Assessing the Impact of Defacing Algorithms on Brain Volumetry Accuracy in MRI Analyses.

Background and Purpose: To ensure data privacy, the development of defacing processes, which anonymize brain images by obscuring facial features, is crucial. However, the impact of these defacing methods on brain imaging analysis poses significant concern. This study aimed to evaluate the reliability of three different defacing methods in automated brain volumetry. Methods: Magnetic resonance imaging with three-dimensional T1 sequences was performed on ten patients diagnosed with subjective cognitive decline. Defacing was executed using mri_deface, BioImage Suite Web-based defacing, and Defacer. Brain volumes were measured employing the QBraVo program and FreeSurfer, assessing intraclass correlation coefficient (ICC) and the mean differences in brain volume measurements between the original and defaced images. Results: The mean age of the patients was 71.10±6.17 years, with 4 (40.0%) being male. The total intracranial volume, total brain volume, and ventricle volume exhibited high ICCs across the three defacing methods and 2 volumetry analyses. All regional brain volumes showed high ICCs with all three defacing methods. Despite variations among some brain regions, no significant mean differences in regional brain volume were observed between the original and defaced images across all regions. Conclusions: The three defacing algorithms evaluated did not significantly affect the results of image analysis for the entire brain or specific cerebral regions. These findings suggest that these algorithms can serve as robust methods for defacing in neuroimaging analysis, thereby supporting data anonymization without compromising the integrity of brain volume measurements.

Increased intraindividual variability (IIV) in reaction time is the earliest indicator of cognitive change in MS: A two-year observational study.

Background: Cognitive decline in multiple sclerosis (MS) is common, but unpredictable, and increases with disease duration. As such, early detection of cognitive decline may improve the effectiveness of interventions. To that end, the Symbol Digit Modalities Test (SDMT) is effective in detecting slow processing speed as it relates to cognitive impairment, and intraindividual variability (IIV) observed in trials assessing continuous reaction time (RT) may be a useful indicator of early cognitive changes. Here, we will assess cognitive IIV changes in adults with early MS. Methods: Adults with relapsing-remitting MS (RRMS), <11 years since diagnosis, were recruited nationally. Baseline and two-year follow-up assessments included Brief International Cognitive Assessment in MS (BICAMS) and Cogstate computerized tests. Intraindividual variability in RT was calculated from psychomotor tasks and data were age-normalized. Results: A total of 44 of the 66 participants completed follow-up (mean age, 34.0 ± 5.5 years; 66 % female; mean disease duration, 4.1 ± 2.9 years; median Expanded Disability Status Scale (EDSS) score, 1.5 [0 to 6.0]). Participants were grouped by SDMT z-score median split. Groups did not differ in demographics or clinical features. The higher baseline SDMT group was faster (p = 0.05) in RT and less variable (lower IIV, p = 0.001). At the two-year follow-up, the higher SDMT group showed increased variability (p = 0.05) compared to the lower SDMT group, with no significant RT or BICAMS changes. Conclusions: In early MS, higher SDMT performance at baseline is associated with less cognitive variability but may indicate susceptibility to increased variability over time, highlighting the importance of monitoring IIV for early cognitive changes.

Accuracy of dynamic computer-assisted implant surgery in fully edentulous patients: An in vitro study.

