Combined conventional factors and the radiomics signature of coronary plaque texture could improve cardiac risk prediction.

OBJECTIVES: This study aims to investigate how radiomics analysis can help understand the association between plaque texture, epicardial adipose tissue (EAT), and cardiovascular risk. Working with a Photon-counting CT, which exhibits enhanced feature stability, offers the potential to advance radiomics analysis and enable its integration into clinical routines. METHODS: Coronary plaques were manually segmented in this retrospective, single-centre study and radiomic features were extracted using pyradiomics. The study population was divided into groups according to the presence of high-risk plaques (HRP), plaques with at least 50% stenosis, plaques with at least 70% stenosis, or triple-vessel disease. A combined group with patients exhibiting at least one of these risk factors was formed. Random forest feature selection identified differentiating features for the groups. EAT thickness and density were measured and compared with feature selection results. RESULTS: A total number of 306 plaques from 61 patients (mean age 61 years +/- 8.85 [standard deviation], 13 female) were analysed. Plaques of patients with HRP features or relevant stenosis demonstrated a higher presence of texture heterogeneity through various radiomics features compared to patients with only an intermediate stenosis degree. While EAT thickness did not significantly differ, affected patients showed significantly higher mean densities in the 50%, HRP, and combined groups, and insignificantly higher densities in the 70% and triple-vessel groups. CONCLUSION: The combination of a higher EAT density and a more heterogeneous plaque texture might offer an additional tool in identifying patients with an elevated risk of cardiovascular events. CLINICAL RELEVANCE STATEMENT: Cardiovascular disease is the leading cause of mortality globally. Plaque composition and changes in the EAT are connected to cardiac risk. A better understanding of the interrelation of these risk indicators can lead to improved cardiac risk prediction. KEY POINTS: Cardiac plaque composition and changes in the EAT are connected to cardiac risk. Higher EAT density and more heterogeneous plaque texture are related to traditional risk indicators. Radiomics texture analysis conducted on PCCT scans can help identify patients with elevated cardiac risk.

Multi-scale structural characterization of ceramic-based photonic glasses for structural colors.

Structural colors arise from selective light interaction with (nano)structures, which give them advantages over pigmented colors such as resistance to fading and possibility to be fabricated out of traditional low-cost and non-toxic materials. Since the color arises from the photonic (nano)structures, different structural features can impact their photonic response and thus, their color. Therefore, the detailed characterization of their structural features is crucial for further improvement of structural colors. In this work, we present a detailed multi-scale structural characterization of ceramic-based photonic glasses by using a combination of high-resolution ptychographic X-ray computed tomography and small angle X-ray scattering. Our results uncover the structure-processing-properties' relationships of such nanoparticles-based photonic glasses and point out to the need of a review of the structural features used in simulation models concomitantly with the need for further investigations by experimentalists, where we point out exactly which structural features need to be improved.

CT evaluation of bowel wall enhancement in pneumatosis intestinalis: preventing non-therapeutic laparotomies.

PURPOSE: To evaluate the diagnostic performance of bowel wall enhancement for diagnosing concomitant bowel ischemia in patients with parietal pneumatosis (PI) diagnosed at abdominal CT. MATERIALS AND METHODS: From January 1, 2012 to December 31, 2021, 226 consecutive patients who presented with PI on abdominal CT from any bowel segment were included. Variables at the time of the CT were retrospectively extracted from medical charts. CT examinations were blindly analyzed by two independent radiologists. The third reader classified all disagreement of bowel enhancement in three categories: (1) normal bowel enhancement; (2) doubtful bowel wall enhancement; (3) absent bowel wall enhancement. Multivariable logistic regression analysis was performed. Concomitant bowel ischemia was defined as requirement of bowel resection specifically due to ischemic lesion in operated patients and death from bowel ischemia in non-operated patients. RESULTS: Overall, 78/226 (35%) patients had PI associated with concomitant bowel ischemia. At multivariate analysis, Only absence or doubtful bowel wall enhancement was associated with concomitant bowel ischemia (OR = 167.73 95%CI [23.39-4349.81], P < 0,001) and acute mesenteric ischemia associated with PP (OR = 67.94; 95%CI [5.18-3262.36], P < 0.009). Among the 82 patients who underwent a laparotomy for suspected bowel ischemia, rate of non-therapeutic laparotomy increased from 15/59 (25%), 2/6 (50%) and 16/17 (94%) when bowel wall enhancement was absent, doubtful and normal respectively. CONCLUSION: Absence of enhancement of the bowel wall is the primary feature associated with concomitant bowel ischemia. It should be carefully assessed when PI is detected to avoid non-therapeutic laparotomy.

