Statistical Analysis of Methotrexate Degradation by UV-C Photolysis and UV-C/TiO2 Photocatalysis.

Methotrexate (MTX) is a folic acid analog and has been used to treat a wide variety of malignant and non-malignant diseases. The wide use of these substances has led to the continuous discharge of the parent compound and its metabolites in wastewater. In conventional wastewater treatment plants, the removal or degradation of drugs is not complete. In order to study the MTX degradation by photolysis and photocatalysis processes, two reactors were used with TiO2 as a catalyst and UV-C lamps as a radiation source. H2O2 addition was also studied (absence and 3 mM/L), and different initial pHs (3.5, 7, and 9.5) were tested to define the best degradation parameters. Results were analyzed by means of ANOVA and the Tukey test. Results show that photolysis in acidic conditions with 3 mM of H2O2 added is the best condition for MTX degradation in these reactors, with a kinetic constant of 0.028 min-1. According to the ANOVA test, all considered factors (process, pH, H2O2 addition, and experimentation time) caused statistically significant differences in the MTX degradation results.

Tumorigenic transformation of human prostatic epithelial cell line RWPE-1 by growth hormone-releasing hormone (GHRH).

BACKGROUND: Growth hormone-releasing hormone (GHRH) and its receptors have been implicated in the progression of various tumors. In this study, we analyzed the carcinogenetic potential of exposure to GHRH of a nontumor human prostate epithelial cell line (RWPE-1) as well as its transforming effect in a xenograft model. METHODS: We performed cell viability, cell proliferation, adhesion and migration assays. In addition, metalloprotease (MMP)-2 activity by means gelatin zymography, GHRH-R subcellular location using confocal immunofluorescence microscopy and vascular endothelial growth factor (VEGF) levels by enzyme-linked immunoassay were assessed. Besides, we developed an in vivo model in order vivo model to determine the role of GHRH on tumorigenic transformation of RWPE-1 cells. RESULTS: In cell cultures, we observed development of a migratory phenotype consistent with the gelatinolytic activity of MMP-2, expression of VEGF, as well as E-cadherin-mediated cell-cell adhesion and increased cell motility. Treatment with 0.1 µM GHRH for 24 h significantly increased cell viability and cell proliferation. Similar effects of GHRH were seen in RWPE-1 tumors developed by subcutaneous injection of GHRH-treated cells in athymic nude mice, 49 days after inoculation. CONCLUSIONS: Thus, GHRH appears to act as a cytokine in the transformation of RWPE-1 cells by mechanisms that likely involve epithelial-mesenchymal transition, thus reinforcing the role of GHRH in tumorigenesis of prostate.

Stimulation of neuroendocrine differentiation in prostate cancer cells by GHRH and its blockade by GHRH antagonists.

Prostate cancer is the second leading cause of cancer-related deaths among men in developed countries. Neuroendocrine prostate cancer, in particular, is associated with an aggressive phenotype and a poor prognosis. Neuroendocrine cells produce and secrete peptide hormones and growth factors in a paracrine/autocrine manner which promote the progression of the disease. Recent studies have demonstrated that extracellular vesicles or exosomes are released by prostate cancer cells, supporting the spread of prostate cancer. Hence, the aim of this study was to investigate the effect of growth hormone-releasing hormone (GHRH) on neuroendocrine differentiation (NED) in the androgen-dependent prostate cancer cell line LNCaP and the molecular mechanisms underlying these effects. GHRH induced an increase in the percentage of neurite-bearing cells and in the protein levels of Neuron-Specific Enolase. Both effects were blocked by the GHRH receptor antagonist MIA-690. In addition, pretreatment of these cells with the calcium chelator BAPTA, the EGFR inhibitor AG-1478 or the HER2 inhibitor AG-825 reduced the effect of GHRH, suggesting that the GHRH-induced stimulation of NED involves calcium channel activation and EGFR/HER2 transactivation. Finally, PC3-derived exosomes led to an increase in NED, cell proliferation and cell adhesion. Altogether, these findings suggest that GHRH antagonists should be considered for in the management of neuroendocrine prostate cancer.

White matter connectomes at birth accurately predict cognitive abilities at age 2.

