Deep learning-based platform performs high detection sensitivity of intracranial aneurysms in 3D brain TOF-MRA: An external clinical validation study.

PURPOSE: To evaluate the diagnostic efficacy of a developed artificial intelligence (AI) platform incorporating deep learning algorithms for the automated detection of intracranial aneurysms in time-of-flight (TOF) magnetic resonance angiography (MRA). METHOD: This retrospective study encompassed 3D TOF MRA images acquired between January 2023 and June 2023, aiming to validate the presence of intracranial aneurysms via our developed AI platform. The manual segmentation results by experienced neuroradiologists served as the "gold standard". Following annotation of MRA images by neuroradiologists using InferScholar software, the AI platform conducted automatic segmentation of intracranial aneurysms. Various metrics including accuracy (ACC), balanced ACC, area under the curve (AUC), sensitivity (SE), specificity (SP), F1 score, Brier Score, and Net Benefit were utilized to evaluate the generalization of AI platform. Comparison of intracranial aneurysm identification performance was conducted between the AI platform and six radiologists with experience ranging from 3 to 12 years in interpreting MR images. Additionally, a comparative analysis was carried out between radiologists' detection performance based on independent visual diagnosis and AI-assisted diagnosis. Subgroup analyses were also performed based on the size and location of the aneurysms to explore factors impacting aneurysm detectability. RESULTS: 510 patients were enrolled including 215 patients (42.16 %) with intracranial aneurysms and 295 patients (57.84 %) without aneurysms. Compared with six radiologists, the AI platform showed competitive discrimination power (AUC, 0.96), acceptable calibration (Brier Score loss, 0.08), and clinical utility (Net Benefit, 86.96 %). The AI platform demonstrated superior performance in detecting aneurysms with an overall SE, SP, ACC, balanced ACC, and F1 score of 91.63 %, 92.20 %, 91.96 %, 91.92 %, and 90.57 % respectively, outperforming the detectability of the two resident radiologists. For subgroup analysis based on aneurysm size and location, we observed that the SE of the AI platform for identifying tiny (diameter＜3mm), small (3 mm ≤ diameter＜5mm), medium (5 mm ≤ diameter＜7mm) and large aneurysms (diameter ≥ 7 mm) was 87.80 %, 93.14 %, 95.45 %, and 100 %, respectively. Furthermore, the SE for detecting aneurysms in the anterior circulation was higher than that in the posterior circulation. Utilizing the AI assistance, six radiologists (i.e., two residents, two attendings and two professors) achieved statistically significant improvements in mean SE (residents: 71.40 % vs. 88.37 %; attendings: 82.79 % vs. 93.26 %; professors: 90.07 % vs. 97.44 %; P < 0.05) and ACC (residents: 85.29 % vs. 94.12 %; attendings: 91.76 % vs. 97.06 %; professors: 95.29 % vs. 98.82 %; P < 0.05) while no statistically significant change was observed in SP. Overall, radiologists' mean SE increased by 11.40 %, mean SP increased by 1.86 %, and mean ACC increased by 5.88 %, mean balanced ACC promoted by 6.63 %, mean F1 score grew by 7.89 %, and Net Benefit rose by 12.52 %, with a concurrent decrease in mean Brier score declined by 0.06. CONCLUSIONS: The deep learning algorithms implemented in the AI platform effectively detected intracranial aneurysms on TOF-MRA and notably enhanced the diagnostic capabilities of radiologists. This indicates that the AI-based auxiliary diagnosis model can provide dependable and precise prediction to improve the diagnostic capacity of radiologists.

Non-contrast computed tomography-based radiomics for staging of connective tissue disease-associated interstitial lung disease.

Rationale and introduction: It is of significance to assess the severity and predict the mortality of patients with connective tissue disease-associated interstitial lung disease (CTD-ILD). In this double-center retrospective study, we developed and validated a radiomics nomogram for clinical management by using the ILD-GAP (gender, age, and pulmonary physiology) index system. Materials and methods: Patients with CTD-ILD were staged using the ILD-GAP index system. A clinical factor model was built by demographics and CT features, and a radiomics signature was developed using radiomics features extracted from CT images. Combined with the radiomics signature and independent clinical factors, a radiomics nomogram was constructed and evaluated by the area under the curve (AUC) from receiver operating characteristic (ROC) analyses. The models were externally validated in dataset 2 to evaluate the model generalization ability using ROC analysis. Results: A total of 245 patients from two clinical centers (dataset 1, n = 202; dataset 2, n = 43) were screened. Pack-years of smoking, traction bronchiectasis, and nine radiomics features were used to build the radiomics nomogram, which showed favorable calibration and discrimination in the training cohort {AUC, 0.887 [95% confidence interval (CI): 0.827-0.940]}, the internal validation cohort [AUC, 0.885 (95% CI: 0.816-0.922)], and the external validation cohort [AUC, 0.85 (95% CI: 0.720-0.919)]. Decision curve analysis demonstrated that the nomogram outperformed the clinical factor model and radiomics signature in terms of clinical usefulness. Conclusion: The CT-based radiomics nomogram showed favorable efficacy in predicting individual ILD-GAP stages.

