European Radiology Experimental最新文献

Background: Aging alters musculoskeletal structure and function, affecting muscle mass, composition, and strength, increasing the risk of falls and loss of independence in older adults. This study assessed cross-sectional area (CSA) and fat infiltration (FI) of six thigh muscles through a validated deep learning model. Gender differences and correlations between fat, muscle parameters, and age were also analyzed.

Methods: We retrospectively analyzed 141 participants (67 females, 74 males) aged 52-82 years. Participants underwent magnetic resonance imaging (MRI) scans of the right thigh and dual-energy x-ray absorptiometry to determine appendicular skeletal muscle mass index (ASMMI) and body fat percentage (FAT%). A deep learning-based application was developed to automate the segmentation of six thigh muscle groups.

Results: Deep learning model accuracy was evaluated using the "intersection over union" (IoU) metric, with average IoU values across muscle groups ranging from 0.84 to 0.99. Mean CSA was 10,766.9 mm² (females 8,892.6 mm², males 12,463.9 mm², p < 0.001). The mean FI value was 14.92% (females 17.42%, males 12.62%, p < 0.001). Males showed larger CSA and lower FI in all thigh muscles compared to females. Positive correlations were identified in females between the FI of posterior thigh muscle groups (biceps femoris, semimembranosus, and semitendinosus) and age (r or ρ = 0.35-0.48; p ≤ 0.004), while no significant correlations were observed between CSA, ASMMI, or FAT% and age.

Conclusion: Deep learning accurately quantifies muscle CSA and FI, reducing analysis time and human error. Aging impacts on muscle composition and distribution and gender-specific assessments in older adults is needed.

Relevance statement: Efficient deep learning-based MRI image segmentation to assess the composition of six thigh muscle groups in over 50 individuals revealed gender differences in thigh muscle CSA and FI. These findings have potential clinical applications in assessing muscle quality, decline, and frailty.

Key points: Deep learning model enhanced MRI segmentation, providing high assessment accuracy. Significant gender differences in cross-sectional area and fat infiltration across all thigh muscles were observed. In females, fat infiltration of the posterior thigh muscles was positively correlated with age.

Background: To determine changes in quantitative T1 relaxation times (qT1) in deep gray matter in patients recovered from coronavirus disease 2019 (COVID-19).

Methods: Unvaccinated COVID-19 participants ≥ 3 months after seropositivity and age- and sex-matched controls were examined using 3-T magnetic resonance imaging. Bilateral measures of thalamus, pallidum, putamen, caudate and accumbens nuclei, and hippocampus were extracted from qT1 maps after automated segmentation. Baseline characteristics and results of tests assessing neurological functions (standardized exam), ability to smell (4-Item Pocket Smell Test), depression (Beck Depression Inventory-II), sleepiness (Epworth Sleepiness Scale), sleep quality (Pittsburgh Sleep Quality Index), health-related quality of life (EQ-5D), and cognitive performance (Montreal Cognitive Assessment) were evaluated.

Results: One hundred forty-five subjects (median age, 46 years; 73 females) were included (11/2020-12/2021): 69 recovered after COVID-19 and 76 controls (age, p = 0.532; sex, p = 0.799), without significant differences in qT1 values overall (all p-values > 0.050). Subgroup analysis of participants aged ≥ 40 (age, p = 0.675; sex, p = 0.447) revealed higher qT1 values in previously hospitalized COVID-19 subjects (23/69) compared to controls (47/76) in left and right caudate nuclei (p = 0.009; p = 0.027), left accumbens nucleus (p = 0.017), right putamen (p = 0.041), and right hippocampus (p = 0.020). No correlations were found with macroscopic imaging findings, pre-existing conditions, time since COVID-19 diagnosis, inpatient treatment duration, or test results.

Conclusion: T1 mapping revealed microstructural changes in striatal and hippocampal regions of unvaccinated individuals aged ≥ 40 who recovered from moderate-to-severe COVID-19 during the pre-Omicron era.

Relevance statement: This study elucidates brain involvement following severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection, underscoring the need for further longitudinal analyses to assess the potential reversibility, stability or deterioration of these findings.