Cognitive ability is an important predictor of mental health outcomes that is influenced by neurodevelopment. Evidence suggests that the foundational wiring of the human brain is in place by birth, and that the white matter (WM) connectome supports developing brain function. It is unknown, however, how the WM connectome at birth supports emergent cognition. In this study, a deep learning model was trained using cross-validation to classify full-term infants (n = 75) as scoring above or below the median at age 2 using WM connectomes generated from diffusion weighted magnetic resonance images at birth. Results from this model were used to predict individual cognitive scores. We additionally identified WM connections important for classification. The model was also evaluated in a separate set of preterm infants (n = 37) scanned at term-age equivalent. Findings revealed that WM connectomes at birth predicted 2-year cognitive score group with high accuracy in both full-term (89.5%) and preterm (83.8%) infants. Scores predicted by the model were strongly correlated with actual scores (r = 0.98 for full-term and r = 0.96 for preterm). Connections within the frontal lobe, and between the frontal lobe and other brain areas were found to be important for classification. This work suggests that WM connectomes at birth can accurately predict a child's 2-year cognitive group and individual score in full-term and preterm infants. The WM connectome at birth appears to be a useful neuroimaging biomarker of subsequent cognitive development that deserves further study.

A deep neural network to assess spontaneous pain from mouse facial expressions.

Grimace scales quantify characteristic facial expressions associated with spontaneous pain in rodents and other mammals. However, these scales have not been widely adopted largely because of the time and effort required for highly trained humans to manually score the images. Convoluted neural networks were recently developed that distinguish individual humans and objects in images. Here, we trained one of these networks, the InceptionV3 convolutional neural net, with a large set of human-scored mouse images. Output consists of a binary pain/no-pain assessment and a confidence score. Our automated Mouse Grimace Scale integrates these two outputs and is highly accurate (94%) at assessing the presence of pain in mice across different experimental assays. In addition, we used a novel set of "pain" and "no pain" images to show that automated Mouse Grimace Scale scores are highly correlated with human scores (Pearson's r = 0.75). Moreover, the automated Mouse Grimace Scale classified a greater proportion of images as "pain" following laparotomy surgery when compared to animals receiving a sham surgery or a post-surgical analgesic. Together, these findings suggest that the automated Mouse Grimace Scale can eliminate the need for tedious human scoring of images and provide an objective and rapid way to quantify spontaneous pain and pain relief in mice.

Growth hormone-releasing hormone receptor antagonists modify molecular machinery in the progression of prostate cancer.

BACKGROUND: Therapeutic strategies should be designed to transform aggressive prostate cancer phenotypes to a chronic situation. To evaluate the effects of the new growth hormone-releasing hormone receptor (GHRH-R) antagonists: MIA-602, MIA-606, and MIA-690 on processes associated with cancer progression as cell proliferation, adhesion, migration, and angiogenesis. METHODS: We used three human prostate cell lines (RWPE-1, LNCaP, and PC3). We analyzed several molecules such as E-cadherin, ß-catenin, Bcl2, Bax, p53, MMP2, MMP9, PCNA, and VEGF and signaling mechanisms that are involved on effects exerted by GHRH-R antagonists. RESULTS: GHRH-R antagonists decreased cell viability and provoked a reduction in proliferation in LNCaP and PC3 cells. Moreover, GHRH-R antagonists caused a time-dependent increase of cell adhesion in all three cell lines and retarded the wound closure with the highest value with MIA-690 in PC3 cells. GHRH-R antagonists also provoked a large number of cells in SubG0 phase revealing an increase in apoptotic cells in PC3 cell line. CONCLUSIONS: Taken all together, GHRH-R antagonists of the MIAMI series appear to be inhibitors of tumor progression in prostate cancer and should be considered for use in future therapeutic strategies on this malignancy.

Systematic Review of Urologic Outcomes from Tethered Cord Release in Occult Spinal Dysraphism in Children.

