Abstract
A novel algorithm to separate S2 heart sounds into their aortic and pulmonary components is proposed. This approach is based on the assumption that, in different heartbeats of a given recording, aortic and pulmonary components maintain the same waveform but with different relative delays, which are induced by the variation of the thoracic pressure at different respiration phases. The proposed algorithm then retrieves the aortic and pulmonary components as the solution of an optimization problem which is approximated via alternating optimization. The proposed approach is shown to provide reconstructions of aortic and pulmonary components with normalized root mean-squared error consistently below 10% in various operational regimes.

Abstract
Respiratory diseases are among the leading causes of death worldwide. Preventive measures are essential to avoid and increase the odds of a successful recovery. An important screening tool is pulmonary auscultation, an inexpensive, noninvasive and safe method to assess the mechanics and dynamics of the lungs. On the other hand, it is a difficult task for a human listener since some lung sound events have a spectrum of frequencies outside of the human hearing ability. Thus, computer assisted decision systems might play an important role in the detection of abnormal sounds, such as crackle or wheeze sounds. In this paper, we propose a novel system, which is not only able to detect abnormal lung sound events, but it is also able to classify them. Furthermore, our system was trained and tested using the publicly available ICBHI 2017 challenge dataset, and using the metrics proposed by the challenge, thus making our framework and results easily comparable. Using a Mel Spectrogram as an input feature for our convolutional neural network, our system achieved results in line with the current state of the art, an accuracy of 43 %, and a sensitivity of 51%.

Abstract
Cardiac auscultation is the key screening procedure to detect and identify cardiovascular diseases (CVDs). One of many steps to automatically detect CVDs using auscultation, concerns the detection and delimitation of the heart sound boundaries, a process known as segmentation. Whether to include or not a segmentation step in the signal classification pipeline is nowadays a topic of discussion. Up to our knowledge, the outcome of a segmentation algorithm has been used almost exclusively to align the different signal segments according to the heartbeat. In this paper, the need for a heartbeat alignment step is tested and evaluated over different machine learning algorithms, including deep learning solutions. From the different classifiers tested, Gate Recurrent Unit (GRU) Network and Convolutional Neural Network (CNN) algorithms are shown to be the most robust. Namely, these algorithms can detect the presence of heart murmurs even without a heartbeat alignment step. Furthermore, Support Vector Machine (SVM) and Random Forest (RF) algorithms require an explicit segmentation step to effectively detect heart sounds and murmurs, the overall performance is expected drop approximately 5% on both cases.

Abstract
Cardiac auscultation is one of the most cost-effective techniques used to detect and identify many heart conditions. Computer-assisted decision systems based on auscultation can support physicians in their decisions. Unfortunately, the application of such systems in clinical trials is still minimal since most of them only aim to detect the presence of extra or abnormal waves in the phonocardiogram signal, i.e., only a binary ground truth variable (normal vs abnormal) is provided. This is mainly due to the lack of large publicly available datasets, where a more detailed description of such abnormal waves (e.g., cardiac murmurs) exists. To pave the way to more effective research on healthcare recommendation systems based on auscultation, our team has prepared the currently largest pediatric heart sound dataset. A total of 5282 recordings have been collected from the four main auscultation locations of 1568 patients, in the process, 215780 heart sounds have been manually annotated. Furthermore, and for the first time, each cardiac murmur has been manually annotated by an expert annotator according to its timing, shape, pitch, grading, and quality. In addition, the auscultation locations where the murmur is present were identified as well as the auscultation location where the murmur is detected more intensively. Such detailed description for a relatively large number of heart sounds may pave the way for new machine learning algorithms with a real-world application for the detection and analysis of murmur waves for diagnostic purposes.

Abstract
Stomach cancer is the third deadliest type of cancer in the world (0.86 million deaths in 2017). In 2035, a 20% increase will be observed both in incidence and mortality due to demographic effects if no interventions are foreseen. Upper GI endoscopy (UGIE) plays a paramount role in early diagnosis and, therefore, improved survival rates. On the other hand, human and technical factors can contribute to misdiagnosis while performing UGIE. In this scenario, artificial intelligence (AI) has recently shown its potential in compensating for the pitfalls of UGIE, by leveraging deep learning architectures able to efficiently recognize endoscopic patterns from UGIE video data. This work presents a review of the current state-of-the-art algorithms in the application of AI to gastroscopy. It focuses specifically on the threefold tasks of assuring exam completeness (i.e., detecting the presence of blind spots) and assisting in the detection and characterization of clinical findings, both gastric precancerous conditions and neoplastic lesion changes. Early and promising results have already been obtained using well-known deep learning architectures for computer vision, but many algorithmic challenges remain in achieving the vision of AI-assisted UGIE. Future challenges in the roadmap for the effective integration of AI tools within the UGIE clinical practice are discussed, namely the adoption of more robust deep learning architectures and methods able to embed domain knowledge into image/video classifiers as well as the availability of large, annotated datasets.

Abstract
Cardiac auscultation is the key exam to screen cardiac diseases both in developed and developing countries. A heart sound auscultation procedure can detect the presence of murmurs and point to a diagnosis, thus it is an important first-line assessment and also cost-effective tool. The design automatic recommendation systems based on heart sound auscultation can play an important role in boosting the accuracy and the pervasiveness of screening tools. One such as step, consists in detecting the fundamental heart sound states, a process known as segmentation. A faulty segmentation or a wrong estimation of the heart rate might result in an incapability of heart sound classifiers to detect abnormal waves, such as murmurs. In the process of understanding the impact of a faulty segmentation, several common heart sound segmentation errors are studied in detail, namely those where the heart rate is badly estimated and those where S1/S2 and Systolic/Diastolic states are swapped in comparison with the ground truth state sequence. From the tested algorithms, support vector machine (SVMs) and random forest (RFs) shown to be more sensitive to a wrong estimation of the heart rate (an expected drop of 6% and 8% on the overall performance, respectively) than to a swap in the state sequence of events (an expected drop of 1.9% and 4.6%, respectively).