ISPUB.com / IJRA/14/1/14083
  • Author/Editor Login
  • Registration
  • Facebook
  • Google Plus

ISPUB.com

Internet
Scientific
Publications

  • Home
  • Journals
  • Latest Articles
  • Disclaimers
  • Article Submissions
  • Contact
  • Help
  • The Internet Journal of Radiology
  • Volume 14
  • Number 1

Original Article

Simulation Of Contrast Enhancement Of Various Brain Lesions (Without Iv Gadolinium) By Using The Neural Network

T Biswas

Citation

T Biswas. Simulation Of Contrast Enhancement Of Various Brain Lesions (Without Iv Gadolinium) By Using The Neural Network. The Internet Journal of Radiology. 2012 Volume 14 Number 1.

Abstract


PURPOSE:To produce an enhancement-like effect of the brain lesions of MRI images mathematically, without intravenous injection of contrast.INTRODUCTION:To improve the visibility of internal body structures, MRI contrast agents are used. Gadolinium (Gd3+), a paramagnetic substance, is the most commonly used compound for contrast enhancement. Gd is introduced into the blood stream for enhancement of brain tumors and various lesions depending upon the degradation of the blood-brain barrier. Due to their hydrophilic character, gadolinium chelates do not pass the blood-brain barrier. Contrast (Gd) mediated nephropathy (CMN) and systemic fibrosis are two notorious, irreversible complications.MATERIALS AND METHODS: A multi-slice EPI IR sequence was used to assess T1 relaxation times of various brain lesions and brain tumors before and after administration of gadolinium. T1 relaxation time and signal intensity with corresponding gray scale values (out of 256 shades) of various brain lesions before and after IV contrast were tabulated. A statistical relationship was determined for the magnitude of changes in the T1 values of brain tumors before and after the contrast material was added. Enhancement-like effects of the lesions could be reproduced mathematically with the help of neural networks without the IV contrast injection. With the help of K-mean clustering, the data were classified. A mapping function was generated that corresponded between these independent components and the cross-sectional data by using the neural network after training the network with a sample dataset. The training sample for the network was selected using K-mean clustering. A mapping of the lesion was done overlaid on the T1 weighted image.CONCLUSION: An attempt was successfully made to enhance various brain lesions statistically utilizing neural networks and without using IV contrast.

 

Introduction

To improve the visibility of internal body structures, MRI contrast agents are used. Gadolinium (Gd3+), a paramagnetic substance, is the most commonly used compounds for contrast enhancement. Chemically Gd is a rare earth element (Z-64)(1-3) that is toxic in its free state, but when it is bound to DTPA by chelation the problem of toxicity is solved (3,4). This paramagnetic substance has small local magnetic fields which cause a shortening of the relaxation times of the surrounding protons; this is known as proton relaxation enhancement effect (2). Gd-based MRI contrast agents alter the T1 relaxation time of tissues (spin-lattice relaxation time of protons) located nearby and in body cavities where they are present(5-9). Paul Lauterbur and his associates(10) were the first to demonstrate the feasibility of using paramagnetic contrast agents to improve tissue discrimination in MRI. Depending on the image weighting, this can give a higher or lower signal of two tissues which can be better differentiated(11). Most clinically used MRI contrast agents work through shortening the relaxation time. The T1 shortening is due to an increase in rate of stimulated emission from high energy states (aligned anti-parallel to the main field) to low energy states (parallel to the main field). The source of the stimulation is thermal vibration from the strongly magnetic metal ions, which create oscillating electromagnetic fields at frequencies corresponding to the energy differences between the spin states (via E = h?)(3,7,11).

MRI contrast agents are administered by injection into the blood stream for brain tumor and lesion enhancement associated with the degradation of the blood=brain barrier. Due to their hydrophilic character, gadolinium chelates do not pass the blood-brain barrier(5,8). Thus these are useful in enhancing lesions and tumors where the Gd leaks out (Figures 1 and 2). In the rest of the body, the Gd initially remains in the circulation before being distributed into the interstitial space or eliminated by the kidney(12).

Figure 1
Figure 1. T1 relaxation time of tissue A and B before and after GD. T1 relaxation further shortens after GD and shifts to right making the contrast between the A and B more.

