Automated detection and classification of coronary atherosclerotic plaques on coronary CT angiography using deep learning algorithm.

Background: Coronary artery disease (CAD) is the leading cause of mortality worldwide. Recent advances in deep learning technology promise better diagnosis of CAD and improve assessment of CAD plaque buildup. The purpose of this study is to assess the performance of a deep learning algorithm in detecting and classifying coronary atherosclerotic plaques in coronary computed tomographic angiography (CCTA) images. Methods: Between January 2019 and September 2020, CCTA images of 669 consecutive patients with suspected CAD from Nanjing Drum Tower Hospital Clinical College of Nanjing University of Chinese Medicine were included in this study. There were 106 patients included in the retrospective plaque detection analysis, which was evaluated by a deep learning algorithm and four independent physicians with varying clinical experience. Additionally, 563 patients were included in the analysis for plaque classification using the deep learning algorithm, and their results were compared with those of expert radiologists. Plaques were categorized as absent, calcified, non-calcified, or mixed. Results: The deep learning algorithm exhibited higher sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy {92% [95% confidence interval (CI): 89.5-94.1%], 87% (95% CI: 84.2-88.5%), 79% (95% CI: 76.1-82.4%), 95% (95% CI: 93.4-96.3%), and 89% (95% CI: 86.9-90.0%)} compared to physicians with ≤5 years of clinical experience in CAD diagnosis for the detection of coronary plaques. The algorithm's overall sensitivity, specificity, PPV, NPV, accuracy, and Cohen's kappa for plaque classification were 94% (95% CI: 92.3-94.7%), 90% (95% CI: 88.8-90.3%), 70% (95% CI: 68.3-72.1%), 98% (95% CI: 97.8-98.5%), 90% (95% CI: 89.8-91.1%) and 0.74 (95% CI: 0.70-0.78), indicating strong performance. Conclusions: The deep learning algorithm has demonstrated reliable and accurate detection and classification of coronary atherosclerotic plaques in CCTA images. It holds the potential to enhance the diagnostic capabilities of junior radiologists and junior intervention cardiologists in the CAD diagnosis, as well as to streamline the triage of patients with acute coronary symptoms.

A radiomics nomogram for predicting postoperative recurrence in esophageal squamous cell carcinoma.

Purpose: To establish and validate a radiomics nomogram for predicting recurrence of esophageal squamous cell carcinoma (ESCC) after esophagectomy with curative intent. Materials and methods: The medical records of 155 patients who underwent surgical treatment for pathologically confirmed ESCC were collected. Patients were randomly divided into a training group (n=109) and a validation group (n=46) in a 7:3 ratio. ​Tumor regions are accurately segmented in computed tomography images of enrolled patients. Radiomic features were then extracted from the segmented tumors. We selected the features by Max-relevance and min-redundancy (mRMR) and least absolute shrinkage and selection operator (LASSO) methods. A radiomics signature was then built by logistic regression analysis. To improve predictive performance, a radiomics nomogram that incorporated the radiomics signature and independent clinical predictors was built. Model performance was evaluated by receiver operating characteristic (ROC) curve, calibration curve, and decision curve analyses (DCA). Results: We selected the five most relevant radiomics features to construct the radiomics signature. The radiomics model had general discrimination ability with an area under the ROC curve (AUC) of 0.79 in the training set that was verified by an AUC of 0.76 in the validation set. The radiomics nomogram consisted of the radiomics signature, and N stage showed excellent predictive performance in the training and validation sets with AUCs of 0.85 and 0.83, respectively. Furthermore, calibration curves and the DCA analysis demonstrated good fit and clinical utility of the radiomics nomogram. Conclusion: We successfully established and validated a prediction model that combined radiomics features and N stage, which can be used to predict four-year recurrence risk in patients with ESCC who undergo surgery.

Soluble CD206 levels correlate with disease deterioration and predict prognosis of anti-MDA5 antibody-positive dermatomyositis related interstitial lung disease.

