Background: Low-kiloelectron volt (keV) virtual monochromatic images (VMIs) from low-dose (LD) dual-energy computed tomography (DECT) can enhance lesion contrast but suffer from high image noise. Recently, a deep learning image reconstruction (DLIR) algorithm has been developed and shown significant potential in suppressing image noise and improving image quality. To date, the capacity of LD low-keV thoracic-abdominal-pelvic DECT with DLIR to detect various types of tumor lesions have not been assessed. Hence, this study aimed to evaluate the image quality and lesion detection capabilities of LD VMIs using DLIR with thoracic-abdominal-pelvic DECT versus standard-dose (SD) iterative reconstruction (IR) in oncology patients. Methods: This prospective intraindividual study included 56 oncology patients who received a SD (13.86 mGy) and a consecutive LD (7.15 mGy) thoracic-abdominal-pelvic DECT from April 2022 to July 2023 at The First Affiliated hospital of Zhengzhou University. SD VMIs were reconstructed using IR at 50 keV (SD-IR50keV), 50 keV ), while LD VMIs were processed using DLIR at 50 keV (LD-DL50 keV) 50 k eV ) and 40 keV (LDDL40 40 keV), ), respectively. Quantitative image parameters [computed tomography (CT) values, image noise, and contrast-to-noise ratios (CNRs)], qualitative metrics (image noise, vessel conspicuity, image contrast, artificial sensation, and overall image quality), and lesion CNRs and conspicuity were compared. The lesion detection rates in the SD-IR50 50 keV, e V , LD-DL50 50 keV, e V , and LD-DL40 40 keV VMIs were assessed according to lesion location (lung, liver, and lymph), type, and size. Repeated measures analysis of variance and the Friedman test were applied for comparing quantitative and qualitative measures, respectively. The Cochran Q test was used for comparing lesion detection rates. Results: Compared to SD-IR50 50 keV VMIs, LD-DL50 50 keV VMIs showed similar CT values and image noise (P>0.05), similar (P>0.05) or higher(P<0.05) CNRs, similar (P>0.05) or superior (P<0.05) perceptual image quality, and similar (P>0.05) or higher (P<0.001) lesion CNR and conspicuity. LD-DL 40 keV VMIs exhibited higher CT values (by 40.4-47.1%) and CNRs (by 21.8-39.8%) (P<0.001), equivalent image noise, similar (P>0.05) or superior (P<0.05) perceptual image quality except for artificial sensation, and similar (P>0.05) or higher (P<0.001) lesion CNRs (by 16.5-46.3%) and conspicuity. The VMIs of LD-DL 50 keV and LD-DL 40 keV were consistent with those of SD-IR50 50 keV in terms of lesion detection capability in pulmonary nodules [SD-IR 50 keV vs. LD-DL 50 keV vs. LD-DL40 keV: 40 k eV : 88/88 (100.0%) vs. 88/88 (100.0%) vs. 88/88 (100.0%); P>0.99], for lymph nodes [125/126 (99.2%) vs. 123/126 (97.6%) vs. 124/126 (98.4%); P>0.05], and high-contrast liver lesions [12/12 (100.0%) vs. 12/12 (100.0%) vs. 12/12 (100.0%); P>0.05], but not for small liver lesions ( <= 0.5 cm) [63/65 (96.9%) vs. 43/65 (66.2%) vs. 51/65 (78.5%); P<0.05] or low-contrast liver lesions [198/200 (99.0%) vs. 174/200 (87.0%) vs. 183/200 (91.5%); P<0.05]. Conclusions: VMIs at 40 keV with DLIR enables a 50% decrease in the radiation dose while largely maintaining diagnostic capabilities for multidetection of pulmonary nodules, lymph nodes, and liver lesions in oncology patients.

