Brain tumor segmentation is the process of separating the tumor from normal brain tissues; in clinical routine, it provides useful information for diagnosis and treatment planning. However, it is still a challenging task due to the irregular form and confusing boundaries of tumors. Tumor cells thermally represent a heat source; their temperature is high compared to normal brain cells. The main aim of the present paper is to demonstrate that thermal information of brain tumors can be used to reduce false positive and false negative results of segmentation performed in MRI images. Pennes bioheat equation was solved numerically using the finite difference method to simulate the temperature distribution in the brain; Gaussian noises of ±2% were added to the simulated temperatures. Canny edge detector was used to detect tumor contours from the calculated thermal map, as the calculated temperature showed a large gradient in tumor contours. The proposed method is compared to Chan–Vese based level set segmentation method applied to T1 contrast-enhanced and Flair MRI images of brains containing tumors with ground truth. The method is tested in four different phantom patients by considering different tumor volumes and locations and 50 synthetic patients taken from BRATS 2012 and BRATS 2013. The obtained results in all patients showed significant improvement using the proposed method compared to segmentation by level set method with an average of 0.8% of the tumor area and 2.48% of healthy tissue was differentiated using thermal images only. We conclude that tumor contours delineation based on tumor temperature changes can be exploited to reinforce and enhance segmentation algorithms in MRI diagnostic.
A brain tumor represents a set of abnormal cells that reproduce in the brain in an uncontrolled way. There are large varieties of brain tumor types that are classified into two categories, benign (noncancerous) brain tumors are less aggressive, formed slowly, and most often remain isolated from surrounding brain normal tissues; they do not spread to other regions of the brain or other parts in the human body and are generally easier to surgically extract than malignancies. Malignant brain tumors (cancerous) are not always easy to distinguish them from surrounding normal tissues. Therefore, it is sometimes difficult to extract them entirely without damaging the surrounding brain tissues (
Magnetic Resonance Imaging or MRI is a noninvasive medical imaging modality commonly used in the clinical routine as it offers images with high spatial resolution and high contrast between soft tissues. MRI provides rich information about shape, size, and localization of brain tumors for more accurate diagnosis and treatment planning [
Accurate segmentation of brain tumors from MRI images represents a crucial and challenging task in diagnosis and treatment planning. Image segmentation is an active field in medical imaging, which consists in extracting from the image one or more regions forming the area of interest. Various algorithms have been developed in the literature to perform brain tumor detection, including threshold-based methods [
Brain tumor segmentation consists of extracting the tumor region from healthy brain tissues; the existence of brain tumors can often be detectable. However, accurate and effective segmentation of tumors remains a challenging task, since the tumors can have different sizes and locations. Their structures are often nonrigid and complex in shape and have various appearance properties. Besides, they have intensities overlapping with normal brain tissues and especially in tumor borders; they show significant variable appearances from patient to patient [
Human body temperature distribution depends on several factors including heat energy generated by cellular metabolism and blood flow, as these are altered in disease; the temperature distribution changes in pathological tissues. The blood flow plays an essential role in the body thermoregulation mechanism, which removes heat from a region with a higher temperature and increases heat in the cooled region. Tumor cells generally generate more heat than adjacent healthy cells due to their high metabolic activity and the blood flow. In the tumorous regions, the blood flow can be significantly less than that in the surrounding healthy tissues [
Consequently, the tumor temperature rises higher than normal tissues [
In this paper, we developed a new approach to improve the segmentation of brain tumors performance in term of accuracy, based on temperature profiles changes in the tumorous region. The temperature distribution in the brain with the tumor is calculated using Pennes bioheat equation. Next, Canny edge detection method was applied in the calculated thermal image to estimate tumor contours, based on the abrupt change of temperature in tumor contours. The obtained results are compared with Chan–Vese based level set segmentation in MRI images.
The rest of this paper presents the proposed method in Section
Temperature distribution in the brain with tumors was simulated by Pennes bioheat transfer equation [
To solve (
Table
Thermal properties used for temperature simulation.
