Breathing Motion Pattern in Cyclists: Role of Inferior against Superior Thorax Compartment.

The thoracoabdominal breathing motion pattern is being considered in sports training because of its contribution, along with other physiological adaptations, to overall performance. We examined whether and how experience with cycling training modifies the thoracoabdominal motion patterns. We utilized optoelectronic plethysmography to monitor ten trained male cyclists and compared them to ten physically active male participants performing breathing maneuvers. Cyclists then participated in a self-paced time trial to explore the similarity between that observed during resting breathing. From the 3D coordinates of 32 markers positioned on each participant's trunk, we calculated the percentage of contribution of the superior thorax, inferior thorax, and abdomen and the correlation coefficient among these compartments. During the rest maneuvers, the cyclists showed a thoracoabdominal motion pattern characterized by an increased role of the inferior thorax relative to the superior thorax (26.69±5.88%, 34.93±5.03%; p=0.002, respectively), in contrast to the control group (26.69±5.88%; 25.71±6.04%, p=0.4, respectively). In addition, the inferior thorax showed higher coordination in phase with the abdomen. Furthermore, the results of the time trial test underscored the same pattern found in cyclists breathing at rest, suggesting that the development of a permanent modification in respiratory mechanics may be associated with cycling practice.

Validation of Step Detection and Distance Calculation Algorithms for Soccer Performance Monitoring.

This study focused on developing and evaluating a gyroscope-based step counter algorithm using inertial measurement unit (IMU) readings for precise athletic performance monitoring in soccer. The research aimed to provide reliable step detection and distance estimation tailored to soccer-specific movements, including various running speeds and directional changes. Real-time algorithms utilizing shank angular data from gyroscopes were created. Experiments were conducted on a specially designed soccer-specific testing circuit performed by 15 athletes, simulating a range of locomotion activities such as walking, jogging, and high-intensity actions. The algorithm outcome was compared with manually tagged data from a high-quality video camera-based system for validation, by assessing the agreement between the paired values using limits of agreement, concordance correlation coefficient, and further metrics. Results returned a step detection accuracy of 95.8% and a distance estimation Root Mean Square Error (RMSE) of 17.6 m over about 202 m of track. A sub-sample (N = 6) also wore two pairs of devices concurrently to evaluate inter-unit reliability. The performance analysis suggested that the algorithm was effective and reliable in tracking diverse soccer-specific movements. The proposed algorithm offered a robust and efficient solution for tracking step count and distance covered in soccer, particularly beneficial in indoor environments where global navigation satellite systems are not feasible. This advancement in sports technology widens the spectrum of tools for coaches and athletes in monitoring soccer performance.

Identification of Characteristic Points in Multivariate Physiological Signals by Sensor Fusion and Multi-Task Deep Networks.

Identification of characteristic points in physiological signals, such as the peak of the R wave in the electrocardiogram and the peak of the systolic wave of the photopletismogram, is a fundamental step for the quantification of clinical parameters, such as the pulse transit time. In this work, we presented a novel neural architecture, called eMTUnet, to automate point identification in multivariate signals acquired with a chest-worn device. The eMTUnet consists of a single deep network capable of performing three tasks simultaneously: (i) localization in time of characteristic points (labeling task), (ii) evaluation of the quality of signals (classification task); (iii) estimation of the reliability of classification (reliability task). Preliminary results in overnight monitoring showcased the ability to detect characteristic points in the four signals with a recall index of about 1.00, 0.90, 0.90, and 0.80, respectively. The accuracy of the signal quality classification was about 0.90, on average over four different classes. The average confidence of the correctly classified signals, against the misclassifications, was 0.93 vs. 0.52, proving the worthiness of the confidence index, which may better qualify the point identification. From the achieved outcomes, we point out that high-quality segmentation and classification are both ensured, which brings the use of a multi-modal framework, composed of wearable sensors and artificial intelligence, incrementally closer to clinical translation.

