Improved infrared thermography based image construction for biomedical applications using Markov Chain monte carlo method

Framework for estimating tumour parameters using thermal imaging

Abstract: Background & objectives: Non-invasive and non-ionizing medical imaging techniques are safe as these can be repeatedly used on as individual and are applicable across all age groups. Breast thermography is a non-invasive and non-ionizing medical imaging that can be potentially used in breast cancer detection and diagnosis. In this study, we used breast thermography to estimate the tumour contour from the breast skin surface temperature. Methods: We proposed a framework called infrared thermography based image construction (ITBIC) to estimate tumour parameters such as size and depth from cancerous breast skin surface temperature data. Markov Chain Monte Carlo method was used to enhance the accuracy of estimation in order to reflect clearly realistic situation. Results: We validated our method experimentally using Watermelon and Agar models. For the Watermelon experiment error in estimation of size and depth parameters was 1.5 and 3.8 per cent respectively. For the Agar model it was 0 and 8 per cent respectively. Further, thermal breast screening was done on female volunteers and compared it with the magnetic resonance imaging. The results were positive and encouraging. Interpretation & conclusions: ITBIC is computationally fast thermal imaging system and is perhaps affordable. Such a system will be useful for doctors or radiologists for breast cancer diagnosis.

Early diagnosis and detection of breast cancer.

Abstract: Background Breast cancer is the most common malignancy in women. It is often characterized by a lack of early symptoms, which results in late detection of the disease. Detection at advanced stages of the decease implies the treatment is more difficult and uncertain. The appropriate screening programs have been conducted within the organized preventive examinations and have made significant contributions to the early breast cancer detection. Objective It is necessary to improve the screening process in order to reduce the percentage of female population that is not covered by screening programs and increase the number of early-detected breast cancers. The improvement of the screening program may be reflected in the following: more efficient determination of the list of the women who have to undergo preventive examination, introduction of screening program in thermography as a diagnostic method applied in pre-screening stage, more efficient analysis of mammograms and continuous follow up of patients. Methods The identification of target population for breast cancer screening program has been based on the age of women. The improvement of the early breast cancer diagnosis process proposed in this paper is reflected in more efficient determination of the group of women who have to undergo preventive examination based on the factors affecting the occurrence of breast cancer. Inclusion of the pre-screening phase in which thermal imaging could be applied and software support to mammographic detection of tumor are suggested. Results This paper describes the breast cancer, current screening program and techniques for early-stage breast cancer detection, module of medical information system MEDIS.NET for creating screening list based on the analysis of risk factors affecting the occurrence of breast cancer, mammography and role of thermal imaging in the process of early breast cancer detection. It also presents an overview on important achievements in computer-aided detection and diagnosis of breast cancer in mammography and thermography. Conclusions Based on the obtained results, dynamics of preventive examinations for particular groups of women that is different from the standard two-year examinations, can be successfully defined. It can be concluded that the use of a computer system for tumor diagnosis in mammogram based on various methods of image processing can help doctors in decision-making, while the use of thermal imaging in the pre-screening phase would significantly reduce the list of women for screening mammograms.

Estimación de parámetros y clasificación de datos

Abstract: Tesis (Doctor en Matematica)--Universidad Nacional de Cordoba. Facultad de Matematica, Astronomia y Fisica, 2011.

Estimation of tumor parameters using neural networks for inverse bioheat problem.

Abstract: Background and objective Some types of cancer cause rapid cell growth, while others cause cells to grow and divide at a slower rate. Certain forms of cancer result in visible growths called tumors. This work proposes an inverse estimation of the size and location of the tumor using a feedforward Neural Network (FFNN) model. Methods The forward model is a 3D model of the breast induced with a tumor of various sizes at different locations within the breast, and it is solved using the Pennes equation. The data obtained from the simulation of the bioheat transfer is used for training the neural network. In order to optimize the neural network architecture, the work proposes varying the number of neurons in the hidden layer and thus finding the best fit to create a relationship between the temperature profile and tumor parameters which can be used to estimate the tumor parameters given the temperature profile. Results These simulations resulted in a temperature distribution profile that could thus be used to locate and determine the parameters of the cancerous tumor within the breast. The prediction accuracy showed the capacity of the trained Feed Forward Neural Network to estimate the unknown parameters within an acceptable range of error. The model validations use the Root Mean Square Error method to quantify and minimize the prediction error. Conclusions In this work, a non-intrusive method for the diagnosis of breast cancer was modelled, which yields conclusive results for the estimation of the tumor parameters.

Estimation of breast tumour size, location and pre-processing algorithm for the breast thermal signatures

Abstract: Breast cancer is the second most cause of the death among the women in society. Thermography is the non-invasive, non-contact imaging modality that can be used for the early detection of breast cancer. This paper proposes the development of the mathematical model using Penne’s bio-heat transfer equation, and the estimation of the location and the size of the tumour using Metropolis-Hasting (MH) algorithm. This paper also proposes the pre-processing of the thermal images using RGB max filter and Grab-cut algorithm to extract out the region of interest where the probability of the presence of the tumour is more.