Figure 2
Figure 2a. Non-contrast Glioblastoma 2b. Contrast enhancement

Gadolinium chelates are extremely well tolerated by the vast majority of patients in whom they are injected. Acute, adverse reactions are encountered with a lower frequency than is observed after administration of iodinated contrast media (7). A serious complication like nephrogenic systemic fibrosis (NSF) and fibrosis in various tissues and organs in the body can occur(13-15). Contrast-mediated nephrotoxicity (CMN) is another complication. The frequency of all acute, adverse events after an injection of 0.1 or 0.2 mmol/kg of gadolinium chelate ranges from 0.07% to 2.4%(15). The vast majority of these reactions are mild. Severe, life-threatening anaphylactoid or non-allergic anaphylactic reactions are exceedingly rare (0.001% to 0.01%)(16).

Assessment of contrast enhancement on T1 weighted images of normal and various brain lesions was the essential element of our study (12). Statistical analysis of the pre- and post- contrast brain lesions, the intensity of signal in gray shades and the extent of contrast enhancement in tissue depends on the gadolinium content within each voxel(7). We measured the magnitude of longitudinal relaxation value (T1 relaxation time) in gray and white matters and in brain tumors before and after administration of a contrast agent using echo-planar inversion recovery sequences(17-19). Echo-planar imaging, a fast imaging-acquisition method, provides inversion recovery images more rapidly. However it could be useful to know the scale of T1 shortening. Inversion recovery (IR) sequences are sensitive to T1 contrast and the most precise means of measuring T1 relaxation rates in tissue in vivo.

A multi-slice EPI IR sequence was used to assess T1 relaxation times of various brain lesions and brain tumors before and after administration of Gd.

Our purpose was to assess whether there was any statistical relationship in the magnitude of changes in the T1 relaxation of brain tumors before and after the contrast material was administered, and whether enhancement-like effects of the lesions could be reproduced mathematically with the help of neural networks and without the IV contrast injection.

T1 relaxation and signal intensity, as represented by the corresponding gray shade values (out of 256 shades), of various brain lesions before and after IV contrast were tabulated. Using independent component analysis (ICA), a statistical technique, the complex dataset was decomposed into independent sub-parts.

With the help of K-mean clustering, the data were classified. A mapping function was generated that corresponded between these independent components and the cross-sectional data by using the neural network after training it with sample datasets (11,12). The training samples for the network were selected using K–mean clustering. A mapping of the lesion was overlaid on the T1 weighted image.

Materials And Methods

Brain T1 mapping is important to determine the T1 relaxation value of brain pathology. We used conventional T1 mapping techniques based on inversion recovery spin echo (IRSE) and its counterpart, inversion recovery spin echo (EPI IR) imaging. Both of them produced good quality images. Multiple inversion times were applied to accurately estimate the T1 relaxation value of white and gray matter and various brain lesions and tumors. All images were produced in a 3T Siemens Magnetom and a 0.3T AIRISII Magnet, (Hitachi, Japan). Conventional axial T1-weighted localizing image, conventional axial T1, proton density and T2 weighted images were obtained. Six consecutive slices were selected for EPI IR with 5 mm thickness without a gap, TI (time to inversion recovery) 50-1500ms with a step of 150ms, TR 15000ms, and TE of 30ms with a partial k-space acquisition. A matrix size of 256X256 and FOV 25X50cm was used. In the 0.3T magnet a matrix size of 256X128, 5mm slice thickness with 5 mm gap and 30 cm field of view (FOV) were used.

The IRSE protocol had TE=15ms, TR-2500 ms, receiver bandwidth = + 15.63kHz and TI = 100,400,700 and 1000 ms. T1 values were obtained by producing a T1 map by fitting the measured SI (signal intensity) to a mono-exponential recovery function of the scanner:

SI=a (1-2e (-TI/T1))-b). Equation 1

We examined 21 patients after getting proper institutional ethics and consents from the patients (Table 1).

Figure 3
Table 1

Before giving contrast we routinely produced T1 maps by conventional IRSE and EPI IR of the entire brain and determined the T1 value of gray/white matter, various part of the lesions and brain tumor. After that each patient received 0.1mmol/Kg of GD DTPA (Magnevist –Schering) by a Power Injector (Magmedix) at a rate of 5ml/second and was imaged by conventional IRSE to produce the T1 map.

