Brain Tumor Segmentation using Enhanced U-Net Model with Empirical Analysis

Nasim, Md Abdullah Al; Munem, Abdullah Al; Islam, Maksuda; Palash, Md Aminul Haque; Haque, Md. Mahim Anjum; Shah, Faisal Muhammad

doi:10.1109/iccit57492.2022.10054934

Cited by 26 publications

(7 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, they introduced a novel regression model for predicting brain tumor patients' survival rates, showing moderate accuracy on the tested datasets. Al Nasim et al [21] focussedon segmenting necrotic, edematous, growing, and healthy tissue regions within the brain tumors. The use of U-Net's encoder-decoder architecture and image segmentation to exclude background details enhances efficiency.…”

Section: Literature Reviewmentioning

confidence: 99%

Ensemble Technique for Brain Tumor Patient Survival Prediction

Vinod,

Prakash,

AlSalman

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Brain tumours pose a significant health challenge, demanding the immediate development of reliable and automated detection methods within the medical sphere. Swift and accurate identification of these tumours is crucial for effective treatment and the well-being of patients. These growths stem from uncontrolled cell multiplication, depleting vital nutrients from healthy brain tissue and leading to organ dysfunction. Presently, the conventional method involves a manual examination of brain MRI scans by medical professionals, but this is hindered by the varied shapes and sizes of tumours, resulting in timeconsuming and occasionally imprecise evaluations. The emergence of automation holds immense potential, promising to bolster efficiency and allow medical practitioners more time for direct patient care. Traditional machine learning approaches have historically depended on labor-intensive feature engineering. In our research, we introduce an innovative approach: a combination of the U-Net model [1], a Convolutional Neural Network (CNN), and Self Organizing Feature Map (SOFM) in an ensemble technique for precise brain tumour segmentation using the BRATS 2020 dataset. Our evaluation not only focuses on segmentation accuracy but also utilizes valuable survival data from the dataset to predict patient survival rates. The proposed model resulted in average training accuracy, mean Intersection over Union (mIoU), and dice coefficient scores of 0.967, 0.521, and 0.990 respectively for different epochs. Also, average validation accuracy, mIoU, and dice coefficient scores of 0.965, 0.546, and 0.992 respectively. The proposed model showcases a 98.28% accuracy in the segmentation of brain tumours. The proposed methodology has the potential to revolutionize the landscape of brain tumour diagnosis and treatment.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Ensemble Technique for Brain Tumor Patient Survival Prediction

Vinod,

Prakash,

AlSalman

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Unfortunately, the model lacked the hyper-parameters needed to evaluate its performance consistency, which was this work's most significant limitation. Using many versions of the BraTS datasets for training and improvement, Al Nasim et al [25] introduced an enhanced structure of a 2D U-Net network. This study shows that the 2019 BraTS dataset yielded necrotic, Edema, and enhancing dice scores of 0.85, 0.94, and 0.88, respectively, which are statistically indistinguishable from the 2017-2018-2020 BraTS datasets.…”

Section: Literature Reviewmentioning

confidence: 99%

“…In contrast, our model applied robust feature maps extracted by a multiattention mechanism to segment and predict the three kinds of brain tumors involved in the BraTS dataset. [25], a 2D UNet network has been introduced to be enhanced and trained using several versions of the BraTS datasets. This study shows that the BraTS datasets from 2017, 2018, 2019, and 2020 have similar dice scores for Necrotic, Edema, and Enhancing regions compared to the 2019 BraTS dataset.…”

Section: Comparative Analysismentioning

confidence: 99%

“…It is now possible to segment 3D MRI images automatically, and this is International Journal of Intelligent Engineering and Systems, Vol.17, No.2, 2024 DOI: 10.22266/ijies2024.0430. 25 being achieved through applying different frameworks of convolutional neural networks (CNN) [6,7]. Labeled 3D MRI scans from the BraTS (brain tumour and segmentation) collection have recently made detecting and segmenting brain tumors in scientific literature easier.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

