RESUMO
Our study aims to evaluate the potential of a deep learning (DL) algorithm for differentiating the signal intensity of bone marrow between osteomyelitis (OM), Charcot neuropathic osteoarthropathy (CNO), and trauma (TR). The local ethics committee approved this retrospective study. From 148 patients, segmentation resulted in 679 labeled regions for T1-weighted images (comprising 151 CNO, 257 OM, and 271 TR) and 714 labeled regions for T2-weighted images (consisting of 160 CNO, 272 OM, and 282 TR). We employed both multi-class classification (MCC) and binary-class classification (BCC) approaches to compare the classification outcomes of CNO, TR, and OM. The ResNet-50 and the EfficientNet-b0 accuracy values were computed at 96.2% and 97.1%, respectively, for T1-weighted images. Additionally, accuracy values for ResNet-50 and the EfficientNet-b0 were determined at 95.6% and 96.8%, respectively, for T2-weighted images. Also, according to BCC for CNO, OM, and TR, the sensitivity of ResNet-50 is 91.1%, 92.4%, and 96.6% and the sensitivity of EfficientNet-b0 is 93.2%, 97.6%, and 98.1% for T1, respectively. For CNO, OM, and TR, the sensitivity of ResNet-50 is 94.9%, 83.6%, and 97.9% and the sensitivity of EfficientNet-b0 is 95.6%, 85.2%, and 98.6% for T2, respectively. The specificity values of ResNet-50 for CNO, OM, and TR in T1-weighted images are 98.1%, 97.9%, and 94.7% and 98.6%, 97.5%, and 96.7% in T2-weighted images respectively. Similarly, for EfficientNet-b0, the specificity values are 98.9%, 98.7%, and 98.4% and 99.1%, 98.5%, and 98.7% for T1-weighted and T2-weighted images respectively. In the diabetic foot, deep learning methods serve as a non-invasive tool to differentiate CNO, OM, and TR with high accuracy.
RESUMO
OBJECTIVE: Magnesium sulfate (MgSO4) provides effective fetal neuroprotection. However, there is conflicting evidence regarding the association between antenatal MgSO4 exposure and patent ductus arteriosus (PDA). Thus, herein, we aimed to evaluate the association between antenatal MgSO4 exposure and PDA. STUDY DESIGN: Preterm infants born between 240/7 and 316/7 weeks of gestation were included in this retrospective study. Infants who died within the first 72 hours of life and those with significant congenital anomalies were excluded from the study. Echocardiographic and clinical assessment parameters were used to define PDA and hemodynamically significant PDA (hsPDA). Treatments were planned according to the standard protocols of the unit. The following data were collected from hospital medical records: perinatal characteristics, neonatal outcomes, detailed PDA follow-up findings, and maternal characteristics including MgSO4 exposure and doses. RESULTS: Of the 300 included infants, 98 (32.6%) were exposed to antenatal MgSO4. hsPDA rates were similar in the infants exposed and not exposed to antenatal MgSO4, when adjusted for antenatal steroid administration, gestational age, and birth weight (OR: 1.6, 95% CI: 0.849-3.118, p = 0.146). The rates of PDA ligation and open PDA at discharge were similar between the groups. A cumulative MgSO4 dose of >20 g was associated with an increased risk of hsPDA (crude OR: 2.476, 95% CI: 0.893-6.864, p = 0.076; adjusted OR: 3.829, 95% CI: 1.068-13.728, p = 0.039). However, the cumulative dose had no effect on the rates of PDA ligation or open PDA at discharge. Rates of prematurity-related morbidities and mortality were similar between the groups. CONCLUSION: Although antenatal MgSO4 exposure may increase the incidence of hsPDA, it may not affect the rates of PDA ligation or open PDA at discharge. Further studies are required to better evaluate the dose-dependent outcomes and identify the MgSO4 dose that not only provides neuroprotection but also has the lowest risk of adverse effects. KEY POINTS: · Antenatal exposure of MgSO4 may cause PDA.. · Antenatal MgSO4 exposure may not increase the rates of PDA ligation or open PDA at discharge.. · Further studies are required to better evaluate the dose-dependent outcomes and optimal MgSO4 dose..
