A system-on-chip solution for deep learning-based automatic fetal biometric measurement

An automatic method able to recognize a presented section through the biparietal plane of the fetal head and a section through the fetal femur in ultrasound images is developed. Once the correct anatomical section for measurement is identified by the machine, the placement of the measurement calipers is automatically determined by fitting an active contour model to the structure of interest. The fetal biparietal diameter (BPD) and femur length (FL) are then measured automatically. The validation data set contained 167 and 197 B-mode images for BPD and FL measurements, respectively. The images were acquired using 4 different ultrasound scanners, which resulted in varied image quality and gain settings. The mean gestational age (GA) of the fetuses was 19.4 weeks, range 16 to 41 weeks. A measurement success rate of 90% was achieved for both BPD and FL. The correlation coefficients between the manual and automatic measurements were 0.995 (BPD) and 0.967 (FL), mean errors were 0.5 mm (BPD) and -1.7 mm (FL) and error range with 95% confidence interval (CI) were ﹣3.8 - 4.8 mm (BPD) and ﹣11.4 - 8.1 mm (FL). The automatic measurement results were consistent in both high and low gain settings. The intraclass correlation coefficients between manual and automatic measurements were 0.995 (95% CI; 0.981 - 0.999) for BPD in high gain, 1.0 (95% CI; 0.998 - 1.0) for BPD in low gain, 0.998 (95% CI; 0.991 - 0.999) for FL in high gain and 0.999 (95% CI; 0.996 - 1.0) for FL in low gain settings. The method was implemented on a prototype, portable ultrasound machine designed to be used in low- and middle-income countries (LMIC). The overall performance of the method supports our hypothesis that automated methods can be used and are beneficial in a clinical setting.

To compare fetal measurements obtained using two-dimensional (2D) and three-dimensional (3D) ultrasonography (US) and the impact of the US technique regarding the intra- and interobservator reproducibility of an experienced ultrasonographer (A) and a trainee (B). Biometric measurements were realised in 33 singleton fetuses (20 to 40WG) by the two study sonographers (A & B). Each sonographer twice measured the cephalic circumference (CC), the abdominal circumference (AC) & the femoral length (FL) and two sets of fetal volumes were stored. CC, AC & FL were then calculated for each stored volume, and the volume of the thigh (Tvol) was also evaluated. The dispersion of fetal biometric measurements was evaluated for each parameter (both 2D and 3D US) by calculating the standard deviations and comparing the rate of values below the 10th and above the 90th centile. Measurements were converted into Z-scores and intra-class correlation coefficients (ICC) were calculated to investigate the reproducibility within and between ultrasonographers A & B. The respective impact of 2D & 3D US on each biometric parameter was evaluated by applying Tuckey tests. We did not observe any significant difference between 2D US and 3D US, although the dispersion appeared smaller with the 3D technique. 3D Ultrasound had a higher intra observer reproducibility for the trainee, especially for AC and FL measurements performed (ICC 0.93 vs 0.88 & 0.96 vs 0.90 respectively). The inter observer reproducibility was also higher with 3D for AC and FL (ICC 0.89 vs 0.60 & 0.63 vs 0.45 respectively). The intra observer reproducibility of the Tvol measurement was high (ICC 0.91 for A and 0.88 for B). The Tvol inter observer reproducibility, however, was low (ICC 0.57). Reproducibility of the measurements (AC & FL) was improved by 3D US for both inter observer and trainee intra observer evaluations. The Tvol didn't display a satisfactory inter observer reproducibility.

