Signal enhancement ratio of multi-phase contrast-enhanced MRI: an imaging biomarker for survival in pancreatic adenocarcinoma.

OBJECTIVES: To evaluate signal enhancement ratio (SER) for tissue characterization and prognosis stratification in pancreatic adenocarcinoma (PDAC), with quantitative histopathological analysis (QHA) as the reference standard. METHODS: This retrospective study included 277 PDAC patients who underwent multi-phase contrast-enhanced (CE) MRI and whole-slide imaging (WSI) from three centers (2015-2021). SER is defined as (SIlt - SIpre)/(SIea - SIpre), where SIpre, SIea, and SIlt represent the signal intensity of the tumor in pre-contrast, early-, and late post-contrast images, respectively. Deep-learning algorithms were implemented to quantify the stroma, epithelium, and lumen of PDAC on WSIs. Correlation, regression, and Bland-Altman analyses were utilized to investigate the associations between SER and QHA. The prognostic significance of SER on overall survival (OS) was evaluated using Cox regression analysis and Kaplan-Meier curves. RESULTS: The internal dataset comprised 159 patients, which was further divided into training, validation, and internal test datasets (n = 60, 41, and 58, respectively). Sixty-five and 53 patients were included in two external test datasets. Excluding lumen, SER demonstrated significant correlations with stroma (r = 0.29-0.74, all p < 0.001) and epithelium (r = -0.23 to -0.71, all p < 0.001) across a wide post-injection time window (range, 25-300 s). Bland-Altman analysis revealed a small bias between SER and QHA for quantifying stroma/epithelium in individual training, validation (all within ± 2%), and three test datasets (all within ± 4%). Moreover, SER-predicted low stromal proportion was independently associated with worse OS (HR = 1.84 (1.17-2.91), p = 0.009) in training and validation datasets, which remained significant across three combined test datasets (HR = 1.73 (1.25-2.41), p = 0.001). CONCLUSION: SER of multi-phase CE-MRI allows for tissue characterization and prognosis stratification in PDAC. CLINICAL RELEVANCE STATEMENT: The signal enhancement ratio of multi-phase CE-MRI can serve as a novel imaging biomarker for characterizing tissue composition and holds the potential for improving patient stratification and therapy in PDAC. KEY POINTS: Imaging biomarkers are needed to better characterize tumor tissue in pancreatic adenocarcinoma. Signal enhancement ratio (SER)-predicted stromal/epithelial proportion showed good agreement with histopathology measurements across three distinct centers. Signal enhancement ratio (SER)-predicted stromal proportion was demonstrated to be an independent prognostic factor for OS in PDAC.

TPA: Two-stage progressive attention segmentation framework for hepatocellular carcinoma on multi-modality MRI.

BACKGROUND: Dynamic contrast enhanced magnetic resonance imaging (DCE-MRI) plays a crucial role in the diagnosis and measurement of hepatocellular carcinoma (HCC). The multi-modality information contained in the multi-phase images of DCE-MRI is important for improving segmentation. However, this remains a challenging task due to the heterogeneity of HCC, which may cause one HCC lesion to have varied imaging appearance in each phase of DCE-MRI. In particular, some phases exhibit inconsistent sizes and boundaries will result in a lack of correlation between modalities, and it may pose inaccurate segmentation results. PURPOSE: We aim to design a multi-modality segmentation model that can learn meaningful inter-phase correlation for achieving HCC segmentation. METHODS: In this study, we propose a two-stage progressive attention segmentation framework (TPA) for HCC based on the transformer and the decision-making process of radiologists. Specifically, the first stage aims to fuse features from multi-phase images to identify HCC and provide localization region. In the second stage, a multi-modality attention transformer module (MAT) is designed to focus on the features that can represent the actual size. RESULTS: We conduct training, validation, and test in a single-center dataset (386 cases), followed by external test on a batch of multi-center datasets (83 cases). Furthermore, we analyze a subgroup of data with weak inter-phase correlation in the test set. The proposed model achieves Dice coefficient of 0.822 and 0.772 in the internal and external test sets, respectively, and 0.829, 0.791 in the subgroup. The experimental results demonstrate that our model outperforms state-of-the-art models, particularly within subgroup. CONCLUSIONS: The proposed TPA provides best segmentation results, and utilizing clinical prior knowledge for network design is practical and feasible.

