Fully automatic identification of post-treatment infarct lesions after endovascular therapy based on non-contrast computed tomography
Authors: 
Ximing Nie, Xiran Liu, Hao Yang, Feng Shi, Weibin Gu, Xinyi Hou, Yufei Wei, Qixuan Lu, Haiwei Bai, Jiaping Chen, Tianhang Liu, Hongyi Yan, Zhonghua Yang, Miao Wen, Yuesong Pan, Chao Huang, Long Wang, Liping LiuAuthors Info & Claims
Ximing Nie, Xiran Liu, Hao Yang, Feng Shi, Weibin Gu, Xinyi Hou, Yufei Wei, Qixuan Lu, Haiwei Bai, Jiaping Chen, Tianhang Liu, Hongyi Yan, Zhonghua Yang, Miao Wen, Yuesong Pan, Chao Huang, Long Wang, Liping LiuAuthors Info & ClaimsPages 22101 - 22114
Abstract
Non-contrast computed tomography (NCCT) of the brain is critical to patients with acute ischemic stroke who receive thrombolysis and thrombectomy. It can help identify reperfusion-related hemorrhage, edema which need intervention. It also can guide the timing and intensity of antithrombotic therapy. Rapid, accurate, and automated detection and segmentation of acute ischemic lesions after endovascular therapy (EVT) are highly needed. In this work, we propose a novel encoder-decoder network for fully automatic segmentation of acute ischemic lesions after EVT on NCCT, which is named ISCT-EDN. NCCT images of AIS (acute ischemic stroke) patients who underwent EVT in a multicenter cohort study were collected in this study. ISCT-EDN takes hierarchical network as backbone. Feature pyramid network (FPN) is designed to aggregate features from multi stages of backbone. Reasonable feature fusion strategy is considered in FPN to enhance multi-level propagation. In addition, to overcome the limitation of fixed geometric structure of convolution for multi-range dependency exploitation, non-local parallel decoder is introduced with deformable convolution and self-attention. The proposed model was compared with 7 segmentation models which are commonly used in the medical domain and the performance was superior to other models in in the segmentation of post-treatment infarct lesions on NCCT images of AIS patients after EVT.
References
[1]
Goyal M, Demchuk AM, Menon BK, Eesa M, Rempel JL, Thornton J, Roy D, Jovin TG, Willinsky RA, Sapkota BL, Dowlatshahi D, Frei DF, Kamal NR, Montanera WJ, Poppe AY, Ryckborst KJ, Silver FL, Shuaib A, Tampieri D, Williams D, Bang OY, Baxter BW, Burns PA, Choe H, Heo JH, Holmstedt CA, Jankowitz B, Kelly M, Linares G, Mandzia JL, Shankar J, Sohn SI, Swartz RH, Barber PA, Coutts SB, Smith EE, Morrish WF, Weill A, Subramaniam S, Mitha AP, Wong JH, Lowerison MW, Sajobi TT, Hill MD, and Investigators ET Randomized assessment of rapid endovascular treatment of ischemic stroke N Engl J Med 2015 372 11 1019-1030
[2]
Dankbaar JW, Horsch AD, van den Hoven AF, Kappelle LJ, van der Schaaf IC, van Seeters T, Velthuis BK, and Investigators D Prediction of clinical outcome after acute ischemic stroke: the value of repeated noncontrast computed tomography, computed tomographic angiography, and computed tomographic perfusion Stroke 2017 48 9 2593-2596
[3]
Qiu W, Kuang H, Teleg E, Ospel JM, Sohn SI, Almekhlafi M, Goyal M, Hill MD, Demchuk AM, and Menon BK Machine learning for detecting early infarction in acute stroke with non-contrast-enhanced CT Radiology 2020 294 3 638-644
[4]