The levator hiatus is the largest potential hernial portal in the human body and an important determinant of pelvic organ prolapse and prolapse recurrence. Manufacturers of ultrasound equipment have started to offer automatic determination of hiatal dimensions. We aimed to validate such data against manual measurement. This was an observational study using routinely obtained data sets of 62 women who attended a urogynecological unit in 2023. A Voluson E 22 system with SonoPelvic software was used for automated determination of hiatal dimensions. The latter were re-measured manually on de-identified stored data sets at a later date, using the software 4D View, blinded against all other data. The results show a comparison of manual (left) and automated (right) measurements of the levator hiatus on Valsalva. Four data sets were unavailable, leaving 58 for a comparison of manual and automatic measurements. The former provided a mean of 27.9 (range, 7- 53.8, SD 10.8)cm2 while the SonoPelvic automated measurements yielded a mean of 23.7 (5-44.8, SD 8.32)cm2, giving a Pearson's correlation of 0.663 (P < 0.0001). The difference between automated and manual measurements was statistically significant (P = 0.019). In 18 out of 58 cases, the discrepancy between automatic and manual measurement was 20% or higher in either direction, and these cases were reviewed. In some instances the discrepancy was due to incorrect placement of the reference plane as a result of misidentification of symphysis pubis or anorectal angle. In 11 others the hiatal circumference was mis- identified, most commonly due to a large cystocele, the contour of which was mis-identified as the hiatus (n = 9). Bland Altman analysis demonstrated a lack of systematic bias, but a substantial number of outliers in the sense of under-estimation of hiatal area by the AI. At this point in time, inexperienced users should not consider AI-based hiatal measurements to be authoritative. This is particularly true in women with large cystocele. Improvement is to be expected as development is ongoing.

To evaluate the tool of automatic measuring CBCT, developed based on deep learning technology, and to compare its accuracy with manual measurement and to verify its effectiveness and feasibility. Twenty-nine adult patients (11 males, 18 females) with mean age of (31.31±13.77) years old were enrolled, CBCT of enrolled patients were collected, and 427 transverse sections of alveolar teeth were extracted(5-5 position). A novel Segment Anything Model(SAM) -based interactive segmentation and measurement tool was developed and applied to the assessment of alveolar socket dimensions in CBCT. Manual and automatic measurements of bone mass in the buccal and lingual transverse section of the alveolar socket were performed by establishing the test set and the validation set, respectively, and the data were compared. There was significant correlation and consistency between CBCT automatic measurement method and manual measurement. The coefficient of determination(R2) of regression analysis in test set was 0.942, the measurement error in validation set was mainly varing between -0.43～0.47 mm, Pearson correlation coefficient was 0.9746 (P＜0.001). This study developed an automatic CBCT measurement tool based on SAM through deep learning, with high accuracy and significantly improved the efficiency of alveolar socket measurement.

IntroductionThe speckle tracking ultrasound is an innovative technology enabling distinct assessment of diaphragmatic movement, yet the relative data are scarce. In this pilot study, we sought to evaluate the predictive value of the weaning outcome of automatic speckle tracking in assessing diaphragm excursion.MethodsThis is a prospective, multicenter, observational study. A total of 160 critically ill subjects underwent speckle-tracking ultrasonography of the right/left hemidiaphragm before the spontaneous breathing trial. Meanwhile, the diaphragm excursion and velocity values were measured manually by M-mode ultrasound. Patients were divided into weaning-failure and weaning-success groups. The correlation was assessed between automatic and manual measurement, and the diagnostic efficacy of automatic measured excursion and velocity for predicting weaning outcome was analyzed.ResultsA total of 88 patients completed the follow-up of the weaning outcome. The overall incidence of weaning failure was 43.18%. There was a significant correlation between the automatic measurement of mean excursion and velocity assessed by speckle tracking imaging and manual measurement (R 0.69 and 0.65, respectively). Receiver operating characteristic (ROC) curve analysis showed that the mean excursion and diaphragmatic velocity exhibited high diagnostic values for prolonged weaning [area under the ROC curve (AUROC) 0.824 and 0.786, respectively]. The diaphragmatic excursion showed moderate diagnostic value for predicting both weaning failure and in-hospital death/withdrawal of treatment (AUROC 0.659 and 0.653, respectively).ConclusionAutomatic speckle tracking analysis of the diaphragm showed high consistency with conventional manual ultrasound measures. Diaphragmatic excursion and its excursion velocity helped predict mechanical ventilation weaning failure, prolonged weaning, as well as in-hospital adverse outcomes, which served as a reliable tool in guiding clinical weaning strategy.Key messageAutomatic speckle tracking analysis of the diaphragm showed high consistency with conventional manual ultrasound measures.Diaphragmatic excursion and its excursion velocity helped predict mechanical ventilation weaning failure, prolonged weaning, as well as in-hospital adverse outcomes.

Using machine learning to automatically measure axial vertebral rotation on radiographs in adolescents with idiopathic scoliosis.

