Brain Tumor Segmentation Based on Deep Learning’s Feature Representation

Aboussaleh, Ilyasse; Riffi, Jamal; Mahraz, Mohamed Adnane; Tairi, Hamid

doi:10.3390/jimaging7120269

Cited by 29 publications

(6 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It signifies that the intensity of pixels of a tumor in an MRI plays a significant role. Both Aboussaleh et al and Bae et al mention this fact [51][52][53].…”

Section: Shap Analysis Resultsmentioning

confidence: 99%

Interpretable machine learning model to predict survival days of malignant brain tumor patients

Rajput

Kapdi

Raval

et al. 2023

Mach. Learn.: Sci. Technol.

View full text Add to dashboard Cite

An artificial intelligence (AI) model's performance is strongly influenced by the input features. Therefore, it is vital to find the optimal feature set. It is more crucial for the survival prediction of the glioblastoma multiforme (GBM) type of brain tumor. In this study, we identify the best feature set for predicting the survival days (SD) of GBM patients that outranks the state-of-the-art methodologies currently in use. The proposed approach is an end-to-end AI model. This model first segments tumors from healthy brain parts in patients' MRI images, extract features from the segmented results, performs feature selection, and makes predictions about patients' survival days based on the features selected. The extracted features are primarily shape based, location-based, and radiomics-based features. Additionally, patient metadata is also included as a feature. The methods used for selecting features include recursive feature elimination (RFE), permutation importance (PI), and finding the correlation between the features. Finally, we examined features behavior at local (single sample) and global (all the samples) levels. In this study, we find that out of 1265 extracted features, only 29 dominant features play a crucial role in predicting patients' survival days (SD). Furthermore, we find explanations of these features using post-hoc interpretability methods to validate the model's robust prediction. Finally, we analysed the behavioural impact of the top six features on survival prediction, and the findings drawn from the explanations were coherent with medical facts. We find that after the Age of 50 years, the likelihood of survival of a patient deteriorates, and survival after 80 years is scarce. Again, for location-based features, the SD is less if the tumor location is in the central or back part of the brain. The results show an overall 33% improvement in the accuracy of SD prediction compared to the top-performing methods of the BraTS-2020 challenge

show abstract

“…It signifies that the intensity of pixels of a tumor in an MRI plays a significant role. Both Aboussaleh et al and Bae et al mention this fact [51][52][53].…”

Section: Shap Analysis Resultsmentioning

confidence: 99%

Interpretable machine learning model to predict survival days of malignant brain tumor patients

Rajput

Kapdi

Raval

et al. 2023

Mach. Learn.: Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…The research used integrated region-growing segmentation and CBIR methods, which are not been using before in past years. Whilst [15] used region-growing segmentation algorithm to improve image quality, and brain tumor detection method in medical imaging have been presented by some researchers, such as [11,13,20,21]. They stated that region-growing algorithms start from an initial, incomplete segmentation and attempt to aggregate the unlabeled pixels into one of the initial regions.…”

Section: A Segmentationmentioning

confidence: 99%

“…When tumor cells invade the brain, then all functions of the body are interrupted, and there is a high risk of death. Additionally, Aboussaleh et al [11] explained that brain tumors can either be malignant or benign. Therefore, this research is aimed at detecting an early stage of a brain tumor so that it does not have time to attack very important parts of the brain and interfere with body functions.…”

Section: Introductionmentioning

confidence: 99%

Study of Manhattan and Region Growing Methods for Brain Tumor Detection

Irianto,

Karnila,

Yuliawati

2024

JAIT

View full text Add to dashboard Cite

This paper investigates the utilization of regiongrowing segmentation and Content-Based Image Retrieval (CBIR) techniques to predict brain cancer, particularly focusing on brain tumors. Recent advancements in medical science have brought about promising diagnostic methods and treatments, offering patients renewed hope for recovery. However, the existing problems in diagnosing brain cancer include time inefficiency, inconsistency, inaccuracy, and costly. Hence, this study aims to find an innovative approach to address the predicaments of cancer diagnosis by harnessing the power of artificial intelligence, specifically within the realm of computer vision. The methods of regiongrowing segmentation and CBIR are particularly employed for this purpose. To predict the presence of brain tumors, these methods are applied to brain CT-scan images. The dataset comprises over 800 images sourced from Kaggle.com and a hospital in Lampung, Indonesia. The effectiveness of the region-growing segmentation method is evaluated using Receiver Operating Characteristics (ROC) analysis, along with an assessment of the quality of affected regions within brain CT-scan images. The study demonstrates that the segmentation methods achieve an accuracy rate of 79% when tested on a dataset consisting of 400 normal brain CT-scan images and 400 brain cancer CT-scan images. Simultaneously, the accuracy of brain image retrieval using CBIR techniques is remarkable, surpassing 96% and 94% with the Manhattan and Euclidean distance metrics, respectively. In conclusion, the findings of this research indicate that the combination of CBIR and segmentation methods can substantially enhance the performance of algorithms designed for brain tumor detection.

show abstract

“…A brain tumor segmentation method based on deep learning's feature representation [20]. The approach uses a convolutional neural network to extract features from MRI images and then uses these features to segment the tumor.…”

Section: Anothermentioning

confidence: 99%

RU-Net2+: A Deep Learning Algorithm for Accurate Brain Tumor Segmentation and Survival Rate Prediction

Zaitoon,

Syed

2023

IEEE Access

View full text Add to dashboard Cite

Brain tumors present a significant medical concern, posing challenges in both diagnosis and treatment. Deep learning has emerged as an evolving technique for automating the diagnostic process for brain tumors. This research paper introduces a novel deep-learning framework designed explicitly for brain tumor diagnosis. The framework encompasses various tasks: tumor detection, classification, segmentation, and survival rate prediction. The framework was applied to the BraTS dataset, an extensive collection of brain tumor images, to evaluate its effectiveness. The proposed workflow initiates with data acquisition, followed by an enhancement of this data using a Convolutional Normalized Mean Filter (CNMF) during pre-processing. This prepares the data for the multi-class classification performed using the novel DBT-CNN classifier model. For precise tumor demarcation, the RU-Net2+ model is employed, yielding segmented regions from which features are subsequently extracted utilizing the Cox model. These extracted features play a pivotal role in the final step, where the survival rate of patients is predicted using a logistic regression model. The experimental results showcased the exceptional performance of the proposed framework, surpassing current benchmarks in classification accuracy, tumor segmentation precision, and survival rate prediction. For high-grade glioma (HGG) tumors, the framework achieved an impressive classification accuracy of 99.51%, while for low-grade glioma (LGG) tumors, the accuracy reached 99.28%. The accuracy of tumor segmentation stood at 98.39% for HGG tumors and 99.1% for LGG tumors. The RU-Net2+ algorithm accurately predict patient survival rates: 85.71% long-term, 72.72% medium-term, and 61.54% short-term, corresponding Mean Squared Errors of 0.13, 0.21, and 0.31. These results provide valuable insights for medical professionals making brain tumor treatment decisions. Additionally, the framework shows promise for automating brain tumor diagnosis and enhancing patient care.

show abstract

Brain Tumor Segmentation Based on Deep Learning’s Feature Representation

Cited by 29 publications

References 29 publications

Interpretable machine learning model to predict survival days of malignant brain tumor patients

Interpretable machine learning model to predict survival days of malignant brain tumor patients

Study of Manhattan and Region Growing Methods for Brain Tumor Detection

RU-Net2+: A Deep Learning Algorithm for Accurate Brain Tumor Segmentation and Survival Rate Prediction

Contact Info

Product

Resources

About