Material | Property name | |||||
---|---|---|---|---|---|---|
| | | | | Refs | |
CSF | 0.6 | 1000 | 4200 | 0 | 0 | [ |
GM | 0.565 | 1035.5 | 3680 | 16,229 | 0.013289 | [ |
WM | 0.503 | 1027.4 | 3600 | 4517.9 | 0.0036956 | [ |
Tumor | 0.565 | 1027.4 | 3600 | 25,000 | 0.0005 | [ |
Towards the stability and convergence of (
Towards the segmentation of brain tumors in T1 contrast and Flair MRI images, we have used active contours without edges proposed by Chan and Vese [
The calculated temperature distribution (thermal image) in this study showed that a large gradient in tumor borders is the reason to use an edge detection method to track the tumor contours. An edge in the image represents a strong local variation in pixels intensity, usually, arising on the boundary between two different regions within an image. Edge detection is the process of objects boundaries detection within an image by finding the changes in discontinuities intensities. There are several edge detection methods, developed in the literature. The most famous methods are the edge detection operators of Roberts, Sobel, Prewitt, Kirsh Marr-Hildreth, Robinson, LoG and Canny, and so on. Here, in this work, to detect tumor contours based on temperature distribution, Canny edge detection method [
To evaluate the performance of brain tumor segmentation, we have used five metrics, Accuracy, Sensitivity, Specificity, Dice Coefficient, and Jaccard coefficient, which are computed according to the following [
To validate the approach in tumors with different locations and volumes, we have taken four synthetic MRI images of patients with brain tumors from [
Synthetic T1, T1 contrast, and Flair images of four patients with tumors of different volumes with their ground truth. (a) Tumor with 11.6 cm3 of volume. (b) Tumor with 27.4 cm3 of volume. (c) Tumor with 51.1 cm3 of volume. (d) Tumor with 81.7 cm3 of volume.
Fifty other synthetic patients were used to test our approach; 25 patients with high-grade tumors were taken from BRATS 2012 Training data, 25 other patients with low-grade tumors were taken from BRATS 2013 Training data [
The bioheat transfer equation, level set method, and Canny edge detection method were implemented using C/C++ on Windows 7 operating system with a CPU Intel i7-4770k. The C/C++ code has been compiled with Visual C++ compiler. The DICOM images were read using ITK (
Brain tumor thermally represents a heat source; its volume affects temperature distribution. A simplified circular tumor with three diameters is placed in the same location in the healthy brain as shown in Figure
Temperature distribution of brain with circular tumors of three different diameters. (a) Tumor with 10 mm of diameter. (b) Tumor with 15 mm of diameter. (c) Tumor with 20 mm of diameter.
1D representation of temperature profile on the path passes through the tumors centers with different sizes.
Next, the temperatures distributions of the brain with realistic tumors were calculated with the addition of Gaussian noise; Figure
Temperature distribution with noise of brains with realistic tumors of different volumes. (a) Tumor with 11.6 cm3 of volume. (b) Tumor with 27.4 cm3 of volume. (c) Tumor with 51.1 cm3 of volume. (d) Tumor with 81.7 cm3 of volume.
Figure
Temperature isotherms in the four cases to show the degree of variation of temperature in the tumorous region.
1D representation of temperature absolute gradient on the path passes in the tumor center in the four cases. (a) Tumor with 11.6 cm3 of volume. (b) Tumor with 27.4 cm3 of volume. (c) Tumor with 51.1 cm3 of volume. (d) Tumor with 81.7 cm3 of volume.
The results of the segmentation are illustrated in Figure
Results of segmentation by level set method in MRI images and the proposed approach. The first and second lines provide the segmentation by level set in T1 contrast and Flair respectively. The last line gives the segmentation using the proposed approach showed in T1. Green: segmentation. Red: ground truth.
To evaluate the segmentation performance, we have used five metrics, Accuracy, Sensitivity, Specificity, Dice Coefficient, and the Jaccard coefficient. The obtained results are presented in Table
The calculated segmentation evaluation metrics for level set method and proposed approach.