Powers WJ, Rabinstein AA, Ackerson T, Adeoye OM, Bambakidis NC, Becker K, Biller J, Brown M, Demaerschalk BM, Hoh B, Jauch EC, Kidwell CS, Leslie-Mazwi TM, Ovbiagele B, Scott PA, Sheth KN, Southerland AM, Summers DV, and Tirschwell DL Guidelines for the early management of patients with acute ischemic stroke: 2019 update to the 2018 guidelines for the early management of acute ischemic stroke: a guideline for healthcare professionals from the american heart association/American stroke association Stroke 2019 50 12 e344-e418
[5]
Campbell BC and Parsons MW Imaging selection for acute stroke intervention Int J Stroke 2018 13 6 554-567
[6]
Rekik I, Allassonniere S, Carpenter TK, and Wardlaw JM Medical image analysis methods in MR/CT-imaged acute-subacute ischemic stroke lesion: segmentation, prediction and insights into dynamic evolution simulation models critical appraisal Neuroimage Clin 2012 1 1 164-178
[7]
Vijh S, Saraswat M, and Kumar S Automatic multilevel image thresholding segmentation using hybrid bio-inspired algorithm and artificial neural network for histopathology images Multimed Tools Appl 2022
[8]
McBee MP, Awan OA, Colucci AT, Ghobadi CW, Kadom N, Kansagra AP, Tridandapani S, and Auffermann WF Deep learning in radiology Acad Radiol 2018 25 11 1472-1480
[9]
Zaharchuk G, Gong E, Wintermark M, Rubin D, and Langlotz CP Deep learning in neuroradiology AJNR Am J Neuroradiol 2018 39 10 1776-1784
[10]
Kuang H, Menon BK, and Qiu W Semi-automated infarct segmentation from follow-up noncontrast CT scans in patients with acute ischemic stroke Med Phys 2019 46 9 4037-4045
[11]
Kuang H, Menon BK, and Qiu W Segmenting hemorrhagic and ischemic infarct simultaneously from follow-up non-contrast CT images in patients with acute ischemic stroke IEEE Access 2019 7 2019 39842-39851
[12]
Latchaw RE, Alberts MJ, Lev MH, Connors JJ, Harbaugh RE, Higashida RT, Hobson R, Kidwell CS, Koroshetz WJ, Mathews V, Villablanca P, Warach S, Walters B, American Heart Association Council on Cardiovascular R, Intervention SC, The Interdisciplinary Council on Peripheral Vascular D (2009) Recommendations for imaging of acute ischemic stroke: a scientific statement from the American Heart Association. Stroke 40(11):3646–3678.
[13]
McArthur KS, Quinn TJ, Dawson J, and Walters MR Diagnosis and management of transient ischaemic attack and ischaemic stroke in the acute phase BMJ 2011 342 d1938
[14]
El-Koussy M, Schroth G, Brekenfeld C, and Arnold M Imaging of acute ischemic stroke Eur Neurol 2014 72 5–6 309-316
[15]
Schriger DL, Kalafut M, Starkman S, Krueger M, and Saver JL Cranial computed tomography interpretation in acute stroke: physician accuracy in determining eligibility for thrombolytic therapy JAMA 1998 279 16 1293-1297
[16]
Simard JM, Kent TA, Chen M, Tarasov KV, and Gerzanich V Brain oedema in focal ischaemia: molecular pathophysiology and theoretical implications Lancet Neurol 2007 6 3 258-268
[17]
Truwit CL, Barkovich AJ, Gean-Marton A, Hibri N, and Norman D Loss of the insular ribbon: another early CT sign of acute middle cerebral artery infarction Radiology 1990 176 3 801-806
[18]
Marks MP, Holmgren EB, Fox AJ, Patel S, von Kummer R, and Froehlich J Evaluation of early computed tomographic findings in acute ischemic stroke Stroke 1999 30 2 389-392
[19]
Patel SC, Levine SR, Tilley BC, Grotta JC, Lu M, Frankel M, Haley EC, Jr., Brott TG, Broderick JP, Horowitz S, Lyden PD, Lewandowski CA, Marler JR, Welch KM, National Institute of Neurological D, Stroke rt PASSG (2001) Lack of clinical significance of early ischemic changes on computed tomography in acute stroke. JAMA 286(22):2830–2838.
