Energy curve based enhanced smell agent optimizer for optimal multilevel threshold selection of thermographic breast image segmentation

Multilevel thresholding image segmentation will subdivide an image into several meaningful regions or objects, which makes the image more informative and easier to analyze. Optimal multilevel thresholding approaches are extensively used for segmentation because they are easy to implement and offer low computational cost. Multilevel thresholding image segmentation is frequently performed using popular methods such as Otsu's between-class variance and Kapur's entropy. Numerous researchers have used evolutionary algorithms to identify the best multilevel thresholds based on the above approaches using histogram. This paper uses the Energy Curve (EC) based thresholding method instead of the histogram. Chaotic Bidirectional Smell Agent Optimization with Adaptive Control Strategy (ChBSAOACS), a powerful evolutionary algorithm, is developed and employed in this paper to create and execute an effective method for multilevel thresholding segmentation of breast thermogram images based on energy curves. The proposed algorithm was tested for viability on standard breast thermogram images. All experimental data are examined quantitatively and qualitatively to verify the suggested method's efficacy.

Applicability of thermography for cancer diagnosis in small animals

Medical thermography is an imaging test used to monitor skin surface temperature. Although it is not a recent technique, significant advances have been made since the 2000s with the equipment modernization, leading to its popularization. In cancer diagnosis, the application of thermography is supported by the difference in thermal distribution between neoplastic processes and adjacent healthy tissue. The mechanisms involved in heat production by cancer cells include neoangiogenesis, increased metabolic rate, vasodilation, and the release of nitric oxide and pro-inflammatory substances. Currently, thermography has been widely studied in humans as a screening tool for skin and breast cancer, with positive results. In veterinary medicine, the technique has shown promise and has been described for skin and soft tissue tumors in felines, mammary gland tumors, osteosarcoma, mast cell tumors, and perianal tumors in dogs. This review discusses the fundamentals of the technique, monitoring conditions, and the role of thermography as a complementary diagnostic tool for cancer in veterinary medicine, as well as future perspectives for improvement.

Three-dimensional numerical evaluation of skin surface thermal contrast by application of hypothermia at different depths and sizes of the breast tumor

BACKGROUND AND OBJECTIVE

Thermal procedures can provide improvements in the thermal contrast of thermographic images in an attempt to diagnose early cases of breast cancer. This work aims to analyze the thermal contrast of different stages and depths of breast tumors from hypothermia treatment using an active thermography analysis. The influence of variation in metabolic heat generation and adipose tissue composition on thermal contrasts is also analyzed.

METHODS

The proposed methodology was based on the solution of the Pennes equation for a three-dimensional model similar to the real anatomy of the breast by commercial software COMSOL Multiphysics. The thermal procedure consists of three steps: Stationary, hypothermia and thermal recovery. During hypothermia, the boundary condition of the external surface was replaced by a constant temperature of 0, 5, 10, and 15 ^∘C, simulating a gel pack, for cooling times of up to 20 min. In the thermal recovery, after the removal of the cooling, the breast was submitted again to the condition of natural convection on the external surface.

RESULTS

Thermal contrasts in superficial tumors, for all hypothermia resulted in improvements in thermographs. For smallest tumor, the use of high resolution and sensitive thermal imaging cameras to acquire this thermal change may be necessary. For tumor of diameter of 10 cm, cooling from 0 ^∘C can increase the thermal contrast by up to 136% compared to the passive thermography. Analyzes with deeper tumors showed very small temperature variations. Even so, the thermal contrast gain in cooling at 0 ^∘C for the tumor with a diameter of 1 cm reached 37% in relation to passive thermography.

CONCLUSIONS

Thus, this work contributes as an important tool in the analysis of the appropriate use of hypothermia for different cases in early stages of breast cancer, considering that long times are needed to obtain the best thermal contrast.

Hyperspectral image-based analysis of thermal damage for ex-vivo bovine liver utilizing radiofrequency ablation

BACKGROUND & OBJECTIVE

Thermal ablation is the predominant methodology to treat liver tumors for segregating patients who are not permitted to have surgical intervention. However, noticing or predicting the size of the thermal strategies is a challenging endeavor. We aim to analyze the effects of ablation district volume following radiofrequency ablation (RFA) of ex-vivo liver exploiting a custom Hyperspectral Imaging (HSI) system.

MATERIALS AND METHODS

RFA was conducted on the ex-vivo bovine liver at focal and peripheral blood vessel sites and observed by Custom HSI system, which has been designed to assess the exactness and proficiency using visible and near-infrared wavelengths region for tissue thermal effect. The experiment comprised up to ten trials with RFA. The experiment was carried out in two stages to assess the percentage of the thermal effect on the investigated sample superficially and for the side penetration effect. Measuring the diffuse reflectance (Ŗ_d) of the sample to identify the spectral reflectance shift which could differentiate between normal and ablated tissue exploiting the designed cross-correlation algorithm for monitoring of thermal ablation.

