Contrast-enhanced CT Examinations Research Articles

N-(2,3-dihydroxypropyl) carbamoyl side chain: a potentially significant factor for recurrent iodinated contrast medium-related adverse drug reactions.

To determine whether switching to contrast media based on the sharing of N-(2,3-dihydroxypropyl) carbamoyl side chain reduces the recurrence of iodinated contrast media (ICM)-associated adverse drug reactions (ADRs). This single-center retrospective study included 2133 consecutive patients (mean age ± SD, 56.1 ± 11.4 years; male, 1052 [49.3%]) who had a history of ICM-associated ADRs and underwent contrast-enhanced CT examinations. The per-patient and per-exam-based recurrence ADR rates were compared between cases of switching and non-switching the ICM from ICMs that caused the previous ADRs, and between cases that used ICMs with common and different carbamoyl side chains from ICMs that caused the previous ADRs. Downgrade rates (no recurrence or the occurrence of ADR less severe than index ADRs) were also compared. Propensity score matching (PSM) and inverse probability of treatment weighting (IPTW) analysis were additionally performed. In per-patient analysis, switching of ICM showed a lower recurrence rate (switching, 10.4% [100/965] vs. non-switching, 28.4% [332/1168]), with the adjusted odds ratio (OR) of 0.27 (95% CI: 0.21, 0.34; p < 0.001). The result was consistent in PSM (OR, 0.29 [95% CI: 0.22, 0.39]; p < 0.001), IPTW (OR, 0.28 [95% CI: 0.22, 0.36]; p < 0.001), and in per-exam analysis (5.5% vs. 13.8%; OR, 0.32 [95% CI: 0.27, 0.37]; p < 0.001). There was lower per-exam recurrence (5.0% [195/3938] vs. 7.8% [79/1017]; OR, 0.63 [95% CI: 0.47, 0.83]; p = 0.001) and higher downgrade rates (95.6% [3764/3938] vs. 93.3% [949/1017]; OR, 1.51 [95% CI: 1.12, 2.03]; p = 0.006) when using different side chain groups. Switching to an ICM with a different carbamoyl side chain reduced the recurrent ADRs and their severity during subsequent examinations. Switching to an iodinated contrast media with a different carbamoyl side chain reduced the recurrent adverse drug reactions and their severity during subsequent examinations.

99mTc-FAPI-04 SPECT/CT outperforms contrast-enhanced CT in detecting metastasis in postoperative patients with colorectal cancer.

To compare the performance of 99mTc-FAPI-04 SPECT/CT and contrast-enhanced CT (CECT) in the detection of postoperative metastasis in patients with colorectal cancer (CRC). The postoperative patients with CRC were consecutively recruited from January 2023 to June 2023, and the enrolled patients completed 99mTc-FAPI-04 SPECT/CT imaging and CECT examination within two weeks. Histopathological analysis and the follow-up results were used as the reference criteria. The location and number of metastatic sites and the detection accuracy between the two imaging methods were compared. The tumor-to-background ratio (TBR) of liver metastasis and lymph node metastasis in 99mTc-FAPI-04 SPECT/CT imaging were also calculated for comparison. In total, 19 postoperative CRC patients, including 15 patients with metastasis, were included in this study. In the patient-based analysis, 99mTc-FAPI-04 SPECT/CT showed a significantly higher sensitivity for the detection of metastasis than CECT (93.3% vs. 80.0%, p = 0.038), but both techniques had the same specificity (100%, 4/4). For the lesion-based analysis, the detection rates of metastatic sites were 92.2% (47/51) and 72.5% (37/51) for 99mTc-FAPI-04 SPECT/CT and CECT, respectively, and the difference between them was statistically significant. In the diagnosis of liver metastasis and lymph node metastasis, 99mTc-FAPI-04 SPECT/CT both exceeded CECT. Additionally, the TBR in lymph node metastasis was higher than that in liver metastasis. The findings suggested that 99mTc-FAPI-04 SPECT/CT could detect metastasis more effectively than CECT, especially liver and lymph node metastases, in postoperative CRC patients.

Prospective Evaluation of Artificial Intelligence Triage of Incidental Pulmonary Emboli on Contrast-Enhanced CT Examinations of the Chest or Abdomen.