OBJECTIVES: To compare miniscrew versus bone tracing registration methods on dental implant placement accuracy and time efficiency in edentulous jaws using a dynamic computer-assisted implant surgery (d-CAIS) system. METHODS: Twelve fully edentulous maxillary models were allocated into two groups: miniscrew tracing (MST) group, where registration was performed by tracing four miniscrews; and bone tracing (BT) group, where registration was conducted by tracing maxillary bone fiducial landmarks. Six implants were placed on each model using the X-Guide® d-CAIS system. Pre- and postoperative cone-beam computed tomography (CBCT) scans were superimposed to evaluate implant placement accuracy. The time required for registration and the overall surgery time were also recorded. RESULTS: Thirty-six implants were placed in each group. The MST group showed significantly lower mean angulation deviations (mean difference (MD): -3.33°; 95% confidence interval (CI): -6.56 to -0.09); p = 0.044), 3D platform deviations (MD: -1.01 mm; 95%CI: -1.74 to -0.29; p = 0.006), 2D platform deviations (MD: -0.97 mm; 95%CI: -1.71 to -0.23; p = 0.010), and 3D apex deviations (MD: -1.18 mm; 95%CI: -1.92 to -0.44; p = 0.002) versus the BT group. The overall surgery time was similar for both groups (MD: 6.10 min.; 95%CI: -0.31 to 12.51; p = 0.06), though bone tracing required significantly more time compared with miniscrew registration (MD: 4.79 min.; 95%CI: 2.96 to 6.62; p < 0.05). CONCLUSIONS: Registration with MST increases the accuracy of implant placement with a d-CAIS system in edentulous jaws compared with the BT method, and slightly reduces the overall surgery time. CLINICAL SIGNIFICANCE: Miniscrew tracing registration improves implant placement accuracy in comparison with bone tracing registration.

Outcome prediction in metabolic dysfunction-associated steatotic liver disease using stain-free digital pathological assessment.

Computational quantification reduces observer-related variability in histological assessment of metabolic dysfunction-associated steatotic liver disease (MASLD). We undertook stain-free imaging using the SteatoSITE resource to generate tools directly predictive of clinical outcomes. Unstained liver biopsy sections (n = 452) were imaged using second-harmonic generation/two-photon excitation fluorescence (TPEF) microscopy, and all-cause mortality and hepatic decompensation indices constructed. The mortality index had greater predictive power for all-cause mortality (index >.14 vs. .31 vs.

Performance and clinical utility of an artificial intelligence-enabled tool for pulmonary embolism detection.

PURPOSE: Diagnosing pulmonary embolism (PE) is still challenging due to other conditions that can mimic its appearance, leading to incomplete or delayed management and several inter-observer variabilities. This study evaluated the performance and clinical utility of an artificial intelligence (AI)-based application designed to assist clinicians in the detection of PE on CT pulmonary angiography (CTPA). PATIENTS AND METHODS: CTPAs from 230 US cities acquired on 57 scanner models from 6 different vendors were retrospectively collected. Three US board certified expert radiologists defined the ground truth by majority agreement. The same cases were analyzed by CINA-PE, an AI-driven algorithm capable of detecting and highlighting suspected PE locations. The algorithm's performance at a per-case and per-finding level was evaluated. Furthermore, cases with PE not mentioned in the clinical report but correctly detected by the algorithm were analyzed. RESULTS: A total of 1204 CTPAs (mean age 62.1 years ± 16.6[SD], 44.4 % female, 14.9 % positive) were included in the study. Per-case sensitivity and specificity were 93.9 % (95%CI: 89.3 %-96.9 %) and 94.8 % (95%CI: 93.3 %-96.1 %), respectively. Per-finding positive predictive value was 89.5 % (95%CI: 86.7 %-91.9 %). Among the 196 positive cases, 29 (15.6 %) were not mentioned in the clinical report. The algorithm detected 22/29 (76 %) of these cases, leading to a reduction in the miss rate from 15.6 % to 3.8 % (7/186). CONCLUSIONS: The AI-based application may improve diagnostic accuracy in detecting PE and enhance patient outcomes through timely intervention. Integrating AI tools in clinical workflows can reduce missed or delayed diagnoses, and positively impact healthcare delivery and patient care.

Skill enactment and knowledge acquisition among community users of digital mental health interventions: qualitative study with thematic analysis.