A computed tomography-based radiomics nomogram for predicting overall survival in patients with connective tissue disease-associated interstitial lung disease.

OBJECTIVES: Accurate prognostic prediction is beneficial for the management of patients with connective tissue disease-associated interstitial lung disease (CTD-ILD). The purpose of the present study was to develop and validate a nomogram using clinical features and computed tomography (CT) based radiomics features to predict overall survival (OS) in patients with CTD-ILD, and to assess the incremental prognostic value the radiomics might add to clinical risk factors. MATERIALS & METHODS: Patients from two clinical centers with CTD-ILD were enrolled in the present retrospective study. A radiomics signature, a clinical model and a combined nomogram were developed and assessed in the cohorts. The incremental value of radiomics signature to the clinical independent risk factors in survival prediction was evaluated. The models were externally validated to evaluate the model generalization ability. RESULTS: A total of 215 patients (mean age, 53 years ± 14 [standard deviation], 45 men) were evaluated. Patients with higher radiomics scores had higher mortality risk than those with lower radiomics scores (Hazard ratio, 12.396; 95% CI, 3.364-45.680; P < 0.001). The combined nomogram showed better predictive capability than the clinical model did with higher C-indices (0.800, 0.738, 0.742 vs. 0.747, 0.631, 0.587 in the training, internal- and external-validation cohort, respectively), time-AUCs and overall net-benefit. CONCLUSION: The radiomics signature is a potential prognostic biomarker of CTD-ILD and add incremental value to the clinical independent risk factors. The combined nomogram can provide a more accurate estimation of OS than the clinical model for CTD-ILD patients. CLINICAL RELEVANCE STATEMENT: The developed combined nomogram showed accurate prognostic prediction performance, which is beneficial for the management of CTD-ILD patients. It also proved radiomics could extract prognostic information from CT images.

CT-based radiomics nomogram for differentiation of adrenal hyperplasia from lipid-poor adenoma: an exploratory study.

BACKGROUND: To establish and verify a radiomics nomogram for differentiating isolated micronodular adrenal hyperplasia (iMAD) from lipid-poor adenoma (LPA) based on computed tomography (CT)-extracted radiomic features. METHODS: A total of 148 patients with iMAD or LPA were divided into three cohorts: a training cohort (n = 72; 37 iMAD and 35 LPA), a validation cohort (n = 36; 22 iMAD and 14 LPA), and an external validation cohort (n = 40; 20 iMAD and 20 LPA). Radiomics features were extracted from contrast-enhanced and non-contrast CT images. The least absolute shrinkage and selection operator (LASSO) method was applied to develop a triphasic radiomics model and unenhanced radiomics model using reproducible radiomics features. A clinical model was constructed using certain laboratory variables and CT findings. Radiomics nomogram was established by selected radiomics signature and clinical factors. Nomogram performance was assessed by calibration curve, the areas under receiver operating characteristic curves (AUC), and decision curve analysis (DCA). RESULTS: Eleven and eight extracted features were finally selected to construct an unenhanced radiomics model and a triphasic radiomics model, respectively. There was no significant difference in AUC between the two models in the external validation cohort (0.838 vs. 0.843, p = 0.949). The radiomics nomogram inclusive of the unenhanced model, maximum diameter, and aldosterone showed the AUC of 0.951, 0.938, and 0.893 for the training, validation, and external validation cohorts, respectively. The nomogram showed good calibration, and the DCA demonstrated the superiority of the nomogram compared with the clinical factors model alone in terms of clinical usefulness. CONCLUSIONS: A radiomics nomogram based on unenhanced CT images and clinical variables showed favorable performance for distinguishing iMAD from LPA. In addition, an efficient unenhanced model can help avoid extra contrast-enhanced scanning and radiation risk.

Two nomograms based on radiomics models using triphasic CT for differentiation of adrenal lipid-poor benign lesions and metastases in a cancer population: an exploratory study.

