Tumor type detection in brain MR images of the deep model developed using hypercolumn technique, attention modules, and residual blocks

Brain cancer is a disease caused by the growth of abnormal aggressive cells in the brain outside of normal cells. Symptoms and diagnosis of brain cancer cases are producing more accurate results day by day in parallel with the development of technological opportunities. In this study, a deep learning model called BrainMRNet which is developed for mass detection in open-source brain magnetic resonance images was used. The BrainMRNet model includes three processing steps: attention modules, the hypercolumn technique, and residual blocks. To demonstrate the accuracy of the proposed model, three types of tumor data leading to brain cancer were examined in this study: glioma, meningioma, and pituitary. In addition, a segmentation method was proposed, which additionally determines in which lobe area of the brain the two classes of tumors that cause brain cancer are more concentrated. The classification accuracy rates were performed in the study; it was 98.18% in glioma tumor, 96.73% in meningioma tumor, and 98.18% in pituitary tumor. At the end of the experiment, using the subset of glioma and meningioma tumor images, it was determined which at brain lobe the tumor region was seen, and 100% success was achieved in the analysis of this determination. In this study, a hybrid deep learning model is presented to determine the detection of the brain tumor. In addition, open-source software was proposed, which statistically found in which lobe region of the human brain the brain tumor occurred. The methods applied and tested in the experiments have shown promising results with a high level of accuracy, precision, and specificity. These results demonstrate the availability of the proposed approach in clinical settings to support the medical decision regarding brain tumor detection.

[1]  A. Jemal,et al.  Cancer statistics, 2019 , 2019, CA: a cancer journal for clinicians.

[2]  Mesut Toğaçar,et al.  BrainMRNet: Brain tumor detection using magnetic resonance images with a novel convolutional neural network model. , 2019, Medical hypotheses.

[3]  In-So Kweon,et al.  CBAM: Convolutional Block Attention Module , 2018, ECCV.

[4]  Kemal Polat,et al.  A Novel Medical Diagnosis model for COVID-19 infection detection based on Deep Features and Bayesian Optimization , 2020, Applied Soft Computing.

[5]  Robert M. Waterhouse,et al.  Brown marmorated stink bug, Halyomorpha halys (Stål), genome: putative underpinnings of polyphagy, insecticide resistance potential and biology of a top worldwide pest , 2020, BMC Genomics.

[6]  Jasjit S. Suri,et al.  Multiclass magnetic resonance imaging brain tumor classification using artificial intelligence paradigm , 2020, Comput. Biol. Medicine.

[7]  T. Lah,et al.  Brain malignancies: Glioblastoma and brain metastases , 2020 .

[8]  Jun Liang,et al.  Residual Recurrent Neural Networks for Learning Sequential Representations , 2018, Inf..

[9]  K. Skelding,et al.  Glioblastoma Multiforme: An Overview of Emerging Therapeutic Targets , 2019, Front. Oncol..

[10]  G. Kaltsas,et al.  Aggressive Pituitary Tumors , 2015, Neuroendocrinology.

[11]  Kahkashan Perveen,et al.  Glioblastoma Multiforme: A Review of its Epidemiology and Pathogenesis through Clinical Presentation and Treatment , 2017, Asian Pacific journal of cancer prevention : APJCP.

[12]  Jitendra Malik,et al.  Object Instance Segmentation and Fine-Grained Localization Using Hypercolumns , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  P. Plowman.  Radiotherapy for pituitary tumours. , 1995, Bailliere's clinical endocrinology and metabolism.

[14]  Klaus H. Maier-Hein,et al.  A Probabilistic U-Net for Segmentation of Ambiguous Images , 2018, NeurIPS.

[15]  Łukasz Szylberg,et al.  Pathologic aspects of skull base tumors. , 2016, Reports of practical oncology and radiotherapy : journal of Greatpoland Cancer Center in Poznan and Polish Society of Radiation Oncology.

[16]  D. Chicco,et al.  The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation , 2020, BMC Genomics.

[17]  F. Kreth,et al.  The surgical perspective in precision treatment of diffuse gliomas , 2019, OncoTargets and therapy.

[18]  Graham W. Taylor,et al.  Skin Lesion Segmentation using Deep Hypercolumn Descriptors , 2017 .

[19]  K. Paul Joseph,et al.  AUTOMATION OF MR BRAIN IMAGE CLASSIFICATION FOR MALIGNANCY DETECTION , 2019 .

[20]  Amjad Rehman,et al.  Computer-assisted brain tumor type discrimination using magnetic resonance imaging features , 2018, Biomedical engineering letters.

[21]  K. Kurian,et al.  Constitutive activation of the EGFR–STAT1 axis increases proliferation of meningioma tumor cells , 2020, Neuro-oncology advances.

[22]  J. W. Rosa,et al.  Prognostic Value of Invasion, Markers of Proliferation, and Classification of Giant Pituitary Tumors, in a Georeferred Cohort in Brazil of 50 Patients, with a Long-Term Postoperative Follow-Up , 2016, International journal of endocrinology.