Tethered cord syndrome describes a condition of multisystem end organ dysfunction due to fixation of the spinal cord. This systematic review focuses on the closed skin variant of this condition, occult spinal dysraphism. The embryology, pathophysiology, presentation, and classification of occult spinal dysraphism are explained to develop a simple framework for discussions regarding this often confusing condition. Following Preferred Reporting Items for Systematic Review and Meta-Analyses (PRISMA) guidelines, we synthesized urologic outcome data after tethered cord release in children from 17 studies performed over the past 25 years. These results prompted several conclusions. First, the different subgroups and different nomenclature of tethered cord syndrome are often confused, making interpretation of results difficult. Second, untethering has a positive effect on urologic symptoms and urodynamics parameters. Third, timing of untethering is important: early intervention prevents significant long-term traction aiming to avoid irreversible neurologic damage. Fourth, pediatric urologists and neurosurgeons have an important role in diagnosing and treating this condition and should work closely as part of a multidisciplinary team.

Growth hormone-releasing hormone antagonists abolish the transactivation of human epidermal growth factor receptors in advanced prostate cancer models.

Growth hormone-releasing hormone (GHRH) and its receptors have been implicated in a variety of cellular phenotypes related with tumorigenesis process. Human epidermal growth factor receptor family members (HER) such as EGFR and HER2 are involved in mitogenic signaling pathways implicated in the progression of prostate cancer. We analyzed the cross-talk between GHRH and EGF receptors in prostate cancer. The effects of GHRH in HER signaling were evaluated on human androgen-independent PC3 prostate cancer cells in vitro and GHRH antagonist in vitro and in nude mice xenografts of PC3 prostate cancer. Time-course studies indicated that GHRH had a stimulatory activity on both the expression of EGFR and HER2. GHRH analogues, JMR-132 and JV-1-38, endowed with antagonistic activity for GHRH receptors, abrogated the response to GHRH in PC3 cells. GHRH stimulated a rapid ligand-independent activation of EGFR and HER2 involving at least cAMP/PKA and Src family signaling pathways. GHRH also stimulated a slow ligand-dependent activation of EGFR and HER2 involving an extracellular pathway with an important role for ADAM. Preliminary results also revealed an increase of mRNA for GHRH and GHRH receptor induced by EGF. The inhibition of tumor growth, in vivo, was associated with a substantial reduction in the expression of mRNA and protein levels of EGFR and HER2 in the tumors. GHRH antagonist JV-1-38, significantly decreased the phosphorylated Src levels. The cross-talk between HER and GHRH-R may be impeded by combining drugs acting upon GHRH receptors and HER family members in human advanced prostate cancer.

Deep learning to estimate gestational age from fly-to cineloop videos: A novel approach to ultrasound quality control.

OBJECTIVE: Low-cost devices have made obstetric sonography possible in settings where it was previously unfeasible, but ensuring quality and consistency at scale remains a challenge. In the present study, we sought to create a tool to reduce substandard fetal biometry measurement while minimizing care disruption. METHODS: We developed a deep learning artificial intelligence (AI) model to estimate gestational age (GA) in the second and third trimester from fly-to cineloops-brief videos acquired during routine ultrasound biometry-and evaluated its performance in comparison to expert sonographer measurement. We then introduced random error into fetal biometry measurements and analyzed the ability of the AI model to flag grossly inaccurate measurements such as those that might be obtained by a novice. RESULTS: The mean absolute error (MAE) of our model (±standard error) was 3.87 ± 0.07 days, compared to 4.80 ± 0.10 days for expert biometry (difference -0.92 days; 95% CI: -1.10 to -0.76). Based on simulated novice biometry with average absolute error of 7.5%, our model reliably detected cases where novice biometry differed from expert biometry by 10 days or more, with an area under the receiver operating characteristics curve of 0.93 (95% CI: 0.92, 0.95), sensitivity of 81.0% (95% CI: 77.9, 83.8), and specificity of 89.9% (95% CI: 88.1, 91.5). These results held across a range of sensitivity analyses, including where the model was provided suboptimal truncated fly-to cineloops. CONCLUSIONS: Our AI model estimated GA more accurately than expert biometry. Because fly-to cineloop videos can be obtained without any change to sonographer workflow, the model represents a no-cost guardrail that could be incorporated into both low-cost and commercial ultrasound devices to prevent reporting of most gross GA estimation errors.

Safety and Pharmacokinetics of a Combined Antioxidant Therapy against Myocardial Reperfusion Injury: A Phase I Randomized Clinical Trial in Healthy Humans.