Objetivo: Comparar as medidas do índice tornozelo-braço e do complexo médio-intimal das carótidas, femorais e subclávias em pacientes com HIV sob uso de terapia antirretroviral em relação ao Grupo Controle.Métodos: Setenta pacientes com HIV em uso de terapia antirretroviral há pelo menos cinco anos e 70 indivíduos sem HIV, pareados por sexo e idade, com até 50 anos, foram avaliados pela medida do índice tornozelo-braço e do complexo médio-intimal em carótidas comuns, internas, femorais e subclávia direita.Nas carótidas comuns, realizou-se a medida manual e automática do complexo médio-intimal, sendo a medida automática da carótida comum o padrão-ouro e considerando o complexo médio-intimal espessado quando >0,8 mm.Foi realizada a análise de homogeneidade dos grupos, com o nível de significância assumido em 5%, e foi realizada a comparação das medidas automática e manual, para carótidas, foram usados os gráficos de Bland-Altman.Resultados: Um paciente do grupo de casos (0,7%) teve o índice tornozelo-braço aumentado (>1,3 bilateralmente e sem sinal de calcificação), e não houve alteração no controle.A média automática do complexo médio-intimal em carótidas comuns não evidenciou espessamento em nenhum indivíduo.Não existiu diferença significante entre os grupos com relação ao índice tornozelo-braço, ao complexo médio-intimal e à presença de placas ateromatosas.A média de idade foi de 40,5 anos, nos casos, e 40,8 anos, nos controles.Os dois grupos foram semelhantes quanto ao tabagismo e à hipertensão arterial sistêmica.O colesterol e o triglicerídeo foram mais elevados nos casos, mas o índice de massa corpórea e a circunferência abdominal tiveram maior percentual de normalidade neste grupo.Ao se comparar a média automática da carótida comum direita (CCD) com outros sítios (subclávia origem, segmento médio e femoral comum), a diferença foi estatisticamente e clinicamente significante na origem da subclávia direita (CCD=0,51 versus 0,91 mm; p<0,001).Conclusão: Pessoas infectadas pelo HIV não apresentam risco mais elevado de aterosclerose do que a população controle, levando em consideração os fatores de risco clássicos da aterosclerose e as características específicas do HIV.Comparando a média automática da CCD com outros sítios, a diferença foi estatisticamente e clinicamente significante na origem da subclávia direita.

Measurement and Rate Correction of the QT Interval

Objective To quantitatively study the correlation of the distance of pulmonary valve to pulmonary artery bifurcation (DPVB) of normal fetuses in second and late trimester with the fetal biometric parameters using fetal echocardiography. Methods The distances of pulmonary valve to pulmonary artery bifurcation in end-systole (DPVBs) and in end-diastole (DPVBd) were measured in a standard short axis view or right ventricular outflow tract view using fetal echocardiography on 419 normal fetuses. The gestation ages ranged from 20 to 35+ weeks. Fetal non-cardiac biometric parameters including biparietal diameter (BPD), femoral length (FL) and gestation age (GA) based on menstrual age, pulmonary valve annulus diameters (PA) at end-systole were measured. The correlation between DPVBs, DPVBd and non-cardiac biometric parameters were analyzed. Results In normal fetuses, the DPVBs was (1.14±0.24)cm with a range of 0.67 to 1.61 cm, the DPVBd was (0.93±0.20)cm with a range of 0.53 to 1.33 cm. The DPVBs and DPVBd were increased with the growth of GA, and were positively correlated with GA, BPD, FL and PA (r=0.827, 0.798, 0.793, 0.769; 0.802, 0.764, 0.773 and 0.771, respectively, all P<0.001). The linear regression equations between DPVBs, DPVBd and GA, BPD, FL, PA were: Y=0.054×GA-0.369, Y=0.184×BPD-0.179, Y=0.217×FL+ 0.011, Y=1.602×PA+ 0.156, Y=0.045×GA-0.330, Y=0.152×BPD-0.157, Y=0.182×FL-0.018, Y=1.380×PA+ 0.080. Conclusions In normal fetuses, the DPVBs and DPVBd increase with the growth of GA, and have good correlation with GA, BPD, FL and PA, respectively. Normal reference ranges of DPVBs and DPVBd have been provided. These normative data may become a new tool for assessment of fetal heart, especially has potential applications in screening of complex congenital heart defects. Key words: Echocardiography; Fetus; Developmental biology; Distance of pulmonary valve to pulmconary artery bifurcation

