Brain Tumor Segmentation and Classification Using MRI Images via Fully Convolution Neural Networks

Kumar, Sanjay; Negi, Ashish; Singh, J. N.; Gaurav, Amit

doi:10.1109/icacccn.2018.8748614

Cited by 27 publications

(11 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The fitness function in the DE is defined as where S is the total number of samples, FN is the number of false negative samples, and FP is the number of false positive samples. So, the first part of Equation (7) indicates the classification error rate. The middle part is the clustering effect in which K is the number of subclasses.…”

Section: Review Of the Problemmentioning

confidence: 99%

“…The CNN-based methods have made significant achievements in tumor detection 3,4 and tumor segmentation. [5][6][7][8] In related studies, the fully convolutional network (FCN) 7 and U-Net 8 are two representative approaches which has strong competitiveness compared with the existing brain tumor MRI image segmentation algorithms. The CNN-based methods show powerful image classification capability, but are subject to complicated and significant memory and computing resources.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A hybrid feature selection‐based approach for brain tumor detection and automatic segmentation on multiparametric magnetic resonance images

Chen

Ban

et al. 2021

Medical Physics

View full text Add to dashboard Cite

Purpose To develop a novel method based on feature selection, combining convolutional neural network (CNN) and ensemble learning (EL), to achieve high accuracy and efficiency of glioma detection and segmentation using multiparametric MRIs. Methods We proposed an evolutionary feature selection‐based hybrid approach for glioma detection and segmentation on 4 MR sequences (T2‐FLAIR, T1, T1Gd, and T2). First, we trained a lightweight CNN to detect glioma and mask the suspected region to process large batch of MRI images. Second, we employed a differential evolution algorithm to search a feature space, which composed of 416‐dimension radiomic features extracted from four sequences of MRIs and 128‐dimension high‐order features extracted by the CNN, to generate an optimal feature combination for pixel classification. Finally, we trained an EL classifier using the optimal feature combination to segment whole tumor (WT) and its subregions including nonenhancing tumor (NET), peritumoral edema (ED), and enhancing tumor (ET) in the suspected region. Experiments were carried out on 300 glioma patients from the BraTS2019 dataset using fivefold cross validation, the model was independently validated using the rest 35 patients from the same database. Results The approach achieved a detection accuracy of 98.8% using four MRIs. The Dice coefficients (and standard deviations) were 0.852 ± 0.057, 0.844 ± 0.046, and 0.799 ± 0.053 for segmentation of WT (NET+ET+ED), tumor core (NET+ET), and ET, respectively. The sensitivities and specificities were 0.873 ± 0.074, 0.863 ± 0.072, and 0.852 ± 0.082; the specificities were 0.994 ± 0.005, 0.994 ± 0.005, and 0.995 ± 0.004 for the WT, tumor core, and ET, respectively. The performances and calculation times were compared with the state‐of‐the‐art approaches, our approach yielded a better overall performance with average processing time of 139.5 s per set of four sequence MRIs. Conclusions We demonstrated a robust and computational cost‐effective hybrid segmentation approach for glioma and its subregions on multi‐sequence MR images. The proposed approach can be used for automated target delineation for glioma patients.

show abstract

Section: Review Of the Problemmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A hybrid feature selection‐based approach for brain tumor detection and automatic segmentation on multiparametric magnetic resonance images

Chen

Ban

et al. 2021

Medical Physics

View full text Add to dashboard Cite

show abstract

“…where S is the total number of samples, FN is the number of false-negative samples, and FPFP is the number of false-positive samples. So, the first part of Equation (7) indicates the classification error rate. The middle part is the clustering effect in which K is the number of sub-classes.…”

Section: Statement Of the Problem And Tg Chargesmentioning

confidence: 99%

“…The CNN-based methods have made significant achievements in tumor detection 3,4 and tumor segmentation. [5][6][7][8] In related studies, the fully convolutional network (FCN) 7 and U-Net 8 are two representative approaches which have strong competitiveness compared with the existing brain tumor MRI image segmentation algorithms. The CNN-based methods show powerful image classification capability, but are subject to complicated and significant memory and computing resources.…”

Section: Introductionmentioning

confidence: 99%

Withdrawn: A hybrid feature selection‐based approach for brain tumor detection and automatic segmentation on multiparametric magnetic resonance images