INTRODUCTION: The prognosis of anti-MDA5 antibody-positive dermatomyositis/clinically amyopathic dermatomyositis-associated interstitial lung disease (MDA5-DM/CADM-ILD) is poor. This study was to evaluate the effect of serum soluble CD206 (sCD206), a biomarker of macrophage activation, on predicting the interstitial lung disease (ILD) deterioration and prognosis for MDA5-DM/CADM-ILD. METHODS: Forty-one patients diagnosed with MDA5-DM/CADM-ILD were retrospectively included. The clinical data were analyzed. Serum sCD206 levels were measured in 41 patients and 30 healthy controls. The relation between sCD206 levels and ILD deterioration was assessed. Receiver operating characteristic (ROC) curve was generated to determine the optimal cut-off value of sCD206 for predicting outcome. The association between sCD206 and survival was examined. RESULTS: The median serum sCD206 level in patients was significantly higher than healthy controls (464.1 ng/mL vs. 349.1 ng/mL, P = 0.002). In DM/CADM patients, the sCD206 level was significantly higher in patients with acute/subacute interstitial lung disease (AILD/SILD) than those with chronic interstitial lung disease (CILD) (539.2 ng/mL vs. 309.4 ng/mL, P = 0.005). The AUC of sCD206 was 0.885 for predicting mortality (95% CI 0.779-0.990). Patients were divided into two groups: sCD206 high level group (≥400 ng/mL) and sCD206 low level group (<400 ng/mL). Patients with sCD206 high level had significantly decreased survival rate than those with low level (25% vs. 88%, P < 0.001). The adjusted hazard ratio of sCD206 for mortality was 1.003 (adjusted for age and gender, P < 0.001), with sCD206 high level associated with higher death risk (HR 4.857, P = 0.006). CONCLUSION: Serum sCD206 might be a potential predictor of ILD deterioration and prognosis for Chinese patients with MDA5-DM/CADM-ILD.

Quantification of Endometrial Fibrosis Using Noninvasive MRI T2 Mapping: Initial Findings.

BACKGROUND: Endometrial fibrosis may cause infertility. Accurate evaluation of endometrial fibrosis helps clinicians to schedule timely therapy. PURPOSE: To explore T2 mapping for assessing endometrial fibrosis. STUDY TYPE: Prospective. POPULATION: Ninety-seven women with severe endometrial fibrosis (SEF) and 21 patients with mild to moderate endometrial fibrosis (MMEF), diagnosed by hysteroscopy, and 37 healthy women. FIELD STRENGTH/SEQUENCE: 3T, T2-weighted turbo spin echo (T2-weighted imaging) and multi-echo turbo spin echo (T2 mapping) sequences. ASSESSMENT: Endometrial MRI parameters (T2, thickness [ET], area [EA], and volume [EV]) were measured by N.Z. and Q.H. (9- and 4-years' experience in pelvic MRI) and compared between the three subgroups. A multivariable model including MRI parameters and clinical variables (including age and body mass index [BMI]) was developed to predict endometrial fibrosis assessed by hysteroscopy. STATISTICAL TESTS: Kruskal-Wallis; ANOVA; Spearman's correlation coefficient (rho); area under the receiver operating characteristic curve (AUC); binary logistic regression; intraclass correlation coefficient (ICC). P value <0.05 for statistical significance. RESULTS: Endometrial T2, ET, EA, and EV of MMEF patients (185 msec, 8.2 mm, 168 mm2 , and 2181 mm3 ) and SEF patients (164 msec, 6.7 mm, 120 mm2 , and 1762 mm3 ) were significantly lower than those of healthy women (222 msec, 11.7 mm, 316 mm2 , and 3960 mm3 ). Endometrial T2 and ET of SEF patients were significantly lower than those of MMEF patients. Endometrial T2, ET, EA, and EV were significantly correlated to the degree of endometrial fibrosis (rho = -0.623, -0.695, -0.694, -0.595). There were significant strong correlations between ET, EA, and EV in healthy women and MMEF patients (rho = 0.850-0.908). Endometrial MRI parameters and the multivariable model accurately distinguished MMEF or SEF from normal endometrium (AUCs >0.800). Age, BMI, and MRI parameters in univariable analysis and age and T2 in multivariable analysis significantly predicted endometrial fibrosis. The reproducibility of MRI parameters was excellent (ICC, 0.859-0.980). DATA CONCLUSION: T2 mapping has potential to noninvasively and quantitatively evaluate the degree of endometrial fibrosis. EVIDENCE LEVEL: 2 Technical Efficacy: Stage 2.

Assessing the inflammatory severity of the terminal ileum in Crohn disease using radiomics based on MRI.