Predicting post-resection recurrence by integrating imaging-based surrogates of distinct vascular patterns of hepatocellular carcinoma.

Background & Aims: Distinct vascular patterns, including microvascular invasion (MVI) and vessels encapsulating tumour clusters (VETC), are associated with poor outcomes of hepatocellular carcinoma (HCC). Imaging surrogates of these vascular patterns potentially help to predict post-resection recurrence. Herein, a prognostic model integrating imaging-based surrogates of these distinct vascular patterns was developed to predict postoperative recurrence-free survival (RFS) in patients with HCC. Methods: Clinico-radiological data of 1,285 patients with HCC from China undergoing surgical resection were retrospectively enrolled from seven medical centres between 2014 and 2020. A prognostic model using clinical data and imaging-based surrogates of MVI and VETC patterns was developed (n = 297) and externally validated (n = 373) to predict RFS. The surrogates (i.e. MVI and VETC scores) were individually built from preoperative computed tomography using two independent cohorts (n = 360 and 255). Whether the model's stratification was associated with postoperative recurrence following anatomic resection was also evaluated. Results: The MVI and VETC scores demonstrated effective performance in their respective training and validation cohorts (AUC: 0.851-0.883 for MVI and 0.834-0.844 for VETC). The prognostic model incorporating serum alpha-foetoprotein, tumour multiplicity, MVI score, and VETC score achieved a C-index of 0.748-0.764 for the developing and external validation cohorts and generated three prognostically distinct strata. For patients at model-predicted medium risk, anatomic resection was associated with improved RFS (p <0.05). By contrast, anatomic resection had no impact on RFS in patients at model-predicted low or high risk (both p >0.05). Conclusions: The proposed model integrating imaging-based surrogates of distinct vascular patterns enabled accurate prediction for RFS. It can potentially be used to identify HCC surgical candidates who may benefit from anatomic resection. Impact and implications: MVI and VETC are distinct vascular patterns of HCC associated with aggressive biological behaviour and poor outcomes. Our multicentre study provided a model incorporating imaging-based surrogates of these patterns for preoperatively predicting RFS. The proposed model, which uses imaging detection to estimate the risk of MVI and VETC, offers an opportunity to help shed light on the association between tumour aggressiveness and prognosis and to support the selection of the appropriate type of surgical resection.

Predicting Microvascular Invasion in Hepatocellular Carcinoma Using CT-based Radiomics Model.

Background Prediction of microvascular invasion (MVI) may help determine treatment strategies for hepatocellular carcinoma (HCC). Purpose To develop a radiomics approach for predicting MVI status based on preoperative multiphase CT images and to identify MVI-associated differentially expressed genes. Materials and Methods Patients with pathologically proven HCC from May 2012 to September 2020 were retrospectively included from four medical centers. Radiomics features were extracted from tumors and peritumor regions on preoperative registration or subtraction CT images. In the training set, these features were used to build five radiomics models via logistic regression after feature reduction. The models were tested using internal and external test sets against a pathologic reference standard to calculate area under the receiver operating characteristic curve (AUC). The optimal AUC radiomics model and clinical-radiologic characteristics were combined to build the hybrid model. The log-rank test was used in the outcome cohort (Kunming center) to analyze early recurrence-free survival and overall survival based on high versus low model-derived score. RNA sequencing data from The Cancer Image Archive were used for gene expression analysis. Results A total of 773 patients (median age, 59 years; IQR, 49-64 years; 633 men) were divided into the training set (n = 334), internal test set (n = 142), external test set (n = 141), outcome cohort (n = 121), and RNA sequencing analysis set (n = 35). The AUCs from the radiomics and hybrid models, respectively, were 0.76 and 0.86 for the internal test set and 0.72 and 0.84 for the external test set. Early recurrence-free survival (P < .01) and overall survival (P < .007) can be categorized using the hybrid model. Differentially expressed genes in patients with findings positive for MVI were involved in glucose metabolism. Conclusion The hybrid model showed the best performance in prediction of MVI. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Summers in this issue.

The impact of iron deposition on the fear circuit of the brain in patients with Parkinson's disease and anxiety.

