European Radiology Experimental最新文献

Background: We assessed the safety and efficacy of computed tomography (CT)-guided high-dose-rate (HDR) brachytherapy in treating hepatocellular carcinoma (HCC) with portal vein tumor thrombosis (PVTT).

Methods: From January 2010 to January 2022, 56 patients (median age 67.5 years) with HCC and PVTT underwent 64 procedures. PVTT was further classified according to the Japan liver cancer study group into VP1-VP4. Tumor response was evaluated by cross-sectional imaging 6 weeks after CT-guided HDR brachytherapy and every 3 months thereafter. Local tumor control (LTC), progression-free survival (PFS), and overall survival (OS) were assessed using Kaplan-Meier curves. The severity of procedure-related complications was classified according to the Society of Interventional Radiology guidelines.

Results: Patients were available for imaging evaluation for a median follow-up of 14.0 months. The median diameter of the largest lesion was 56 mm. Estimated median PFS, LTC, and OS were 7.0 (95% CI 5.0-13.0), 14.0 (95% CI 7.0-21.0), and 20.0 (95% CI 13.0-26.0) months respectively. Actuarial 1-, 2-, and 3-year OS rates were 66%, 41%, and 27%, respectively. Subclassified for VP1, VP2, VP3, and VP4 estimated OS was 38.0 (95% CI 9.0-Not-a-number), 21.5 (95% CI 15.0-25.0), 15.0 (95% CI 7.0-33.0), and 13.0 (95% CI 6.0-34.0) months, respectively. Considering the 64 procedures, we recorded no complications for 49 (76.6%), mild-to-moderate complications for 12 (18.8%), and major complications for 3 (4.7%).

Conclusion: CT-guided HDR brachytherapy was safe and effective for locoregional treatment in patients with advanced HCC due to PVTT, achieving long-lasting local tumor control.

Relevance statement: CT-guided HDR brachytherapy is an option to be considered for locoregional treatment of patients with advanced HCC due to PVTT.

Key points: Evaluation of CT-guided high-dose-rate (HDR) brachytherapy in treating HCC patients with portal vein tumor thrombosis (PVTT). Median OS was 20.0 months ranging between 13.0 and 38.0 months. CT-guided HDR brachytherapy seems to be a safe and effective treatment option in HCC patients with PVTT.

Background: Gadolinium-enhanced "sampling perfection with application-optimized contrasts using different flip angle evolution" (SPACE) sequence allows better visualization of brain metastases (BMs) compared to "magnetization-prepared rapid acquisition gradient echo" (MPRAGE). We hypothesize that this better conspicuity leads to high-quality annotation (HAQ), enhancing deep learning (DL) algorithm detection of BMs on MPRAGE images.

Methods: Retrospective contrast-enhanced (gadobutrol 0.1 mmol/kg) SPACE and MPRAGE data of 157 patients with BM were used, either annotated on MPRAGE resulting in normal annotation quality (NAQ) or on coregistered SPACE resulting in HAQ. Multiple DL methods were developed with NAQ or HAQ using either SPACE or MRPAGE images and evaluated on their detection performance using positive predictive value (PPV), sensitivity, and F1 score and on their delineation performance using volumetric Dice similarity coefficient, PPV, and sensitivity on one internal and four additional test datasets (660 patients).

Results: The SPACE-HAQ model reached 0.978 PPV, 0.882 sensitivity, and 0.916 F1-score. The MPRAGE-HAQ reached 0.867, 0.839, and 0.840, the MPRAGE NAQ 0.964, 0.667, and 0.798, respectively (p ≥ 0.157). Relative to MPRAGE-NAQ, the MPRAGE-HAQ F1-score detection increased on all additional test datasets by 2.5-9.6 points (p < 0.016) and sensitivity improved on three datasets by 4.6-8.5 points (p < 0.001). Moreover, volumetric instance sensitivity improved by 3.6-7.6 points (p < 0.001).

Conclusion: HAQ improves DL methods without specialized imaging during application time. HAQ alone achieves about 40% of the performance improvements seen with SPACE images as input, allowing for fast and accurate, fully automated detection of small (< 1 cm) BMs.

