Purpose: The purpose of this study was to identify possible association between noncontrast computed tomography (NCCT)-based radiomics features of perihematomal edema (PHE) and poor functional outcome at 90 days after intracerebral hemorrhage (ICH) and to develop a NCCT-based radiomics-clinical nomogram to predict 90-day functional outcomes in patients with ICH. Materials and methods: In this multicenter retrospective study, 107 radiomics features were extracted from 1098 NCCT examinations obtained in 1098 patients with ICH. There were 652 men and 446 women with a mean age of 60 +/- 12 (SD) years (range: 23-95 years). After harmonized and univariable and multivariable screening, seven of these radiomics features were closely associated with the 90-day functional outcome of patients with ICH. The radiomics score (Rad-score) was calculated based on the seven radiomics features. A clinical-radiomics nomogram was developed and validated in three cohorts. The model performance was evaluated using area under the curve analysis and decision and calibration curves. Results: Of the 1098 patients with ICH, 395 had a good outcome at 90 days. Hematoma hypodensity sign and intraventricular and subarachnoid hemorrhages were identified as risk factors for poor outcomes (P < 0.001). Age, Glasgow coma scale score, and Rad-score were independently associated with outcome. The clinical-radiomics nomogram showed good predictive performance with AUCs of 0.882 (95% CI: 0.859-0.905), 0.834 (95% CI: 0.776-0.891) and 0.905 (95% CI: 0.839-0.970) in the three cohorts and clinical applicability. Conclusion: NCCT-based radiomics features from PHE are highly correlated with outcome. When combined with Rad-score, radiomics features from PHE can improve the predictive performance for 90-day poor out-come in patients with ICH. (c) 2023 The Authors. Published by Elsevier Masson SAS on behalf of Societe francaise de radiologie. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

We aimed to develop and validate an objective and easy-to-use model for identifying patients with spontaneous intracerebral hemorrhage (ICH) who have a poor 90-day prognosis. This three-center retrospective study included a large cohort of 1,122 patients with ICH who presented within 6 h of symptom onset [training cohort, n = 835; internal validation cohort, n = 201; external validation cohort (center 2 and 3), n = 86]. We collected the patients' baseline clinical, radiological, and laboratory data as well as the 90-day functional outcomes. Independent risk factors for prognosis were identified through univariate analysis and multivariate logistic regression analysis. A nomogram was developed to visualize the model results while a calibration curve was used to verify whether the predictive performance was satisfactorily consistent with the ideal curve. Finally, we used decision curves to assess the clinical utility of the model. At 90 days, 714 (63.6%) patients had a poor prognosis. Factors associated with prognosis included age, midline shift, intraventricular hemorrhage (IVH), subarachnoid hemorrhage (SAH), hypodensities, ICH volume, perihematomal edema (PHE) volume, temperature, systolic blood pressure, Glasgow Coma Scale (GCS) score, white blood cell (WBC), neutrophil, and neutrophil-lymphocyte ratio (NLR) (p < 0.05). Moreover, age, ICH volume, and GCS were identified as independent risk factors for prognosis. For identifying patients with poor prognosis, the model showed an area under the receiver operating characteristic curve of 0.874, 0.822, and 0.868 in the training cohort, internal validation, and external validation cohorts, respectively. The calibration curve revealed that the nomogram showed satisfactory calibration in the training and validation cohorts. Decision curve analysis showed the clinical utility of the nomogram. Taken together, the nomogram developed in this study could facilitate the individualized outcome prediction in patients with ICH.

Spontaneous intracerebral hemorrhage (ICH) has high morbidity and mortality. Computed tomography (CT) plays an important role in the diagnosis, treatment, and research of cerebrovascular diseases. Non-contrast CT is widely used in the clinical diagnosis of ICH because of its high imaging speed and high sensitivity and specificity in the detection of stroke. Many markers-based CT imaging, quantitative parameters, and artificial intelligence (AI) methods based on CT are increasingly used for the prediction of hematoma expansion (HE), prognosis of ICH, and the evaluation of perihematomal edema (PHE). Therefore, we performed a comprehensive review of studies, focusing on current research evidence related to CT use for the prediction of HE and prognostic. This review discusses recent insights into, outlines current limitations, and puts forward suggestions for the challenges and directions of future research. Although at present the prognosis for ICH is not optimistic, the treatment methods remain controversial. However, identifying imaging markers that can evaluate and predict existing possible existing therapeutic targets could help to provide individualized advice for patients and achieve patient risk stratification, which is a key step in improving treatment outcomes.

