Brain tumor refers to the formation of abnormal cells in the brain. It can be divided into benign and malignant. The main diagnostic methods for brain tumors are plain X-ray film, Magnetic resonance imaging (MRI), and so on. However, these artificial diagnosis methods are easily affected by external factors. Scholars have made such impressive progress in brain tumors classification by using convolutional neural network (CNN). However, there are still some problems: (i) There are many parameters in CNN, which require much calculation. (ii) The brain tumor data sets are relatively small, which may lead to the overfitting problem in CNN. In this paper, our team proposes a novel model (RBEBT) for the automatic classification of brain tumors. We use fine-tuned ResNet18 to extract the features of brain tumor images. The RBEBT is different from the traditional CNN models in that the randomized neural network (RNN) is selected as the classifier. Meanwhile, our team selects the bat algorithm (BA) to optimize the parameters of RNN. We use five-fold cross-validation to verify the superiority of the RBEBT. The accuracy (ACC), specificity (SPE), precision (PRE), sensitivity (SEN), and F1-score (F1) are 99.00%, 95.00%, 99.00%, 100.00%, and 100.00%. The classification performance of the RBEBT is greater than 95%, which can prove that the RBEBT is an effective model to classify brain tumors.
Brain tumor refers to the formation of abnormal cells in the brain. It can be divided into benign and malignant. The cause of the brain tumor is not clear. The etiological investigation can be divided into environmental factors and host factors. At present, the main diagnostic methods of brain tumors are plain X-ray film, Magnetic resonance imaging (MRI), and so on. However, these artificial diagnosis methods are easily affected by external factors, such as fatigue, emotion, and so on. At the same time, the early symptoms of brain tumors are not obvious and are easy to be ignored. Now more and more researchers try to use the artificial intelligence to diagnose brain tumors.
Rehman et al. [
Above reviewing the aforementioned research, scholars have done much impressive progress in brain tumors classification. However, there are several problems: (i) There are many parameters in CNN, which require much calculation. (ii) The brain tumor data sets are relatively small, which may lead to the overfitting problem in CNN.
Our team proposes a novel model (RBEBT) for the automatic classification of brain tumors to solve these above problems. We want to propose a model which can achieve great classification performance in small brain tumors data set. The main contributions of this paper are summarized as: (i) Our team proposes a new model that can accurately classify brain tumors. (ii) A new classifier is proposed to classify the brain tumor faster and more accurately than the traditional CNNs. (iii) The proposed novel model has superior classification to state-of-the-art methods.
The rest structure of this paper is as follows: We introduce the public brain tumor data set in Section 2. The details of the proposed model are presented in Section 3. Several experiments, results, and the corresponding discussions are shown in Section 4. Section 5 is mainly about the conclusion.
We obtain the brain tumor images from the public data set on the Harvard Medical School website (
For image recognition and classification, extracting key features from images is one of the most important steps. Before, people tried to extract features from images by hand, but manually extracting features needs a lot of time and energy, and the results were not very satisfactory. The continuous development of machine learning in computers [
In the RBEBT, we use fine-tuned ResNet18 to extract the features of brain tumor images. The RBEBT is different from the traditional CNN models in that the randomized neural network (RNN) is selected as the classifier. The training time of RNN is shorter than that of the CNN models because of the simpler structure of RNN. What’s more, it is not easy to produce overfitting problems on small data sets in RNN. However, it may also cause some other problems because the parameters in the RNN are random, such as redundant nodes. We use the bat algorithm (BA) to optimize it to get the ideal parameters. The five-fold cross-validation is chosen to verify the superiority of the RBEBT.