High-Resolution Model for Segmenting and Predicting Brain Tumor Based on Deep UNet with Multi Attention Mechanism

2024

IJIES

View full text Add to dashboard Cite

The research presents a new technique for segmenting brain tumors using the UNet framework enhanced with an attention mechanism. By incorporating attention processes that selectively emphasize prominent aspects while recording comprehensive contextual information, our strategy overcomes the challenges of brain tumor delineation. The suggested UNet-attention model is intended to outperform traditional segmentation techniques regarding precision and clinical applicability. Integrating spatial and channel attention processes into the UNet design is one of our study's significant achievements. The spatial attention mechanism's focus improves the capacity of the model to differentiate the mechanism's tumor and non-tumor areas. Also, incorporating contextual clues from multi-scale hierarchies allows for a thorough comprehension of visual properties. The discrete wavelet transform has been applied as a feature extraction method to enhance the model performance regarding time and memory consumption. A wide range of datasets is evaluated in-depth, proving our UNet-attention model's superiority. Advanced deep learning is made possible by combining attention processes and contextual data to delineate tumors precisely and clinically. Many evaluation criteria involving dice scores, accuracy, mean IoU, sensitivity, specificity, and Hausdorff distance have been applied to evaluate our model performance in different aspects. The model attained a dice coefficient of 0.9971. The model's specificity of 0.9988 is particularly noteworthy, demonstrating its exceptional ability to identify regions without tumors accurately. The model also achieved 0.9986 accuracies, 0.9142 mean IoU, Hausdorff distance (mm) 3.48. These evaluation values were obtained for applying our model on flair images from BraTS 2020.

show abstract

“…The authors of the article [25] have incorporated a 3D attention module with the decoder pathways of a basic U-Net architecture and obtained mean dice scores of 0.778, 0.868, and 0.777 for enhancing tumor, whole, and core respectively on Brats 2019 dataset. Another work based on the U-Net architecture was carried out by Al Nasim et al [26], in which a 2D approach was developed. The proposed model outperformed the same dataset, achieving maximum accuracy of 99.8%, sensitivity of 99.7%, specificity of 99.91% and mean scores of 0.94, 0.95 and 0.871 for tumors, whole body and cardiac enhancement respectively, compared to other CNN-based models such as FCNN and RCNN.…”

Section: Related Workmentioning

confidence: 99%

NeuroMorphNet: A Multiscale Convolutional Neural Network for High-Precision Brain Tumor Segmentation in 3D Medical Images

Guennich,

Othmani,

Ltifi

2023

Preprint

View full text Add to dashboard Cite

The use of high-precision automatic algorithms to segment brain tumors offers the potential for improved disease diagnosis, treatment monitoring, as well as the possibility of large-scale pathological studies. In this study, we present a new 9-layer multiscale architecture dedicated to the semantic segmentation of 3D medical images, with a particular focus on brain tumor images, using convolutional neural networks. Our innovative solution draws inspiration from the Deepmedic architecture while incorporating significant enhancements. The use of variable-sized filters between layers and the early incorporation of residual connections from the very first layer greatly enhance the accuracy of 3D medical image segmentation. Additionally, the reduction in the number of layers in our dual-pathway network optimizes efficiency while maintaining exceptional performance. This combination of innovations, with Deepmedic as a starting point, positions our solution as a major advancement in the field of 3D medical image segmentation, offering an optimal balance between accuracy and efficiency for clinical applications.

show abstract

Brain Tumor Segmentation using Enhanced U-Net Model with Empirical Analysis

Cited by 26 publications

References 21 publications

Ensemble Technique for Brain Tumor Patient Survival Prediction

Ensemble Technique for Brain Tumor Patient Survival Prediction

High-Resolution Model for Segmenting and Predicting Brain Tumor Based on Deep UNet with Multi Attention Mechanism

NeuroMorphNet: A Multiscale Convolutional Neural Network for High-Precision Brain Tumor Segmentation in 3D Medical Images

Contact Info

Product

Resources

About