Development and validation of a predictive model for vertebral fracture risk in osteoporosis patients.

OBJECTIVE: This study aimed to develop and validate a predictive model for osteoporotic vertebral fractures (OVFs) risk by integrating demographic, bone mineral density (BMD), CT imaging, and deep learning radiomics features from CT images. METHODS: A total of 169 osteoporosis-diagnosed patients from three hospitals were randomly split into OVFs (n = 77) and Non-OVFs (n = 92) groups for training (n = 135) and test (n = 34). Demographic data, BMD, and CT imaging details were collected. Deep transfer learning (DTL) using ResNet-50 and radiomics features were fused, with the best model chosen via logistic regression. Cox proportional hazards models identified clinical factors. Three models were constructed: clinical, radiomics-DTL, and fusion (clinical-radiomics-DTL). Performance was assessed using AUC, C-index, Kaplan-Meier, and calibration curves. The best model was depicted as a nomogram, and clinical utility was evaluated using decision curve analysis (DCA). RESULTS: BMD, CT values of paravertebral muscles (PVM), and paravertebral muscles' cross-sectional area (CSA) significantly differed between OVFs and Non-OVFs groups (P < 0.05). No significant differences were found between training and test cohort. Multivariate Cox models identified BMD, CT values of PVM, and CSAPS reduction as independent OVFs risk factors (P < 0.05). The fusion model exhibited the highest predictive performance (C-index: 0.839 in training, 0.795 in test). DCA confirmed the nomogram's utility in OVFs risk prediction. CONCLUSION: This study presents a robust predictive model for OVFs risk, integrating BMD, CT data, and radiomics-DTL features, offering high sensitivity and specificity. The model's visualizations can inform OVFs prevention and treatment strategies.

New powder reuse schema in laser-based powder bed fusion of polymers.

The laser-based powder bed fusion of polymers (PBF-LB/P) process often utilizes a blend of powders with varying degrees of degradation. Specifically, for polyamide 12, the traditional reuse schema involves mixing post-processed powder with virgin powder at a predetermined ratio before reintroducing it to the process. Given that only about 15% of the powder is utilized in part production, and powders are refreshed in equal proportions, there arises a challenge with the incremental accumulation of material across build cycles. To mitigate the consumption of fresh powder relative to the actual material usage, this study introduces the incorporation of recycled material into the PBF-LB/P process. This new powder reuse schema is presented for the first time, focusing on the laser sintering process. The characteristics of the recycled powder were evaluated through scanning electron microscopy, differential scanning calorimetry, X-ray diffraction, particle size distribution, and dynamic powder flowability assessments. The findings reveal that waste powders can be effectively reused in PBF-LB/P to produce components with satisfactory mechanical properties, porosity levels, dimensional accuracy, and surface quality.

3D airway geometry analysis of factors in airway navigation failure for lung nodules.