Patient No. | Method | | | | | | | | | |
---|---|---|---|---|---|---|---|---|---|---|
Patient 1 | T1c | 593 | 191 | 14609 | 0 | 1 | 0.987 | 0.9875 | 0.8612 | 0.7563 |
Flair | 592 | 285 | 14515 | 1 | 0.9983 | 0.9807 | 0.9814 | 0.8054 | 0.6742 | |
| | | | | | | | | | |
| ||||||||||
Patient 2 | T1c | 1160 | 287 | 18241 | 0 | 1 | 0.9845 | 0.9854 | 0.8899 | 0.8016 |
Flair | 1138 | 369 | 18159 | 22 | 0.981 | 0.98 | 0.9801 | 0.8533 | 0.7442 | |
| | | | | | | | | | |
| ||||||||||
Patient 3 | T1c | 1593 | 105 | 18116 | 28 | 0.9827 | 0.9942 | 0.9932 | 0.9599 | 0.9229 |
Flair | 1598 | 431 | 17790 | 23 | 0.9858 | 0.9763 | 0.9771 | 0.8756 | 0.7787 | |
| | | | | | | | | | |
| ||||||||||
Patient 4 | T1c | 2224 | 109 | 17545 | 204 | 0.9159 | 0.9938 | 0.9844 | 0.9342 | 0.8766 |
Flair | 2428 | 418 | 17236 | 0 | 1 | 0.9763 | 0.9791 | 0.9207 | 0.8531 | |
| | | | | | | | | |
The temperature is obtained using the Pennes bioheat equation, which can produce errors in calculation compared to the experimentally measured temperature, as the model is isotropic and the used thermal properties do not represent the realistic properties of the patient. However, our interest in this work is the way the temperature is diffused, and its variation in tumor borders independently of the degree of temperature rises in the tumorous region. Figure
The calculated segmentation evaluation metrics for the proposed approach by considering different values of blood perfusion rate.
Patient No. | | | | | | | | | | |
---|---|---|---|---|---|---|---|---|---|---|
Patient 1 | 0.001 | 549 | 3 | 14797 | 44 | 0.9258 | 0.9997 | 0.9969 | 0.9589 | 0.9211 |
0.0016 | 556 | 5 | 14795 | 37 | 0.9376 | 0.9996 | 0.9972 | 0.9636 | 0.9297 | |
0.002 | 559 | 5 | 14795 | 34 | 0.9426 | 0.9996 | 0.9974 | 0.9662 | 0.9347 | |
| ||||||||||
Patient 2 | 0.001 | 1099 | 29 | 18499 | 61 | 0.9474 | 0.9984 | 0.9954 | 0.9606 | 0.9243 |
0.0016 | 1112 | 37 | 18491 | 48 | 0.9586 | 0.998 | 0.9956 | 0.9631 | 0.9289 | |
0.002 | 1118 | 47 | 18481 | 42 | 0.9637 | 0.9974 | 0.9954 | 0.9617 | 0.9262 | |
| ||||||||||
Patient 3 | 0.001 | 1538 | 1 | 18220 | 83 | 0.9487 | 0.9999 | 0.9957 | 0.9734 | 0.9482 |
0.0016 | 1547 | 7 | 18214 | 74 | 0.9543 | 0.9996 | 0.9959 | 0.9744 | 0.9502 | |
0.002 | 1558 | 14 | 18207 | 63 | 0.9611 | 0.9992 | 0.9961 | 0.9758 | 0.9529 | |
| ||||||||||
Patient 4 | 0.001 | 2330 | 17 | 17637 | 98 | 0.9596 | 0.999 | 0.9942 | 0.9759 | 0.9529 |
0.0016 | 2375 | 25 | 17629 | 53 | 0.9781 | 0.9985 | 0.9961 | 0.9838 | 0.9682 | |
0.002 | 2387 | 31 | 17623 | 41 | 0.9831 | 0.9982 | 0.9964 | 0.9851 | 0.9707 |
Temperature distribution with noise of brains with realistic tumors of different volumes by considering three values of blood perfusion rate. (a) Tumor with 11.6 cm3 of volume. (b) Tumor with 27.4 cm3 of volume. (c) Tumor with 51.1 cm3 of volume. (d) Tumor with 81.7 cm3 of volume.
Thus far, tumors contours were detected using steady-state thermal analysis, where the segmentation was performed in the equilibrium state of temperature distribution. In order to study the effect of transient thermal analysis in brain tumors segmentation, cold stress was applied. From an initial temperature distribution at thermal equilibrium obtained using (
The calculated segmentation evaluation metrics for transient thermal analysis in brain tumor contours detection.