OBJECTIVES: To investigate the effectiveness of CT-based radiomics nomograms in differentiating adrenal lipid-poor benign lesions and metastases in a cancer population. METHODS: This retrospective study enrolled 178 patients with cancer history from three medical centres categorised as those with adrenal lipid-poor benign lesions or metastases. Patients were divided into training, validation, and external testing cohorts. Radiomics features were extracted from triphasic CT images (unenhanced, arterial, and venous) to establish three single-phase models and one triphasic radiomics model using logistic regression. Unenhanced and triphasic nomograms were established by incorporating significant clinico-radiological factors and radscores. The models were evaluated by the receiver operating characteristic curve, Delong's test, calibration curve, and decision curve. RESULTS: Lesion side, diameter, and enhancement ratio resulted as independent factors and were selected into nomograms. The areas under the curves (AUCs) of unenhanced and triphasic radiomics models in validation (0.878, 0.914, p = 0.381) and external testing cohorts (0.900, 0.893, p = 0.882) were similar and higher than arterial and venous models (validation: 0.842, 0.765; testing: 0.814, 0.806). Unenhanced and triphasic nomograms yielded similar AUCs in validation (0.903, 0.906, p = 0.955) and testing cohorts (0.928, 0.946, p = 0.528). The calibration curves showed good agreement and decision curves indicated satisfactory clinical benefits. CONCLUSION: Unenhanced and triphasic CT-based radiomics nomograms resulted as a useful tool to differentiate adrenal lipid-poor benign lesions from metastases in a cancer population. They exhibited similar predictive efficacies, indicating that enhanced examinations could be avoided in special populations. KEY POINTS: • All four radiomics models and two nomograms using triphasic CT images exhibited favourable performances in three cohorts to characterise the cancer population's adrenal benign lesions and metastases. • Unenhanced and triphasic radiomics models had similar predictive performances, outperforming arterial and venous models. • Unenhanced and triphasic nomograms also exhibited similar efficacies and good clinical benefits, indicating that contrast-enhanced examinations could be avoided when identifying adrenal benign lesions and metastases.

A novel computed tomography angiography technique: guided preoperative localization and design of anterolateral thigh perforator flap.

BACKGROUND: Anterolateral thigh perforator (ALTP) flap is considered a versatile flap for soft tissue reconstruction. Computed tomography angiography (CTA) is used for mapping perforator in abdominal-based reconstruction; however, it is less commonly used in ALTP due to its poor imaging efficacy. In this study, we introduced a novel CTA technique for preoperative localization and design of ALTP flap and evaluated its value in directing surgical reconstruction. RESULTS: Thirty-five patients with soft tissue defects were consecutively enrolled. Modified CTA procedures, such as sharp convolution kernel, ADMIRE iterative reconstruction, 80 kV tube voltage, high flow contrast agent and cinematic rendering image reconstruction, were used to map ALTPs. A total of 287 perforators (including 884 sub-branches) were determined, with a mean of 5 perforators per thigh (range 2-11). The ALTPs were mainly concentrated in the "hot zone" (42%, 121/287) or the distal zone (41%, 118/287). Most perforators originated from the descending branch of the lateral circumflex femoral artery (76%, 219/287). Three perforator types, namely musculocutaneous (62%, 177/287), septocutaneous (33%, 96/287), and mixed pattern (5%, 14/287), were identified. The median pedicle length measured by two methods was 4.1 cm (range 0.7-20.3 cm) and 17.0 cm (range 4.7-33.9 cm), respectively, and the median diameter of the skin flap nourished by one perforator was 3.4 cm (IQR 2.1-5.7 cm). Twenty-eight ALTP flaps were obtained with the guidance of CTA, and 26 flaps survived after follow-up. CONCLUSIONS: The proposed CTA mapping technique is a useful tool for preoperative localization and design of ALTP flap.

Association of serum anion gap and risk of long-term mortality in patients following coronary artery bypass grafting: A propensity score matching study.

