Enhancing intracranial efficacy prediction of osimertinib in non-small cell lung cancer: a novel approach through brain MRI radiomics.

Introduction: Osimertinib, a third-generation EGFR-TKI, is known for its high efficacy against brain metastases (BM) in non-small cell lung cancer (NSCLC) due to its ability to penetrate the blood-brain barrier. This study aims to evaluate the use of brain MRI radiomics in predicting the intracranial efficacy to osimertinib in NSCLC patients with BM. Materials and methods: This study analyzed 115 brain metastases from NSCLC patients with the EGFR-T790M mutation treated with second-line osimertinib. The primary endpoint was intracranial response, and the secondary endpoint was intracranial progression-free survival (iPFS). We performed tumor delineation, image preprocessing, and radiomics feature extraction. Using a 5-fold cross-validation strategy, we built radiomic models with eight feature selectors and eight machine learning classifiers. The models' performance was evaluated by the area under the receiver operating characteristic curve (AUC), calibration curves, and decision curve analysis. Results: The dataset of 115 brain metastases was divided into training and validation sets in a 7:3 ratio. The radiomic model utilizing the mRMR feature selector and stepwise logistic regression classifier showed the highest predictive accuracy, with AUCs of 0.879 for the training cohort and 0.786 for the validation cohort. This model outperformed a clinical-MRI morphological model, which included age, ring enhancement, and peritumoral edema (AUC: 0.794 for the training cohort and 0.697 for the validation cohort). The radiomic model also showed strong performance in calibration and decision curve analyses. Using a radiomic-score threshold of 199, patients were classified into two groups with significantly different median iPFS (3.0 months vs. 15.4 months, p < 0.001). Conclusion: This study demonstrates that MRI radiomics can effectively predict the intracranial efficacy of osimertinib in NSCLC patients with brain metastases. This approach holds promise for assisting clinicians in personalizing treatment strategies.

Additive effect of metabolic dysfunction-associated fatty liver disease on left ventricular function and global strain in type 2 diabetes mellitus patients: a 3.0 T cardiac magnetic resonance feature tracking study.

BACKGROUND: Type 2 diabetes mellitus (T2DM) and metabolic-associated fatty liver disease (MAFLD) are both metabolic disorders that negatively impact the cardiovascular system. This study comprehensively analyzed the additive effect of MAFLD on left ventricular function and global strain in T2DM patients by cardiac magnetic resonance (CMR). METHODS: Data of 261 T2DM patients, including 109 with and 152 without MAFLD, as well as 73 matched normal controls from our medical center between June 2015 and March 2022 were retrospectively analyzed. CMR-derived parameters, including LV function and global strain parameters, were compared among different groups. Univariate and multivariate linear regression analyses were conducted to investigate the impact of various factors on LV function and global strain. RESULTS: Our investigation revealed a progressive deterioration in LV functional parameters across three groups: control subjects, T2DM patients without MAFLD, and T2DM patients with MAFLD. Statistically significant increases in left ventricular end-diastolic volume index (LVEDVI), left ventricular end-systolic volume index (LVESVI), left ventricular mass index (LVMI) were observed, along with decreases in left ventricular ejection fraction (LVEF) and left ventricular global function index (LVGFI). Among these three groups, significant reductions were also noted in the absolute values of LV global radial, circumferential, and longitudinal peak strains (GRPS, GCPS, and GLPS), as well as in peak systolic (PSSR) and peak diastolic strain rates (PDSR). MAFLD was identified as an independent predictor of LVEF, LVMI, LVGFI, GRPS, GCPS, and GLPS in multivariate linear analysis. Besides, the incidence of late gadolinium enhancement was higher in MAFLD patients than in non-MAFLD patients (50/109 [45.9%] vs. 42/152 [27.6%], p = 0.003). Furthermore, escalating MAFLD severity was associated with a numerical deterioration in both LV function parameters and global strain values. CONCLUSIONS: This study thoroughly compared CMR parameters in T2DM patients with and without MAFLD, uncovering MAFLD's adverse impact on LV function and deformation in T2DM patients. These findings highlight the critical need for early detection and comprehensive management of cardiac function in T2DM patients with MAFLD.

Additive effect of admission hyperglycemia on left ventricular stiffness in patients following acute myocardial infarction verified by CMR tissue tracking.