BACKGROUND: Evaluating inflammatory severity using imaging is essential for Crohn's disease, but it is limited by potential interobserver variation and subjectivity. We compared the efficiency of magnetic resonance index of activity (MaRIA) collected by radiologists and a radiomics model in assessing the inflammatory severity of terminal ileum (TI). METHODS: 121 patients were collected from two centers. Patients were divided into ulcerative group and mucosal remission group based on the TI Crohn's disease Endoscopic Severity Index. The consistency of bowel wall thickness (BWT), relative contrast enhancement (RCE), edema, ulcer, MaRIA and features of the region of interest between radiologists were described by weighted Kappa test and intraclass correlation coefficient (ICC), and developed receiver operating curve of MaRIA. The radiomics model was established using reproducible features of logistic regression based on arterial staging of T1WI sequences. Delong test was used to compare radiomics with MaRIA. RESULTS: The consistency between radiologists were moderate in BWT (ICC = 0.638), fair in edema (κ = 0.541), RCE (ICC = 0.461), MaRIA (ICC = 0.579) and poor in ulcer (κ = 0.271). Radiomics model was developed by 6 reproducible features (ICC = 0.93-0.96) and equivalent to MaRIA which evaluated by the senior radiologist (0.872 vs 0.883 in training group, 0.824 vs 0.783 in validation group, P = 0.847, 0.471), both of which were significantly higher than MaRIA evaluated by junior radiologist (AUC: 0.621 in training group, 0.557 in validation group, all, P < 0.05). CONCLUSION: The evaluation of inflammatory severity could be performed by radiomics objectively and reproducibly, and was comparable to MaRIA evaluated by the senior radiologist. Radiomics may be an important method to assist junior radiologists to assess the severity of inflammation objectively and accurately.

Integrative Predictive Models of Computed Tomography Texture Parameters and Hematological Parameters for Lymph Node Metastasis in Lung Adenocarcinomas.

OBJECTIVES: The aims of the study were to integrate characteristics of computed tomography (CT), texture, and hematological parameters and to establish predictive models for lymph node (LN) metastasis in lung adenocarcinoma. METHODS: A total of 207 lung adenocarcinoma cases with confirmed postoperative pathology and preoperative CT scans between February 2017 and April 2019 were included in this retrospective study. All patients were divided into training and 2 validation cohorts chronologically in the ratio of 3:1:1. The χ2 test or Fisher exact test were used for categorical variables. The Shapiro-Wilk test and Mann-Whitney U test were used for continuous variables. Logistic regression and machine learning algorithm models based on CT characteristics, texture, and hematological parameters were used to predict LN metastasis. The performance of the multivariate models was evaluated using a receiver operating characteristic curve; prediction performance was evaluated in the validation cohorts. Decision curve analysis confirmed its clinical utility. RESULTS: Logistic regression analysis demonstrated that pleural thickening (P = 0.013), percentile 25th (P = 0.033), entropy gray-level co-occurrence matrix 10 (P = 0.019), red blood cell distribution width (P = 0.012), and lymphocyte-to-monocyte ratio (P = 0.049) were independent risk factors associated with LN metastasis. The area under the curve of the predictive model established using the previously mentioned 5 independent risk factors was 0.929 in the receiver operating characteristic analysis. The highest area under the curve was obtained in the training cohort (0.777 using Naive Bayes algorithm). CONCLUSIONS: Integrative predictive models of CT characteristics, texture, and hematological parameters could predict LN metastasis in lung adenocarcinomas. These findings may provide a reference for clinical decision making.

Development and validation of a magnetic resonance imaging-based nomogram for predicting invasive forms of placental accreta spectrum disorders.

AIM: The aim of the study was to develop and validate a magnetic resonance imaging (MRI)-based nomogram for predicting invasive forms of placental accreta spectrum (PAS) disorders (placenta increta and percreta) with "uncertain ultrasound diagnosis." METHODS: This was a retrospective cohort study of a primary cohort of 118 patients and a validation cohort of 65 patients with "uncertain ultrasound diagnosis," who were further evaluated by MRI. MRI signs associated with PAS disorders were analyzed between invasive and noninvasive groups by both univariate and logistic regression to construct the nomogram. The accuracy and discriminative ability of the nomogram were measured by concordance index (C-index) and calibration curve internally and externally. RESULTS: The history of previous cesarean deliveries (odds ratio [OR], 3.27; 95% confidence interval [CI], 1.16-9.27), loss of double-line sign (OR, 9.49; 95% CI, 3.06-29.48), abnormal uterine bulging (OR, 4.05; 95% CI, 1.53-10.69), and disorganized abnormal placenta vascularity (OR, 3.38; 95% CI, 1.09-10.50) were imputed for the nomogram. The C-index of the nomogram was 0.85 for internal validation and 0.84 for external validation. Calibration curve showed good agreement with predicted risk and actual observation for both primary and validation cohort. CONCLUSIONS: MRI can be a useful adjunct for clinical staging of patients with "uncertain ultrasound diagnosis."