Study question Can automatic measurement of follicles be used to predict the number of oocytes retrieved as accurately as manual physicians’ reports? Summary answer Automated follicular annotations generated by an artificial intelligence platform have similar predictive ability of the number of retrieved and mature oocytes as physician reports. What is known already Ovarian follicle counting is a time-consuming, frequently performed assessment, which has significant inter-observer variability. It’s a perfect candidate for automation using artificial intelligence. The main purpose of this monitoring is to determine the optimal day for trigger administration which maximises the number of retrieved oocytes and increases the chance of pregnancy. This decision typically depends on follicle sizes and hormone levels, while also considering the unique conditions of each patient. Research in this area is ongoing, but it primarily focuses on follicle sizes as measured by physicians, rather than by automated systems. Study design, size, duration This study included 589 in vitro cycles of 545 patients performed in 5 centers in Poland between 2019 and 2021. The 719 examinations that were done at most 3 days before the administration of the trigger were analyzed. Manual reports from follicle measurements have been collected, together with 2D cine loop scans (videos) of the ovaries, and final counts of retrieved oocytes and mature (stage MII) oocytes. The Folliscan artificial intelligence platform provided automatic measurements. Participants/materials, setting, methods Follicles in each ovary were grouped by size, starting from 8mm, then every 2mm up to 24mm, and one group for follicles larger than 24mm. The number of follicles in each group, with the number of days until the trigger shot, was used as features in a linear regression model to predict the number of retrieved oocytes, or MIIs. Two datasets were created: one based on physician reports, and the other on automatic measurements. Main results and the role of chance Ten-fold cross-validation was performed. The model based on manual measurements achieved an R² of 0.62 (Confidence Interval: 0.56–0.68) for predicting the number of retrieved oocytes and 0.51 (CI: 0.45–0.57) for MIIs. In comparison, the model based on automatic annotations achieved an R² of 0.63 (CI: 0.57–0.69) for oocytes and 0.50 (0.43–0.56) for MIIs. The mean average errors (MAE) in the predicted number of oocytes and MIIs were 3.12 (CI: 2.88–3.36) and 2.54 (CI: 2.36–2.72), respectively, for manual measurements. They amounted to 3.09 (CI: 2.85–3.33) and 2.56 (CI: 2.38–2.73) for automatic annotations. Two one-sided tests for equivalence were conducted on the mean average error, with a margin set at 0.2. The results yielded a p-value of 0.026 for oocytes errors and 0.0023 for MIIs errors. Limitations, reasons for caution The study had a limited scope, focusing on research from 5 in vitro clinics. A linear regression model was used, comparing only the potential of automatic measurements with manual measurements. Further development of the model is needed to achieve better accuracy. Wider implications of the findings Manual follicular measurements and automated measurements provide similar predictive values in predicting the number of retrieved and mature oocytes. Automated measurements can be used during stimulation monitoring, offering a reliable and efficient alternative to manual methods. However, clinical studies focusing on interpretable metrics are needed to further validate these findings. Trial registration number Polish National Center for Research and Development no. POIR.01.01.01-00-1634/20-00 and ERC Consolidator Grant TUgbOAT no. 772346.

