Edge-Type Hyperintense Intracranial Artery Plaque: A Potential MRI Biomarker of Stroke Recurrence.

BACKGROUND: Identifying patients at high risk of stroke recurrence is important for stroke prevention and treatment. PURPOSE: To explore the characteristics of T1 hyperintense plaques (HIP) and their relationship with stroke recurrence in patients with symptomatic intracranial atherosclerotic stenosis (sICAS). STUDY TYPE: Retrospective. POPULATION: One hundred fifty-seven patients with moderate-to-severe (≥50%) nonocclusive sICAS and MRI studies (42 females and 115 males, mean age 58.69 ± 10.68 years). FIELD STRENGTH/SEQUENCE: 3D higher-resolution black-blood T1-weighted fast-spin-echo sequence at 3.0 T. ASSESSMENT: HIP (signal intensity [SI] of plaque-to-adjacent gray matter >1.0 on non-contrast T1-weighted images) and non-HIP plaques were identified. HIP plaques were categorized as edge type (high SI adjacent to lumen) and non-edge type (high SI within plaque). Clinical and imaging features of different plaque types were compared. Stroke recurrence was assessed through telephone or medical records at 3 and 6 months, and then once a year post-MRI. The relationship between edge type and non-edge types HIP with stroke recurrence was analyzed. STATISTICAL TESTS: Student's t test, Mann-Whitney U-test, chi square test and Fisher's exact test to compare features between plaque types. Kaplan-Meier curves (with log-rank tests) and Cox proportional hazards regression to assess relationship between stroke recurrence and different plaque types. A two-tailed P-value of <0.05 was considered statistically significant. RESULTS: Of 157 culprit lesions, 87 (55%) were HIPs (43 edge type, 44 non-edge type) and 70 (45%) were non-HIPs. Plaque thickness, area, and volume were significantly higher for HIPs than for non-HIPs. Among patients with HIPs, edge type was significantly more likely in the posterior circulation (53.5% vs. 27.3%), and had significantly higher plaque thickness, length, area, volume, plaque burden, and remodeling index than non-edge type. Edge-type HIP was significantly more common than non-edge HIP in patients with diabetes mellitus (51.2% vs. 29.5%) and dyslipidemia (79.1% vs. 54.5%). During median follow-up of 27 months, 33 patients experienced stroke recurrence. Recurrence was associated with edge-type HIP (adjusted hazard ratio = 2.83; 95% confidence interval: 1.40-5.69), both in the overall cohort (34.9% vs. 15.8%) and in patients with HIP (34.9% vs. 9.0%). Age ≥60 years and edge-type HIP had a significant interaction. DATA CONCLUSIONS: Hyperintense plaque may be categorized as edge type or non-edge type. Edge-type HIP may be a potential MRI biomarker of stroke recurrence. EVIDENCE LEVEL: 3 TECHNICAL EFFICACY: Stage 2.

Stent-specific fat attenuation index is associated with target vessel revascularization after PCI.

OBJECTIVES: To explore the clinical relevance of stent-specific perivascular fat attenuation index (FAI) in patients with stent implantation. METHODS: A total of 162 consecutive patients who underwent coronary computed tomography angiography (CCTA) following stent implantation were retrospectively included. The stent-specific FAI at 2 cm adjacent to the stent edge was calculated. The endpoints were defined as target vessel revascularization (TVR) on the stented vessel after CCTA and readmission times due to chest pain after stent implantation. Binary logistic regression analysis for TVR and ordinal regression models were conducted to identify readmission times (0, 1, and ≥ 2) with generalized estimating equations on a per-stent basis. RESULTS: On a per-stent basis, 9 stents (4.5%) experienced TVR after PCI at a median 30 months' follow-up duration. Stent-specific FAI differed significantly among subgroups of patients with stent implantation and different readmission times (p = 0.002); patients with at least one readmission had higher stent-specific FAI than those without readmission (p < 0.001). Bifurcated stents (odds ratio [OR]: 11.192, p = 0.001) and stent-specific FAI (OR: 1.189, p = 0.04) were independently associated with TVR. With no readmission as a reference, stent-specific FAI (OR: 0.984, p = 0.007) was an independent predictor for hospital readmission times ≥ 2 (p = 0.003). CONCLUSION: Non-invasive stent-specific FAI derived from CCTA was found to be associated with TVR, which was a promising imaging marker for functional assessment in patients who underwent stent implantation. CLINICAL RELEVANCE STATEMENT: Noninvasive fat attenuation index adjacent to the stents edge derived from CCTA, an imaging marker reflecting the presence of inflammation acting on the neointimal tissue at the sites of coronary stenting, might be relevant clinically with target vessel revascularization. KEY POINTS: • Non-invasive stent-specific FAI derived from CCTA was associated with TVR (OR: 1.189 [95% CI: 1.007-1.043], p = 0.04) in patients who underwent stent implantation. • Stent-specific FAI significantly differed among a subgroup of patients with chest pain after stent implantation and with different readmission times (p = 0.002); the patients with at least one readmission had higher stent-specific FAI than those without readmission (p < 0.001). • Non-invasive stent-specific FAI derived from CCTA could be used as an imaging maker for the functional assessment of patients following stent implantation.

