RESUMO
Thermographic image analysis is a subfield of diagnostic image processing aimed at detecting breast abnormalities in women at an early stage. It is a developing field of research and its effectiveness and scope require scientific assessment to be determined. An open-access dataset has been created for the scientific community to test and develop techniques for computational detection of normal and abnormal breast conditions from thermograms. This dataset is a valuable resource for researchers due to the scarcity of publicly available datasets of breast thermographic images. It includes thermographic images of the female chest area in three capture positions: anterior, left oblique and right oblique. The data set comes from 119 women ranging from 18 to 81 years of age. A table is attached to the dataset with the diagnosis of breast pathology, showing that 84 patients had benign pathology and 35 patients had malignant pathology. The diagnoses of women with healthy breast pathology are not included.
RESUMO
Infrared Thermography (IRT) is a non-contact, non-intrusive, and non-ionizing radiation tool used for detecting breast lesions. This paper analyzes the surface temperature distribution (STD) on an optimal Region of Interest (RoI) for extraction of suitable internal heat source parameters. The physiological parameters are estimated through the inverse solution of the bio-heat equation and the STD of suspicious areas related to the hottest spots of the RoI. To reach these values, the STD is analyzed by means: the Depth-Intensity-Radius (D-I-R) measurement model and the fitting method of Lorentz curve. A highly discriminative pattern vector composed of the extracted physiological parameters is proposed to classify normal and abnormal breast thermograms. A well-defined RoI is delimited at a radial distance, determined by the Support Vector Machines (SVM). Nevertheless, this distance is less than or equal to 1.8 cm due to the maximum temperature location close to the boundary image. The methodology is applied to 87 breast thermograms that belong to the Database for Mastology Research with Infrared Image (DMR-IR). This methodology does not apply any image enhancements or normalization of input data. At an optimal position, the three-dimensional scattergrams show a correct separation between normal and abnormal thermograms. In other cases, the feature vectors are highly correlated. According to our experimental results, the proposed pattern vector extracted at optimal position a=1.6 cm reaches the highest sensitivity, specificity, and accuracy. Even more, the proposed technique utilizes a reduced number of physiological parameters to obtain a Correct Rate Classification (CRC) of 100%. The precision assessment confirms the performance superiority of the proposed method compared with other techniques for the breast thermogram classification of the DMR-IR.
Assuntos
Neoplasias da Mama , Termografia , Neoplasias da Mama/diagnóstico por imagem , Feminino , Temperatura Alta , Humanos , Aumento da Imagem , Máquina de Vetores de Suporte , TemperaturaRESUMO
Medical thermography has been around for several decades however due to its low specificity it has not become a popular medical diagnostic technique. The development of computational models of heat transfer in biological tissue can provide a deeper knowledge of healthy and nonhealthy thermal patterns which could increase the specificity of this technique increasing its usefulness in clinical diagnosis. In this work, the thermal pattern of cancerous tumors and cysts are calculated through finite element computer simulations using a real human female torso. The simulation results show a thermal pattern that agrees with infrared thermal images taken from female subjects, the simulated thermal patterns show real thermal features that do not appear in simulations performed using other approximate geometries of the breast. Results show that the temperature on the region of the skin closest to the tumor decreases for cysts while it increases for malignant tumors. The temperature patterns show a 20% deviation from thermal simulations using a hemispherical model of the breast, these results reinforce the notion that the geometry used for thermal simulation plays an important role in the accuracy of the simulations. These results are a first step in understanding benign and malignant thermal processes of the breast which might help increase the usefulness of infrared imaging in breast clinical diagnosis.