Key points: We hypothesized altered T1 relaxation times in deep gray matter after COVID-19. Unvaccinated participants ≥ 40 years exhibited higher striatal, hippocampal qT1 after moderate-to-severe COVID-19. No qT1 correlations were found with hospitalization duration, pre-existing conditions, or neuro-(psycho)logical tests.

Osteoporosis is widespread with a high incidence rate, resulting in fragility fractures which are a major contributor to mortality among the elderly. Artificial intelligence (AI), in particular artificial neural networks, appears to be useful in managing osteoporosis complexity, where bone mineral density usually reduces with aging, losing the pivotal role in decision-making regarding fracture prediction and treatment choice. Nevertheless, only some osteoporotic patients develop fragility fractures, and treatments often are not prescribed because of the high costs and poor patient adherence. AI can help clinicians to identify patients prone to fragility fractures who can benefit from preventive interventions. We describe herein the methodology issues underlying the potential advantages of introducing AI methods to support clinical decision-making in osteoporosis, being aware of challenges regarding data availability and quality, model interpretability, integration into clinical workflows, and validation of predictive accuracy. The fact that no AI fracture risk prediction software is still publicly available can be related to the fact that few high-quality datasets are available and that AI models, particularly deep learning approaches, often act as 'black boxes', making it difficult to understand how predictions are made. In addition, the effective implementation of predictive software has not reached sufficient integration with existing systems. RELEVANCE STATEMENT: With aging, bone mineral density may lose the pivotal role in osteoporosis decision-making regarding fracture prediction and treatment choice. In this scenario, AI, particularly artificial neural networks (ANNs), can be useful in supporting the clinical management of patients affected by osteoporosis. KEY POINTS: Osteoporosis is a complex disease with many interlinked clinical and radiological variables. Bone mineral density and other known indices do not allow optimal decision-making in patients affected by osteoporosis. ANN analysis can better discriminate osteoporotic patients particularly prone to fragility fractures and can predict future fractures.

Background: In acute neck infections, magnetic resonance imaging (MRI) shows retropharyngeal edema (RPE), which is a prognostic imaging biomarker for a severe course of illness. This study aimed to develop a deep learning-based algorithm for the automated detection of RPE.

Methods: We developed a deep neural network consisting of two parts using axial T2-weighted water-only Dixon MRI images from 479 patients with acute neck infections annotated by radiologists at both slice and patient levels. First, a convolutional neural network (CNN) classified individual slices; second, an algorithm classified patients based on a stack of slices. Model performance was compared with the radiologists' assessment as a reference standard. Accuracy, sensitivity, specificity, and area under receiver operating characteristic curve (AUROC) were calculated. The proposed CNN was compared with InceptionV3, and the patient-level classification algorithm was compared with traditional machine learning models.

Results: Of the 479 patients, 244 (51%) were positive and 235 (49%) negative for RPE. Our model achieved accuracy, sensitivity, specificity, and AUROC of 94.6%, 83.3%, 96.2%, and 94.1% at the slice level, and 87.4%, 86.5%, 88.2%, and 94.8% at the patient level, respectively. The proposed CNN was faster than InceptionV3 but equally accurate. Our patient classification algorithm outperformed traditional machine learning models.

Conclusion: A deep learning model, based on weakly annotated data and computationally manageable training, achieved high accuracy for automatically detecting RPE on MRI in patients with acute neck infections.

Relevance statement: Our automated method for detecting relevant MRI findings was efficiently trained and might be easily deployed in practice to study clinical applicability. This approach might improve early detection of patients at high risk for a severe course of acute neck infections.

Key points: Deep learning automatically detected retropharyngeal edema on MRI in acute neck infections. Areas under the receiver operating characteristic curve were 94.1% at the slice level and 94.8% at the patient level. The proposed convolutional neural network was lightweight and required only weakly annotated data.

Background: To evaluate the impact of an annotation guideline on the performance of large language models (LLMs) in extracting data from stroke computed tomography (CT) reports.

Methods: The performance of GPT-4o and Llama-3.3-70B in extracting ten imaging findings from stroke CT reports was assessed in two datasets from a single academic stroke center. Dataset A (n = 200) was a stratified cohort including various pathological findings, whereas dataset B (n = 100) was a consecutive cohort. Initially, an annotation guideline providing clear data extraction instructions was designed based on a review of cases with inter-annotator disagreements in dataset A. For each LLM, data extraction was performed under two conditions: with the annotation guideline included in the prompt and without it.

