Skull stripping using traditional and soft-computing approaches for magnetic resonance images: a semi-systematic meta-analysis

Azam, None Humera; Tariq, Humera

doi:10.22630/mgv.2020.29.1.3

Cited by 1 publication

(2 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Mask–RCNN is the latest DLNN-based method for image segmentation. Literature suggests that learning weights of numerous objects and classes for the training of DLNN are readily available [ 28 , 43 ]. Extensive literature did not provide sufficient empirical evidence about utilizing Mask–RCNN for skull stripping from brain MR images [ 43 ].…”

Section: Research Gapmentioning

confidence: 99%

“…Literature suggests that learning weights of numerous objects and classes for the training of DLNN are readily available [ 28 , 43 ]. Extensive literature did not provide sufficient empirical evidence about utilizing Mask–RCNN for skull stripping from brain MR images [ 43 ]. Moreover, renowned public libraries such as COCO do not have training weights to train systems for predicting the brain and skull stripping from the given brain MR image [ 44 ].…”

Section: Research Gapmentioning

confidence: 99%

See 1 more Smart Citation

Fully Automated Skull Stripping from Brain Magnetic Resonance Images Using Mask RCNN-Based Deep Learning Neural Networks

Azam,

Tariq,

Shehzad

et al. 2023

Brain Sciences

Self Cite

View full text Add to dashboard Cite

This research comprises experiments with a deep learning framework for fully automating the skull stripping from brain magnetic resonance (MR) images. Conventional techniques for segmentation have progressed to the extent of Convolutional Neural Networks (CNN). We proposed and experimented with a contemporary variant of the deep learning framework based on mask region convolutional neural network (Mask–RCNN) for all anatomical orientations of brain MR images. We trained the system from scratch to build a model for classification, detection, and segmentation. It is validated by images taken from three different datasets: BrainWeb; NAMIC, and a local hospital. We opted for purposive sampling to select 2000 images of T1 modality from data volumes followed by a multi-stage random sampling technique to segregate the dataset into three batches for training (75%), validation (15%), and testing (10%) respectively. We utilized a robust backbone architecture, namely ResNet–101 and Functional Pyramid Network (FPN), to achieve optimal performance with higher accuracy. We subjected the same data to two traditional methods, namely Brain Extraction Tools (BET) and Brain Surface Extraction (BSE), to compare their performance results. Our proposed method had higher mean average precision (mAP) = 93% and content validity index (CVI) = 0.95%, which were better than comparable methods. We contributed by training Mask–RCNN from scratch for generating reusable learning weights known as transfer learning. We contributed to methodological novelty by applying a pragmatic research lens, and used a mixed method triangulation technique to validate results on all anatomical modalities of brain MR images. Our proposed method improved the accuracy and precision of skull stripping by fully automating it and reducing its processing time and operational cost and reliance on technicians. This research study has also provided grounds for extending the work to the scale of explainable artificial intelligence (XAI).

show abstract

Section: Research Gapmentioning

confidence: 99%