BACKGROUND: The acquisition of knowledge and use of skills from digital mental health interventions (DMHIs) are considered important for effectiveness. However, our understanding of user experiences implementing skills learned from these interventions is limited, particularly outside of research trials. This qualitative study aimed to investigate how community users learn and apply knowledge and skills from DMHIs based on cognitive behavioural therapy (CBT) in daily life. The study also examined factors influencing the selection and use of skills and explored perceived changes in mental health resulting from the intervention. METHODS: Thirteen adults aged 26 to 66 years (10 females) were recruited using social media advertising and participated in semi-structured interviews by telephone or videoconference. All participants were living in Australia and had used a digital CBT program within the past 3 months. Interviews lasted on average 45 min. Transcripts were analysed using theoretical thematic analysis. RESULTS: Participants demonstrated high levels of program engagement. Findings were organised into three topics with six major themes. Participants reported that their chosen intervention reinforced existing knowledge and fostered new skills and insights (Topic 1, Theme 1: knowledge consolidation). Most described actively applying skills (Topic 1, Theme 2: active approach to skill enactment), although the extent of learning and range of skills enacted varied across participants. Influences on skill selection included the perceived relevance of intervention strategies to the user's needs and personal characteristics (Topic 2, Theme 1: relevance of intervention strategies), as well as the perceived or experienced effectiveness of those strategies (Topic 2, Theme 2: perceived and experienced benefit). Challenges to ongoing skill enactment included time scarcity, prioritisation difficulties, and lack of motivation (Topic 2, Theme 3: navigating time constraints and low motivation). Improvements in mental health were generally modest and attributed mainly to participants' proactive efforts (Topic 3, Theme 1: perceived changes). CONCLUSIONS: DMHIs may reinforce existing understanding of psychotherapeutic strategies, offer new knowledge, and encourage the application of skills in everyday life among community users who actively engage with these interventions. Future research should prioritise personalising DMHIs and investigating methods to optimise the acquisition, retention, and sustained application of knowledge and skills.

Application of image recognition-based tracker-less augmented reality navigation system in a series of sawbone trials.

BACKGROUND: This study introduced an Augmented Reality (AR) navigation system to address limitations in conventional high tibial osteotomy (HTO). The objective was to enhance precision and efficiency in HTO procedures, overcoming challenges such as inconsistent postoperative alignment and potential neurovascular damage. METHODS: The AR-MR (Mixed Reality) navigation system, comprising HoloLens, Unity Engine, and Vuforia software, was employed for pre-clinical trials using tibial sawbone models. CT images generated 3D anatomical models, projected via HoloLens, allowing surgeons to interact through intuitive hand gestures. The critical procedure of target tracking, essential for aligning virtual and real objects, was facilitated by Vuforia's feature detection algorithm. RESULTS: In trials, the AR-MR system demonstrated significant reductions in both preoperative planning and intraoperative times compared to conventional navigation and metal 3D-printed surgical guides. The AR system, while exhibiting lower accuracy, exhibited efficiency, making it a promising option for HTO procedures. The preoperative planning time for the AR system was notably shorter (4 min) compared to conventional navigation (30.5 min) and metal guides (75.5 min). Intraoperative time for AR lasted 8.5 min, considerably faster than that of conventional navigation (31.5 min) and metal guides (10.5 min). CONCLUSIONS: The AR navigation system presents a transformative approach to HTO, offering a trade-off between accuracy and efficiency. Ongoing improvements, such as the incorporation of two-stage registration and pointing devices, could further enhance precision. While the system may be less accurate, its efficiency renders it a potential breakthrough in orthopedic surgery, particularly for reducing unnecessary harm and streamlining surgical procedures.

Efficacy of computer-controlled local anesthesia delivery system on pain in dental anesthesia: a systematic review of randomized clinical trials.

Computer-controlled local anesthesia delivery (CCLAD) is an innovative electronic injection device that represents a cutting-edge approach to dental anesthesia. This system is promising for painless anesthesia using controlled anesthetic injections. This review aimed to compare the discomfort experienced by patients during local anesthesia using a traditional syringe and the CCLAD system and evaluate the potential of the CCLAD system as a painless dental anesthesia solution. The inclusion criteria for this study were based on the recommendations of the Preferred Reporting Items for Systematic Reviews and Meta-Analysis guidelines. The study population, including children and adults, underwent dental anesthesia using the CCLAD system, ensuring a comprehensive and representative sample that instills confidence in the validity of the results. Fourteen clinical trials were included in the analysis after they fulfilled the eligibility criteria. We found that using computer-assisted anesthetic equipment not only led to a significantly lower pain perception score, but also had a profound positive impact on patient behavior. Patients using the CCLAD device exhibited more cooperative and helpful conduct, indicating the system's effectiveness in improving patient comfort and experience and reassuring the audience about its positive impact. In conclusion, using a computer-assisted anesthetic device such as the CCLAD system significantly reduced pain perception scores and improved patient behavior, making them more cooperative and helpful. These findings offer hope for pediatric dentistry and apprehensive adult patients, suggesting a more comfortable and less daunting dental experience with the CCLAD system.