BACKGROUND. Artificial intelligence (AI) algorithms improved detection of incidental pulmonary embolism (IPE) on contrast-enhanced CT (CECT) examinations in retrospective studies; however, prospective validation studies are lacking. OBJECTIVE. The purpose of this study was to assess the effect on radiologists' real-world diagnostic performance and report turnaround times of a radiology department's clinical implementation of an AI triage system for detecting IPE on CECT examinations of the chest or abdomen. METHODS. This prospective single-center study included consecutive adult patients who underwent CECT of the chest or abdomen for reasons other than pulmonary embolism (PE) detection from May 12, 2021, to June 30, 2021 (phase 1), or from September 30, 2021, to December 4, 2021 (phase 2). Before phase 1, the radiology department installed a commercially available AI triage algorithm for IPE detection that automatically processed CT examinations and notified radiologists of positive results through an interactive floating widget. In phase 1, the widget was inactive, and radiologists interpreted examinations without AI assistance. In phase 2, the widget was activated, and radiologists interpreted examinations with AI assistance. A review process involving a panel of radiologists was implemented to establish the reference standard for the presence of IPE. Diagnostic performance and report turnaround times were compared using the Pearson chi-square test and Wilcoxon rank sum test, respectively. RESULTS. Phase 1 included 1467 examinations in 1434 patients (mean age, 53.8 ± 18.5 [SD] years; 753 men, 681 women); phase 2 included 3182 examinations in 2886 patients (mean age, 55.4 ± 18.2 years; 1520 men, 1366 women). The frequency of IPE was 1.4% (20/1467) in phase 1 and 1.6% (52/3182) in phase 2. Radiologists without AI, in comparison to radiologists with AI, showed significantly lower sensitivity (80.0% vs 96.2%, respectively; p = .03), without a significant difference in specificity (99.9% vs 99.9%, p = .58), for the detection of IPE. The mean report turnaround time for IPE-positive examinations was not significantly different between radiologists without AI and radiologists with AI (78.3 vs 74.6 minutes, p = .26). CONCLUSION. An AI triage system improved radiologists' sensitivity for IPE detection on CECT examinations of the chest or abdomen without significant change in report turnaround times. CLINICAL IMPACT. This prospective real-world study supports the use of AI assistance for maximizing IPE detection.

Improved detection of small pulmonary embolism on unenhanced computed tomography using an artificial intelligence-based algorithm - a single centre retrospective study.

To preliminarily verify the feasibility of a deep-learning (DL) artificial intelligence (AI) model to localize pulmonary embolism (PE) on unenhanced chest-CT by comparison with pulmonary artery (PA) CT angiography (CTA). In a monocentric study, we retrospectively reviewed 99 oncological patients (median age in years: 64 (range: 28-92 years); percentage of female: 39.4%) who received unenhanced and contrast-enhanced chest CT examinations in one session between January 2020 and October 2022 and who were diagnosed incidentally with PE. Findings in the unenhanced images were correlated with the contrast-enhanced images, which were considered the gold standard for central, segmental and subsegmental PE. The new algorithm was trained and tested based on the 99 unenhanced chest-CT image data sets. Based on them, candidate boxes, which were output by the model, were post-processed by evaluating whether the predicted box intersects with the patient's lung segmentation at any position. The AI-based algorithm proved to have an overall sensitivity of 54.5% for central, of 81.9% for segmental and 80.0% for subsegmental PE if taking n = 20 candidate boxes into account. Depending on the localization of the pulmonary embolism, the detection rate for only one box was: 18.1% central, 34.7% segmental and 0.0% subsegmental. The median volume of the clots differed significantly between the three subgroups and was 846.5 mm3 (IQR:591.1-964.8) in central, 201.3 mm3 (IQR:98.3-390.9) in segmental and 110.6 mm3 (IQR:94.3-128.0) in subsegmental PA (p < 0.05). The new algorithm proved to have high sensitivity in detecting PE in particular in segmental/subsegmental localization and may guide to decide whether a second contrast enhanced CT is necessary.

CT Surveillance for Local Recurrence After Pancreatic Cancer Resection: Evaluation of Imaging Findings From the SAR Disease-Focused Panel Consensus Statement.

Background: A Society of Abdominal Radiology (SAR) Pancreatic Ductal Adenocarcinoma (PDAC) Disease-Focused Panel (DFP) consensus statement described findings suspicious for local recurrence (LR) on surveillance imaging after PDAC resection. Objective: To evaluate the interreader agreement and predictive utility of potential imaging findings of LR on serial surveillance CT examinations after Whipple procedure for PDAC, using the SAR PDAC DFP consensus statement. Methods: This retrospective study included 126 patients (mean age, 68.5±10.3 years; 72 men, 54 women) who underwent Whipple surgery for PDAC between January 2009 and December 2014. Three radiologists independently reviewed baseline and subsequent postoperative contrast-enhanced abdominopelvic CT examinations performed within 2 years postoperatively, evaluating features in the SAR PDAC DFP consensus statement relating to surgical bed stranding, surgical bed soft tissue, vessel encasement, main pancreatic duct dilatation, and ascites. Interreader agreement was calculated. The reference standard for LR development within 2 years postoperatively incorporated all available information. Imaging features' frequencies were calculated for recurrence examinations (i.e., first surveillance examinations indicating LR). For baseline postoperative examinations, features associations' with eventual LR development were assessed by multivariable logistic regression analysis. Results: LR developed within 2 years postoperatively in 81/126 patients. For both baseline and subsequent examinations, agreement for stranding and soft tissue morphology were poor, for vessel encasement was fair, for soft tissue and ascites were moderate, and for main pancreatic duct dilatation was substantial. On recurrence examinations, across readers, new or increased stranding was present in 27-77%; new or increased soft tissue, 80-86%; soft tissue with vessel encasement and luminal narrowing, 36-59%; new or increased main pancreatic duct dilatation, 25-26%; and new or increased ascites, 20-23%. On baseline postoperative examinations, independent predictors of eventual LR were soft tissue for all three readers (OR=2.78-6.85) and stranding for reader 1 (OR=3.59); main pancreatic duct dilatation and ascites were not independent predictors of LR for any reader. Conclusion: This study highlights the role of soft tissue, particularly when associated with vessel encasement and luminal narrowing, in raising suspicion for LR after PDAC resection. Clinical Impact: This study supports the SAR PDAC DFP consensus statement, while highlighting opportunities for continued optimization.

