KEYWORDS: Image segmentation, Thalamus, Convolutional neural networks, Medical imaging, Visualization, Traumatic brain injury, Super resolution, Magnetism, Magnetic resonance imaging, Image processing algorithms and systems
Thalamus segmentation plays an important role in studies that are related to neural system diseases. Existing thalamus segmentation algorithms use traditional image processing techniques on magnetic resonance images (MRI), which suffer from accuracy and efficiency. In recent years, deep convolutional neural networks (CNN) have been able to outperform many conventional algorithms in medical imaging tasks. We propose segmenting the thalamus using a 3D CNN that takes an MPRAGE image and a set of feature images derived from a diffusion tensor image (DTI). Experimental results demonstrate that using CNNs to segment the thalamus can improve accuracy and efficiency on various datasets.
The abnormal thermogram has been shown to be a reliable indicator of a high risk of breast cancer. Nevertheless, a
major weakness of current infrared breast thermography is its poor sensitivity for deeper tumors. Numerical modeling
for breast thermography provides an effective tool to investigate the complex relationships between the breast thermal
behaviors and the underlying patho-physiological conditions. We have developed a set of new modeling techniques to
take into account some subtle factors usually ignored in previous studies, such as gravity-induced elastic deformations of
the breast, nonlinear elasticity of soft tissues, and dynamic behavior of thermograms. Conventional "forward problem"
modeling cannot be used directly to improve tumor detectability, however, because the underlying tissue thermal
properties are generally unknown. Therefore, we propose an "inverse problem" modeling technique that aims to estimate
the tissue thermal properties from the breast surface thermogram. Our data suggest that the estimation of the tumor-induced
thermal contrast can be improved significantly by using the proposed inverse problem solving techniques to
provide the individual-specific thermal background, especially for deeper tumors. We expect the proposed new methods,
taken together, to provide a stronger foundation for, and greater specificity and precision in, thermographic diagnosis,
and treatment, of breast cancer.
Infrared thermography has been shown to be a useful adjunctive tool for breast cancer detection. Previous thermography
modeling techniques generally dealt with the "forward problem", i.e., to estimate the breast thermogram from known
properties of breast tissues. The present study aims to deal with the so-called "inverse problem", namely to estimate the
thermal properties of the breast tissues from the observed surface temperature distribution. By comparison, the inverse
problem is a more direct way of interpreting a breast thermogram for specific physiological and/or pathological
information. In tumor detection, for example, it is particularly important to estimate the tumor-induced thermal contrast,
even though the corresponding non-tumor thermal background usually is unknown due to the difficulty of measuring the
individual thermal properties. Inverse problem solving is technically challenging due to its ill-posed nature, which is
evident primarily by its sensitivity to imaging noise. Taking advantage of our previously developed forward-problemsolving
techniques with comprehensive thermal-elastic modeling, we examine here the feasibility of solving the inverse
problem of the breast thermography. The approach is based on a presumed spatial constraint applied to three major
thermal properties, i.e., thermal conductivity, blood perfusion, and metabolic heat generation, for each breast tissue type.
Our results indicate that the proposed inverse-problem-solving scheme can be numerically stable under imaging noise of
SNR ranging 32 ~ 40 dB, and that the proposed techniques can be effectively used to improve the estimation to the
tumor-induced thermal contrast, especially for smaller and deeper tumors.
Understanding the complex relationship between the thermal contrasts on the breast surface and the underlying
physiological and pathological factors is important for thermogram-based breast cancer detection. Our previous
work introduced a combined thermal-elastic modeling method with improved ability to simultaneously
characterize both elastic-deformation-induced and tumor-induced thermal contrasts on the breast. In this paper,
the technique is further extended to investigate the dynamic behaviors of the breast thermal contrasts during cold
stress and thermal recovery procedures in the practice of dynamic thermal imaging. A finite-element method
(FEM) has been developed for dynamic thermal and elastic modeling. It is combined with a technique to address
the nonlinear elasticity of breast tissues, as would arise in the large deformations caused by gravity. Our
simulation results indicate that different sources of the thermal contrasts, such as the presence of a tumor, and
elastic deformation, have different transient time courses in dynamic thermal imaging with cold-stress and
thermal-recovery. Using appropriate quantifications of the thermal contrasts, we find that the tumor- and
deformation-induced thermal contrasts show opposite changes in the initial period of the dynamic courses,
whereas the global maxima of the contrast curves are reached at different time points during a cold-stress or
thermal-recovery procedure. Moreover, deeper tumors generally lead to smaller peaks but have larger lags in the
thermal contrast time course. These findings suggest that dynamic thermal imaging could be useful to
differentiate the sources of the thermal contrast on breast surface and hence to enhance tumor detectability.
The abnormal thermogram has been shown to be a reliable indicator of a high risk of breast cancer, but an open question
is how to quantify the complex relationships between the breast thermal behaviors and the underlying
physiological/pathological conditions. Previous thermal modeling techniques generally did not utilize the breast
geometry determined by the gravity-induced elastic deformations arising from various body postures. In this paper, a 3-D
finite-element method is developed for combined modeling of the thermal and elastic properties of the breast, including
the mechanical nonlinearity associated with large deformations. The effects of the thermal and elastic properties of the
breast tissues are investigated quantitatively. For the normal breast in a standing/sitting up posture, the gravity-induced
deformation alone is found to be able to cause an asymmetric temperature distribution even though all the thermal/elastic
properties are symmetrical, and this temperature asymmetry increases for softer and more compressible breast tissues.
For a tumorous breast, we found that the surface-temperature alterations generally can be recognizable for superficial
tumors at depths less than 20 mm. Tumor size plays a less important role than the tumor depth in determining the tumor-induced
temperature difference. This result may imply that a higher thermal sensitivity is critical for a breast thermogram
system when deeper tumors are present, even if the tumor is relatively large. We expect this new method to provide a
stronger foundation for, and greater specificity and precision in, thermographic diagnosis and treatment of breast tumors.
This paper presents a color image segmentation method with Self-Organize Feature Map and General Learning Vector Quantity which, in the uniform color space, divides color into clusters based on the least sum of squares criterion. At the first step of this method, SOFM is employed to make a preliminary classification on the original image, and then GLVQ is used to segment it. Both of their advantages can be fully taken of to improve the precision and velocity of color image segmentation.
In this paper, a novel stepwise thresholding is first addressed. Then the design of intensity homogeneity segmentation criteria is presented. Some examples of the experiment results of fuzzy image segmentation by the method are given at the end.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.