Academic Radiology最新文献

Rationale and objectives: Immunotherapy combined with chemotherapy has improved outcomes for some esophageal squamous cell carcinoma (ESCC) patients, but accurate pre-treatment risk stratification remains a critical gap. This study constructed a deep learning (DL) model to predict survival outcomes in ESCC patients receiving immunotherapy combined with chemotherapy.

Materials and methods: A DL model was developed to predict survival outcomes in ESCC patients receiving immunotherapy and chemotherapy. Retrospective data from 482 patients across three institutions were split into training (N=322), internal test (N=79), and external test (N=81) sets. Unenhanced computed tomography (CT) scans were processed to analyze tumor and peritumoral regions. The model evaluated multiple input configurations: original tumor regions of interest (ROIs), ROI subregions, and ROIs expanded by 1 and 3 pixels. Performance was assessed using Harrell's C-index and receiver operating characteristic (ROC) curves. A multimodal model combined DL-derived risk scores with five key clinical and laboratory features. The Shapley Additive Explanations (SHAP) method elucidated the contribution of individual features to model predictions.

Results: The DL model with 1-pixel peritumoral expansion achieved the best accuracy, yielding a C-index of 0.75 for the internal test set and 0.60 for the external test set. Hazard ratios for high-risk patients were 1.82 (95% CI: 1.19-2.46; P=0.02) in internal test set. The multimodal model achieved C-indices of 0.74 and 0.61 for internal and external test sets, respectively. Kaplan-Meier analysis revealed significant survival differences between high- and low-risk groups (P<0.05). SHAP analysis identified tumor response, risk score, and age as critical contributors to predictions.

Conclusion: This DL model demonstrates efficacy in stratifying ESCC patients by survival risk, particularly when integrating peritumoral imaging and clinical features. The model could serve as a valuable pre-treatment tool to facilitate the implementation of personalized treatment strategies for ESCC patients undergoing immunotherapy and chemotherapy.

Background: This study aimed to characterize the imaging features and the outcomes of endovascular treatment (EVT) in patients with moderate hemodynamic stroke due to large vessel stenosis.

Methods: Data from patients with moderate hemodynamic stroke due to large vessel stenosis who underwent EVT at a single center between January 2021 and June 2024 were retrospectively analyzed. Hemodynamic stroke was defined as infarction in the watershed area on diffusion-weighted imaging and hypoperfusion on perfusion-weighted imaging. Demographics, National Institutes of Health Stroke Scale (NIHSS), imaging findings, cerebral circulation time (CCT; the interval from arterial origin visualization to completion of the intracranial arterial phase), and EVT details were collected. The primary outcome was functional independence, defined as a modified Rankin Scale score of 0-2 at 90-day post-stroke.

Results: Among 313 patients treated with EVT, 14 (4.4%) were diagnosed with moderate hemodynamic stroke secondary to large vessel stenosis. The mean age was 64.6±11.8 years, and the median NIHSS score was 9 (range, 6-12). Stenosis was predominantly located at the origin of the vertebral artery in 12 cases and at the origin of the internal carotid artery in 2 cases. All patients underwent stent angioplasty, leading to a significant reduction in median CCT from 3.0 s preoperatively to 1.43 s postoperatively (P=0.00001). At 90-day post-stroke, 78.6% of patients (11/14) achieved a functional independence.

Conclusion: Moderate hemodynamic stroke caused by large vessel stenosis was relatively rare but could be safely and effectively treated with EVT.

Rationale and objectives: To investigate the effect of accelerated deep-learning (DL) multi-b-value DWI (Mb-DWI) on acquisition time, image quality, and predictive ability of microvascular invasion (MVI) in BCLC stage A hepatocellular carcinoma (HCC), compared to standard Mb-DWI.

Methods: Patients who underwent liver MRI were prospectively collected. Subjective image quality, signal-to-noise ratio (SNR), lesion contrast-to-noise ratio (CNR), and Mb-DWI-derived parameters from various models (mono-exponential model, intravoxel incoherent motion, diffusion kurtosis imaging, and stretched exponential model) were calculated and compared between the two sequences. The Mb-DWI parameters of two sequences were compared between MVI-positive and MVI-negative groups, respectively. ROC and logistic regression analysis were performed to evaluate and identify the predictive performance.

Results: The study included 118 patients. 48/118 (40.67%) lesions were identified as MVI positive. DL Mb-DWI significantly reduced acquisition time by 52.86%. DL Mb-DWI produced significantly higher overall image quality, SNR, and CNR than standard Mb-DWI. All diffusion-related parameters except pseudo-diffusion coefficient showed significant differences between the two sequences. Both in DL and standard Mb-DWI, the apparent diffusion coefficient, true diffusion coefficient (D), perfusion fraction (f), mean diffusivity (MD), mean kurtosis (MK), and distributed diffusion coefficient (DDC) values were significantly different between MVI-positive and MVI-negative groups. The combination of D, f, and MK yield the highest AUC of 0.912 and 0.928 in standard and DL sequences, with no significant difference regarding the predictive efficiency.

Conclusion: The DL Mb-DWI significantly reduces acquisition time and improves image quality, with comparable predictive performance to standard Mb-DWI in discriminating MVI status in BCLC stage A HCC.

