Novel artificial intelligence approach for automatic differentiation of fetal occiput anterior and non-occiput anterior positions during labor.

OBJECTIVES: To describe a newly developed machine-learning (ML) algorithm for the automatic recognition of fetal head position using transperineal ultrasound (TPU) during the second stage of labor and to describe its performance in differentiating between occiput anterior (OA) and non-OA positions. METHODS: This was a prospective cohort study including singleton term (> 37 weeks of gestation) pregnancies in the second stage of labor, with a non-anomalous fetus in cephalic presentation. Transabdominal ultrasound was performed to determine whether the fetal head position was OA or non-OA. For each case, one sonographic image of the fetal head was then acquired in an axial plane using TPU and saved for later offline analysis. Using the transabdominal sonographic diagnosis as the gold standard, a ML algorithm based on a pattern-recognition feed-forward neural network was trained on the TPU images to discriminate between OA and non-OA positions. In the training phase, the model tuned its parameters to approximate the training data (i.e. the training dataset) such that it would identify correctly the fetal head position, by exploiting geometric, morphological and intensity-based features of the images. In the testing phase, the algorithm was blinded to the occiput position as determined by transabdominal ultrasound. Using the test dataset, the ability of the ML algorithm to differentiate OA from non-OA fetal positions was assessed in terms of diagnostic accuracy. The F1 -score and precision-recall area under the curve (PR-AUC) were calculated to assess the algorithm's performance. Cohen's kappa (κ) was calculated to evaluate the agreement between the algorithm and the gold standard. RESULTS: Over a period of 24 months (February 2018 to January 2020), at 15 maternity hospitals affiliated to the International Study group on Labor ANd Delivery Sonography (ISLANDS), we enrolled into the study 1219 women in the second stage of labor. On the basis of transabdominal ultrasound, they were classified as OA (n = 801 (65.7%)) or non-OA (n = 418 (34.3%)). From the entire cohort (OA and non-OA), approximately 70% (n = 824) of the patients were assigned randomly to the training dataset and the rest (n = 395) were used as the test dataset. The ML-based algorithm correctly classified the fetal occiput position in 90.4% (357/395) of the test dataset, including 224/246 with OA (91.1%) and 133/149 with non-OA (89.3%) fetal head position. Evaluation of the algorithm's performance gave an F1 -score of 88.7% and a PR-AUC of 85.4%. The algorithm showed a balanced performance in the recognition of both OA and non-OA positions. The robustness of the algorithm was confirmed by high agreement with the gold standard (κ = 0.81; P < 0.0001). CONCLUSIONS: This newly developed ML-based algorithm for the automatic assessment of fetal head position using TPU can differentiate accurately, in most cases, between OA and non-OA positions in the second stage of labor. This algorithm has the potential to support not only obstetricians but also midwives and accoucheurs in the clinical use of TPU to determine fetal occiput position in the labor ward. © 2021 International Society of Ultrasound in Obstetrics and Gynecology.

New technique for automatic sonographic measurement of change in head-perineum distance and angle of progression during active phase of second stage of labor.

OBJECTIVE: To evaluate the performance of a new ultrasound technique for the automatic assessment of the change in head-perineum distance (delta-HPD) and angle of progression (delta-AoP) during the active phase of the second stage of labor. METHODS: This was a prospective observational cohort study including singleton term pregnancies with fetuses in cephalic presentation during the active phase of the second stage of labor. In each patient, two videoclips of 10 s each were acquired transperineally, one in the axial and one in the sagittal plane, between rest and the acme of an expulsive effort, in order to measure HPD and AoP, respectively. The videoclips were processed offline and the difference between the acme of the pushing effort and rest in HPD (delta-HPD) and AoP (delta-AoP) was calculated, first manually by an experienced sonographer and then using a new automatic technique. The reliability of the automatic algorithm was evaluated by comparing the automatic measurements with those obtained manually, which was considered as the reference gold standard. RESULTS: Overall, 27 women were included. A significant correlation was observed between the measurements obtained by the automatic and the manual methods for both delta-HPD (intraclass correlation coefficient (ICC) = 0.97) and delta-AoP (ICC = 0.99). The high accuracy provided by the automatic algorithm was confirmed by the high values of the coefficient of determination (r2 = 0.98 for both delta-HPD and delta-AoP) and the low residual errors (root mean square error = 1.2 mm for delta-HPD and 1.5° for delta-AoP). A Bland-Altman analysis showed a mean difference of 0.52 mm (limits of agreement, -1.58 to 2.62 mm) for delta-HPD (P = 0.034) and 0.35° (limits of agreement, -2.54 to 3.09°) for delta-AoP (P = 0.39) between the manual and automatic measurements. CONCLUSIONS: The automatic assessment of delta-AoP and delta-HPD during maternal pushing efforts is feasible. The automatic measurement of delta-AoP appears to be reliable when compared with the gold standard manual measurement by an experienced operator. Copyright © 2020 ISUOG. Published by John Wiley & Sons Ltd.

Radiofrequency echographic multispectrometry compared with dual X-ray absorptiometry for osteoporosis diagnosis on lumbar spine and femoral neck.

