Deep Learning for Hemorrhagic Lesion Detection and Segmentation on Brain CT Images

Stroke is an acute cerebral vascular disease that is likely to cause long-term disabilities and death. Immediate emergency care with accurate diagnosis of computed tomographic (CT) images is crucial for dealing with a hemorrhagic stroke. However, due to the high variability of a stroke's location, contrast, and shape, it is challenging and time-consuming even for experienced radiologists to locate them. In this paper, we propose a U-net based deep learning framework to automatically detect and segment hemorrhage strokes in CT brain images. The input of the network is built by concatenating the flipped image with the original CT slice which introduces symmetry constraints of the brain images into the proposed model. This enhances the contrast between hemorrhagic areas and normal brain tissue. Various Deep Learning topologies are compared by varying the layers, batch normalization, dilation rates, and pre-train models. This could increase the respective filed and preserves more information on lesion characteristics. Besides, the adversarial training is also adopted in the proposed network to improve the accuracy of the segmentation. The proposed model is trained and evaluated on two different datasets, which achieve the competitive performance with human experts with the highest location accuracy 0.9859 for detection, 0.8033 Dice score, and 0.6919 IoU for segmentation. The results demonstrate the effectiveness, robustness, and advantages of the proposed deep learning model in automatically hemorrhage lesion diagnosis, which make it possible to be a clinical decision support tool in stroke diagnosis.

[1]  Daniel S. Kermany,et al.  Identifying Medical Diagnoses and Treatable Diseases by Image-Based Deep Learning , 2018, Cell.

[2]  D L Schriger,et al.  Cranial computed tomography interpretation in acute stroke: physician accuracy in determining eligibility for thrombolytic therapy. , 1998, JAMA.

[3]  Kyung-shik Shin,et al.  Image classification of fine-grained fashion image based on style using pre-trained convolutional neural network , 2018, 2018 IEEE 3rd International Conference on Big Data Analysis (ICBDA).

[4]  L. R. Dice.  Measures of the Amount of Ecologic Association Between Species , 1945 .

[5]  Navalgund Rao,et al.  Deep 3D convolution neural network for CT brain hemorrhage classification , 2018, Medical Imaging.

[6]  Cheng G. Weng,et al.  A New Evaluation Measure for Imbalanced Datasets , 2008, AusDM.

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

[8]  Vladlen Koltun,et al.  Multi-Scale Context Aggregation by Dilated Convolutions , 2015, ICLR.

[9]  Changming Sun,et al.  RA-UNet: A Hybrid Deep Attention-Aware Network to Extract Liver and Tumor in CT Scans , 2018, Frontiers in Bioengineering and Biotechnology.

[10]  Bijoy K. Menon,et al.  Segmenting Hemorrhagic and Ischemic Infarct Simultaneously From Follow-Up Non-Contrast CT Images in Patients With Acute Ischemic Stroke , 2019, IEEE Access.

[11]  George Papandreou,et al.  Rethinking Atrous Convolution for Semantic Image Segmentation , 2017, ArXiv.

[12]  Taku Komura,et al.  Dilated Saliency U-Net for White Matter Hyperintensities Segmentation Using Irregularity Age Map , 2019, bioRxiv.

[13]  Fabio Maria Carlucci,et al.  From Source to Target and Back: Symmetric Bi-Directional Adaptive GAN , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[14]  Alexey Shvets,et al.  TernausNet: U-Net with VGG11 Encoder Pre-Trained on ImageNet for Image Segmentation , 2018, Computer-Aided Analysis of Gastrointestinal Videos.

[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]  Srikrishna Varadarajan,et al.  RADnet: Radiologist level accuracy using deep learning for hemorrhage detection in CT scans , 2017, 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).

[18]  Allan Hanbury,et al.  Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool , 2015, BMC Medical Imaging.

[19]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[20]  Wei-Shi Zheng,et al.  Efficient symmetry-driven fully convolutional network for multimodal brain tumor segmentation , 2017, 2017 IEEE International Conference on Image Processing (ICIP).

[21]  Qi Tian,et al.  Classification of CT Brain Images of Head Trauma , 2007, PRIB.

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

[23]  Augusto Silva,et al.  Spontaneous Intracerebral Hemorrhage Image Analysis Methods: A Survey , 2009 .

[24]  Mohammad Mansouri,et al.  An explainable deep-learning algorithm for the detection of acute intracranial haemorrhage from small datasets , 2018, Nature Biomedical Engineering.

[25]  Yong Xia,et al.  D-UNet: A Dimension-Fusion U Shape Network for Chronic Stroke Lesion Segmentation , 2019, IEEE/ACM Transactions on Computational Biology and Bioinformatics.

[26]  Murtadha D. Hssayeni,et al.  Intracranial Hemorrhage Segmentation Using Deep Convolutional Model , 2019, Data.

[27]  Chew Lim Tan,et al.  Hemorrhage slices detection in brain CT images , 2008, 2008 19th International Conference on Pattern Recognition.

[28]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

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

[30]  Gavriel Salomon,et al.  T RANSFER OF LEARNING , 1992 .

[31]  Ian D. Reid,et al.  RefineNet: Multi-path Refinement Networks for High-Resolution Semantic Segmentation , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[33]  Sheng Liu,et al.  Towards Clinical Diagnosis: Automated Stroke Lesion Segmentation on Multi-Spectral MR Image Using Convolutional Neural Network , 2018, IEEE Access.

[34]  Pyin Oo Lwin,et al.  Computer-Aided Detection system for Hemorrhage contained region , 2013 .

[35]  Jonathan Rubin,et al.  Ischemic Stroke Lesion Segmentation in CT Perfusion Scans using Pyramid Pooling and Focal Loss , 2018, BrainLes@MICCAI.

[36]  Aggelos K. Katsaggelos,et al.  A deep symmetry convnet for stroke lesion segmentation , 2016, 2016 IEEE International Conference on Image Processing (ICIP).

[37]  Hui Li,et al.  Digital mammographic tumor classification using transfer learning from deep convolutional neural networks , 2016, Journal of medical imaging.

[38]  Tao Chan,et al.  Computer aided detection of small acute intracranial hemorrhage on computer tomography of brain , 2007, Comput. Medical Imaging Graph..

[39]  Soumith Chintala,et al.  Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks , 2015, ICLR.

[40]  Eric P. Xing,et al.  SCAN: Structure Correcting Adversarial Network for Organ Segmentation in Chest X-Rays , 2017, DLMIA/ML-CDS@MICCAI.

[41]  L. Sugrue,et al.  Hybrid 3D/2D Convolutional Neural Network for Hemorrhage Evaluation on Head CT , 2018, American Journal of Neuroradiology.

[42]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[43]  P. Reddy,et al.  Peripheral biomarkers of stroke: Focus on circulatory microRNAs. , 2016, Biochimica et biophysica acta.