Background: In routine ultrasonography, the ultrasonologist measures the bi-parietal diameter (BPD), head circumference (HC), abdominal circumference (AC) and femur length (FL) in estimating the gestational age (GA) and estimated date of delivery. However, as the pregnancy advances these parameters become increasingly unreliable in prediction of GA. Estimation of GA in late second and third trimester accurately still a problem till now. Fetal kidney has been shown a steady growth of 1.7 mm fortnightly (every 2 weeks) along pregnancy and is unaffected by growth abnormalities. Many studies have reported that fetal kidney length (FKL) correlates with the gestational age in late trimester very strong. The study aimed to assess the accuracy of the gestational age estimated by mean fetal kidney length compared to multiple growth parameters like BPD, HC, AC & FL in addition to the actual gestational age derived from the reliable last menstrual period. Methods: Cross sectional hospital based study, was conducted at ultrasound unit; department of Obstetrics and Gynecology, Faculty of Medicine, Ain Shams University from the period of July 2018 to December 2018. A total number of 115 Pregnant women at their third trimester by reliable LMP attended antenatal care clinic at Ain-Shams University Hospital and consented to participate in this study. Every woman was subjected to: Expected date of delivery was calculated according to Naegle’s formula: Ultrasonography: Fetal biometry and estimated date of delivery (EDD) by assessment of BPD, HC, FL & AC. Expected fetal weight measured by Hadlock formula. Fetal lie and presentation. Exclusion of fetal anomalies. Measurement of both right & left fetal kidney length. Results: In this study, 255 participants were recruited and assessed for eligibility, 125 women were allocated to perform obstetric ultrasound just 115 completed and were included in the final analysis. The current study found that there was a highly significant positive correlation between gestational age (according to ultrasound parameters) and KL, BDP, HC, AC and FL but Kidney length was the most correlated parameter. Also this study found that there was significant positive correlation between gestational age (according to LMP) and gestational age estimated by BPD, HC, AC, FL and KL with the most significant positive correlation being with KL. Also this study found that there was no significant difference (matched) in KL and Gestational age compared to other parameters. This means that KL is the most accurate parameter for Estimating Gestational age, correlation between MKL and GA by LMP (r = 0.951, p = 0.000) the most significant correlation. In this study, no significant difference was found between gestational age estimated by KL and gestational age in all stages of pregnancy. This means that KL remains accurate as a predictor for gestational age regardless stage of pregnancy. Conclusion: Kidney length can be used as an individual parameter in estimating gestational age.

Small fetal size is the most important risk factor for stillbirth. To our knowledge, no previous study has considered combinations of mid-trimester measures of fetal size as predictors of stillbirth risk. The aim of this cohort study was to assess whether small fetal measurements by mid-pregnancy ultrasound, in conjunction with maternal factors, can predict the risk of stillbirth. In this historical cohort study, we identified 377 563 singleton pregnancies in the Swedish Pregnancy Register between 2014 and 2021, with delivery at ≥22+0 gestational weeks with a first trimester (6+0-13+6 weeks) dating ultrasound, and second trimester (16+0-21+6 weeks) measurements of biparietal diameter (BPD), abdominal circumference (AC), and femur length (FL). Relative risks (RR) with a 95% confidence interval (CI) for stillbirth were calculated for fetuses with any second-trimester biometry <5th centile, and adjusted for maternal characteristics. Odds ratios (ORs) with 95% CI were used to assess the individual contributions of fetal biometry and maternal characteristics to stillbirth risk. Significant factors were included in a multivariate prediction model, and the area under the receiver operating characteristic curve (AUC) was used to assess predictive performance. Short second-trimester FL was associated with increased risk of stillbirth, especially when combined with small AC or both small BPD and AC (aRR [95% CI] 2.78 [1.44-5.34] and 2.40 [1.14-5.06], respectively), whereas normal FL with small BPD and/or AC was not. In the multivariable model, short FL in combination with small AC was the strongest contributor to stillbirth risk assessment. The AUC of the prediction model, including both maternal characteristics, small AC, and short FL, was 0.623 for stillbirth in all pregnancies, 0.635 for term stillbirth, and 0.591 for preterm stillbirth. We found evidence of increased risk of stillbirth among fetuses with short FL, especially in combination with small AC, but not with normal FL, regardless of other small fetal dimensions. However, maternal characteristics and mid-gestational biometry perform poorly in predicting stillbirth.