Rationale and objectives: To explore the association between contrast-enhanced cone-beam breast CT (CE-CBBCT) imaging features and lymphovascular invasion (LVI) status.

Materials and methods: Female patients with breast cancer by postoperative histopathology who underwent preoperative CE-CBBCT from August 2020 to December 2023 were retrospectively enrolled. Two radiologists reviewed the CBBCT image features independently. Clinicopathologic and CBBCT characteristics between LVI-positive and LVI-negative were compared by χ2 or Fisher's exact tests and Student's t or Mann-Whitney U test, as appropriate. Multivariate logistic regression analysis was performed to identify independent predictive factors of LVI. The receiver operating characteristic curve was used to evaluate predictive performance.

Results: A total of 401 women were enrolled. LVI status of breast cancer was significantly associated with histologic type, Ki-67 index, adjacent vessel sign (AVS), increased ipsilateral whole-breast vascularity (IIV) number, and IIV degree (all p<0.05). In mass, calcification, AVS, IIV number, and IIV degree were significantly associated with LVI (all p<0.05). In non-mass enhancement (NME), AVS, IIV number, and IIV degree were associated with LVI (all p<0.05). Multivariate logistic regression showed AVS (OR=4.367, p<0.001) and IIV degree (OR of moderate and prominent IIV=4.732, 3.641, both p<0.005) as independent risk factors for LVI. Specifically, in mass, AVS (OR=4.397, p<0.001) and moderate-to-prominent IIV (OR=4.815, 3.563, both p<0.01) were independent predictors. For NME, moderate-to-prominent IIV (OR=13.695, 4.054, both p=0.001) was also an independent factor. The combined LVI prediction model which included AVS and IIV degree showed excellent performance (AUC=0.804).

Conclusion: CBBCT imaging features can help identify LVI status in breast cancer patients, which will guide the accurate planning of treatment management.

This article serves as a step-by-step guide for students and trainees who wish to conduct a systematic review, meta-analysis, or scoping review. As the field of evidence synthesis progresses, more students and trainees are attempting to conduct reviews, and it can be unclear how to approach such a project. In 10 organized steps, we describe different types of reviews, explain how to choose the most appropriate one, detail the steps involved in conducting a review, and list resources that are available to support authors of reviews. We describe the steps involved in 1) forming an appropriate research team; 2) developing a compelling research question; 3) writing a review; and 4) reporting the findings with clarity.

Pars interarticularis stress injury and spondylolysis are frequent causes of back pain among young athletes. Accurate diagnosis and grading of these conditions are essential to institute appropriate management strategies in order to achieve optimal outcomes. The aim of management strategies for acute active spondylolysis stress reactions and stress fractures is to achieve bone healing while avoiding recurrence and non-union, with the ultimate goal of returning to sports as determined by symptom resolution. Although various radiological classification systems for spondylolysis have been described, their application for prognostication and surveillance has been limited. The development of a standardised, validated classification system that guides management decisions and predicts healing outcomes would immensely benefit radiologists and clinicians. This article reviews the current imaging recommendations for diagnosing and grading pars stress injuries and spondylolysis before proposal of a novel radiological classification system. The system utilises standard MRI sagittal sequences with clear inter- and intra-observer agreement. We aim to validate the classification system through interrogation of the injury, clinical and return-to-play data in young athletes, with an aim to determine early prognostic accuracy of pars stress injuries.

Rationale and objectives: To evaluate the performance of photon-counting detector CT (PCD-CT) in identifying and quantifying intracranial calcifications compared to conventional energy-integrating CT (EID-CT), utilizing micro-CT (µCT) as benchmark.

Method: Thirty cross-sectional histopathological samples of the intracranial arteries were scanned using PCD-CT, EID-CT and µCT. Scans were optimized for µCT for maximum image quality, while clinical protocols were followed for PCD-CT and EID-CT. Additional reconstruction kernels (EID-CT: Hv40/Hv49/Hv59, PCD-CT: Hv40/Hv48/Hv56/Hv64/Hv72/Hv89) were used to enhance the spatial resolution. Two observers evaluated calcification presence subjectively, using Cohen's kappa (κ) and concordance percentages. Mass scores were utilized to objectively analyze calcium detection using intraclass correlation coefficients and Bland-Altman plots.

Results: Observer 1 detected calcifications in 24 samples and Observer 2 in 23 samples using µCT (90% concordance, κ=0.706). The highest agreement was with EID-CT Hv59 (97% concordance, κ=0.911), but calcium detection rates were low (observer 1; 27%, observer 2: 25%) compared to µCT. The most optimal results of calcium detection were obtained with PCD-CT Hv48 (observer 1: concordance=90%, κ=0.706) and PCD-CT Hv56 (observer 2: concordance 77%, κ=0.314) compared to μCT. Mass scores revealed the highest detection rate with PCD-CT Hv64 but also increased noise levels compared to softer kernels (

Conclusion: PCD-CT outperformed EID-CT in detecting intracranial calcifications compared to µCT. Reconstructions with Hv48 or Hv56 kernels are recommended, considering the noise increase with sharper kernels.