Analysis of Grunting Sound in Infants for Predicting the Severity of Respiratory Distress Syndrome.

OBJECTIVE: Vocalizations from infants, particularly sounds associated with respiratory distress, are fundamental for observational scoring of respiratory tract issues. Listening to these infant sounds is a prevalent technique for decision-making in newborn intensive care units. Expiratory grunting, indicative of the severity and presence of potential conditions, is valuable, however, this evaluative method is subjective and prone to error. This study investigates the potential of computer-aided analysis to offer an objective scale for assessing the severity of respiratory tract problems, utilizing digital recordings of grunting sounds. METHODS: The original data set is formed with a total of 189 grunting sound segments collected from 38 infants. Multiple evaluation approaches were performed to reveal the relation between spectral characteristics of the recordings and the severity or existence of respiratory distress. RESULTS: Three spectral features were evaluated as prominently related to hospital stay duration and respiratory distress. The harmonic ratio of the recordings was graded as the most-related spectral feature that would characterize the severity. CONCLUSIONS: The potential of an innovative and objective grading approach is first investigated for replacing the human ear with a computer-aided evaluation system. The results are promising and the detected relation between expert ear-based scoring and harmonic ratio suggests that the spectral character of the grunting sounds would reflect the nature of respiratory conditions. Moreover, this study underlines those spectral features of digital grunting recordings that would be functional for automated prediction and decision-making.

Diagnostic agreement between visual examination and an automated scanner system with fluorescence for detecting and classifying occlusal carious lesions in primary teeth.

OBJECTIVES: To investigate the in vivo diagnostic agreement between visual examination (VE) using the International Caries Detection and Assessment System (ICDAS) and an automated scanner system for detecting and classifying carious lesions in primary teeth. METHODS: 5-year-old children (n = 216) underwent VE and intraoral scanning (TRIOS 4, 3Shape TRIOS A/S, Copenhagen, Denmark). Dental caries experience was recorded for each tooth surface using ICDAS. An automated, fluorescence-based caries scoring system was applied to eligible primary teeth occlusal surfaces on the 3D models using commercially available software. The automated system classified surfaces as sound, initial caries (ICDAS 01/02), or moderate-extensive caries (ICDAS ≥03). The diagnostic agreement was investigated using multi-level modelling and intraclass correlation coefficients. Analyses were repeated at both the initial threshold (ICDAS ≥01) and the moderate-extensive threshold (ICDAS ≥03). RESULTS: 213 participants were included in the study, and 1525 primary molar occlusal surfaces were included in the analysis. The odds of detecting caries using the automated system were 46 % lower at the initial disease threshold (OR 0.54, 95 % CI 0.39-0.74) and 70 % lower at the moderate-extensive disease threshold (OR 0.30, 95 % CI 0.16-0.58) compared to VE. The intraclass correlation estimates at the initial and moderate-extensive thresholds were 0.90 (95 % CI 0.70-0.96) and 0.76 (95 % CI 0.22-0.94) respectively. CONCLUSION: The automated system is less likely to detect initial lesions and is more likely to underestimate lesion severity relative to visual examination using ICDAS. CLINICAL SIGNIFICANCE: Clinically, using the automated tool to replace thorough visual inspection in primary teeth could result in missed opportunities to provide professional or self-care to arrest or reverse early disease. Additionally, it could misclassify moderate lesions as initial caries, potentially leading to complications associated with the delayed management of dental caries.

Intraoperative surgical navigation as a precision medicine tool in sinonasal and craniofacial oncologic surgery.