BACKGROUND: This study aimed to quantitatively reveal contributing factors to airway navigation failure during radial probe endobronchial ultrasound (R-EBUS) by using geometric analysis in a three-dimensional (3D) space and to investigate the clinical feasibility of prediction models for airway navigation failure. METHODS: We retrospectively reviewed patients who underwent R-EBUS between January 2017 and December 2018. Geometric quantification was analyzed using in-house software built with open-source python libraries including the Vascular Modeling Toolkit ( http://www.vmtk.org ), simple insight toolkit ( https://sitk.org ), and sci-kit image ( https://scikit-image.org ). We used a machine learning-based approach to explore the utility of these significant factors. RESULTS: Of the 491 patients who were eligible for analysis (mean age, 65 years +/- 11 [standard deviation]; 274 men), the target lesion was reached in 434 and was not reached in 57. Twenty-seven patients in the failure group were matched with 27 patients in the success group based on propensity scores. Bifurcation angle at the target branch, the least diameter of the last section, and the curvature of the last section are the most significant and stable factors for airway navigation failure. The support vector machine can predict airway navigation failure with an average area under the curve of 0.803. CONCLUSIONS: Geometric analysis in 3D space revealed that a large bifurcation angle and a narrow and tortuous structure of the closest bronchus from the lesion are associated with airway navigation failure during R-EBUS. The models developed using quantitative computer tomography scan imaging show the potential to predict airway navigation failure.

Computed Tomography-Based Intratumor Heterogeneity Predicts Response to Immunotherapy Plus Chemotherapy in Esophageal Squamous Cell Carcinoma.

RATIONALE AND OBJECTIVES: This study explored the intratumor heterogeneity (ITH) of esophageal squamous cell carcinoma (ESCC) using computed tomography (CT) and investigated the value of CT-based ITH in predicting the response to immune checkpoint inhibitor (ICI) plus chemotherapy in patients with ESCC. MATERIALS AND METHODS: This retrospective study included 416 patients with ESCC who received ICI plus chemotherapy at two independent hospitals between January 2019 and July 2022. Multiparametric CT features were extracted from ESCC lesions and screened using hierarchical clustering and dimensionality reduction algorithms. Logistic regression and machine learning models based on selected features were developed to predict treatment response and validated in separate datasets. ITH was quantified using the score calculated by the best-performing model and visualized through feature clustering and feature contribution heatmaps. A gene set enrichment analysis (GSEA) was performed to identify the biological pathways underlying the CT-based ITH. RESULTS: The extreme gradient boosting model based on CT-derived ITH had higher discriminative power, with areas under the receiver operating characteristic curve of 0.864 (95% confidence interval [CI]: 0.774-0.954) and 0.796 (95% CI: 0.698-0.893) in the internal and external validation sets. The CT-based ITH pattern differed significantly between responding and non-responding patients. The GSEA indicated that CT-based ITH was associated with immunity-, keratinization-, and epidermal cell differentiation-related pathways. CONCLUSION: CT-based ITH is an effective biomarker for identifying patients with ESCC who could benefit from ICI plus chemotherapy. Immunity-, keratinization-, and epidermal cell differentiation-related pathways may influence the patient's response to ICI plus chemotherapy.

CT radiomics to differentiate neuroendocrine neoplasm from adenocarcinoma in patients with a peripheral solid pulmonary nodule: a multicenter study.

Purpose: To construct and validate a computed tomography (CT) radiomics model for differentiating lung neuroendocrine neoplasm (LNEN) from lung adenocarcinoma (LADC) manifesting as a peripheral solid nodule (PSN) to aid in early clinical decision-making. Methods: A total of 445 patients with pathologically confirmed LNEN and LADC from June 2016 to July 2023 were retrospectively included from five medical centers. Those patients were split into the training set (n = 316; 158 LNEN) and external test set (n = 129; 43 LNEN), the former including the cross-validation (CV) training set and CV test set using ten-fold CV. The support vector machine (SVM) classifier was used to develop the semantic, radiomics and merged models. The diagnostic performances were evaluated by the area under the receiver operating characteristic curve (AUC) and compared by Delong test. Preoperative neuron-specific enolase (NSE) levels were collected as a clinical predictor. Results: In the training set, the AUCs of the radiomics model (0.878 [95% CI: 0.836, 0.915]) and merged model (0.884 [95% CI: 0.844, 0.919]) significantly outperformed the semantic model (0.718 [95% CI: 0.663, 0.769], p both<.001). In the external test set, the AUCs of the radiomics model (0.787 [95% CI: 0.696, 0.871]), merged model (0.807 [95%CI: 0.720, 0.889]) and semantic model (0.729 [95% CI: 0.631, 0.811]) did not exhibit statistical differences. The radiomics model outperformed NSE in sensitivity in the training set (85.3% vs 20.0%; p <.001) and external test set (88.9% vs 40.7%; p = .002). Conclusion: The CT radiomics model could non-invasively, effectively and sensitively predict LNEN and LADC presenting as a PSN to assist in treatment strategy selection.