Relevance statement: Training with higher-quality annotations, created using the SPACE sequence, improves the detection and delineation sensitivity of DL methods for the detection of brain metastases (BMs)on MPRAGE images. This MRI cross-technique transfer learning is a promising way to increase diagnostic performance.

Key points: Delineating small BMs on SPACE MRI sequence results in higher quality annotations than on MPRAGE sequence due to enhanced conspicuity. Leveraging cross-technique ground truth annotations during training improved the accuracy of DL models in detecting and segmenting BMs. Cross-technique annotation may enhance DL models by integrating benefits from specialized, time-intensive MRI sequences while not relying on them. Further validation in prospective studies is needed.

Background: A variety of animal models has been developed for research on atherosclerosis and neointimal hyperplasia. While small animal models contain limits for translational research, we aimed to develop an atherosclerosis model with lumen-narrowing plaques to foster basic research in vascular biology, the development of new angioplasty devices, and vessel wall imaging approaches.

Methods: Endothelial denudation was performed via a minimally invasive approach through the auricular artery, followed by stent-retriever mediated endothelial injury in New Zealand White rabbits (n = 10). Along with a high-fat diet, the rabbits developed lumen-narrowing atherosclerosis and neointimal hyperplasia of the iliac arteries within a 6-week period after mechanical injury. The stent-retriever method was compared with a conventional rabbit model (n = 10) using balloon denudation via surgical access, and both models were analyzed with a particular focus on animal welfare. Fisher's exact, Mann-Whitney U, and unpaired t-tests were used.

Results: The average time for the entire procedure was 62 min for the balloon group and 31 min for the stent-retriever group (p < 0.001). The stent-retriever model resulted in less periprocedural morbidity (including expenditure, intubation time, anesthetics, and end-tidal CO₂ level) and mortality (40% mortality in the conventional group compared to 0% in the stent-retriever model, p = 0.011), while generating lumen-narrowing atherosclerotic lesions with key features as compared to humans as revealed by time-of-flight magnetic resonance imaging and histology.

Conclusion: We developed a minimally invasive model of iliac atherosclerosis with high reproducibility and improved animal welfare for translational research.

Relevance statement: This advanced rabbit model could allow for translational research in atherosclerosis, including pharmacological investigations as well as research on interventional angioplasty procedures.

Key points: Rabbit models show similar lipid metabolism as humans. Stent-retriever mediated endothelial denudation causes neointimal hyperplasia and lumen narrowing. This minimal invasive model allows for clinical translation, including pharmacological investigations and vessel wall imaging.

Background: Metasurface coils (MCs) are a promising magnetic resonance imaging (MRI) technology. Aiming to evaluate the image quality of MCs for knee and elbow imaging, we compared signal-to-noise ratio (SNRs) obtained in standard clinical setups.

Methods: Knee and elbow MRI routine sequences were applied at 1.5 T, implementing four coil scenarios: (1) 15-channel transmit/receive knee coil; (2) four-channel multipurpose coil (flex coil); (3) MC + spine coil; and (4) MC + multipurpose coil. Three regions of interest (ROIs) at different anatomical depths were compared.

Results: Seven participants (aged 28 ± 2 years; 6 males) were enrolled. In elbow MRI, the MC + spine coil demonstrated the highest SNR across all ROIs (superficial-anterior: +114%, p = 0.008; middle: +147%, p = 0.008; deep-posterior: +24%, p = 0.039) compared to the flex coil and all ROIs, except the deepest from the MC, compared to the knee coil (superficial-anterior: +28%, p = 0.016; middle: +104%, p = 0.008; deep-posterior: -1%, p = 0.531). In knee MRI, the MC + spine coil provided higher SNR compared to the flex coil, except posterior (superficial-anterior: +69%, p = 0.008; middle: +288%, p = 0.008; deep-posterior: -12%, p = 0.148) versus the knee coil, the MC + spine coil was superior in the middle but non-different in superficial pre-patellar areas and less in deep-posterior areas (superficial-anterior: -8%, p = 0.188; middle: +44%, p = 0.008; deep-posterior: -36%, p = 0.016).