Regions of interest presenting enhancing and/or non-enhancing parts of tumors were selected by viewing the post-contrast conventional SE images. Regions of interest containing white and gray matter areas were identified in the contralateral hemisphere. T1 values of the various part of the tumor were directly measured from the T1 map produced by IRSE and EPI IR protocols and tabulated (Table 2).

Figure 4
Table 2 Pre- and post-contrast T1 relaxation values of gray and white matter and pathological lesions (noted as brain tumor)

A segmentation technique was applied to decompose the image into mosaic form of the gray shades of the pre- and post-contrast parts of the normal brain tissue (such as gray and white matter) and brain tumors or lesions (Figure 3 A and B).

Figure 5
Figure 3 mosaic pattern of T1 pre and post contrast decomposed images of medulloblastoma in various shades. Gray shade scale of 256 in 16 different slabs.

Figure 6

Figure 9
Figure 4A Relationship of pre- and post-contrast T1 values

Figure 10
Figure 4B Relationship of the Pre- and post-contrast signals expressed in gray shades

By applying K-mean clustering the gray shade values (out of 256) of various parts were determined and tabulated. K-mean clustering classified the data based on attributes/features. Each attribute represented the T1 relaxation value of tissue before and after contrast and gray shade value (out of 256 shades) as the signal. The grouping is done by minimizing the sum of squares of distances between data and the corresponding cluster centroid. Then pre- and post-contrast values of the tissues were transferred into the Excel sheet of the neural network program.

Neural Network

Neural Network Design and Steps

We followed the standard steps for designing neural networks to predict the signal and gray shade values of unknown tissues in four application areas: function fitting, pattern recognition, clustering, and time series analysis. The work flow for any of these problems had seven primary steps:

To collect data from T1 mapping and k mean clustering.

To create the network

To configure the network

To initialize the weights and biases

To train the network

To test and Validate the network

To use the network for prediction of value of unknown tissue.

A data set manager is prepared in Microsoft Excel: neural networks that contain 5 variables, 32 cells per variable containing known data. A trial version of the neural network program Neural Tool version 5.7 of the Palisade Inc(20) was used which imitated the brain-like functions in order to learn the structure of the data provided.

Out of 5 variables

A. One independent category variable (of tissue),

B. Three independent numeric category variables such as T1 value (in ms) of

i) Pre-contrast ii) post-contrast Tissue iii) gray shade signal value of pre- and post-contrast tissue (out of 256 shades)

C. One dependent numeric category variable, which ultimately produced live predict variables of post contrast values.

After understanding the data, the program worked through the following steps: analysis of the data, training the network on the data provided, testing the network for accuracy, and making intelligent predictions of the signal (gray values of the pixel out of 256 shades) from the new input of the T1 value of the unknown (target tissue).

Contrast Enhancement Simulation

A radial basis function network was then used to generate a contrast enhanced map overlay on the background T1 weighted image. It produced correspondences between independent components of gray shades of the pre-contrast T1 weighted image and live prediction of the dependent variable of gray shades (out of 256) of tumor/lesion of the T1 weighted image, pixel by pixel. The training samples for the neural network were selected using the k-mean clustering algorithm to give a contrast-like effect of the image of the tumor.

Results

The mean T1 relaxation time in tumors was 1416 ms before administration of contrast, and 631 ms after the injection compared to 646 ms in white matter. T1 relaxation time decreased from 1179 ± 130 ms to 926 ± 126 ms in gray matter (p<0.001), and from 706 ± 107 ms to 646 ± 27 ms in white matter (p<0.001) after the 0.1 mmol/kg of contrast. Post-contrast T1 relaxation times in tumors showed considerable variation and remained, on average, relatively long compared to white matter.

Figure 11
Figure 5: T1 map of a meningioma

Figure 12
Figure 6. Layers of neural network

In figure 4A, the relationship of pre- and post-contrast T1 values of pathological tissue was established:

Post-contrast T1 relaxation = - 0.514 x T1 Pre-contrast relaxation + 1427.6 (Equation 2)

Figure 4B depicts the relationship of the pre- and post-contrast signals expressed in gray scales:

Post-contrast T1 signal = 0.0068x2 - 2.2861xPrecontrast T1 signal + 392.18 (Equation 3)

In Table 2, pre-contrast T1, post-contrast T1, pre- and post-contrast signal in gray scale are tabulated.