Are Action Sport Cameras Accurate Enough for 3D Motion Analysis? A Comparison With a Commercial Motion Capture System.

The aim of this study was to assess the precision and accuracy of an Action Sport Camera (ASC) system (4 GoPro Hero3+ Black) by comparison with a commercial motion capture (MOCAP) system (4 ViconMX40). Both systems were calibrated using the MOCAP protocol and the 3D markers coordinates of a T-shaped tool were reconstructed, concurrently. The 3D precision was evaluated by the differences in the reconstructed position using a Bland-Altman test, while accuracy was assessed by a rigid bar test (Wilcoxon rank sum). To examine the accuracy of the ASC in respect to the knee flexion angles, a jump and gait task were also examined using one subject (Wilcoxon rank sum). The ASC system provided a maximum error of 2.47 mm, about 10 times higher than the MOCAP (0.21 mm). The reconstructed knee flexion angles were highly correlated (r2>0.99) and showed no significant differences between systems (<2.5°; p>0.05). As expected, the MOCAP obtained better 3D precision and accuracy. However, we show such differences have little practical effect on reconstructed 3D kinematics.

Navigated "small implants" in knee reconstruction.

PURPOSE: At the beginning of this century, unprecedented interest in the concept of using less invasive approaches for the treatment of knee degenerative diseases was ignited. Initial interest in this approach was about navigated and non-navigated knee reconstruction using small implants and conventional total knee arthroplasty. METHODS: To this end, a review of the published literature relating to less invasive compartmental arthroplasty of the knee using computer-based alignment techniques and on soft tissue-dedicated small implants is presented. The authors present and compare their personal results using these techniques with those reported in the current literature. These involved the use of a shorter incision and an emphasis sparing. However, nowadays most surgeons look at compartmental knee resurfacing with the use of small implants as the new customized approach for younger and higher-demand patients. The aim of this paper is to stimulate further debate. RESULTS: Since the beginning of 2000, computer-assisted surgery has been applied to total knee arthroplasty (TKA) and later to compartmental knee arthroplasty. Recent studies in the literature have reported better implant survivorship for younger patients using navigation in TKA at longer-term follow-up. Only one published report was identified showing superior clinical outcomes at short-term follow-up using computer-assisted technology compared with conventional alignment techniques in small implant surgery. No studies were found in the literature that demonstrated similar clinical advantages with navigated small implants at long-term follow-up. Two published meta-analyses were identified reporting better implant and limb alignment and no increase in complications using a navigated unicompartmental knee arthroplasty. However, neither meta-analysis showed superior clinical outcomes or survivorship with the navigated techniques. CONCLUSION: In conclusion, we can assert that replacing just the damaged compartment and preserving the normal biomechanics will require not only new implant designs but also new technologies allowing the surgeon to make extremely precise adjustments to implant alignment and providing continuous feedback during surgery. LEVEL OF EVIDENCE: IV.

Computer-assisted unicompartmental knee arthroplasty using dedicated software versus a conventional technique.

PURPOSE: The aim of this study was to retrospectively compare the results of two matched-paired groups of patients who had undergone a medial unicompartmental knee arthroplasty (UKA) performed using either a conventional or a non-image-guided navigation technique specifically designed for unicompartmental prosthesis implantation. METHODS: Thirty-one patients with isolated medial-compartment knee arthritis who underwent an isolated navigated UKA were included in the study (group A) and matched with patients who had undergone a conventional medial UKA (group B). The same inclusion criteria were used for both groups. At a minimum of six months, all patients were clinically assessed using the Knee Society Score (KSS) and the Western Ontario and McMaster Osteoarthritis Index (WOMAC) index. Radiographically, the frontal-femoral-component angle, the frontal-tibial-component angle, the hip-knee-ankle angle and the sagittal orientation of components (slopes) were evaluated. Complications related to the implantation technique, length of hospital stay and surgical time were compared. RESULTS: At the latest follow-up, no statistically significant differences were seen in the KSS, function scores and WOMAC index between groups. Patients in group B had a statistically significant shorter mean surgical time. Tibial coronal and sagittal alignments were statistically better in the navigated group, with five cases of outliers in the conventional alignment technique group. Postoperative mechanical axis was statistically better aligned in the navigated group, with two cases of overcorrection from varus to valgus in group B. No differences in length of hospital stay or complications related to implantation technique were seen between groups. CONCLUSION: This study shows that a specifically designed UKA-dedicated navigation system results in better implant alignment in UKA surgery. Whether this improved alignment results in better clinical results in the long term has yet to be proven.

