Maternal pelvic anatomical changes during the second stage of labor (SSL) remain poorly understood because of the difficulty in visualizing internal structures in vivo. Mechanical models have attempted to predict these changes but lack real-time confirmation. This proof-of-concept study assessed the feasibility of using open-field magnetic resonance imaging (MRI) to visualize maternal and fetal structural movements during the SSL. Twenty-seven term pregnant women were recruited for an open-field MRI study at a single center. Each participant was scheduled for scans in a 1-T open magnet within 2 h before labor onset and again during the SSL. Owing to logistical constraints, seven patients underwent both pre-labor and intrapartum MRI. Qualitative assessments of intrapartum pelvic anatomy changes were performed and supplemented by basic quantitative measurements of pelvic dimensions. Intrapartum MRI was successfully performed in seven women (aged 23–34 years). All showed marked perineal expansion and deformation of the pelvic floor during fetal descent. The iliococcygeal portion of the levator ani flattened and reversed its curvature under fetal head pressure, corresponding to the perineal bulge. Posterior coccygeal deflection occurred in all the patients (mean coccyx–symphysis increase of 0.8 cm), along with vaginal canal distension. Six patients had a partially filled bladder, which was displaced cranially as the fetal head descended. No adverse events occurred during MRI acquisition. Open-field MRI during the SSL is technically feasible and provides novel real-time observations of pelvic floor adaptations to fetal descent. These findings improve the understanding of intrapartum pelvic mechanics but require confirmation in larger cohorts. Open MRI offers a way to observe directly how maternal pelvic structures adapt during childbirth in real time. This feasibility study’s insights are descriptive and hypothesis-generating, laying the groundwork for future research on protecting the pelvic floor during delivery rather than providing immediate clinical recommendations. By clarifying how maternal pelvic structures adapt to fetal descent, these MRI findings can inform strategies to minimize perineal trauma, guide interventions (e.g., episiotomy, not emptying the bladder before maternal efforts), and ultimately improve maternal postpartum pelvic floor health.
To determine whether quantitative radiomic features extracted from noncontrast postmortem computed tomography (PMCT) can reliably detect autopsy-confirmed myocardial infarction (MI), and to evaluate the diagnostic performance of machine-learning models for automated MI detection. We retrospectively analyzed 106 PMCT examinations (55 MI cases, 51 controls). The left ventricular myocardium was semiautomatically segmented, and radiomic features were extracted. After reproducibility filtering (intraclass correlation coefficient ≥ 0.75), redundancy reduction based on Spearman correlation (ρ > 0.8), and feature selection were performed within a nested stratified cross-validation framework, including no additional selection (N.S.), random forest (RF)-based ranking, and recursive feature elimination with logistic regression (RFE-LR). Seven supervised machine-learning classifiers were trained and evaluated using area under the receiver operating characteristic curve (AUROC) and other metrics. Logistic regression with N.S. achieved the highest performance, with a mean AUROC of 0.817 ± 0.12 (mean ± standard deviation), with accuracy 0.746 ± 0.05, sensitivity 0.764 ± 0.14, and specificity 0.724 ± 0.13. Support vector machines and RF with N.S. showed comparable performance (AUROC 0.814 ± 0.10 and 0.814 ± 0.08, respectively). Across most classifiers, RF-based and RFE-LR feature selection did not improve diagnostic performance compared with N.S. Four radiomic features were identified by both RF and RFE-LR, being selected in at least two outer cross-validation folds. Radiomics combined with machine learning demonstrated good performance for MI detection on noncontrast PMCT, emphasizing its potential as an objective, noninvasive tool for cause-of-death assessment, while suggesting a possible translational relevance for clinical contrast-free cardiac imaging.
Dark-field radiography allows the visualization of lung tissue changes associated with pulmonary emphysema. Simulations were used to investigate the impact of radiation dose reduction on the diagnostic accuracy of emphysema detection. Dark-field and attenuation chest radiographs acquired during an ongoing clinical study were used to simulate multiple low-dose counterparts corresponding to median effective doses between 7 and 18 µSv. All study participants had undergone a medically indicated chest computed tomography scan that showed either pulmonary emphysema or no lung pathologies. In a randomized reader study, three radiologists independently assessed the simulated low-dose dark-field and attenuation radiographs as well as the original images for the presence of emphysema. The area under the curves (AUC) of the receiver operating characteristics (ROC) were analyzed using Obuchowski’s method. ROC curves were also generated by using different values of the dark-field coefficient to differentiate between absent and at least mild emphysema. The original (full-dose) images and simulated low-dose images of 93 participants (57 males, 36 females) were included, with participants’ median age of 66 years (interquartile range 54 to 73 years). The radiologists’ ROC curves of the simulated low-dose images at 11 µSv (AUC = 0.84) did not differ significantly (p = 0.177) from the full-dose curve (AUC = 0.86). For all dose levels, the dark-field coefficient could distinguish between absent and at least mild emphysema with an AUC of 0.85. Radiation dose reduction in dark-field imaging for emphysema assessment might be feasible, with median effective doses potentially as low as 11 µSv.
To evaluate the image quality of a novel deep-learning iterative reconstruction (DLIR) algorithm combined with high-frequency kernels compared with iterative reconstruction (IR) algorithms through the assessment of the detectability of small high-contrast lesions. Three image-quality phantoms were scanned with doses from 0.8 to 15 mGy. Images were reconstructed using ASIR-V0, ASIR-V80, and DLIR (Low, Medium, High), with an edge-enhancing kernel for a chest protocol and a sharp kernel for a spine protocol. A dedicated cubic phantom was used to assess axial, longitudinal resolution, and noise power spectra. Contrast of calcium-based lesions of 3 and 5 mm in diameter was assessed at three concentrations (200, 400, and 800 mg/cc) using two anthropomorphic chest and abdominal phantoms. Detectability was evaluated using a non-prewhitening with eye filter model observer. In-plane spatial resolution was stable across DLIR strength levels and slightly better than ASIR-V0, while longitudinal resolution did not depend on algorithms. DLIR markedly reduced image noise, below ASIR-V80 for DLIR-High with both kernels. While IR preserved the contrast of lesions, it decreased with DLIR strength for the small lesion 200 mg/cc-3mm. The highest detectability was achieved with DLIR-High, except for the HA200-3mm below 3 mGy for the chest protocol and 7 mGy for the spine protocol. DLIR combined with high-frequency kernels reduced image noise while preserving spatial resolution and FBP-like noise texture, outperforming IR in detectability for most lesion sizes, concentrations, and dose levels. DLIR reduced contrast for small and low-concentration lesions, especially at low doses, which partially counterbalanced its detectability advantage over IR. The new deep-learning reconstruction combined with high-frequency kernels improves detection of small lesions in comparison with iterative reconstruction at standard doses, but very small or low-density lesions may appear less visible at lower dose levels.
Chest radiography provides limited precision of pleural effusion volume estimates. This study compares volume estimates from experienced radiologists and a multimodal artificial intelligence (AI) model, using computed tomography (CT)-derived volumetry as the reference standard. In this retrospective observational study, same-day chest CT and radiographs from adult patients with CT-confirmed pleural effusion (≥ 20 mL) were evaluated. Manually segmented pleural effusion volumes from CT served as the reference standard. Two board-certified radiologists independently estimated left and right pleural fluid volume on radiographs. A general-purpose multimodal AI model analyzed each radiograph using a standardized prompt and generated volume estimates for each hemithorax. Eighty-eight patients (72.0 ± 14.4 years (mean ± standard deviation); 56
