Abstract
In this study, we used machine learning techniques to reconstruct the wavelength dependence of the absorption coefficient of human normal and pathological colorectal mucosa tissues. Using only diffuse reflectance spectra from the ex vivo mucosa tissues as input to algorithms, several approaches were tried before obtaining good matching between the generated absorption coefficients and the ones previously calculated for the mucosa tissues from invasive experimental spectral measurements. Considering the optimized match for the results generated with the multilayer perceptron regression method, we were able to identify differentiated accumulation of lipofuscin in the absorption coefficient spectra of both mucosa tissues as we have done before with the corresponding results calculated directly from invasive measurements. Considering the random forest regressor algorithm, the estimated absorption coefficient spectra almost matched the ones previously calculated. By subtracting the absorption of lipofuscin from these spectra, we obtained similar hemoglobin ratios at 410/550 nm: 18.9-fold/9.3-fold for the healthy mucosa and 46.6-fold/24.2-fold for the pathological mucosa, while from direct calculations, those ratios were 19.7-fold/10.1-fold for the healthy mucosa and 33.1-fold/17.3-fold for the pathological mucosa. The higher values obtained in this study indicate a higher blood content in the pathological samples used to measure the diffuse reflectance spectra. In light of such accuracy and sensibility to the presence of hidden absorbers, with a different accumulation between healthy and pathological tissues, good perspectives become available to develop minimally invasive spectroscopy methods for in vivo early detection and monitoring of colorectal cancer.

Abstract
The ability to select, isolate, and manipulate micron-sized particles or small clusters has made optical tweezers one of the emergent tools for modern biotechnology. In conventional setups, the classification of the trapped specimen is usually achieved through the acquired image, the scattered signal, or additional information such as Raman spectroscopy. In this work, we propose a solution that uses the temporal data signal from the scattering process of the trapping laser, acquired with a quadrant photodetector. Our methodology rests on a pre-processing strategy that combines Fourier transform and principal component analysis to reduce the dimension of the data and perform relevant feature extraction. Testing a wide range of standard machine learning algorithms, it is shown that this methodology allows achieving accuracy performances around 90%, validating the concept of using the temporal dynamics of the scattering signal for the classification task. Achieved with 500 millisecond signals and leveraging on methods of low computational footprint, the results presented pave the way for the deployment of alternative and faster classification methodologies in optical trapping technologies.

Abstract
Lung cancer is the deadliest type of cancer worldwide and late detection is the major factor for the low survival rate of patients. Low dose computed tomography has been suggested as a potential screening tool but manual screening is costly and time-consuming. This has fuelled the development of automatic methods for the detection, segmentation and characterisation of pulmonary nodules. In spite of promising results, the application of automatic methods to clinical routine is not straightforward and only a limited number of studies have addressed the problem in a holistic way. With the goal of advancing the state of the art, the Lung Nodule Database (LNDb) Challenge on automatic lung cancer patient management was organized. The LNDb Challenge addressed lung nodule detection, segmentation and characterization as well as prediction of patient follow-up according to the 2017 Fleischner society pulmonary nodule guidelines. 294 CT scans were thus collected retrospectively at the Centro Hospitalar e Universitrio de So Joo in Porto, Portugal and each CT was annotated by at least one radiologist. Annotations comprised nodule centroids, segmentations and subjective characterization. 58 CTs and the corresponding annotations were withheld as a separate test set. A total of 947 users registered for the challenge and 11 successful submissions for at least one of the sub-challenges were received. For patient follow-up prediction, a maximum quadratic weighted Cohen's kappa of 0.580 was obtained. In terms of nodule detection, a sensitivity below 0.4 (and 0.7) at 1 false positive per scan was obtained for nodules identified by at least one (and two) radiologist(s). For nodule segmentation, a maximum Jaccard score of 0.567 was obtained, surpassing the interobserver variability. In terms of nodule texture characterization, a maximum quadratic weighted Cohen's kappa of 0.733 was obtained, with part solid nodules being particularly challenging to classify correctly. Detailed analysis of the proposed methods and the differences in performance allow to identify the major challenges remaining and future directions data collection, augmentation/generation and evaluation of under-represented classes, the incorporation of scan-level information for better decision making and the development of tools and challenges with clinical-oriented goals. The LNDb Challenge and associated data remain publicly available so that future methods can be tested and benchmarked, promoting the development of new algorithms in lung cancer medical image analysis and patient followup recommendation.