Automatic vessel attenuation measurement for quality control of contrast-enhanced CT: Validation on the portal vein.

Adequate image enhancement of organs and blood vessels of interest is an important aspect of image quality in contrast-enhanced computed tomography (CT). There is a need for an objective method for evaluation of vessel contrast that can be automatically and systematically applied to large sets of CTexams. The purpose of this work was to develop a method to automatically segment and measure attenuation Hounsfield Unit (HU) in the portal vein (PV) in contrast-enhanced abdomen CTexaminations. Input CT images were processed by a vessel enhancing filter to determine candidate PV segmentations. Multiple machine learning (ML) classifiers were evaluated for classifying a segmentation as corresponding to the PV based on segmentation shape, location, and intensity features. A public data set of 82 contrast-enhanced abdomen CT examinations was used to train the method. An optimal ML classifier was selected by training and tuning on 66 out of the 82 exams (80% training split) in the public data set. The method was evaluated in terms of segmentation classification accuracy and PV attenuation measurement accuracy, compared to manually determined ground truth, on a test set of the remaining 16 exams (20% test split) held out from public data set. The method was further evaluated on a separate, independently collected test set of 21examinations. The best classifier was found to be a random forest, with a precision of 0.892 in the held-out test set to correctly identify the PV from among the input candidate segmentations. The mean absolute error of the measured PV attenuation relative to ground truth manual measurement was 13.4HU. On the independent test set, the overall precision decreased to 0.684. However, the PV attenuation measurement remained relatively accurate with a mean absolute error of 15.2HU. The method was shown to accurately measure PV attenuation over a large range of attenuation values, and was validated in an independently collected dataset. The method did not require time-consuming manual contouring to supervise training. The method may be applied to systematic quality control of contrast-enhanced CTexaminations.

조영 증강 CT 검사 시 금식 여부에 따른 조영제 과민반응 사례 비교

Contrast agent is a medication that aids in diagnosis by enhancing the visibility of tissues or blood vessels during a CT scan. However, to prevent hypersensitivity reactions, patients were inconvenienced by having to fast for more than a few hours before the contrast-enhanced CT examination. Recently, the importance of fasting is gradually diminishing as indicated by numerous studies. Our hospital has also revised the fasting guidelines accordingly. As a result, tests other than the abdomen test are now being conducted without requiring fasting. The number of cases of hypersensitivity reactions and nausea before and after the revision was not significant, and retesting did not occur either. Currently, many hospitals in Korea are implementing various fasting guidelines before contrast-enhanced CT scans. It is urgently necessary to revise these guidelines in accordance with the recently announced trend.

조영증강 복부 CT 검사에서 조영제 사용량 감소에 관한 연구

In our hospital, we implement a reduction in contrast media dose (calculated as body weight × 1.2 mL) for clinical examinations conducted with dual-source dual-energy CT during contrast-enhanced abdominal CT examinations. Therefore, by applying the CE-Boost technique, the degree of contrast enhancement of blood vessels and tissues was compared with standard contrast media dose (body weight × 1.6 mL) in 120 kV single-source computed tomography images. In contrast-enhanced abdominal CT using the standard contrast media dose, the CE-Boost technique was applied to investigate the feasibility of reducing the contrast media dose. From January 2023, a retrospective study was conducted on 62 subjects. The study included an experimental group (A) that received a reduced contrast media dose, an experimental group + CE-Boost (B), and a control group (C) that received the standard contrast media dose. For quantitative evaluation, in the image where the Main Portal Vein (MPV) is the widest, CT number (HU), Signal-to-Noise Ratio (SNR), and Contrast-to-Noise Ratio (CNR) were calculated. Qualitative evaluation was independently assessed by five experienced radiotechnologists, who evaluated 10 samples as the assessment items for contrast enhancement and overall image quality. In the HU values, the (B) group with CE-Boost technique showed the highest value (P &lt; .05), while the (A)-(C) group without CE-Boost technique showed no statistically significant difference. In the SNR, the group (B) that received the CE-Boost technique exhibited the highest value,(P&lt;.05) but there was no significant difference compared to the group (C) that did not receive the CE-Boost technique in the evaluation of liver parenchyma.(P&gt;.05) In CNR, the (B) group utilizing the CE-Boost technique showed the highest value (P&lt;.05), but there was no statistically significant difference between (B) and (C). In the qualitative evaluation, the group (B) to which CE-Boost was applied was rated the highest in two evaluation items. If an AI-based CE-Boost technique is used for contrast-enhanced abdominal CT, it is believed that safe medical services can be provided to patients by implementing a 25% reduction in the standard contrast media dose while still maintaining image quality, even in a single-source 120kV CT.

