3D dissimilar-siamese-u-net for hyperdense Middle cerebral artery sign segmentation

The hyperdense middle cerebral artery sign (HMCAS) representing a thromboembolus has been declared as a vital CT finding for intravascular thrombus in the diagnosis of acute ischemia stroke. Early recognition of HMCAS can assist in patient triage and subsequent thrombolysis or thrombectomy treatment. A total of 624 annotated head non-contrast-enhanced CT (NCCT) image scans were retrospectively collected from multiple public hospitals in Hong Kong. In this study, we present a deep Dissimilar-Siamese-U-Net (DSU-Net) that is able to precisely segment the lesions by integrating Siamese and U-Net architectures. The proposed framework consists of twin sub-networks that allow inputs of left and right hemispheres in head NCCT images separately. The proposed Dissimilar block fully explores the feature representation of the differences between the bilateral hemispheres. Ablation studies were carried out to validate the performance of various components of the proposed DSU-Net. Our findings reveal that the proposed DSU-Net provides a novel approach for HMCAS automatic segmentation and it outperforms the baseline U-Net and many state-of-the-art models for clinical practice.

[1]  Gregory R. Koch,et al.  Siamese Neural Networks for One-Shot Image Recognition , 2015 .

[2]  George Papandreou,et al.  Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation , 2018, ECCV.

[3]  Christopher Joseph Pal,et al.  Brain tumor segmentation with Deep Neural Networks , 2015, Medical Image Anal..

[4]  Shenghua Gao,et al.  CE-Net: Context Encoder Network for 2D Medical Image Segmentation , 2019, IEEE Transactions on Medical Imaging.

[5]  M. Wintermark,et al.  Guidelines for the Early Management of Patients With Acute Ischemic Stroke: A Guideline for Healthcare Professionals From the American Heart Association/American Stroke Association , 2013, Stroke.

[6]  Andreas K. Maier,et al.  Automatic Thrombus Detection in Non-enhanced Computed Tomography Images in Patients With Acute Ischemic Stroke , 2017, VCBM.

[7]  Mark W. Woolrich,et al.  Bayesian analysis of neuroimaging data in FSL , 2009, NeuroImage.

[8]  Philip S. Yu,et al.  Burden of large vessel occlusion stroke and the service gap of thrombectomy: A population-based study using a territory-wide public hospital system registry , 2020, International journal of stroke : official journal of the International Stroke Society.

[9]  B. Mackert,et al.  Association Between Dispatch of Mobile Stroke Units and Functional Outcomes Among Patients With Acute Ischemic Stroke in Berlin. , 2021, JAMA.

[10]  Deniz Erdogmus,et al.  Tversky Loss Function for Image Segmentation Using 3D Fully Convolutional Deep Networks , 2017, MLMI@MICCAI.

[11]  C. Truwit,et al.  Loss of the insular ribbon: another early CT sign of acute middle cerebral artery infarction. , 1990, Radiology.

[12]  Y. Lee,et al.  Clinical implications of CT hyperdense artery sign in patients with acute middle cerebral artery occlusion in the era of modern mechanical thrombectomy , 2017, Journal of Neurology.

[13]  Nico Karssemeijer,et al.  Classifying symmetrical differences and temporal change for the detection of malignant masses in mammography using deep neural networks , 2017, Journal of medical imaging.

[14]  Seyed-Ahmad Ahmadi,et al.  V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation , 2016, 2016 Fourth International Conference on 3D Vision (3DV).

[15]  Bram van Ginneken,et al.  A survey on deep learning in medical image analysis , 2017, Medical Image Anal..

[16]  Nima Tajbakhsh,et al.  UNet++: A Nested U-Net Architecture for Medical Image Segmentation , 2018, DLMIA/ML-CDS@MICCAI.

[17]  Du-Yih Tsai,et al.  An automated detection method for the MCA dot sign of acute stroke in unenhanced CT , 2013, Radiological Physics and Technology.

[18]  S. Han,et al.  Keratinocytic Skin Cancer Detection on the Face Using Region-Based Convolutional Neural Network. , 2019, JAMA dermatology.

[19]  Ciprian M. Crainiceanu,et al.  Validated automatic brain extraction of head CT images , 2015, NeuroImage.

[20]  Kalim Qureshi,et al.  A Hybrid Approach of Using Symmetry Technique for Brain Tumor Segmentation , 2014, Comput. Math. Methods Medicine.