Abstract
As technology and artificial intelligence conquer a place under the spotlight in the automotive world, driver drowsiness monitoring systems have sparked much interest as a way to increase safety and avoid sleepiness-related accidents. Such technologies, however, stumble upon the observation that each driver presents a distinct set of behavioral and physiological manifestations of drowsiness, thus rendering its objective assessment a non-trivial process. The AUTOMOTIVE project studied the application of signal processing and machine learning techniques for driver-specific drowsiness detection in smart vehicles, enabled by immersive driving simulators. More broadly, comprehensive research on biometrics using the electrocardiogram (ECG) and face enables the continuous learning of subject-specific models of drowsiness for more efficient monitoring. This paper aims to offer a holistic but comprehensive view of the research and development work conducted for the AUTOMOTIVE project across the various addressed topics and how it ultimately brings us closer to the target of improved driver drowsiness monitoring.

Abstract
In recent years, deep neural networks have shown significant progress in computer vision due to their large generalization capacity; however, the overfitting problem ubiquitously threatens the learning process of these highly nonlinear architectures. Dropout is a recent solution to mitigate overfitting that has witnessed significant success in various classification applications. Recently, many efforts have been made to improve the Standard dropout using an unsupervised merit-based semantic selection of neurons in the latent space. However, these studies do not consider the task-relevant information quality and quantity and the diversity of the latent kernels. To solve the challenge of dropping less informative neurons in deep learning, we propose an efficient end-to-end dropout algorithm that selects the most informative neurons with the highest correlation with the target output considering the sparsity in its selection procedure. First, to promote activation diversity, we devise an approach to select the most diverse set of neurons by making use of determinantal point process (DPP) sampling. Furthermore, to incorporate task specificity into deep latent features, a mutual information (MI)-based merit function is developed. Leveraging the proposed MI with DPP sampling, we introduce the novel DPPMI dropout that adaptively adjusts the retention rate of neurons based on their contribution to the neural network task. Empirical studies on real-world classification benchmarks including, MNIST, SVHN, CIFAR10, CIFAR100, demonstrate the superiority of our proposed method over recent state-of-the-art dropout algorithms in the literature.

Abstract
Objective: Patients with epilepsy, mainly drug-resistant, have reduced heart rate variability (HRV), linked to an increased risk of sudden death in various other diseases. In this context, it could play a role in SUDEP. Generalized convulsive seizures (GCS) are one of the most consensual risk factors for SUDEP. Our objective was to assess the influence of GCS in HRV parameters in patients with drug-resistant epilepsy. Methods: We prospectively evaluated 121 patients with refractory epilepsy admitted to our Epilepsy Monitoring Unit. All patients underwent a 48-hour Holter recording. Only patients with GCS were included (n = 23), and we selected the first as the index seizure. We evaluated HRV (AVNN, SDNN, RMSSD, pNN50, LF, HF, and LF/HF) in 5-min epochs (diurnal and nocturnal baselines; preictal - 5 min before the seizure; ictal; postictal - 5 min after the seizure; and late postictal - >5 h after the seizure). These data were also compared with normative values from a healthy population (controlling for age and gender). Results: We included 23 patients, with a median age of 36 (min-max, 16-55) years and 65% were female. Thirty percent had cardiovascular risk factors, but no previously known cardiac disease. HRV parameters AVNN, RMSSD, pNN50, and HF were significantly lower in the diurnal than in the nocturnal baseline, whereas the opposite occurred with LF/HF and HR. Diurnal baseline parameters were inferior to the normative population values (which includes only diurnal values). We found significant differences in HRV parameters between the analyzed periods, especially during the postictal period. All parameters but LF/HF suffered a reduction in that period. LF/HF increased in that period but did not reach statistical significance. Visually, there was a tendency for a global reduction in our patients' HRV parameters, namely AVNN, RMSSD, and pNN50, in each period, comparing with those from a normative healthy population. No significant differences were found in HRV between diurnal and nocturnal seizures, between temporal lobe and extra-temporal-lobe seizures, between seizures with and without postictal generalized EEG suppression, or between seizures of patients with and without cardiovascular risk factors. Significance/conclusion: Our work reinforces the evidence of autonomic cardiac dysfunction in patients with refractory epilepsy, at baseline and mainly in the postictal phase of a GCS. Those changes may have a role in some SUDEP cases. By identifying patients with worse autonomic cardiac function, HRV could fill the gap of a lacking SUDEP risk biomarker.