Main challenges on the curation of large scale datasets for pancreas segmentation using deep learning in multi-phase CT scans: Focus on cardinality, manual refinement, and annotation quality.

Accurate segmentation of the pancreas in computed tomography (CT) holds paramount importance in diagnostics, surgical planning, and interventions. Recent studies have proposed supervised deep-learning models for segmentation, but their efficacy relies on the quality and quantity of the training data. Most of such works employed small-scale public datasets, without proving the efficacy of generalization to external datasets. This study explored the optimization of pancreas segmentation accuracy by pinpointing the ideal dataset size, understanding resource implications, examining manual refinement impact, and assessing the influence of anatomical subregions. We present the AIMS-1300 dataset encompassing 1,300 CT scans. Its manual annotation by medical experts required 938 h. A 2.5D UNet was implemented to assess the impact of training sample size on segmentation accuracy by partitioning the original AIMS-1300 dataset into 11 smaller subsets of progressively increasing numerosity. The findings revealed that training sets exceeding 440 CTs did not lead to better segmentation performance. In contrast, nnU-Net and UNet with Attention Gate reached a plateau for 585 CTs. Tests on generalization on the publicly available AMOS-CT dataset confirmed this outcome. As the size of the partition of the AIMS-1300 training set increases, the number of error slices decreases, reaching a minimum with 730 and 440 CTs, for AIMS-1300 and AMOS-CT datasets, respectively. Segmentation metrics on the AIMS-1300 and AMOS-CT datasets improved more on the head than the body and tail of the pancreas as the dataset size increased. By carefully considering the task and the characteristics of the available data, researchers can develop deep learning models without sacrificing performance even with limited data. This could accelerate developing and deploying artificial intelligence tools for pancreas surgery and other surgical data science applications.

Feasibility of proton dosimetry overriding planning CT with daily CBCT elaborated through generative artificial intelligence tools.

Radiotherapy commonly utilizes cone beam computed tomography (CBCT) for patient positioning and treatment monitoring. CBCT is deemed to be secure for patients, making it suitable for the delivery of fractional doses. However, limitations such as a narrow field of view, beam hardening, scattered radiation artifacts, and variability in pixel intensity hinder the direct use of raw CBCT for dose recalculation during treatment. To address this issue, reliable correction techniques are necessary to remove artifacts and remap pixel intensity into Hounsfield Units (HU) values. This study proposes a deep-learning framework for calibrating CBCT images acquired with narrow field of view (FOV) systems and demonstrates its potential use in proton treatment planning updates. Cycle-consistent generative adversarial networks (cGAN) processes raw CBCT to reduce scatter and remap HU. Monte Carlo simulation is used to generate CBCT scans, enabling the possibility to focus solely on the algorithm's ability to reduce artifacts and cupping effects without considering intra-patient longitudinal variability and producing a fair comparison between planning CT (pCT) and calibrated CBCT dosimetry. To showcase the viability of the approach using real-world data, experiments were also conducted using real CBCT. Tests were performed on a publicly available dataset of 40 patients who received ablative radiation therapy for pancreatic cancer. The simulated CBCT calibration led to a difference in proton dosimetry of less than 2%, compared to the planning CT. The potential toxicity effect on the organs at risk decreased from about 50% (uncalibrated) up the 2% (calibrated). The gamma pass rate at 3%/2 mm produced an improvement of about 37% in replicating the prescribed dose before and after calibration (53.78% vs 90.26%). Real data also confirmed this with slightly inferior performances for the same criteria (65.36% vs 87.20%). These results may confirm that generative artificial intelligence brings the use of narrow FOV CBCT scans incrementally closer to clinical translation in proton therapy planning updates.