INTRODUCTION: Recent evidence supports the efficacy of surgical navigation (SN) in improving outcomes of sinonasal and craniofacial oncologic surgery. This study aims to demonstrate the utility of SN as a tool for integrating surgical, radiologic, and pathologic information. Additionally, a system for recording and mapping biopsy samples has been devised to facilitate sharing of spatial information. MATERIALS AND METHODS: SN was utilized for biopsy mapping in 10 sinonasal/craniofacial oncologic procedures. Twenty-five raters with experience in anterior skull base oncology were interviewed to identify 15 anatomical structures in preoperative imaging, relying on topographical descriptions and surgical video clips. The difference in the localization of anatomical structures by raters was analyzed, using the SN-mapped coordinates as a reference (this difference was defined as spatial error). RESULTS: The analysis revealed an average spatial error of 9.0 mm (95 % confidence interval: 8.3-9.6 mm), with significant differences between surgeons and radiation oncologists (7.9 mm vs 12.5 mm, respectively, p < 0.0001). The proposed model for transferring SN-mapped coordinates can serve as a tool for consultation in multidisciplinary discussions and radiotherapy planning. CONCLUSIONS: The current standard method to evaluate disease extension and margin status is associated with a spatial error approaching 1 cm, which could affect treatment precision and outcomes. The study emphasizes the potential of SN in increasing spatial precision and information sharing. Further research is needed to incorporate this method into a multidisciplinary workflow and measure its impact on outcomes.

Accuracy and time efficiency of a novel deep learning algorithm for Intracranial Hemorrhage detection in CT Scans.

PURPOSE: To evaluate a deep learning-based pipeline using a Dense-UNet architecture for the assessment of acute intracranial hemorrhage (ICH) on non-contrast computed tomography (NCCT) head scans after traumatic brain injury (TBI). MATERIALS AND METHODS: This retrospective study was conducted using a prototype algorithm that evaluated 502 NCCT head scans with ICH in context of TBI. Four board-certified radiologists evaluated in consensus the CT scans to establish the standard of reference for hemorrhage presence and type of ICH. Consequently, all CT scans were independently analyzed by the algorithm and a board-certified radiologist to assess the presence and type of ICH. Additionally, the time to diagnosis was measured for both methods. RESULTS: A total of 405/502 patients presented ICH classified in the following types: intraparenchymal (n = 172); intraventricular (n = 26); subarachnoid (n = 163); subdural (n = 178); and epidural (n = 15). The algorithm showed high diagnostic accuracy (91.24%) for the assessment of ICH with a sensitivity of 90.37% and specificity of 94.85%. To distinguish the different ICH types, the algorithm had a sensitivity of 93.47% and a specificity of 99.79%, with an accuracy of 98.54%. To detect midline shift, the algorithm had a sensitivity of 100%. In terms of processing time, the algorithm was significantly faster compared to the radiologist's time to first diagnosis (15.37 ± 1.85 vs 277 ± 14 s, p < 0.001). CONCLUSION: A novel deep learning algorithm can provide high diagnostic accuracy for the identification and classification of ICH from unenhanced CT scans, combined with short processing times. This has the potential to assist and improve radiologists' ICH assessment in NCCT scans, especially in emergency scenarios, when time efficiency is needed.

Guided versus non-guided chin repositioning: a retrospective study on accuracy.

Genioplasty is a widely used surgical approach to address chin deformities by performing an osteotomy on the inferior border of the mandible to allow for comprehensive repositioning of the chin. This study aimed to compare the accuracy of freehand chin repositioning with a guided technique that employed specialised surgical guides. For this retrospective study, data from 30 adult patients who underwent orthognathic surgery to correct dentofacial deformities were analysed. All patients underwent virtual planning before surgery, with half of them treated using freehand chin repositioning and the other half using the guided technique. The surgical outcomes were measured and compared with the virtual plan to assess the positional and rotational accuracy of the techniques. In terms of translational assessment, noteworthy values that exceeded clinically acceptable limits were observed only in sagittal movement in the freehand group (0.97 mm, interquartile range (IQR) 0.73-2.29 mm). Regarding rotational accuracy, both groups exhibited an IQR that surpassed acceptable limits for pitch (3.26°, IQR 2.06-5.20 for the guided group and 2.57°, IQR 1.63-4.24° for the freehand group). The Mann-Whitney test indicated no statistical differences between the groups in any translational or rotational assessment. In conclusion, although there was no statistical difference, the guided technique proved effective in achieving clinically acceptable accuracy in all positions and almost all rotations, displaying superior results in sagittal positioning compared with the freehand technique. To fully harness the advantages of guides and to guarantee accuracy in all rotations, we recommend further research involving guides made of more rigid materials, and customised implants.

