On the Automation of Radiomics-Based Identification and Characterization of NSCLC.

Proper detection and accurate characterization of Non-Small Cell Lung Cancer (NSCLC) are an open challenge in the imaging field. Biomedical imaging is fundamental in lung cancer assessment and offers the possibility of calculating predictive biomarkers impacting patients' management. Within this context, radiomics, which consists of extracting quantitative features from digital images, shows encouraging results for clinical applications, but the sub-optimal standardization of the procedure and the lack of definitive results are still a concern in the field. For these reasons, this work proposes the design and development of LuCIFEx, a fully-automated pipeline for non-invasive in-vivo characterization of NSCLC, aiming to speed up the analysis process and enable an early diagnosis of the tumor.LuCIFEx pipeline relies on routinely acquired [18F]FDG-PET/CT images for the automatic segmentation of the cancer lesion, allowing the computation of accurate radiomic features, then employed for cancer characterization through Machine Learning algorithms. The proposed multi-stage segmentation process can identify the lesion with a mean accuracy of 94.2±5.0%. Finally, the proposed data analysis pipeline demonstrates the potential of PET/CT features for the automatic recognition of lung metastases and NSCLC histological subtypes, while highlighting the main current limitations of the radiomic approach.

Automated real-time atrial fibrillation detection on a wearable wireless sensor platform.

This paper presents an automated real-time atrial fibrillation (AF) detection approach that relies on the observation of two characteristic irregularities of AF episodes in the electrocardiogram (ECG) signal. The results generated after the analysis of these irregularities are subsequently analyzed in real-time using a new fuzzy classifier. We have optimized this novel AF classification framework to require very limited processing, memory storage and energy resources, which makes it able to operate in real-time on a wearable wireless sensor platform. Moreover, our experimental results indicate that the proposed on-line approach shows a similar accuracy to state-of-the-art off-line AF detectors, achieving up to 96% sensitivity and 93% specificity. Finally, we present a detailed energy study of each component of the target wearable wireless sensor platform, while executing the automated AF detection approach in a real operating scenario, in order to evaluate the lifetime of the overall system. This study indicates that the lifetime of the platform is increased by using the proposed method to detect AF in real-time and diagnose the patient with respect to a streaming application that sends the raw signal to a central coordinator (e.g., smartphone or laptop) for its ulterior processing.