Chen

Ban

et al. 2021

Medical Physics

View full text Add to dashboard Cite

Purpose To develop a novel method based on feature selection, combining convolutional neural network (CNN) and ensemble learning (EL), to achieve high accuracy and efficiency of glioma detection and segmentation using multiparametric MRIs. Methods We proposed an evolutionary feature selection‐based hybrid approach for glioma detection and segmentation on 4 MR sequences (T2‐FLAIR, T1, T1Gd, and T2). First, we trained a lightweight CNN to detect glioma and mask the suspected region to process large batch of MRI images. Second, we employed a differential evolution algorithm to search a feature space, which composed of 416‐dimensions radiomics features extracted from four sequences of MRIs and 128‐dimensions high‐order features extracted by the CNN, to generate an optimal feature combination for pixel classification. Finally, we trained an EL classifier using the optimal feature combination to segment whole tumor (WT) and its subregions including non‐enhancing tumor (NET), peritumoral edema (ED), and enhancing tumor (ET) in the suspected region. Experiments were carried out on 300 glioma patients from the BraTS2019 dataset using fivefold cross‐validation, and the model was independently validated using the rest 35 patients from the same database. Results The approach achieved a detection accuracy of 98.8% using four MRIs. The Dice coefficients (and standard deviations) were 0.852 ± 0.057, 0.844 ± 0.046, and 0.799 ± 0.053 for segmentation of WT (NET+ET+ED), tumor core (NET+ET), and ET, respectively. The sensitivities and specificities were 0.873 ± 0.074, 0.863 ± 0.072, and 0.852 ± 0.082; the specificities were 0.994 ± 0.005, 0.994 ± 0.005, and 0.995 ± 0.004 for the WT, tumor core, and ET, respectively. The performances and calculation times were compared with the state‐of‐the‐art approaches, our approach yielded a better overall performance with average processing time of 139.5 s per set of four sequence MRIs. Conclusions We demonstrated a robust and computational cost‐effective hybrid segmentation approach for glioma and its subregions on multi‐sequence MR images. The proposed approach can be used for automated target delineation for glioma patients.

show abstract

“…Dalam beberapa kasus yang rumit, tahap biopsi atau penetapan kelas dan jenis tumor menjadi pekerjaan yang membingungkan dan membosankan bagi dokter atau ahli radiologi [3]. Kasus-kasus tersebut memerlukan ahli untuk menganalisa tekstur tumor, melokalisasi tumor, menerapkan filter pada gambar jika diperlukan agar MRI menjadi lebih jelas dan akhirnya menyimpulkan tingkat dari tumor otak tersebut.…”

Section: Pendahuluanunclassified

Penerapan Deep Learning Menggunakan VGG-16 untuk Klasifikasi Citra Glioma

Putri

Negara

Sanjaya

2022

json

View full text Add to dashboard Cite

One of the types of brain tumors in humans is glioma. Glioma is considered to be the most common type of primary brain tumor in adults. To determine the follow-up action that will be carried out by the doctor, the level of glioma needs to be known first. Glioma is divided into 3 grades. To be able to distinguish grades from gliomas, a classification process can be carried out using deep learning with CNN architecture. Glioma grade classification applies Histogram Equalization (HE) preprocessing. The training model uses CNN with the VGG-16 architecture. data using split data with a comparison of 70% training 30% testing, 80% training 20% testing, and 90% training 10% testing. The results of this study using original data have better results compared to data using HE preprocessing on batch size 16 testing and split data 90% training 10% testing.

show abstract

Brain Tumor Segmentation and Classification Using MRI Images via Fully Convolution Neural Networks

Cited by 27 publications

References 10 publications

A hybrid feature selection‐based approach for brain tumor detection and automatic segmentation on multiparametric magnetic resonance images

A hybrid feature selection‐based approach for brain tumor detection and automatic segmentation on multiparametric magnetic resonance images

Withdrawn: A hybrid feature selection‐based approach for brain tumor detection and automatic segmentation on multiparametric magnetic resonance images

Penerapan Deep Learning Menggunakan VGG-16 untuk Klasifikasi Citra Glioma

Contact Info

Product

Resources

About