Automated post-operative brain tumour segmentation: A deep learning model based on transfer learning from pre-operative images

Ghaffari, Mina; Samarasinghe, Gihan; Jameson, Michael; Aly, Farhannah; Holloway, Lois; Chlap, Phillip; Koh, Eng‐Siew; Sowmya, Arcot; Oliver, Ruth

doi:10.1016/j.mri.2021.10.012

Cited by 22 publications

(11 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sub-compartmental segmentation, including TC, is a major influence on tumor progression monitoring and radiotherapy planning. 97 Hence, our finding cautions the application of machine learning in all its potential uses in routine clinical practice and highlights the need for further research on sub-compartmental automated segmentation (TC and ET). Since most methods used conventional MRI scans (ie, T1, T2, T1CE, and FLAIR), future studies could combine these multimodal sequences with other specialized MRI sequences to increase the number of features, assessing for potential enhanced segmentation results.…”

Section: Discussionmentioning

confidence: 76%

Automated brain tumor identification using magnetic resonance imaging: A systematic review and meta-analysis

Kouli

Hassane

Badran

et al. 2022

Neuro-Oncology Advances

View full text Add to dashboard Cite

Background Automated brain tumor identification facilitates diagnosis and treatment planning. We evaluate the performance of traditional machine learning (TML) and deep learning (DL) in brain tumor detection and segmentation, using MRI. Methods A systematic literature search from January 2000 to May 8, 2021 was conducted. Study quality was assessed using the Checklist for Artificial Intelligence in Medical Imaging (CLAIM). Detection meta-analysis was performed using a unified hierarchical model. Segmentation studies were evaluated using a random effects model. Sensitivity analysis was performed for externally validated studies. Results Of 224 studies included in the systematic review, 46 segmentation and 38 detection studies were eligible for meta-analysis. In detection, DL achieved a lower false positive rate compared to TML; 0.018 (95% CI, 0.011 to 0.028) and 0.048 (0.032 to 0.072) (P < .001), respectively. In segmentation, DL had a higher dice similarity coefficient (DSC), particularly for tumor core (TC); 0.80 (0.77 to 0.83) and 0.63 (0.56 to 0.71) (P < .001), persisting on sensitivity analysis. Both manual and automated whole tumor (WT) segmentation had “good” (DSC ≥ 0.70) performance. Manual TC segmentation was superior to automated; 0.78 (0.69 to 0.86) and 0.64 (0.53 to 0.74) (P = .014), respectively. Only 30% of studies reported external validation. Conclusions The comparable performance of automated to manual WT segmentation supports its integration into clinical practice. However, manual outperformance for sub-compartmental segmentation highlights the need for further development of automated methods in this area. Compared to TML, DL provided superior performance for detection and sub-compartmental segmentation. Improvements in the quality and design of studies, including external validation, are required for the interpretability and generalizability of automated models.

show abstract

Section: Discussionmentioning

confidence: 76%

Automated brain tumor identification using magnetic resonance imaging: A systematic review and meta-analysis

Kouli

Hassane

Badran

et al. 2022

Neuro-Oncology Advances

View full text Add to dashboard Cite

show abstract

“…Hybrid feature map = VGG19 feature map F1 × wt1 + CNN feature map without augmentation F2 × wt2 + CNN feature map with augmentation F3 × wt3 (1) With the help of optimized weights, a hybrid feature map is generated which is further fed to a fully connected layer to determine the classified output.…”

Section: Classification Using Ensembling Of Three Different Modelsmentioning

confidence: 99%

“…These weights are further optimized by using a grid search combination to achieve the maximum accuracy value of the ensemble model. Equation (1) shows the formula of the hybrid feature map for the best combination of weights.…”

Section: Classification Using Ensembling Of Three Different Modelsmentioning

confidence: 99%

“…A brain tumor, which is regarded as one of the most serious illnesses of the nervous system, is an unexpected and uncontrollable development of brain cells. The Tumor Society estimates that approximately 4 lakh people worldwide are impacted with brain tumors every year [ 1 , 2 ]. Brain tumors can cause a range of complications, including seizures, cognitive problems, and physical disabilities.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Weighted Average Ensemble Deep Learning Model for Stratification of Brain Tumor in MRI Images

