ArticlePDF AvailableLiterature Review


The successful early diagnosis of brain tumors plays a major role in improving the treatment outcomes and thus improving patient survival. Manually evaluating the numerous magnetic resonance imaging (MRI) images produced routinely in the clinic is a difficult process. Thus, there is a crucial need for computer-aided methods with better accuracy for early tumor diagnosis. Computer-aided brain tumor diagnosis from MRI images consists of tumor detection, segmentation, and classification processes. Over the past few years, many studies have focused on traditional or classical machine learning techniques for brain tumor diagnosis. Recently, interest has developed in using deep learning techniques for diagnosing brain tumors with better accuracy and robustness. This study presents a comprehensive review of traditional machine learning techniques and evolving deep learning techniques for brain tumor diagnosis. This review paper identifies the key achievements reflected in the performance measurement metrics of the applied algorithms in the three diagnosis processes. In addition, this study discusses the key findings and draws attention to the lessons learned as a roadmap for future research.
Contents lists available at ScienceDirect
Magnetic Resonance Imaging
journal homepage:
Review Article
A review on brain tumor diagnosis from MRI images: Practical implications,
key achievements, and lessons learned
Mahmoud Khaled Abd-Ellah
, Ali Ismail Awad
, Ashraf A.M. Khalaf
, Hesham F.A. Hamed
Electronics and Communications Department, Al-Madina Higher Institute for Engineering and Technology, Giza, Egypt
Department of Computer Science, Electrical and Space Engineering, Luleå University of Technology, Luleå 97187, Sweden
Faculty of Engineering, Al-Azhar University, P.O. Box 83513, Qena, Egypt
Electronics and Communications Department, Faculty of Engineering, Minia University, Minia, Egypt
Brain tumor diagnosis
Computer-aided methods
MRI images
Tumor detection
Tumor segmentation
Tumor classication
Traditional machine learning techniques
Deep learning techniques
The successful early diagnosis of brain tumors plays a major role in improving the treatment outcomes and thus
improving patient survival. Manually evaluating the numerous magnetic resonance imaging (MRI) images
produced routinely in the clinic is a dicult process. Thus, there is a crucial need for computer-aided methods
with better accuracy for early tumor diagnosis. Computer-aided brain tumor diagnosis from MRI images consists
of tumor detection, segmentation, and classication processes. Over the past few years, many studies have
focused on traditional or classical machine learning techniques for brain tumor diagnosis. Recently, interest has
developed in using deep learning techniques for diagnosing brain tumors with better accuracy and robustness.
This study presents a comprehensive review of traditional machine learning techniques and evolving deep
learning techniques for brain tumor diagnosis. This review paper identies the key achievements reected in the
performance measurement metrics of the applied algorithms in the three diagnosis processes. In addition, this
study discusses the key ndings and draws attention to the lessons learned as a roadmap for future research.
1. Introduction
Brain tumors consist of abnormally growing tissue resulting from
the uncontrolled multiplication of cells, and this tissue has no physio-
logical function inside the brain. Tumors not only increase the size of
and pressure in the brain but also cause swelling, all of which cause
abnormal neurological symptoms. According to the National Brain
Tumor Foundation (NBTF), the number of people in developed coun-
tries who die as a result of brain tumors has increased by 300% [1,2].
Brain tumors are classied as either metastatic or primary brain tumors.
In primary tumors, the cells are originally brain cells, but in metastatic
tumors, the cancer cells have spread into the brain from another in-
fected area of the body. Gliomas are the main type of tumor currently
attracting the interest of brain tumor researchers. The term glioma
describes dierent types of gliomas, ranging from high-grade (HG) tu-
mors, called glioblastoma multiforme (GBM), to low-grade (LG) tumors,
such as oligodendrogliomas or astrocytomas. Chemotherapy, radio-
therapy, and surgery may be applied to treat gliomas [3].
The main goal of computerized brain tumor diagnosis is to obtain
important clinical information regarding the tumor presence, location,
and type. The information obtained through clinical imaging can guide
and control any future interventions and thus leads to the correct di-
agnosis and treatment of the tumor. These automatic brain tumor di-
agnosis methods include dierent techniques that can be organized in a
pyramid. At each stage of the pyramid, distinct techniques are needed
to prepare, select, label, and describe the data, as indicated in [4].