Distinguishing Intracranial Diabetes-Related Atherosclerotic Plaques: A High-Resolution Magnetic Resonance Imaging-Based Radiomics Study.

INTRODUCTION: Diabetes markedly affects the formation and development of intracranial atherosclerosis. The study was aimed at evaluating whether radiomics features can help distinguish plaques primarily associated with diabetes. MATERIALS AND METHODS: We retrospectively analyzed patients who were admitted to our center because of acute ischemic stroke due to intracranial atherosclerosis between 2016 and 2022. Clinical data, blood biomarkers, conventional plaque features, and plaque radiomics features were collected for all patients. Odds ratios (ORs) with 95% confidence intervals (CIs) were determined from logistic regression models. The receiver operating characteristic (ROC) curve and area under the ROC curve (AUC) were used to describe diagnostic performance. The DeLong test was used to compare differences between models. RESULTS: Overall, 157 patients (115 men; mean age, 58.7 ± 10.7 years) were enrolled. Multivariate logistic regression analysis showed that plaque length (OR: 1.17; 95% CI: 1.07-1.28) and area (OR: 1.13; 95% CI: 1.02-1.24) were independently associated with diabetes. On combining plaque length and area as a conventional model, the AUCs of the training and validation cohorts for identifying diabetes patients were 0.789 and 0.720, respectively. On combining radiomics features on T1WI and contrast-enhanced T1WI sequences, a better diagnostic value was obtained in the training and validation cohorts (AUC: 0.889 and 0.861). The DeLong test showed the model combining radiomics and conventional plaque features performed better than the conventional model in both cohorts (p < 0.05). CONCLUSIONS: The use of radiomics features of intracranial plaques on high-resolution magnetic resonance imaging can effectively distinguish culprit plaques with diabetes as the primary pathological cause, which will provide new avenues of research into plaque formation and precise treatment.

Immune characteristics of dedifferentiated retroperitoneal liposarcomas and the reliability of regional samples in evaluating their tumor immune microenvironments.

BACKGROUND: Tumor immunotherapy is a new treatment breakthrough for retroperitoneal liposarcoma (RPLS), which is highly invasive and has few effective treatment options other than tumor resection. However, the heterogeneity of the tumor immune microenvironment (TIME) leads to missed clinical diagnosis and inappropriate treatment. Therefore, it is crucial to evaluate whether the TIME of a certain part of the tumor reliably represents the whole tumor, particularly for very large tumors, such as RPLS. METHODS: We conducted a prospective study to evaluate the TIME in different regions of dedifferentiated RPLS (DDRPLS) by detecting the expressions of markers such as CD4+, CD8+, Foxp3+, CD20+, CD68+, LAMP3+, PD-1+ tumor-infiltrating lymphocytes (TILs), and PD-L1 in tumors and corresponding paratumor tissues via immunohistochemistry and RNA sequencing. RESULTS: In DDRPLS, very few TILs were observed. Differentially expressed genes were significantly enriched in cell part and cell functions, as well as the metabolic pathway and PI3K-Akt signaling pathway. In addition, for most tumors (70-80%), the TIME was similar in different tumor regions. CONCLUSIONS: For most tumors (70-80%), the TIME in any region of the tumor reliably represents the whole tumor. DDRPLS may regulate cell functions by modulating the metabolic and PI3K-Akt signaling pathways to promote its malignant behavior.

Silver(I)-Catalyzed Diastereoselective Hydroborylation of Cyclopropenes.

An effective (NHC)AgCl catalysis was developed in the hydroborylation of cyclopropenes with B2pin2, delivering a variety of cyclopylboronates in a stereoselective manner, which could be easily transformed for the construction of versatile cyclopropanes. This protocol works effectively under mild reaction conditions in an open-air atmosphere, and it was easy to apply on a gram scale. This novel method in detail was also explored by control experiments, providing a number of key insights. The kinetic process followed by 1H NMR indicated that the reaction was finished in 15 min. Furthermore, the mechanism of silver(I)-catalyzed hydroborylation of cyclopropenes was proposed, with the protonation by methanol as the rate-determining step.

Transition-metal-free and additive-free intermolecular hydroarylation of alkenes with indoles in hexafluoroisopropanol.