RESULTS

Determination of the diffuse reflection (Ŗ_d) spectral signature responses from normal, thermal effected, and thermal ablation regions of the investigated liver sample. Where the ideal wavelength range at (600-640 nm) could discriminate between these different regions. Then, exploited the converted RGB image of the HS liver tissue after RFA for more validations which shows that the optimum wavelength for differentiation at (530-560 nm and 600-640 nm). Finally, applying statistical analysis to validate our results presenting that wavelength 600 nm had the highest standard deviation (δ) to differentiate between various thermally affected regions regarding the normal tissue and wavelength 640 nm shows the highest (δ) to differentiate between the ablated and normal regions.

CONCLUSION

The designed and implemented medical imaging system incorporated the hyperspectral camera capabilities with the associate cross-correlation algorithm that could successfully distinguish between the ablated and thermally affected regions to assist the surgery during the tumor therapy.

BREAST CANCER DETECTION USING RSFS-BASED FEATURE SELECTION ALGORITHMS IN THERMAL IMAGES

Breast cancer is a common cancer in female. Accurate and early detection of breast cancer can play a vital role in treatment. This paper presents and evaluates a thermogram based Computer-Aided Detection (CAD) system for the detection of breast cancer. In this CAD system, the Random Subset Feature Selection (RSFS) algorithm and hybrid of minimum Redundancy Maximum Relevance (mRMR) algorithm and Genetic Algorithm (GA) with RSFS algorithm are utilized for feature selection. In addition, the Support Vector Machine (SVM) and k-Nearest Neighbors (kNN) algorithms are utilized as classifier algorithm. The proposed CAD system is verified using MATLAB 2017 and a dataset that is composed of breast images from 78 patients. The implementation results demonstrate that using RSFS algorithm for feature selection and kNN and SVM algorithms as classifier have accuracy of 85.36% and 75%, and sensitivity of 94.11% and 79.31%, respectively. In addition, using hybrid GA and RSFS algorithm for feature selection and kNN and SVM algorithms as classifier have accuracy of 83.87% and 69.56%, and sensitivity of 96% and 81.81%, respectively, and using hybrid mRMR and RSFS algorithms for feature selection and kNN and SVM algorithms as classifier have accuracy of 77.41% and 73.07%, and sensitivity of 98% and 72.72%, respectively.

Thermogram Breast Cancer Detection: A Comparative Study of Two Machine Learning Techniques

Breast cancer is considered one of the major threats for women’s health all over the world. The World Health Organization (WHO) has reported that 1 in every 12 women could be subject to a breast abnormality during her lifetime. To increase survival rates, it is found that it is very effective to early detect breast cancer. Mammography-based breast cancer screening is the leading technology to achieve this aim. However, it still can not deal with patients with dense breast nor with tumor size less than 2 mm. Thermography-based breast cancer approach can address these problems. In this paper, a thermogram-based breast cancer detection approach is proposed. This approach consists of four phases: (1) Image Pre-processing using homomorphic filtering, top-hat transform and adaptive histogram equalization, (2) ROI Segmentation using binary masking and K-mean clustering, (3) feature extraction using signature boundary, and (4) classification in which two classifiers, Extreme Learning Machine (ELM) and Multilayer Perceptron (MLP), were used and compared. The proposed approach is evaluated using the public dataset, DMR-IR. Various experiment scenarios (e.g., integration between geometrical feature extraction, and textural features extraction) were designed and evaluated using different measurements (i.e., accuracy, sensitivity, and specificity). The results showed that ELM-based results were better than MLP-based ones with more than 19%.