[20]
Barber PA, Demchuk AM, Zhang J, and Buchan AM Validity and reliability of a quantitative computed tomography score in predicting outcome of hyperacute stroke before thrombolytic therapy. ASPECTS study group. Alberta stroke programme early CT score Lancet 2000 355 9216 1670-1674
[21]
Young JY and Schaefer PW Acute ischemic stroke imaging: a practical approach for diagnosis and triage Int J Cardiovasc Imaging 2016 32 1 19-33
[22]
Na DG, Kim EY, Ryoo JW, Lee KH, Roh HG, Kim SS, Song IC, and Chang KH CT sign of brain swelling without concomitant parenchymal hypoattenuation: comparison with diffusion- and perfusion-weighted MR imaging Radiology 2005 235 3 992-998
[23]
Wu S, Mair G, Cohen G, Morris Z, von Heijne A, Bradey N, Cala L, Peeters A, Farrall AJ, Adami A, Potter G, Liu M, Lindley RI, Sandercock PAG, Wardlaw JM, and Group I S T C Hyperdense artery sign, symptomatic infarct swelling and effect of alteplase in acute ischaemic stroke Stroke Vasc Neurol 2021 6 2 238-243
[24]
Mahajan U, Raina S, and Sharma R Hyperdense middle cerebral artery sign J Assoc Physicians India 2019 67 4 75
[25]
Tan X and Guo Y Hyperdense basilar artery sign diagnoses acute posterior circulation stroke and predicts short-term outcome Neuroradiology 2010 52 12 1071-1078
[26]
Merino JG and Warach S Imaging of acute stroke Nat Rev Neurol 2010 6 10 560-571
[27]
Leys D, Pruvo JP, Godefroy O, Rondepierre P, and Leclerc X Prevalence and significance of hyperdense middle cerebral artery in acute stroke Stroke 1992 23 3 317-324
[28]
von Kummer R, Meyding-Lamade U, Forsting M, Rosin L, Rieke K, Hacke W, Sartor K (1994) Sensitivity and prognostic value of early CT in occlusion of the middle cerebral artery trunk. AJNR Am J Neuroradiol 15(1):9–15, discussion 16–18
[29]
Elofuke P, Reid JM, Rana A, and Macleod MJ Disappearance of the hyperdense MCA sign after stroke thrombolysis: implications for prognosis and early patient selection for clot retrieval J R Coll Physicians Edinb 2016 46 2 81-86
[30]
Sun H, Liu Y, Gong P, Zhang S, Zhou F, and Zhou J Intravenous thrombolysis for ischemic stroke with hyperdense middle cerebral artery sign: a meta-analysis Acta Neurol Scand 2020 141 3 193-201
[31]
Deo RC Machine learning in medicine Circulation 2015 132 20 1920-1930
[32]
McKinley R, Hani L, Gralla J, El-Koussy M, Bauer S, Arnold M, Fischer U, Jung S, Mattmann K, Reyes M, and Wiest R Fully automated stroke tissue estimation using random forest classifiers (FASTER) J Cereb Blood Flow Metab 2017 37 8 2728-2741
[33]
Nielsen A, Hansen MB, Tietze A, and Mouridsen K Prediction of tissue outcome and assessment of treatment effect in acute ischemic stroke using deep learning Stroke 2018 49 6 1394-1401
[34]
Anwar SM, Majid M, Qayyum A, Awais M, Alnowami M, and Khan MK Medical image analysis using convolutional neural networks: a review J Med Syst 2018 42 11 226
[35]
Chilamkurthy S, Ghosh R, Tanamala S, Biviji M, Campeau NG, Venugopal VK, Mahajan V, Rao P, and Warier P Deep learning algorithms for detection of critical findings in head CT scans: a retrospective study Lancet 2018 392 10162 2388-2396
[36]
Park A, Chute C, Rajpurkar P, Lou J, Ball RL, Shpanskaya K, Jabarkheel R, Kim LH, McKenna E, Tseng J, Ni J, Wishah F, Wittber F, Hong DS, Wilson TJ, Halabi S, Basu S, Patel BN, Lungren MP, Ng AY, and Yeom KW Deep learning-assisted diagnosis of cerebral aneurysms using the HeadXNet model JAMA Netw Open 2019 2 6 e195600
[37]
Rajpurkar P, Irvin J, Zhu K, Yang B, Mehta H, Duan T, Ding D, Bagul A, Langlotz C,Shpanskaya K (2017) CheXNet: radiologist-level pneumonia detection on chest X-rays with deep learning. arXiv preprint http://arxiv.org/abs/1711.05225
[38]
Winzeck S, Hakim A, McKinley R, Pinto J, Alves V, Silva C, Pisov M, Krivov E, Belyaev M, Monteiro M, Oliveira A, Choi Y, Paik MC, Kwon Y, Lee H, Kim BJ, Won JH, Islam M, Ren H, Robben D, Suetens P, Gong E, Niu Y, Xu J, Pauly JM, Lucas C, Heinrich MP, Rivera LC, Castillo LS, Daza LA, Beers AL, Arbelaezs P, Maier O, Chang K, Brown JM, Kalpathy-Cramer J, Zaharchuk G, Wiest R, and Reyes M ISLES 2016 and 2017-benchmarking ischemic stroke lesion outcome prediction based on multispectral MRI Front Neurol 2018 9 679
[39]
Robben D, Boers AMM, Marquering HA, Langezaal L, Roos Y, van Oostenbrugge RJ, van Zwam WH, Dippel DWJ, Majoie C, van der Lugt A, Lemmens R, and Suetens P Prediction of final infarct volume from native CT perfusion and treatment parameters using deep learning Med Image Anal 2020 59 101589
[40]
Wei Y, Pu Y, Pan Y, Nie X, Duan W, Liu D, Yan H, Lu Q, Zhang Z, Yang Z, Wen M, Gu W, Hou X, Ma N, Leng X, Miao Z, Liu L, and Co I Cortical microinfarcts associated with worse outcomes in patients with acute ischemic stroke receiving endovascular treatment Stroke 2020 51 9 2742-2751
[41]
Woo I, Lee A, Jung SC, Lee H, Kim N, Cho SJ, Kim D, Lee J, Sunwoo L, and Kang DW Fully automatic segmentation of acute ischemic lesions on diffusion-weighted imaging using convolutional neural networks: comparison with conventional algorithms Korean J Radiol 2019 20 8 1275-1284
[42]
Lin TY, Dollar P, Girshick R, He K, and Belongie S Feature pyramid networks for object detection Proc IEEE Conf Comput Vision Pattern Recog 2017 2017 2117-2125
[43]
Dai J, Qi H, Xiong Y, Li Y, Zhang G, Hu H, and Wei Y Deformable convolutional networks Proc IEEE Int Conf Comput Vision 2017 2017 764-773
[44]
Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017) Attention is all you need.