A SICE (Società Italiana di Chirurgia Endoscopica e Nuove Tecnologie) observational prospective multicenter study on anatomical variants of the superior mesenteric artery: intraoperative analysis during laparoscopic right hemicolectomy-CoDIG 2 database (ColonDx Italian Group).

Colorectal cancer, the third most common cancer worldwide, affects 40-45% of patients on the right side. Surgery, especially minimally invasive methods such as laparoscopic and robotic procedures, is the preferred treatment. However, these techniques present technical complications. The anatomical complexity and variations in vessel branching patterns pose challenges, particularly for less experienced surgeons. The CoDIG 2 is a nationwide observational study involving 76 specialized Italian general surgery departments focused on colorectal surgery. The centres were directed to maintain their standard surgical and clinical practices. The aim of this study was to analyse the intraoperative vascular anatomy of Italian patients who underwent laparoscopic right colectomy and explore the ligature techniques used by Italian surgeons. Surgeons reported information about vascularization of the right colon for 616 patients and about surgical anatomy of RCA for 368 patients. Fifty-three patients (10.8%) showed no RCA intraoperatively. The right colic artery (RCA) was categorized according to the Yada classification (types 1-4) during evaluation, and intraoperative assessments revealed that Yada type 1 was the most common type (55.2%), while radiologic evaluations revealed a higher prevalence of type 2. Furthermore, compared with the superior mesenteric vein (SMV), the RCA is more often located anteriorly according to intraoperative and contrast-enhancedCT examination; 59.9% were found in the anterior position during intraoperative examination, while 40.1% were found in the same position on preoperative contrast-enhanced CT. Vascularization of the right colon, including missing branches, additional branches, shared trunks, and retro-superior courses of the mesenteric vein, exhibited notable variations. To understand vascular variations, a preoperative radiological study is necessary; although there was no concordance between the intraoperative and radiological evaluations, this is a limitation of preinterventional radiological evaluation (PII) because it is always needed for oncological staging. This approach is especially critical for inexperienced surgeons to avoid potential complications, such as problematic bleeding.

Pancreatic cyst prevalence and detection with photon counting CT compared with conventional energy integrating detector CT

PurposeTo calculate the prevalence of pancreatic cysts on photon counting CT (PCCT) and compare with that of 128-slice conventional energy-integrating detector CT (EIDCT). MethodA retrospective single institution database search identified all contrast-enhanced abdominal CT examinations performed at an outpatient facility that has both a PCCT and EIDCT between 4/11/2022 and 7/26/2022. The presence and size of pancreatic cysts were recorded. In patients with PCCT reported pancreatic cysts, prior CT imaging (EIDCT) was reviewed for reported pancreatic cysts. Fisher’s exact test was used to compare the pancreatic cyst detection rate for PCCT and EIDCT. Wilcoxon rank sum test was used to compare cyst size and patient age. A p <.05 indicated statistical significance. Results2494 patients were included. Our pancreatic cyst detection rate was 4.9 % (49/1009) with PCCT and 3.0 % (44/1485) for EIDCT (p =.017). For CT angiograms, pancreatic cysts were detected in 6.6 % (21/319) with PCCT and 0.0 % (0/141) with EIDCT (p <.001). Pancreatic cyst detection rate was not statistically different for portal venous, enterography, renal mass, pancreas, 3-phase liver, or venogram protocols (all p >.05). Mean[SD] pancreatic cyst size was 13.7[9.7]mm for PCCT and 15.3[14.7] for EIDCT (p =.95). 55.1 % (27/49) of PCCT and 61.4 % (27/44) of EIDCT that described pancreatic cysts had prior contrast-enhanced EIDCTs. Of these, 40.7 % (11/27) of PCCT and 14.8 % (4/27) of EIDCT described pancreatic cysts were not previously reported (p =.027). ConclusionsPhoton-counting CT afforded greater pancreatic cyst detection than conventional energy-integrating detector CT, particularly with CT angiograms.

Safety of Administering Intravenous CT Contrast Agents Repeatedly or Using Both CT and MRI Contrast Agents on the Same Day: An Animal Study.