Results: GPT-4o consistently demonstrated superior performance over Llama-3.3-70B under identical conditions, with micro-averaged precision ranging from 0.83 to 0.95 for GPT-4o and from 0.65 to 0.86 for Llama-3.3-70B. Across both models and both datasets, incorporating the annotation guideline into the LLM input resulted in higher precision rates, while recall rates largely remained stable. In dataset B, the precision of GPT-4o and Llama-3-70B improved from 0.83 to 0.95 and from 0.87 to 0.94, respectively. Overall classification performance with and without the annotation guideline was significantly different in five out of six conditions.

Conclusion: GPT-4o and Llama-3.3-70B show promising performance in extracting imaging findings from stroke CT reports, although GPT-4o steadily outperformed Llama-3.3-70B. We also provide evidence that well-defined annotation guidelines can enhance LLM data extraction accuracy.

Relevance statement: Annotation guidelines can improve the accuracy of LLMs in extracting findings from radiological reports, potentially optimizing data extraction for specific downstream applications.

Key points: LLMs have utility in data extraction from radiology reports, but the role of annotation guidelines remains underexplored. Data extraction accuracy from stroke CT reports by GPT-4o and Llama-3.3-70B improved when well-defined annotation guidelines were incorporated into the model prompt. Well-defined annotation guidelines can improve the accuracy of LLMs in extracting imaging findings from radiological reports.

Objectives: To evaluate a deep learning sequence-adaptive liver multiparametric MRI (mpMRI) assessment with validation in different populations using total and segmental T1 and T2 relaxation time maps.

Methods: A neural network was trained to label liver segmental parenchyma and its vessels on noncontrast T1-weighted gradient-echo Dixon in-phase acquisitions on 200 liver mpMRI examinations. Then, 120 unseen liver mpMRI examinations of patients with primary sclerosing cholangitis or healthy controls were assessed by coregistering the labels to noncontrast and contrast-enhanced T1 and T2 relaxation time maps for optimization and internal testing. The algorithm was externally tested in a segmental and total liver analysis of previously unseen 65 patients with biopsy-proven liver fibrosis and 25 healthy volunteers. Measured relaxation times were compared to manual measurements using intraclass correlation coefficient (ICC) and Wilcoxon test.

Results: Comparison of manual and deep learning-generated segmental areas on different T1 and T2 maps was excellent for segmental (ICC = 0.95 ± 0.1; p < 0.001) and total liver assessment (0.97 ± 0.02, p < 0.001). The resulting median of the differences between automated and manual measurements among all testing populations and liver segments was 1.8 ms for noncontrast T1 (median 835 versus 842 ms), 2.0 ms for contrast-enhanced T1 (median 518 versus 519 ms), and 0.3 ms for T2 (median 37 versus 37 ms).

Conclusion: Automated quantification of liver mpMRI is highly effective across different patient populations, offering excellent reliability for total and segmental T1 and T2 maps. Its scalable, sequence-adaptive design could foster comprehensive clinical decision-making.

Relevance statement: The proposed automated, sequence-adaptive algorithm for total and segmental analysis of liver mpMRI may be co-registered to any combination of parametric sequences, enabling comprehensive quantitative analysis of liver mpMRI without sequence-specific training.

Key points: A deep learning-based algorithm automatically quantified segmental T1 and T2 relaxation times in liver mpMRI. The two-step approach of segmentation and co-registration allowed to assess arbitrary sequences. The algorithm demonstrated high reliability with manual reader quantification. No additional sequence-specific training is required to assess other parametric sequences. The DL algorithm has the potential to enhance individual liver phenotyping.

Background: We assessed immunotherapy response in a murine melanoma model using multiparametric magnetic resonance imaging (mpMRI) features with ex vivo immunohistochemical validation.