Craniomaxillofacial landmarks detection in CT scans with limited labeled data via semi-supervised learning.

Background: Three-dimensional cephalometric analysis is crucial in craniomaxillofacial assessment, with landmarks detection in craniomaxillofacial (CMF) CT scans being a key component. However, creating robust deep learning models for this task typically requires extensive CMF CT datasets annotated by experienced medical professionals, a process that is time-consuming and labor-intensive. Conversely, acquiring large volume of unlabeled CMF CT data is relatively straightforward. Thus, semi-supervised learning (SSL), leveraging limited labeled data supplemented by sufficient unlabeled dataset, could be a viable solution to this challenge. Method: We developed an SSL model, named CephaloMatch, based on a strong-weak perturbation consistency framework. The proposed SSL model incorporates a head position rectification technique through coarse detection to enhance consistency between labeled and unlabeled datasets and a multilayers perturbation method which is employed to expand the perturbation space. The proposed SSL model was assessed using 362 CMF CT scans, divided into a training set (60 scans), a validation set (14 scans), and an unlabeled set (288 scans). Result: The proposed SSL model attained a detection error of 1.60 ± 0.87 mm, significantly surpassing the performance of conventional fully supervised learning model (1.94 ± 1.12 mm). Notably, the proposed SSL model achieved equivalent detection accuracy (1.91 ± 1.00 mm) with only half the labeled dataset, compared to the fully supervised learning model. Conclusions: The proposed SSL model demonstrated exceptional performance in landmarks detection using a limited labeled CMF CT dataset, significantly reducing the workload of medical professionals and enhances the accuracy of 3D cephalometric analysis.

Changes of the peripapillary vascular parameters in premature infants without retinopathy of prematurity using U-net segmentation.

AIM: To quantitatively assess the changes in mean vascular tortuosity (mVT) and mean vascular width (mVW) around the optic disc and their correlation with gestational age (GA) and birth weight (BW) in premature infants without retinopathy of prematurity (ROP). METHODS: A single-center retrospective study included a total of 133 (133 eyes) premature infants [mean corrected gestational age (CGA) 43.6wk] without ROP as the premature group and 130 (130 eyes) CGA-matched full-term infants as the control group. The peripapillary mVT and mVW were quantitatively measured using computer-assisted techniques. RESULTS: Premature infants had significantly higher mVT (P=0.0032) and lower mVW (P=0.0086) by 2.68 (104 cm-3) and 1.85 µm, respectively. Subgroup analysis with GA showed significant differences (P=0.0244) in mVT between the early preterm and middle to late preterm groups, but the differences between mVW were not significant (P=0.6652). The results of the multiple linear regression model showed a significant negative correlation between GA and BW with mVT after adjusting sex and CGA (P=0.0211 and P=0.0006, respectively). For each day increase in GA at birth, mVT decreased by 0.1281 (104 cm-3) and for each 1 g increase in BW, mVT decreased by 0.006 (104 cm-3). However, GA (P=0.9402) and BW (P=0.7275) were not significantly correlated with mVW. CONCLUSION: Preterm birth significantly affects the peripapillary vascular parameters that indicate higher mVT and narrower mVW in premature infants without ROP. Alterations in these parameters may provide new insights into the pathogenesis of ocular vascular disease.

Applications and accuracy of 3D-printed surgical guides in traumatology and orthopaedic surgery: A systematic review and meta-analysis.