Background: Accurate risk stratification of patients with intracerebral hemorrhage (ICH) could help refine adjuvant therapy selection and better understand the clinical course. We aimed to evaluate the value of radio-mics features from hematomal and perihematomal edema areas for prognosis prediction and to develop a model combining clinical and radiomic features for accurate outcome prediction of patients with ICH. Methods: This multicenter study enrolled patients with ICH from January 2016 to November 2021. Their out-comes at 3 months were recorded based on the modified Rankin Scale (good, 0-3; poor, 4-6). Independent clinical and radiomic risk factors for poor outcome were identified through multivariate logistic regression analysis, and predictive models were developed. Model performance and clinical utility were evaluated in both internal and external cohorts. Results: Among the 1098 ICH patients evaluated (mean age, 60 & PLUSMN; 13 years), 703 (64 %) had poor outcomes. Age, hemorrhage volume and location, and Glasgow Coma Scale (GCS) were independently associated with outcomes. The area under the receiver operating characteristic curve (AUC) of the clinical model was 0.881 in the external validation cohort. Addition of the Rad-score (combined hematoma and perihematomal edema area) improved predictive accuracy and model performance (AUC, 0.893), net reclassification improvement, 0.140 (P < 0.001), and integrated discrimination improvement, 0.050 (P < 0.001). Conclusions: The radiomics features of hematomal and perihematomal edema area have additional value in prognostic prediction; moreover, addition of radiomic features significantly improves model accuracy.

Pancreatic cancer has been becoming the second cause of cancer death in the western world, and its disease burden has increased. Neoadjuvant therapy is one of the current research hotspots in the field of pancreatic cancer, aiming to improve the surgical rate and prognosis of pancreatic cancer. Based on the latest evidence, this review discussed neoadjuvant therapy in pancreatic cancer from the following three aspects: patient selection, protocols selection of neoadjuvant therapy, and treatment response evaluation and resectability prediction. A big controversy existed on the indications of neoadjuvant treatment, but it was agreed that any patient who is likely to achieve R0 resection due to neoadjuvant therapy should be the targeted population. A variety of chemotherapy regimens were tried for neoadjuvant therapy in pancreatic cancer, and FOLFIRINOX and Nab-Paclitaxel plus Gemcitabine are two preferred regimens at present. It was challenging to evaluate treatment response and predict resectability after neoadjuvant therapy, although imaging by CT is widely used. Based on new findings of the remarkable performance of several chemotherapy regimens with or without radiotherapy, the neoadjuvant indications of pancreatic cancer have extended in recent years. However, it is still a challenge to assess the neoadjuvant treatment response and determine the timing of surgery.

Introduction Venous thromboembolism (VTE) is a serious life-threatening complication in patients with gastric cancer. Abnormal coagulation function and tumour-related treatment may contribute to the occurrence of VTE. Many guidelines considered that surgical treatment would put patients with cancer at high risk of VTE, so positive prevention is needed. However, there are no studies that have systematically reviewed the postoperative risk and distribution of VTE in patients with gastric cancer. We thus conduct this systematic review to determine the risk of VTE in patients with gastric cancer undergoing surgery and provide some evidence for clinical decision-making. Methods and analysis Studies reporting the incidence of VTE after gastric cancer surgery will be included. Primary studies of randomised controlled trials, cohort studies, population-based surveys and cross-sectional studies are eligible for this review and only studies published in Chinese and English will be included. We will search the Medline, Embase, Web of Science, CBM, CNKI and Wanfang data from their inception to November 2019. Two reviewers will independently select studies and extract data. The quality of each included study will be assessed with tools corresponding to their study design. Meta-analysis will be used to pool the incidence data from included studies. Heterogeneity of the estimates across studies will be assessed, if necessary, a subgroup analysis will be performed to explore the source of heterogeneity. The Grades of Recommendation, Assessment, Development and Evaluation method is applied to assess the level of evidence obtained from this systematic review. Ethics and dissemination This proposed systematic review and meta-analysis is based on published data, and thus ethical approval is not required. The results of this review will be sought for publication. PROSPERO registration number CRD42019144562