To investigate molecular and functional consequences of additional exposures to iodine- or gadolinium-based contrast agents within 24 hours from the initial intravenous administration of iodine-based contrast agents through an animal study. Fifty-six Sprague-Dawley male rats were equally divided into eight groups: negative control, positive control (PC) with single-dose administration of CT contrast agent, and additional administration of either CT or MR contrast agents 2, 4, or 24 hours from initial CT contrast agent injection. A 12 µL/g of iodinated contrast agent or a 0.47 µL/g of gadolinium-based contrast agent were injected into the tail vein. Serum levels of blood urea nitrogen, creatinine, cystatin C (Cys C), and malondialdehyde (MDA) were measured. mRNA and protein levels of kidney injury molecule-1 (KIM-1) and neutrophil gelatinase-associated lipocalin (NGAL) were evaluated. Levels of serum creatinine (SCr) were significantly higher in repeated CT contrast agent injection groups than in PC (0.21 ± 0.02 mg/dL for PC; 0.40 ± 0.02, 0.34 ± 0.03, and 0.41 ± 0.10 mg/dL for 2-, 4-, and 24-hour interval groups, respectively; P < 0.001). There was no significant difference in the average Cys C and MDA levels between PC and repeated CT contrast agent injection groups (Cys C, P = 0.256-0.362; MDA, P > 0.99). Additional doses of MR contrast agent did not make significant changes compared to PC in SCr (P > 0.99), Cys C (P = 0.262), and MDA (P = 0.139-0.771) levels. mRNA and protein levels of KIM-1 and NGAL were not significantly different among additional CT or MR contrast agent groups (P > 0.05). A sufficient time interval, probably more than 24 hours, between repeated contrast-enhanced CT examinations may be necessary to avoid deterioration in renal function. However, conducting contrast-enhanced MRI on the same day as contrast-enhanced CT may not induce clinically significant kidney injury.

Association between acute adverse reactions to iodinated contrast media and anxiety in patients undergoing contrast-enhanced CT examination.

As the use of iodinated contrast media has become more widely with advances in imaging, several guidelines have suggested that anxiety increases the risk of acute adverse reactions associated with iodinated contrast media. This study aims to evaluate the impact of anxiety on the occurrence of acute adverse reactions (AAR) to iodinated contrast media in patients undergoing contrast-enhanced CT examinations. Inpatients who underwent contrast-enhanced CT examinations at the Third Xiangya Hospital between February and October 2021 were prospectively recruited. Prior to the imaging examinations, all patients completed the Generalized Anxiety Disorder Scale-7 (GAD-7) assessment before the imaging examinations to determine the severity of anxiety, which was categorized as mild, moderate, or severe. Based on the occurrence of AAR, patients were classified into an AAR group and a non-AAR group. The difference in anxiety was compared between the 2 groups. Multivariate logistic regression analysis was used to identify independent risk factors associated with AAR. To ensure comparability between the 2 groups, propensity score matching (PSM) was utilized to align the clinical characteristics. Subsequently, the difference in anxiety within the matched groups was analyzed. The study comprised 880 patients, with 80 patients in the AAR group and 800 patients in the non-AAR group. There was a significant difference in proportion of patients with mild-severe anxiety between the 2 groups (75% in the AAR group and 36% in the non-AAR group, P<0.001). Additionally, differences were also observed in occupation, income, underlying diseases, and allergy history (all P<0.001). The results of multivariate logistic regression analysis revealed that patients' income, allergy history, and anxiety were independent risk factors for AAR to iodinated contrast media (all P<0.05). Following PSM, each matched group included 66 cases, and no significant differences in clinical characteristics were observed between the 2 groups (all P>0.05). However, the proportion of patients with mild-severe anxiety remained significantly higher in the AAR group compared to the non-AAR group (75% in the AAR group and 31% in the non-AAR group, P<0.001). Anxiety is associated with an increased risk of AAR to iodinated contrast media in patients undergoing contrast-enhanced CT examinations, suggesting the clinical importance of screening for anxiety before imaging examinations.

Development and Validation of a Risk Model for Predicting Contrast-Associated Acute Kidney Injury in Patients With Cancer: Evaluation in Over 46,000 CT Examinations.

BACKGROUND. Patients with cancer undergo frequent CT examinations with iodinated contrast media and may be uniquely predisposed to contrast-associated acute kidney injury (CA-AKI). OBJECTIVE. The purpose of this study was to develop and validate a model for predicting the risk of CA-AKI after contrast-enhanced CT in patients with cancer. METHODS. This retrospective study included 25,184 adult patients (12,153 men, 13,031 women; mean age, 62.3 ± 13.7 [SD] years) with cancer who underwent 46,593 contrast-enhanced CT examinations between January 1, 2016, and June 20, 2020, at one of three academic medical centers. Information was recorded regarding demographics, malignancy type, medication use, baseline laboratory values, and comorbid conditions. CA-AKI was defined as a 0.3-mg/dL or greater increase in serum creatinine level from baseline within 48 hours after CT or a 1.5-fold or greater increase in the peak measurement within 14 days after CT. Multivariable models accounting for correlated data were used to identify risk factors for CA-AKI. A risk score for predicting CA-AKI was generated in a development set (n = 30,926) and tested in a validation set (n = 15,667). RESULTS. CA-AKI occurred after 5.8% (2682/46,593) of CT examinations. The final multivariable model for predicting CA-AKI included hematologic malignancy, diuretic use, angiotensin-converting enzyme inhibitor or angiotensin receptor blocker use, chronic kidney disease (CKD) stage 3a, CKD stage 3b, CKD stage 4 or 5, serum albumin level less than 3.0 g/dL, platelet count less than 150 × 103/μL, 1+ or greater proteinuria on baseline urinalysis, diabetes mellitus, heart failure, and contrast medium volume 100 mL or greater. A risk score (range, 0-53 points) was generated with these variables. The most points (13) were for CKD stage 4 or 5 and for albumin level less than 3 g/dL. The frequency of CA-AKI progressively increased in higher risk categories. For example, in the validation set, CA-AKI occurred after 2.2% of CT examinations in the lowest risk category (score ≤ 4) and after 32.7% of CT examinations in the highest risk category (score ≥ 30). The Hosmer-Lemeshow test result indicated that the risk score was a good fit (p = .40). CONCLUSION. A risk model in which readily available clinical data are used to predict the likelihood of CA-AKI after contrast-enhanced CT in patients with cancer was developed and validated. CLINICAL IMPACT. The model may help facilitate appropriate implementation of preventive measures in the care of patients at high risk of CA-AKI.