Discussion

The IR data sets generated T1 maps on a pixel by pixel basis (Figure 5)

Figure 13

Analysis Of T1 Relaxation

T1 relaxation times of the various parts of tumors, contralateral gray and white matters were obtained from the T1 map (21,22). Considerable variation in T1 relaxation times in tumors in different patients was noticed before the contrast injection (22). Detectable tumor enhancement was noticed in all 21 patients in conventional T1 weighted images. After the contrast injection, T1 relaxation time shortened both in the tumors and in the contralateral gray and white matters. From Table 2, it is evident that T1 relaxation in the tumor is more marked compared to gray/white matter, possibly due to intratumoral, vasogenic edema and perilesional edema which interfere with the heat dissipation during relaxation. After contrast, shortening of T1 relaxation time was noted in most of the tumors (17). Analyzing the percentage of T1 relaxation after contrast enhancement, it is evident that it is at a minimum in white matter (0.15 to 12.84%, mean-3.3%) and maximum (79%, mean) in case of tumors(23).

Neural Network

We used the General Regression Neural Networks (GRNN) numeric predictor configuration.

Architecture of a PNN/GRNN Network

In 1990, Donald F. Specht proposed a method to formulate the weighted-neighbor method described above in the form of a neural network(24-27). He called this a “Probabilistic Neural Network.” Here is a diagram of a PNN/GRNN network (Figure 6)(28,29):

Figure 14
TABLE 3: Summary of The Neural Net

All PNN/GRNN networks have four layers: input, hidden, pattern/summation and decision/prediction.

Input layer — Pre- and post-contrast T1 values of gray and white matters, various tumors and brain lesions.

Figure 15
Table 4: Dataset manager with Training and testing

The input neurons/nodes (or processing before the input layer) standardize the range of the values by subtracting the median and dividing by the interquartile range used to summarize the extent of the spread of the data (variability between 75 th and 25 th percentiles). The input neurons then feed the values to each of the neurons in the hidden layer(30). In table 3, a summary of the neural network is provided.

Figure 16
TABLE 5: Testing Data showing actual Predicted and residual values

Table 4 depicts how the dataset manager trains the inputs and tests to predict. Most of the predictions were found to be good. Residual values (between original and predicted value) show a range from -0.97 to -19.28.

Figure 17
TABLE 6A: Trained Neural Net’s prediction (auto-testing) of unknown post contrast T1 value lesions when pre contrast T1 value and signal shades were known

Hidden layer — There were 26 cases and, during training, 98 trials were applied. During testing, the tool tried 6 predictions, out of which a 16.66% were found bad after analyzing the residual values (actual values minus predicted values). Testing data generated by the dataset manager along with histogram bins are depicted in Table 5.

Figure 18
Table 6B: Trained neural net’s prediction (auto testing) of unknown post contrast signal shades of pathological tissues

The trained Neural Net’s prediction (auto-testing) of unknown post-contrast T1 values of pathological tissues when pre-contrast T1 values and signal shades were provided are in Table 6A and 6B .

Figure 19

Figure 20
Figure 7A Predicted Vs Actual training

In Table 6C are the values for R-square (training) and root mean square error (training and testing) of Linear Predictor and Neural Net

6C.R-Square (Training), Root mean Sq error(training), Root mean Sq (Testing)

Figure 21
Figure 7B Residual Vs Actual training

Figures 7A, 7B and 7C discern the relationship of Predicted versus Actual, Residual versus Actual (Training) and Predicted versus Actual testing.

Figure 22
Figure 7C Predicted Vs Actual testing

Figure 23
Figures 8A, 8B, 8C show the non-contrast T1 weighted, contrasted (post-GD) image and brain mapping of the contrast-like effect overlay on the T1 wt. image

Figure 24
9A: T1 weighted plain B: Contrast enhanced (GD) and simulated enhancement of Glioblastoma in the right frontal lobe region. Image B is a machine generated DICOM format whereas image C is a JPEG image available for mapping or simulation effect.