Conclusion: Wireless MCs exhibited great potential for knee and elbow MRI outperforming the flex coil. Future developments will improve the posterior illumination to increase its clinical value.

Relevance statement: MCs offer enhanced versatility, flexibility, and patient comfort. If universal MC designs can achieve image quality comparable to those of standard coils and simultaneously be utilized across multiple body areas, the technology may revolutionize future musculoskeletal MRIs.

Key points: MCs are promising in MRI, but homogeneity is challenging depending on the design. Signal-to-noise-ratio was improved for knee and elbow imaging with slight inhomogeneous illumination. MCs could match the image quality of standard coils in both knee and elbow imaging.

Background: To define optimal parameters for the evaluation of vessel visibility in intracranial stents (ICS) and flow diverters (FD) using photon-counting detector computed tomography angiography (PCD-CTA) with spectral reconstructions.

Methods: We retrospectively analyzed consecutive patients with implanted ICS or FD, who received a PCD-CTA between April 2023 and March 2024. Polyenergetic, virtual monoenergetic, pure lumen, and iodine reconstructions with different keV levels (40, 60, and 80) and reconstruction kernels (body vascular [Bv]48, Bv56, Bv64, Bv72, and Bv76) were evaluated by two radiologists with regions of interests and Likert scales. Reconstructions were compared in descriptive analysis.

Results: In total, twelve patients with nine FDs and six ICSs were analyzed. In terms of quantitative image quality, sharper kernels as Bv64 and Bv72 yielded increased image noise and decreased signal-to-noise and contrast-to-noise ratios compared to the smoothest kernel Bv48 (p = 0.001). Among the different keV levels and kernels, readers selected the 40 keV level (p = 0.001) and sharper kernels (in the majority of cases Bv72) as the best to visualize the in-stent vessel lumen. Assessing the different spectral reconstructions virtual monoenergetic and iodine reconstructions proved to be best to evaluate in-stent vessel lumen (p = 0.001).

Conclusion: PCD-CTA and spectral reconstructions with sharper reconstruction kernels and a low keV level of 40 seem to be beneficial to achieve optimal image quality for the evaluation of ICS and FD. Iodine and virtual monoenergetic reconstructions were superior to pure lumen and polyenergetic reconstructions to evaluate in-stent vessel lumen.

Relevance statement: PCD-CTA offers the opportunity to reduce the need for invasive angiography serving as follow-up examination after intracranial stent (ICS) or flow diverter (FD) implantation.

Key points: Neuroimaging of intracranial vessels with implanted stents and flow diverters is limited by artifacts. Twelve patients with nine flow diverters and six intracranial stents underwent photon-counting detector computed tomography angiography (PCD-CTA). In-stent vessel lumen visibility improved using sharp reconstruction kernels and a low keV level. Virtual monoenergetic and iodine reconstructions were best to evaluate in-stent vessel lumen.

Background: Body composition scores allow for quantifying the volume and physical properties of specific tissues. However, their manual calculation is time-consuming and prone to human error. This study aims to develop and validate CompositIA, an automated, open-source pipeline for quantifying body composition scores from thoraco-abdominal computed tomography (CT) scans.

Methods: A retrospective dataset of 205 contrast-enhanced thoraco-abdominal CT examinations was used for training, while 54 scans from a publicly available dataset were used for independent testing. Two radiology residents performed manual segmentation, identifying the centers of the L1 and L3 vertebrae and segmenting the corresponding axial slices. MultiResUNet was used to identify CT slices intersecting the L1 and L3 vertebrae, and its performance was evaluated using the mean absolute error (MAE). Two U-nets were used to segment the axial slices, with performance evaluated through the volumetric Dice similarity coefficient (vDSC). CompositIA's performance in quantifying body composition indices was assessed using mean percentage relative error (PRE), regression, and Bland-Altman analyses.

Results: On the independent dataset, CompositIA achieved a MAE of about 5 mm in detecting slices intersecting the L1 and L3 vertebrae, with a MAE < 10 mm in at least 85% of cases and a vDSC greater than 0.85 in segmenting axial slices. Regression and Bland-Altman analyses demonstrated a strong linear relationship and good agreement between automated and manual scores (p values < 0.001 for all indices), with mean PREs ranging from 5.13% to 15.18%.