BACKGROUND: Stress hyperglycemia occurs frequently in patients following acute myocardial infarction (AMI) and may aggravate myocardial stiffness, but relevant evidence is still lacking. Accordingly, this study aimed to examine the impact of admission stress hyperglycemia on left ventricular (LV) myocardial deformation in patients following AMI. METHODS: A total of 171 patients with first AMI (96 with normoglycemia and 75 with hyperglycemia) underwent cardiac magnetic resonance (CMR) examination were included. AMI patients were classified according to admission blood glucose level (aBGL): < 7.8 mmol/L (n = 96), 7.8-11.1 mmol/L (n = 41) and ≥ 11.1 mmol/L (n = 34). LV strains, including global radial/circumferential/longitudinal peak strain (PS)/peak systolic strain rate (PSSR)/peak diastolic strain rate (PDSR), were measured and compared between groups. Further, subgroup analyses were separately conducted for AMI patients with and without diabetes. Multivariate analysis was employed to assess the independent association between aBGL and LV global PS in AMI patients. RESULTS: LV global PS, PSSR and PDSR were decreased in radial, circumferential and longitudinal directions in hyperglycemic AMI patients compared with normoglycemic AMI patients (all P < 0.05). These differences were more obvious in patients with diabetes than those without diabetes. AMI patients with aBGL between 7.8 and 11.1 mmol/L demonstrated significant decreased radial and longitudinal PS, radial PSSR, and radial and longitudinal PDSR than those with aBGL < 7.8 mmol/L (all P < 0.05). AMI patients with aBGL ≥ 11.1 mmol/L showed significantly decreased PS, PSSR and PDSR in all three directions than those with aBGL < 7.8 mmol/L, and decreased longitudinal PSSR than those with aBGL between 7.8 and 11.1 (all P < 0.05). Further, aBGL was significantly and independently associated with radial (ß = - 0.166, P = 0.003) and longitudinal (ß = 0.143, P = 0.008) PS. CONCLUSIONS: Hyperglycemia may exacerbate LV myocardial stiffness in patients experienced first AMI, leading to reduction in LV strains. aBGL was an independent indicator of impaired LV global PS in AMI patients. Blood glucose monitoring is more valuable for AMI patients with diabetes.

Type 2 diabetes mellitus aggravates coronary atherosclerosis in hypertensive individuals based on coronary CT angiography: a retrospective propensity score-based study.

Background: The effect of type 2 diabetes mellitus (T2DM) on coronary atherosclerosis detected on coronary computed tomography angiography (CCTA) in hypertensive patients has attracted increasing attention. This study investigated the relationships of T2DM with coronary artery plaque characteristics and semiquantitative CCTA scores in hypertensive patients. Materials and methods: In this single-center study, 1,700 hypertensive patients, including 850 T2DM [HT(T2DM+)] and 850 non-T2DM [HT(T2DM-)] individuals, were retrospectively analyzed after propensity matching. Plaque type, extent, coronary stenosis, segment involvement score (SIS), segment stenosis score (SSS), and CT-based Leaman score (CT-LeSc) based on CCTA were assessed and compared between the two groups. Results: HT(T2DM+) patients had more coronary segments with calcified plaque (2.08 ± 2.20 vs. 1.40 ± 1.91), mixed plaque (2.90 ± 2.87 vs. 2.50 ± 2.66), nonobstructive stenosis (4.23 ± 2.44 vs. 3.62 ± 2.42), and obstructive stenosis (1.22 ± 2.18 vs. 0.78 ± 1.51), a lower proportion of 1-vessel disease (15.3% vs. 25.5%), a higher proportion of 3-vessel disease (59.6% vs. 46.7%), and higher SIS (5.5 ± 3.1 vs. 4.4 ± 3.0), SSS (10.3 ± 8.5 vs. 7.7 ± 7.1), and CT-LeSc (9.4 ± 5.6 vs. 7.9 ± 5.2) than HT(T2DM-) patients (all P-values <0.05). Multivariable analysis revealed that T2DM was an independent risk factor for calcified plaque [odds ratio (OR) = 2.213], obstructive coronary artery disease (CAD) (OR = 1.271), multivessel disease (OR = 1.838), SIS > 4 (OR = 1.910), SSS > 6 (OR = 1.718), and CT-LeSc > 5 (OR = 1.584) in hypertension population (all P-values <0.05). Conclusion: T2DM was independently associated with the presence of calcified coronary artery plaque and increased the risk of obstructive CAD, multivessel disease, and CT-LeSc > 5 in hypertensive patients. More attention should be given to the assessment and management for coronary atherosclerosis in hypertensive patients with T2DM, as this population may have a higher risk of cardiovascular events.

Artificial intelligence-assisted diagnosis of congenital heart disease and associated pulmonary arterial hypertension from chest radiographs: A multi-reader multi-case study.

