RisCO2: Implementation and Performance Evaluation of RISC-V Processors for Low-Power CO2 Concentration Sensing.

In the field of embedded systems, energy efficiency is a critical requirement, particularly for battery-powered devices. RISC-V processors have gained popularity due to their flexibility and open-source nature, making them an attractive choice for embedded applications. However, not all RISC-V processors are equally energy-efficient, and evaluating their performance in specific use cases is essential. This paper presents RisCO2, an RISC-V implementation optimized for energy efficiency. It evaluates its performance compared to other RISC-V processors in terms of resource utilization and energy consumption in a signal processing application for nondispersive infrared (NDIR) CO2 sensors.The processors were implemented in the PULPino SoC and synthesized using Vivado IDE. RisCO2 is based on the RV32E_Zfinx instruction set and was designed from scratch by the authors specifically for low-power signal demodulation in CO2 NDIR sensors. The other processors are Ri5cy, Micro-riscy, and Zero-riscy, developed by the PULP team, and CV32E40P (derived from Ri5cy) from the OpenHW Group, all of them widely used in the RISC-V community. Our experiments showed that RisCO2 had the lowest energy consumption among the five processors, with a 53.5% reduction in energy consumption compared to CV32E40P and a 94.8% reduction compared to Micro-riscy. Additionally, RisCO2 had the lowest FPGA resource utilization compared to the best-performing processors, CV32E40P and Ri5cy, with a 46.1% and a 59% reduction in LUTs, respectively. Our findings suggest that RisCO2 is a highly energy-efficient RISC-V processor for NDIR CO2 sensors that require signal demodulation to enhance the accuracy of the measurements. The results also highlight the importance of evaluating processors in specific use cases to identify the most energy-efficient option. This paper provides valuable insights for designers of energy-efficient embedded systems using RISC-V processors.

BronchoPose: an analysis of data and model configuration for vision-based bronchoscopy pose estimation.

BACKGROUND AND OBJECTIVE: Recent advances in neural networks and temporal image processing have provided new results and opportunities for vision-based bronchoscopy tracking. However, such progress has been hindered by the lack of comparative experimental data conditions. We address the issue by sharing a novel synthetic dataset, which allows for a fair comparison of methods. Moreover, as incorporating deep learning advances in temporal structures is not yet explored in bronchoscopy navigation, we investigate several neural network architectures for learning temporal information at different levels of subject personalization, providing new insights and results. METHODS: Using our own shared synthetic dataset for bronchoscopy navigation and tracking, we explore deep learning temporal information architectures (Recurrent Neural Networks and 3D convolutions), which have not been fully explored on bronchoscopy tracking, putting a special focus on network efficiency by using a modern backbone (EfficientNet-B0) and ShuffleNet blocks. Finally, we provide a study of different losses for rotation tracking and population modeling schemes (personalized vs. population) for bronchoscopy tracking. RESULTS: Temporal information architectures provide performance improvements, both in position and angle estimation. Additionally, population scheme analysis illustrates the benefits of offering a personalized model, while loss analysis indicates the benefits of using an adequate metric, improving results. We finally compare with a state-of-the-art model obtaining better results both in performance, with  12.2% and  18.7% improvement for position and rotation respectively, and around  67.6% reduction in memory consumption. CONCLUSIONS: Proposed advances in temporal information architectures, loss configuration, and population scheme definition allow for improving the current state of the art in bronchoscopy analysis. Moreover, the publication of the first synthetic dataset allows for further improving bronchoscopy research by enabling proper comparison grounds among methods.

Gait Analysis Platform for Measuring Surgery Recovery.

Gait analysis has evolved significantly during last years due to the great development of the Medical Internet of Things (MIoT) platforms that allow an easy integration of sensors (inertial, magnetic and pressure in our case) to the complex analytics required to compute, not only relevant parameters, but also meaningful indexes. In this paper, we extend a previous development based on a fully wireless pair of insoles by implementing an updated version with more reliable and user-friendly devices, smartphone app and web front-end and back-end. We also extend previous work focused on fall analysis (with the corresponding fall risk index or FRI) with the proposal of a new surgery recovery index (SRI) to account for the individual speed recovery speed that can be measured either at clinical facilities or at home in a telemedicine environment or while doing daily life activities. This new index can be personalized for different types of surgeries that affect gait such as hip, knee, etc. This paper presents the case of hip recovery and is built on top of the clinical standard SPPB test and allows obtaining quantitative parameters directly from the sensors.

Tumour Versus Germline BRCA Testing in Ovarian Cancer: A Single-Site Institution Experience in the United Kingdom.

The aim of this audit was to evaluate the usefulness and serviceability of testing for pathogenic mutations in BRCA1 or BRCA2 (BRCA1/2) genes in ovarian cancer (OC) patients. One hundred and thirty-five patients with more common histological sub-types of OC were retrospectively identified between 2011 and 2019. The fail rate of the molecular analysis was 7.4% (10/135). One hundred and twenty-five records were evaluated: 99 (79.2%) patients had wild-type BRCA (both somatic and germline); tumour BRCA1/2 (tBRCA1/2) pathogenic mutations were found in 20 (16%) patients with distribution between BRCA1 and BRCA2 being 40% and 60%, respectively; 13 (10.4%) patients with pathogenic variants had germline mutations; and tBRCA1/2 with variant of unknown significance (VUS), in the absence of pathogenic BRCA1 or BRCA2 variants, was detected in 6 (4.8%) patients. Our data show that expanding the molecular service to the routine first-tumour testing for patients with OC will potentially increase the detection rate of BRCA mutations, thereby providing early benefits of PARP inhibitors therapy. The tumour testing service should continue to be offered to newly diagnosed patients with high-grade epithelial cancers, including high-grade serous carcinoma, but also with carcinosarcomas and poorly-differentiated metastatic adenocarcinomas of unknown origin.