Hydroarylation of alkenes is one of the most straightforward and atom-economical strategy for the construction of multi-aryl-substituted alkanes, but systematic studies have been limited to transition metal catalysis. Here we report a hexafluoroisopropanol (HFIP)-promoted hydroarylation of alkenes with indoles without the presence of transition metal catalysts or any additive. HFIP was the only reagent used in this work, and could be easily removed via evaporation, and recovered via distillation in industry settings. This reaction was shown to provide an efficient, clean and operationally simple procedure with a remarkable substrate scope and versatile transformations, delivering a variety of multi-aryl alkanes incorporating the indole motif. In preliminary studies, several of these products showed biologically activity against cells from an array of human cancer cell lines. A mechanistic study was also carried out and suggested that the quinone methide might be the key intermediate. And in contrast to the conclusions of a previous report, the current work suggested that protonation by HFIP might not be the rate-determining step.

The MRI enhancement ratio and plaque steepness may be more accurate for predicting recurrent ischemic cerebrovascular events in patients with intracranial atherosclerosis.

OBJECTIVES: To assess the complementary value of high-resolution multi-contrast MRI (hrMRI) in identifying symptomatic patients with intracranial atherosclerosis (ICAS) who are likely to experience recurrent ischemic cerebrovascular events. METHODS: In this retrospective cohort study, eighty patients with acute ischemic events attributed to ICAS who underwent hrMRI examination between January 2015 and January 2019 were included. Median follow-up for all patients was 30 months (range: 1 to 52 months) and recurrent ischemic cerebrovascular events were recorded. Cox regression analysis and time-dependent ROC were performed to quantify the association between the plaque characteristics and recurrent events. RESULTS: During the follow-up, 14 patients experienced recurrent ischemic cerebrovascular events. Young males and those with diabetes and poor medication persistence were more likely to experience recurrent events. ICAS in patients with recurrence had significantly higher enhancement ratio and steepness which is defined as the ratio between the plaque height and length than those without (p < 0.001 and p = 0.015, respectively). After adjustment of clinical factors, enhancement ratio (HR, 13.13 [95% CI, 3.58-48.20], p < 0.001) and plaque steepness (HR, 110.27 [95% CI, 4.75-2560.91], p = 0.003) were independent imaging biomarkers associated with recurrent events. Time-dependent ROC indicated that integrated high enhancement ratio and steepness into clinical risk factors improved discrimination power with the ROC increased from 0.79 to 0.94 (p = 0.008). CONCLUSIONS: The enhancement ratio and plaque steepness improved the accuracy over traditional clinical risk factors in predicting recurrent ischemic cerebrovascular events for patients with ICAS. KEY POINTS: • High-resolution magnetic resonance imaging helps clinicians to evaluate high-risk Intracranial plaque. • The higher enhancement ratio and plaque steepness (= height/length) were the primary biomarkers associated with future ischemic cerebrovascular events. • High-resolution magnetic resonance imaging combined with clinical characteristics showed a higher accuracy for the prediction of recurrent events in patients with intracranial atherosclerosis.

Automated quantitative lesion water uptake in acute stroke is a predictor of malignant cerebral edema.

OBJECTIVES: Net water uptake (NWU) has been shown to have a linear relationship with brain edema. Based on an automated-Alberta Stroke Program Early Computed Tomography Score (ASPECTS) technique, we automatically derived NWU from baseline multimodal computed tomography (CT), namely ASPECTS-NWU. We aimed to determine if ASPECTS-NWU can predict the development of malignant cerebral edema (MCE). METHODS: One hundred and forty-six patients with large-vessel occlusion were retrospectively enrolled. Quantitative NWU based on automated-ASPECTS was measured both on nonenhanced CT (NECT) and CT angiography (CTA), namely NECT-ASPECT-NWU and CTA-ASPECTS-NWU. The correlation between ASPECTS-NWU and cerebral edema (CED) grades was calculated using Spearman rank correlation. Univariate logistic regression was used to assess the effect of radiological and clinical features on MCE, and a multivariable model with significant factors from the univariate regression analysis was built. Receiver operating characteristic (ROC) was obtained and area under curve (AUC) was compared. RESULTS: CTA-ASPECTS-NWU had a moderate positive correlation with CED grades (r = 0.62; 95% confidence interval [CI], 0.51-0.71; p < 0.001). The CTA-ASPECTS-NWU performed better than the NECT-ASPECTS-NWU with AUC: 0.88 vs. 0.71 (p < 0.001). Multivariable logistic regression model integrating CTA-ASPECTS-NWU, collateral score, and age showed the CTA-ASPECTS-NWU was an independent predictor of MCE with an AUC of 0.94 (95% CI: 0.90-0.98; p < 0.001). CONCLUSIONS: This study demonstrates that ASPECTS-NWU is a quantitative predictor of MCE after large-vessel occlusion of the middle cerebral artery territory. The multivariable logistic regression model may enhance the identification of patients with MCE needing anti-edematous treatment. KEY POINTS: • The automated-ASPECTS technique can automatically detect the affected regions with early ischemic changes and NWU could be manually calculated. • The CTA-ASPECTS-NWU performs better than the NECT-ASPECTS-NWU on predicting the development of MCE. • The multivariable logistic regression model may enhance the identification of patients with MCE needing anti-edematous treatment.