Early tumor diagnosis plays a signicant role in enhancing treat-
ment possibilities. Brain imaging techniques, such as positron emission
tomography (PET), single-photon emission computed tomography
(SPECT), computed tomography (CT), magnetic resonance imaging
(MRI), and magnetic resonance spectroscopy (MRS), are used to pro-
vide information about the location, size, shape, and type of brain
tumor to assist in the diagnosis. MRI provides rich information about
the anatomy of human tissues, and due to its widespread availability
and soft tissue contrast, it is considered to be a standard technique. MRI
uses radio frequency signals with a powerful magnetic eld to produce
images of human tissues [5,6].
Brain tumor diagnosis consists of tumor detection, segmentation,
and classication processes. Brain tumor detection techniques are
mainly used to identify MRI images of tumors from a database, which is
Received 31 August 2018; Received in revised form 20 May 2019; Accepted 20 May 2019
Corresponding author.
E-mail addresses: (M.K. Abd-Ellah), (A.I. Awad), (A.A.M. Khalaf), (H.F.A. Hamed).
Magnetic Resonance Imaging 61 (2019) 300–318
0730-725X/ © 2019 Elsevier Inc. All rights reserved.
considered a basic and obvious process. However, brain tumor seg-
mentation techniques are used for localizing and isolating dierent
tumor tissues inside MRI images. Furthermore, brain tumor classica-
tion techniques are used to classify abnormal images as malignant or
benign tumors. These three hybrid methods and techniques present
useful information to radiologists and aid in the understanding of MRI
information required for diagnosis.
Signicant work in the eld of brain tumor diagnosis has been
conducted by many researchers over the past several decades. Both
tumor segmentation and classication methods have been proposed.
The clinical acceptance of diagnosis methods has depended on the de-
gree of user supervision and the simplicity of computation [4]. How-
ever, the clinical applications are still limited, and although an ex-
tensive amount of work has been performed, clinicians still depend on
the manual projection of the tumor, probably because of the lack of a
connection between clinicians and researchers.
This study presents a review of the most important existing brain
tumor diagnosis methods. The survey focuses on MRI brain tumor di-
agnosis with traditional machine learning and deep learning techni-
ques. Although several reviews are available in the literature, a specic
focus is typically placed on one particular process, such as segmentation
in [4-9], classication in [10], or diagnosis in [3,11-13]. This article
oers a comprehensive overview of the whole brain tumor diagnosis
system in terms of tumor detection, segmentation, and classication. In
addition, the study covers the applications of traditional machine
learning and deep learning approaches in each phase or process of the
The contributions of this study span multiple dimensions. First, the
study takes the entire brain tumor diagnosis system using MRI images
into account and considers the current conventional machine learning
and deep learning approaches for brain tumor diagnosis. Second, a
complete picture of the dierences between and similarities of several
techniques is provided in terms of their performance in three brain
tumor diagnosis processes. Furthermore, the study introduces the
available MRI image databases that are used in evaluating the perfor-
mance of the reported techniques. Third, an extended discussion of the
current research ndings and possible future improvements and trends
is provided. Fourth, a potential trial of integrating the three diagnosis
processes is outlined for future research using a single automated
system or model.
The remainder of this review is structured as follows. Section 2
presents necessary information on the brain tumor diagnosis frame-
work, the benets of machine learning and deep learning techniques for
radiologists and clinicians, brain MRI images and available databases,
and the deep learning paradigm. Section 3 is dedicated to an in-depth
discussion of brain tumor diagnosis, which consists of tumor detection,
segmentation, and classication. This section introduces the key
achievements that have emerged from using classical machine learning
and trending deep learning techniques and related comparisons.
Section 4 is dedicated to discussing the research ndings, the limita-
tions, and the lessons learned. Finally, conclusions are provided in
Section 5. A concise representation of the ow of this survey is shown in
Fig. 1.
2. Preliminaries
The general framework of a computer-aided diagnosis (CAD) system
for brain tumor diagnosis using MRI images, as summarized in Fig. 2,
consists of data collection, preprocessing, segmentation, feature ex-
traction, feature selection, feature reduction, classication, perfor-
mance evaluation and diagnosis. Data collection is the process of ob-
taining the brain images required for diagnosis that will be fed through
the diagnosis techniques. Brief explanations of the image types and the
databases are provided in Sections 2.2 and 2.3, respectively. The pre-
processing stage is a simple but necessary stage of brain image analysis.
Preprocessing is commonly used to improve the resolution and contrast
and to reduce the noise in the images. Several preprocessing approaches
can be used, such as unsharp masking, median lters and Wiener lters.