Scholars hope that the increasing number of layers in the CNN models could improve the performance. However, the increase in the number of layers leads to the problem of gradient explosion. Many methods have been proposed to alleviate such problems, such as batch normalization (BN). However, gradient degradation has not been well solved. He et al. [
The data set in this paper is classified into two categories, but the output nodes of the pre-trained ResNet18 are 1000. In this paper, our team classifies this public data set into two categories. Therefore, we fine-tune the ResNet18, as given in
This paper chooses the RNN as the classifier. The advantages of RNN are to shorten the training time and avoid the overfitting problem. RNN used in this paper is the extreme learning machine (ELM). The structure of ELM is presented in
Given a data set with the
The formula of the output matrix of the hidden layer is shown as:
The calculation of final output weight (
However, the parameters assigned at random may not be the optimal solution. Our team selects the bat algorithm (BA) to optimize it. Suppose the velocity of the
The optimal position will be updated as:
The emission rate and loudness will be generated when the
Five-fold cross-validation is chosen to verify the superiority of the RBEBT. In this paper, the abnormal brain and the normal brain are defined as the positive and the negative, respectively. Five indexes are selected in this paper, which are accuracy (ACC), specificity (SPE), precision (PRE), sensitivity (SEN), and F1-score (F1). Their equations are shown as below:
The five-fold cross-validation is chosen to verify the superiority of the RBEBT, as shown in
Methods | Fold | ACC | SPE | PRE | SEN | F1 |
---|---|---|---|---|---|---|
RBEBT (Ours) | F 1 | 0.97 | 0.75 | 0.97 | 1.00 | 0.99 |
F 2 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | |
F 3 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | |
F 4 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | |
F 5 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | |
Avr | 0.99 | 0.95 | 0.99 | 1.00 | 1.00 | |
Std | ±0.01 | ±0.10 | ±0.01 | ±0.00 | ±0.01 | |
AlexNet-BA-ELM | F 1 | 0.97 | 1.00 | 1.00 | 0.97 | 0.99 |
F 2 | 0.87 | 0.25 | 0.92 | 0.94 | 0.93 | |
F 3 | 0.95 | 0.50 | 0.95 | 1.00 | 0.97 | |
F 4 | 0.95 | 0.50 | 0.95 | 1.00 | 0.97 | |
F 5 | 0.95 | 0.50 | 0.95 | 1.00 | 0.97 | |
Avr | 0.94 | 0.55 | 0.95 | 0.98 | 0.97 | |
Std | ±0.03 | ±0.24 | ±0.02 | ±0.02 | ±0.02 | |
MobileNet-BA-ELM | F 1 | 0.95 | 0.50 | 0.95 | 1.00 | 0.97 |
F 2 | 0.95 | 0.50 | 0.95 | 1.00 | 0.97 | |
F 3 | 0.97 | 0.75 | 0.97 | 1.00 | 0.99 | |
F 4 | 0.97 | 0.75 | 0.97 | 1.00 | 0.99 | |
F 5 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | |
Avr | 0.97 | 0.70 | 0.97 | 1.00 | 0.98 | |
Std | ±0.02 | ±0.19 | ±0.02 | ±0.00 | ±0.01 | |
ResNet50-BA-ELM | F 1 | 0.90 | 0.75 | 0.97 | 0.91 | 0.94 |
F 2 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | |
F 3 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | |
F 4 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | |
F 5 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | |
Avr | 0.98 | 0.95 | 0.99 | 0.98 | 0.99 | |
Std | ±0.04 | ±0.10 | ±0.01 | ±0.03 | ±0.02 | |
VGG-BA-ELM | F 1 | 0.92 | 1.00 | 1.00 | 0.91 | 0.96 |
F 2 | 0.95 | 0.75 | 0.97 | 0.97 | 0.97 | |
F 3 | 0.97 | 1.00 | 1.00 | 0.97 | 0.99 | |
F 4 | 0.90 | 0.00 | 0.90 | 1.00 | 0.95 | |
F 5 | 0.97 | 1.00 | 1.00 | 0.97 | 0.99 | |