[21]  Seyed-Ahmad Ahmadi,et al.  Automatic Liver and Lesion Segmentation in CT Using Cascaded Fully Convolutional Neural Networks and 3D Conditional Random Fields , 2016, MICCAI.

[22]  Roberto Cipolla,et al.  SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[23]  S. Ulmer,et al.  Assessment of Thrombus in Acute Middle Cerebral Artery Occlusion Using Thin-Slice Nonenhanced Computed Tomography Reconstructions , 2010, Stroke.

[24]  J A Maldjian,et al.  Automated CT segmentation and analysis for acute middle cerebral artery stroke. , 2001, AJNR. American journal of neuroradiology.

[25]  Thomas Brox,et al.  U-Net: deep learning for cell counting, detection, and morphometry , 2018, Nature Methods.

[26]  N. Razavian,et al.  Classification and mutation prediction from non–small cell lung cancer histopathology images using deep learning , 2018, Nature Medicine.

[27]  A. Fox,et al.  Evaluation of early computed tomographic findings in acute ischemic stroke. , 1999, Stroke.

[28]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[29]  J. Fiehler,et al.  Sensitivity of visual and quantitative detection of middle cerebral artery occlusion on non-contrast-enhanced computed tomography , 2014, Neuroradiology.

[30]  W Hacke,et al.  Sensitivity and prognostic value of early CT in occlusion of the middle cerebral artery trunk. , 1994, AJNR. American journal of neuroradiology.

[31]  Mark W. Woolrich,et al.  Advances in functional and structural MR image analysis and implementation as FSL , 2004, NeuroImage.

[32]  W. Powers,et al.  2018 Guidelines for the Early Management of Patients With Acute Ischemic Stroke: A Guideline for Healthcare Professionals From the American Heart Association/American Stroke Association , 2018, Stroke.

[33]  M. Froehler,et al.  The CT‐Defined Hyperdense Arterial Sign as a Marker for Acute Intracerebral Large Vessel Occlusion , 2018, Journal of neuroimaging : official journal of the American Society of Neuroimaging.

[34]  A. Demchuk,et al.  Validity and reliability of a quantitative computed tomography score in predicting outcome of hyperacute stroke before thrombolytic therapy , 2000, The Lancet.

[35]  Wu Qiu,et al.  Automated Infarct Segmentation from Follow-up Non-Contrast CT Scans in Patients with Acute Ischemic Stroke Using Dense Multi-Path Contextual Generative Adversarial Network , 2019, MICCAI.

[36]  Xiaogang Wang,et al.  Pyramid Scene Parsing Network , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[37]  A. Demchuk,et al.  Hyperdense Sylvian Fissure MCA “Dot” Sign: A CT Marker of Acute Ischemia , 2001, Stroke.

[38]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[39]  Trevor Darrell,et al.  Fully Convolutional Networks for Semantic Segmentation , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[40]  Nico Karssemeijer,et al.  Computer-Aided Detection of Prostate Cancer in MRI , 2014, IEEE Transactions on Medical Imaging.

[41]  F. Shishido,et al.  Early CT finding in cerebral infarction: obscuration of the lentiform nucleus. , 1988, Radiology.

[42]  Mark W. Woolrich,et al.  FSL , 2012, NeuroImage.

[43]  A. Demchuk,et al.  Machine Learning for Detecting Early Infarction in Acute Stroke with Non-Contrast-enhanced CT. , 2020, Radiology.

[44]  Aneta Lisowska,et al.  Context-Aware Convolutional Neural Networks for Stroke Sign Detection in Non-contrast CT Scans , 2017, MIUA.

[45]  I. Katzan,et al.  The Location of Pretreatment Hyperdense Middle Cerebral Artery Sign Predicts the Outcome of Intraarterial Thrombectomy for Acute Stroke , 2015, Journal of neuroimaging : official journal of the American Society of Neuroimaging.

[46]  Philip L. H. Yu,et al.  Automated Hierarchy Evaluation System of Large Vessel Occlusion in Acute Ischemia Stroke , 2020, Frontiers in Neuroinformatics.

[47]  Eufrozina Selariu,et al.  Hyperdense middle cerebral artery sign in multidetector computed tomography: definition, occurrence, and reliability analysis. , 2009, Neurology India.

[48]  Thomas G. Dietterich.  Approximate Statistical Tests for Comparing Supervised Classification Learning Algorithms , 1998, Neural Computation.