Deep learning in pulmonary nodule detection and segmentation: a systematic review.

OBJECTIVES: The accurate detection and precise segmentation of lung nodules on computed tomography are key prerequisites for early diagnosis and appropriate treatment of lung cancer. This study was designed to compare detection and segmentation methods for pulmonary nodules using deep-learning techniques to fill methodological gaps and biases in the existing literature. METHODS: This study utilized a systematic review with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines, searching PubMed, Embase, Web of Science Core Collection, and the Cochrane Library databases up to May 10, 2023. The Quality Assessment of Diagnostic Accuracy Studies 2 criteria was used to assess the risk of bias and was adjusted with the Checklist for Artificial Intelligence in Medical Imaging. The study analyzed and extracted model performance, data sources, and task-focus information. RESULTS: After screening, we included nine studies meeting our inclusion criteria. These studies were published between 2019 and 2023 and predominantly used public datasets, with the Lung Image Database Consortium Image Collection and Image Database Resource Initiative and Lung Nodule Analysis 2016 being the most common. The studies focused on detection, segmentation, and other tasks, primarily utilizing Convolutional Neural Networks for model development. Performance evaluation covered multiple metrics, including sensitivity and the Dice coefficient. CONCLUSIONS: This study highlights the potential power of deep learning in lung nodule detection and segmentation. It underscores the importance of standardized data processing, code and data sharing, the value of external test datasets, and the need to balance model complexity and efficiency in future research. CLINICAL RELEVANCE STATEMENT: Deep learning demonstrates significant promise in autonomously detecting and segmenting pulmonary nodules. Future research should address methodological shortcomings and variability to enhance its clinical utility. KEY POINTS: Deep learning shows potential in the detection and segmentation of pulmonary nodules. There are methodological gaps and biases present in the existing literature. Factors such as external validation and transparency affect the clinical application.

Virtual noncontrast images reveal gouty tophi in contrast-enhanced dual-energy CT: a phantom study.

BACKGROUND: Dual-energy computed tomography (DECT) is useful for detecting gouty tophi. While iodinated contrast media (ICM) might enhance the detection of monosodium urate crystals (MSU), higher iodine concentrations hamper their detection. Calculating virtual noncontrast (VNC) images might improve the detection of enhancing tophi. The aim of this study was to evaluate MSU detection with VNC images from DECT acquisitions in phantoms, compared against the results with standard DECT reconstructions. METHODS: A grid-like and a biophantom with 25 suspensions containing different concentrations of ICM (0 to 2%) and MSU (0 to 50%) were scanned with sequential single-source DECT using an ascending order of tube current time product at 80 kVp (16.5-220 mAs) and 135 kVp (2.75-19.25 mAs). VNC images were equivalently reconstructed at 80 and 135 kVp. Two-material decomposition analysis for MSU detection was applied for the VNC and conventional CT images. MSU detection and attenuation values were compared in both modalities. RESULTS: For 0, 0.25, 0.5, 1, and 2% ICM, the average detection indices (DIs) for all MSU concentrations (35-50%) with VNC postprocessing were respectively 25.2, 36.6, 30.9, 38.9, and 45.8% for the grid phantom scans and 11.7, 9.4, 5.5, 24.0, and 25.0% for the porcine phantom scans. In the conventional CT image group, the average DIs were respectively 35.4, 54.3, 45.4, 1.0, and 0.0% for the grid phantom and 19.4, 17.9, 3.0, 0.0, and 0.0% for the porcine phantom scans. CONCLUSIONS: VNC effectively reduces the suppression of information caused by high concentrations of ICM, thereby improving the detection of MSU. RELEVANCE STATEMENT: Contrast-enhanced DECT alone may suffice for diagnosing gout without a native acquisition. KEY POINTS: • Highly concentrated contrast media hinders monosodium urate crystal detection in CT imaging • Virtual noncontrast imaging redetects monosodium urate crystals in high-iodinated contrast media concentrations. • Contrast-enhanced DECT alone may suffice for diagnosing gout without a native acquisition.