Cancer is an adaptation that selects in animals against energy dissipation

As cancer usually follows reproduction, it is generally assumed that cancer does not select. Graham has however argued that juvenile cancer, which precedes reproduction, could during evolution have implemented a "cancer selection" that resulted in novel traits that suppress this juvenile cancer; an example is protection against UV sunlight-induced cancer, required for the emergence of terrestrial animals from the sea. We modify the cancer selection mechanism to the posited "cancer adaptation" mechanism, in which juvenile mortality is enhanced through the diminished care received by juveniles from their (grand) parents when these suffer from cancer in old age. Moreover, it is posited that the cancer adaptation selects against germline "dissipative genes", genes that result in enhanced free energy dissipation. Cancer's progression is interpreted as a cascade at increasing scale of repeated amplification of energy dissipation, a cascade involving heat shock, the Warburg effect, the cytokine IL-6, tumours, and hypermetabolism. Disturbance of any physiological process must enhance energy dissipation if the animal remains functioning normally, what explains multicausality, why "everything gives you cancer". The hypothesis thus comprises two newly invoked partial processes-diminished (grand) parental care and dissipation amplification-and results in a "selection against enhanced energy dissipation" which gives during evolution the benefit of energy conservation. Due to this benefit, cancer would essentially be an adaptation, and not a genetic disease, as assumed in the "somatic mutation theory". Cancer by somatic mutations is only a side process. The cancer adaptation hypothesis is substantiated by (1) cancer's extancy, (2) the failure of the somatic mutation theory, (3) cancer's initiation by a high temperature, (4) the interpretation of cancer's progression as a thermal process, and (5) the interpretation of tumours as organs that implement thermogenesis. The hypothesis could in principle be verified by monitoring in a population over several generations (1) the presence of dissipative genes, (2) the incidence of cancer, and (3) the beneficial effect of dissipative gene removal by cancer on starvation/famine survival.

Preliminary results of a new approach for three-dimensional reconstruction of Dynamic AngioThermography (DATG) images based on the inversion of heat equation

Dynamic AngioThermography (DATG) is a contact-plate technique capable of producing a digital representation of breast vascularity. The inception and growth of a tumor are associated with neoangenesis, which may result in a demonstrable alteration in the regional blood flow, while in normal health conditions the vascularity remains unchanged throughout life. DATG, if included in the clinical evaluation for breast cancer, could potentially improve the accuracy of the diagnosis of this disease. Conventional DATG is limited, however, in that it is a projection (i.e. two-dimensional) imaging technique that does not provide any information on the depth and its effect on the pattern of the perfusion revealed by this technique. In fact, the blood pattern is detected by projecting temperature signals on the plate, thus acquiring a digital two-dimensional image. In this article we propose a new approach for extracting information on depth through the inversion of the Fourier heat equation. The idea is to extract the information along the third axis while acquiring and analyzing the temporal sequence during the process of image formation. The method implemented has been tested on a dedicated "electric phantom" and in one in vivo experiment. In spite of the limits of these preliminary tests, the experimental results have shown that this method makes it possible to obtain a 3D representation of the vascularity. Although it appears to be promising, further validation and characterization of our technique are required.

Comparison of the Accuracy of Thermography and Mammography in the Detection of Breast Cancer

BACKGROUND

Benefits and harms of screening mammography have been disputed in recent years. This fact, along with the limitations of mammography as well as its unavailability in all our medical centers, tempted us to evaluate the accuracy of thermography in detecting breast abnormalities.

PATIENTS AND METHODS

All patients who were candidates for breast biopsy were examined by both mammography and thermography before tissue sampling in a referral center between January 2013 and January 2014. We defined sensitivities and specificities, and positive predictive values (PPVs) and negative predictive values (NPVs), of the 2 modalities in comparison with histologic results as the gold standard.

RESULTS

132 patients were included. The median age of all patients was 49.5 ± 10.3 years (range 24-75 years). The sensitivity, specificity, PPV, NPV, and accuracy for mammography were 80.5%, 73.3%, 85.4%, 66.0%, and 76.9%, respectively, whereas for thermography the figures were 81.6%, 57.8%, 78.9%, 61.9%, and 69.7%, respectively.

CONCLUSION

Our study confirms that, at the present time, thermography cannot substitute for mammography for the early diagnosis of breast cancer.

Hybrid analysis for indicating patients with breast cancer using temperature time series

Breast cancer is the most common cancer among women worldwide. Diagnosis and treatment in early stages increase cure chances. The temperature of cancerous tissue is generally higher than that of healthy surrounding tissues, making thermography an option to be considered in screening strategies of this cancer type. This paper proposes a hybrid methodology for analyzing dynamic infrared thermography in order to indicate patients with risk of breast cancer, using unsupervised and supervised machine learning techniques, which characterizes the methodology as hybrid. The dynamic infrared thermography monitors or quantitatively measures temperature changes on the examined surface, after a thermal stress. In the dynamic infrared thermography execution, a sequence of breast thermograms is generated. In the proposed methodology, this sequence is processed and analyzed by several techniques. First, the region of the breasts is segmented and the thermograms of the sequence are registered. Then, temperature time series are built and the k-means algorithm is applied on these series using various values of k. Clustering formed by k-means algorithm, for each k value, is evaluated using clustering validation indices, generating values treated as features in the classification model construction step. A data mining tool was used to solve the combined algorithm selection and hyperparameter optimization (CASH) problem in classification tasks. Besides the classification algorithm recommended by the data mining tool, classifiers based on Bayesian networks, neural networks, decision rules and decision tree were executed on the data set used for evaluation. Test results support that the proposed analysis methodology is able to indicate patients with breast cancer. Among 39 tested classification algorithms, K-Star and Bayes Net presented 100% classification accuracy. Furthermore, among the Bayes Net, multi-layer perceptron, decision table and random forest classification algorithms, an average accuracy of 95.38% was obtained.