Median lters are most commonly used in the preprocessing stage to
preserve image edges [3].
Several segmentation methods are used to perform the segmenta-
tion task. One of these methodologies is the multilayer articial neural
network (MANN). Many researchers have used the MANN and maintain
a similar structure and learning algorithm but mention it in dierent
ways, such as the feedforward backpropagation neural network
(FFBPNN), the backpropagation neural network (BPNN), and the mul-
tilayer perceptron (MLP). Other segmentation methodologies and
techniques include edge-based algorithms, region-based techniques,
and clustering algorithms (e.g., k-means, mean shift, fuzzy c-means
(FCM), and expectation maximization), and high performance can be
achieved by deep learning algorithms. There are dierent methods for
feature extraction, e.g., wavelet transform, texture features, Gabor
features, principal component analysis (PCA), decision boundary fea-
ture extraction, and spectral mixture analysis. Many dierent ap-
proaches have been developed for medical image segmentation and
analysis, as described in [14].
An increase in the feature vector dimension considerably decreases
the accuracy of the system. Hence, feature selection techniques are
applied to select the most important features. The popular feature se-
lection algorithms used in the literature are sequential backward se-
lection (SBS), genetic algorithm (GA), particle swarm optimization
(PSO), and sequential forward selection (SFS), while independent
component analysis (ICA), PCA, and kernel PCA are used for feature
dimensionality reduction [10].
Several classiers are used in the detection and classication stages,
and they are reported here as they are mentioned in the published
papers, such as support vector machine (SVM), kernel SVM (KSVM),
feedforward backpropagation neural network (FFBPNN), self-orga-
nizing mapping neural network (SOMNN), backpropagation neural
network (BPNN), probabilistic neural network (PNN), articial neural
network (ANN), probabilistic neural network-radial basis function
(PNN-RBF), normalized cross-correlation (NCC), PSO, sequential
minimal optimization (SMO), learning vector quantization (LVQ),
multilayer perceptron (MLP), k-nearest neighbor (KNN), hybrid of ge-
netic algorithm and support vector machine (GA-SVM), spectral clus-
tering independent component analysis (SC-ICA), least-squares feature
transformation (LSFT), fuzzy Hopeld neural network algorithm
(FHNN), sparse representation classication (SRC), unsupervised linear
discriminant analysis (ULDA), FCM and convolutional neural network
(CNN). Most of these tools are used eciently; however, the highest
performances are achieved by deep learning algorithms.
2.1. Machine learning: a clinical perspective
From a clinical perspective, the goal of brain tumor diagnosis is to
accurately detect and localize tumor tissues from MRI images using
well-established clinical information and diagnostic features. The cor-
rect clinical diagnosis should lead to timely and appropriate disease
treatment. To achieve this goal, it is important to obtain clinical
knowledge and a database representing the information at a high level
from which a decision and diagnosis can be made [4]. Manual brain
tumor diagnosis is time consuming and less accurate due to the variety
of tumor shapes and types, as there are more than 120 known types of
brain tumors.
Machine learning has received considerable interest in modern
computing, and the medical eld is one of the areas of interest. The
brain tumor diagnosis eld has adopted dierent modern machine
learning techniques. For instance, advanced algorithms such as image
denoising [15,16], image reconstruction [17-19], skull stripping, and
registration [20] have been applied to simplify the use of brain images
and to enhance the obtained information. Therefore, machine learning
has created opportunities for collaboration among clinicians, engineers
M.K. Abd-Ellah, et al. Magnetic Resonance Imaging 61 (2019) 300–318
... With the advancement of technology in medical sciences, imaging techniques are being used increasingly in medical radiation [8]. MRIs are noninvasive imaging technologies that produce detailed threedimensional anatomical images that are often used for disease detection, diagnosis, and treatment monitoring [9]. The idea behind MRI is to detect changes in the direction of rotation of protons that make up the water that makes up living tissues through sophisticated technology [10]. ...
... There are various representations of datasets used in medical diagnosis like Physiologic imaging [21] as well as high-resolution structural imaging [22]. In the last few decades, different imaging modalities have been introduced to aid the study and diagnosis of brain tumors, such as Magnetic Resonance Imaging (MRI) [9], Diffusion-Weighted Imaging Techniques [23], MR Spectroscopy [24], Perfusion Imaging [25] etc. After dataset collection, the next step is data pre-processing Data pre-processing is the process of applying changes to the collected raw data in order to create a clean data that can be fed to an algorithm or machine. ...
