MR image normalization dilemma and the accuracy of brain tumor classification model

Alnowami, Majdi R.; Taha, Eslam; Alsebaeai, Saeed; Anwar, Syed Muhammad; Alhawsawi, Abdulsalam M.

doi:10.1016/j.jrras.2022.05.014

Cited by 18 publications

(7 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The application of intensity standardization visually improves the separation of metastatic versus healthy bone intensity distributions, allowing for improved disease reading from the MRI image, and better separation of intensity feature classes, commonly used in machine learning classifiers. These proof-of-concept results are in line with previous works in the field of impact of MRI intensity normalization on machine learning , Alnowami et al 2022, Jacobsen et al 2019.…”

Section: Discussionsupporting

confidence: 89%

Comparison of intra- and inter-patient intensity standardization methods for multi-parametric whole-body MRI

Ceranka

Lecouvet

Michoux

et al. 2023

Biomed. Phys. Eng. Express

View full text Add to dashboard Cite

Objective: To test and compare different intensity standardization approaches for whole-body multi-parametric MRI, allowing for the compensation of univocal representation of image intensities between scans, which pose problems in image quantification, assessment of changes between a baseline and follow-up scan and hinder performance of image processing and machine learning algorithms. Approach: In this work, we present a comparison on the accuracy of intensity standardization approaches with increasing complexity, for intra- and inter-patient multi-parametric whole-body MRI. Several approaches were used: z-scoring of the intensities, piecewise linear mapping and deformable mapping of intensity distributions into established reference intensity space. Additionally, the use reference image and average population distribution reference; as well as, whole image and region of interest standardization approaches were investigated. All methods were validated on a data set of 18 whole-body anatomical and diffusion-weighted MR scans consisting of baseline and follow-up examinations acquired from advanced prostate cancer patients and healthy volunteers. Main results: The piecewise linear intensity standardisation approach provided the best compromise between standardization accuracy and method stability, with average deviations in intensity profile of 0.011-0.027 and mean absolute difference of 0.29-0.37 standard score (intra-patient) and 0.014-0.056 (inter-patient), depending on the type of used MR modality. Significance: Linear piecewise approaches showed the overall best performance across multiple validation metrics, mostly because of its robustness. The inter-patient standardization proved to perform better when using population average reference image; in contrary to intra-patient approach, where the best results were achieved by standardizing towards a reference image taken as the baseline scan.

show abstract

Section: Discussionsupporting

confidence: 89%

Comparison of intra- and inter-patient intensity standardization methods for multi-parametric whole-body MRI

Ceranka

Lecouvet

Michoux

et al. 2023

Biomed. Phys. Eng. Express

View full text Add to dashboard Cite

show abstract

“… 24 , 25 Alnowami et al also showed promising results in brain tumour classification using MRI, achieving an accuracy rate of 96.25%, sensitivity rate of 98.5% and specificity rate of 82.1% ( Table 1 ). 26 These studies demonstrate that AI can potentially improve patient outcomes by providing quick diagnosis and accurate tumour classification in neurosurgical oncology.…”

Section: Application and Outcomes Of Ai ML And Dl In Various Neurosur...mentioning

confidence: 85%

Recent Outcomes and Challenges of Artificial Intelligence, Machine Learning, and Deep Learning in Neurosurgery

Awuah,

Adebusoye,

Wellington

et al. 2024

World Neurosurgery: X

View full text Add to dashboard Cite

“…In the diagnosis of brain tumors, studies have been carried out using models from scratch [19][20][21][22][23][24][25], transfer learning [26][27][28][29][30][31][32][33][34][35][36], and ensemble learning [1,[37][38][39][40][41][42] techniques. Ayadi et al [19] performed a brain tumor diagnosis with a scratch model.…”

Section: Discussionmentioning

confidence: 99%

“…Badije and Deniz Ülker [31] used the AlexNet model in their study. Alnowami et al [32] used the DenseNet architecture in their work. Talukder et al [33] used various transfer learning architectures (DenseNet201, InceptionResNetV2, ResNet50V2, and Xception) in their study.…”

Section: Related Workmentioning

confidence: 99%

“…When the existing studies are examined, there are many studies using scratch models [19][20][21][22][23][24][25], transfer learning [26][27][28][29][30][31][32][33][34][35][36], ensemble learning [1,[37][38][39][40][41][42], and different optimization algorithms [4,[43][44][45][46][47][48][49][50][51][52][53][54]. Table 1 summarizes related studies on brain tumor classification in terms of method, dataset, classification type, and results.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A Novel Ensemble Framework for Multi-Classification of Brain Tumors Using Magnetic Resonance Imaging

Çetin-Kaya,

Kaya

2024

Diagnostics

View full text Add to dashboard Cite

Brain tumors can have fatal consequences, affecting many body functions. For this reason, it is essential to detect brain tumor types accurately and at an early stage to start the appropriate treatment process. Although convolutional neural networks (CNNs) are widely used in disease detection from medical images, they face the problem of overfitting in the training phase on limited labeled and insufficiently diverse datasets. The existing studies use transfer learning and ensemble models to overcome these problems. When the existing studies are examined, it is evident that there is a lack of models and weight ratios that will be used with the ensemble technique. With the framework proposed in this study, several CNN models with different architectures are trained with transfer learning and fine-tuning on three brain tumor datasets. A particle swarm optimization-based algorithm determined the optimum weights for combining the five most successful CNN models with the ensemble technique. The results across three datasets are as follows: Dataset 1, 99.35% accuracy and 99.20 F1-score; Dataset 2, 98.77% accuracy and 98.92 F1-score; and Dataset 3, 99.92% accuracy and 99.92 F1-score. We achieved successful performances on three brain tumor datasets, showing that the proposed framework is reliable in classification. As a result, the proposed framework outperforms existing studies, offering clinicians enhanced decision-making support through its high-accuracy classification performance.

show abstract

MR image normalization dilemma and the accuracy of brain tumor classification model

Cited by 18 publications

References 19 publications

Comparison of intra- and inter-patient intensity standardization methods for multi-parametric whole-body MRI

Comparison of intra- and inter-patient intensity standardization methods for multi-parametric whole-body MRI

Recent Outcomes and Challenges of Artificial Intelligence, Machine Learning, and Deep Learning in Neurosurgery

A Novel Ensemble Framework for Multi-Classification of Brain Tumors Using Magnetic Resonance Imaging

Contact Info

Product

Resources

About