Background: Patient-Specific Surgical Guides (PSSGs) are advocated for reducing radiation exposure, operation time and enhancing precision in surgery. However, existing accuracy assessments are limited to specific surgeries, leaving uncertainties about variations in accuracy across different anatomical sites, three-dimensional (3D) printing technologies and manufacturers (traditional vs. printed at the point of care). This study aimed to evaluate PSSGs accuracy in traumatology and orthopaedic surgery, considering anatomical regions, printing methods and manufacturers. Methods: A systematic review was conducted following the Preferred Reporting Items for Systematic Reviews and Meta-Analysis guidelines. Studies were eligible if they (1) assessed the accuracy of PSSGs by comparing preoperative planning and postoperative results in at least two different planes (2) used either computer tomography or magnetic resonance imaging (3) covered the field of orthopaedic surgery or traumatology and (4) were available in English or German language. The 'Quality Assessment Tool for Quantitative Studies' was used for methodological quality assessment. Descriptive statistics, including mean, standard deviation, and ranges, are presented. A random effects meta-analysis was performed to determine the pooled mean absolute deviation between preoperative plan and postoperative result for each anatomic region (shoulder, hip, spine, and knee). Results: Of 4212 initially eligible studies, 33 were included in the final analysis (8 for shoulder, 5 for hip, 5 for spine, 14 for knee and 1 for trauma). Pooled mean deviation (95% confidence interval) for total knee arthroplasty (TKA), total shoulder arthroplasty (TSA), total hip arthroplasty (THA) and spine surgery (pedicle screw placement during spondylodesis) were 1.82° (1.48, 2.15), 2.52° (1.9, 3.13), 3.49° (3.04, 3.93) and 2.67° (1.64, 3.69), respectively. Accuracy varied between TKA and THA and between TKA and TSA. Conclusion: Accuracy of PSSGs depends on the type of surgery but averages around 2-3° deviation from the plan. The use of PSSGs might be considered for selected complex cases. Level of Evidence: Level 3 (meta-analysis including Level 3 studies).

Automated cardiovascular MR myocardial scar quantification with unsupervised domain adaptation.

Quantification of myocardial scar from late gadolinium enhancement (LGE) cardiovascular magnetic resonance (CMR) images can be facilitated by automated artificial intelligence (AI)-based analysis. However, AI models are susceptible to domain shifts in which the model performance is degraded when applied to data with different characteristics than the original training data. In this study, CycleGAN models were trained to translate local hospital data to the appearance of a public LGE CMR dataset. After domain adaptation, an AI scar quantification pipeline including myocardium segmentation, scar segmentation, and computation of scar burden, previously developed on the public dataset, was evaluated on an external test set including 44 patients clinically assessed for ischemic scar. The mean ± standard deviation Dice similarity coefficients between the manual and AI-predicted segmentations in all patients were similar to those previously reported: 0.76 ± 0.05 for myocardium and 0.75 ± 0.32 for scar, 0.41 ± 0.12 for scar in scans with pathological findings. Bland-Altman analysis showed a mean bias in scar burden percentage of -0.62% with limits of agreement from -8.4% to 7.17%. These results show the feasibility of deploying AI models, trained with public data, for LGE CMR quantification on local clinical data using unsupervised CycleGAN-based domain adaptation. RELEVANCE STATEMENT: Our study demonstrated the possibility of using AI models trained from public databases to be applied to patient data acquired at a specific institution with different acquisition settings, without additional manual labor to obtain further training labels.

Correcting facial asymmetry through guided plate assisted mandibular angle osteotomy.

Background: Asian women prefer a smooth and narrowed mandibular appearance. The purpose of the retrospective cohort study is to evaluate guide plate-assisted mandibular angle ostectomy (MAO) in improving mandibular symmetry for Asian female patients with mandibular angle hypertrophy (MAH) with normal occlusal relationship. Methods: We retrospectively examined 11 patients with asymmetry MAH with normal occlusal relationship who received MAO at Shanghai Ninth People's Hospital between September, 2020, and January, 2022. Preoperative plans were designed based on CT data and executed using metal guide plate during the operation. Preoperative and one-week postoperative CT scans were used to assess measurements including Height_Go, Divergence_Go, ∠ZyZy-GoGo, and osteotomy volume, to evaluate symmetry. For precision, compare the postoperative CT with the preoperative design, assessing osteotomy distance, angle, and volume error. Patient satisfacation was evaluated with Likert Scale in 6-month follow-up. Secondary lipofilling procedures were given as appropriate. Statistical analysis was performed using paired t-tests in SPSS. Results: The mean age of the 11 patients was 28.5 years (range 23-34 years). 2 of these underwent lipofilling procedures. No complications were observed during the following-up. Postoperative results were not statistically different from the design, demonstrating a precision of within 2 mm. Height_Go disparity within 5 mm get corrected notably, reducing asymmetry from 15.09% preoperatively to 2.74% postoperatively. Patients satisfaction was rated at 4.5 out of 5 in 6 month follow-up. Conclusions: Guide plate-assisted mandibular angle osteotomies achieve effective and precise surgery. This approach demonstrates a safe option for correction for mandibular asymmetry, achieving patient satisfaction.