CT and MRI radiomic features of lung cancer (NSCLC): comparison and software consistency.

BACKGROUND: Radiomics is a quantitative approach that allows the extraction of mineable data from medical images. Despite the growing clinical interest, radiomics studies are affected by variability stemming from analysis choices. We aimed to investigate the agreement between two open-source radiomics software for both contrast-enhanced computed tomography (CT) and contrast-enhanced magnetic resonance imaging (MRI) of lung cancers and to preliminarily evaluate the existence of radiomic features stable for both techniques. METHODS: Contrast-enhanced CT and MRI images of 35 patients affected with non-small cell lung cancer (NSCLC) were manually segmented and preprocessed using three different methods. Sixty-six Image Biomarker Standardisation Initiative-compliant features common to the considered platforms, PyRadiomics and LIFEx, were extracted. The correlation among features with the same mathematical definition was analyzed by comparing PyRadiomics and LIFEx (at fixed imaging technique), and MRI with CT results (for the same software). RESULTS: When assessing the agreement between LIFEx and PyRadiomics across the considered resampling, the maximum statistically significant correlations were observed to be 94% for CT features and 95% for MRI ones. When examining the correlation between features extracted from contrast-enhanced CT and MRI using the same software, higher significant correspondences were identified in 11% of features for both software. CONCLUSIONS: Considering NSCLC, (i) for both imaging techniques, LIFEx and PyRadiomics agreed on average for 90% of features, with MRI being more affected by resampling and (ii) CT and MRI contained mostly non-redundant information, but there are shape features and, more importantly, texture features that can be singled out by both techniques. RELEVANCE STATEMENT: Identifying and selecting features that are stable cross-modalities may be one of the strategies to pave the way for radiomics clinical translation. KEY POINTS: • More than 90% of LIFEx and PyRadiomics features contain the same information. • Ten percent of features (shape, texture) are stable among contrast-enhanced CT and MRI. • Software compliance and cross-modalities stability features are impacted by the resampling method.

Diagnostic accuracy of CT-based radiomics and deep learning for predicting lymph node metastasis in esophageal cancer.

BACKGROUND: Esophageal cancer remains a global challenge due to late diagnoses and limited treatments. Lymph node metastasis (LNM) is crucial for prognosis, yet traditional diagnostics fall short. Integrating radiomics and deep learning (DL) with CT imaging for LNM diagnosis could revolutionize prognostic assessment and treatment planning. METHODS: A systematic review and meta-analysis were conducted by searching PubMed, Scopus, Web of Science, and Embase up to October 1, 2023. The focus was on studies developing CT-based radiomics and/or DL models for preoperative LNM detection in esophageal cancer. Methodological quality was assessed using the METhodological RadiomICs Score (METRICS). RESULTS: Twelve studies were reviewed, and seven were included in the meta-analysis, most showing excellent methodological quality. Training sets revealed a pooled AUC of 87 % (95 % CI: 78 %-90 %), and internal validation sets showed an AUC of 85 % (95 % CI: 76 %-89 %), with no significant difference (p = 0.39). Sensitivity and specificity for training sets were 78.7 % and 81.8 %, respectively, with validation sets at 81.2 % and 76.2 %. DL models in training sets showed better diagnostic accuracy than radiomics (p = 0.054), significant after removing outliers (p < 0.01). Incorporating clinical data improved sensitivity in validation sets (p = 0.029). No significant difference was found between models based on CE or non-CE imaging (p = 0.281) or arterial or venous phase imaging (p = 0.927). CONCLUSION: Integrating CT-based radiomics and DL improves LNM detection in esophageal cancer. Including clinical data could enhance model performance. Future research should focus on multicenter studies with independent validations to confirm these findings and promote broader clinical adoption.