A human-computer collaboration for COVID-19 differentiation: combining a radiomics model with deep learning and human auditing.

BACKGROUND: This study aimed to build a radiomics model with deep learning (DL) and human auditing and examine its diagnostic value in differentiating between coronavirus disease 2019 (COVID-19) and community-acquired pneumonia (CAP). METHODS: Forty-three COVID-19 patients, whose diagnoses had been confirmed with reverse-transcriptase polymerase-chain-reaction (RT-PCR) tests, and 60 CAP patients, whose diagnoses had been confirmed with sputum cultures, were enrolled in this retrospective study. The candidate regions of interest (ROIs) on the computed tomography (CT) images of the 103 patients were determined using a DL-based segmentation model powered by transfer learning. These ROIs were manually audited and corrected by 3 radiologists (with an average of 12 years of experience; range 6-17 years) to check the segmentation acceptance for the radiomics analysis. ROI-derived radiomics features were subsequently extracted to build the classification model and processed using 4 different algorithms (L1 regularization, Lasso, Ridge, and Z test) and 4 classifiers, including the logistic regression (LR), multi-layer perceptron (MLP), support vector machine (SVM), and extreme Gradient Boosting (XGboost). A receiver operating characteristic curve (ROC) analysis was conducted to evaluate the performance of the model. RESULTS: Quantitative CT measurements derived from human-audited segmentation results showed that COVID-19 patients had significantly decreased numbers of infected lobes compared to patients in the CAP group {median [interquartile range (IQR)]: 4 [3, 4] and 4 [4, 5]; P=0.031}. The infected percentage (%) of the whole lung was significantly more elevated in the CAP group [6.40 (2.77, 11.11)] than the COVID-19 group [1.83 (0.65, 4.42); P<0.001], and the same trend applied to each lobe, except for the superior lobe of the right lung [1.81 (0.09, 5.28) for COVID-19 vs. 1.32 (0.14, 7.02) for CAP; P=0.649]. Additionally, the highest proportion of infected lesions were observed in the CT value range of (-470, -370) Hounsfield units (HU) in the COVID-19 group. Conversely, the CAP group had a value range of (30, 60) HU. Radiomic model using corrected ROIs exhibited the highest area under ROC (AUC) of 0.990 [95% confidence interval (CI): 0.962-1.000] using Lasso for feature selection and MLP for classification. CONCLUSIONS: The proposed radiomics model based on human-audited segmentation made accurate differential diagnoses of COVID-19 and CAP. The quantification of CT measurements derived from DL could potentially be used as effective biomarkers in current clinical practice.

Novel typing of iliac vein compression in asymptomatic individuals evaluated by contrast enhanced CT.

PURPOSE: Compression of the iliac vein between the iliac artery and lumbosacral vertebra can cause iliac vein compression syndrome (IVCS). The purpose of this study is to assess compression characteristics and establish a new sub-typing in asymptomatic IVCS individuals using contrast-enhanced CT. METHODS: A retrospective analysis of abdomen contrast-enhanced CT images from 195 asymptomatic subjects with iliac vein compressed was investigated. Patients had no history of venous pathology, and images were collected from June 2018 to January 2019. Qualitative and quantitative characteristics of compression were examined including the location, pattern, minor diameter, area, and the percentage compression on an orthogonal section by the post-processing of multiple planar reconstruction and volume rendering. RESULTS: There were 107 females and 88 males with age range 18-92 years. The most common site of iliac vein compression was localized to the left common iliac vein (LCIV) (178/195, 91.3%). Notably, four compression types (type I-IV) were established according to the compression location, with type II being the most common. The four compression types had differences in the upper limit and fluctuation range of compression. It was found that the average level of iliac vein compression was below 25%. The compression degree of the left common iliac vein in type II was relatively concentrated, and the upper limit of compression was close to 70%. CONCLUSION: Asymptomatic iliac vein compression was categorized according to compression location. The proposal of four types might help clinicians to predict which IVCS patients would benefit from interventional therapy.

