Background: Traditional methods for calculating perfusion parameter maps such as Ktrans require significant computational resources and time, leading to errors due to the variety of analysis models and the difficulty in estimating the arterial input function (AIF). Thus, it is difficult to apply Ktrans measurements to clinical diagnosis. The purpose of this study was to investigate whether deep learning (DL) techniques can synthesize Ktrans perfusion parameter maps from contrast-enhanced magnetic resonance (MR) images.
Methods: A pix2pix-based conditional generative adversarial networks (cGAN) architecture was proposed to generate breast Ktrans perfusion maps. The peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) were used to evaluate the quality of the synthetic Ktrans maps. Two experienced radiologists were tasked with distinguishing between real and synthesized Ktrans maps. The Ktrans values of the tumor regions in the synthetic and real Ktrans maps were subjected to Pearson correlation analysis and Bland-Altman analysis.
Results: The best performance was obtained when synthesizing Ktrans maps using the pix2pix model with spectral normalization (SN) and a local discriminator (LD) (PSNR of 15.167±0.125 and SSIM of 0.690±0.014 for synthesizing Ktrans maps from contrast-enhanced MR images). The Ktrans values of the tumor regions in the synthetic and real Ktrans maps showed a strong correlation (r=0.82), allowed for significant differentiation between benign and malignant tumors (P<0.001), and were not reliably distinguished from real maps by radiologists (accuracy: 41.18%).
Conclusions: The synthesis of breast Ktrans perfusion parameter maps from dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is enabled by the proposed DL-based method. This provides a new feasible solution for the generation of Ktrans.
Background: Stereotactic body radiation therapy (SBRT) is an effective treatment for pulmonary oligometastases. Understanding the temporal evolution of computed tomography (CT) imaging features post-SBRT is crucial for optimizing patient management and improving prognostic outcomes. This study aimed to characterize the CT imaging evolution of pulmonary oligometastatic nodules following SBRT and evaluate the prognostic value of early tumor response for local control.
Methods: This multicenter retrospective study analyzed 246 pulmonary oligometastatic nodules in 191 patients treated with SBRT. We evaluated clinical characteristics, biologically effective dose (BED10), and CT imaging features, categorized by recurrence within 2 years. Tumor response at 1-month follow-up was classified as favorable [partial response (PR) or complete response (CR)] or bad [stable disease (SD) or progressive disease (PD)]. Statistical analyses included t-tests, Chi-squared tests, and Kaplan-Meier analysis.
Results: Significant predictors of non-recurrence included tumor diameter ≤20 mm (P<0.001), BED10 ≥100 Gy (P=0.022), and favorable early tumor response (P=0.001). The 2-year local control rate was 87.8% overall, 95.0% for nodules with a favorable early response, and 81.1% for those with a bad response. CT imaging showed that non-recurrent nodules typically exhibit early significant shrinkage, transient loose consolidation with ground-glass opacity (GGO), and eventual stable fibrosis, whereas recurrent nodules progress to mass-like consolidation.
Conclusions: Favorable early response on 1-month follow-up CT, tumor diameter ≤20 mm, and BED10 ≥100 Gy are strong predictors of local control. Integrating early CT-based assessment into routine follow-up may improve recurrence detection and guide timely intervention.
Background: Axillary lymph node metastasis (ALNM) is pivotal for breast cancer treatment and prognosis. Invasive tests may carry complications, while non-invasive methods like physical examination have poor accuracy. Existing AI-based models rely mostly on tumor-centric features. However, metastatic lymph nodes show neoangiogenesis and altered hemodynamics, leading to time-intensity curve (TIC) profiles similar to those of adjacent vessels. This study aimed to quantify these hemodynamic disparities from dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) and enhance ALNM prediction accuracy.
Methods: A retrospective study included 186 patients (92 ALNM+, 94 ALNM-). Axillary vessels and lymph nodes were semi-automatically segmented via Hessian matrix algorithms. Four TIC-derived features [lymph-node TIC area (LNTICA), the difference in TIC area between the vessel ROI and lymph-node ROI (DIFF), non-negative area difference (NON-NEG DIFF), ratio of area difference to lymph node TIC area (RATIO TO LYMPH)] were extracted. ResNet50 extracted image features, and a Stacking framework integrated image, clinical, and TIC features, using support vector machine (SVM) and nomogram as classifiers. Statistical tests (F-test, t-test, and Kolmogorov-Smirnov test) validated feature discriminability.
Results: All TIC features differed significantly between groups (P<0.001 for F-test, P<0.001 for t-test/Kolmogorov-Smirnov test for NON-NEG DIFF and RATIO TO LYMPH). RATIO TO LYMPH (mean: 0.11 vs. 0.36) showed optimal discriminability. Integrating TIC features improved area under the receiver operating characteristic curve (AUC): SVM (0.876→0.914) and nomogram (0.902→0.941) in the test set. SHapley Additive exPlanations (SHAP) analysis confirmed RATIO TO LYMPH as one of the top predictive features.