Simultaneous in-air and underwater 3D kinematic analysis of swimmers: Feasibility and reliability of action sport cameras.

This study explored the potential of reconstructing the 3D motion of a swimmer's hands with accuracy and consistency using action sport cameras (ASC) distributed in-air and underwater. To record at least two stroke cycles of an athlete performing a front crawl task, the cameras were properly calibrated to cover an acquisition volume of 3 m in X, 8 m in Y, and 3.5 m in Z axis, approximately. Camera calibration was attained by applying bundle adjustment in both environments. A testing wand, carrying two markers, was acquired to evaluate the three-dimensional (3D) reconstruction accuracy in-air, underwater, and over the water transition. The global 3D accuracy (mean absolute error) was less than 1.5 mm. The standard error of measurement and the coefficient of variation were smaller than 1 mm and 1%, respectively, revealing that the camera calibration procedure was highly repeatable. No significant correlation between the error magnitude (percentage error during the test and the retest sessions: 1.2 to 0.8%) and the transition from in-air to underwater was observed. The feasibility of the hand motion reconstruction was demonstrated by recording five swimmers during the front crawl stroke, in three different tasks performed at increasing efforts. Intra-class correlation confirmed the optimal agreement (ICC>0.90) among repeated stroke cycles of the same swimmer, irrespective of task effort. Skewness, close to 0, and kurtosis, close to 3.5, supported the hypothesis of negligible effects of the calibration and tracking errors on the motion and speed patterns. In conclusion, we may argue that ASCs, equipped with a robust bundle adjustment camera calibration technique, ensure reliable reconstruction of swimming motion in in-air and underwater large volumes.

Mixed Reality and Artificial Intelligence: A Holistic Approach to Multimodal Visualization and Extended Interaction in Knee Osteotomy.

OBJECTIVE: Recent advancements in augmented reality led to planning and navigation systems for orthopedic surgery. However little is known about mixed reality (MR) in orthopedics. Furthermore, artificial intelligence (AI) has the potential to boost the capabilities of MR by enabling automation and personalization. The purpose of this work is to assess Holoknee prototype, based on AI and MR for multimodal data visualization and surgical planning in knee osteotomy, developed to run on the HoloLens 2 headset. METHODS: Two preclinical test sessions were performed with 11 participants (eight surgeons, two residents, and one medical student) executing three times six tasks, corresponding to a number of holographic data interactions and preoperative planning steps. At the end of each session, participants answered a questionnaire on user perception and usability. RESULTS: During the second trial, the participants were faster in all tasks than in the first one, while in the third one, the time of execution decreased only for two tasks ("Patient selection" and "Scrolling through radiograph") with respect to the second attempt, but without statistically significant difference (respectively [Formula: see text] = 0.14 and [Formula: see text] = 0.13, [Formula: see text]). All subjects strongly agreed that MR can be used effectively for surgical training, whereas 10 (90.9%) strongly agreed that it can be used effectively for preoperative planning. Six (54.5%) agreed and two of them (18.2%) strongly agreed that it can be used effectively for intraoperative guidance. DISCUSSION/CONCLUSION: In this work, we presented Holoknee, the first holistic application of AI and MR for surgical planning for knee osteotomy. It reported promising results on its potential translation to surgical training, preoperative planning, and surgical guidance. Clinical and Translational Impact Statement - Holoknee can be helpful to support surgeons in the preoperative planning of knee osteotomy. It has the potential to impact positively the training of the future generation of residents and aid surgeons in the intraoperative stage.

