Spatial‐channel relation learning for brain tumor segmentation

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.

“…We compared our results with the other six state‐of‐the‐art approaches 29‐34 . Cheng, et al 29 used spatial‐channel relation learning for brain tumor segmentation.…”

Section: Methodsmentioning

confidence: 99%

“…We compared our results with the other six stateof-the-art approaches. [29][30][31][32][33][34] Cheng, et al 29 used spatial-channel relation learning for brain tumor segmentation. Sun, et al 30 proposed a novel model based on three-dimensional fully convolutional network to create an automated and accurate segmentation.…”

Section: Experiments Settingmentioning

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

“…We compared our results with the other six state‐of‐the‐art approaches 29‐34 . Cheng et al 29 use Spatial‐channel relation learning for brain tumor segmentation.…”

Section: Methodsmentioning

confidence: 99%

“…We compared our results with the other six state-ofthe-art approaches. [29][30][31][32][33][34] Cheng et al 29 use Spatialchannel relation learning for brain tumor segmentation. Sun et al 30 propose a novel model based on 3D fully convolutional network to create an automated and accurate segmentation.…”

Section: Experiments Settingmentioning

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

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.

“…The segmentation performance was improved by penalizing the deviation between the outputs of semantic segmentation and the instance class prediction 23 . The U‐Net and its variations 19,24–27 have shown impressive performance on many medical image segmentation tasks, including the brain glioma segmentation. For examples, the cascade structure network 19 performed well in brain glioma segmentation task by developing a context exploitation module for each subnetwork and modeling the relation between the spatial and channel spaces.…”

Section: Introductionmentioning

confidence: 99%

Attention‐guided multi‐scale context aggregation network for multi‐modal brain glioma segmentation

Cao

et al. 2023

BackgroundAccurate segmentation of brain glioma is a critical prerequisite for clinical diagnosis, surgical planning and treatment evaluation. In current clinical workflow, physicians typically perform delineation of brain tumor subregions slice‐by‐slice, which is more susceptible to variabilities in raters and also time‐consuming. Besides, even though convolutional neural networks (CNNs) are driving progress, the performance of standard models still have some room for further improvement.PurposeTo deal with these issues, this paper proposes an attention‐guided multi‐scale context aggregation network (AMCA‐Net) for the accurate segmentation of brain glioma in the magnetic resonance imaging (MRI) images with multi‐modalities.MethodsAMCA‐Net extracts the multi‐scale features from the MRI images and fuses the extracted discriminative features via a self‐attention mechanism for brain glioma segmentation. The extraction is performed via a series of down‐sampling, convolution layers, and the global context information guidance (GCIG) modules are developed to fuse the features extracted for contextual features. At the end of the down‐sampling, a multi‐scale fusion (MSF) module is designed to exploit and combine all the extracted multi‐scale features. Each of the GCIG and MSF modules contain a channel attention (CA) module that can adaptively calibrate feature responses and emphasize the most relevant features. Finally, multiple predictions with different resolutions are fused through different weightings given by a multi‐resolution adaptation (MRA) module instead of the use of averaging or max‐pooling to improve the final segmentation results.ResultsDatasets used in this paper are publicly accessible, that is, the Multimodal Brain Tumor Segmentation Challenges 2018 (BraTS2018) and 2019 (BraTS2019). BraTS2018 contains 285 patient cases and BraTS2019 contains 335 cases. Simulations show that the AMCA‐Net has better or comparable performance against that of the other state‐of‐the‐art models. In terms of the Dice score and Hausdorff 95 for the BraTS2018 dataset, 90.4% and 10.2 mm for the whole tumor region (WT), 83.9% and 7.4 mm for the tumor core region (TC), 80.2% and 4.3 mm for the enhancing tumor region (ET), whereas the Dice score and Hausdorff 95 for the BraTS2019 dataset, 91.0% and 10.7 mm for the WT, 84.2% and 8.4 mm for the TC, 80.1% and 4.8 mm for the ET. Conclusions: The proposed AMCA‐Net performs comparably well in comparison to several state‐of‐the‐art neural net models in identifying the areas involving the peritumoral edema, enhancing tumor, and necrotic and non‐enhancing tumor core of brain glioma, which has great potential for clinical practice. In future research, we will further explore the feasibility of applying AMCA‐Net to other similar segmentation tasks.