Radiomics versus Conventional Assessment to Identify Symptomatic Participants at Carotid Computed Tomography Angiography.

INTRODUCTION: Carotid computed tomography angiography (CTA) is routinely used for evaluating the atherosclerotic process. Radiomics allows the extraction of imaging markers of lesion heterogeneity and spatial complexity. These quantitative features can be used as the input for machine learning (ML). Therefore, in this study, we aimed to evaluate the diagnostic performance of radiomics-based ML assessment of carotid CTA data to identify symptomatic patients with carotid artery atherosclerosis. METHODS: In this retrospective study, participants with carotid artery atherosclerosis who underwent carotid CTA and brain magnetic resonance imaging from May 2010 to December 2017 were studied. The participants were grouped into symptomatic and asymptomatic groups according to their recent symptoms (determination of ipsilateral ischemic stroke). Eight conventional plaque features and 2,107 radiomics parameters were extracted from carotid CTA images. A radiomics-based ML model was fitted on the training set, and the radiomics-based ML model and conventional assessment were compared using the area under the curve (AUC) to identify symptomatic participants. RESULTS: After excluding participants with other stroke sources, 120 patients with 148 carotid arteries were analyzed. Of these 148 carotid arteries, 34 (22.97%) were classified into the symptomatic group. Plaque ulceration (odds ratio [OR] = 0.257; 95% confidence interval [CI], 0.094-0.698) and plaque enhancement (OR = 0.305; 95% CI, 0.094-0.988) were associated with the symptomatic status. Twenty radiomics parameters were chosen to be inputs in the radiomics-based ML model. In the identification of symptomatic participants, the discriminatory value of the radiomics-based ML model was significantly higher than that of the conventional assessment (AUC = 0.858 vs. AUC = 0.706, p = 0.021). CONCLUSION: Radiomics-based ML analysis improves the discriminatory power of carotid CTA in the identification of recent ischemic symptoms in patients with carotid artery atherosclerosis.

ASPECTS-Based Attenuation Changes on CT Angiography as an Imaging Biomarker to Predict Hemorrhagic Transformation in Acute Ischemic Stroke.

INTRODUCTION: Imaging-based early warning indicators and feasible stratification of acute ischemic stroke (AIS) patients with hemorrhagic transformation (HT), especially high-risk patients with parenchymal hematoma (PH), are crucial in determining subsequent treatment strategies. This study combined automated ASPECTS software with noncontrast CT (NCCT) and CTA source image (CTASI) attenuation changes using Hounsfield unit (HU) values to predict HT and PH in patients with AIS. MATERIALS AND METHODS: We retrospectively enrolled 172 consecutive patients with anterior circulation large-vessel occlusion between 2016 and 2020. Univariate and multivariate logistic regression and receiver operating characteristic (ROC) analyses were used to investigate the relationship between NCCT and CTASI-ASPECTS-HU, as well as other clinical and radiological parameters of HT and PH. Univariate and multivariate logistic regression analyses were performed to explore risk factors for HT or PH, and an ROC curve was used to evaluate their diagnostic values. RESULTS: A multivariate analysis showed that CTASI-ASPECTS-HU and NIHSS score were independent predictors of HT (CTASI-ASPECTS-HU: odds ratio (OR), 2.22; 95% CI, 1.01-4.92; NIHSS: OR, 1.07; 95% CI, 1.02-1.13) and PH (CTASI-ASPECTS-HU: OR, 6.51; 95% CI, 2.29-18.50; NIHSS: OR, 1.07; 95% CI, 1.01-1.13). According to ROC analysis, CTASI-ASPECTS-HU >0.09 identified HT (area under the curve, 0.70; sensitivity, 70.15%; specificity, 61.90%), and CTASI-ASPECTS-HU >0.10 identified PH (area under the curve, 0.79; sensitivity, 76.19%; specificity, 73.33%). The area under the curve for predicting HT or PH increased when CTASI-ASPECTS-HU was combined with NIHSS score (HT: area under the curve, 0.74; sensitivity, 73.13%; specificity, 70.48%; PH: area under the curve, 0.81; sensitivity, 85.71%; specificity, 72.38%). CONCLUSION: CTASI-ASPECTS-HU is a reliable radiological predictor of HT and PH in patients with AIS. Its predictive efficacy is moderately improved when combined with NIHSS score.

Combination of computed tomography imaging-based radiomics and clinicopathological characteristics for predicting the clinical benefits of immune checkpoint inhibitors in lung cancer.