Myocardial reperfusion injury (MRI) accounts for up to 50% of the final size in acute myocardial infarction and other conditions associated with ischemia-reperfusion. Currently, there is still no therapy to prevent MRI, but it is well known that oxidative stress has a key role in its mechanism. We previously reduced MRI in rats through a combined antioxidant therapy (CAT) of ascorbic acid, N-acetylcysteine, and deferoxamine. This study determines the safety and pharmacokinetics of CAT in a Phase I clinical trial. Healthy subjects (n = 18) were randomized 2:1 to CAT or placebo (NaCl 0.9% i.v.). Two different doses/infusion rates of CATs were tested in a single 90-minute intravenous infusion. Blood samples were collected at specific times for 180 minutes to measure plasma drug concentrations (ascorbic acid, N-acetylcysteine, and deferoxamine) and oxidative stress biomarkers. Adverse events were registered during infusion and followed for 30 days. Both CAT1 and CAT2 significantly increased the CAT drug concentrations compared to placebo (P < .05). Most of the pharmacokinetic parameters were similar between CAT1 and CAT2. In total, 6 adverse events were reported, all nonserious and observed in CAT1. The ferric-reducing ability of plasma (an antioxidant biomarker) increased in both CAT groups compared to placebo (P < .001). The CAT is safe in humans and a potential treatment for patients with acute myocardial infarction undergoing reperfusion therapy.

Vasoactive intestinal peptide (VIP) inhibits human renal cell carcinoma proliferation.

Clear renal cell carcinoma (cRCC) is an aggressive and fatal neoplasm. The present work was undertaken to investigate the antiproliferative potential of vasoactive intestinal peptide (VIP) exposure on non-tumoral (HK2) and tumoral (A498, cRCC) human proximal tubular epithelial cell lines. Reverse transcription and semiquantitative PCR was used at the VIP mRNA level whereas enzyme immunoanalysis was performed at the protein level. Both renal cell lines expressed VIP as well as VIP/pituitary adenylate cyclase-activating peptide (VPAC) receptors whereas only HK2 cells expressed formyl peptide receptor-like 1 (FPRL-1). Receptors were functional, as shown by VIP stimulation of adenylyl cyclase activity. Treatment with 0.1µM VIP (24h) inhibited proliferation of A498 but not HK2 cells as based on a reduction in the incorporation of [(3)H]-thymidine and BrdU (5'-Br-2'-deoxyuridine), PCNA (proliferating-cell nuclear antigen) expression and STAT3 (signal transducer and activator of transcription 3) expression and activation. VPAC(1)-receptor participation was established using JV-1-53 antagonist and siRNA transfection. Growth-inhibitory response to VIP was related to the cyclic adenosine monophosphate (cAMP)/exchange protein directly activated by cAMP (EPAC)/phosphoinositide 3-kinase (PI3-K) signaling systems as shown by studies on adenylate cyclase stimulation, and using the EPAC-specific compound 8CPT-2Me-cAMP and specific kinase inhibitors such as H89, wortmannin and PD98059. The efficacy of VIP on the prevention of tumor progression was confirmed in vivo using xenografted athymic mouse. These actions support a potential role of this peptide and its agonists in new therapies for cRCC.

Inhibitory effects of antagonists of growth hormone-releasing hormone on growth and invasiveness of PC3 human prostate cancer.

New approaches are needed to the therapy of advanced prostate cancer. This study determined the effect of growth hormone-releasing hormone (GHRH) antagonists, JMR-132 and JV-1-38 on growth of PC3 tumors as well as on angiogenesis and metastasis through the evaluation of various factors that contribute largely to the progression of prostate cancer. Human PC3 androgen-independent prostate cancer cells were injected subcutaneously into nude mice. The treatment with JMR-132 (10 µg/day) or JV-1-38 (20 µg/day) lasted 41 days. We also evaluated the effects of JMR-132 and JV-1-38 on proliferation, cell adhesion and migration in PC-3 cells in vitro. Several techniques (Western blot, reverse transcription polymerase chain reaction, immunohistochemistry, ELISA and zymography) were used to evaluate the expression levels of GHRH receptors and its splice variants, GHRH, vascular endothelial growth factor (VEGF), hypoxia inducible factor (HIF)-1α, metalloproteinases (MMPs) -2 and -9, ß-catenin and E-cadherin. GHRH antagonists suppressed the proliferation of PC-3 cells in vitro and significantly inhibited growth of PC3 tumors. After treatment with these analogues, we found an increase in expression of GHRH receptor accompanied by a decrease of GHRH levels, a reduction in both VEGF and HIF-1α expression and in active forms of MMP-2 and MMP-9, a significant increase in levels of membrane-associated ß-catenin and a significant decline in E-cadherin. These results support that the blockade of GHRH receptors can modulate elements involved in angiogenesis and metastasis. Consequently, GHRH antagonists could be considered as suitable candidates for therapeutic trials in the management of androgen-independent prostate cancer.