Spontaneous patella fracture associated with anterior tibial tubercle pseudarthrosis in a revised knee replacement following knee arthrodesis.

BACKGROUND: Conversion of a knee arthrodesis to a Total Knee Arthroplasty is an uncommon procedure. Revision Total Knee Arthroplasty in this setting presents the surgeon with a number of challenges including the management of the extensor mechanism and patella. CASE PRESENTATION: We describe a unique case of a 69 years old Caucasian man who underwent a revision Total Knee Arthroplasty using a tibial tubercle osteotomy after a previous conversion of a knee arthrodesis without patella resurfacing. Unfortunately 9 months following surgery a tibial tubercle pseudarthrosis and spontaneous patella fracture occurred. Both were managed with open reduction and internal fixation. At 30 months follow-up the tibial tubercle osteotomy had completely consolidated while the patella fracture was still evident but with no signs of further displacement. The patient was completely satisfied with the outcome and had a painless range of knee flexion between 0-95°. CONCLUSIONS: We believe that patients undergoing this type of surgery require careful counseling regarding the risk of complications both during and after surgery despite strong evidence supporting improved functional outcomes.

An uncommon cause of cemented unicompartmental knee arthroplasty failure: fracture of metallic components.

PURPOSE: Despite good overall clinical results, unicompartmental knee replacements (UKR) are not without their problems and failures have been reported. The most common causes of UKR failure are component loosening, poor patient selection, poor surgical technique, polyethylene wear and progression of arthritis in other compartments. The purpose of this study is to present a series of atraumatic fractures of metallic components in a UKR treated in a single orthopaedic centre. METHOD: Since 1999, 121 failed unicompartmental knee arthroplasties have been referred to our centre. In six of these, atraumatic breakage of a metal component in the cemented UKR was seen and included in this study. Pre-operative alignment, BMI and implant longevity were documented. The femoral implant failed in 4 patients and the tibial implant in a further 2. RESULTS: All the femoral implant fractures occurred within 3 years of UKR surgery (mean: 22.2 months, SD: 10.6 months). Tibial implant breakage occurred at a mean of 8.5 years (SD: 2.4 months) following UKR. All patients were treated with conversion to a navigated total knee replacement. A primary total knee arthroplasty was used in all cases with one patient requiring a tibial component incorporating a wedge and stem following breakage of the original UKR tibial implant. CONCLUSION: Fracture of the metallic components is a potential cause of failure of unicompartmental knee arthroplasty. In our experience, the incidence of this complication was 4.9 % of all UKR failures. Patients with a BMI greater than 30 and a progressive deterioration in limb alignment were at greater risk.

A new system for in-room image guidance in particle therapy at CNAO.

This paper describes the design, installation, and commissioning of an in-room imaging device developed at the Centro Nazionale di Adroterapia Oncologica (CNAO, Pavia, Italy). The system is an upgraded version of the one previously installed in 2014, and its design accounted for the experience gained in a decade of clinical practice of patient setup verification and correction through robotic-supported, off-isocenter in-room image guidance. The system's basic feature consists of image-based setup correction through 2D/3D and 3D/3D registration through a dedicated HW/SW platform. The major update with respect to the device already under clinical usage resides in the implementation of a functionality for extending the field of view of the reconstructed Cone Beam CT (CBCT) volume, along with improved overall safety and functional optimization. We report here details on the procedures implemented for system calibration under all imaging modalities and the results of the technical and preclinical commissioning of the device performed on two different phantoms. In the technical commissioning, specific attention was given to the assessment of the accuracy with which the six-degrees-of-freedom correction vector computed at the off-isocenter imaging position was propagated to the planned isocentric irradiation geometry. During the preclinical commissioning, the entire clinical-like procedure for detecting and correcting imposed, known setup deviation was tested on an anthropomorphic radioequivalent phantom. Results showed system performance within the sub-millimeter and sub-degree range according to project specifications under each imaging modality, making it ready for clinical application.