Full-text available
Brain cancer is a disease of the brain caused by a brain tumor. A brain tumor is the development of cells in the brain that grow in an unregulated and unnatural manner. Patients may suffer irreversible brain damage or even death if these tumors are not detected and treated properly. As with all types of treatment, Positional information and tumor size are critical for conventional systems. Thus, establishing a meticulous and automated approach to providing information to medical practitioners is required. With machine learning, deep learning, and several imaging modalities, physicians may now more reliably detect tumor types in a shorter period. The paper aims to provide an overview of newly developed systems that use machine learning and deep learning approaches to analyze various medical imaging modalities in the case of diagnosing brain tumors. Datasets used by the authors, dataset partitioning strategies, and different performance evaluation matrices are also described in this paper. To better understand the policy of categorization, we propose a taxonomy here where we have categorized deep learning and machine learning based systems with respect to single classifier, multiple classifiers, single dataset and multiple dataset. Finally, we focus on the challenges of deep learning algorithms for brain tumor classification and possible future trends in this field.
... If brain tumours are not detected quickly, they can cause permanent brain damage or even death. According to the National Brain Tumour Foundation (NBTF), the number of deaths due to brain tumours in developed countries has increased by 300% [1]. ...
Full-text available
The automatic segmentation of brain tumours is a critical task in patient disease management. It can help specialists easily identify the location, size, and type of tumour to make the best decisions regarding the patients' treatment process. Recently, deep learning methods with attention mechanism helped increase the performance of segmentation models. The proposed method consists of two main parts: the first part leverages a deep neural network architecture for biggest tumour detection (BTD) and in the second part, ResNet152V2 makes it possible to segment the image with the attention block and the extraction of local and global features. The custom attention block is used to consider the most important parts in the slices, emphasizing on related information for segmentation. The results show that the proposed method achieves average Dice scores of 0.81, 0.87 and 0.91 for enhancing core, tumour core and whole tumour on BraTS2020 dataset, respectively. Compared with other segmentation approaches, this method achieves better performance on tumour core and whole tumour. Further comparisons on BraTS2018 and BraTS2017 validation datasets show that this method outperforms other models based on Dice score and Hausdorff criterion.
... 15 Opting manual segmentation results in complex task which takes more time for processing, especially for brain tumor diagnosis. 16 As an effective solution, machine learning turned to be the best solution. 17 Random Forest Classifier has been utilized to improve the identification of brain tumors in multispectral MRI. ...
Full-text available
One of the most difficult problems that develop when brain cells start to grow out of control is a brain tumor, which is regarded as the most lethal disease of the century. Finding and identifying malignant brain magnetic resonance imaging (MRI) images is the major challenge before therapy. Researchers have been putting a lot of effort into creating the best method for more accurate real‐world medical image recognition. For manual categorization, it is quite time‐consuming to segment large quantities of MRI data. To mitigate these issues, this paper suggests the information exchange gateway‐based residual UNet (IEGResUNet) model, which uses the ResUNet model as a base model. Additionally, including principal component analysis (PCA) data augmentation will increase the model's efficiency while also enhancing its speed. The IEGResUNet model shows an ablation investigation on three Brats datasets, with and without PCA augmentation. The results demonstrate that IEGResUNet will improve segmentation effectiveness and can also manage the imbalance in input data when PCA data augmentation models are included. The dice score on BraTS 2019 for whole tumor, region of core tumor, and region of enhancing tumor were 0.9083, 0.883, and 0.8106 respectively. Also, on BraTS 2020, the dice score for WT, CT, and ET 0.9083, 0.883, and 0.8106 was respectively. Similarly, on BraTS 2021, the dice score for WT, CT, and ET was 0.8737, 0.8866, and 0.7963 respectively. Comparing against baseline models, the IEGResUNet scored well in terms of dice score and intersection over union.
Brain tumors are created when unusual cells develop within the brain. These tumors can be divided into four groups, and some can be surgically removed while others gradually spread to neighboring tissues. In this study, we explore the classification of brain tumors using a convolutional neural network (CNN) and the concept of transfer learning. We also attempted to deploy the proposed model on a web application.