The value of the radiological diameter-to-thickness ratio in patients with HER2-positive resectable advanced gastric cancer: implications for long survival and stage migration.

PURPOSE: To investigate the clinical significance and stage migration effect of radiological diameter-to-thickness (DT) ratio in HER2-positive resectable advanced gastric cancer (HER2-p RAGC). METHODS: 369 HER2-p RAGC patients were retrospectively enrolled and information on clinical pathological characteristics, radiological DT ratio, and outcomes [i.e., overall survival (OS) and progression-free survival (PFS)] was collected. Pearson's Chi-square and Student's t-test were employed to compare baseline characteristics. Clinical outcomes were estimated using Kaplan-Meier analysis and Log-rank test. Univariate and multivariate Cox regression models were utilized to analyze independent prognostic factors. RESULTS: HER2-p RAGC patients were stratified into two groups using a DT ratio cutoff value of 4.0 (p < 0.05). Patients with a DT ratio < 4.0 exhibited significantly longer OS (58.0 vs. 31.0 months) and PFS (43.0 vs. 24.0 months) than those with a DT ratio ≥ 4.0. DT ratio significantly predicted prognosis for N0 and II stage patients (p < 0.05). Patients with gastric body and antrum cancers demonstrated longer OS and PFS in the DT ratio < 4.0 group (p = 0.046, 0.017, 0.036 and 0.028). Multivariate Cox proportional hazard model identified age, pathological T category, pathological N category, pathological TNM category and DT ratio as independent prognostic factors. Notably, pStage II patients with a DT ratio ≥ 4.0 exhibited a similar prognosis to pStage III patients with a DT ratio < 4.0 (p = 0.418 for OS, 0.867 for PFS). CONCLUSION: Radiological DT ratio could evaluate the prognosis and detect higher malignant cases in HER2-p RAGC patients. Moreover, DT ratio might guide clinicians make postoperative strategies. TRIAL REGISTRATION: Retrospectively registered.

Impact of reconstruction parameters on the accuracy of myocardial extracellular volume quantification on a first-generation, photon-counting detector CT.