Objective: Anxiety is one of the most common psychiatric symptoms of Parkinson's disease (PD), and brain iron deposition is considered to be one of the pathological mechanisms of PD. The objective of this study was to explore alterations in brain iron deposition in PD patients with anxiety compared to PD patients without anxiety, especially in the fear circuit. Methods: Sixteen PD patients with anxiety, 23 PD patients without anxiety, and 26 healthy elderly controls were enrolled prospectively. All subjects underwent neuropsychological assessments and brain magnetic resonance imaging (MRI) examinations. Voxel-based morphometry (VBM) was used to study morphological brain differences between the groups. Quantitative susceptibility mapping (QSM), an MRI technique capable of quantifying susceptibility changes in brain tissue, was used to compare susceptibility changes in the whole brain among the three groups. The correlations between brain susceptibility changes and anxiety scores quantified using the Hamilton Anxiety Rating Scale (HAMA) were compared and analyzed. Results: PD patients with anxiety had a longer duration of PD and higher HAMA scores than PD patients without anxiety. No morphological brain differences were observed between the groups. In contrast, voxel-based and ROI-based QSM analyses showed that PD patients with anxiety had significantly increased QSM values in the medial prefrontal cortex, anterior cingulate cortex, hippocampus, precuneus, and angular cortex. Furthermore, the QSM values of some of these brain regions were positively correlated with the HAMA scores (medial prefrontal cortex: r = 0.255, p = 0.04; anterior cingulate cortex: r = 0.381, p < 0.01; hippocampus: r = 0.496, p < 0.01). Conclusion: Our findings support the idea that anxiety in PD is associated with iron burden in the brain fear circuit, providing a possible new approach to explaining the potential neural mechanism of anxiety in PD.

Spleen volume-based non-invasive tool for predicting hepatic decompensation in people with compensated cirrhosis (CHESS1701).

Background & Aims: Non-invasive stratification of the liver decompensation risk remains unmet in people with compensated cirrhosis. This study aimed to develop a non-invasive tool (NIT) to predict hepatic decompensation. Methods: This retrospective study recruited 689 people with compensated cirrhosis (median age, 54 years; 441 men) from 5 centres from January 2016 to June 2020. Baseline abdominal computed tomography (CT), clinical features, and liver stiffness were collected, and then the first decompensation was registered during the follow-up. The spleen-based model was designed for predicting decompensation based on a deep learning segmentation network to generate the spleen volume and least absolute shrinkage and selection operator (LASSO)-Cox. The spleen-based model was trained on the training cohort of 282 individuals (Institutions I-III) and was validated in 2 external validation cohorts (97 and 310 individuals from Institutions IV and V, respectively) and compared with the conventional serum-based models and the Baveno VII criteria. Results: The decompensation rate at 3 years was 23%, with a 37.6-month median (IQR 21.1-52.1 months) follow-up. The proposed model showed good performance in predicting decompensation (C-index ≥0.84) and outperformed the serum-based models (C-index comparison test p <0.05) in both the training and validation cohorts. The hazard ratio (HR) for decompensation in individuals with high risk was 7.3 (95% CI 4.2-12.8) in the training and 5.8 (95% CI 3.9-8.6) in the validation (log-rank test, p <0.05) cohorts. The low-risk group had a negligible 3-year decompensation risk (≤1%), and the model had a competitive performance compared with the Baveno VII criteria. Conclusions: This spleen-based model provides a non-invasive and user-friendly method to help predict decompensation in people with compensated cirrhosis in diverse healthcare settings where liver stiffness is not available. Lay summary: People with compensated cirrhosis with larger spleen volume would have a higher risk of decompensation. We developed a spleen-based model and validated it in external validation cohorts. The proposed model might help predict hepatic decompensation in people with compensated cirrhosis when invasive tools are unavailable.

A Dual-Energy CT Radiomics of the Regional Largest Short-Axis Lymph Node Can Improve the Prediction of Lymph Node Metastasis in Patients With Rectal Cancer.