| Time (s) | | | | | |
---|---|---|---|---|---|---|
| 5 | 0.9773 | 0.9986 | 0.996 | 0.9836 | 0.9677 |
100 | 0.9761 | 0.999 | 0.9963 | 0.9846 | 0.9697 | |
600 | 0.9794 | 0.9985 | 0.9962 | 0.9842 | 0.969 | |
1000 | 0.9781 | 0.9985 | 0.9961 | 0.9838 | 0.9682 | |
20000 | 0.9781 | 0.9985 | 0.9961 | 0.9838 | 0.9682 | |
25000 | 0.9781 | 0.9985 | 0.9961 | 0.9838 | 0.9682 | |
| ||||||
| 5 | 0.9744 | 0.9986 | 0.9957 | 0.9823 | 0.9653 |
100 | 0.9703 | 0.9993 | 0.9958 | 0.9826 | 0.9659 | |
600 | 0.981 | 0.9986 | 0.9965 | 0.9855 | 0.9714 | |
1000 | 0.9794 | 0.9985 | 0.9962 | 0.9842 | 0.969 | |
20000 | 0.9781 | 0.9985 | 0.9961 | 0.9838 | 0.9682 | |
25000 | 0.9781 | 0.9985 | 0.9961 | 0.9838 | 0.9682 | |
| ||||||
| 5 | 0.9707 | 0.997 | 0.9938 | 0.9745 | 0.9504 |
100 | 0.953 | 0.9994 | 0.9938 | 0.9741 | 0.9495 | |
600 | 0.9831 | 0.9987 | 0.9968 | 0.9869 | 0.9742 | |
1000 | 0.918 | 0.9986 | 0.9889 | 0.9525 | 0.9094 | |
20000 | 0.9785 | 0.9985 | 0.9961 | 0.984 | 0.9686 | |
25000 | 0.9781 | 0.9985 | 0.9961 | 0.9838 | 0.9682 |
Figures
The calculated segmentation evaluation metrics for level set method and proposed approach in BRATS Training data 2012.
Patient No. | Method | | | | | | | | | |
---|---|---|---|---|---|---|---|---|---|---|
Patient 1 | Flair | 1102 | 178 | 17090 | 66 | 0.9434 | 0.9896 | 0.9867 | 0.9 | 0.818 |
| | | | | | | | | | |
| ||||||||||
Patient 2 | Flair | 1067 | 165 | 15176 | 2 | 0.9981 | 0.9892 | 0.9898 | 0.9274 | 0.8646 |
| | | | | | | | | | |
| ||||||||||
Patient 3 | Flair | 2891 | 498 | 14358 | 4 | 0.9986 | 0.9664 | 0.9717 | 0.9201 | 0.852 |
| | | | | | | | | | |
| ||||||||||
Patient 4 | Flair | 1678 | 342 | 9386 | 4 | 0.9976 | 0.9648 | 0.9696 | 0.9065 | 0.829 |
| | | | | | | | | | |
| ||||||||||
Patient 5 | Flair | 1810 | 191 | 17340 | 69 | 0.9632 | 0.9891 | 0.9866 | 0.9329 | 0.8743 |
| | | | | | | | | | |
| ||||||||||
Patient 6 | Flair | 1982 | 628 | 16415 | 1 | 0.9994 | 0.9631 | 0.9669 | 0.863 | 0.759 |
| | | | | | | | | |
The calculated segmentation evaluation metrics for level set method and proposed approach in BRATS Training data 2013.
Patient No. | Method | | | | | | | | | |
---|---|---|---|---|---|---|---|---|---|---|
Patient 1 | Flair | 2831 | 371 | 16731 | 106 | 0.9639 | 0.9783 | 0.9761 | 0.9223 | 0.8558 |
| | | | | | | | | | |
| ||||||||||
Patient 2 | Flair | 1378 | 331 | 13666 | 26 | 0.9814 | 0.9763 | 0.9768 | 0.8853 | 0.7942 |
| | | | | | | | | | |
| ||||||||||
Patient 3 | Flair | 1274 | 413 | 17336 | 10 | 0.9922 | 0.9767 | 0.9777 | 0.8576 | 0.7507 |
| | | | | | | | | | |
| ||||||||||
Patient 4 | Flair | 1762 | 560 | 18243 | 1 | 0.9994 | 0.9702 | 0.9727 | 0.8626 | 0.7585 |
| | | | | | | | | | |
| ||||||||||
Patient 5 | Flair | 2015 | 807 | 13191 | 0 | 1 | 0.9423 | 0.9496 | 0.8331 | 0.714 |
| | | | | | | | | | |
| ||||||||||
Patient 6 | Flair | 1383 | 644 | 13522 | 0 | 1 | 0.9545 | 0.9585 | 0.8111 | 0.6822 |
| | | | | | | | | |
The percent of tumor and healthy areas differentiated by segmentation in thermal images only.