Conclusions: Lymph node-vessel hemodynamic disparities are robust ALNM biomarkers. Integrating these TIC-derived features with clinical and image data significantly enhances prediction accuracy, providing a non-invasive tool for clinical decision-making.
Background: The early diagnosis of abnormalities in transplanted kidney function is crucial for timely intervention in transplant patients. Non-invasive tests play a key role in this process. This study aimed to explore the value of blood oxygenation level-dependent (BOLD) and arterial spin labeling (ASL) techniques, based on magnetic resonance angiography (MRA) examination, in evaluating early renal allograft function.
Methods: A total of 68 consecutive renal transplant recipients were prospectively recruited. Of them, 10 were excluded due to magnetic resonance imaging (MRI) contraindications, hydronephrosis, and renal artery stenosis. Finally, 58 patients were included. The recipients were separated into three groups based on their estimated glomerular filtration rate (eGFR): Group A, recipients with good renal allograft function (eGFR ≥60 mL/min/1.73 m2); Group B, recipients with mild-to-moderate impaired renal allograft function (30≤ eGFR <60 mL/min/1.73 m2); Group C, recipients with severe renal allograft function (eGFR <30 mL/min/1.73 m2). Some patients underwent biopsy. All patients underwent ASL, BOLD, and renal-MRA to assess the anastomotic status of the grafted renal artery and to analyze renal blood flow (RBF) and the apparent relaxation rate (R2*).
Results: A total of 58 patients (Group A, 29 cases; Group B, 18 cases; and Group C, 11 cases) were included in this study. Groups B and C presented with significantly decreased RBF as compared with Group A (259.74±47.52 vs. 166.50±19.79 and 112.76±32.08 mL/100 g/min). R2* decreased in Group B (cortical/medullary: 10.503±1.136/11.609±1.665 sec-1) and Group C (cortical/medullary: 9.471±0.997/10.785±1.114 sec-1), compared with Group A (cortical/medullary: 10.933±0.996/12.689±1.348 sec-1). Correlation analysis revealed that cortical RBF, cortical R2*, and medullary R2* were positively correlated with eGFR (r=0.877, 0.536, and 0.359, respectively). The higher area under the curve (AUC) of BOLD and ASL for distinguishing Group A from Group B, Group B from Group C, and Group A from Group C were 0.973 [95% confidence interval (CI): 0.936-1.000; P<0.001], 0.914 (95% CI: 0.753-1.000; P<0.001), and 0.994 (95% CI: 0.977-1.000; P<0.001), respectively, exceeding the performance of BOLD alone.
Conclusions: BOLD and ASL can evaluate the different functional transplanted kidneys' oxygenation status and perfusion level. ASL demonstrates superior diagnostic efficacy compared to BOLD. BOLD combined with ASL has high value in identifying different transplanted kidney functions in the early stage.
Background: Valve-sparing root replacement (VSRR) prevents prosthesis-related complications in aortic root aneurysms but lacks objective feasibility criteria. Cusp prolapse frequently coexists with aortic root aneurysms, but its effect on VSRR outcomes remains unclear. We characterized prolapse mechanisms using three-dimensional (3D) transesophageal echocardiography (TEE) and examined the correlation between imaging features and surgical success as well as midterm outcomes.
Methods: This retrospective cohort study analyzed the data of 203 consecutive patients considered for VSRR. Cusp prolapse was diagnosed and mechanistically classified using quantitative 3D TEE analysis. The intraoperative findings confirmed regurgitation mechanisms. The outcomes compared the native valve preservation rates, postoperative echocardiographic results, mortality, regurgitation recurrence, and reintervention between prolapse and non-prolapse groups over a median 41-month follow-up period.
Results: Among the 203 patients (mean age 48.0±13.7 years), 70 (34.5%) exhibited cusp prolapse. The predominant mechanism was disproportionate free margin (FM) elongation (64.3%). Surgical success was significantly lower in the prolapse group than the non-prolapse group (50.0% vs. 86.5%; P<0.001). Among the patients with cusp prolapse, prolapse mechanisms other than FM elongation, compared with FM elongation, were independently associated with unsuccessful VSRR [odds ratio (OR) =12.44; 95% confidence interval (CI): 3.42-45.24; P<0.001]. In addition, a reduced minimum geometric height was also independently associated with unsuccessful VSRR (OR =0.70; 95% CI: 0.50-0.97; P=0.035). There were no significant differences in the midterm outcomes between the prolapse and non-prolapse groups in terms of the echocardiographic parameters (P=0.373), mortality (P=0.581), regurgitation recurrence (P=0.769), or reintervention rates (P=0.580).