BACKGROUND: In this study, we tested whether a combination of radiomic features extracted from baseline pre-immunotherapy computed tomography (CT) images and clinicopathological characteristics could be used as novel noninvasive biomarkers for predicting the clinical benefits of non-small cell lung cancer (NSCLC) patients treated with immune checkpoint inhibitors (ICIs). METHODS: The data from 92 consecutive patients with lung cancer who had been treated with ICIs were retrospectively analyzed. In total, 88 radiomic features were selected from the pretreatment CT images for the construction of a random forest model. Radiomics model 1 was constructed based on the Rad-score. Using multivariate logistic regression analysis, the Rad-score and significant predictors were integrated into a single predictive model (radiomics nomogram model 1) to predict the durable clinical benefit (DCB) of ICIs. Radiomics model 2 was developed based on the same Rad-score as radiomics model 1.Using multivariate Cox proportional hazards regression analysis, the Rad-score, and independent risk factors, radiomics nomogram model 2 was constructed to predict the progression-free survival (PFS). RESULTS: The models successfully predicted the patients who would benefit from ICIs. For radiomics model 1, the area under the receiver operating characteristic curve values for the training and validation cohorts were 0.848 and 0.795, respectively, whereas for radiomics nomogram model 1, the values were 0.902 and 0.877, respectively. For the PFS prediction, the Harrell's concordance indexes for the training and validation cohorts were 0.717 and 0.760, respectively, using radiomics model 2, whereas they were 0.749 and 0.791, respectively, using radiomics nomogram model 2. CONCLUSIONS: CT-based radiomic features and clinicopathological factors can be used prior to the initiation of immunotherapy for identifying NSCLC patients who are the most likely to benefit from the therapy. This could guide the individualized treatment strategy for advanced NSCLC.

Advanced gastric cancer: CT radiomics prediction and early detection of downstaging with neoadjuvant chemotherapy.

OBJECTIVES: To develop and evaluate machine learning models using baseline and restaging computed tomography (CT) for predicting and early detecting pathological downstaging (pDS) with neoadjuvant chemotherapy in advanced gastric cancer (AGC). METHODS: We collected 292 AGC patients who received neoadjuvant chemotherapy. They were classified into (a) primary cohort (206 patients with 3-4 cycles chemotherapy) for model development and internal validation, (b) testing cohort I (46 patients with 3-4 cycles chemotherapy) for evaluating models' predictive ability before and after the complete course, and (c) testing cohort II (n = 40) for model evaluation on its performance at early treatment. We extracted 1,231 radiomics features from venous phase CT at baseline and restaging. We selected radiomics models based on 28 cross-combination models and measured the areas under the curve (AUC). Our prediction radiomics (PR) model is designed to predict pDS outcomes using baseline CT. Detection radiomics (DR) model is applied to restaging CT for early pDS detection. RESULTS: PR model achieved promising outcomes in two testing cohorts (AUC 0.750, p = .009 and AUC 0.889, p = .000). DR model also showed a good predictive ability (AUC 0.922, p = .000 and AUC 0.850, p = .000), outperforming the commonly used RECIST method (NRI 39.5% and NRI 35.4%). Furthermore, the improved DR model with averaging outcome scores of PR and DR models showed boosted results in two testing cohorts (AUC 0.961, p = .000 and AUC 0.921, p = .000). CONCLUSIONS: CT-based radiomics models perform well on prediction and early detection tasks of pDS and can potentially assist surgical decision-making in AGC patients. KEY POINTS: • Baseline contrast-enhanced computed tomography (CECT)-based radiomics features were predictive of pathological downstaging, allowing accurate identification of non-responders before therapy. • Restaging CECT-based radiomics features were predictive to achieve pDS after and even at an early stage of neoadjuvant chemotherapy. • Combination of baseline and restaging CECT-based radiomics features was promising for early detection and preoperative evaluation of pathological downstaging of AGC.

Comparison of automated and manual DWI-ASPECTS in acute ischemic stroke: total and region-specific assessment.