Objective: To explore the value of dual-energy computed tomography (DECT) radiomics of the regional largest short-axis lymph nodes for evaluating lymph node metastasis in patients with rectal cancer. Materials and Methods: One hundred forty-one patients with rectal cancer (58 in LNM+ group, 83 in LNM- group) who underwent preoperative total abdominal DECT were divided into a training group and testing group (7:3 ratio). After post-processing DECT venous phase images, 120kVp-like images and iodine (water) images were obtained. The highest-risk lymph nodes were identified, and their long-axis and short-axis diameter and DECT quantitative parameters were measured manually by two experienced radiologists who were blind to the postoperative pathological results. Four DECT parameters were analyzed: arterial phase (AP) normalized iodine concentration, AP normalized effective atomic number, the venous phase (VP) normalized iodine concentration, and the venous phase normalized effective atomic number. The carcinoembryonic antigen (CEA) levels were recorded one week before surgery. Radiomics features of the largest lymph nodes were extracted, standardized, and reduced before modeling. Radomics signatures of 120kVp-like images (Rad-signature120kVp) and iodine map (Rad-signatureImap) were built based on Logistic Regression via Least Absolute Shrinkage and Selection Operator (LASSO). Results: Eight hundred thirty-three features were extracted from 120kVp-like and iodine images, respectively. In testing group, the radiomics features based on 120kVp-like images showed the best diagnostic performance (AUC=0.922) compared to other predictors [CT morphological indicators (short-axis diameter (AUC=0.779, IDI=0.262) and long-axis diameter alone (AUC=0.714, IDI=0.329)), CEA alone (AUC=0.540, IDI=0.414), and normalized DECT parameters alone (AUC=0.504-0.718, IDI=0.290-0.476)](P<0.05 in Delong test). Contrary, DECT iodine map-based radiomic signatures showed similar performance in predicting lymph node metastasis (AUC=0.866). The decision curve showed that the 120kVp-like-based radiomics signature has the highest net income. Conclusion: Predictive model based on DECT and the largest short-axis diameter lymph nodes has the highest diagnostic value in predicting lymph node metastasis in patients with rectal cancer.

Thoracic CT radiomics analysis for predicting synchronous brain metastasis in patients with lung cancer.

PURPOSE: We aimed to assess the feasibility of radiomics analysis based on non-contrast-enhanced thoracic CT images in predicting synchronous brain metastasis (SBM) in lung cancer patients at initial diagnosis. METHODS: This retrospective study enrolled 371 lung cancer patients (with SBM n=147, without SBM n=224) confirmed by histopathology. Patients were allocated to the training set (n=258) and testing set (n=113). The optimal radiomics features were selected by using the least absolute shrinkage and selection operator (LASSO) algorithm. The radiomics, clinicoradiologic, and combined models were developed to predict SBM using multivariable logistic regression. Then the discrimination ability of the models was assessed. Furthermore, the prediction performance of the abovementioned three models for oligometastatic (1-3 lesions) or multiple (>3 lesions) brain metastases in SBM, metachronous brain metastasis (MBM), and total (SBM and MBM) groups were investigated. RESULTS: Six radiomics features and two clinicoradiologic characteristics were chosen for predicting SBM. Both the radiomics model (area under the receiver operating characteristic curve [AUC] = 0.870 and 0.824 in the training and testing sets, respectively) and the combined model (AUC = 0.912 and 0.859, respectively) presented better predictive ability for SBM than the clinicoradiologic model (AUC = 0.712 and 0.692, respectively). The decision curve analysis (DCA) demonstrated the clinical usefulness of the radiomics-based models. The radiomics model can also be used to predict oligometastatic or multiple brain metastases in SBM, MBM, and total groups (P = .045, P = .022, and P = .030, respectively). CONCLUSION: The radiomics model and the combined model we presented can be used as valuable imaging markers for predicting patients at high risk of SBM at the initial diagnosis of lung cancer. Furthermore, the radiomics model can also be utilized as an indicator for identifying oligometastatic or multiple brain metastases.

Preoperative Microvascular Invasion Prediction to Assist in Surgical Plan for Single Hepatocellular Carcinoma: Better Together with Radiomics.