A CT-Based Clinical, Radiological and Radiomic Machine Learning Model for Predicting Malignancy of Solid Renal Tumors (UroCCR-75).

Differentiating benign from malignant renal tumors is important for patient management, and it may be improved by quantitative CT features analysis including radiomic. This study aimed to compare performances of machine learning models using bio-clinical, conventional radiologic and 3D-radiomic features for the differentiation of benign and malignant solid renal tumors using pre-operative multiphasic contrast-enhanced CT examinations. A unicentric retrospective analysis of prospectively acquired data from a national kidney cancer database was conducted between January 2016 and December 2020. Histologic findings were obtained by robotic-assisted partial nephrectomy. Lesion images were semi-automatically segmented, allowing for a 3D-radiomic features extraction in the nephrographic phase. Conventional radiologic parameters such as shape, content and enhancement were combined in the analysis. Biological and clinical features were obtained from the national database. Eight machine learning (ML) models were trained and validated using a ten-fold cross-validation. Predictive performances were evaluated comparing sensitivity, specificity, accuracy and AUC. A total of 122 patients with 132 renal lesions, including 111 renal cell carcinomas (RCCs) (111/132, 84%) and 21 benign tumors (21/132, 16%), were evaluated (58 +/- 14 years, men 74%). Unilaterality (100/111, 90% vs. 13/21, 62%; p = 0.02), necrosis (81/111, 73% vs. 8/21, 38%; p = 0.02), lower values of tumor/cortex ratio at portal time (0.61 vs. 0.74, p = 0.01) and higher variation of tumor/cortex ratio between arterial and portal times (0.22 vs. 0.05, p = 0.008) were associated with malignancy. A total of 35 radiomics features were selected, and "intensity mean value" was associated with RCCs in multivariate analysis (OR = 0.99). After ten-fold cross-validation, a C5.0Tree model was retained for its predictive performances, yielding a sensitivity of 95%, specificity of 42%, accuracy of 87% and AUC of 0.74. Our machine learning-based model combining clinical, radiologic and radiomics features from multiphasic contrast-enhanced CT scans may help differentiate benign from malignant solid renal tumors.

Age-related morphometrics of normal adrenal glands based on deep learning-aided segmentation

Objective.This study aims to evaluate the morphometrics of normal adrenal glands in adult patients semiautomatically using a deep learning-based segmentation model.Materials and Methods.A total of 520 abdominal CT image series with normal findings, from January 1, 2016, to March 14, 2019, were retrospectively collected for the training of the adrenal segmentation model. Then, 1043 portal venous phase image series of inpatient contrast-enhanced abdominal CT examinations with normal adrenal glands were included for analysis and grouped by every 10-year gap. A 3D U-Net-based segmentation model was used to predict bilateral adrenal labels followed by manual modification of labels as appropriate. Quantitative parameters (volume, CT value, and diameters) of the bilateral adrenal glands were then analyzed.Results.In the study cohort aged 18–77 years old (554 males and 489 females), the left adrenal gland was significantly larger than the right adrenal gland [all patients, 2867.79 (2317.11–3499.89) mm3 vs. 2452.84 (1983.50–2935.18) mm3, P < 0.001]. Male patients showed a greater volume of bilateral adrenal glands than females in all age groups (all patients, left: 3237.83 ± 930.21 mm3 vs. 2646.49 ± 766.42 mm3, P < 0.001; right: 2731.69 ± 789.19 mm3 vs. 2266.18 ± 632.97 mm3, P = 0.001). Bilateral adrenal volume in male patients showed an increasing then decreasing trend as age increased that peaked at 38–47 years old (left: 3416.01 ± 886.21 mm3, right: 2855.04 ± 774.57 mm3).Conclusions.The semiautomated measurement revealed that the adrenal volume differs as age increases. Male patients aged 38–47 years old have a peaked adrenal volume.

External validation of a machine learning based algorithm to differentiate hepatic mucinous cystic neoplasms from benign hepatic cysts.