Cardioprotection against ischaemia/reperfusion by vitamins C and E plus n-3 fatty acids: molecular mechanisms and potential clinical applications.

The role of oxidative stress in ischaemic heart disease has been thoroughly investigated in humans. Increased levels of ROS (reactive oxygen species) and RNS (reactive nitrogen species) have been demonstrated during ischaemia and post-ischaemic reperfusion in humans. Depending on their concentrations, these reactive species can act either as benevolent molecules that promote cell survival (at low-to-moderate concentrations) or can induce irreversible cellular damage and death (at high concentrations). Although high ROS levels can induce NF-κB (nuclear factor κB) activation, inflammation, apoptosis or necrosis, low-to-moderate levels can enhance the antioxidant response, via Nrf2 (nuclear factor-erythroid 2-related factor 2) activation. However, a clear definition of these concentration thresholds remains to be established. Although a number of experimental studies have demonstrated that oxidative stress plays a major role in heart ischaemia/reperfusion pathophysiology, controlled clinical trials have failed to prove the efficacy of antioxidants in acute or long-term treatments of ischaemic heart disease. Oral doses of vitamin C are not sufficient to promote ROS scavenging and only down-regulate their production via NADPH oxidase, a biological effect shared by vitamin E to abrogate oxidative stress. However, infusion of vitamin C at doses high enough to achieve plasma levels of 10 mmol/l should prevent superoxide production and the pathophysiological cascade of deleterious heart effects. In turn, n-3 PUFA (polyunsaturated fatty acid) exposure leads to enhanced activity of antioxidant enzymes. In the present review, we present evidence to support the molecular basis for a novel pharmacological strategy using these antioxidant vitamins plus n-3 PUFAs for cardioprotection in clinical settings, such as post-operative atrial fibrillation, percutaneous coronary intervention following acute myocardial infarction and other events that are associated with ischaemia/reperfusion.

Assessment of systemic AAV-microdystrophin gene therapy in the GRMD model of Duchenne muscular dystrophy.

Duchenne muscular dystrophy (DMD) is a progressive muscle wasting disease caused by the absence of dystrophin, a membrane-stabilizing protein encoded by the DMD gene. Although mouse models of DMD provide insight into the potential of a corrective therapy, data from genetically homologous large animals, such as the dystrophin-deficient golden retriever muscular dystrophy (GRMD) model, may more readily translate to humans. To evaluate the clinical translatability of an adeno-associated virus serotype 9 vector (AAV9)-microdystrophin (µDys5) construct, we performed a blinded, placebo-controlled study in which 12 GRMD dogs were divided among four dose groups [control, 1 × 1013 vector genomes per kilogram (vg/kg), 1 × 1014 vg/kg, and 2 × 1014 vg/kg; n = 3 each], treated intravenously at 3 months of age with a canine codon-optimized microdystrophin construct, rAAV9-CK8e-c-µDys5, and followed for 90 days after dosing. All dogs received prednisone (1 milligram/kilogram) for a total of 5 weeks from day -7 through day 28. We observed dose-dependent increases in tissue vector genome copy numbers; µDys5 protein in multiple appendicular muscles, the diaphragm, and heart; limb and respiratory muscle functional improvement; and reduction of histopathologic lesions. As expected, given that a truncated dystrophin protein was generated, phenotypic test results and histopathologic lesions did not fully normalize. All administrations were well tolerated, and adverse events were not seen. These data suggest that systemically administered AAV-microdystrophin may be dosed safely and could provide therapeutic benefit for patients with DMD.

CONTINUITY: CONnectivity Tool with INtegration of sUbcortical regions, regIstration and visualization of TractographY.