OBJECTIVES: To explore the possibility of automatic diagnosis of congenital heart disease (CHD) and pulmonary arterial hypertension associated with CHD (PAH-CHD) from chest radiographs using artificial intelligence (AI) technology and to evaluate whether AI assistance could improve clinical diagnostic accuracy. MATERIALS AND METHODS: A total of 3255 frontal preoperative chest radiographs (1174 CHD of any type and 2081 non-CHD) were retrospectively obtained. In this study, we adopted ResNet18 pretrained with the ImageNet database to establish diagnostic models. Radiologists diagnosed CHD/PAH-CHD from 330/165 chest radiographs twice: the first time, 50% of the images were accompanied by AI-based classification; after a month, the remaining 50% were accompanied by AI-based classification. Diagnostic results were compared between the radiologists and AI models, and between radiologists with and without AI assistance. RESULTS: The AI model achieved an average area under the receiver operating characteristic curve (AUC) of 0.948 (sensitivity: 0.970, specificity: 0.982) for CHD diagnoses and an AUC of 0.778 (sensitivity: 0.632, specificity: 0.925) for identifying PAH-CHD. In the 330 balanced (165 CHD and 165 non-CHD) testing set, AI achieved higher AUCs than all 5 radiologists in the identification of CHD (0.670-0.858) and PAH-CHD (0.610-0.688). With AI assistance, the mean ± standard error AUC of radiologists was significantly improved for CHD (ΔAUC + 0.096, 95 % CI: 0.001-0.190; P = 0.048) and PAH-CHD (ΔAUC + 0.066, 95 % CI: 0.010-0.122; P = 0.031) diagnosis. CONCLUSION: Chest radiograph-based AI models can detect CHD and PAH-CHD automatically. AI assistance improved radiologists' diagnostic accuracy, which may facilitate a timely initial diagnosis of CHD and PAH-CHD.

Right-Left Ventricular Interdependence in Repaired Tetralogy of Fallot Patients With Right Ventricular Heart Failure.

BACKGROUND: Patients with repaired tetralogy of Fallot (rTOF) continue to face a heightened risk of deteriorating cardiac function, and quantitative techniques of cardiac MRI-derived cardiac structure and function provide an opportunity to explore the causes and mechanisms of cardiac deterioration. PURPOSE: To explore right-left ventricular interdependence in rTOF patients before and after the onset of right ventricular (RV) heart failure. STUDY TYPE: Retrospective. POPULATION: One hundred eighteen rTOF patients (21.85 [16.74, 29.20] years, 58 females) and 34 controls (23.5 [21, 26.5] years, 17 females) that underwent cardiac MRI were analyzed, with rTOF patients being further subdivided into those with preserved RV function (N = 54) and those that experienced RV heart failure (N = 64). FIELD STRENGTH/SEQUENCE: 3.0 T/balanced steady-state free precession sequence. ASSESSMENT: RV, left ventricular (LV), and septal strain; RV and LV volume. STATISTICAL TESTS: Chi-squared tests or Fisher's exact test, One-way ANOVAs with Bonferroni's post hoc test, Pearson/Spearman correlation, and multivariate backward linear regression analysis. A two-tailed P < 0.05 was deemed as the significance threshold. RESULTS: The MRI-derived RV, LV, and septal strain decreased sequentially in controls, patients with preserved RV function, and patients with RV heart failure, with a good intra-observer (0.909-0.964) and inter-observer (0.879-0.937) agreement. Correlations between LV and RV strain were found to change sequentially with RV function and were the closest in rTOF patients with RV heart failure (r = -0.270 to 0.506). Correlations between RV volume and septal strain was variable in controls (r = 0.483 to -0.604), patients with preserved RV function (r = -0.034 to -0.295), and patients with RV heart failure (r = -0.026 to 0.500). Multivariate analyses revealed that the RV longitudinal strain was independently correlated with LV strain in three directions in rTOF patients with RV heart failure (Radial -0.70 [-1.33, -0.06]; Circumferential 0.44 [0.17, 0.72]; Longitudinal 0.54 [0.26, 0.81]). DATA CONCLUSION: In rTOF patients, the coupling between RV volume and septal strain was broken during RV function compensation, and the adverse effect of RV on LV deformation was highest in patients with RV heart failure. EVIDENCE LEVEL: 4 TECHNICAL EFFICACY: Stage 5.

Prognostic prediction of left ventricular myocardial noncompaction using machine learning and cardiac magnetic resonance radiomics.