In this work, we aim at classification and quantification of emphysema in computed tomography (CT) images of lungs. Most previous works are limited to extracting low-level features or mid-level features without enough high-level information. Moreover, these approaches do not take the characteristics (scales) of different emphysema into account, which are crucial for feature extraction. In contrast to previous works, we propose a novel deep learning method based on multi-scale deep convolutional neural networks. There are three contributions for this paper. First, we propose to use a base residual network with 20 layers to extract more high-level information. Second, we incorporate multi-scale information into our deep neural networks so as to take full consideration of the characteristics of different emphysema. A 92.68% classification accuracy is achieved on our original dataset. Finally, based on the classification results, we also perform the quantitative analysis of emphysema in 50 subjects by correlating the quantitative results (the area percentage of each class) with pulmonary functions. We show that centrilobular emphysema (CLE) and panlobular emphysema (PLE) have strong correlation with the pulmonary functions and the sum of CLE and PLE can be used as a new and accurate measure of emphysema severity instead of the conventional measure (sum of all subtypes of emphysema). The correlations between the new measure and various pulmonary functions are up to |r| $$= 0.922$$ (r is correlation coefficient).

PURPOSE:The bag of visual words (BoVW) model is a powerful tool for feature representation that can integrate various handcrafted features like intensity, texture, and spatial information. In this paper, we propose a novel BoVW-based method that incorporates texture and spatial information for the content-based image retrieval to assist radiologists in clinical diagnosis.METHODS:This paper presents a texture-specific BoVW method to represent focal liver lesions (FLLs). Pixels in the region of interest (ROI) are classified into nine texture categories using the rotation-invariant uniform local binary pattern method. The BoVW-based features are calculated for each texture category. In addition, a spatial cone matching (SCM)-based representation strategy is proposed to describe the spatial information of the visual words in the ROI. In a pilot study, eight radiologists with different clinical experience performed diagnoses for 20 cases with and without the top six retrieved results. A total of 132 multiphase computed tomography volumes including five pathological types were collected.RESULTS:The texture-specific BoVW was compared to other BoVW-based methods using the constructed dataset of FLLs. The results show that our proposed model outperforms the other three BoVW methods in discriminating different lesions. The SCM method, which adds spatial information to the orderless BoVW model, impacted the retrieval performance. In the pilot trial, the average diagnosis accuracy of the radiologists was improved from 66 to 80% using the retrieval system.CONCLUSION:The preliminary results indicate that the texture-specific features and the SCM-based BoVW features can effectively characterize various liver lesions. The retrieval system has the potential to improve the diagnostic accuracy and the confidence of the radiologists.

Objective: The aim of this study was to investigate the image quality of cerebral dual-energy computed tomography (CT) angiography using a nonlinear image blending technique as compared with the conventional linear blending method in patients with spontaneous subarachnoid hemorrhage (SAH).Methods: A retrospective review of 30 consecutive spontaneous SAH patients who underwent a dual-source, dual-energy (80 kV and Sn140 kV mode) cerebral CT angiography was performed with permission from hospital ethical committee. Optimized images using nonlinear blending method were generated and compared with the 0.6 linear blending images by evaluating cerebral artery enhancement, attenuation of SAH, image noise, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR), respectively. Two neuroradiologists independently assessed subjective vessel visualization per segment using a 5-point scale.Results: The nonlinear blending images showed higher cerebral artery enhancement (307.24 +/- 58.04 Hounsfield unit [HU]), lower attenuation of SAH (67.07 +/- 6.79 HU), and image noise (7.18 +/- 1.20 HU), thus achieving better SNR (43.92 +/- 11.14) and CNR (34.34 +/- 10.25), compared with those of linear blending images (235.47 +/- 46.45 HU for cerebral artery enhancement, 70.00 +/- 6.41 HU for attenuation of SAH, 8.39 +/- 1.25 HU for image noise, 28.86 +/- 8.43 for SNR, and 20.37 +/- 7.74 for CNR) (all P < 0.01). The segmental scorings of the nonlinear blending image (31.6% segments with a score of 5, 57.4% segments with a score of 4, 11% segments with a score of 3) ranged significantly higher than those of linear blending images (11.5% segments with a score of 5, 77.5% segments with a score of 4, 11% segments with a score of 3) (P < 0.01). The interobserver agreement was good (K = 0.762), and intraobserver agreement was excellent for both observers (K = 0.844 and 0.858, respectively).Conclusions: The nonlinear image blending technique improved vessel visualization of cerebral dual-energy CT angiography by optimizing contrast enhancement in spontaneous SAH patients.