Methods: Murine melanoma cells (B16-F10) were inoculated into the subcutaneous flank of n = 28 C57BL/6 mice (n = 14 therapy; n = 14 control). Baseline mpMRI was acquired on day 7 at 3 T. The immunotherapy group received three intraperitoneal injections of anti-PD-L1 and anti-CTLA-4 antibodies on days 7, 9, and 11 after inoculation. Controls received a volume equivalent placebo. Follow-up mpMRI was performed on day 12. We assessed tumor volume, diffusion-weighted imaging parameters, including the apparent diffusion coefficient (ADC), and dynamic-contrast-enhanced metrics, including plasma volume and plasma flow. Tumor-infiltrating lymphocytes (TIL; CD8+), cell proliferation (Ki-67), apoptosis (terminal deoxynucleotidyl transferase deoxyuridine triphosphate nick-end labeling, TUNEL), and microvascular density (CD31+) were assessed in a validation cohort of n = 24 animals for time-matched ex vivo validation.

Results: An increase in tumor volume was observed in both groups (p ≤ 0.004) without difference at follow-up (p = 0.630). A lower ADC value was observed in the immunotherapy group at follow-up (p = 0.001). Immunohistochemistry revealed higher TUNEL values (p < 0.001) and CD8+ TILs (p = 0.048) following immunotherapy, as well as lower tumor cell Ki-67 values (p < 0.001) and microvascular density/CD31+ (p < 0.001).

Conclusion: Lower tumor ADC, paired with higher intratumoral expression of CD8+ TIL, was observed five days after immunotherapy, suggestive of early immunological response. Ex vivo immunohistochemistry confirmed the antitumoral efficacy of immunotherapy.

Relevance statement: Compared to tumor size, diffusion-weighted MRI demonstrated potential for early response assessment to immunotherapy in a murine melanoma model, which could reflect changes in the tumor microenvironment and immune cell infiltration.

Key points: No difference in tumor volume was observed between groups before and after therapy. Lower ADC values paired with increased CD8+ TILs were observed following immunotherapy. Ex vivo immunohistochemistry confirmed antitumoral efficacy of anti-PD-L1 and anti-CTLA-4 immunotherapy.

Background: Neurofibromatosis type 1 (NF1) is a genetic disorder characterised by skin and nervous system anomalies, primarily involving glial cells and nerve tumours. Pain, particularly chronic pain, is a significant but often overlooked symptom in NF1 patients, affecting their health-related quality of life. The dorsal root ganglion (DRG) is essential for pain signal transmission, yet in vivo studies of DRG in NF1 patients are lacking.

Methods: This prospective study included 20 NF1 patients (8 with neuropathic pain) and 28 healthy controls. Magnetic resonance imaging (MRI) scans of lumbosacral DRG (L5 + S1) were performed using a 3-T scanner. Quantitative MRI techniques were applied to assess DRG volume, T2 relaxation time, and proton density (PD). Statistical analyses compared NF1 patients and controls, and NF1 patients with and without pain.

Results: NF1 patients had a significantly larger DRG volume and higher quantitative T2 and PD values compared to controls. Furthermore, DRG PD was significantly higher in NF1 patients with neuropathic pain than in those without pain. Receiver operator characteristic curve analysis identified DRG PD as the best discriminator of pain in NF1 patients, with an area under the curve of 0.84, indicating relevant and useful discriminatory power.

Conclusion: NF1 patients showed objective macrostructural and microstructural DRG injury changes using dedicated DRG MRI, discriminating neuropathic pain status from non-pain status at the disease-symptom group level. These findings highlight the potential of DRG MRI to quantify DRG pathology in vivo and to determine the risk of functional pain status by imaging.

Relevance statement: The identification of structural and microstructural changes of the DRG by quantitative MRI provides a novel in vivo biomarker for understanding neuropathic pain mechanisms, pain risk assessment and treatment monitoring in NF1.

Key points: Dorsal root ganglia (DRG) in NF1 are enlarged by 176.3% in MRI. In quantitative MRI of DRG NF1, T2 relaxation time is increased by 22.9% and PD by 8.4%. DRG PD can distinguish a painful from a non-painful NF1 phenotype.

Background: The chick chorioallantoic membrane (CAM) model has been utilized for radiofrequency ablation and electroporation, but not yet for cryoablation. This study aims to evaluate the feasibility of the CAM model for preclinical cryoablation research.

