CardioVascular and Interventional Radiology最新文献

Objectives: To develop and validate a deep learning model for detecting post-endovascular aortic repair (EVAR) endoleak from non-contrast CT.

Methods: This retrospective study involved 245 patients who underwent EVAR between September 2016 and December 2022. All patients underwent both non-enhanced and enhanced follow-up CT. The presence of endoleak was evaluated based on computed tomography angiography (CTA) and radiology reports. First, the aneurysm sac was segmented, and radiomic features were extracted on non-contrast CT. Statistical analysis was conducted to investigate differences in shape and density characteristics between aneurysm sacs with and without endoleak. Subsequently, a deep learning model was trained to generate predicted segmentation of the endoleak. A binary decision was made based on whether the model produced a segmentation to detect the presence of endoleak. The absence of a predicted segmentation indicated no endoleak, while the presence of a predicted segmentation indicated endoleak. Finally, the performance of the model was evaluated by comparing the predicted segmentation with the reference segmentation obtained from CTA. Model performance was assessed using metrics such as dice similarity coefficient, sensitivity, specificity, and the area under the curve (AUC).

Results: This study finally included 85 patients with endoleak and 82 patients without endoleak. Compared to patients without endoleak, patients with endoleak had higher CT values and greater dispersion. The AUC in validation group was 0.951, dice similarity coefficient was 0.814, sensitivity was 0.877, and specificity was 0.884.

Conclusion: This deep learning model based on non-contrast CT can detect endoleak after EVAR with high sensitivity.

Purpose: To retrospectively analyze the technical and long-term clinical outcome of angioplasty and stenting using the Venovo™ venous stent for the treatment of malignant and benign superior vena cava (SVC) occlusive disease.

Materials and methods: Consecutive patients treated with the Venovo™ venous stent for SVC occlusive disease were included. SVC obstruction symptoms were classified according to the Kishi score. The Wilcoxon signed-rank test was used for testing significance of changes. Technical success, defined as correct placement of the stent, completely covering and re-expanding the obstruction, between groups was tested using the Fisher exact test. Overall survival was calculated using the Kaplan-Meier method.

Results: Fifty-five patients underwent stent insertion for symptomatic benign (n = 13; 24%) or malignant (n = 42; 76%) SVC occlusive disease. A significant drop in Kishi score, mean 3.91 before versus mean 1.02 after the procedure (P < 0.0001), was observed. In one patient (1.8%), an additional balloon-expandable stent was needed to manage incomplete expansion of the nitinol stent. In one patient, a procedure-related lung embolic complication was noted. Early thrombotic occlusion of the stent occurred in one patient. Late symptomatic restenosis occurred in 3 patients. Overall primary stent patency and primary-assisted stent patency were 86% (95% CI 66-95) and 97% (95% CI 83-100) at 1-year follow-up and 98% (95% CI 87-100), 98% (87-100) at 2-year follow-up, respectively.

Conclusion: In this retrospective analysis, angioplasty and stent placement using the Venovo™ venous stent is safe and clinically effective for the treatment of both benign and malignant SVC occlusive disease. Reintervention for symptomatic restenosis is rare.

Purpose: Proton therapy is highly effective for liver malignancies, and to increase its accuracy, placement of fiducial markers in the liver is preferred. We retrospectively evaluated the safety and feasibility of CT-guided fiducial marker implantation using ultra-fine 25-gauge needles before proton therapy for liver malignancies.

Materials and methods: Between May 2016 and April 2021, 334 cases were investigated. All of procedures were performed without anesthesia. Technical success was defined as the completion of implantation at the intended site. Tumor-marker distance and possibility of synchronization between tumors and markers were evaluated and compared with Mann-Whitney U test. Complications were evaluated using the Common Terminology Criteria for Adverse Events, version 4.0.

Results: Technical success rate was 97.3%. Tumor-marker distance was 19.1 mm (median, range 0-96) in the group in which the implanted marker was synchronized with tumor (n = 315), while it was 34.5 mm (median, range 6-94) in the group in which the implanted marker was not synchronized (n = 13) (p value = 0.011 < 0.05). The complication rate was 2.4%, 2 were classified as grade 4 and 5 as grade 1, and 1 as grade 2. There were no grade 3 or higher complications that seemed to be related to the procedure.

Conclusion: CT-guided marker implantation using a 25-gauge needle achieved a satisfactory success rate with few complications and was useful for the image-guided and respiratory-synchronized proton therapy. LEVEL OF EVIDENCE 3: Local non-random sample.