Conclusions: Cusp prolapse-driven by heterogeneous mechanisms-is prevalent in tricuspid aortic valve root aneurysms and reduces the likelihood of successful VSRR. Preoperative 3D TEE quantification of cusp pathology can aid in surgical planning. Despite lower preservation rates in prolapse patients, both groups achieved comparable midterm outcomes following judicious patient selection.
Background: Hyperthyroidism complicates approximately 2.4% of pregnancies and is associated with adverse outcomes such as preterm birth, placental abruption, and fetal demise. However, its specific effects on fetal cardiac structure and function remain poorly characterized. This study aimed to quantitatively assess the morphological and functional changes in the fetal heart associated with maternal hyperthyroidism using novel fetal heart quantification (HQ) technology.
Methods: In total, 282 pregnant women were enrolled in this prospective study, of whom 197 had healthy pregnancies and 85 had hyperthyroid pregnancies. All the participants underwent detailed fetal echocardiography using a GE Voluson E10 system. The fetal HQ analysis was used to evaluate cardiac geometry parameters, such as the global sphericity index (GSI) and ventricular dimensions, and functional parameters, such as global longitudinal strain (GLS) and fractional area change (FAC).
Results: Compared with the healthy controls, the fetuses in the hyperthyroidism group had a larger left ventricular (LV) systolic area (2.68±0.14 vs. 2.27±0.11 cm2, P<0.001) and right ventricular (RV) systolic area (3.23±0.31 vs. 2.74±0.23 cm2, P<0.001), as well as increased diastolic areas (LV diastolic area: 3.86±0.35 vs. 3.21±0.29 cm2; RV diastolic area: 4.16±0.38 vs. 3.63±0.30 cm2; both P<0.001). The fetuses in the hyperthyroidism group also showed altered cardiac geometry, including a lower GSI (1.19±0.11 vs. 1.24±0.16, P=0.009), and impaired systolic function reflected by less negative LV GLS values (-21.8%±6.2% vs. -23.4%±5.1%, P=0.024) and reduced LV FAC (37.3%±7.9% vs. 39.7%±8.5%, P=0.027). The correlation analyses suggested potential associations between maternal thyroid hormone levels and fetal cardiac parameters.
Conclusions: Maternal hyperthyroidism significantly affects fetal cardiac morphology and function. Fetal HQ provides valuable quantitative insights into these changes, supporting its clinical utility in the prenatal evaluation of at-risk pregnancies.
Background: Stack-of-spirals ultrashort echo time (spiral-UTE) has been reported to be feasible for lung imaging; however, the performance of free-breathing contrast-enhanced and unenhanced spiral-UTE (UTEe and UTEu) is still unknown. Therefore, this study aimed to evaluate their performance of lung imaging in patients with malignant tumors.
Methods: A total of 76 patients with malignancies suspected of pulmonary metastatic nodules were enrolled in free-breathing UTEe, UTEu and routine contrast-enhanced T1-weighted imaging [volumetric interpolated breath-hold examination (VIBE)] for lung follow-up. Two radiologists independently assessed the image quality, and qualitative analysis was scored via a 5-point scale (4, excellent; 0, unreadable) with respect to the visibility of fissures, airways and vessels; signal homogeneity; motion artifacts; lesion conspicuity; and overall image quality. Quantitative analysis included measurements of the apparent contrast-to-noise ratio (CNR) and apparent signal-to-noise ratio (SNR). Pulmonary nodules detected via magnetic resonance (MR) images were compared with those by computed tomography (CT) as the reference standard.
Results: Both UTEu and UTEe outperformed VIBE in all the qualitative metrics (P<0.001) and there was no significant difference between UTEu and UTEe (P>0.05) in those metrics. UTEe exhibited the best performance in depicting pulmonary vessels, achieving the highest apparent SNR and apparent CNR values. Among the 130 pulmonary nodules identified via CT, spiral-UTE had a sensitivity of 76.9% and a positive predictive value (PPV) of 99.0%, significantly outperforming VIBE (sensitivity of 47.7% and PPV of 95.4%). The detection rates for spiral-UTE were 90.0% for nodules larger than 5 mm, 98.5% for nodules larger than 7 mm and 100.0% for nodules larger than 10 mm.
Conclusions: Spiral-UTE demonstrated superior image quality and greater sensitivity for pulmonary nodule detection than breath-hold VIBE did. Both unenhanced and enhanced spiral-UTE showed comparable performance in nodule detection, highlighting its potential as a reliable imaging modality for patients with malignant tumors during follow-up imaging.
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：