OBJECTIVE: To compare the DWI-Alberta Stroke Program Early Computed Tomography Score calculated by a deep learning-based automatic software tool (eDWI-ASPECTS) with the neuroradiologists' evaluation for the acute stroke, with emphasis on its performance on 10 individual ASPECTS regions, and to determine the reasons for inconsistencies between eDWI-ASPECTS and neuroradiologists' evaluation. METHODS: This retrospective study included patients with middle cerebral artery stroke who underwent MRI from 2010 to 2019. All scans were evaluated by eDWI-ASPECTS and two independent neuroradiologists (with 15 and 5 years of experience in stroke study). Inter-rater agreement and agreement between manual vs. automated methods for total and each region were evaluated by calculating Kendall's tau-b, intraclass correlation coefficient (ICC), and kappa coefficient. RESULTS: In total, 309 patients met our study criteria. For total ASPECTS, eDWI-ASPECTS and manual raters had a strong positive correlation (Kendall's tau-b = 0.827 for junior raters vs. eDWI-ASPECTS; Kendall's tau-b = 0.870 for inter-raters; Kendall's tau-b = 0.848 for senior raters vs. eDWI-ASPECTS) and excellent agreement (ICC = 0.923 for junior raters and automated scores; ICC = 0.954 for inter-raters; ICC = 0.939 for senior raters and automated scores). Agreement was different for individual ASPECTS regions. All regions except for M5 region (κ = 0.216 for junior raters and automated scores), internal capsule (κ = 0.525 for junior raters and automated scores), and caudate (κ = 0.586 for senior raters and automated scores) showed good to excellent concordance. CONCLUSION: The eDWI-ASPECTS performed equally well as senior neuroradiologists' evaluation, although interference by uncertain scoring rules and midline shift resulted in poor to moderate consistency in the M5, internal capsule, and caudate nucleus regions. KEY POINTS: • The eDWI-ASPECTS based on deep learning perform equally well as senior neuroradiologists' evaluations. • Among the individual ASPECTS regions, the M5, internal capsule, and caudate regions mainly affected the overall consistency. • Uncertain scoring rules and midline shift are the main reasons for regional inconsistency.

Discrimination between transient and persistent subsolid pulmonary nodules on baseline CT using deep transfer learning.

OBJECTIVES: To develop and validate a deep learning model to discriminate transient from persistent subsolid nodules (SSNs) on baseline CT. METHODS: A cohort of 1414 SSNs, consisting of 319 transient SSNs in 168 individuals and 1095 persistent SSNs in 816 individuals, were identified on chest CT. The cohort was assigned by examination date into a development set of 996 SSNs, a tuning set of 212 SSNs, and a validation set of 206 SSNs. Our model was built by transfer learning, which was transferred from a well-performed deep learning model for pulmonary nodule classification. The performance of the model was compared with that of two experienced radiologists. Each nodule was categorized by Lung CT Screening Reporting and Data System (Lung-RADS) to further evaluate the performance and the potential clinical benefit of the model. Two methods were employed to visualize the learned features. RESULTS: Our model achieved an AUC of 0.926 on the validation set with an accuracy of 0.859, a sensitivity of 0.863, and a specificity of 0.858, and outperformed the radiologists. The model performed the best among Lung-RADS 2 nodules and maintained well performance among Lung-RADS 4 nodules. Feature visualization demonstrated the model's effectiveness in extracting features from images. CONCLUSIONS: The transfer learning model presented good performance on the discrimination between transient and persistent SSNs. A reliable diagnosis on nodule persistence can be achieved at baseline CT; thus, an early diagnosis as well as better patient care is available. KEY POINTS: • Deep learning can be used for the discrimination between transient and persistent subsolid nodules. • A transfer learning model can achieve good performance when it is transferred from a model with a similar task. • With the assistance of deep learning model, a reliable diagnosis on nodule persistence can be achieved at baseline CT, which can bring a better patient care strategy.

Reliability and Reproducibility of the Diameters Method in Rapid Determination of Acute Infarct Volume in Magnetic Resonance Diffusion-Weighted Imaging.

BACKGROUND: In acute ischemic stroke, diffusion-weighted imaging (DWI) volume is an independent predictive factor of poor outcome and an exclusion criterion for thrombolytic treatment. A simplified diameters method (ABC/2, orthogonal diameter [OD], and the maximum diameter [MD]) was proposed to replace the conventional measuring method and overcome the tedious and time-consuming defects, but its accuracy remains to be determined. OBJECTIVE: The objective of this study is to clarify the reliability and reproducibility of the diameter-based estimations in the infarct volume in DWI (Vol-DWI) measured by automated software. METHODS: Data of 316 patients with acute ischemic stroke who underwent MRI within 72 h at Jinling Hospital were retrospectively reviewed. Subgroup analysis by the location (cortex, white matter and deep gray nuclei, and combined) and volume (<70 and >70 mL) of cerebral infarction was evaluated. Relationship and consistency between the diameters methods and Vol-DWI were determined using Spearman rank correlation, Wilcoxon signed-rank test, and Bland-Altman plots. The OD and MD thresholds indicating infarct size >15, 70, and 100 mL were determined by generating receiver-operating characteristic (ROC) curves. Interobserver reliability was established using intraclass correlation coefficient and Bland-Altman plot. RESULTS: There was a strong positive correlation between the diameters and the Vol-DWI (ABC/2: r = 0.992, OD: r = 0.984, MD: r = 0.970, p < 0.001). Infarct volumes measured using the ABC/2 formula were significantly lower than those measured with Vol-DWI (Wilcoxon signed-rank test, z = 6.476, p < 0.001). Bland-Altman plot showed that the agreement of the volume <70 mL group, and white matter and deep gray nuclei groups was better than that of the other subgroups. For infarct volumes >15, 70, and 100 mL, the cutoff value for the MD was identified at 5, 6.9, and 8.4 cm, and the OD was identified at 12.47, 26.4, and 36.4 cm2, respectively, with a sensitivity and specificity >90%. CONCLUSIONS: The MD method was the best for achieving a rapid and excellent interobserver reliability for estimating infarct volume. Both OD and MD methods can quickly screen patients suitable for recanalization treatment and predict poor prognosis through threshold evaluation.