Data set | Patient No. | Reduced false positive rate | Reduced false negative rate |
---|---|---|---|
Galimzianova et al. [ | Patient 1 | 0.16 | 1.89 |
Patient 2 | 1.03 | 1.82 | |
Patient 3 | 0.12 | 2.32 | |
Patient 4 | 0 | 2.22 | |
| |||
BRATS 2012 | Patient 1 | 5.13 | 0.93 |
Patient 2 | 0.18 | 0.95 | |
Patient 3 | 0 | 3.08 | |
Patient 4 | 0 | 3.13 | |
Patient 5 | 1.27 | 0.82 | |
Patient 6 | 0 | 3.49 | |
| |||
BRATS 2013 | Patient 1 | 2.24 | 1.84 |
Patient 2 | 1.78 | 2.15 | |
Patient 3 | 0.77 | 2.28 | |
Patient 4 | 0 | 2.8 | |
Patient 5 | 0 | 5.67 | |
Patient 6 | 0 | 4.4 |
Results of segmentation by level set method in Flair MRI images and the proposed approach applied in six patients taken from BRATS 2012. (a) Flair images (b) segmentation by level set in Flair images. (c) Temperature distribution with noise (d) the segmentation using the proposed approach showed in T1-weighted images (green: segmentation, red: ground truth).
Results of segmentation by level set method in, MRI images and the proposed approach applied in six patients taken from BRATS 2013. (a) Flair images (c) segmentation by level set in Flair images. (c) Temperature distribution with noise (d) the segmentation using the proposed approach showed in T1-weighted images (green: segmentation, red: ground truth).
In Figure
In order to show further the robustness of the proposed approach, we have applied Canny edge detector in obtained thermal images with additional noise of all 25 patients with high-grade tumors taken from BRATS 2012 database and 25 patients with low-grade tumors taken from BRATS 2013 database. Figures
Sensitivity in thermal images for 50 patients; (a) 25 with high-grade taken from BRATS 2012; (b) 25 with low-grade taken from BRATS 2013.
Specificity in thermal images for 50 patients; (a) 25 with high-grade taken from BRATS 2012; (b) 25 with low-grade taken from BRATS 2013.
Accuracy in thermal images for 50 patients; (a) 25 with high-grade taken from BRATS 2012; (a) 25 with low-grade taken from BRATS 2013.
Dice index in thermal images for 50 patients; (a) 25 with high-grade taken from BRATS 2012; (b) 25 with low-grade taken from BRATS 2013.
Jaccard in thermal images for 50 patients; (a) 25 with high-grade taken from BRATS 2012; (b) 25 with low-grade taken from BRATS 2013.
In this work, we considered temperature distribution for brain tumor borders delineation. Brain tumors modify the normal temperature due to the variation in heat generation by cells metabolism and blood flow in tumors. Temperature reveals abrupt changes in tumor borders. Thus, we used the Canny edge detection method to locate the edges. The experiments showed that the proposed approach detects tumor borders with good accuracy and reduces false positive and false negative of segmentation by level set method in MRI images used in clinical routine. To the best of our knowledge, we are the first to incorporated thermal analysis of brain tumor in MRI images segmentation.
Effective and accurate brain tumor segmentation from MRI images is still a challenging task due to the structural complexity of brain tumors. In this paper, we proposed a new approach to enhance brain tumor segmentation based on the thermal analysis of brain tumors. We have presented and investigated the effect of tumor on brain temperature distribution as well as its size on temperature distribution. Next, we have used tumor thermal profile for segmentation to detect tumors contours. We calculated the temperature distribution in the brain using Pennes bioheat equation implemented by finite difference method (FDM). The obtained results were compared with level set method tested in different synthetic MRI sequences of different patients. We showed a significant improvement in segmentation accuracy. Therefore, the proposed approach can be used as a new indicator to enhance tumors segmentation. The present work can be very useful towards the creation of a new MRI thermal imaging sequence in future studies, which measure the absolute temperature distribution, as all MR-based temperature-mapping approaches require a baseline data set.
The data used to support the findings of this study are included within the article.
The authors of this publication confirm that there are no conflicts of interest associated with this publication and there has been no significant financial support for this work that could have influenced its outcome.
Thanks are due to the National Center for Scientific and Technical Research (CNRST-Morocco) (Grant no. 13UH22016).