[45]
Lin TY, Dollar P, Girshick R, He K, Hariharan B, Belongie S (2017) Feature pyramid networks for object detection. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR)
[46]
Li X, You A, Zhu Z, Zhao H, Yang M, Yang K, and Tong Y Semantic flow for fast and accurate scene parsing European conference on computer vision 2020 Cham Springer 775-793
[47]
Wang X, Girshick R, Gupta A, He K (2017) Non-local neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7794–7803.
[48]
Zhu X, Hu H, Lin S,Dai J (2018) Deformable ConvNets v2: more deformable, Better results
[49]
Khan S, Naseer M, Hayat M, Zamir SW, and Shah M Transformers in vision: a survey ACM Comput Surv (CSUR) 2021 54 10s 1-41
[50]
Musulin J, Stifanic D, Zulijani A, Cabov T, Dekanic A, and Car Z An enhanced histopathology analysis: an AI-based system for multiclass grading of oral squamous cell carcinoma and segmenting of epithelial and stromal tissue Cancers (Basel) 2021
[51]
Hiasa Y, Otake Y, Takao M, Ogawa T, Sugano N, and Sato Y Automated muscle segmentation from clinical CT using Bayesian U-net for personalized musculoskeletal modeling IEEE Trans Med Imaging 2020 39 4 1030-1040
[52]
Zhou Z, Siddiquee MMR, Tajbakhsh N, Liang J (2018) UNet++: a nested U-net architecture for medical image segmentation. In: Deep learn med image anal multimodal learn clin decis support, 11045, p 3–11.
[53]
Yuan Y,Wang J (2018) OCNet: object context network for scene parsing. arXiv preprint arXiv:1809.00916
[54]
Zhang Z, Gao S, and Huang Z An automatic glioma segmentation system using a multilevel attention pyramid scene parsing network Curr Med Imaging 2021 17 6 751-761
[55]
Jiang J, Wang R, Lin S,Wang F (2019) SFSegNet: parse freehand sketches using deep fully convolutional networks. In: 2019 International joint conference on neural networks (IJCNN), pp 1–8.