Anand

Gupta

et al. 2023

Diagnostics

View full text Add to dashboard Cite

Brain tumor diagnosis at an early stage can improve the chances of successful treatment and better patient outcomes. In the biomedical industry, non-invasive diagnostic procedures, such as magnetic resonance imaging (MRI), can be used to diagnose brain tumors. Deep learning, a type of artificial intelligence, can analyze MRI images in a matter of seconds, reducing the time it takes for diagnosis and potentially improving patient outcomes. Furthermore, an ensemble model can help increase the accuracy of classification by combining the strengths of multiple models and compensating for their individual weaknesses. Therefore, in this research, a weighted average ensemble deep learning model is proposed for the classification of brain tumors. For the weighted ensemble classification model, three different feature spaces are taken from the transfer learning VGG19 model, Convolution Neural Network (CNN) model without augmentation, and CNN model with augmentation. These three feature spaces are ensembled with the best combination of weights, i.e., weight1, weight2, and weight3 by using grid search. The dataset used for simulation is taken from The Cancer Genome Atlas (TCGA), having a lower-grade glioma collection with 3929 MRI images of 110 patients. The ensemble model helps reduce overfitting by combining multiple models that have learned different aspects of the data. The proposed ensemble model outperforms the three individual models for detecting brain tumors in terms of accuracy, precision, and F1-score. Therefore, the proposed model can act as a second opinion tool for radiologists to diagnose the tumor from MRI images of the brain.

show abstract

“…In the literature studies, brain-based analyses (segmentation, classification, etc.) are handled and examined many times by using 2D-or 3D-based evaluations [6][7][8][9][10][11][12]. However, the accurate classification of brain tumors is evaluated less than the segmentation issue.…”

Section: Introductionmentioning

confidence: 99%

3t2FTS: A Novel Feature Transform Strategy to Classify 3D MRI Voxels and Its Application on HGG/LGG Classification

Hajmohamad

Koyuncu

2023

MAKE

View full text Add to dashboard Cite

The distinction between high-grade glioma (HGG) and low-grade glioma (LGG) is generally performed with two-dimensional (2D) image analyses that constitute semi-automated tumor classification. However, a fully automated computer-aided diagnosis (CAD) can only be realized using an adaptive classification framework based on three-dimensional (3D) segmented tumors. In this paper, we handle the classification section of a fully automated CAD related to the aforementioned requirement. For this purpose, a 3D to 2D feature transform strategy (3t2FTS) is presented operating first-order statistics (FOS) in order to form the input data by considering every phase (T1, T2, T1c, and FLAIR) of information on 3D magnetic resonance imaging (3D MRI). Herein, the main aim is the transformation of 3D data analyses into 2D data analyses so as to applicate the information to be fed to the efficient deep learning methods. In other words, 2D identification (2D-ID) of 3D voxels is produced. In our experiments, eight transfer learning models (DenseNet201, InceptionResNetV2, InceptionV3, ResNet50, ResNet101, SqueezeNet, VGG19, and Xception) were evaluated to reveal the appropriate one for the output of 3t2FTS and to design the proposed framework categorizing the 210 HGG–75 LGG instances in the BraTS 2017/2018 challenge dataset. The hyperparameters of the models were examined in a comprehensive manner to reveal the highest performance of the models to be reached. In our trails, two-fold cross-validation was considered as the test method to assess system performance. Consequently, the highest performance was observed with the framework including the 3t2FTS and ResNet50 models by achieving 80% classification accuracy for the 3D-based classification of brain tumors.

show abstract

Automated post-operative brain tumour segmentation: A deep learning model based on transfer learning from pre-operative images

Cited by 22 publications

References 7 publications

Automated brain tumor identification using magnetic resonance imaging: A systematic review and meta-analysis

Automated brain tumor identification using magnetic resonance imaging: A systematic review and meta-analysis

Weighted Average Ensemble Deep Learning Model for Stratification of Brain Tumor in MRI Images

3t2FTS: A Novel Feature Transform Strategy to Classify 3D MRI Voxels and Its Application on HGG/LGG Classification

Contact Info

Product

Resources

About