Background: As pregnancy progresses, the effectiveness of current methods for estimating gestational age diminishes. Meanwhile, fetal kidney length and placental thickness typically increase linearly with advancing gestational age. This observational study aims to explore whether fetal kidney length and placental thickness can serve as reliable indicators for estimating gestational age in healthy singleton pregnancies. This was a prospective observational study in which 125 patie Methodology: nts who came for regular antenatal checkup after 20weeks of gestation has undergone antenatal ultrasound examination were included on the basis of a predefined inclusion and exclusion criteria. First gestational age estimation was done using fetal biometry (head circumference, biparietal diameter, abdominal circumference and femur length). To measure fetal kidney length, the ultrasound transducer was first oriented longitudinally along the fetal spine. A slight adjustment in angulation allowed visualization of the paravertebral plane, capturing the complete length of each fetal kidney separately. Measurements were then averaged for accuracy. Placental thickness was assessed at its thickest point, typically near the umbilical cord insertion site. The correlation between placental thickness and gestational age, and between fetal kidney length and gestational age, was evaluated using biometric measurements and analyzed using Pearsons correlation coefficient. P value less than 0.05 was taken as statistically significant. In our study, the fetal kidney length and placental thickness correlated Results: well with assigned gestational age. A positive linear relationship of gestational age with fetal kidney length and placental thickness was found. Correlation of gestational age with fetal kidney length and placental thickness was 0.966 and 0.966 respectively. In conclusion, the study's Conclusion: results confirm the efficacy of using fetal kidney length (FKL) and placental thickness measurements as reliable indicators for estimating gestational age. These ultrasound measurements have proven accurate in adverse sample, enhancing the potential for widespread application in prenatal care. By enabling precise gestational age estimation, these biometric parameters can improve the timing of prenatal interventions, potentially reducing the risk of premature births and optimizing neonatal outcomes. The findings highlight the importance of integrating these measurements into routine prenatal screening protocols, suggesting that they could significantly enhance the quality and effectiveness of maternal and fetal health management. Despite challenges such as measurement variability due to operator dependency and the limitations of a cross-sectional study design, the study's impact is potentially transformative, particularly in settings where access to advanced prenatal care technologies is limited. Moving forward, further research should focus on longitudinal studies to track these measurements over time and refine the methodology to reduce variability and increase the reliability of these crucial prenatal assessments.

Objetivo: Determinar la correlación de la biometría fetal estándar y la biometría secundaria con la edad gestacional en gestantes del segundo y tercer trimestre. Diseño: Estudio transversal analítico. Institución: Hospital III Honorio Delgado de Arequipa, Perú. Participantes: Gestantes del segundo y tercer trimestre de gestación que acudieron para evaluación ecográfica de rutina sin evidencia de patología, desde enero hasta mayo de 2014. Métodos: Se consideró como biometría fetal estándar a la medición del diámetro biparietal (DBP), circunferencia cefálica (CC), longitud del fémur (LF) y circunferencia abdominal (CA); y biometría fetal secundaria a la medición del diámetro cerebeloso transverso (DCT), longitud renal (LR) y longitud del pie (LP). Principales medidas de resultados: Cálculo de regresión y correlación de la biometría fetal estándar y secundaria con la edad gestacional. Resultados: Se evaluó 140 gestantes del segundo y tercer trimestre de gestación con una edad materna promedio de 26,14 años y se encontró que todos los parámetros biométricos tuvieron buena correlación con la EG. Sin embargo, la mejor correlación con la EG fue la de la LF (r2 = 0,943) seguido por la LP (r2 = 0,940) y la más baja correlación fue de la LR (r2 = 0,860). En el tercer trimestre, las correlaciones fueron más bajas que en el segundo trimestre, siendo la más alta correlación de la LF (r2 = 0,756), seguida de la LP (r2 = 0,713); la más baja correlación fue de la LR (r2 = 0,395). Conclusiones: En nuestra población existió buena correlación de la biometría fetal estándar y secundaria con la edad gestacional, siendo la correlación de la longitud del fémur y la longitud del pie las mejores en el segundo y tercer trimestre de gestación; la longitud renal tuvo correlación pobre en el tercer trimestre.

Assessing distal radius malunions traditionally relies on measuring volar tilt and radial inclination in 2D radiographs. Reliability of these parameters is limited by projection errors and landmark ambiguity. Using 3D models allows more precise quantification of these parameters. This study validated an algorithm for measuring volar tilt and radial inclination on 3D virtual models of malunited and healthy radii. The algorithm establishes a 3D coordinate system and anatomical landmarks replicating conventional 2D definitions to maintain clinical compatibility. Automatic 3D measurements on models from 16 participants were compared with manual measurements on 2D radiographs (by three surgeons in consensus) and on 3D models (by two independent raters). Agreement was assessed using Bland-Altman analysis, and landmark discrepancies were quantified. Mean differences between automatic 3D and manual 2D measurements were small: for volar tilt, 2.0° in malunited and 3.5° in healthy radii; for radial inclination, 1.5° and 2.3°, respectively. Strong agreement was also found between automatic and manual 3D measurements. Landmark deviations ranged from 0.5 to 2.8mm, with an average longitudinal axis difference of 2.5°. This open-source algorithm provides a reproducible 3D assessment of distal radius alignment. By closely matching 2D standards, the algorithm has a high potential for clinical integration.