OBJECTIVES:To assess image quality and liver metastasis detection of reduced-dose dual-energy CT (DECT) with deep learning image reconstruction (DLIR) compared to standard-dose single-energy CT (SECT) with DLIR or iterative reconstruction (IR). METHODS:In this prospective study, two groups of 40 participants each underwent abdominal contrast-enhanced scans with full-dose SECT (120-kVp images, DLIR and IR algorithms) or reduced-dose DECT (40- to 60-keV virtual monochromatic images [VMIs], DLIR algorithm), with 122 and 106 metastases, respectively. Groups were matched by age, sex ratio, body mass index, and cross-sectional area. Noise power spectrum of liver images and task-based transfer function of metastases were calculated to assess the noise texture and low-contrast resolution. The image noise, signal-to-noise ratios (SNR) of liver and portal vein, liver-to-lesion contrast-to-noise ratio (LLR), lesion conspicuity, lesion detection rate, and the subjective image quality metrics were compared between groups on 1.25-mm reconstructed images. RESULTS:Compared to 120-kVp images with IR, 40- and 50-keV VMIs with DLIR showed similar noise texture and LLR, similar or higher image noise and low-contrast resolution, improved SNR and lesion conspicuity, and similar or better perceptual image quality. When compared to 120-kVp images with DLIR, 50-keV VMIs with DLIR had similar low-contrast resolution, SNR, LLR, lesion conspicuity, and perceptual image quality but lower frequency noise texture and higher image noise. For the detection of hepatic metastases, reduced-dose DECT by 34% maintained observer lesion detection rates. CONCLUSION:DECT assisted with DLIR enables a 34% dose reduction for detecting hepatic metastases while maintaining comparable perceptual image quality to full-dose SECT. CLINICAL RELEVANCE STATEMENT:Reduced-dose dual-energy CT with deep learning image reconstruction is as accurate as standard-dose single-energy CT for the detection of liver metastases and saves more than 30% of the radiation dose. KEY POINTS:• The 40- and 50-keV virtual monochromatic images (VMIs) with deep learning image reconstruction (DLIR) improved lesion conspicuity compared with 120-kVp images with iterative reconstruction while providing similar or better perceptual image quality. • The 50-keV VMIs with DLIR provided comparable perceptual image quality and lesion conspicuity to 120-kVp images with DLIR. • The reduction of radiation by 34% by DLIR in low-keV VMIs is clinically sufficient for detecting low-contrast hepatic metastases.

目的:基于术前CT构建预测肝门部胆管癌(pCCA)神经侵犯(PNI)的影像组学模型,并评价其效能.方法:回顾性分析本院 2013 年 2 月-2021 年 2 月 149 例经病确诊的 pCCA 患者的临床资料,其中PNI组患者 108 例,无PNI组患者 41 例.采用R语言将所有患者按 3:1 比例随机分为训练集和验证集.在静脉期图像上,沿肿瘤边缘在所有层面上手动勾画 3D感兴趣区(ROI),使用 3D Slicer提取影像组学特征.采用组内相关系数(ICC)、相关性分析去除冗余特征,采用随机森林算法(RF)对所有临床、影像组学特征进行重要性排序,并选取前 18 个重要特征构建 RF 模型.使用准确性、敏感性、特异性及受试者操作特征(ROC)曲线评价模型效能.结果:在训练集中,RF 模型的准确性、敏感性、特异性均为 100%,ROC 曲线下面积 AUC 为 1;在验证集中,RF 模型的准确性为 70.3%,敏感性为59.3%,特异性为 100%,AUC 为 0.846(0.713～0.979).结论:基于增强 CT 图像建立的影像组学模型可用于术前无创性预测pCCA患者的PNI状态.