Simulation Of Contrast Enhancement

Figures 8A, 8B, and 8C show the non-contrast T1 weighted, contrasted (post-GD) image and brain mapping of contrast-like effect. Contrast simulation and original GD enhancement have similarities in shape and pattern, as depicted in 8B and 8C respectively.

Figure 25
Figure 10: Contrast simulation effect in A. intraventricular meningioma B. Medulloblastoma C. Oligodendroglioma D. wall of an Arachnoid Cyst

Figure 9C depicts the simulation of contrast enhancement of a glioblastoma overlaying the T1 weighted plain image

Figure 26
Figure 11A: T1 weighted plain and B.simulation of contrast enhancement of left parietal lobe Glioblastoma

Figure 27
Figure 11A. Lymphoma-Non contrast T1 wt B. Contrast effect overlay on T1 Wt image.

{image:26}

Figure 10 shows a contrast enhancement effect in: A. an intra-ventricular meningioma B. a medulloblastoma C. an oligodendroglioma and D. Arachnoid cyst respectively. Increased enhancement of the gyri is also noted. A contrasted image of lymphoma (Figure 11B)overlaid on a T1 pre-contrast image (11B).

{image:27}

DICOM FORMAT VS JPEG FORMAT

Smooth and regular enhancement is noted in the peripheral component of the tumor (9A) in

GD enhancement whereas the contrast-like effect, though very similar, shows an irregular outline and is interrupted in texture (9B). This can be explained by the fact that the MR images are displayed in Digital Imaging and Communications in Medicine (DICOM) format compared to exported images in JPEG (JPEG baseline (lossy 8 bits/pixel) compression) format used for simulation effect. The DICOM image is a 16-bit gray scale image (signed/unsigned). This means each pixel is represented by 16 bits, 216 or 65,536 shades/pixel in DICOM compared to 8-bit or 28 = 256 shades/pixel of gray level combinations available in a JPEG saved image, so a smooth and regular outline is not depicted in the simulation effect, unlike in the GD-enhanced image. The problem is extracting raw data from the DICOM image available for the simulation effect.

Conclusion

An attempt was successfully made to get an enhancement effect in various brain lesions statistically, utilizing a neural network and without IV contrast. I am working to retrieve the raw data and the signal from the DICOM format directly so that an accurate, contrast-like effect can be generated.

Acknowledgement

I am thankful to Palisade Inc, Asia- Pacific Pty Inc, Sydney, NSW 2000 Australia, for providing a 15 days Trial version of Neural Tool (5.7).I sincerely thank MR Samir Roy of Biswas Scan Centre, DR Sadallah Ramadan of New Castle University, Australia.