Parameter estimation of breast tumour using dynamic neural network from thermal pattern

This article presents a new approach for estimating the depth, size, and metabolic heat generation rate of a tumour. For this purpose, the surface temperature distribution of a breast thermal image and the dynamic neural network was used. The research consisted of two steps: forward and inverse. For the forward section, a finite element model was created. The Pennes bio-heat equation was solved to find surface and depth temperature distributions. Data from the analysis, then, were used to train the dynamic neural network model (DNN). Results from the DNN training/testing confirmed those of the finite element model. For the inverse section, the trained neural network was applied to estimate the depth temperature distribution (tumour position) from the surface temperature profile, extracted from the thermal image. Finally, tumour parameters were obtained from the depth temperature distribution. Experimental findings (20 patients) were promising in terms of the model's potential for retrieving tumour parameters.

Potentialities of steady-state and transient thermography in breast tumour depth detection: A numerical study

Breast thermography still has inherent limitations that prevent it from being fully accepted as a breast screening modality in medicine. The main challenges of breast thermography are to reduce false positive results and to increase the sensitivity of a thermogram. Further, it is still difficult to obtain information about tumour parameters such as metabolic heat, tumour depth and diameter from a thermogram. However, infrared technology and image processing have advanced significantly and recent clinical studies have shown increased sensitivity of thermography in cancer diagnosis. The aim of this paper is to study numerically the possibilities of extracting information about the tumour depth from steady state thermography and transient thermography after cold stress with no need to use any specific inversion technique. Both methods are based on the numerical solution of Pennes bioheat equation for a simple three-dimensional breast model. The effectiveness of two approaches used for depth detection from steady state thermography is assessed. The effect of breast density on the steady state thermal contrast has also been studied. The use of a cold stress test and the recording of transient contrasts during rewarming were found to be potentially suitable for tumour depth detection during the rewarming process. Sensitivity to parameters such as cold stress temperature and cooling time is investigated using the numerical model and simulation results reveal two prominent depth-related characteristic times which do not strongly depend on the temperature of the cold stress or on the cooling period.

Application of infrared thermography in computer aided diagnosis

The invention of thermography, in the 1950s, posed a formidable problem to the research community: What is the relationship between disease and heat radiation captured with Infrared (IR) cameras? The research community responded with a continuous effort to find this crucial relationship. This effort was aided by advances in processing techniques, improved sensitivity and spatial resolution of thermal sensors. However, despite this progress fundamental issues with this imaging modality still remain. The main problem is that the link between disease and heat radiation is complex and in many cases even non-linear. Furthermore, the change in heat radiation as well as the change in radiation pattern, which indicate disease, is minute. On a technical level, this poses high requirements on image capturing and processing. On a more abstract level, these problems lead to inter-observer variability and on an even more abstract level they lead to a lack of trust in this imaging modality. In this review, we adopt the position that these problems can only be solved through a strict application of scientific principles and objective performance assessment. Computing machinery is inherently objective; this helps us to apply scientific principles in a transparent way and to assess the performance results. As a consequence, we aim to promote thermography based Computer-Aided Diagnosis (CAD) systems. Another benefit of CAD systems comes from the fact that the diagnostic accuracy is linked to the capability of the computing machinery and, in general, computers become ever more potent. We predict that a pervasive application of computers and networking technology in medicine will help us to overcome the shortcomings of any single imaging modality and this will pave the way for integrated health care systems which maximize the quality of patient care.

Wavelet-based multifractal analysis of dynamic infrared thermograms to assist in early breast cancer diagnosis

Breast cancer is the most common type of cancer among women and despite recent advances in the medical field, there are still some inherent limitations in the currently used screening techniques. The radiological interpretation of screening X-ray mammograms often leads to over-diagnosis and, as a consequence, to unnecessary traumatic and painful biopsies. Here we propose a computer-aided multifractal analysis of dynamic infrared (IR) imaging as an efficient method for identifying women with risk of breast cancer. Using a wavelet-based multi-scale method to analyze the temporal fluctuations of breast skin temperature collected from a panel of patients with diagnosed breast cancer and some female volunteers with healthy breasts, we show that the multifractal complexity of temperature fluctuations observed in healthy breasts is lost in mammary glands with malignant tumor. Besides potential clinical impact, these results open new perspectives in the investigation of physiological changes that may precede anatomical alterations in breast cancer development.