To externally validate an algorithm for non-invasive differentiation of hepatic mucinous cystic neoplasms (MCN) from benign hepatic cysts (BHC), which differ in management. Patients with cystic liver lesions pathologically confirmed as MCN or BHC between January 2005 and March 2022 from multiple institutions were retrospectively included. Five readers (2 radiologists, 3 non-radiologist physicians) independently reviewed contrast-enhanced CT or MRI examinations before tissue sampling and applied the 3-feature classification algorithm described by Hardie et al. to differentiate between MCN and BHC, which had a reported accuracy of 93.5%. The classification was then compared to the pathology results. Interreader agreement between readers across different levels of experience was evaluated with Fleiss' Kappa. The final cohort included 159 patients, median age of 62years (IQR [52.0, 70.0]), 66.7% female (106). Of all patients, 89.3% (142) had BHC, and the remaining 10.7% (17) had MCN on pathology. Agreement for class designation between the radiologists was almost perfect (Fleiss' Kappa 0.840, p < 0.001). The algorithm had an accuracy of 98.1% (95% CI [94.6%, 99.6%]), a positive predictive value of 100.0% (95% CI [76.8%, 100.0%]), a negative predictive value of 97.9% (95% CI [94.1%, 99.6%]), and an area under the receiver operator characteristic curve (AUC) of 0.911 (95% CI [0.818, 1.000]). The evaluated algorithm showed similarly high diagnostic accuracy in our external, multi-institutional validation cohort. This 3-feature algorithm is easily and rapidly applied and its features are reproducible among radiologists, showing promise as a clinical decision support tool.

Clinical Follow-up in Patients With Moderate or Severe Allergic-Like Reactions to Iodinated Contrast Material

ObjectiveTo examine follow-up care in patients with a history of acute allergic-like reaction to iodinated contrast material (ICM), including subsequent imaging management, allergy consultation, and repeat ICM exposure and reactions. MethodsAll patients who had a moderate or severe acute allergic-like reaction to ICM after contrast-enhanced CT (CECT) examination from June 1, 2009, to January 1, 2022, at our institution were included. Chart review was performed to determine (1) whether subsequent imaging was not performed or was altered in these patients, (2) whether the patient underwent a subsequent CECT examination, and (3) whether the patient had an allergist consultation. ResultsA total of 251 patients were identified. One-third of patients (90 of 251, 36%) had at least one change to their subsequent imaging management due to their reaction, including performing an unenhanced CT (62 of 251, 25%) or MRI (22 of 251, 8.8%) instead of a CECT or not performing a CECT when otherwise clinically indicated (20 of 251, 8.0%). Patients with a prior severe reaction were more likely to have a change in management than patients with a prior moderate reaction (severe: 22 of 32 [69%] versus moderate: 68 of 219 [31%], P < .0001). Only 17 patients (6.8%) had an allergy consult for their ICM reaction. A total of 90 patients underwent 274 subsequent CECT examinations. Repeat allergic-like reactions were observed in one quarter of patients (24 of 90, 27%) and a tenth of CECT examinations (29 of 274, 11%). DiscussionOne-third of patients with a history of a moderate or severe allergic-like reaction to ICM had their subsequent imaging care modified due to their reaction.

Outcomes of Bosniak Classification Version 2019 Class IIF Cystic Renal Masses at Imaging Surveillance.

BACKGROUND. Bosniak classification system version 2019 (v2019) recommends that class IIF masses undergo follow-up imaging at 6 months, 12 months, and then annually for 5 years. The frequency and timing of upgrade on follow-up imaging are incompletely understood. OBJECTIVE. The purpose of this article is to describe the temporal evolution of Bosniak v2019 class IIF cystic renal masses, with attention to outcomes at 6-month follow-up, the time to class upgrade, and malignant histologic diagnoses. METHODS. This retrospective study included 219 patients (91 women, 128 men; median age, 72 years) with 246 localized class IIF masses from January 2005 to June 2022. Patients underwent both a baseline and at least one follow-up renal-mass protocol contrast-enhanced CT or MRI examination. Two radiologists evaluated masses at all follow-up time points to categorize masses as downgraded (class I or II), stable (localized class IIF), or upgraded (class III or IV, solid, or category T3a, N1, or M1 or higher disease); a third radiologist resolved discrepancies. Incidence rate of upgrade was determined. Histopathologic outcomes were assessed for resected masses. RESULTS. Median follow-up was 28.4 months (IQR, 13.7-59.4 months). At 6-month follow-up, five (2%) masses were downgraded, 241 (98%) were stable, and none were upgraded. On the basis of final follow-up, 14 (6%) masses were downgraded, 223 (91%) were stable, and nine (4%) were upgraded. All upgrade events entailed a class increase to III (n = 7) or IV (n = 2); no mass became solid or developed T3, N1, or M1 disease. Among the nine upgraded masses, median time to upgrade was 53.5 months (IQR, 23.2-63.7 months). Incidence rate of upgrade was 3.006 per 100,000 person-days (95% CI, 1.466-5.516). Ten masses were resected; histopathology was benign in six and malignant in four. Of the four malignant masses, one was upgraded to class III after 15 months of preoperative follow-up imaging, and three remained class IIF on preoperative follow-up imaging. No resected malignant mass developed postoperative recurrence. CONCLUSION. Bosniak v2019 class IIF masses are unlikely to represent aggressive malignancy; only 4% were upgraded over time and never on initial 6-month follow-up. CLINICAL IMPACT. The currently recommended initial 6-month follow-up imaging examination for class IIF masses is of questionable clinical utility.