In this work, we present CONTINUITY, a novel, open-source interactive computation and visualization tool for brain connectome data. The connectome processing pipeline performs surface based processing as the main mode of operation. The automated processing includes structural-to-diffusion image co-registration, surface reconstruction for subcortical structures, as well as fiber tractography. The tool supports 3 different probabilistic methods of tractography offered by the tractography frameworks in FSL, MRtrix and DIPY. All methods employ brain and subcortical surfaces as seeds to initialize the tractography algorithms. CONTINUITY implements a friendly Graphical User Interface (GUI) to make the workflow accessible for nontechnical users. Additionally, it offers the possibility to visualize the results of the brain connectome in several interactive plot types such as a hierarchical edge bundling circle plot and over 2D/3D brain templates. This visualization tool can also be applied to connectome matrices computed with other tools and pipelines.

Effect of goal-directed haemodynamic therapy guided by non-invasive monitoring on perioperative complications in elderly hip fracture patients within an enhanced recovery pathway.

BACKGROUND: Goal-directed haemodynamic therapy (GDHT) has been shown to reduce morbidity and mortality in high-risk surgical patients. However, there is little evidence of its efficacy in patients undergoing hip fracture surgery. This study aims to evaluate the effect of GDHT guided by non-invasive haemodynamic monitoring on perioperative complications in patients undergoing hip fracture surgery. METHODS: Patients > 64 years undergoing hip fracture surgery within an enhanced recovery pathway (ERP) were enrolled in this single-centre, non-randomized, intervention study with a historical control group and 12-month follow-up. Exclusion criteria were patients with pathological fractures, traffic-related fractures and refractures. Control group (CG) patients received standard care treatment. Intervention group (IG) patients received a GDHT protocol based on achieving an optimal stroke volume, in addition to a systolic blood pressure > 90 mmHg and an individualized cardiac index. No changes were made between groups in the ERP during the study period. Primary outcome was percentage of patients who developed intraoperative haemodynamic instability. Secondary outcomes were intraoperative arrhythmias, postoperative complications (cardiovascular, respiratory, infectious and renal complications), administered fluids, vasopressor requirements, perioperative transfusion, length of hospital stay, readmission and 1-year survival. RESULTS: In total, 551 patients (CG=272; IG=279) were included. Intraoperative haemodynamic instability was lower in the IG (37.5% vs 28.0%; p=0.017). GDHT patients had fewer postoperative cardiovascular (18.8% vs 7.2%; p < 0.001), respiratory (15.1% vs 3.6%; p<0.001) and infectious complications (21% vs 3.9%; p<0.001) but not renal (12.1% vs 33.7%; p<0.001). IG patients had less vasopressor requirements (25.5% vs 39.7%; p<0.001) and received less fluids [2.600 ml (IQR 1700 to 2700) vs 850 ml (IQR 750 to 1050); p=0.001] than control group. Fewer patients required transfusion in GDHT group (73.5% vs 44.4%; p<0.001). For IG patients, median length of hospital stay was shorter [11 days (IQR 8 to 16) vs 8 days; (IQR 6 to 11) p < 0.001] and 1-year survival higher [73.4% (95%CI 67.7 to 78.3 vs 83.8% (95%CI 78.8 to 87.7) p<0.003]. CONCLUSIONS: The use of GDHT decreases intraoperative complications and postoperative cardiovascular, respiratory and infectious but not postoperative renal complications. This strategy was associated with a shorter hospital stay and increased 1-year survival. TRIAL REGISTRATION: ClinicalTrials.gov NCT02479321 .

AI Estimation of Gestational Age from Blind Ultrasound Sweeps in Low-Resource Settings.