T. marneffei infection complications in an HIV-negative patient with pre-existing pulmonary sarcoidosis: a rare case report.

BACKGROUND: Talaromyces marneffei (T. marneffei) is a thermal dimorphic pathogenic fungus that often causes fatal opportunistic infections in human immunodeficiency virus (HIV)-infected patients. Although T. marneffei-infected cases have been increasingly reported among non-HIV-infected patients in recent years, no cases of T. marneffei infection have been reported in pulmonary sarcoidosis patients. In this case, we describe a T. marneffei infection in an HIV-negative patient diagnosed with pulmonary sarcoidosis. CASE PRESENTATION: A 41-year-old Chinese man who had pre-existing pulmonary sarcoidosis presented with daily hyperpyrexia and cough. Following a fungal culture from bronchoalveolar lavage (BAL), the patient was diagnosed with T. marneffei infection. A high-resolution computed tomography (HRCT) chest scan revealed bilateral lung diffuse miliary nodules, multiple patchy exudative shadows in the bilateral superior lobes and right inferior lobes, air bronchogram in the consolidation of the right superior lobe, multiple hilar and mediastinal lymphadenopathies and local pleural thickening. After 3 mos of antifungal therapy, the patient's pulmonary symptoms rapidly disappeared, and the physical condition improved markedly. A subsequent CT re-examination demonstrated that foci were absorbed remarkably after treatment. The patient is receiving follow-up therapy and assessment for a cure. CONCLUSION: This case suggested that clinicians should pay more attention to non-HIV-related lung infections in patients with pulmonary sarcoidosis. Early diagnosis and treatment with antifungal therapy can improve the prognosis of T. marneffei infection.

Dynamic change of neutrophil to lymphocyte ratio and hemorrhagic transformation after thrombolysis in stroke.

BACKGROUND: The neutrophil to lymphocyte ratio (NLR) has been shown to predict short- and long-term outcomes in ischemic stroke patients. We sought to explore the temporal profile of the plasma NLR in stroke patients treated with intravenous thrombolysis (IVT) and its relationship with intracranial bleeding complications after thrombolysis. METHODS: A total of 189 ischemic stroke patients were prospectively enrolled. Blood samples for leukocyte, neutrophil, and lymphocyte counts were obtained at admission and at 3-6, 12-18, and 36-48 h after IVT. Head CT was performed on admission and repeated after 36-48 h, and a CT scan was done immediately in case of clinical worsening. Hemorrhagic events were categorized as symptomatic intracranial hemorrhage (sICH) and parenchymal hematomas (PH) according to previously published criteria. RESULTS: An increasing trend in the NLR was observed after stroke, and the NLR was higher in patients who developed PH or sICH at 3-6, 12-18, and 36-48 h after IVT (P < 0.01) than in those without PH or sICH. The optimal cutoff value for the serum NLR as an indicator for auxiliary diagnosis of PH and sICH was 10.59 at 12-18 h. Furthermore, the NLR obtained at 12-18-h post-treatment was independently associated with PH (adjusted odds ratio [OR] 1.14) and sICH (adjusted OR 1.14). In addition, patients with a NLR ≥10.59 had an 8.50-fold greater risk for PH (95 % confidence interval [CI] 2.69-26.89) and a 7.93-fold greater risk for sICH (95 % CI 2.25-27.99) than patients with a NLR <10.59. CONCLUSIONS: NLR is a dynamic variable, and its variation is associated with HT after thrombolysis in stroke patients.

Risk factors of venous thromboembolism in focal segmental glomerulosclerosis with nephrotic syndrome.

