Resumo Introdução: A termografia por imagem infravermelha (IR) é uma técnica para diagnóstico não-invasiva que permite a avaliação e quantificação de variações de temperatura na superfície da pele. Apesar de fornecer informações significativas para auxiliar no diagnóstico médico, esta técnica não permite avaliar detalhes anatômicos da região sendo analisada. Este artigo apresenta uma nova metodologia para realizar a fusão entre diferentes modalidades de imagens, tais como ressonância magnética (MRI) ou tomografia computadorizada por raios X (CT), juntamente com imagens de termografia infravermelha. Métodos: Para a construção do modelo 3D, primeiramente são adquiridas as imagens por ressonância magnética (MRI) ou tomografia computadorizada (CT) e um conjunto de imagens térmicas da região de interesse. Em seguida, realiza-se o registro utilizando as projeções 2D (dos planos tomográficos) com as imagens térmicas. Após o registro, as imagens térmicas são combinadas e projetadas sobre o modelo 3D das imagens de MRI ou CT. Resultados: O resultado é uma imagem 3D que combina informação de duas modalidades de imagens médicas diferentes. A combinação dessas duas modalidades de imagens médicas disponibiliza uma nova técnica de imagem 3D que agrupa informações anatômicas (MRI ou CT) e funcionais (variações de temperatura na superfície do corpo). Conclusão: Os resultados obtidos até o momento com essa nova metodologia indicam que ela pode auxiliar em diagnósticos médicos.Palavras-chave Termografia, Registro, Fusão de imagens, Visualização 3D. 3D image fusion using MRI/CT and infrared imagesAbstract Introduction: Infrared (IR) thermal imaging is a non-invasive and diagnostic technique that allows evaluation and quantification based on the temperature changes of the skin surface. It provides significant information for clinical diagnosis; however this technique does not present the anatomical details of the region under inspection. In this work, it is presented an innovative image fusion method between different imaging modalities, such as magnetic resonance images (MRI) or X-ray computed tomography (CT), together with IR thermal images. Methods: Firstly, in order to build the 3D model, the MRI or CT images and the IR thermal images (from the region of interest) are acquired. Then, based on the tomographic planes (image slices), the 2D projections are generated, and the IR images are registered accordingly. Next, the already registered IR set of images are combined and projected over the 3D MRI or CT model. Results: The result is a 3D fused image that combines the information contents from the two different medical imaging modalities. The combination of these two medical imaging modalities offers a new 3D imaging technique that combines anatomical (MRI or CT) and functional (the body´s surface temperature) information. Conclusion: The results obtained up to now with this new methodology indicate that it can aid in medical diagnosis.

The measurement of temperature variation along the surface of the body, provided by digital infrared thermal imaging (DITI), is becoming a valuable auxiliary tool for the early detection of many diseases in medicine. However, DITI is essentially a 2-D technique and its image does not provide useful anatomical information associated with it. However, multimodal image registration and fusion may overcome this difficulty and provide additional information for diagnosis purposes. In this paper, a new method of registering and merging 2-D DITI and 3-D MRI is presented. Registration of the images acquired from the two modalities is necessary as they are acquired with different image systems. Firstly, the body volume of interest is scanned by a MRI system and a set of 2-D DITI of it, at orthogonal angles, is acquired. Next, it is necessary to register these two different sets of images. This is done by creating 2-D MRI projections from the reconstructed 3-D MRI volume and registering it with the DITI. Once registered, the DITI is then projected over the 3-D MRI. The program developed to assess the proposed method to combine MRI and DITI resulted in a new tool for fusing two different image modalities, and it can help medical doctors.

Three-dimensional medical image reconstruction using different images modalities require registration techniques that are, in general, based on the stacking of 2D MRI/CT images slices. In this way, the integration of two different imaging modalities: anatomical (MRI/CT) and physiological information (infrared image), to generate a 3D thermal model, is a new methodology still under development. This paper presents a 3D THERMO interface that provides flexibility for the 3D visualization: it incorporates the DICOM parameters; different color scale palettes at the final 3D model; 3D visualization at different planes of sections; and a filtering option that provides better image visualization. To summarize, the 3D thermographc medical image visualization provides a realistic and precise medical tool. The merging of two different imaging modalities allows better quality and more fidelity, especially for medical applications in which the temperature changes are clinically significant.

No abstract

ABSTRACT:Cancer is responsible for about 7 million annual deaths worldwide. Among them, the melanoma type, responsible for 4% of the skin cancers, whose incidence has doubled in the last ten years. The processing of digital images has shown good potential for assistance in the early detection of melanomas. In this sense, the objective of the current study was to develop a software for clinical images processing and reach a score of accuracy higher than 95%. The ABCD rule was used as a guide for the development of computational analysis methods. MATLAB was used as programming environment for the development of the processing of digital images software. The images used were acquired from two banks of free images. They included images of melanomas (n=15) and nevi images (not cancer) (n=15). Images in RGB color channel were used, which were converted to grayscale, 8x8 median filter applications and 3x3 neighborhood approach technique. After, we proceeded to the binarization and inversion of black and white for later extraction of contour characteristics of the lesion. The classifier used was an artificial neural network of radial basis, getting accuracy for diagnosis of melanomas images of 100% and of 90.9% for not cancer images. Thus, global correction for diagnostic prediction was 95.5%. An area under the ROC graph 0.967 was achieved, suggesting a great diagnostic predictive ability. Besides, the software presents low cost use, since it can be run on most operating systems used nowadays.

No abstract

No abstract

No abstract