BACKGROUND: Ultrasound is indispensable to gestational age estimation and thus to quality obstetrical care, yet high equipment cost and the need for trained sonographers limit its use in low-resource settings. METHODS: From September 2018 through June 2021, we recruited 4695 pregnant volunteers in North Carolina and Zambia and obtained blind ultrasound sweeps (cineloop videos) of the gravid abdomen alongside standard fetal biometry. We trained a neural network to estimate gestational age from the sweeps and, in three test data sets, assessed the performance of the artificial intelligence (AI) model and biometry against previously established gestational age. RESULTS: In our main test set, the mean absolute error (MAE) (±SE) was 3.9±0.12 days for the model versus 4.7±0.15 days for biometry (difference, -0.8 days; 95% confidence interval [CI], -1.1 to -0.5; P<0.001). The results were similar in North Carolina (difference, -0.6 days; 95% CI, -0.9 to -0.2) and Zambia (-1.0 days; 95% CI, -1.5 to -0.5). Findings were supported in the test set of women who conceived by in vitro fertilization (MAE of 2.8±0.28 vs. 3.6±0.53 days for the model vs. biometry; difference, -0.8 days; 95% CI, -1.7 to 0.2) and in the set of women from whom sweeps were collected by untrained users with low-cost, battery-powered devices (MAE of 4.9±0.29 vs. 5.4±0.28 days for the model vs. biometry; difference, -0.6; 95% CI, -1.3 to 0.1). CONCLUSIONS: When provided blindly obtained ultrasound sweeps of the gravid abdomen, our AI model estimated gestational age with accuracy similar to that of trained sonographers conducting standard fetal biometry. Model performance appears to extend to blind sweeps collected by untrained providers in Zambia using low-cost devices. (Funded by the Bill and Melinda Gates Foundation.).

Performance Enhanced Ultrasound Probe Tracking With a Hemispherical Marker Rigid Body.

Among tracking techniques applied in the 3-D freehand ultrasound (US), the camera-based tracking method is relatively mature and reliable. However, constrained by manufactured marker rigid bodies, the US probe is usually limited to operate within a narrow rotational range before occlusion issues affect accurate and robust tracking performance. Thus, this study proposed a hemispherical marker rigid body to hold passive noncoplanar markers so that the markers could be identified by the camera, mitigating self-occlusion. The enlarged rotational range provides greater freedom for sonographers while performing examinations. The single-axis rotational and translational tracking performances of the system, equipped with the newly designed marker rigid body, were investigated and evaluated. Tracking with the designed marker rigid body achieved high tracking accuracy with 0.57° for the single-axis rotation and 0.01 mm for the single-axis translation for sensor distance between 1.5 and 2 m. In addition to maintaining high accuracy, the system also possessed an enhanced ability to capture over 99.76% of the motion data in the experiments. The results demonstrated that with the designed marker rigid body, the missing data were remarkably reduced from over 15% to less than 0.5%, which enables interpolation in the data postprocessing. An imaging test was further conducted, and the volume reconstruction of a four-month fetal phantom was demonstrated using the motion data obtained from the tracking system.

An automated framework for image classification and segmentation of fetal ultrasound images for gestational age estimation.

Accurate assessment of fetal gestational age (GA) is critical to the clinical management of pregnancy. Industrialized countries rely upon obstetric ultrasound (US) to make this estimate. In low- and middle- income countries, automatic measurement of fetal structures using a low-cost obstetric US may assist in establishing GA without the need for skilled sonographers. In this report, we leverage a large database of obstetric US images acquired, stored and annotated by expert sonographers to train algorithms to classify, segment, and measure several fetal structures: biparietal diameter (BPD), head circumference (HC), crown rump length (CRL), abdominal circumference (AC), and femur length (FL). We present a technique for generating raw images suitable for model training by removing caliper and text annotation and describe a fully automated pipeline for image classification, segmentation, and structure measurement to estimate the GA. The resulting framework achieves an average accuracy of 93% in classification tasks, a mean Intersection over Union accuracy of 0.91 during segmentation tasks, and a mean measurement error of 1.89 centimeters, finally leading to a 1.4 day mean average error in the predicted GA compared to expert sonographer GA estimate using the Hadlock equation.

FlyBy CNN: A 3D surface segmentation framework.

In this paper, we present FlyBy CNN, a novel deep learning based approach for 3D shape segmentation. FlyByCNN consists of sampling the surface of the 3D object from different view points and extracting surface features such as the normal vectors. The generated 2D images are then analyzed via 2D convolutional neural networks such as RUNETs. We test our framework in a dental application for segmentation of intra-oral surfaces. The RUNET is trained for the segmentation task using image pairs of surface features and image labels as ground truth. The resulting labels from each segmented image are put back into the surface thanks to our sampling approach that generates 1-1 correspondence of image pixels and triangles in the surface model. The segmentation task achieved an accuracy of 0.9.