[56]
Fan DP, Zhou T, Ji GP, Zhou Y, Chen G, Fu H, Shen J, and Shao L Inf-Net: automatic COVID-19 lung infection segmentation from CT images IEEE Trans Med Imaging 2020 39 8 2626-2637
[57]
Ernst M, Boers AMM, Aigner A, Berkhemer OA, Yoo AJ, Roos YB, Dippel DWJ, Aad VDL, Van Oostenbrugge RJ, and Van Zwam WH Association of computed tomography ischemic lesion location with functional outcome in acute large vessel occlusion ischemic stroke Stroke 2017 48 9 2426-2433
[58]
Bivard A, Levi C, Lin L, Cheng X, Aviv R, Spratt NJ, Lou M, Kleinig T, O’Brien B, and Butcher K Validating a predictive model of acute advanced imaging biomarkers in ischemic stroke Stroke 2017 48 3 645
[59]
Barros RS, Tolhuisen ML, Boers AM, Jansen I, and Marquering HA Automatic segmentation of cerebral infarcts in follow-up computed tomography images with convolutional neural networks J Neurointerv Surg 2019 12,9 2020 848-852
[60]
Phan CM, Yoo AJ, Hirsch JA, Nogueira RG, and Gupta R Differentiation of hemorrhage from iodinated contrast in different intracranial compartments using dual-energy head CT AJNR Am J Neuroradiol 2012 33 6 1088-1094
[61]
Balami JS, White PM, Mcmeekin PJ, Ford GA, and Buchan AM Complications of endovascular treatment for acute ischemic stroke: prevention and management Int J Stroke 2017 13 4 174749301774305
[62]
Zhang R, Zhao L, Lou W, Abrigo JM, Mok VC, Chu WC, Wang D, and Shi L Automatic segmentation of acute ischemic stroke from DWI using 3-D fully convolutional densenets IEEE Trans Med Imaging 2018 37 2149-2160
[63]
Clèrigues A, Valverde S, Bernal J, Freixenet J, Oliver A, and Lladó X Acute ischemic stroke lesion core segmentation in CT perfusion images using fully convolutional neural networks Comput Biol Med 2019 115 103487
[64]
Sah RG, d’Esterre CD, Hill MD, and Moiz H Diffusion-weighted MRI stroke volume following recanalization treatment is threshold-dependent Clin Neuroradiol 2017 29 135-141
[65]
Kranz PG and Eastwood JD Does diffusion-weighted imaging represent the ischemic core? An evidence-based systematic review AJNR Am J Neuroradiol 2009 30 6 1206-1212
[66]
Rekik I, Allassonnière S, Carpenter TK, and Wardlaw JM Medical image analysis methods in MR/CT-imaged acute-subacute ischemic stroke lesion: segmentation, prediction and insights into dynamic evolution simulation models. A critical appraisal Neuroimage Clin 2012 1 164-178
[67]
Soffer S, Ben-Cohen A, Shimon O, Amitai MM, Greenspan H, and Klang E Convolutional neural networks for radiologic images: A radiologist's guide Radiology 2019 290 3 590-606
[68]
Krizhevsky A, Sutskever I, and Hinton GE Imagenet classification with deep convolutional neural networks Commun ACM 2017 60 6 84-90
[69]
Boers AM, Marquering HA, Jochem JJ, Besselink NJ, and Majoi CB Automated cerebral infarct volume measurement in follow-up noncontrast CT scans of patients with acute ischemic stroke Am J Neuroradiol 2013 34 8 1522-1527
[70]
Vos PC, Novak CL, Aylward S, Biesbroek JM, Weaver NA, Velthuis BK, and Viergever MA Automatic detection and segmentation of ischemic lesions in computed tomography images of stroke patients Proce SPIE Int Soc Opt Eng 2013 8670 13
[71]
Yoon W, Jung MY, Jung SH, Park MS, Kim JT, and Kang HK Subarachnoid hemorrhage in a multimodal approach heavily weighted toward mechanical thrombectomy with solitaire stent in acute stroke Stroke 2013 44 2 414-419
Recommendations
Automatic detection of acute ischemic stroke using non-contrast computed tomography and two-stage deep learning model
Highlights- Detection system of acute ischemic stroke on non-contract CT images was developed.
- Two-stage deep learning model was used for the system.
- The system could be used to assist specialists in their clinical practice.
- The system ...
Abstract Background and objectiveCurrently, it is challenging to detect acute ischemic stroke (AIS)-related changes on computed tomography (CT) images. Therefore, we aimed to develop and evaluate an automatic AIS detection system involving a two-stage ...
Towards the Detection of Pulmonary Embolism Based on Deep Learning in Non-Contrast Computed Tomography Pulmonary Angiogram
ICEA '23: Proceedings of the 2023 International Conference on Intelligent Computing and Its Emerging ApplicationsPulmonary embolism is a life-threatening disease, early detection and treatment of pulmonary embolism can effectively reduce mortality. In recent years, many studies have been using deep learning in the diagnosis of pulmonary embolism with contrast medium ...
Segmenting Extra Pulmonary Tuberculous Lesions in Computed Tomography Images Using Positron Emission Tomography Intensity Markers
ICIME '09: Proceedings of the 2009 International Conference on Information Management and EngineeringVarious studies have been conducted to expand the utilization of Combined Positron Emission Tomography and Computed Tomography (PET/CT) covering cases of infection and inflammation. PET images provide the functional activity of a lesion while CT images ...
Comments
Information & Contributors
Information
Published In
© The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2022. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
Publisher
Springer-Verlag
Berlin, Heidelberg
Publication History
Published: 12 December 2022
Accepted: 22 November 2022
Received: 21 May 2022
Author Tags
Qualifiers
- Research-article
Funding Sources
- National Key R&D program of China
- National Natural Science Foundation of China
- Beijing Municipal Administration of Hospitals’ Youth Programme
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 17 Feb 2025