目的 探讨Revolution CT低管电压联合自适应迭代重建(ASIR)对胸部体模低剂量扫描图像质量的影响.方法 分别采用70 kV(低剂量,试验组)、80 kV(常规剂量,对照组)管电压,50 mAs自动管电流调节(ATCM)对体模进行多次扫描.胸部图像包括纵隔窗、肺窗2种.每组均进行0、30％、50％、80％、100％ASIR权重重建.测量不同管电压及ASIR值下心影、前胸壁的CT值及客观噪声,计算信噪比(SNR),并记录不同扫描条件中CT剂量指数(CTDIvol)、剂量长度乘积(DLP),计算有效辐射剂量(ED).客观因素分析辐射剂量,由两位影像科高年资医生对图像进行主观评价.应用SPSS22.0统计软件进行分析,采用Kappa检验,两位放射科医生主观评价的一致性.结果 随着ASIR权重增加,心影,前胸壁噪声(SD)减少,SNR增加.试验组SNR、CTDIvol、DLP、ED、主观评价得分均低于对照组,差异均有统计学意义(P＜0.05),两组影像主观评分均大于3分.结论 Revolution CT管电压70 kV,管电流50 mAs,结合ASIR技术可降低辐射剂量和噪声,同时使图像质量能满足诊断的要求.

PurposeThis study aimed to investigate the value of quantified extracellular volume fraction (fECV) derived from dual-energy CT (DECT) for predicting the survival outcomes of patients with hepatocellular carcinoma (HCC) after transarterial chemoembolization (TACE).Materials and methodsA total of 63 patients with HCC who underwent DECT before treatment were retrospectively included. Virtual monochromatic images (VMI) (70 keV) and iodine density images (IDI) during the equilibrium phase (EP) were generated. The tumor VMI-fECV and IDI-fECV were measured and calculated on the whole tumor (Whole) and maximum enhancement of the tumor (Maximum), respectively. Univariate and multivariate Cox models were used to evaluate the effects of clinical and imaging predictors on overall survival (OS) and progression-free survival (PFS).ResultsThe correlation between tumor VMI-fECV and IDI-fECV was strong (both p< 0.001). The Bland–Altman plot between VMI-fECV and IDI-fECV showed a bias of 5.16% for the Whole and 6.89% for the Maximum modalities, respectively. Increasing tumor VMI-fECV and IDI-fECV were positively related to the effects on OS and PFS (both p< 0.05). The tumor IDI-fECV-Maximum was the only congruent independent predictor in patients with HCC after TACE in the multivariate analysis on OS (p = 0.000) and PFS (p = 0.028). Patients with higher IDI-fECV-Maximum values had better survival rates above the optimal cutoff values, which were 35.42% for OS and 29.37% for PFS.ConclusionThe quantified fECV determined by the equilibrium-phase contrast-enhanced DECT can potentially predict the survival outcomes of patients with HCC following TACE treatment.

This study aimed to evaluate the image quality and lesion conspicuity of the deep learning image reconstruction (DLIR) algorithm compared with standard image reconstruction algorithms on abdominal enhanced computed tomography (CT) scanning with a wide range of body mass indexes (BMIs). A total of 112 participants who underwent contrast-enhanced abdominal CT scans were divided into three groups according to BMIs: the 80-kVp group (BMI ≤ 23.9 kg/m2), 100-kVp group (BMI 24–28.9 kg/m2), and 120-kVp group (BMI ≥ 29 kg/m2). All images were reconstructed using filtered back projection (FBP), adaptive statistical iterative reconstruction-V of 50 • DLIR improved the image quality and lesion conspicuity across a wide range of BMIs. • DLIR at medium level had the highest subjective parameters and lesion conspicuity scores among all reconstruction levels. • On the basis of the FBP, the 80-kVp group had improved image quality and lesion conspicuity more than the 100-kVp and 120-kVp groups.

To develop a CT-based radiomics model for preoperative prediction of lymph node (LN) metastasis in perihilar cholangiocarcinoma (pCCA). The study enrolled consecutive pCCA patients from three independent Chinese medical centers. The Boruta algorithm was applied to build the radiomics signature for the primary tumor and LN. The k-means algorithm was employed to cluster the selected LNs based on the radiomics signature LN. Support vector machines were used to construct the prediction models. The diagnostic efficiency was measured by the area under the receiver operating characteristic curve (AUC). The optimal model was evaluated in terms of calibration, clinical usefulness, and prognostic value. A total of 214 patients were included in the study (mean age: 61.6 years ± 9.4; 130 male). The selected LNs were classified into two clusters, which were significantly correlated with LN metastasis in all cohorts (p < 0.001). The model incorporated the clinical risk factors, radiomics signature primary tumor, and the LN cluster obtained the best discrimination, with AUC values of 0.981 (95 • The radiomics model based on contrast-enhanced CT is a useful tool for preoperative prediction of lymph node metastasis in perihilar cholangiocarcinoma. • Radiomics features extracted from lymph nodes show great potential for predicting lymph node metastasis. • The study is the first to identify a lymph node phenotype with a high probability of metastasis based on radiomics.