Preoperative T2-weighted MR imaging texture analysis of gastric cancer: prediction of TNM stages.

PURPOSE: To explore the capability of algorithms to build multivariate models integrating morphological and texture features derived from preoperative T2-weighted magnetic resonance (MR) images of gastric cancer (GC) to evaluate tumor- (T), node- (N), and metastasis- (M) stages. METHODS: A total of 80 patients at our hospital who underwent abdominal MR imaging and were diagnosed with GC from December 2011 to November 2016 were retrospectively included. Texture features were calculated using T2-weighted images with a manual region of interest. Morphological characteristics were also evaluated. Classifiers and regression analyses were used to build multivariate models. Receiver operating characteristic (ROC) curve analysis was performed to assess diagnostic efficacy. RESULTS: There were 8, 10, and 3 texture parameters that showed significant differences in GCs at different overall (I-II vs. III-IV), T (1-2 vs. 3-4), and N (- vs. +) stages (all p < 0.05), respectively. Mild thickening was more common in stages I-II, T1-2, and N- GCs (all p < 0.05). An irregular outer contour was more commonly observed in stages III-IV (p = 0.001) and T3-4 (p = 0.001) GCs. T3-4 and N+ GCs tended to be thickening type lesions (p = 0.005 and 0.032, respectively). The multivariate models using the naive bayes algorithm showed the highest diagnostic efficacy in predicting T and N stages (area under the ROC curves [AUC] = 0.900 and 0.863, respectively), and the model based on regression analysis had the best predictive performance in overall staging (AUC = 0.839). CONCLUSION: Multivariate models combining morphological characteristics with texture parameters based on machine learning algorithms were able to improve diagnostic efficacy in predicting the overall, T, and N stages of GCs.

Modification and comparison of CT criteria in the preoperative assessment of hepatic arterial invasion by hilar cholangiocarcinoma.

OBJECTIVE: To compare the diagnostic performance of three CT criteria and two signs in evaluating hepatic arterial invasion by hilar cholangiocarcinoma. METHODS: In this study, we retrospectively reviewed the CT images of 85 patients with hilar cholangiocarcinoma. Modified Loyer's, Lu's, and Li's standards were used to evaluate hepatic arterial invasion by hilar cholangiocarcinoma with the reference of intraoperative findings and/or the postoperative pathological diagnosis. Arterial tortuosity and contact length were also evaluated. RESULTS: Loyer's, Lu's, and Li's standards showed sensitivities of 91.7%, 90.3%, and 72.2%, specificities of 94.0%, 94.5%, and 95.6%, and accuracies of 93.3%, 93.3%, and 89.0%, respectively, in evaluating hepatic arterial invasion by hilar cholangiocarcinoma. Loyer's and Lu's standards and contact length performed better than Li's standard (P < 0.001). Arterial tortuosity performed worse than other criteria (P < 0.001). The CT criteria performed best in evaluating proper hepatic arterial invasion compared with the left and right hepatic artery. When the cut-off contact length of 6.73 mm was combined with Loyer's standard, 4 false-negative cases could be avoided. CONCLUSIONS: Loyer's and Lu's standards and the contact length performed best in evaluating hepatic arterial invasion by hilar cholangiocarcinoma on preoperative CT images, particularly in assessing the proper hepatic artery. Arterial tortuosity could serve as an important supplement. The combination of the contact length and Loyer's standard could improve the diagnostic performance.

Postmortem 9.4-T MRI for Fetuses With Congenital Heart Defects Diagnosed in the First Trimester.