Effect of blood flow, tumour and cold stress in a female breast: a novel time-accurate computer simulation.

Abstract: Breast cancer is a dreadful disease among women and early detection helps in achieving a cure. The mammogram is presently the standard tool for detecting breast abnormality, but its sensitivity is lower for women with dense breasts. It has been found that women with an abnormal thermogram are at a higher risk and have a poorer prognosis. However, performing and interpreting thermograms requires meticulous training. Computer simulations can be an additional tool to help the clinician in the interpretation. In this paper, a novel and flexible finite element model of a female breast is developed. Both steady state and time-dependent solutions are obtained. Steady state solutions globally match experimental thermographic results with the proper choice of blood perfusion source terms, tissue thickness and geometric scaling factor. Although the simulations may not be useful in providing a unique solution (i.e. exact size and location of the tumour owing to the complex physiological relationship between ...

Identification of tumor region parameters using evolutionary algorithm and multiple reciprocity boundary element method

Abstract: In the paper the inverse problems consisting in the simultaneous estimation of unknown thermophysical and/or geometrical parameters (thermal conductivity, perfusion coefficient, metabolic heat source, location, size) of the tumor region are solved. The additional information concerning the knowledge of local skin surface temperature at the selected set of points is assumed to be known. The problem of thermal processes proceeding in the domain considered is described by the system of the Pennes equations and boundary conditions given on the outer and contact surfaces. On the stage of numerical solution the evolutionary algorithm coupled with the multiple reciprocity boundary element method has been applied.

Thermal simulation of breast tumors

Abstract: It is well known that differences in energy consumption exist for normal and cancerous tissue. These differences lead to small but detectable local temperature changes, which is why infrared imaging has been used in the detection of different types of cancer; however, the early instrumentation was not sensitive enough to detect the subtle changes in temperature needed to accurately diagnose and monitor the disease. In recent years the sensitivity of infrared instruments has greatly improved. In this paper the bioheat transfer equation is solved for a simplified model of a female breast and a cancerous tumor in order to quantify the minimum size of a tumor or the maximum depth of a certain sized tumor that a modern state-of-the-art infrared imaging system can detect. Finite Element simulations showed that current state-of-the-art imagers are capable of detecting 3 cm tumors located deeper than 7 cm from the skin surface, and tumors smaller than 0.5 cm can be detected if they are located close to the surface of the skin.

Breast Tumor simulation and parameters estimation using evolutionary algorithms

Abstract: An estimation methodology is presented to determine the breast tumor parameters using the surface temperature profile that may be obtained by infrared thermography. The estimation methodology involves evolutionary algorithms using artificial neural network (ANN) and genetic algorithm (GA). The ANN is used to map the relationship of tumor parameters (depth, size, and heat generation) to the temperature profile over the idealized breast model. The relationship obtained from ANN is compared to that obtained by finite element software. Results from ANN training/testing were in good agreement with those obtained from finite element model. After ANN validation, GA is used to estimate tumor parameters by minimizing a fitness function involving comparing the temperature profiles from simulated or clinical data to those obtained by ANN. Results show that it is possible to determine the depth, diameter, and heat generation rate from the surface temperature data (with 5% random noise) with good accuracy for the 2D model. With 10% noise, the accuracy of estimation deteriorates for deep-seated tumors with low heat generation. In order to further develop this methodology for use in a clinical scenario, several aspects such as 3D breast geometry and the effects of nonuniform cooling should be considered in future investigations.

Estimation of parameters in multi-mode heat transfer problems using Bayesian inference : Effect of noise and a priori

Abstract: Parameter estimation problems and heat source/flux reconstruction problems are some of the most frequently encountered inverse heat transfer problems. These problems find their application in many areas of science and engineering. The primary focus of this paper is on the heat transfer parameter estimation for a two-dimensional unsteady heat conduction problem with (a) convection boundary condition and (b) convection and radiation boundary condition. The paper demonstrates the effect of a priori model on the performance of the algorithm at different noise levels in the measured data. The inverse problem is solved using three different a priori models namely normal, log normal and uniform. The posterior PDF is sampled using the Metropolis–Hastings sampling algorithm. Both single-parameter estimation and multi-parameter estimation problems are addressed and the effects of corresponding a priori models are studied. It was found that the mean and maximum a posteriori estimates for thermal conductivity and the convection heat transfer coefficient were insensitive to the a priori model at all the considered noise levels for the single-parameter estimation problem. At high noise levels in the two-parameter estimation problem, the estimates for thermal conductivity and convection coefficient were sensitive to the a priori model. It was also found that the standard deviation of the samples was correlated to the error in estimation in the single-parameter estimation case. In three parameter estimation case, alternate solutions to the same problem were retrieved due to a strong correlation between the convection coefficient and the emissivity. However, a more informative a priori model could address this issue.