Abstract
Label noise is omnipresent in the annotations process and has an impact on supervised learning algorithms. This work focuses on the impact of label noise on the performance of learning models by examining the effect of random and class-dependent label noise on a binary classification task: quality assessment for photoplethysmography (PPG). PPG signal is used to detect physiological changes and its quality can have a significant impact on the subsequent tasks, which makes PPG quality assessment a particularly good target for examining the impact of label noise in the field of biomedicine. Random and class-dependent label noise was introduced separately into the training set to emulate the errors associated with fatigue and bias in labeling data samples. We also tested different representations of the PPG, including features defined by domain experts, 1D raw signal and 2D image. Three different classifiers are tested on the noisy training data, including support vector machine (SVM), XGBoost, 1D Resnet and 2D Resnet, which handle three representations, respectively. The results showed that the two deep learning models were more robust than the two traditional machine learning models for both the random and class-dependent label noise. From the representation perspective, the 2D image shows better robustness compared to the 1D raw signal. The logits from three classifiers are also analyzed, the predicted probabilities intend to be more dispersed when more label noise is introduced. From this work, we investigated various factors related to label noise, including representations, label noise type, and data imbalance, which can be a good guidebook for designing more robust methods for label noise in future work.

Abstract
Hereditary amyloidosis associated with transthyretin (ATTRv), is a rare autosomal dominant disease characterized by length-dependent symmetric polyneuropathy that has gait impairment as one of its consequences. The gait pattern of V30M ATTRv amyloidosis patients has been described as similar to that of diabetic neuropathy, associated with steppage, but has never been quantitatively characterized. In this study we aim to characterize the gait pattern of patients with V30M ATTRv amyloidosis, thus providing information for a better understanding and potential for supporting diagnosis and disease progression evaluation. We present a case series in which we conducted two gait analyses, 18 months apart, of five V30M ATTRv amyloidosis patients using a 12-camera, marker based, optical system as well as six force platforms. Linear kinematics, ground reaction forces, and angular kinematics results are analyzed for all patients. All patients, except one, showed a delayed toe-off in the second assessment, as well as excessive pelvic rotation, hip extension and external transverse rotation and knee flexion (in stance and swing phases), along with reduced vertical and mediolateral ground reaction forces. The described gait anomalies are not clinically quantified; thus, gait analysis may contribute to the assessment of possible disease progression along with the clinical evaluation.

Abstract
Total white blood cells count is an important diagnostic parameter in both human and veterinary medicines. State-of-the-art is performed by flow cytometry combined with light scattering or impedance measurements. Spectroscopy point-of-care has the advantages of miniaturization, low sampling, and real-time hemogram analysis. While white blood cells are in low proportions, while red blood cells and bilirubin dominate spectral information, complicating detection in blood. We performed a feasibility study for the direct detection of white blood cells counts in canine blood by visible-near infrared spectroscopy for veterinary applications, benchmarking current chemometrics techniques (similarity, global and local partial least squares, artificial neural networks and least-squares support vector machines) with self-learning artificial intelligence, introducing data augmentation to overcome the hurdle of knowledge representativity. White blood cells count information is present in the recorded spectra, allowing significant discrimination and equivalence between hemogram and spectra principal component scores. Chemometrics methods correlate white blood cells count to spectral features but with lower accuracy. Self-Learning Artificial Intelligence has the highest correlation (0.8478) and a small standard error of 6.92 x 10(9) cells/L, corresponding to a mean absolute percentage error of 25.37%. Such allows the accurate diagnosis of white blood cells in the range of values of the reference interval (5.6 to 17.8 x 10(9) cells/L) and above. This research is an important step toward the existence of a miniaturized spectral point-of-care hemogram analyzer.

Abstract
Advances in data-driven deep learning for chest X-ray image analysis underscore the need for explainability, privacy, large datasets and significant computational resources. We frame privacy and explainability as a lossy single-image compression problem to reduce both computational and data requirements without training. For Cardiomegaly detection in chest X-ray images, we propose HeartSpot and four spatial bias priors. HeartSpot priors define how to sample pixels based on domain knowledge from medical literature and from machines. HeartSpot privatizes chest X-ray images by discarding up to 97% of pixels, such as those that reveal the shape of the thoracic cage, bones, small lesions and other sensitive features. HeartSpot priors are ante-hoc explainable and give a human-interpretable image of the preserved spatial features that clearly outlines the heart. HeartSpot offers strong compression, with up to 32x fewer pixels and llx smaller filesize. Cardiomegaly detectors using HeartSpot are up to 9x faster to train or at least as accurate (up to +.01 AUC ROC) when compared to a baseline DenseNet121. HeartSpot is post-hoc explainable by re-using existing attribution methods without requiring access to the original non-privatized image. In summary, HeartSpot improves speed and accuracy, reduces image size, improves privacy and ensures explainability.

Abstract

Abstract
Cardiac auscultation is still the most cost-effective screening procedure for cardiovascular diseases. The development of computer assisted methods can empower a large variety of health professionals and thus enable mass cardiac health low-cost screening. The procedure for correct cardiac auscultation includes listening to the heart sounds of the four main auscultation spots. Until recently, attempts to develop automatic heart sound analysis methods that explore the multi-channel richness of a real auscultation, were very difficult due to the lack of adequate public datasets. In this work, we use the CirCor Dataset which is characterized by the existence of more than one heart sound per patient (each patient has heart sounds collected at different auscultation spots). Using this dataset, we evaluate and quantify the comparative impact of using a single or a multichannel approach. A single channel approach uses the sound from a single auscultation spot, whereas a multi-channel approach uses four auscultation spots in an asynchronous way. From the different classifiers tested, models that use four auscultation spots achieved a higher overall performance than those that search for abnormalities in a single heart sound spot. Our best result is a multi-channel SVM that analyzes four auscultation spots, with an overall performance of 87,4 %. This opens the path to future research using a multi-channel approach.