OBJECTIVE: To evaluate the feasibility of 9. 4-T postmortem MRI (pm-MRI) for assessment of major congenital heart defects (CHD) cases terminated in the early stage of gestation. METHODS: Fetuses with CHD detected by the detailed first-trimester ultrasound scan and terminated before 18 gestational weeks were recruited between January 2018 and June 2020. All fetuses were offered 9.4-T pm-MRI examinations and those terminated over 13+6 weeks were offered conventional autopsies simultaneously. Findings of pm-MRI were compared with those of conventional autopsy and prenatal ultrasound. RESULTS: A total of 19 fetuses with major CHD were analyzed, including 6 cases of the atrioventricular septal defect, 5 cases of Tetralogy of Fallot, 3 cases of hypoplastic left heart syndrome, 1 case of tricuspid atresia, 1 case of transposition of the great arteries, 1 case of severe tricuspid regurgitation, and 2 cases of complex CHD. Pm-MRI had concordant findings in 73.7% (14/19) cases, discordant findings in 15.8% (3/19) cases, and additional findings in 10.5% (2/19) cases when compared with prenatal ultrasound. Pm-MRI findings were concordant with autopsy in all 8 CHD cases terminated over 13+6 weeks. CONCLUSION: It is feasible to exhibit the structure of fetal heart terminated in the first trimester clearly on 9.4-T pm-MRI with an optimized scanning protocol. High-field pm-MRI could provide medical imaging information of CHD for those terminated in the early stage of gestation, especially for those limited by conventional autopsy.

Molecular Magnetic Resonance Imaging with Contrast Agents for Assessment of Inflammatory Bowel Disease: A Systematic Review.

Background and Aims: Magnetic resonance imaging (MRI) has taken an important role in the diagnosis of inflammatory bowel diseases (IBD). In the wake of current advances in nanotechnology, the drug delivery industry has seen a surge of nanoparticles advertising high specificity in target imaging. Given the rapid development of the field, this review has assembled related articles to explore whether molecular contrast agents can improve the diagnostic capability on gastrointestinal imaging, especially for IBD. Methods: Relevant articles published between 1998 and 2018 from a literature search of PubMed and EMBASE were reviewed. Data extraction was performed on the studies' characteristics, experimental animals, modelling methods, nanoparticles type, magnetic resonance methods, and means of quantitative analysis. Results: A total of 8 studies were identified wherein the subjects were animals, and all studies employed MR equipment. One group utilized a perfluorocarbon solution and the other 7 groups used either magnetic nanoparticles or gadolinium- (Gd-) related nanoparticles for molecular contrast. With ultrasmall superparamagnetic iron oxide (USPIO) particles and Gd-related nanoparticles, signal enhancements were found in the mucosa or with focal lesion of IBD-related model in T1-weighted images (T1WI), whereas superparamagnetic iron oxide (SPIO) particles showed a signal decrease in the intestinal wall of the model in T1WI or T2-weighted images. The signal-to-noise ratio (SNR) was employed to analyze bowel intensity in 3 studies. And the percentage of normalized enhancement was used in 1 study for assessing the severity of inflammation. Conclusion: Molecular MRI with contrast agents can improve the early diagnosis of IBD and quantitate the severity of inflammation in experimental studies.

Evaluation of Lymph Node Metastasis in Advanced Gastric Cancer Using Magnetic Resonance Imaging-Based Radiomics.

Objective: To develop and evaluate a diffusion-weighted imaging (DWI)-based radiomic nomogram for lymph node metastasis (LNM) prediction in advanced gastric cancer (AGC) patients. Overall Study: This retrospective study was conducted with 146 consecutively included pathologically confirmed AGC patients from two centers. All patients underwent preoperative 3.0 T magnetic resonance imaging (MRI) examination. The dataset was allocated to a training cohort (n = 71) and an internal validation cohort (n = 47) from one center along with an external validation cohort (n = 28) from another. A summary of 1,305 radiomic features were extracted per patient. The least absolute shrinkage and selection operator (LASSO) logistic regression and learning vector quantization (LVQ) methods with cross-validations were adopted to select significant features in a radiomic signature. Combining the radiomic signature and independent clinical factors, a radiomic nomogram was established. The MRI-reported N staging and the MRI-derived model were built for comparison. Model performance was evaluated considering receiver operating characteristic (ROC) analysis, calibration curves, and decision curve analysis (DCA). Results: A two-feature radiomic signature was found significantly associated with LNM (p < 0.01, training and internal validation cohorts). A radiomic nomogram was established by incorporating the clinical minimum apparent diffusion coefficient (ADC) and MRI-reported N staging. The radiomic nomogram showed a favorable classification ability with an area under ROC curve of 0.850 [95% confidence interval (CI), 0.758-0.942] in the training cohort, which was then confirmed with an AUC of 0.857 (95% CI, 0.714-1.000) in internal validation cohort and 0.878 (95% CI, 0.696-1.000) in external validation cohort. Meanwhile, the specificity, sensitivity, and accuracy were 0.846, 0.853, and 0.851 in internal validation cohort, and 0.714, 0.952, and 0.893 in external validation cohort, compensating for the MRI-reported N staging and MRI-derived model. DCA demonstrated good clinical use of radiomic nomogram. Conclusions: This study put forward a DWI-based radiomic nomogram incorporating the radiomic signature, minimum ADC, and MRI-reported N staging for individualized preoperative detection of LNM in patients with AGC.