目的 探讨深度学习图像重建(DLIR)算法、多模型迭代重建(ASiR-V)算法和滤波反投影(FBP)算法在低管电压条件下对腹部平扫CT图像质量的影响.方法 前瞻性搜集因病情需要行全腹部CT平扫检查的 56 例患者,根据体质量指数(BMI)将入选患者分为A组(18 kg/m2≤BMI<24 kg/m2,管电压 80 kVp,n =29)、B组(24 kg/m2≤BMI<29 kg/m2,管电压100 kVp,n =27).所有图像数据均进行FBP、权重为50%的ASiR-V(ASiR-V50%)和高强度DLIR(DLIR-H)图像重建.采用Kruskal-Wallis H检验比较不同重建算法图像间的各项客观评价指标[噪声、肝脏和胰腺的信号噪声比(SNR)、肝脏和胰腺的对比噪声比(CNR)]和主观评价指标(噪声、总体图像质量),组内两两比较采用Bonferroni校正检验.结果 A组和B组的DLIR-H图像的噪声,肝脏、胰腺SNR均显著优于FBP和ASiR-V50%,差异均有统计学意义(P值均<0.05).在 80 kVp组和 100 kVp组,DLIR-H的噪声较FBP降低66.8%和68.7%,较ASiR-V50%降低46.1%和48.7%.DLIR-H肝脏和胰腺的CNR高于FBP,差异有统计学意义(P<0.05),DLIR-H 和 ASiR-V50%、ASiR-V50%和 FBP 间肝脏和胰腺的 CNR 差异无统计学意义(P 值均>0.05).主观评分上,A组和B组DLIR-H的主观噪声和总体图像质量高达4 分以上,均高于FBP和ASiR-V50%(P值均<0.05).结论 与ASiR-V50%和FBP相比,DLIR-H降低了图像噪声,提高了图像质量,在辐射剂量优化方面有更大的潜力.

Purpose The study aimed to construct and evaluate a CT-Based radiomics model for noninvasive detecting perineural invasion (PNI) of perihilar cholangiocarcinoma (pCCA) preoperatively. Materials and Methods From February 2012 to October 2021, a total of 161 patients with pCCA who underwent resection were retrospectively enrolled in this study. Patients were allocated into the training cohort and the validation cohort according to the diagnostic time. Venous phase images of contrast-enhanced CT were used for radiomics analysis. The intraclass correlation efficient (ICC), the correlation analysis, and the least absolute shrinkage and selection operator (LASSO) regression were applied to select radiomics features and built radiomics signature. Logistic regression analyses were performed to establish a clinical model, a radiomics model, and a combined model. The performance of the predictive models was measured by area under the receiver operating characteristic curve (AUC), and pairwise ROC comparisons between models were tested using the Delong method. Finally, the model with the best performance was presented as a nomogram, and its calibration and clinical usefulness were assessed. Results Finally, 15 radiomics features were selected to build a radiomics signature, and three models were developed through logistic regression. In the training cohort, the combined model showed a higher predictive capability (AUC = 0.950) than the radiomics model and the clinical model (AUC: radiomics = 0.914, clinical = 0.756). However, in the validation cohort, the AUC of the radiomics model (AUC = 0.885) was significantly higher than the other two models (AUC: combined = 0.791, clinical = 0.567). After comprehensive consideration, the radiomics model was chosen to develop the nomogram. The calibration curve and decision curve analysis (DCA) suggested that the nomogram had a good consistency and clinical utility. Conclusion We developed a CT-based radiomics model with good performance to noninvasively predict PNI of pCCA preoperatively.