References

1. D.H. C, Brown J, Bydder GM, J. WH, U S, J TD, I.R Y. Intravenous chelated gadolinium as a contrast agent in NMR in cerebral tumors. Lancet 1984;2:484-486.
2. Allisey-Roberts P, Williams J. Farr's Physics for medical imaging. 2008:184.
3. Carr DH, Brown J, Bydder GM, Weinmann HJ, Speck U, Thomas DJ, Young IR. Intravenous chelated gadolinium as a contrast agent in NMR in cerebral tumors. Lancet 1984;2:484-486.
4. Schild H. MRI made easy. 1992:72-73.
5. Swaighofer BW, Klein MV, Wesbey G, Hesselink JR. Clinical Experience with routineGD-DTPA administration for the MR imaging of the brain. J Comput Assist Tomogr 1990;14:11-17.
6. Elster AD, Moody DM, Ball MR, Laster DW. Is Gd-DTPA administration required routine cranial MR imaging? Radiology 1989;173:231-238.
7. Gadian DG, Payne JA, Bryant DJ, Yamada S, Bydder GM. Gadolinium-DTPA as a contrast agent in MR imaging:theoretical projections and practical observation. J Comput Assist Tomogr 1985;9:242-251.
8. Felix R, Schoner W, Laniado M, Niendorf HP, Claussen C, Fiegler W, Speck U. Brain Tumors:MR Imaging with gadolinium-DTPA. Radiology 1985;156:651-688.
9. Schwaighofer BW,Klein MV,Wesbey G,Hesselink JR. Clinical experience with routine Gd-DTPA administration for MR imaging of the brain. JcomputAssistTomogr 1990;14:11-17.
10. Lauterbaur PC. Image formation by induced local interactions:examples using nuclear magnetic resonance. Nature 1973:190.
11. Wehrli FW, Macfall jR, Shutts D, Breger R, Herfenks RJ. Mechanism of contrast in NMR imaging. JcomputAssistTomogr 1994;8:369.
12. Garif M, Bydder G, Steiner R, Niendorf H, Thomas D, Young I. Contrast-enhancing MR imaging of malignant brain tumors. Am J Neuroradiol 1985;6:855-862.
13. Solomon R. Contrast-medium-induced acute renal failure. Kidney Int 1998;53:230–242.
14. Katholi R, Taylor G, McCann W. Nephrotoxicity from contrast media: attenuation with theophylline. Radiology 1995;195:17–22.
15. Tumlin J, Stacul F, Adam A. Pathophysiology of contrast-induced nephropathy. Am J Cardiol 2006:14K–20K.
16. Gruberg L, Mintz GS, Megran R. The prognostic implications of further renal function deterioration within 48 hours of interventional coronary procedures in patients with pre-existent chronic renal insufficiency. J Am Coll Cardiol 2000;36:1542–1548.
17. Steen RG, Grnemeyer SA, Kingsley PB, Reddick WE, Langston JS, Taylor JS. Precise and accurate measurement of proton T1 in Human Brain in vivo.Validation and preliminary clinical application. J magnResonImaging 1994;4:691.
18. Bydder GM, Young IR. MR imaging.Clinical use of the inversion recovery sequence. JcomputAssistTomogr 1985;9:659.
19. Lee JN, Riederer SJ. A modified saturation -recovery approximation for multiple spin-echo pulse sequences. Magn Reson Med 1986;3:132-134.
20. Iglesias-Rozas JR. NeuralTools Used for Tumor Diagnosis. 2010.
21. Aronen HJ, Niemi P, Kwong KK, Pardo FS, Davis TL. The effect of paramagnetic. ActaRADIOL 1998;39:474-481.
22. Niemi P, Paajanen H, Maattnen H, Komu M, Erkintalo M, Alanen A, Dean PB, Martti K. Paramagnetic contrast enhancement at 0.02 T: An experimental study using Gd-DOTA in normal and hydronephrotic kidneys. Magn Reson Med 1988;7:311-318.
23. Yamada S, Matsuzawa T, Yarnada K, Yoshioka S, Ono S, Hishinuma T. A modified signal intensity equation of Carr- Purcell-Meiboom-Gill pulse sequence for MR imaging. Tohuko J ExpMed 1989;158:203-209.
24. Gurney JW. Solitary Pulmonary Nodules: Determining the Likelyhood of Malignancy with Neural Network Analysis. Radiology 1995(September).
25. Boone JM. Sidetracked at the Crossroads. Radiology 1995(October).
26. Brown E, Kass R, Mitra P. Multiple neural spike train data analysis: state-of-the-art and future challenges. Nature Neuroscience 2004;7:456–461.
27. Dawson A, E., Austin(Jr) R, E, Weinberg D, S. Nuclear Grading of Breast Carcinoma by Image Analysis. Am J Clin Pathol, 1991:S29-S37.
28. Specht D, F. Probabilistic neural networks. Neural Networks 1990 3:109-118
29. Erkmen B, Yildirim T. Improving classification performance of sonar targets by applying general regression neural network with PCA. Expert Systems with Applications 2008;Volume 35:472-475
30. Kulkarni SG, Chaudhary AK, Nandi S, Tambe SS, Kulkarni BD. Modeling and monitoring of batch processes using principal component analysis (PCA) assisted generalized regression neural networks (GRNN) Biochemical Engineering Journal 2004;18:193-210.

Author Information

Tapan K Biswas
Researcher And Radiologist, Biswas X Ray And Scan Centre

Download PDF

Your free access to ISPUB is funded by the following advertisements:

 

 

BACK TO TOP
  • Facebook
  • Google Plus

© 2013 Internet Scientific Publications, LLC. All rights reserved.    UBM Medica Network Privacy Policy

Close

Enter the site

Login

Password

Remember me

Forgot password?

Login

SIGN IN AS A USER

Use your account on the social network Facebook, to create a profile on BusinessPress