Combined Edge Loss UNet for Optimized Segmentation in Total Knee Arthroplasty Preoperative Planning.

Bone segmentation and 3D reconstruction are crucial for total knee arthroplasty (TKA) surgical planning with Personalized Surgical Instruments (PSIs). Traditional semi-automatic approaches are time-consuming and operator-dependent, although they provide reliable outcomes. Moreover, the recent expansion of artificial intelligence (AI) tools towards various medical domains is transforming modern healthcare. Accordingly, this study introduces an automated AI-based pipeline to replace the current operator-based tibia and femur 3D reconstruction procedure enhancing TKA preoperative planning. Leveraging an 822 CT image dataset, a novel patch-based method and an improved segmentation label generation algorithm were coupled to a Combined Edge Loss UNet (CEL-UNet), a novel CNN architecture featuring an additional decoding branch to boost the bone boundary segmentation. Root Mean Squared Errors and Hausdorff distances compared the predicted surfaces to the reference bones showing median and interquartile values of 0.26 (0.19-0.36) mm and 0.24 (0.18-0.32) mm, and of 1.06 (0.73-2.15) mm and 1.43 (0.82-2.86) mm for the tibia and femur, respectively, outperforming previous results of our group, state-of-the-art, and UNet models. A feasibility analysis for a PSI-based surgical plan revealed sub-millimetric distance errors and sub-angular alignment uncertainties in the PSI contact areas and the two cutting planes. Finally, operational environment testing underscored the pipeline's efficiency. More than half of the processed cases complied with the PSI prototyping requirements, reducing the overall time from 35 min to 13.1 s, while the remaining ones underwent a manual refinement step to achieve such PSI requirements, performing the procedure four to eleven times faster than the manufacturer standards. To conclude, this research advocates the need for real-world applicability and optimization of AI solutions in orthopedic surgical practice.

SLEEP-SEE-THROUGH: Explainable Deep Learning for Sleep Event Detection and Quantification From Wearable Somnography.

Evidence is rapidly accumulating that multifactorial nocturnal monitoring, through the coupling of wearable devices and deep learning, may be disruptive for early diagnosis and assessment of sleep disorders. In this work, optical, differential air-pressure and acceleration signals, acquired by a chest-worn sensor, are elaborated into five somnographic-like signals, which are then used to feed a deep network. This addresses a three-fold classification problem to predict the overall signal quality (normal, corrupted), three breathing-related patterns (normal, apnea, irregular) and three sleep-related patterns (normal, snoring, noise). In order to promote explainability, the developed architecture generates additional information in the form of qualitative (saliency maps) and quantitative (confidence indices) data, which helps to improve the interpretation of the predictions. Twenty healthy subjects enrolled in this study were monitored overnight for approximately ten hours during sleep. Somnographic-like signals were manually labeled according to the three class sets to build the training dataset. Both record- and subject-wise analyses were performed to evaluate the prediction performance and the coherence of the results. The network was accurate (0.96) in distinguishing normal from corrupted signals. Breathing patterns were predicted with higher accuracy (0.93) than sleep patterns (0.76). The prediction of irregular breathing was less accurate (0.88) than that of apnea (0.97). In the sleep pattern set, the distinction between snoring (0.73) and noise events (0.61) was less effective. The confidence index associated with the prediction allowed us to elucidate ambiguous predictions better. The saliency map analysis provided useful insights to relate predictions to the input signal content. While preliminary, this work supported the recent perspective on the use of deep learning to detect particular sleep events in multiple somnographic signals, thus representing a step towards bringing the use of AI-based tools for sleep disorder detection incrementally closer to clinical translation.

A 3D kinematic analysis of breathing patterns in competitive swimmers.

