Brain Tumor Detection and Classification Using Fine-Tuned CNN with ResNet50 and U-Net Model: A Study on TCGA-LGG and TCIA Dataset for MRI Applications

Asiri, Abdullah A.; Shaf, Ahmad; Ali, Tariq; Aamir, Muhammad; Irfan, Muhammad; Alqahtani, Saeed; Mehdar, Khlood M.; Halawani, Hanan T.; Alghamdi, Ali; Alshamrani, Abdullah Fahad A.; Alqhtani, Samar M.

doi:10.3390/life13071449

Cited by 22 publications

(4 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A CSV logger is initialized for recording training metrics, and two callbacks, ReduceLROnPlateau and CSV logger, are employed for dynamic learning rate adjustments and logging training information. The final model summary provides a concise overview of the entire segmentation architecture, offering insights into the U-Net and the integrated ResNet50 encoder (Asiri et al, 2023; Khodadadi Shoushtari et al, 2022; Thhntb. (2021), n.d.).…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Comprehensive Benchmarking of CNN-Based Tumor Segmentation Methods Using Multimodal MRI Data

Kundal,

Rao,

Majumdar

et al. 2024

Preprint

View full text Add to dashboard Cite

Magnetic resonance imaging (MRI) is become an essential and a frontline technique in the detection of brain tumor. However, manual segmentation of tumor from MRI scans is a time-consuming and labour-intensive process. There is a prevalent trend in employing fully automated methods for accurate tumor segmentation using MRI scans. The precision in brain tumor segmentation is essential for the better diagnosis, treatment and prognosis. This study focuses on benchmarking and evaluating the performance of four widely used convolutional neural network (CNN) based brain tumor segmentation methods CaPTk, 2DVNet, EnsembleUNets, and ResNet50. We used 1251 multimodal MRI scans from the BraTS2021 dataset, which encompasses T1, T2, T1ce, and Flair imaging modalities. We compared the performance of these CNN-based methods against a reference set of previously segmented images obtained with the assistance of radiologists. The evaluation encompasses direct utilization of segmented outputs and also by employing radiomic features. Performance evaluation with direct segments method using Dice Similarity Coefficient score (DSC) and Hausdorff Distance (HD) suggested better performance of EnsembleUNets with DSC and HD of 0.93 and 18 respectively, outperforming the other methods. Comparative analysis using radiomics features also revealed that EnsembleUNets is the most precise segmentation method as compared to CaPTk, 2DVNet, and ResNet50. EnsembleUNets achieved Concordance Correlation Coefficient (CCC), Total Deviation Index (TDI), and Root Mean Square Error (RMSE) of 0.79, 1.14 and 0.53 respectively and outperformed its counterparts. These findings contribute valuable insight into the comparative efficacy of EnsembleUNets, facilitating informed decision for accurate brain tumor segmentation.

show abstract

Section: Methodsmentioning

confidence: 99%

“…ResNet is a semantic segmentation model developed using TensorFlow/Keras and the segmentation models library. (Asiri et al, 2023;Khodadadi Shoushtari et al, 2022;Thhntb. (2021), n.d.).…”

Section: Resnet50mentioning

confidence: 99%

Comprehensive Benchmarking of CNN-Based Tumor Segmentation Methods Using Multimodal MRI Data

Kundal,

Rao,

Majumdar

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…U-Net with ResNet50 backbone. In their paper, Asiri et al [30] present a CNN model that combines fine-tuned ResNet50 and U-net architectures for accurate brain tumor classification and detection in MRI images. The fine-tuned ResNet50 excels in tumor detection, while U-net precisely segments tumors.…”

Section: End-to-end Model Flowmentioning

confidence: 99%

Post-Operative Brain MRI Resection Cavity Segmentation Model and Follow-Up Treatment Assistance

Xavier P,

P. K.,

Raju G

2024

Int. J. Onl. Eng.

View full text Add to dashboard Cite

Post-operative brain magnetic resonance imaging (MRI) segmentation is inherently challenging due to the diverse patterns in brain tissue, which makes it difficult to accurately identify resected areas. Therefore, there is a crucial need for a precise segmentation model. Due to the scarcity of post-operative brain MRI scans, it is not feasible to use complex models that require a large amount of training data. This paper introduces an innovative approach for accurately segmenting and quantifying post-operative brain resection cavities in MRI scans. The proposed model, named Attention-Enhanced VGG-U-Net, integrates VGG16 initial weights in the encoder section and incorporates a self-attention module in the decoder, offering improved accuracy for postoperative brain MRI segmentation. The attention mechanism enhances its accuracy by concentrating on a specific area of interest. The VGG16 model is comparatively lightweight, has pre-trained weights, and allows the model to extract incredibly detailed information from the input. The model is trained on publicly available post-operative brain MRI data and achieved a Dice coefficient value of 0.893. The model is then assessed using a clinical dataset of postoperative brain MRIs. The model facilitates the quantification of the resected regions and enables comparisons with each brain region based on pre-operative images. The capabilities of the model assist radiologists in evaluating surgical success and directing follow-up procedures.

show abstract

“…Considering these unique features of brain tumors, doctors can correctly identify and treat brain tumors [ 3 ]. With the advent of deep learning techniques, fine-tuned pre-trained convolutional neural network (CNN) models [ 4 ] and ViTs [ 5 ] have emerged as powerful tools in the field of medical image analysis, enabling accurate and efficient brain tumor detection.…”

Section: Introductionmentioning

confidence: 99%

Advancing Brain Tumor Classification through Fine-Tuned Vision Transformers: A Comparative Study of Pre-Trained Models

Asiri,

Shaf,

Ali

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

This paper presents a comprehensive study on the classification of brain tumor images using five pre-trained vision transformer (ViT) models, namely R50-ViT-l16, ViT-l16, ViT-l32, ViT-b16, and ViT-b32, employing a fine-tuning approach. The objective of this study is to advance the state-of-the-art in brain tumor classification by harnessing the power of these advanced models. The dataset utilized for experimentation consists of a total of 4855 images in the training set and 857 images in the testing set, encompassing four distinct tumor classes. The performance evaluation of each model is conducted through an extensive analysis encompassing precision, recall, F1-score, accuracy, and confusion matrix metrics. Among the models assessed, ViT-b32 demonstrates exceptional performance, achieving a high accuracy of 98.24% in accurately classifying brain tumor images. Notably, the obtained results outperform existing methodologies, showcasing the efficacy of the proposed approach. The contributions of this research extend beyond conventional methods, as it not only employs cutting-edge ViT models but also surpasses the performance of existing approaches for brain tumor image classification. This study not only demonstrates the potential of ViT models in medical image analysis but also provides a benchmark for future research in the field of brain tumor classification.

show abstract

Brain Tumor Detection and Classification Using Fine-Tuned CNN with ResNet50 and U-Net Model: A Study on TCGA-LGG and TCIA Dataset for MRI Applications

Cited by 22 publications

References 43 publications

Comprehensive Benchmarking of CNN-Based Tumor Segmentation Methods Using Multimodal MRI Data

Comprehensive Benchmarking of CNN-Based Tumor Segmentation Methods Using Multimodal MRI Data

Post-Operative Brain MRI Resection Cavity Segmentation Model and Follow-Up Treatment Assistance

Advancing Brain Tumor Classification through Fine-Tuned Vision Transformers: A Comparative Study of Pre-Trained Models

Contact Info

Product

Resources

About