BACKGROUND: The potential role of cardiac computed tomography (CT) has increasingly been demonstrated for the assessment of diffuse myocardial fibrosis through the quantification of extracellular volume (ECV). Photon-counting detector (PCD)-CT technology may deliver more accurate ECV quantification compared to energy-integrating detector CT. We evaluated the impact of reconstruction settings on the accuracy of ECV quantification using PCD-CT, with magnetic resonance imaging (MRI)-based ECV as reference. METHODS: In this post hoc analysis, 27 patients (aged 53.1 ± 17.2 years (mean ± standard deviation); 14 women) underwent same-day cardiac PCD-CT and MRI. Late iodine CT scans were reconstructed with different quantum iterative reconstruction levels (QIR 1-4), slice thicknesses (0.4-8 mm), and virtual monoenergetic imaging levels (VMI, 40-90 keV); ECV was quantified for each reconstruction setting. Repeated measures ANOVA and t-test for pairwise comparisons, Bland-Altman plots, and Lin's concordance correlation coefficient (CCC) were used. RESULTS: ECV values did not differ significantly among QIR levels (p = 1.000). A significant difference was observed throughout different slice thicknesses, with 0.4 mm yielding the highest agreement with MRI-based ECV (CCC = 0.944); 45-keV VMI reconstructions showed the lowest mean bias (0.6, 95% confidence interval 0.1-1.4) compared to MRI. Using the most optimal reconstruction settings (QIR4. slice thickness 0.4 mm, VMI 45 keV), a 63% reduction in mean bias and a 6% increase in concordance with MRI-based ECV were achieved compared to standard settings (QIR3, slice thickness 1.5 mm; VMI 65 keV). CONCLUSIONS: The selection of appropriate reconstruction parameters improved the agreement between PCD-CT and MRI-based ECV. RELEVANCE STATEMENT: Tailoring PCD-CT reconstruction parameters optimizes ECV quantification compared to MRI, potentially improving its clinical utility. KEY POINTS: • CT is increasingly promising for myocardial tissue characterization, assessing focal and diffuse fibrosis via late iodine enhancement and ECV quantification, respectively. • PCD-CT offers superior performance over conventional CT, potentially improving ECV quantification and its agreement with MRI-based ECV. • Tailoring PCD-CT reconstruction parameters optimizes ECV quantification compared to MRI, potentially improving its clinical utility.

Predicting lymphovascular invasion in non-small cell lung cancer using deep convolutional neural networks on preoperative chest CT.

RATIONALE AND OBJECTIVES: Lymphovascular invasion (LVI) plays a significant role in precise treatments of non-small cell lung cancer (NSCLC). This study aims to build a non-invasive LVI prediction diagnosis model by combining preoperative CT images with deep learning technology. MATERIALS AND METHODS: This retrospective observational study included a series of consecutive patients who underwent surgical resection for non-small cell lung cancer (NSCLC) and received pathologically confirmed diagnoses. The cohort was randomly divided into a training group comprising 70 % of the patients and a validation group comprising the remaining 30 %. Four distinct deep convolutional neural network (DCNN) prediction models were developed, incorporating different combination of two-dimensional (2D) and three-dimensional (3D) CT imaging features as well as clinical-radiological data. The predictive capabilities of the models were evaluated by receiver operating characteristic curves (AUC) values and confusion matrices. The Delong test was utilized to compare the predictive performance among the different models. RESULTS: A total of 3034 patients with NSCLC were recruited in this study including 106 LVI+ patients. In the validation cohort, the Dual-head Res2Net_3D23F model achieved the highest AUC of 0.869, closely followed by the models of Dual-head Res2Net_3D3F (AUC, 0.868), Dual-head Res2Net_3D (AUC, 0.867), and EfficientNet-B0_2D (AUC, 0.857). There was no significant difference observed in the performance of the EfficientNet-B0_2D model when compared to the Dual-head Res2Net_3D3F and Dual-head Res2Net_3D23F. CONCLUSION: Findings of this study suggest that utilizing deep convolutional neural network is a feasible approach for predicting pathological LVI in patients with NSCLC.

Quantitative evaluation of CTP derived time-density alterations versus CTP for collateral status prediction with stroke.

BACKGROUND AND OBJECTIVES: Collateral status is a pivotal determinant of clinical outcomes in acute ischemic stroke (AIS); however, its evaluation can be challenging. We investigated the predictive value of CT perfusion (CTP) derived time and density alterations versus CTP for collateral status prediction in AIS. METHODS: Consecutive patients with anterior circulation occlusion within 24 h were retrospectively included. Time-density curves of the CTP specified ischemic core, penumbra, and the corresponding contralateral unaffected brain were obtained. The collateral status was dichotomised into robust (4-5 scores) and poor (0-3 scores) using multiphase collateral scoring, as described by Menon et al.. Receiver operating characteristic curves and multivariable regression analysis were performed to assess the predictive ability of CTP-designated tissue time and density alterations, CTP for robust collaterals, and favourable outcomes (mRS score of 0-2 at 90 days). RESULTS: One-hundred patients (median age, 68 years; interquartile range, 57-80 years; 61 men) were included. A smaller ischemic core, shorter peak time delay, lower peak density decrease, lower cerebral blood volume ratio, and cerebral blood flow ratio in the CTP specified ischemic core were significantly associated with robust collaterals (PFDR ≤ 0.004). The peak time delay demonstrated the highest diagnostic value (AUC, 0.74; P < 0.001) with 66.7 % sensitivity and 73.7 % specificity. Furthermore, the peak time delay of less than 8.5 s was an independent predictor of robust collaterals and favourable clinical outcomes. CONCLUSIONS: Robust collateral status was significantly associated with the peak time delay in the ischemic core. It is a promising image marker for predicting collateral status and functional outcomes in AIS.