BACKGROUND: Prediction models with or without radiomic analysis for microvascular invasion (MVI) in hepatocellular carcinoma (HCC) have been reported, but the potential for model-predicted MVI in surgical planning is unclear. Therefore, we aimed to explore the effect of predicted MVI on early recurrence after anatomic resection (AR) and non-anatomic resection (NAR) to assist surgical strategies. METHODS: Patients with a single HCC of 2-5 cm receiving curative resection were enrolled from 2 centers. Their data were used to develop (n = 230) and test (n = 219) two prediction models for MVI using clinical factors and preoperative computed tomography images. The two prediction models, clinico-radiologic model and clinico-radiologic-radiomic (CRR) model (clinico-radiologic variables + radiomic signature), were compared using the Delong test. Early recurrence based on model-predicted high-risk MVI was evaluated between AR (n = 118) and NAR (n = 85) via propensity score matching using patient data from another 2 centers for external validation. RESULTS: The CRR model showed higher area under the curve values (0.835-0.864 across development, test, and external validation) but no statistically significant improvement over the clinico-radiologic model (0.796-0.828). After propensity score matching, difference in 2-year recurrence between AR and NAR was found in the CRR model predicted high-risk MVI group (P = 0.005) but not in the clinico-radiologic model predicted high-risk MVI group (P = 0.31). CONCLUSIONS: The prediction model incorporating radiomics provided an accurate preoperative estimation of MVI, showing the potential for choosing the more appropriate surgical procedure between AR and NAR.

An Investigation of the Impacts of Three Anesthetic Regimens on Task-Functional Magnetic Resonance Imaging and Functional Connectivity Resting-State Functional Magnetic Resonance Imaging in Sprague Dawley and Wistar Rats.

Aim: The aim of this study was to investigate basic task-functional magnetic resonance imaging (fMRI) or resting-state fMRI (rs-fMRI) results on Sprague Dawley (SD) rats and Wistar rats under three anesthetic regimens. Introduction: SD rats and Wistar rats are the two-most commonly used rat strains in medical research and neuroimaging studies. It still lacks a direct comparison of basic task-fMRI and rs-fMRI results between the Wistar rats and SD rats under different anesthetic regimens. Methods: Two rat strains and different time points were adopted to investigate task-fMRI activation and rs-fMRI functional connectivity (FC) results under three kinds of anesthetic regimens (2-2.5% isoflurane only, dexmedetomidine bolus combined with a continuous infusion, and dexmedetomidine bolus combined with 0.3-0.5% isoflurane). The electrical forepaw stimulation method and seed-based FC results were used to compare the task-fMRI brain activation and rs-fMRI FC patterns between the two rat strains. Results: The results showed that Wistar rats had more robust brain activation in task fMRI experiments while exhibiting a less specific interhemispheric FC than that of SD rats under the two dexmedetomidine anesthetic regimens. Moreover, even low-level isoflurane could significantly affect task-fMRI and rs-fMRI results in both rat strains. Conclusions: SD and Wistar rats showed different brain activations and interhemispheric FC patterns under the two dexmedetomidine anesthetic regimens. These results may serve as reference information for small-animal fMRI studies. Impact statement Our study demonstrates different stimulation-induced blood oxygen level-dependent responses and functional connectivity patterns between Sprague Dawley rats and Wistar rats under three anesthetics. This study provides some reference results for different anesthetics' effects on different rat strains in different functional magnetic resonance imaging modalities.

Comparison of MRI and CT for the Prediction of Microvascular Invasion in Solitary Hepatocellular Carcinoma Based on a Non-Radiomics and Radiomics Method: Which Imaging Modality Is Better?

BACKGROUND: Computed tomography (CT) and magnetic resonance imaging (MRI) are both capable of predicting microvascular invasion (MVI) in hepatocellular carcinoma (HCC). However, which modality is better is unknown. PURPOSE: To intraindividually compare CT and MRI for predicting MVI in solitary HCC and investigate the added value of radiomics analyses. STUDY TYPE: Retrospective. SUBJECTS: Included were 402 consecutive patients with HCC (training set:validation set = 300:102). FIELD STRENGTH/SEQUENCE: T2-weighted, diffusion-weighted, and contrast-enhanced T1-weighted imaging MRI at 3.0T and contrast-enhanced CT. ASSESSMENT: CT- and MR-based radiomics signatures (RS) were constructed using the least absolute shrinkage and selection operator regression. CT- and MR-based radiologic (R) and radiologic-radiomics (RR) models were developed by univariate and multivariate logistic regression. The performance of the RS/models was compared between two modalities. To investigate the added value of RS, the performance of the R models was compared with the RR models in HCC of all sizes and 2-5 cm in size. STATISTICAL TESTS: Model performance was quantified by the area under the receiver operating characteristic curve (AUC) and compared using the Delong test. RESULTS: Histopathologic MVI was identified in 161 patients (training set:validation set = 130:31). MRI-based RS/models tended to have a marginally higher AUC than CT-based RS/models (AUCs of CT vs. MRI, P: RS, 0.801 vs. 0.804, 0.96; R model, 0.809 vs. 0.832, 0.09; RR model, 0.835 vs. 0.872, 0.54). The improvement of RR models over R models in all sizes was not significant (P = 0.21 at CT and 0.09 at MRI), whereas the improvement in 2-5 cm was significant at MRI (P < 0.05) but not at CT (P = 0.16). DATA CONCLUSION: CT and MRI had a comparable predictive performance for MVI in solitary HCC. The RS of MRI only had significant added value for predicting MVI in HCC of 2-5 cm. LEVEL OF EVIDENCE: 3 TECHNICAL EFFICACY: Stage 2.