BACKGROUND: The present study aimed to explore the relationship between serum anion gap (AG) and long-term mortality in patients undergoing coronary artery bypass grafting (CABG). METHODS: Clinical variables were extracted among patients undergoing CABG from Medical Information Mart for Intensive Care III (MIMIC III) database. The primary outcome was 4-year mortality following CABG. An optimal cut-off value of AG was determined by the receiver operating characteristic (ROC) curve. The Kaplan-Meier (K-M) analysis and multivariate Cox hazard analysis were performed to investigate the prognostic value of AG in long-term mortality after CABG. To eliminate the bias between different groups, propensity score matching (PSM) was conducted to validate the findings. RESULTS: The optimal cut-off value of AG was 17.00 mmol/L. Then a total of 3162 eligible patients enrolled in this study were divided into a high AG group (≥17.00, n = 1022) and a low AG group (<17.00, n = 2,140). A lower survival rate was identified in the high AG group based on the K-M curve (p < .001). Compared with patients in the low AG group, patients in the high AG group had an increased risk of long-term mortality [1-year mortality: hazard ratio, HR: 2.309, 95% CI (1.672-3.187), p < .001; 2-year mortality: HR: 1.813, 95% CI (1.401-2.346), p < .001; 3- year mortality: HR: 1.667, 95% CI (1.341-2.097), p < .001; 4-year mortality: HR: 1.710, 95% CI (1.401-2.087), p < .001] according to multivariate Cox hazard analysis. And further validation of above results was consistent in the matched cohort after PSM. CONCLUSIONS: The AG is an independent predictive factor for long-term all-cause mortality in patients following CABG, where a high AG value is associated with an increased mortality.

Comparison of symptomatic vertebrobasilar plaques between patients with and without Diabetes Mellitus using computed tomographic angiography and vessel wall magnetic resonance imaging.

OBJECTIVES: Diabetes mellitus is significantly associated with posterior circulation ischemic stroke. We aimed to compare the characteristics of vertebrobasilar plaques in symptomatic patients with and without diabetes using high-resolution vessel wall magnetic resonance imaging and computed tomographic angiography. METHODS: From April 2017 to May 2021, cases from patients with transient ischemic attack or stroke in the posterior circulation territory who underwent high-resolution vessel wall magnetic resonance imaging and computed tomographic angiography were reviewed. Characteristics of culprit vertebrobasilar plaques were compared between patients with and without diabetes. Multivariate regression analysis was performed to assess the correlation between culprit plaque characteristics and diabetes. RESULTS: A total of 148 patients were included and 75 patients were diagnosed with diabetes mellitus. Patients with diabetes had more intraplaque hemorrhage, calcification, spotty calcification presence, and higher calcification volume (all p < 0.05) compared with those without diabetes. Multivariate analysis demonstrated differences in the presence of intraplaque hemorrhage (p = 0.045) and number of spotty calcifications (p = 0.047) were statistically significant after adjusting for baseline characteristics. CONCLUSIONS: Symptomatic patients with diabetes have a higher incidence of intraplaque hemorrhage and larger calcification burden than those without diabetes, indicating the association of diabetes with more advanced plaque features in the posterior circulation.

T1 Stage Clear Cell Renal Cell Carcinoma: A CT-Based Radiomics Nomogram to Estimate the Risk of Recurrence and Metastasis.

OBJECTIVES: To develop and validate a radiomics nomogram to improve prediction of recurrence and metastasis risk in T1 stage clear cell renal cell carcinoma (ccRCC). METHODS: This retrospective study recruited 168 consecutive patients (mean age, 53.9 years; range, 28-76 years; 43 women) with T1 ccRCC between January 2012 and June 2019, including 50 aggressive ccRCC based on synchronous metastasis or recurrence after surgery. The patients were divided into two cohorts (training and validation) at a 7:3 ratio. Radiomics features were extracted from contrast enhanced CT images. A radiomics signature was developed based on reproducible features by means of the least absolute shrinkage and selection operator method. Demographics, laboratory variables (including sex, age, Fuhrman grade, hemoglobin, platelet, neutrophils, albumin, and calcium) and CT findings were combined to develop clinical factors model. Integrating radiomics signature and independent clinical factors, a radiomics nomogram was developed. Nomogram performance was determined by calibration, discrimination, and clinical usefulness. RESULTS: Ten features were used to build radiomics signature, which yielded an area under the curve (AUC) of 0.86 in the training cohort and 0.85 in the validation cohort. By incorporating the sex, maximum diameter, neutrophil count, albumin count, and radiomics score, a radiomics nomogram was developed. Radiomics nomogram (AUC: training, 0.91; validation, 0.92) had higher performance than clinical factors model (AUC: training, 0.86; validation, 0.90) or radiomics signature as a means of identifying patients at high risk for recurrence and metastasis. The radiomics nomogram had higher sensitivity than clinical factors mode (McNemar's chi-squared = 4.1667, p = 0.04) and a little lower specificity than clinical factors model (McNemar's chi-squared = 3.2, p = 0.07). The nomogram showed good calibration. Decision curve analysis demonstrated the superiority of the nomogram compared with the clinical factors model in terms of clinical usefulness. CONCLUSION: The CT-based radiomics nomogram could help in predicting recurrence and metastasis risk in T1 ccRCC, which might provide assistance for clinicians in tailoring precise therapy.