Prognostic effects of clinical and CT imaging features on critically ill patients with interstitial lung disease hospitalized in respiratory intensive care unit.

The study aimed to evaluate the clinical and imaging features of critically ill patients with interstitial lung disease (ILD) treated in respiratory intensive care unit (RICU) and assess the prognostic effects of these factors. A total of 160 severe ILD patients admitted to the RICU were finally enrolled in this study. The clinical, imaging and follow-up data of them were studied retrospectively. The in-hospital mortality and total mortality were 43.1% and 63.8% respectively. By multivariate cox regression analysis, shock (OR = 2.39, P = 0.004), pulmonary fibrosis on CT (OR = 2.85, P = 0.002) and non-invasive ventilation (OR = 1.86, P = 0.037) were harmful factors to survivals of critically ill patients with ILD. In contrast, oxygenation index (OR = 0.99, P = 0.028), conventional oxygen therapy (OR = 0.59, P = 0.048) and ß-lactam antibiotics use (OR = 0.51, P = 0.004) were protective factors. There is significant difference of survivals between patients with and without fibrosing ILD on CT (Log-rank, p = 0.001). The prognosis of critically ill patients with ILD was poor. Shock, respiratory failure and fibrosing signs on chest CT affected the prognosis. Chest CT was considered as a valuable tool to indicate the prognosis.

The relationship between MUC5B promoter, TERT polymorphisms and telomere lengths with radiographic extent and survival in a Chinese IPF cohort.

Genetic factors were identified to be associated with the development of idiopathic pulmonary fibrosis (IPF). We aimed to investigate associations between mucin 5B (MUC5B) and telomerase reverse transcriptase (TERT) polymorphisms and telomere length (TL) with honeycombing extent and survival in a Chinese IPF cohort. Seventy-nine patients diagnosed with IPF were enrolled. The honeycombing extents in high resolution CT scan (HRCT) were quantitatively scored and defined as mild (<10%), moderate (10-50%), and severe (>50%) upon the honeycombing extents involving the total lung. We tested five single-nucleotide polymorphisms [rs35705950, rs868903 in MUC5B, rs2736100, rs2853676 in TERT and rs1881984 in Telomerase RNA Gene (TERC) and TLs in peripheral blood leucocytes, and evaluated their associations with radiographic extent and survival in IPF. The minor allele frequencies (MAF) were significantly greater for MUC5B rs868903 (P = 0.042) and TERT rs2853676 (P = 0.041) in IPF than those in healthy controls. CT/CC genotype of MUC5B rs868903 (p = 0.045) and short TLs (p = 0.035) were correlated with the more extensive honeycombing opacities in HRCT. After adjustment for age, sex, and smoking status, MUC5B rs868903 polymorphism was the significant gene risk factors for reduced survival (p = 0.044) in IPF. MUC5B promoter rs868903 polymorphism and TLs were associated with radiographic extent and survival in a Chinese IPF cohort. These findings suggested a genetic clue for exploring the underlying molecular basis and pathogenesis of IPF.

A long-term retrospective study of patients with biopsy-proven cryptogenic organizing pneumonia.