Avr | 0.94 | 0.75 | 0.97 | 0.97 | 0.97 | |
Std | ±0.03 | ±0.39 | ±0.04 | ±0.03 | ±0.02 | |
ResNet18-ELM | F 1 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 |
F 2 | 0.97 | 0.75 | 0.97 | 1.00 | 0.99 | |
F 3 | 0.97 | 1.00 | 1.00 | 0.97 | 0.99 | |
F 4 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | |
F 5 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | |
Avr | 0.99 | 0.95 | 0.99 | 0.99 | 0.99 | |
Std | ±0.01 | ±0.10 | ±0.01 | ±0.01 | ±0.01 | |
Fine-tuned ResNet18 | F 1 | 0.90 | 1.00 | 1.00 | 0.89 | 0.94 |
F 2 | 0.72 | 1.00 | 1.00 | 0.69 | 0.81 | |
F 3 | 0.72 | 1.00 | 1.00 | 0.69 | 0.81 | |
F 4 | 0.69 | 1.00 | 1.00 | 0.663 | 0.79 | |
F 5 | 0.64 | 0.75 | 0.96 | 0.63 | 0.76 | |
Avr | 0.73 | 0.95 | 0.99 | 0.71 | 0.82 | |
Std | ±0.09 | ±0.10 | ±0.02 | ±0.09 | ±0.06 |
In this paper, we test five different backbone models, which are ResNet18, AlexNet, MobileNet, ResNet50, and VGG. The results are shown in
The ResNet18 can deal with the problem of gradient explosion by residual connection. Other backbone models may meet the problem of gradient explosion. Therefore, our model can achieve the best performance than other models.
To prove the superiority of our network, we compare the proposed RBEBT with the fine-tuned model and the model with only RNN. The results are shown in
The ELM can get better classification performance in small data set because of its simpler structure. What’s more, the BA is selected to optimize the ELM. Based on these reasons, the RBEBT can get better results than the fine-tuned ResNet18 and ResNet18-ELM.
The proposed RBEBT is compared with seven other state-of-the-art methods, which are 3D-CNN [
Methods | ACC | SPE | PRE | SEN | F1 |
---|---|---|---|---|---|
3D-CNN [ |
98.32 | – | – | – | – |
SVM-CNN [ |
95.82 | 99.30 | 97.30 | – | – |
KNN-CNN [ |
96.25 | – | 96.67 | – | 96.25 |
2D-CNN [ |
91.30 | – | – | – | – |
BPNN [ |
57.23 | 54.50 | 91.71 | 57.54 | 70.72 |
LVQNN [ |
60.05 | 61.00 | 93.08 | 59.94 | 72.92 |
LRC [ |
95.74 | 58.50 | 95.47 | 100.00 | 97.68 |
Note: Bold means the best results, - means not available.
In the RBEBT, we use fine-tuned ResNet18 to extract the features of brain tumor images and select ELM as the classifier. The fine-tuned ResNet18 can extract features accurately and ELM has good performance in small data sets. Therefore, the RBEBT can produce better classification performance than other methods.
In this paper, our team proposes a novel model (RBEBT) for the automatic classification of brain tumors. We use fine-tuned ResNet18 to extract the features of brain tumor images. The RBEBT is different from the traditional CNN models in that the RNN is selected as the classifier. The parameters assigned at random may not be the optimal solution. Our team selects the BA to optimize it. We use five-fold cross-validation to verify the superiority of the RBEBT. The ACC, SPE, PRE, SEN, and F1 are 99.00%, 95.00%, 99.00%, 100.00%, and 100.00%. The classification performance of the RBEBT is greater than 95%, which can prove that the RBEBT is an effective model to classify brain tumors.
The limitations of this paper are: (i) The data set used in this paper is small; (ii) There are only two categories in this paper. In the future, we will apply our model to more public brain tumors data sets to verify its classification performance. Meanwhile, our team will try more methods, such as VIT, U-Net, etc. In addition, we will test our model in other diseases classification.