Development and validation of a radiomics signature as a non-invasive complementary predictor of gastroesophageal varices and high-risk varices in compensated advanced chronic liver disease: A multicenter study.

BACKGROUND AND AIM: Gastroesophageal varices (GEV) present in compensated advanced chronic liver disease (cACLD) and can develop into high-risk varices (HRV). The gold standard for diagnosing GEV is esophagogastroduodenoscopy (EGD). However, EGD is invasive and less tolerant. This study aimed to develop and validate radiomics signatures based on noncontrast-enhanced computed tomography (CT) images for non-invasive diagnosis of GEV and HRV in patients with cACLD. METHODS: The multicenter trial enrolled 161 patients with cACLD from six university hospitals in China between January 2015 and September 2019, who underwent both EGD and noncontrast-enhanced CT examination within 14 days prior to the endoscopy. Two radiomics signatures, termed rGEV and rHRV, respectively, were built based on CT images in a training cohort of 129 patients and validated in a prospective validation cohort of 32 patients (ClinicalTrials. gov identifier: NCT03749954). RESULTS: In the training cohort, both rGEV and rHRV exhibited high discriminative abilities on determining the existence of GEV and HRV with the area under receiver operating characteristic curve (AUC) of 0.941 (95% confidence interval [CI] 0.904-0.978) and 0.836 (95% CI 0.766-0.905), respectively. In validation cohort, rGEV and rHRV showed high discriminative abilities with AUCs of 0.871 (95% CI 0.739-1.000) and 0.831 (95% CI 0.685-0.978), respectively. CONCLUSIONS: This study demonstrated that rGEV and rHRV could serve as the satisfying auxiliary parameters for detection of GEV and HRV with good diagnostic performance.

Machine learning-based CT radiomics method for predicting hospital stay in patients with pneumonia associated with SARS-CoV-2 infection: a multicenter study.

BACKGROUND: The coronavirus disease 2019 (COVID-19) has become a global challenge since the December 2019. The hospital stay is one of the prognostic indicators, and its predicting model based on CT radiomics features is important for assessing the patients' clinical outcome. The study aimed to develop and test machine learning-based CT radiomics models for predicting hospital stay in patients with COVID-19 pneumonia. METHODS: This retrospective, multicenter study enrolled patients with laboratory-confirmed SARS-CoV-2 infection and their initial CT images from 5 designated hospitals in Ankang, Lishui, Lanzhou, Linxia, and Zhenjiang between January 23, 2020 and February 8, 2020. Patients were classified into short-term (≤10 days) and long-term hospital stay (>10 days). CT radiomics models based on logistic regression (LR) and random forest (RF) were developed on features from pneumonia lesions in first four centers. The predictive performance was evaluated in fifth center (test dataset) on lung lobe- and patients-level. RESULTS: A total of 52 patients were enrolled from designated hospitals. As of February 20, 21 patients remained in hospital or with non-findings in CT were excluded. Therefore, 31 patients with 72 lesion segments were included in analysis. The CT radiomics models based on 6 second-order features were effective in discriminating short- and long-term hospital stay in patients with COVID-19 pneumonia, with areas under the curves of 0.97 (95% CI, 0.83-1.0) and 0.92 (95% CI, 0.67-1.0) by LR and RF, respectively, in test. The LR and RF model showed a sensitivity and specificity of 1.0 and 0.89, 0.75 and 1.0 in test respectively. As of February 28, a prospective cohort of six discharged patients were all correctly recognized as long-term stay using RF and LR models. CONCLUSIONS: The machine learning-based CT radiomics features and models showed feasibility and accuracy for predicting hospital stay in patients with COVID-19 pneumonia.

