Application of deep learning for automatic segmentation of brain tumors on magnetic resonance imaging: a heuristic approach in the clinical scenario

Ieva, Antonio Di; Russo, Carlo; Liu, Sidong; Jian, Anne; Bai, Michael Y.; Qian, Yi; Magnussen, John

doi:10.1007/s00234-021-02649-3

Cited by 47 publications

(21 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Antonio et al, using magnetic resonance imaging (MRI), suggested an accurate brain tumor segmentation method that has a wide range of applications [ 25 ], including radiosurgery planning. Automatic segmentation has been made possible by breakthroughs in artificial intelligence, notably deep learning (DL), which have paved the way for the abolition of labor-intensive and operator-dependent manual segmentation.…”

Section: Related Workmentioning

confidence: 99%

Brain Tumor Segmentation Using Deep Capsule Network and Latent-Dynamic Conditional Random Fields

et al. 2022

View full text Add to dashboard Cite

Because of the large variabilities in brain tumors, automating segmentation remains a difficult task. We propose an automated method to segment brain tumors by integrating the deep capsule network (CapsNet) and the latent-dynamic condition random field (LDCRF). The method consists of three main processes to segment the brain tumor—pre-processing, segmentation, and post-processing. In pre-processing, the N4ITK process involves correcting each MR image’s bias field before normalizing the intensity. After that, image patches are used to train CapsNet during the segmentation process. Then, with the CapsNet parameters determined, we employ image slices from an axial view to learn the LDCRF-CapsNet. Finally, we use a simple thresholding method to correct the labels of some pixels and remove small 3D-connected regions from the segmentation outcomes. On the BRATS 2015 and BRATS 2021 datasets, we trained and evaluated our method and discovered that it outperforms and can compete with state-of-the-art methods in comparable conditions.

show abstract

Section: Related Workmentioning

confidence: 99%

Brain Tumor Segmentation Using Deep Capsule Network and Latent-Dynamic Conditional Random Fields

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Deep learning algorithms and CNNs have been applied in research for radiological diagnosis of a number of pathologies [21][22][23][24][25][26]; however, current literature on AI applications in CM1 is limited. Urbizu et al [27,28] proposed a diagnostic predictive model based on machine learning, identifying and utilizing different anatomical morphometric parameters rather than the standard sole use of the measurement of tonsillar herniation.…”

Section: Introductionmentioning

confidence: 99%

Use of deep learning in the MRI diagnosis of Chiari malformation type I

et al. 2022

Self Cite

View full text Add to dashboard Cite

Purpose To train deep learning convolutional neural network (CNN) models for classification of clinically significant Chiari malformation type I (CM1) on MRI to assist clinicians in diagnosis and decision making. Methods A retrospective MRI dataset of patients diagnosed with CM1 and healthy individuals with normal brain MRIs from the period January 2010 to May 2020 was used to train ResNet50 and VGG19 CNN models to automatically classify images as CM1 or normal. A total of 101 patients diagnosed with CM1 requiring surgery and 111 patients with normal brain MRIs were included (median age 30 with an interquartile range of 23–43; 81 women with CM1). Isotropic volume transformation, image cropping, skull stripping, and data augmentation were employed to optimize model accuracy. K-fold cross validation was used to calculate sensitivity, specificity, and the area under receiver operating characteristic curve (AUC) for model evaluation. Results The VGG19 model with data augmentation achieved a sensitivity of 97.1% and a specificity of 97.4% with an AUC of 0.99. The ResNet50 model achieved a sensitivity of 94.0% and a specificity of 94.4% with an AUC of 0.98. Conclusions VGG19 and ResNet50 CNN models can be trained to automatically detect clinically significant CM1 on MRI with a high sensitivity and specificity. These models have the potential to be developed into clinical support tools in diagnosing CM1.

show abstract

“…5 The sub-regions of brain tumor identification are a significant matter in medical applications such as tumor growth monitoring, surgery, radiotherapy, and so forth. 6 Moreover, without identifying the boundary or sub-region of the brain, segmenting the Tumor with a high exactness rate is more complex. 7 The basic brain tumor segmentation system is described in Figure 1.…”

Section: Introductionmentioning

confidence: 99%

An automated brain tumor segmentation framework using a novel fruit fly UNet

Boda¹,

Cherian

Kumar

2022

Concurrency and Computation

View full text Add to dashboard Cite

Summary Brain image analysis and segmentation are the most difficult tasks in medical image processing because of image complexity. Moreover, MRI images are mostly utilized to predict different brain‐based diseases; if the images are complex, the disease prediction accuracy is very low. To overcome this problem, the current research has planned to design a novel fruit fly‐based UNet (FFbU) framework to detect the Tumor accurately. Moreover, the fitness of the fruit fly was upgraded in the UNet pooling module that has tended to gain the finest results. Initially, the standard datasets were gathered from the net source and trained to the system. Consequently, the training error is removed in the primary layer of FFbU then the error‐cleared data is entered into the UNet dense layer for tumor detection and segmentation. Finally, the proposed model is executed in a MATLAB environment, and the proficiency of the designed FFbU model is estimated in terms of accuracy, recall, precision, Dice, and Jaccard. In addition, the planned novel FFbU model has the ability to predict and segment different tumor types.

show abstract

Application of deep learning for automatic segmentation of brain tumors on magnetic resonance imaging: a heuristic approach in the clinical scenario

Cited by 47 publications

References 34 publications

Brain Tumor Segmentation Using Deep Capsule Network and Latent-Dynamic Conditional Random Fields

Brain Tumor Segmentation Using Deep Capsule Network and Latent-Dynamic Conditional Random Fields

Use of deep learning in the MRI diagnosis of Chiari malformation type I

An automated brain tumor segmentation framework using a novel fruit fly UNet

Contact Info

Product

Resources

About