[23]  Pengfei Chen,et al.  Rethinking the Usage of Batch Normalization and Dropout in the Training of Deep Neural Networks , 2019, ArXiv.

[24]  Qianjin Feng,et al.  Retrieval of Brain Tumors by Adaptive Spatial Pooling and Fisher Vector Representation , 2016, PloS one.

[25]  Guoying Zhang,et al.  An Improved OTSU Algorithm Using Histogram Accumulation Moment for Ore Segmentation , 2019, Symmetry.

[26]  Tolga Tasdizen,et al.  Decoding crystallography from high-resolution electron imaging and diffraction datasets with deep learning , 2019, Science Advances.

[27]  U. Ricardi,et al.  Radiation therapy for older patients with brain tumors , 2017, Radiation Oncology.

[28]  M. Shiroishi,et al.  Advanced Imaging of Intracranial Meningiomas. , 2016, Neurosurgery clinics of North America.

[29]  Steven D Chang,et al.  Gold Nanoparticles for Brain Tumor Imaging: A Systematic Review , 2018, Front. Neurol..

[30]  M. Jaffrain-Rea,et al.  How to Classify Pituitary Neuroendocrine Tumors (PitNET)s in 2020 , 2020, Cancers.

[31]  Derleme Makale,et al.  Düzce Üniversitesi Bilim ve Teknoloji Dergisi , 2015 .

[32]  Pritee Khanna,et al.  Glioma detection on brain MRIs using texture and morphological features with ensemble learning , 2019, Biomed. Signal Process. Control..

[33]  Giancarlo Fortino,et al.  A Hybrid Feature Extraction Method With Regularized Extreme Learning Machine for Brain Tumor Classification , 2019, IEEE Access.

[34]  Abhimanyu S. Ahuja,et al.  The impact of artificial intelligence in medicine on the future role of the physician , 2019, PeerJ.

[35]  Jun Cheng,et al.  brain tumor dataset , 2016 .

[36]  R PushpaB,et al.  Detection and classification of brain tumor using machine learning approaches , 2019 .

[37]  Thomas Brox,et al.  3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation , 2016, MICCAI.

[38]  B. O'neill,et al.  Second malignancies in patients with primary central nervous system lymphoma. , 2015, Neuro-oncology.

[39]  El-Sayed M. El-Horbaty,et al.  Classification using deep learning neural networks for brain tumors , 2017, Future Computing and Informatics Journal.

[40]  K. Schaller,et al.  Extent of Resection in Meningioma: Predictive Factors and Clinical Implications , 2019, Scientific Reports.

[41]  Hugo Germain,et al.  Sparse-to-Dense Hypercolumn Matching for Long-Term Visual Localization , 2019, 2019 International Conference on 3D Vision (3DV).

[42]  Örjan Smedby,et al.  Automatic brain segmentation using artificial neural networks with shape context , 2018, Pattern Recognit. Lett..

[43]  Brian O'Connor,et al.  Analysis of Sentinel-2 and RapidEye for Retrieval of Leaf Area Index in a Saltmarsh Using a Radiative Transfer Model , 2019, Remote. Sens..

[44]  Yang Ding,et al.  Using Deep Convolutional Neural Networks for Neonatal Brain Image Segmentation , 2020, Frontiers in Neuroscience.

[45]  Muhammad Umar Farooq,et al.  A Complex Lie-Symmetry Approach to Calculate First Integrals and Their Numerical Preservation , 2019, Symmetry.

[46]  Abdulkadir Sengur,et al.  A survey on neutrosophic medical image segmentation , 2019, Neutrosophic Set in Medical Image Analysis.

[47]  Mai S. Mabrouk,et al.  Fully automated computer-aided diagnosis system for micro calcifications cancer based on improved mammographic image techniques , 2019, Ain Shams Engineering Journal.

[48]  Zhuowen Tu,et al.  Aggregated Residual Transformations for Deep Neural Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[49]  P. M. Ameer,et al.  Brain tumor classification using deep CNN features via transfer learning , 2019, Comput. Biol. Medicine.

[50]  Zafer Cömert,et al.  BreastNet: A novel convolutional neural network model through histopathological images for the diagnosis of breast cancer , 2020 .

[51]  Licheng Jiao,et al.  Fully Dense Multiscale Fusion Network for Hyperspectral Image Classification , 2019, Remote. Sens..

[52]  Burhan Ergen,et al.  Recognition of Road Type and Quality for Advanced Driver Assistance Systems with Deep Learning , 2018, Elektronika ir Elektrotechnika.

[53]  Jean Ponce,et al.  Learning to Compose Hypercolumns for Visual Correspondence , 2020, ECCV.

[54]  Walid Al-Atabany,et al.  Multi-Classification of Brain Tumor Images Using Deep Neural Network , 2019, IEEE Access.

[55]  Cömert Zafer,et al.  Fusing fine-tuned deep features for recognizing different tympanic membranes , 2020 .

[56]  Ben Glocker,et al.  Attention Gated Networks: Learning to Leverage Salient Regions in Medical Images , 2018, Medical Image Anal..