Prediction of CD8+T lymphocyte infiltration levels in gastric cancer from contrast-enhanced CT and clinical factors using machine learning.

BACKGROUND: CD8+ T lymphocyte infiltration is closely associated with the prognosis and immunotherapy response of gastric cancer (GC). For now, the examination of CD8 infiltration levels relies on endoscopic biopsy, which is invasive and unsuitable for longitude assessment during anti-tumor therapy. PURPOSE: This work aims to develop and validate a noninvasive workflow based on contrast-enhanced CT (CECT) images to evaluate the CD8+ T-cell infiltration profiles of GC. METHODS: GC patients were retrospectively and consecutively enrolled and randomly assigned to the training (validation) or test cohort at a 7:3 ratio. All patients were binary classified into the CD8-high (infiltrated proportion ≥ 20%) or CD8-low group (infiltrated proportion < 20%) group. A total of 1170 radiomics features were extracted from each presurgical CECT series. After feature selection, fifteen radiomics features were transmitted to three independent machine-learning models for the computation of predictive radiological scores. Multilayer perceptron (MLP) was applied to merge the radiological scores with clinical factors. The predictive efficacy of the radiological scores and of the combined model was evaluated by receiver operating characteristic curve, calibration curve, and decision curve analysis in both the training and test cohorts. RESULTS: A total of 210 patients were enrolled in this study (mean age: 63.22 ± 8.74 years, 151 men), and were randomly assigned to the training set (n = 147) or the test set (n = 63). The merged radiological score was correlated with CD8 infiltration in both the training (p = 1.8e-10) and test cohorts (p = 0.00026). The combined model integrating the radiological scores and clinical features achieved an area under the curve (AUC) value of 0.916 (95% CI: 0.872-0.960) in the training set and 0.844 (95% CI: 0.742-0.946) in the test set for classifying CD8-high GCs. The model was well-calibrated and exhibited net benefit over "treat-all" and"treat-none" strategies in decision curve analysis. CONCLUSIONS: Artificial intelligent systems combining radiological features and clinical factors could accurately predict CD8 infiltration levels of GC, which may benefit personalized treatment of GC in the context of immunotherapy.

Evaluation of the hinotori™ Surgical Robot System for accurate suturing in small cavities.

The hinotori™ Surgical Robot System (hinotori™, Medicaroid, Kobe, Japan) is increasingly being utilized primarily in urology and adult surgery; however, data on its application in pediatric surgery are lacking. This preclinical study aimed to evaluate the limitations of this system for accurate suturing in small cavities designed for pediatric and neonatal applications. Two trained operators performed simple ligature sutures (easy task [ET]) and hepaticojejunostomy sutures (difficult task [DT]) within five differently sized boxes, ranging from 5123 to 125 mL. The suture time, number of internal and external instrument/instrument collisions, instrument/box collisions, and suture accuracy were evaluated. The suture accuracy was assessed using the A-Lap Mini endoscopic surgery skill assessment system. As a result, an increase in the number of collisions and extended suturing times were observed in boxes with volumes smaller than 215 mL. Despite these variations, there were no significant differences between the boxes, and all tasks were precisely performed in all boxes (p = 0.10 for the ET and p = 1.00 for the DT). These findings demonstrate the capability of the hinotori™ system to perform precise suturing techniques within tightly confined simulated neonatal cavities as small as 125 mL. To advance the integration of pediatric robotic surgery utilizing the hinotori™ system, additional trials comparing it with conventional laparoscopic and thoracoscopic techniques using pediatric and animal models are necessary to assess its clinical safety and applicability.