近年来，CT图像算法中基于深度学习的图像重建（DLIR）技术不断发展，日益成熟，目前已经逐步应用于临床实践中。DLIR算法较常规迭代重建算法具有在降低辐射剂量和图像噪声的同时不改变图像纹理，保持或提高解剖细节显示能力、总体图像质量和医生诊断信心的众多优势。因此，笔者重点就DLIR算法的原理、优劣势及其在人体各系统的临床应用进展进行综述，旨在进一步提高对DLIR算法的认识，并对其可能的应用情景提供借鉴。

Objective:To investigate the efficiency of deep learning image reconstruction (DLIR) algorithm in the image quality and detection of hypovascular hepatic metastases under low radiation doses in comparison with adaptive statistical iterative construction-V (ASiR-V).Methods:Fifty-six patients with suspected hypovascular hepatic metastases who needed abdominal enhanced CT scans were collected prospectively in the First Affiliated Hospital of Zhengzhou University from January to April 2021. The patients received conventional radiation dose with tube current-time products of 400 mA CT scans in the first venous phase, low-dose CT scans in the second venous phase, which were set as tube current-time products of 280 mA for group A (19 cases), 200 mA for group B (19 cases) and 120 mA for group C (18 case), respectively. The images of first venous phase and 3 groups of second venous phase were both reconstructed with ASiR-V60% and high-DLIR (DLIR-H). Quantitative parameters [image noise, liver and portal vein signal to noise ratio (SNR), contrast to noise ratio (CNR)] and qualitative parameters (overall image quality, lesion conspicuity, diagnostic confidence) were compared between ASiR-V60% and DLIR-H images, and the effective radiation dose (ED) and the lesion detectability of each group was recorded. The paired t test was used to compare quantitative parameters, whereas the Wilcoxon signed-rank test of paired data was used to compare qualitative parameters. Results:In the second venous phase, ED was (5.56±0.35) mSv in group A, (3.88±0.23) mSv in group B, and (2.42±0.23) mSv in group C, with a decrease of 30%, 50% and 70% compared with the first venous phase, respectively. Moreover, with the decrease of radiation dose, the noise gradually increased, and the CNR lesions, SNR liver and SNR portal vein all gradually decreased. DLIR-H images had statistically better quantitative scores than ASiR-V60% images when the same radiation dose was applied (all P<0.001). Furthermore, the qualitative parameters of each group decreased with the decrease of radiation dose. Under the same radiation dose, the overall image quality, lesion conspicuity and diagnostic confidence of DLIR-H were higher than those of ASiR-V60% (all P<0.001). All lesions [100% (84/84)] were detected by ASIR-V60% and DLIR-H in group A, 92.0% (75/81) in group B, and 88.0% (79/89) in group C. Conclusions:Compared with ASiR-V60%, DLIR-H could reduce image noise, improve overall image quality and lesion conspicuity of hypovascular hepatic metastases as well as increase diagnostic confidence under different radiation doses.