Background: Although there are many studies on the prognostic factors of left ventricular myocardial noncompaction (LVNC), the determinants are varied and not entirely consistent. This study aimed to build predictive models using radiomics features and machine learning to predict major adverse cardiovascular events (MACEs) in patients with LVNC. Methods: In total, 96 patients with LVNC were included and randomly divided into training and test cohorts. A total of 105 cine cardiac magnetic resonance (CMR)-derived radiomics features and 35 clinical characteristics were extracted. Five different oversampling algorithms were compared for selection of the optimal imbalanced processing. Feature importance was assessed with extreme gradient boosting (XGBoost). We compared the performance of 5 machine learning classification methods with different sample:feature ratios to determine the optimal hybrid classification strategy. Subsequently, radiomics, clinical, and combined radiomics-clinical models were developed and compared. Results: The machine learning pipeline included an adaptive synthetic (ADASYN) algorithm for imbalanced processing, XGBoost feature selection with a sample:feature ratio of 10, and support vector machine (SVM) modeling. The areas under the receiver operating characteristic curves (AUCs) of the radiomics model, clinical model, and combined model in the validation cohort were 0.87 (sensitivity 83.33%, specificity 64.29%), 0.65 (sensitivity 16.67%, specificity 78.57%), and 0.92 (specificity 33.33%, sensitivity 100.00%), respectively. The radiomics model performed similarly to the clinical and combined models (P=0.124 and P=0.621, respectively). The performance of the combined model was significantly better than that of the clinical model (P=0.003). Conclusions: The machine learning-based cine CMR radiomics model performed well at predicting MACEs in patients with LVNC. Adding radiomics features offered incremental prognostic value over clinical factors alone.

Prognostic Value of Left Atrial Reservoir Strain in Left Ventricular Myocardial Noncompaction: A 3.0 T Cardiac Magnetic Resonance Feature Tracking Study.

BACKGROUND: The relationship of left atrial (LA) strain to high-risk heart failure (HF) events in patients with left ventricular myocardial noncompaction (LVNC) remains to be thoroughly investigated. PURPOSE: To evaluate the LA performance in patients with LVNC, and to investigate the prognostic value of LA phasic strain on high-risk HF events, and its influencing factors. STUDY TYPE: Retrospective. POPULATION: A total of 95 LVNC patients (74 with LA enlargement [LAE] and 21 without LAE) and 50 healthy controls. FIELD STRENGTH/SEQUENCE: A 3.0 T, balanced steady-state free-precession cine imaging. ASSESSMENT: LA longitudinal strains were measured by cardiac MRI feature tracking technique. LA volume index (LAVI) and LA ejection fraction (LAEF) were calculated. Their intraobserver and interobserver reproducibility were evaluated. The primary outcome was high-risk HF events, a composite of first HF hospitalization, hospitalization for worsening HF and death from HF. STATISTICAL TESTS: Student's t/Mann-Whitney U, one-way analysis of variance/Kruskal-Wallis, Chi-squared, receiver operating characteristic, Kaplan-Meier, log-rank, Cox regression, Pearson and Spearman correlation and linear regression analyses were performed. The significance threshold was set at P < 0 .05. RESULTS: LAEF and LA longitudinal strains decreased in LVNC patients irrespective of the presence of LAE. During a median follow-up of 32.17 months, high-risk HF occurred in 13 (13.68%) patients. Patients with increased LAVI, decreased LAEF and decreased LA longitudinal strain had significantly higher risks of high-risk HF events. In patients with LVNC, LA reservoir strain (εs) was independently associated with high-risk HF (hazard ratio = 23.208 [95% CI: 2.993-179.967]). LV global longitudinal strain (LV GLS) (ß = -1.783 [95% CI: -2.493 to -1.073]) was significantly and independently associated with εs. Intraobserver and interobserver reproducibility was excellent for LAVI, LAEF, and LA strain. CONCLUSION: In patients with LVNC, εs was an independent predictor for high-risk HF events. LV GLS was an independent determinant of εs in LVNC. EVIDENCE LEVEL: 4 TECHNICAL EFFICACY: Stage 4.

Impact of T2DM on right ventricular systolic dysfunction and interventricular interactions in patients with essential hypertension: evaluation using CMR tissue tracking.