The purpose of this paper was to understand which differences long-term swimming training can cause on trunk mechanics during breathing and how these differences are related to the years of swimming training. The variations and coordination among trunk compartments were considered as target movement patterns. Video-based plethysmography was utilised for data acquisition and pre-processing. A group of swimmers, who followed a long-term intensive swimming training previously to this study, was compared with a non-swimmer control group. The participants of both groups performed quiet breathing and vital capacity tests. From the compartmental volumes associated with each breathing curves, the relative amplitude and cross-correlation among these volumetric time-varying signals were calculated, in order to analyse the relative partial volume variation and the coordination among trunk compartments involved in respiration. The results of a Mixed-ANOVA test (P ≤ 0.05) revealed higher coefficient of variation (P < 0.001) and correlations among trunk compartments in the swimmers group when vital capacity was performed. Significant linear regression was found between the years of swim training and the coefficients of variation and correlation. The results suggest that after long periods of intensive swim training, athletes might develop specific breathing patterns featuring higher volume variations in the abdominal region and more coordination among compartments involved in forced respiratory tasks such as vital capacity.

Is computer-assisted total knee replacement for beginners or experts? Prospective study among three groups of patients treated by surgeons with different levels of experience.

BACKGROUND: Computer-assisted total knee replacement (TKR) has been shown to improve radiographic alignment and therefore the clinical outcome. Outliers with greater than 3° of varus or valgus malalignment in TKR can suffer higher failure rates. The aim of this study was to determine the impact of experience with both computer navigation and knee replacement surgery on the frequency of errors in intraoperative bone cuts and implant alignment, as well as the actual learning curve. MATERIALS AND METHODS: Three homogeneous groups who underwent computer-assisted TKR were included in the study: group A [surgery performed by a surgeon experienced in both TKR and computer-assisted surgery (CAS)], B [surgery performed by a surgeon experienced in TKR but not CAS], and C [surgery performed by a general orthopedic surgeon]. In other words, all of the surgeons had different levels of experience in TKR and CAS, and each group was treated by only one of the surgeons. Cutting errors, number of re-cuts, complications, and mean surgical times were recorded. Frontal femoral component angle, frontal tibial component angle, hip-knee-ankle angle, and component slopes were evaluated. RESULTS: The number of cutting errors varied significantly: the lowest number was recorded for TKR performed by the surgeon with experience in CAS. Superior results were achieved in relation to final mechanical axis alignment by the surgeon experienced in CAS compared to the other surgeons. However, the total number of outliers showed no statistically significant difference among the three surgeons. After 11 cases, there were no differences in the number of re-cuts between groups A and C, and after 9 cases there were no differences in surgical time between groups A and B. CONCLUSION: A beginner can reproduce the results of an expert TKR surgeon by means of navigation (i.e., CAS) after a learning curve of 16 cases; this represents the break-even point after which no statistically significant difference is observed between the expert surgeon and the beginner utilizing CAS.

Analytical Challenges in Diabetes Management: Towards Glycated Albumin Point-of-Care Detection.

Diabetes mellitus is a worldwide-spread chronic metabolic disease that occurs when the pancreas fails to produce enough insulin levels or when the body fails to effectively use the secreted pancreatic insulin, eventually resulting in hyperglycemia. Systematic glycemic control is the only procedure at our disposal to prevent diabetes long-term complications such as cardiovascular disorders, kidney diseases, nephropathy, neuropathy, and retinopathy. Glycated albumin (GA) has recently gained more and more attention as a control biomarker thanks to its shorter lifespan and wider reliability compared to glycated hemoglobin (HbA1c), currently the "gold standard" for diabetes screening and monitoring in clinics. Various techniques such as ion exchange, liquid or affinity-based chromatography and immunoassay can be employed to accurately measure GA levels in serum samples; nevertheless, due to the cost of the lab equipment and complexity of the procedures, these methods are not commonly available at clinical sites and are not suitable to home monitoring. The present review describes the most up-to-date advances in the field of glycemic control biomarkers, exploring in particular the GA with a special focus on the recent experimental analysis techniques, using enzymatic and affinity methods. Finally, analysis steps and fundamental reading technologies are integrated into a processing pipeline, paving the way for future point-of-care testing (POCT). In this view, we highlight how this setup might be employed outside a laboratory environment to reduce the time from measurement to clinical decision, and to provide diabetic patients with a brand-new set of tools for glycemic self-monitoring.

