Abstract
Body skin temperature is a useful parameter for diagnosing diseases and infrared thermography can, be a powerful tool in providing important information to detect body temperature changes in a noninvasive way. The aim of this work was to study the pattern of skin temperature during pregnancy, to establish skin temperature reference values and to find correlations between these and the pregnant population characteristics. Sixty-one healthy pregnant women (mean age 30.6 +/- 5.1 years) in the 8th-40th gestational week with normal pregnancies were examined in 31 regions of interest (ROI). The ROIs were defined all over the body in order to determine the most influenced by factors such as age or body mass index (BMI). The results obtained in this work highlight that in normal pregnant women the skin temperature is symmetrically distributed, with the symmetrical areas differing less than 0.5 degrees C, with a mean value of 0.25 +/- 0.23 degrees C. This study identified a significant negative correlation between the BMI and temperature. Age has been shown to have great influence on the skin temperature, with a significant increase of temperature observed with age. This work explores a novel medical application of infrared thermography and provides a characterization of thermal skin profile in human pregnancy for a large set of ROIs while also evaluating the effects of age and BMI.

Abstract
A multi-wavelengths analysis for pulse waveform extraction using laser speckle is conducted. The proposed system consists of three coherent light sources (532 nm, 635 nm, 850 nm). A bench-test composed of a moving skin-like phantom (silicone membrane) is used to compare the results obtained from different wavelengths. The system is able to identify a skin-like phantom vibration frequency, within physiological values, with a minimum error of 0.5 mHz for the 635 nm and 850 nm wavelengths and a minimum error of 1.3 mHz for the 532 nm light wavelength using a FFT-based algorithm. The phantom velocity profile is estimated with an error ranging from 27% to 9% using a bidimensional correlation coefficient-based algorithm. An in vivo trial is also conducted, using the 532 nm and 635 nm laser sources. The 850 nm light source has not been able to extract the pulse waveform. The heart rate is identified with a minimum error of 0.48 beats per minute for the 532 nm light source and a minimal error of 1.15 beats per minute for the 635 nm light source. Our work reveals that a laser speckle-based system with a 532 nm wavelength is able to give arterial pulse waveform with better results than those given with a 635 nm laser.

Abstract
The ability to detect pathological changes early and in a non-invasive way represents important advantages in the medical field. Diagnosis should become less intrusive, more accurate and less expensive in order to implement in the clinical routine. Infrared thermography has the advantages of being non-invasive, fast, reliable, capable of producing multiple recordings in short intervals, and absolutely safe for patients and clinicians. Thermographic image (TI) came to be an extensively studied technique to quantify sensitive changes in skin temperature in relation to certain diseases: early in the pathological process (lesions, inflammation and infection) the circulation fluxes are altered and, consequently, the tissues’ temperature is reflected in thermography pattern, before structural or functional changes can be observed. This technique proved to be able to give relevant clinical information, such as breast cancer, foot disease in diabetes, rheumatoid arthritis and sports injuries. Monitoring the temperature profile of a patient will allow understanding the physiological evolution of some diseases or monitoring the pharmacologic therapy effect. However, the high cost of this technology and the small number of commercial solutions do not allow a general implementation in the clinical environmental. The future direction is the combination of this technique with the other images techniques in order to add clinical information for a more reliable diagnostic.

Abstract
Artificial Intelligence (AI) is one of the big hopes for the future of a positive revolution in the use of medical data to improve clinical routine and personalized medicine [...]

Abstract
Bone marrow edema (BME) is the term given to the abnormal fluid signal seen within the bone marrow on magnetic resonance imaging (MRI). It usually indicates the presence of underlying pathology and is associated with a myriad of conditions/causes. However, it can be misleading, as in some cases, it may be associated with normal changes in the bone, especially during the growth period of childhood, and objective methods for assessment are lacking. In this work, learning models for BME detection were developed. Transfer learning was used to overcome the size limitations of the dataset, and two different regions of interest (ROI) were defined and compared to evaluate their impact on the performance of the model: bone segmention and intensity mask. The best model was obtained for the high intensity masking technique, which achieved a balanced accuracy of 0.792 +/- 0.034. This study represents a comparison of different models and data regularization techniques for BME detection and showed promising results, even in the most difficult range of ages: children and adolescents. The application of machine learning methods will help to decrease the dependence on the clinicians, providing an initial stratification of the patients based on the probability of edema presence and supporting their decisions on the diagnosis.

Abstract
Biomedical engineering has been targeted as a potential research candidate for machine learning applications, with the purpose of detecting or diagnosing pathologies. However, acquiring relevant, high-quality, and heterogeneous medical datasets is challenging due to privacy and security issues and the effort required to annotate the data. Generative models have recently gained a growing interest in the computer vision field due to their ability to increase dataset size by generating new high-quality samples from the initial set, which can be used as data augmentation of a training dataset. This study aimed to synthesize artificial lung images from corresponding positional and semantic annotations using two generative adversarial networks and databases of real computed tomography scans: the Pix2Pix approach that generates lung images from the lung segmentation maps; and the conditional generative adversarial network (cCGAN) approach that was implemented with additional semantic labels in the generation process. To evaluate the quality of the generated images, two quantitative measures were used: the domain-specific Frechet Inception Distance and Structural Similarity Index. Additionally, an expert assessment was performed to measure the capability to distinguish between real and generated images. The assessment performed shows the high quality of synthesized images, which was confirmed by the expert evaluation. This work represents an innovative application of GAN approaches for medical application taking into consideration the pathological findings in the CT images and the clinical evaluation to assess the realism of these features in the generated images.