BACKGROUND: Previous studies reported that there was right ventricular (RV) systolic dysfunction in patients with hypertension. The aim of this study was to evaluate the impact of type 2 diabetes mellitus (T2DM) on RV systolic dysfunction and interventricular interactions using cardiac magnetic resonance feature tracking (CMR-FT) in patients with essential hypertension. METHODS AND METHODS: Eighty-five hypertensive patients without T2DM [HTN(T2DM -)], 58 patients with T2DM [HTN(T2DM +)] and 49 normal controls were included in this study. The biventricular global radial, circumferential and longitudinal peak strains (GRS, GCS, GLS, respectively) and RV regional strains at the basal-, mid- and apical-cavity, were calculated with CMR-FT and compared among controls and different patient groups. Backward stepwise multivariable linear regression analyses were used to determine the effects of T2DM and left ventricular (LV) strains on RV strains. RESULTS: The biventricular GLS and RV apical longitudinal strain deteriorated significantly from controls, through HTN(T2DM-), to HTN(T2DM +) groups. RV middle longitudinal strain in patient groups were significantly reduced, and LV GRS and GCS and RV basal longitudinal strain were decreased in HTN(T2DM +) but preserved in HTN(T2DM-) group. Multivariable regression analyses adjusted for covariates demonstrated that T2DM was independently associated with LV strains (LV GRS: ß = - 4.278, p = 0.004, model R2 = 0.285; GCS: ß = 1.498, p = 0.006, model R2 = 0.363; GLS: ß = 1.133, p = 0.007, model R2 = 0.372) and RV GLS (ß = 1.454, p = 0.003, model R2 = 0.142) in hypertension. When T2DM and LV GLS were included in the multiple regression analysis, both T2DM and LV GLS (ß = 0.977 and 0.362, p = 0.039 and < 0.001, model R2 = 0.224) were independently associated with RV GLS. CONCLUSIONS: T2DM exacerbates RV systolic dysfunction in patients with hypertension, which may be associated with superimposed LV dysfunction by coexisting T2DM and suggests adverse interventricular interactions.

Unsupervised machine learning based on clinical factors for the detection of coronary artery atherosclerosis in type 2 diabetes mellitus.

BACKGROUND: Coronary atherosclerosis can lead to serious cardiovascular events. In type 2 diabetes (T2DM) patients, the effects of clinical factors on coronary atherosclerosis have not been fully elucidated. We used a clustering method to distinguish the population heterogeneity of T2DM and the differences in coronary atherosclerosis evaluated on coronary computed tomography angiography (CCTA) among groups and to facilitate clinical management. METHODS: Clinical data from 1157 T2DM patients with coronary atherosclerosis who underwent CCTA in our hospital from January 2018 to September 2021 were retrospectively collected. The coronary artery segment plaque type and stenosis, the number of involved vessels, the segment involvement score (SIS) and the segment stenosis score (SSS) were evaluated and calculated. Unsupervised clustering analysis based on clinical information was used (cluster 1: n = 463; cluster 2: n = 341; cluster 3: n = 353). The association of coronary plaque characteristics with cluster groups was evaluated. RESULTS: The clinical data among the three groups were different in several aspects: (1) Cluster 1 had the least male patients (41.7%), the lowest proportion of patients with smoking (0%) or alcohol history (0.9%), and the lowest level of serum creatinine (74.46 ± 22.18 µmol/L); (2) Cluster 2 had the shortest duration of diabetes (7.90 ± 8.20 years) and was less likely to be treated with diabetes (42.2%) or statins (17.6%) and (3) Cluster 3 was the youngest (65.89 ± 10.15 years old) and had the highest proportion of male patients (96.6%), the highest proportion of patients with smoking (91.2%) and alcohol (59.8%) history, the highest level of eGFR (83.81 ± 19.06 ml/min/1.73m2), and the lowest level of HDL-C (1.07 ± 0.28 mmol/L). The CCTA characteristics varied with different clusters: (1) Cluster 1 had the largest number of segments with calcified plaques (2.43 ± 2.46) and the least number of segments with mixed plaques (2.24 ± 2.59) and obstructive stenosis (0.98 ± 2.00); (2) Cluster 1 had the lowest proportion of patients with mixed plaques (68%) and obstructive stenosis (32.2%); (3) Cluster 3 had more segments with noncalcified plaques than cluster 1 (0.63 ± 1.02 vs 0.40 ± 0.78, P < 0.05) and the highest proportion of patients with noncalcified plaques (39.9%) and (4) There was no significant difference in the extent of coronary plaques among the three clusters. CONCLUSIONS: The unsupervised clustering method could address T2DM patients with heterogeneous clinical indicators and identify groups with different types of coronary plaque and degrees of coronary stenosis. This method has the potential for patient stratification, which is essential for the clinical management of T2DM patients with coronary atherosclerosis.