Automatic detection of pulmonary nodules in thoracic computed tomography (CT) scans has been an active area of research for the last two decades. However, there have only been few studies that provide a comparative performance evaluation of different systems on a common database. We have therefore set up the LUNA16 challenge, an objective evaluation framework for automatic nodule detection algorithms using the largest publicly available reference database of chest CT scans, the LIDC-IDRI data set. In LUNA16, participants develop their algorithm and upload their predictions on 888 CT scans in one of the two tracks: 1) the complete nodule detection track where a complete CAD system should be developed, or 2) the false positive reduction track where a provided set of nodule candidates should be classified. This paper describes the setup of LUNA16 and presents the results of the challenge so far. Moreover, the impact of combining individual systems on the detection performance was also investigated. It was observed that the leading solutions employed convolutional networks and used the provided set of nodule candidates. The combination of these solutions achieved an excellent sensitivity of over 95% at fewer than 1.0 false positives per scan. This highlights the potential of combining algorithms to improve the detection performance. Our observer study with four expert readers has shown that the best system detects nodules that were missed by expert readers who originally annotated the LIDC-IDRI data. We released this set of additional nodules for further development of CAD systems.
The grown interest in healthcare applications has made biomedical engineering one of the fastest growing disciplines in recent years. Photoplethysmography (PPG) has gained popularity in recent years due to its versatility for noninvasive monitoring of vital signs such as heart rate, respiratory rate, blood oxygen saturation and blood pressure. In this work, an adjustable PPG-based educational device called PPG EduKit, which aims to facilitate the learning of the PPG technology for a wide range of engineering and medical disciplines is proposed. Through the use of this educational platform, the PPG signal can be understood, modified and implemented along with the extraction of its relevant physiological information from a didactic, intuitive and practical way. The PPG Edukit is evaluated for the extraction of physiological parameters such as heart rate and blood oxygen level, demonstrating how its features contribute to engineering and medical students to assimilate technical concepts in electrical circuits, biomedical instrumentation, and human physiology.
Photoplethysmography (PPG) is widely used to assess cardiovascular health. Yet, its effectiveness is often hindered by external factors like contact force (CF), which significantly affects the accuracy and reliability of measurements. This study investigates how variations in the CF at the index fingertips influence six signal quality indices (SQIs)—including the perfusion index, skewness, kurtosis, entropy, zero-crossing rate, and relative power—using data from 11 healthy participants. Our analysis of normalized CF values reveals that lower CF ranges (0.2 to 0.4) may be optimal for extracting information about perfusion and blood flow. However, they may not be the best range to capture all the physiological details within the PPG pulse. In contrast, higher CF ranges (0.4 to 0.6) enable capturing more complex signals that could be physiologically representative. The findings underscore the necessity of considering viscoelastic tissue properties and individual biomechanical differences, advocating for both the normalization of CF for improved cross-subject comparison and personalized CF calibration to adapt PPG devices to diverse populations. These strategies ensure measurement reliability and consistency, thereby advancing the accuracy of cardiac and vascular assessments. Our study offers guidelines for adjusting the CF levels to balance signal detail and perfusion quality, customized to meet specific analytical requirements, with direct implications for both clinical and research environments.