Brain tumor detection is challenging for radiologists. The early detection of brain tumors is critical, and automated techniques are necessary to achieve this goal. In this study, an automated method is proposed to distinguish between malignant and non-cancerous brain Magnetic Resonance Images (MRI). An ensemble technique was proposed that includes two Deep Learning (DL) models, a 6-Convolutional Neural Network (6-CNN) model with an efficient end-to-end, and a pre-trained Residual Network50 (ResNet50) model. The MRI image classification was experimented in two directions: one using the average probabilities of the ensemble model, and the other considering the optimal weights of the ensemble model for a Support Vector Machine (SVM) classifier with different kernels. Two datasets, Harvard and Retrospective Image Registration Evaluation (RIDER), were used to evaluate the performance of the proposed model. The 6-CNN-ResNet-SVM model achieved the highest accuracy of 97.32% for 10-fold validation, with the remaining performance metrics being an Area Under the Curve (AUC) of 0.98%, sensitivity of 93.62%, specificity of 98%, False Negative Rate (FNR) of 0.06, and False Positive Rate (FPR) of 0.00 for the linear kernel. The proposed model can identify tumors more accurately and quickly than existing approaches.
The abnormal growth of brain cells is a disease that can damage human brains and lead to malignant brain cancer. This abnormal growth in the brain is called a brain tumor. In the past few years, the number of brain tumor-related patients has increased at an extraordinary rate, due to which brain tumor is at the tenth position in the list of common tumors. But if a brain tumor is detected very early, it is possible to increase the way to get rid of this disease. Researchers are working tirelessly to develop automatic systems for brain tumor recognition. Hence, this paper proposes an automated system for brain tumor recognition based on deep learning and image processing. The dataset used in this article was collected from Kaggle and was not balanced. The dataset was preprocessed using a high boost filter and non-local means denoising technique, and then augmentation and SMOTE were applied to balance the dataset. Finally, different deep learning architectures were utilized. Among them, the ResNet50 model achieved 99.62% accuracy for 15-class recognition. The experimental result showed the reliability of the proposed model. This research will enable the research community to explore further brain tumor recognition from MRI using deep learning. It will also help the physician to detect brain tumors earlier.
Brain tumor has become one of the fatal causes of death worldwide in recent years, affecting many individuals annually and resulting in loss of lives. Brain tumors are characterized by the abnormal or irregular growth of brain tissues that can spread to nearby tissues and eventually throughout the brain. Although several traditional machine learning and deep learning techniques have been developed for detecting and classifying brain tumors, they do not always provide an accurate and timely diagnosis. This study proposes a conditional generative adversarial network (CGAN) that leverages the fine-tuning of a convolutional neural network (CNN) to achieve more precise detection of brain tumors. The CGAN comprises two parts, a generator and a discriminator, whose outputs are used as inputs for fine-tuning the CNN model. The publicly available dataset of brain tumor MRI images on Kaggle was used to conduct experiments for Datasets 1 and 2. Statistical values such as precision, specificity, sensitivity, F1-score, and accuracy were used to evaluate the results. Compared to existing techniques, our proposed CGAN model achieved an accuracy value of 0.93 for Dataset 1 and 0.97 for Dataset 2.
Full-text available
This paper tries to give a gentle introduction to deep learning in medical image processing, proceeding from theoretical foundations to applications. We first discuss general reasons for the popularity of deep learning, including several major breakthroughs in computer science. Next, we start reviewing the fundamental basics of the perceptron and neural networks, along with some fundamental theory that is often omitted. Doing so allows us to understand the reasons for the rise of deep learning in many application domains. Obviously medical image processing is one of these areas which has been largely affected by this rapid progress, in particular in image detection and recognition, image segmentation, image registration, and computer-aided diagnosis. There are also recent trends in physical simulation, modeling, and reconstruction that have led to astonishing results. Yet, some of these approaches neglect prior knowledge and hence bear the risk of producing implausible results. These apparent weaknesses highlight current limitations of deep learning. However, we also briefly discuss promising approaches that might be able to resolve these problems in the future.