Diagnosis of Clinically Significant Portal Hypertension Using CT- and MRI-based Vascular Model.

Background Currently, the hepatic venous pressure gradient (HVPG) remains the reference standard for diagnosis of clinically significant portal hypertension (CSPH) but is limited by its invasiveness and availability. Purpose To investigate a vascular geometric model for noninvasive diagnosis of CSPH (HVPG ≥10 mm Hg) in patients with liver cirrhosis for both contrast-enhanced CT and MRI. Materials and Methods In this retrospective study, consecutive patients with liver cirrhosis who underwent HVPG measurement from August 2016 to April 2019 were included. Patients without hepatic diseases were included and marked as non-CSPH to balance the ratio of CSPH 1:1. A variety of vascular parameters were extracted from the portal vein, hepatic vein, aorta, and inferior vena cava and then entered into a vascular geometric model for identification of CSPH. Diagnostic performance was assessed with the area under the receiver operating characteristic curve (AUC). Results The model was developed and tested with retrospective data from 250 patients with liver cirrhosis and 273 patients without clinical evidence of hepatic disease at contrast-enhanced CT examination, including 213 patients with CSPH (mean age, 49 years ± 12 [SD]; 138 women) and 310 patients without CSPH (mean age, 50 years ± 9; 177 women). For external validation, an MRI data set with 224 patients with cirrhosis (mean age, 49 years ± 10; 158 women) and a CT data set with 106 patients with cirrhosis (mean age, 53 years ± 12; 71 women) were analyzed. Significant reductions in mean whole-vessel volumes were observed in the portal vein (ranging from 36.9 cm3 ± 16.0 to 29.6 cm3 ± 11.1; P < .05) and hepatic vein (ranging from 35.3 cm3 ± 21.5 to 22.4 cm3 ± 15.7; P < .05) when CSPH occurred. Similarly, the mean whole-vessel lengths were shorter in patients with CSPH (portal vein: 1.7 m ± 1.2 vs 3.0 m ± 2.4, P < .05; hepatic vein: 0.9 m ± 1.5 vs 1.8 m ± 1.5, P < .05) than in those without CSPH. The proposed vascular model performed well in the internal test set (mean AUC, 0.90 ± 0.02) and external test sets (mean AUCs, 0.84 ± 0.12 and 0.87 ± 0.11). Conclusion A contrast-enhanced CT- and MRI-based vascular model was proposed with good diagnostic consistency for hepatic venous pressure gradient measurement. ClinicalTrials.gov registration nos. NCT03138915 and NCT03766880 © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Roldán-Alzate and Reeder in this issue.

Spectral CT-based radiomics signature for distinguishing malignant pulmonary nodules from benign

ObjectivesTo evaluate the discriminatory capability of spectral CT-based radiomics to distinguish benign from malignant solitary pulmonary solid nodules (SPSNs).Materials and methodsA retrospective study was performed including 242 patients with SPSNs who underwent contrast-enhanced dual-layer Spectral Detector CT (SDCT) examination within one month before surgery in our hospital, which were randomly divided into training and testing datasets with a ratio of 7:3. Regions of interest (ROIs) based on 40-65 keV images of arterial phase (AP), venous phases (VP), and 120kVp of SDCT were delineated, and radiomics features were extracted. Then the optimal radiomics-based score in identifying SPSNs was calculated and selected for building radiomics-based model. The conventional model was developed based on significant clinical characteristics and spectral quantitative parameters, subsequently, the integrated model combining radiomics-based model and conventional model was established. The performance of three models was evaluated with discrimination, calibration, and clinical application.ResultsThe 65 keV radiomics-based scores of AP and VP had the optimal performance in distinguishing benign from malignant SPSNs (AUC65keV-AP = 0.92, AUC65keV-VP = 0.88). The diagnostic efficiency of radiomics-based model (AUC = 0.96) based on 65 keV images of AP and VP outperformed conventional model (AUC = 0.86) in the identification of SPSNs, and that of integrated model (AUC = 0.97) was slightly further improved. Evaluation of three models showed the potential for generalizability.ConclusionsAmong the 40-65 keV radiomics-based scores based on SDCT, 65 keV radiomics-based score had the optimal performance in distinguishing benign from malignant SPSNs. The integrated model combining radiomics-based model based on 65 keV images of AP and VP with Zeff-AP was significantly superior to conventional model in the discrimination of SPSNs.