Hodgkin lymphoma: hypodense lesions in mediastinal masses.

Hypodense volumes (HDV) in mediastinal masses can be visualized in a computed tomography scan in Hodgkin lymphoma. We analyzed staging CT scans of 1178 patients with mediastinal involvement from the EuroNet-PHL-C1 trial and explored correlations of HDV with patient characteristics, mediastinal tumor volume and progression-free survival. HDV occurred in 350 of 1178 patients (29.7%), typically in larger mediastinal volumes. There were different patterns in appearance with single lesions found in 243 patients (69.4%), multiple lesions in 107 patients (30.6%). Well delineated lesions were found in 248 cases (70.1%), diffuse lesions were seen in 102 cases (29.1%). Clinically, B symptoms occurred more often in patients with HDV (47.7% compared to 35.0% without HDV (p = 0.039)) and patients with HDV tended to be in higher risk groups. Inadequate overall early-18F-FDG-PET-response was strongly correlated with the occurrence of hypodense lesions (p < 0.001). Patients with total HDV > 40 ml (n = 80) had a 5 year PFS of 79.6% compared to 89.7% (p = 0.01) in patients with HDV < 40 ml or no HDV. This difference in PFS is not caused by treatment group alone. HDV is a common phenomenon in HL with mediastinal involvement.

Quantitative analysis of interstitial lung abnormalities on computed tomography to predict symptomatic radiation pneumonitis after lung stereotactic body radiotherapy.

BACKGROUND AND PURPOSE: Symptomatic radiation pneumonitis (SRP) is a complication of thoracic stereotactic body radiotherapy (SBRT). As visual assessments pose limitations, artificial intelligence-based quantitative computed tomography image analysis software (AIQCT) may help predict SRP risk. We aimed to evaluate high-resolution computed tomography (HRCT) images with AIQCT to develop a predictive model for SRP. MATERIALS AND METHODS: AIQCT automatically labelled HRCT images of patients treated with SBRT for stage I lung cancer according to lung parenchymal pattern. Quantitative data including the volume and mean dose (Dmean) were obtained for reticulation + honeycombing (Ret + HC), consolidation + ground-glass opacities, bronchi (Br), and normal lungs (NL). After associations between AIQCT's quantified metrics and SRP were investigated, we developed a predictive model using recursive partitioning analysis (RPA) for the training cohort and assessed its reproducibility with the testing cohort. RESULTS: Overall, 26 of 207 patients developed SRP. There were significant between-group differences in the Ret + HC, Br-volume, and NL-Dmean in patients with and without SRP. RPA identified the following risk groups: NL-Dmean ≥ 6.6 Gy (high-risk, n = 8), NL-Dmean < 6.6 Gy and Br-volume ≥ 2.5 % (intermediate-risk, n = 13), and NL-Dmean < 6.6 Gy and Br-volume < 2.5 % (low-risk, n = 133). The incidences of SRP in these groups within the training cohort were 62.5, 38.4, and 7.5 %; and in the testing cohort 50.0, 27.3, and 5.0 %, respectively. CONCLUSION: AIQCT identified CT features associated with SRP. A predictive model for SRP was proposed based on AI-detected Br-volume and the NL-Dmean.