Conclusion: CompositIA facilitated the automated quantification of body composition scores, achieving high precision in independent testing.

Relevance statement: CompositIA is an automated, open-source pipeline for quantifying body composition indices from CT scans, simplifying clinical assessments, and expanding their applicability.

Key points: Manual body composition assessment from CTs is time-consuming and prone to errors. CompositIA was trained on 205 CT scans and tested on 54 scans. CompositIA demonstrated mean percentage relative errors under 15% compared to manual indices. CompositIA simplifies body composition assessment through an artificial intelligence-driven and open-source pipeline.

Background: Minimizing radiation exposure is crucial in monitoring adolescent idiopathic scoliosis (AIS). Generative adversarial networks (GANs) have emerged as valuable tools being able to generate high-quality synthetic images. This study explores the use of GANs to generate synthetic sagittal radiographs from coronal views in AIS patients.

Methods: A dataset of 3,935 AIS patients who underwent spine and pelvis radiographic examinations using the EOS system, which simultaneously acquires coronal and sagittal images, was analyzed. The dataset was divided into training-set (85%, n = 3,356) and test-set (15%, n = 579). GAN model was trained to generate sagittal images from coronal views, with real sagittal views as reference standard. To assess accuracy, 100 subjects from the test-set were randomly selected for manual measurement of lumbar lordosis (LL), sacral slope (SS), pelvic incidence (PI), and sagittal vertical axis (SVA) by two radiologists in both synthetic and real images.

Results: Sixty-nine synthetic images were considered assessable. The intraclass correlation coefficient ranged 0.93-0.99 for measurements in real images, and from 0.83 to 0.88 for synthetic images. Correlations between parameters of real and synthetic images were 0.52 (LL), 0.17 (SS), 0.18 (PI), and 0.74 (SVA). Measurement errors showed minimal correlation with scoliosis severity. Mean ± standard deviation absolute errors were 7 ± 7° (LL), 9 ± 7° (SS), 9 ± 8° (PI), and 1.1 ± 0.8 cm (SVA).

Conclusion: While the model generates sagittal images visually consistent with reference images, their quality is not sufficient for clinical parameter assessment, except for promising results in SVA.

Relevance statement: AI can generate synthetic sagittal radiographs from coronal views to reduce radiation exposure in monitoring adolescent idiopathic scoliosis (AIS). However, while these synthetic images appear visually consistent with real ones, their quality remains insufficient for accurate clinical assessment.

Key points: AI can be exploited to generate synthetic sagittal radiographs from coronal views. Dataset of 3,935 subjects was used to train and test AI-model; spinal parameters from synthetic and real images were compared. Synthetic images were visually consistent with real ones, but quality was generally insufficient for accurate clinical assessment.

Interventional radiology (IR) has evolved rapidly, but the clinical integration of interventional radiologists has not kept pace with technical advancements. This trial will address a gap in the literature by providing a robust investigation into specific measures for enhancing the clinical role of interventional radiologists, with potential implications for improving patient experiences and outcomes. The single-center randomized controlled trial will include 428 patients undergoing IR procedures. The control group will receive information about the procedure from the ordering physician, while the experimental group will have an additional consultation with an interventional radiologist and be shown procedure-specific explanatory videos. The primary outcomes are patients' knowledge, satisfaction with the information and communication, and anxiety. Data collection will involve specific questionnaires and scales. This trial is designed to investigate the importance of proactive clinical roles in patient care within IR. The study explores the potential of consultations and audiovisual tools, highlighting their role in educating patients about procedures. The results may help foster a more widespread acceptance of clinical responsibilities in IR and underscore the pivotal role of audiovisual aids in patient education and satisfaction.

Trial registration: NCT05461482 at clinicaltrials.gov.

Relevance statement: This randomized controlled trial will assess the impact of clinical consultations and explanatory audiovisual tools on patient understanding, satisfaction, and anxiety in interventional radiology. The findings could help establish a more proactive clinical role for interventional radiologists and improve the overall quality of patient-centered care.