Radiomics Analysis on Multiphase Contrast-Enhanced CT: A Survival Prediction Tool in Patients With Hepatocellular Carcinoma Undergoing Transarterial Chemoembolization.

Patients with HCC receiving TACE have various clinical outcomes. Several prognostic models have been proposed to predict clinical outcomes for patients with hepatocellular carcinomas (HCC) undergoing transarterial chemoembolization (TACE), but establishing an accurate prognostic model remains necessary. We aimed to develop a radiomics signature from pretreatment CT to establish a combined radiomics-clinic (CRC) model to predict survival for these patients. We compared this CRC model to the existing prognostic models in predicting patient survival. This retrospective study included multicenter data from 162 treatment-naïve patients with unresectable HCC undergoing TACE as an initial treatment from January 2007 and March 2017. We randomly allocated patients to a training cohort (n = 108) and a testing cohort (n = 54). Radiomics features were extracted from intra- and peritumoral regions on both the arterial phase and portal venous phase CT images. A radiomics signature (Rad-signature) for survival was constructed using the least absolute shrinkage and selection operator method in the training cohort. We used univariate and multivariate Cox regressions to identify associations between the Rad- signature and clinical factors of survival. From these, a CRC model was developed, validated, and further compared with previously published prognostic models including four-and-seven criteria, six-and-twelve score, hepatoma arterial-embolization prognostic scores, and albumin-bilirubin grade. The CRC model incorporated two variables: The Rad-signature (composed of features extracted from intra- and peritumoral regions on the arterial phase and portal venous phase) and tumor number. The CRC model performed better than the other seven well-recognized prognostic models, with concordance indices of 0.73 [95% confidence interval (CI) 0.68-0.79] and 0.70 [95% CI 0.62-0.82] in the training and testing cohorts, respectively. Among the seven models tested, the six-and-12 score and four-and-seven criteria performed better than the other models, with C-indices of 0.64 [95% CI 0.58-0.70] and 0.65 [95% CI 0.55-0.75] in the testing cohort, respectively. The CT radiomics signature represents an independent biomarker of survival in patients with HCC undergoing TACE, and the CRC model displayed improved predictive performance.

Penumbra-based radiomics signature as prognostic biomarkers for thrombolysis of acute ischemic stroke patients: a multicenter cohort study.

BACKGROUND AND PURPOSE: This study aimed at developing a radiomics signature (R score) as prognostic biomarkers based on penumbra quantification and to validate the radiomics nomogram to predict the clinical outcomes for thrombolysis for acute ischemic stroke (AIS) patients. METHODS: In total, 168 patients collected from seven centers were retrospectively included. A score of mismatch was defined as MIS. Based on a short-term clinical label, 456 radiomics features were evaluated with feature selection methods. R score was constructed with the selected features. To compare the predictive capabilities of the clinical factors, MIS, and R score, three nomograms were developed and evaluated, according to the short-term clinical assessment on day 7. Finally, the radiomics nomogram was validated by predicting the 3-month clinical outcomes of AIS patients, in an external cohort. RESULTS: R scores were found to be significantly higher in patients with favorable clinical outcomes in both training and validation datasets. The predictive value of the radiomics nomogram estimating favorable clinical outcomes was modest, with a concordance index (C-index) of 0.695 [95% confidence interval (CI) 0.667-0.723) in an external validation dataset. In addition, the area under curve (AUC) of the radiomics nomogram predicting favorable clinical outcome reached 0.886 (95% CI 0.809-0.963) on day 7 and 0.777 (95% CI 0.666-0.888) at 3 months. CONCLUSIONS: The radiomics signature is an independent biomarker for estimating the clinical outcomes in AIS patients. By improving the individualized prediction of the clinical outcome for AIS patients 3 months after onset, the radiomics nomogram adds more value to the current clinical decision-making process.

Altered amplitude of low-frequency fluctuation in basal ganglia correlates to pulmonary ventilation function in COPD patients: A resting-state fMRI study.