Full-text available
Brain tumour is a serious disease, and the number of people who are dying due to brain tumours is increasing. Manual tumour diagnosis from magnetic resonance images (MRIs) is a time consuming process and is insufficient for accurately detecting, localizing, and classifying the tumour type. This research proposes a novel two-phase multi-model automatic diagnosis system for brain tumour detection and localization. In the first phase, the system structure consists of preprocessing, feature extraction using a convolutional neural network (CNN), and feature classification using the error-correcting output codes support vector machine (ECOC-SVM) approach. The purpose of the first system phase is to detect brain tumour by classifying the MRIs into normal and abnormal images. The aim of the second system phase is to localize the tumour within the abnormal MRIs using a fully designed five-layer region-based convolutional neural network (R-CNN). The performance of the first phase was assessed using three CNN models, namely, AlexNet, Visual Geometry Group (VGG)-16, and VGG-19, and a maximum detection accuracy of 99.55% was achieved with AlexNet using 349 images extracted from the standard Reference Image Database to Evaluate Response (RIDER) Neuro MRI database. The brain tumour localization phase was evaluated using 804 3D MRIs from the Brain Tumor Segmentation (BraTS) 2013 database, and a DICE score of 0.87 was achieved. The empirical work proved the outstanding performance of the proposed deep learning-based system in tumour detection compared to other non-deep-learning approaches in the literature. The obtained results also demonstrate the superiority of the proposed system concerning both tumour detection and localization.
Compressive sensing can be used to reduce noise. However, some details also are sparsified. This paper presents a new denoising model based on compressive sensing with L1 and Hessian regularizations for magnetic resonance images denoising. Firstly, the proposed model can make an image more sparse through L1 regularization and reduce noise. Secondly, Hessian regularization is introduced to protect some details from being over-smoothed. Experimental results demonstrate that the proposed method is efficient, and has better denoising capability.
The health care sector is totally different from any other industry. It is a high priority sector and consumers expect the highest level of care and services regardless of cost. The health care sector has not achieved society’s expectations, even though the sector consumes a huge percentage of national budgets. Mostly, the interpretations of medical data are analyzed by medical experts. In terms of a medical expert interpreting images, this is quite limited due to its subjectivity and the complexity of the images; extensive variations exist between experts and fatigue sets in due to their heavy workload. Following the success of deep learning in other real-world applications, it is seen as also providing exciting and accurate solutions for medical imaging, and is seen as a key method for future applications in the health care sector. In this chapter, we discuss state-of-the-art deep learning architecture and its optimization when used for medical image segmentation and classification. The chapter closes with a discussion of the challenges of deep learning methods with regard to medical imaging and open research issue.
A review on the recent segmentation and tumor grade classification techniques of brain Magnetic Resonance (MR) Images is the objective of this paper. The requisite for early detection of a brain tumor and its grade is the motivation for this study. In Magnetic Resonance Imaging (MRI), the tumor might appear clear but physicians need quantification of the tumor area for further treatment. This is where the digital image processing methodologies along with machine learning aid further diagnosis, treatment, prior and post-surgical procedures, synergizing between the radiologist and computer. These hybrid techniques provide a second opinion and assistance to radiologists in understanding medical images hence improving diagnostic accuracy. This article aims to retrospect the current trends in segmentation and classification relevant to tumor infected human brain MR images with a target on gliomas which include astrocytoma. The methodologies used for extraction and grading of tumors which can be integrated into the standard clinical imaging protocols are elucidated. Lastly, a crucial assessment of the state of the art, future developments and trends are dissertated.
Conference Paper
Tracking the progression of brain tumors is a challenging task, due to the slow growth rate and the combination of different tumor components, such as cysts, enhancing patterns, edema and necrosis. In this paper, we propose a Deep Neural Network based architecture that does automatic segmentation of brain tumor, and focuses on improving accuracy at the edges of these different classes. We show that enhancing the loss function to give more weight to the edge pixels significantly improves the neural network’s accuracy at classifying the boundaries. In the BRATS 2016 challenge, our submission placed third on the task of predicting progression for the complete tumor region.
Conference Paper
Magnetic Resonance Imaging is the preferred imaging modality for assessing brain tumors, and segmentation is necessary for diagnosis and treatment planning. Thus, robust automatic segmentation methods are required. Machine learning proposals where the model is learned from data are quite successful. Hierarchical segmentation approaches firstly segment the whole tumor, followed by intra-tumor tissue identification. However, results comparing it with single stages approaches are needed, as state of the art results are also achieved by all-at-once strategies. Currently, fully convolutional networks approaches for segmentation are very efficient. In this paper, a hierarchical approach for brain tumor segmentation using a fully convolutional network is studied. The evaluation is performed on the Brain Tumor Segmentation Challenge 2013 dataset, and we report the metrics Dice Score Coefficient, Positive Predictive Value, and Sensitivity. Results show benefits from segmenting the complete tumor first, over all tissues in one stage. Moreover, the tumor core also benefits from such approach. This behavior may be justified by the high data imbalance observed between tumor and normal tissues, which is mitigated by considering the tumor as a whole.