Methods: Two cryoablation protocols were established for the study: 120 s-freeze-120 s-thaw-120 s freeze (120 s protocol) and 180 s-freeze-120 s-thaw-180 s freeze (180 s protocol). The study was divided into two parts. First, to evaluate embryo survival, fertilized chicken eggs were incubated. On embryonic day (ED) 12, cryoablation on CAM was performed according to the two protocols. During cryoablation, the temperature of the CAM was recorded using a thermal camera. Embryo survival was monitored until ED 14. Second, to evaluate tumor cryoablation, human neuroendocrine tumor cells (BON-1) were xenografted onto the CAM of fertilized chicken eggs at ED 8. Cryoablation of the xenografted tumors was then performed on ED 12 according to the two protocols. Ablation outcomes were evaluated by stereomicroscopic and histological assessments after harvesting on ED 14.

Results: Embryo survival rates were 8/9 in both protocols. A decrease in the peripheral temperature of 4.5 (± 0.9) °C and 6.7 (± 1.0) °C was observed in the 120 s and 180 s protocols, respectively. Complete ablation of CAM-grown tumors was observed in 2/6 (120 s protocol) and 2/5 (180 s protocol) cases, few scattered tumor cells remaining in 2/6 (120 s protocol) and 2/5 (180 s protocol) cases. Residual interconnected tumor cells were visible in 2/6 (120 s protocol) and 1/5 (180 s protocol) cases.

Conclusion: The CAM model is a feasible platform for preclinical cryoablation studies.

Relevance statement: Chorioallantoic membrane model is a suitable platform for preclinical cryoablation research.

Key points: Chick embryos tolerate the temperature drop during cryoablation well with high survival. Effectiveness of cryoablation on xenografted tumors can be histologically evaluated. Cryoablation protocols for xenografted tumors can be further optimized.

Background: Prostate imaging reporting and data system (PI-RADS) v2.1 guidelines for magnetic resonance imaging acquisition define a standard of 0.40 mm × 0.70 mm in-plane resolution (0.280 mm² pixel area), but adherence has been challenging. We questioned if a modification of a PI-RADS-adherent T2-weighted (T2WI) sequence to one having equivalent pixel area could allow reduced acquisition time but provide improved diagnostic quality (DQ).

Methods: An adherent T2WI sequence was modified by reducing the frequency sampling, thereby reducing the signal bandwidth (BW). This was compensated by increasing the phase sampling for an equivalent pixel area (0.50 mm × 0.57 mm = 0.285 mm²). The BW reduction allowed a two-fold reduction in averaging, also enabling reduced acquisition time. The adherent and modified sequences were evaluated in phantoms and 62 consecutive prostate MRI subjects. Images were evaluated individually by four radiologists using a four-point DQ scale and using prostate imaging quality (PI-QUAL)v2. Each reviewer also indicated any sequence preference. The Wilcoxon test was used.

Results: In the phantom, mean signal-to-noise ratios were equivalent for the two sequences; superior frequency resolution for the adherent sequence, and superior phase resolution for the modified sequence were shown. Across 62 participants, the median acquisition time was reduced by 23%, from 3:55 min:s to 3:01 min:s. For all three means of comparison (DQ, PI-QUALv2, reader preference), the modified sequence was significantly superior (p ≤ 0.037).

Conclusion: Modification of the PI-RADS standard (0.40-mm frequency resolution) to an equivalent, more isotropic pixel area (0.28 mm²) reduced acquisition time and improved image quality.

Relevance statement: Generalization of the PI-RADSv.2.1 minimum technical standard for T2WI in-plane resolution to be more isotropic preserves the targeted high resolution, allowing reduced acquisition time, also reducing motion sensitivity, and improving image quality. This approach may also reduce the need for rescanning poor-quality sequences.

Key points: PI-RADSv2.1 suggests a standard T2WI sequence with 0.40 × 0.70 mm² in-plane resolution. A modified PI-RADSv.2.1-adherent T2WI sequence with equivalent but more isotropic pixel area (0.50 × 0.57 mm²) allowed reduced scan times by 23% and significantly improved DQ. Superiority of the modified sequence appears due to reduced motion sensitivity.