AIM:To investigate the accuracy of high-pitch prospectively electrocardiogram (ECG)-triggering low-dose, dual-source computed tomography (CT) coronary angiography for assessing coronary artery stenosis compared with conventional coronary angiography. MATERIALS AND METHODS:One hundred and three patients undergoing high-pitch CT coronary angiography (CTCA) and conventional coronary angiography (CCA) within 30 days were enrolled. The sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of high-pitch CTCA for detecting >50 and >70% stenosis were evaluated using CCA as the reference standard on a per-segment, per-vessel, and per-patient basis. Two experienced radiologists independently rated high-pitch CTCA images for quality using a four-point scale (1 = excellent, 4 = non-diagnostic) on a per-segment basis. The effective dose was calculated by multiplying the conversion coefficient of 0.028 by the dose-length product. RESULTS:The mean heart rate of patients was 57 ± 6 beats/min. For detecting >50% stenosis, the sensitivity, specificity, PPV, and NPV of high-pitch CTCA were 89, 97, 87, and 97% on a per-segment basis; 91, 92, 92, and 91% on a per-vessel basis; and 99, 85, 96, and 94% on a per-patient basis. For detecting >70% stenosis, the sensitivity, specificity, PPV, and NPV of high-pitch CTCA were 96, 98, 90, and 99% on a per-segment basis. Coronary segments were rated as diagnostic in 98.6% (1355/1375) of cases (score 1, 72.5%; score 2, 23.1%; score 3, 3%; score 4, 1.4%). The effective dose of high-pitch CTCA was 1.51 ± 0.31 mSv. CONCLUSION:High-pitch prospectively ECG-triggering dual-source CTCA provides good image quality and high diagnostic accuracy with a 1.51 mSv radiation dose.

To investigate the image quality and dose performance of 80 kV high-pitch spiral (HPS) coronary CT angiography (CCTA). 106 patients consecutively enrolled into prospectively ECG-triggering HPS CCTA (pitch = 3.4) exam using kV/ref. mAs = 80/400, 100/370, and 120/370 when patient BMI was ≤22.5 (n = 40), between 22.5 and 27.5 (n = 53) and >27.5 kg/m² (n = 13). Image quality was assessed per-segment by two observers independently using a 4-point scale (1—excellent, 4—non-diagnosable). Image noise and signal-to-noise ratio (SNR), contrast-to-noise ratio were measured. Diagnostic image quality was obtained in 503 of 507, 687 of 693, 164 of 167 coronary segments in 80, 100, 120 kV groups without significant difference (P = 0.482). The proportions of segments with score 1–4 were not significantly different among three kV groups (all P > 0.05). Image noise were significantly higher in 80 kV group than 100 and 120 groups (P < 0.001), while SNR was not (P = 0.097). The effective dose of 80 kV group (0.36 ± 0.03 mSv) was significantly lower than that of 100 kV group (0.86 ± 0.08 mSv) and 120 kV group (1.77 ± 0.18 mSv). The mean ± SD of HR in all patients was 54.8 ± 5.1 bpm. 80 kV HPS CCTA is feasible for patient with BMI ≤ 22.5 kg/m² which can save 58% dose than 100 kV group, while maintain diagnosable image quality.

Objective To assess the value of dual-energy computed tomography myelography (CTM) on detecting leaks of cerebrospinal fluid (CSF) in patients with spontaneous intracranial hypotension (SIH). Methods Six patients with SIH underwent spinal CTM on a 2nd generation dual-source CT with tube voltage set at 100 and 140 kVp(with tin filter). The virtual non-contrast (VNC) and iodine map images were calculated from dual-energy images. The average weighted (AW) CTM images were mixed from two kVp images with mix factor of 0. 5. Two radiologists evaluated CSF leak using two sets of images respectively: VNC + iodine map images and AW-CTM images. The results from two reading methods were compared. The level of CSF leaks along the nerve roots, C1-2 retrospinal CSF collections, epidural CSF collections and spinal epidural venous plexus were marked. The consensus about leak sites and CSF collections was made by two radiologists in the third session Kappa statistics were used to measure the agreement between the two methods. Results Forty-one leaks were detected using VNC + iodine map images. Forty-three leaks were detected on AW images. The agreement between two methods was excellent (Kappa =0. 997 ,P ＜0. 01). There were no differences in the detection of C1-2 retrospinal CSF collections (n = 2), epidural CSF collections(n = 3) or spinal epidural venous plexus (n = 1). VNC and iodine map images demonstrated superior visual effects than AW images. Conclusion Dual-energy CTM can be used to diagnose spontaneous spinal cerebrospinal fluid leaks in SIH patient.