INTRODUCTION: Patients under chronic obstructive pulmonary disease (COPD) has been reported to be associated with a higher prevalence of cognitive impairment (CI). However, it is still largely unknown whether the aberrant resting-state spontaneous neuronal activity pattern reflected by the amplitude of low-frequency fluctuation (ALFF) analysis will be associated with the CI in COPD patients. MATERIALS: A total of 28 COPD patients and 26 healthy controls were enrolled in this study. Of all the subjects, structural and functional MRI data, spirometry tests performance and neuropsychological assessments of different cognitive domains were collected. Voxel-based two-sample t tests were used to detect brain regions showing differences in the ALFF value between COPD patients and healthy controls. An additional fMRI runs with supplementary oxygen delivery were employed to explore the impact of elevated partial pressure of oxygen (PaO2 ) or moderate hyperoxia on ALFF in COPD patients and healthy controls respectively. RESULTS: More extensive white matter lesion was detected in COPD patients. COPD patients exhibit decreased ALFF value in bilateral basal ganglia areas and right thalamus, and aberrant ALFF value is correlated with PaO2 and pulmonary ventilation function (FEV1%pred). COPD patients performed worse in the Digit Span Test (reverse), Digit Symbol Substitution Test, Trail-making test (A and B) than controls. After supplementary oxygen inhalation, the ALFF value of basal ganglia and right thalamus significantly increased in the controls, but not in the COPD patients. CONCLUSIONS: COPD patients mainly exhibit impaired executive function but not long-term memory in cognitive function assessment. Aberrant ALFF alteration in the deep brain may be directly related to lower PaO2 in COPD patients.

Diabetes risk assessment with imaging: a radiomics study of abdominal CT.

OBJECTIVES: To identify CT markers for screening of early type 2 diabetes and assessment of the risk of incident diabetes using a radiomics method. METHODS: The medical records of 26,947 inpatients were reviewed. A total of 690 patients were selected and allocated to a primary cohort, a validation cohort, and a prediction cohort and used to build prediction models for diabetes. Three radiomics signatures were constructed using CT image features extracted from three regions of interest, i.e., in the pancreas, liver, and psoas major muscle. By incorporating radiomics signatures and other markers, we built a radiomics nomogram that could be used to screen for early diabetes and predict future diabetes. RESULTS: Of the three abdominal organs for which radiomics signature were constructed, that of the pancreas showed the best discriminatory power for early diabetes screening and prediction (C-statistics of 0.833, 0.846, and 0.899 for the primary cohort, validation cohort, and prediction cohort, respectively). The sensitivity and specificity of the nomogram for prediction of 3-year incident diabetes were 0.827 and 0.807, respectively. CONCLUSIONS: This study presents alternative radiomics markers that have potential for use in screening for undiagnosed type 2 diabetes and prediction of 3-year incident diabetes. KEY POINTS: • CT images may provide useful information to evaluate the risk of developing diabetes. • Radiomics score for diabetes prediction is based on subtle changes of abdominal organs detected by CT. • The radiomics signature of pancreas, a combination of five features of CT images, is efficient for early diabetes screening and prediction of future diabetes (AUC > 0.8).

Structural change of thalamus in cirrhotic patients with or without minimal hepatic encephalopathy and the relationship between thalamus volume and clinical indexes related to cirrhosis.

Aberrant brain structural change in cirrhotic patients with or without hepatic encephalopathy is one of the most typical cases in voxel-based morphometry (VBM) studies. However, there exist inconsistent results regarding to the volume change of the thalamus. Furthermore, the relationship between thalamus structural change and cirrhotic symptoms has not yet been fully elucidated. To address these two issues, we repeated two VBM analyses in SPM and FreeSurfer and compared the two measurements with manually measured thalamic volumes. We also correlated the VBM results with clinical indexes related to cirrhosis to further investigate the relationship between thalamic structural change and liver cirrhosis. The inconsistent result of thalamic structural change was successfully reproduced in regard to the volume measurements of SPM and FreeSurfer. The manually measured results demonstrate an increase in the volume of the thalamus in cirrhotic patients compared to healthy controls, which differs from the results of FreeSurfer. The structural change of thalamus closely correlated with the blood biochemical indexes, including albumin levels, blood coagulation time, and AST/ALT ratio. All of these biochemical indexes are closely related to the severity of liver cirrhosis. Beyond all the results, this study also provides a good demonstration of the difference between multiple VBM measurements for clinicians.