 10669236]
[28]
Erly WK, Berger WG, Krupinski E, Seeger JF, Guisto JA. Radiology resident evaluation of head CT scan orders in the emergency department. AJNR Am J Neuroradiol 2002; 23(1): 103-7.
[PMID: 11827881]
[29]
Lee H, Yune S, Mansouri M, et al. An explainable deep-learning algorithm for the detection of acute intracranial haemorrhage from small datasets. Nat Biomed Eng 2019; 3(3): 173-82.
[http://dx.doi.org/10.1038/s41551-018-0324-9] [PMID: 30948806]

Rights & Permissions Print Cite
Article Metrics
29
5
© 2024 Bentham Science Publishers | Privacy Policy