Hybrid Convolutional Networks for End-to-End Event Detection in Concurrent PPG and PCG Signals Affected by Motion Artifacts.

The accurate detection of physiologically-related events in photopletismographic (PPG) and phonocardiographic (PCG) signals, recorded by wearable sensors, is mandatory to perform the estimation of relevant cardiovascular parameters like the heart rate and the blood pressure. However, the measurement performed in uncontrolled conditions without clinical supervision leaves the detection quality particularly susceptible to noise and motion artifacts. This work proposes a new fully-automatic computational framework, based on convolutional networks, to identify and localize fiducial points in time as the foot, maximum slope and peak in PPG signal and the S1 sound in the PCG signal, both acquired by a custom chest sensor, described recently in the literature by our group. The event detection problem was reframed as a single hybrid regression-classification problem entailing a custom neural architecture to process sequentially the PPG and PCG signals. Tests were performed analysing four different acquisition conditions (rest, cycling, rest recovery and walking). Cross-validation results for the three PPG fiducial points showed identification accuracy greater than 93 % and localization error (RMSE) less than 10 ms. As expected, cycling and walking conditions provided worse results than rest and recovery, however reaching an accuracy greater than 90 % and a localization error less than 15 ms. Likewise, the identification and localization error for S1 sound were greater than 90 % and less than 25 ms. Overall, this study showcased the ability of the proposed technique to detect events with high accuracy not only for steady acquisitions but also during subject movements. We also showed that the proposed network outperformed traditional Shannon-energy-envelope method in the detection of S1 sound, reaching detection performance comparable to state of the art algorithms. Therefore, we argue that coupling chest sensors and deep learning processing techniques may disclose wearable devices to unobtrusively acquire health information, being less affected by noise and motion artifacts.

CEL-Unet: a novel CNN architecture for 3D Segmentation of Knee Bones affected by Severe Osteoarthritis for PSI-Based Surgical Planning.

Unet architectures are promising deep learning networks exploited to perform the automatic segmentation of bone CT images, in line with their ability to deal with pathological deformations and size-varying anatomies. However, bone degeneration, like the development of irregular osteophytes as well as mineral density alterations might interfere with this automated process and demand extensive manual refinement. The aim of this work is to implement an innovative Unet variant, the CEL-Unet, to improve the femur and tibia segmentation outcomes in osteoarthritic knee joints. In this network the decoding path is split into a region and contour-aware branch to increase the prediction reliability in such pathological conditions. The comparison between the segmentation results achieved with a standard Unet and its novel variant (CEL-Unet) was performed as follows: the Unet was trained with 5 different loss functions: Dice Loss, Focal Loss, Exponential Logarithmic Loss, Double Cross Entropy Loss and Distanced Cross Entropy loss. The CEL-Unet was instead trained with two loss functions, one for each of the network outputs, namely Mask and Edge, yielding the so-called Combined Edge Loss (CEL) function. A set of 259 knee CT scans was used to train the model and test segmentation performance. The CEL-Unet outperformed all other Unet-based models, reaching the highest Jaccard values of about 0.97 and 0.96 on femur and tibia, respectively. Clinical Relevance- With the increasing rate of Total Knee Arthoplasty deep learning-based methods can achieve fast accurate and automatic 3D segmentation of the knee joint bones to enhance new costumized pre-operative planning.