Realizing the Effective Detection of Tumor in Magnetic Resonance Imaging using Cluster-Sparse Assisted Super-Resolution

Abstract

Recently, significant research has been done in Super-Resolution (SR) methods for augmenting the spatial resolution of the Magnetic Resonance (MR) images, which aids the physician in improved disease diagnoses. Single SR methods have drawbacks; they fail to capture self-similarity in non-local patches and are not robust to noise. To exploit the non-local self-similarity and intrinsic sparsity in MR images, this paper proposes the use of Cluster-Sparse Assisted Super-Resolution. This SR method effectively captures similarity in non-locally positioned patches by training on clusters of patches using a self-adaptive dictionary. This method of training also leads to better edge and texture detection. Experiments show that using Cluster-Sparse Assisted Super-Resolution for brain MR images results in enhanced detection of lesions leading to better diagnosis.

MRI brain tumor segmentation using residual Spatial Pyramid Pooling-powered 3D U-Net

“…In many vision tasks like segmentation, particularly in the healthcare industry, deep learning-based segmentation systems have shown amazing success, outperforming other traditional methods in brain tumor analysis ( 4 – 8 ). With exceptional results, Fully Convolutional Networks (FCN) ( 9 ) achieve end-to-end semantic segmentation for the first time.…”

Potential roles of transformers in brain tumor diagnosis and treatment

“…AI has progressed exponentially and is now being applied to various visualization analyses in healthcare. Deep learning (DL)‐based segmentation systems have achieved immense success, outperforming many traditional protocols for BT analysis [6–10] . DL networks indicate promising outcomes for BT classification and detection by magnetic resonance imaging (MRI) and demonstrate high efficiency.…”

“…Deep learning (DL)-based segmentation systems have achieved immense success, outperforming many traditional protocols for BT analysis. [6][7][8][9][10] DL networks indicate promising outcomes for BT classification and detection by magnetic resonance imaging (MRI) and demonstrate high efficiency. DL has been used for BT identification, diagnosis, segmentation, classification, and evolution [11][12][13] and is more accurate than expert radiologists.…”