目的 探讨低辐射剂量联合深度学习重建算法(DLIR)在提高肝转移图像质量和诊断能力中的应用价值.方法 前瞻性搜集因临床需要行上腹部CT增强检查的肝转移患者30例,静脉期采用标准辐射剂量扫描联合前置多模型迭代重建算法V(ASiR-V)40％算法行图像重建(对照组),加扫第二静脉期采用50％低辐射剂量扫描并联合DLIR算法三个强度水平[低(L)、中(M)、高(H)]行图像重建(实验组).对所有图像行客观评价[图像噪声、肝转移病灶的对比噪声比(CNR)、肝脏和门静脉的信噪比(SNR)]及主观评价[总体图像质量和病灶显示能力].采用单因素方差分析和Kruskal-Wallis H检验比较4组图像的客观和主观评价指标.结果 DLIR-L组的噪声高于ASiR-V40％组(P＜0.05),病灶CNR、肝脏和门静脉SNR、总体图像质量和病灶显示能力均低于ASiR-V40％,但两组的肝脏SNR与总体图像质量差异均无统计学意义.DLIR-M组和ASiR-V40％组的噪声、病灶CNR、肝脏和门静脉SNR、总体图像质量与病灶显示能力差异均无统计学意义.与ASiR-V40％组相比,DLIR-H组的噪声减低(P＜0.05),病灶CNR、肝脏和门静脉SNR和病灶显示能力相当,总体图像质量提高(P＜0.05).在DLIR 3组间,噪声随重建强度水平(DLIR-L、DLIR-M、DLIR-H)的升高而降低,总体图像质量和病灶显示能力随强度水平的提高而提高,且各组间差异有统计学意义(P＜0.05).病灶CNR、肝脏和门静脉SNR随DLIR强度的提高而降低,但仅DLIR-H与DLIR-L组差异有统计学意义(P＜0.05).结论 与ASiR-V40％相比,采用DLIR-H重建在减低50％辐射剂量条件下提高总体图像质量且保持肝转移病灶诊断能力不降低.

Background: Preoperative assessment of lymph node (LN) status is crucial for the optimal management of perihilar cholangiocarcinoma (pCCA).Methods: This retrospective study enrolled consecutive pCCA patients from three Chinese centers. Logistic regression was employed to identify clinical risk factors. The Boruta algorithm was applied to build radiomics signatures of the tumor and the selected LNs. Clustering was performed using the k-means algorithm based on the radiomics signature for the selected LNs. The prediction models were constructed using support vector machines. The diagnostic efficiency was quantified with the area under the receiver operating characteristic curve (AUC). The optimal model achieving the best AUC was further evaluated in calibration, clinical usefulness, and prognostic value.Findings: 214 patients were included in the study (61.6 years ± 9.4; 130 men). The selected LNs were classified into two clusters, which was significantly correlated with LN metastasis in all cohorts (P < 0.001). The model incorporated the clinical risk factors, the tumor radiomics, and the LN cluster obtained the best discrimination with AUC values of 0.981 (95% CI: 0.962, 1), 0.896 (95% CI: 0.810, 0.982), and 0.865 (95% CI: 0.768–0.961) in the training, internal validation, and external validation cohorts, respectively. Patients with a high risk of LN metastasis, predicted by the optimal model, had shorter overall survival than low-risk patients (median, 13.7 vs 27.3 months, P < 0.001).Interpretation: This study proposed a radiomics model with good performance to predict LN metastasis in pCCA. The radiomics model could inform treatment options and improve patient care.Funding Information: Supported by the Key Scientific Research Project of Higher Education in Henan Province (No.22A320057).Declaration of Interests: We declare no conflicts of interest.Ethics Approval Statement: This multicenter retrospective study was approved by the Ethics Committee (2021-KY-0778-001), and written informed consent was waived.

To compare the image quality and hepatic metastasis detection of low-dose deep learning image reconstruction (DLIR) with full-dose filtered back projection (FBP)/iterative reconstruction (IR). A contrast-detail phantom consisting of low-contrast objects was scanned at five CT dose index levels (10, 6, 3, 2, and 1 mGy). A total of 154 participants with 305 hepatic lesions who underwent abdominal CT were enrolled in a prospective non-inferiority trial with a three-arm design based on phantom results. Data sets with full dosage (13.6 mGy) and low dosages (9.5, 6.8, or 4.1 mGy) were acquired from two consecutive portal venous acquisitions, respectively. All images were reconstructed with FBP (reference), IR (control), and DLIR (test). Eleven readers evaluated phantom data sets for object detectability using a two-alternative forced-choice approach. Non-inferiority analyses were performed to interpret the differences in image quality and metastasis detection of low-dose DLIR relative to full-dose FBP/IR. The phantom experiment showed the dose reduction potential from DLIR was up to 57 • Radiation dose levels for DLIR can be reduced to 50 • The reduction of radiation by 70