Cryptogenic organizing pneumonia (COP) is characterized by good response to corticosteroids, but frequent relapses after reduction or cessation of treatment are noted. The incidence, risk factors of relapse, and long-term outcomes of patients with COP remain undetermined. Patients with COP from September 2010 to December 2017 were enrolled. Hospital and office records were used as data sources. Clinical information, lab examinations, chest radiographs, treatment courses, and follow-up data were collected. Relapse group was defined as worsening of clinical manifestations in combination with progression of radiographic abnormalities in the absence of identified causes. Eighty-seven patients with COP were enrolled. Of them, 73 patients were treated with corticosteroids with relapse rate yielding 31.5% (23 of 73). Eleven patients were treated with macrolides and none of them relapsed. Fever was more common (65.2% vs. 32.0%, p = 0.004), C-reactive protein (CRP) was higher (31.5 ± 39.4 mg/L vs. 17.5 ± 32.2 mg/L, p = 0.038), and diffusion capacity for carbon monoxide (DLCO) % predicted was lower (45.9 ± 14.2% vs. 57.6 ± 18.5%, p = 0.050) in relapse group compared to nonrelapse group. Four patients who presented with organizing pneumonia (OP) as the first manifestation were ultimately diagnosed with OP secondary to autoimmune disease in follow-up. We showed relapse was common in COP patients treated with corticosteroids, but the prognosis was favorable. Fever, elevated CRP, and a reduced DLCO were related to relapse. As OP may not always be cryptogenic, a careful follow-up should be programmed to diagnose the underlying systemic disease.

IILS: Intelligent imaging layout system for automatic imaging report standardization and intra-interdisciplinary clinical workflow optimization.

BACKGROUND: To achieve imaging report standardization and improve the quality and efficiency of the intra-interdisciplinary clinical workflow, we proposed an intelligent imaging layout system (IILS) for a clinical decision support system-based ubiquitous healthcare service, which is a lung nodule management system using medical images. METHODS: We created a lung IILS based on deep learning for imaging report standardization and workflow optimization for the identification of nodules. Our IILS utilized a deep learning plus adaptive auto layout tool, which trained and tested a neural network with imaging data from all the main CT manufacturers from 11,205 patients. Model performance was evaluated by the receiver operating characteristic curve (ROC) and calculating the corresponding area under the curve (AUC). The clinical application value for our IILS was assessed by a comprehensive comparison of multiple aspects. FINDINGS: Our IILS is clinically applicable due to the consistency with nodules detected by IILS, with its highest consistency of 0·94 and an AUC of 90·6% for malignant pulmonary nodules versus benign nodules with a sensitivity of 76·5% and specificity of 89·1%. Applying this IILS to a dataset of chest CT images, we demonstrate performance comparable to that of human experts in providing a better layout and aiding in diagnosis in 100% valid images and nodule display. The IILS was superior to the traditional manual system in performance, such as reducing the number of clicks from 14·45 ±â€¯0·38 to 2, time consumed from 16·87 ±â€¯0·38 s to 6·92 ±â€¯0·10 s, number of invalid images from 7·06 ±â€¯0·24 to 0, and missing lung nodules from 46·8% to 0%. INTERPRETATION: This IILS might achieve imaging report standardization, and improve the clinical workflow therefore opening a new window for clinical application of artificial intelligence. FUND: The National Natural Science Foundation of China.

Clinical features, risk factors, and outcomes of patients with interstitial pneumonia with autoimmune features: a population-based study.

To investigate the clinical features, risk factors and outcomes of patients with interstitial pneumonia with autoimmune features (IPAF). A total of 1429 patients with idiopathic interstitial pneumonia (IIP) and undifferentiated connective tissue disease-associated interstitial lung disease (UCTD-ILD) were screened to identify patients who met IPAF criteria. Clinical, serological, and morphological features of patients with IPAF were characterized. Outcomes between patients with IPAF, UCTD-ILD, and IIP who were divided into idiopathic pulmonary fibrosis (IPF) and non-IPF groups were compared using survival as an endpoint. Patients with IPAF were much common in young female and had lower percentage of ever smoking and a significantly shorter survival than those with non-IPAF (P < 0.001). Subgroup analysis revealed that IPAF cohort survival was worse than that in non-IPF (P < 0.001), but better than that in IPF (P < 0.001). In IPAF cohort, the most common systemic symptom and serological abnormality were Raynaud's phenomenon (12.9%) and ANA ≥ 1:320 (49.2%); the most frequent high-resolution computed tomography (HRCT) pattern was nonspecific interstitial pneumonia (NSIP) (61.6%). Multivariate analysis indicated that several factors including age, smoking history, organizing pneumonia (OP) pattern in HRCT, and anti-RNP positivity were independently associated with significantly worse survival. IPAF had the distinct clinical features and outcomes compared with other groups of ILD. Additional studies should be needed to explore the underlying autoimmune mechanism and to determine risk stratification in future clinical research.