Automatic and accurate abnormality detection from brain MR images using a novel hybrid UnetResNext-50 deep CNN model. (April 2021)

• Record Type: Journal Article
• Authors: Rai, Hari Mohan; Chatterjee, Kalyan; Dashkevich, Sergey
• Is Part Of: Biomedical signal processing and control. Volume 66(2021)
• Publication Date: 2021-04
• Subjects: Brain tumor detection -- Magnetic resonance imaging -- Biomedical imaging -- Deep neural network -- Convolution neural network; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2021.102477
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: UnetResNext-50: A hybrid Deep CNN model designed for brain tumor detection. Automatic segmentation and classification of abnormal tumors from Brain MRI. Publically available datasets with 3929 MR images to develop the model. Excellent DICE score of 95.73%. Very efficient with exceptional accuracy of 99.7%. Abstract: The automatic and accurate detection and segmentation of brain tumors is a very tedious and challenging task for medical experts and radiologists. This paper proposes a hybrid deep convolutional neural network (CNN) model with a large number of layers and parameters for the automatic and accurate prediction and segmentation of brain tumors from the magnetic resonance imaging (MRI) images. The proposed model has a skip connection with cardinality which solves the problem of gradient degradation and also reduces the computational cost of Deep CNN architecture and it also improves the pixel quality at the decoder side. MRI dataset containing a total of 3929 MR images including 1373 images with tumors and 2556 images of normal type (without tumor). The dataset is preprocessed and augmented with 21 parameters before feeding the train images to the proposed models for learning. Performance metrics used for the evaluation of model efficiency are Jaccard Index, DICE score, F1-score, accuracy, precision, and recall. Our model performance is also evaluated by comparing it with the other two models UnetResNet-50 and Vanilla Unet and also with state-of-art techniques. In the post-processing stage, the scores of segmented tumor areas are calculated based on the scores of IoU and DICE and are also presented for comparison with the original images. Performance evaluation metrics show that the proposed model UnetResNext-50 shows excellent efficacy with 99.7% accuracy and a 95.73% DICE score.