Key points: We describe the protocol of an interventional radiology randomized clinical trial. The control group will receive procedure information from the referring physician and the experimental group receives additional consultation with interventionalists and views a video. Knowledge, satisfaction with information, and patient anxiety will be evaluated. This study will provide insights about the benefits of consultations and videos in interventional radiology.

Background: The large language model ChatGPT can now accept image input with the GPT4-vision (GPT4V) version. We aimed to compare the performance of GPT4V to pretrained U-Net and vision transformer (ViT) models for the identification of the progression of multiple sclerosis (MS) on magnetic resonance imaging (MRI).

Methods: Paired coregistered MR images with and without progression were provided as input to ChatGPT4V in a zero-shot experiment to identify radiologic progression. Its performance was compared to pretrained U-Net and ViT models. Accuracy was the primary evaluation metric and 95% confidence interval (CIs) were calculated by bootstrapping. We included 170 patients with MS (50 males, 120 females), aged 21-74 years (mean 42.3), imaged at a single institution from 2019 to 2021, each with 2-5 MRI studies (496 in total).

Results: One hundred seventy patients were included, 110 for training, 30 for tuning, and 30 for testing; 100 unseen paired images were randomly selected from the test set for evaluation. Both U-Net and ViT had 94% (95% CI: 89-98%) accuracy while GPT4V had 85% (77-91%). GPT4V gave cautious nonanswers in six cases. GPT4V had precision (specificity), recall (sensitivity), and F1 score of 89% (75-93%), 92% (82-98%), 91 (82-97%) compared to 100% (100-100%), 88 (78-96%), and 0.94 (88-98%) for U-Net and 94% (87-100%), 94 (88-100%), and 94 (89-98%) for ViT.

Conclusion: The performance of GPT4V combined with its accessibility suggests has the potential to impact AI radiology research. However, misclassified cases and overly cautious non-answers confirm that it is not yet ready for clinical use.

Relevance statement: GPT4V can identify the radiologic progression of MS in a simplified experimental setting. However, GPT4V is not a medical device, and its widespread availability highlights the need for caution and education for lay users, especially those with limited access to expert healthcare.

Key points: Without fine-tuning or the need for prior coding experience, GPT4V can perform a zero-shot radiologic change detection task with reasonable accuracy. However, in absolute terms, in a simplified "spot the difference" medical imaging task, GPT4V was inferior to state-of-the-art computer vision methods. GPT4V's performance metrics were more similar to the ViT than the U-net. This is an exploratory experimental study and GPT4V is not intended for use as a medical device.

Good practices in artificial intelligence (AI) model validation are key for achieving trustworthy AI. Within the cancer imaging domain, attracting the attention of clinical and technical AI enthusiasts, this work discusses current gaps in AI validation strategies, examining existing practices that are common or variable across technical groups (TGs) and clinical groups (CGs). The work is based on a set of structured questions encompassing several AI validation topics, addressed to professionals working in AI for medical imaging. A total of 49 responses were obtained and analysed to identify trends and patterns. While TGs valued transparency and traceability the most, CGs pointed out the importance of explainability. Among the topics where TGs may benefit from further exposure are stability and robustness checks, and mitigation of fairness issues. On the other hand, CGs seemed more reluctant towards synthetic data for validation and would benefit from exposure to cross-validation techniques, or segmentation metrics. Topics emerging from the open questions were utility, capability, adoption and trustworthiness. These findings on current trends in AI validation strategies may guide the creation of guidelines necessary for training the next generation of professionals working with AI in healthcare and contribute to bridging any technical-clinical gap in AI validation. RELEVANCE STATEMENT: This study recognised current gaps in understanding and applying AI validation strategies in cancer imaging and helped promote trust and adoption for interdisciplinary teams of technical and clinical researchers. KEY POINTS: Clinical and technical researchers emphasise interpretability, external validation with diverse data, and bias awareness in AI validation for cancer imaging. In cancer imaging AI research, clinical researchers prioritise explainability, while technical researchers focus on transparency and traceability, and see potential in synthetic datasets. Researchers advocate for greater homogenisation of AI validation practices in cancer imaging.