An innovative, non-ionizing technique to diagnose osteoporosis on lumbar spine and femoral neck was evaluated through a multicenter study involving 1914 women. The proposed method showed significant agreement with reference gold standard method and, therefore, a potential for early osteoporosis diagnoses and possibly improved patient management. INTRODUCTION: To assess precision (i.e., short term intra-operator precision) and diagnostic accuracy of an innovative non-ionizing technique, REMS (Radiofrequency Echographic Multi Spectrometry), in comparison with the clinical gold standard reference DXA (dual X-ray absorptiometry), through an observational multicenter clinical study. METHODS: In a multicenter cross-sectional observational study, a total of 1914 postmenopausal women (51-70 years) underwent spinal (n = 1553) and/or femoral (n = 1637) DXA, according to their medical prescription, and echographic scan of the same anatomical sites performed with the REMS approach. All the medical reports (DXA and REMS) were carefully checked to identify possible errors that could have caused inaccurate measurements: erroneous REMS reports were excluded, whereas erroneous DXA reports were re-analyzed where possible and otherwise excluded before assessing REMS accuracy. REMS precision was independently assessed. RESULTS: In the spinal group, quality assessment on medical reports produced the exclusion of 280 patients because of REMS errors and 78 patients because of DXA errors, whereas 296 DXA reports were re-analyzed and corrected. Analogously, in the femoral group there were 205 exclusions for REMS errors, 59 exclusions for DXA errors, and 217 re-analyzed DXA reports. In the resulting dataset (n = 1195 for spine, n = 1373 for femur) REMS outcome showed a good agreement with DXA: the average difference in bone mineral density (BMD, bias ± 2SD) was -0.004 ± 0.088 g/cm2 for spine and - 0.006 ± 0.076 g/cm2 for femur. Linear regression showed also that the two methods were well correlated: standard error of the estimate (SEE) was 5.3% for spine and 5.8% for femur. REMS precision, expressed as RMS-CV, was 0.38% for spine and 0.32% for femur. CONCLUSIONS: The REMS approach can be used for non-ionizing osteoporosis diagnosis directly on lumbar spine and femoral neck with a good level of accuracy and precision. However, a more rigorous operator training is needed to limit the erroneous acquisitions and to ensure the full clinical practicability.

Automatic ultrasound technique to measure angle of progression during labor.

OBJECTIVE: To evaluate the accuracy and reliability of an automatic ultrasound technique for assessment of the angle of progression (AoP) during labor. METHODS: Thirty-nine pregnant women in the second stage of labor, with fetus in cephalic presentation, underwent conventional labor management with additional translabial sonographic examination. AoP was measured in a total of 95 acquisition sessions, both automatically by an innovative algorithm and manually by an experienced sonographer, who was blinded to the algorithm outcome. The results obtained from the manual measurement were used as the reference against which the performance of the algorithm was assessed. In order to overcome the common difficulties encountered when visualizing by sonography the pubic symphysis, the AoP was measured by considering as the symphysis landmark its centroid rather than its distal point, thereby assuring high measurement reliability and reproducibility, while maintaining objectivity and accuracy in the evaluation of progression of labor. RESULTS: There was a strong and statistically significant correlation between AoP values measured by the algorithm and the reference values (r = 0.99, P < 0.001). The high accuracy provided by the automatic method was also highlighted by the corresponding high values of the coefficient of determination (r2 = 0.98) and the low residual errors (root mean square error = 2°27' (2.1%)). The global agreement between the two methods, assessed through Bland-Altman analysis, resulted in a negligible mean difference of 1°1' (limits of agreement, 4°29'). CONCLUSIONS: The proposed automatic algorithm is a reliable technique for measurement of the AoP. Its (relative) operator-independence has the potential to reduce human errors and speed up ultrasound acquisition time, which should facilitate management of women during labor. Copyright © 2017 ISUOG. Published by John Wiley & Sons Ltd.

Polymeric meshes for internal sutures with differentiated adhesion on the two sides.

The aim of this work is to investigate the effects of different plasma treatments on ePTFE abdominal prostheses with the final goal of obtaining a new prosthesis, made of a single strand of ePTFE, with clearly differentiated adhesion properties on the two sides, which should be able to promote tissue ingrowth on one side and prevent post surgical visceral adhesions on the other. Samples obtained from ePTFE Bard Dulex Meshes have been treated sequentially with three different gases (N(2), O(2) and NH(3)) in order to choose the optimal treatment conditions to improve ePTFE wettability. In particular, no modification was induced by N(2) treatment, while the full treatment after the final ammonia gas resulted in the best suitable candidate. As demonstrated by scanning electron microscopy, AFM analyses and contact angle measurements, ammonia plasma treatment increases ePTFE surface roughness and renders it more hydrophilic, thus promoting adhesion without any alteration of the material's bulk properties. The reported results also evidence the possibility to obtain the maximum wettability with a cheap treatment by optimizing plasma exposure time. As a preliminary cell adhesion study, Swiss 3T3 fibroblasts (mouse, embryo) have been seeded on the treated and untreated materials in order to assess whether there was any difference in terms of cell attachment and spreading. Cells seeded on the ammonia plasma treated material showed a better adhesion and spreading when compared to the untreated material.

Cellulose derivative-hyaluronic acid-based microporous hydrogels cross-linked through divinyl sulfone (DVS) to modulate equilibrium sorption capacity and network stability.

The aim of this work is to obtain a chemically cross-linked hydrogel from hyaluronic acid and cellulose derivatives that exhibits sensitivity to variation of the composition of the external absorbing medium and an equilibrium sorption capacity higher than a common hyaluronic acid-based hydrogel, in view of its potential use in prevention of postsurgical soft tissue adhesion. This has been achieved by chemical stabilization of hyaluronic acid (HA) and cellulose derivatives, hydroxyethylcellulose (HEC) and carboxymethylcellulose (CMCNa) through the difunctional cross-linker divinyl sulfone. Significant increase in sorption capacity, both in water and in water solutions at different ionic strength, has been observed for these samples in comparison with hydrogels obtained through chemical stabilization of hyaluronic acid. Moreover, different dehydration procedures adopted for the xerogel synthesis have been used, which resulted in a modulation of the equilibrium sorption capacity. Hyaluronic acid stability has been confirmed by means of NMR analysis.