BACKGROUND: Venous thromboembolism (VTE) is an important and potentially life-threatening complication in focal segmental glomerulosclerosis (FSGS). The aim of this study was to investigate the prevalence and predisposing risk factors of venous thromboembolism in patients with FSGS with nephrotic syndrome. METHODS: A total of 120 FSGS patients with nephrotic syndrome were enrolled in this study. Venous thromboembolism was confirmed by contrast-enhanced dual-source computed tomography angiography or magnetic resonance venography. Potential clinical and laboratory risk factors for VTE were screened. RESULTS: Venous thrombosis was demonstrated in 12 (10 %) patients. Venous thrombosis occurred during the first episode of nephrotic syndrome in 3 patients and during a relapse in 9 patients. Eight patients had a pulmonary embolism, four had a renal vein thrombosis, three had a lower limb deep vein thrombosis, one had a cerebral sinovenous thrombosis, and one had a portal vein thrombosis. The positive predictive value for the D-dimer level was 22.4 % in the patients with FSGS, and the negative predictive value for the D-dimer level was 100 %. Of the screened risk factors, higher hematocrit and relapse of nephrotic syndrome were risk factors for VTE. Other risk factors, such as proteinuria, hypoalbuminemia, platelet count, fibrinogen level, and antithrombin III level, were not risk factors for VTE in patients with FSGS. CONCLUSION: We found that the prevalence of venous thromboembolism is approximately 10 % in FSGS patients with nephrotic syndrome. Most of the patients had a PE. Hemoconcentration and relapse of nephrotic syndrome were risk factors for the development of VTE in FSGS. Negative D-dimer may exclude venous thromboembolism in patients with nephrotic syndrome.

Assessment of extracranial-intracranial bypass in Moyamoya disease using 3T time-of-flight MR angiography: comparison with CT angiography.

BACKGROUND: To evaluate the value of time-of-flight MR angiography (TOF MRA) for the assessment of extracranial-intracranial (EC-IC) bypass in Moyamoya disease in comparison with computed tomography angiography (CTA). PATIENTS AND METHODS: A consecutive series of 23 patients with Moyamoya disease were analyzed retrospectively. Twenty three patients underwent 25 procedures of extracranial-intracranial bypass. Cranial CTA was performed within one week after the surgery to assess bypass patency. Then TOF MRA was scanned within 24 h after CTA on a 3T MRI system. Using 5-point scales (0 = poor to 4 = excellent), two radiologists rated the image quality and vessel integrity of bypass for three segments (extracranial, trepanation, intracranial). RESULTS: Image quality was high in both CTA and TOF MRA (mean quality score 3.84 ± 0.37 and 3.8 ± 0.41), without statistical difference (p = 0.66). Mean scores of TOF MRA with respect to bypass visualization were higher than CTA in the intracranial segment (p = 0.026). No significant difference of bypass visualization regarding the extracranial and trepanation segments was found between TOF MRA and CTA (p = 0.66 and p = 0.34, respectively). For the trepanation segment, TOF MRA showed pseudo lesions in 2 of all 25 cases. CONCLUSIONS: 3T TOF MRA, a non-contrast technique not exposing the patients to radiation, proved to be at least equal to CTA for the assessment of EC-IC bypass, and even superior to CTA with respect to the intracranial segment. In addition, readers should be aware of a potential overestimation showing focal pseudo lesions of the bypass at the trepanation segment in TOF MRA.

Deep Learning for Chest X-ray Diagnosis: Competition Between Radiologists with or Without Artificial Intelligence Assistance.

This study aimed to assess the performance of a deep learning algorithm in helping radiologist achieve improved efficiency and accuracy in chest radiograph diagnosis. We adopted a deep learning algorithm to concurrently detect the presence of normal findings and 13 different abnormalities in chest radiographs and evaluated its performance in assisting radiologists. Each competing radiologist had to determine the presence or absence of these signs based on the label provided by the AI. The 100 radiographs were randomly divided into two sets for evaluation: one without AI assistance (control group) and one with AI assistance (test group). The accuracy, false-positive rate, false-negative rate, and analysis time of 111 radiologists (29 senior, 32 intermediate, and 50 junior) were evaluated. A radiologist was given an initial score of 14 points for each image read, with 1 point deducted for an incorrect answer and 0 points given for a correct answer. The final score for each doctor was automatically calculated by the backend calculator. We calculated the mean scores of each radiologist in the two groups (the control group and the test group) and calculated the mean scores to evaluate the performance of the radiologists with and without AI assistance. The average score of the 111 radiologists was 597 (587-605) in the control group and 619 (612-626) in the test group (P < 0.001). The time spent by the 111 radiologists on the control and test groups was 3279 (2972-3941) and 1926 (1710-2432) s, respectively (P < 0.001). The performance of the 111 radiologists in the two groups was evaluated by the area under the receiver operating characteristic curve (AUC). The radiologists showed better performance on the test group of radiographs in terms of normal findings, pulmonary fibrosis, heart shadow enlargement, mass, pleural effusion, and pulmonary consolidation recognition, with AUCs of 1.0, 0.950, 0.991, 1.0, 0.993, and 0.982, respectively. The radiologists alone showed better performance in aortic calcification (0.993), calcification (0.933), cavity (0.963), nodule (0.923), pleural thickening (0.957), and rib fracture (0.987) recognition. This competition verified the positive effects of deep learning methods in assisting radiologists in interpreting chest X-rays. AI assistance can help to improve both the efficacy and efficiency of radiologists.