RESUMEN
Objective@#To investigate the prognostic utility of radiomics features extracted from 18 F-fluorodeoxyglucose (FDG) PET/CT combined with clinical factors and metabolic parameters in predicting progression-free survival (PFS) and overall survival (OS) in individuals diagnosed with extranodal nasal-type NK/T cell lymphoma (ENKTCL). @*Materials and Methods@#A total of 126 adults with ENKTCL who underwent 18 F-FDG PET/CT examination before treatment were retrospectively included and randomly divided into training (n = 88) and validation cohorts (n = 38) at a ratio of 7:3.Least absolute shrinkage and selection operation Cox regression analysis was used to select the best radiomics features and calculate each patient’s radiomics scores (RadPFS and RadOS). Kaplan–Meier curve and Log-rank test were used to compare survival between patient groups risk-stratified by the radiomics scores. Various models to predict PFS and OS were constructed, including clinical, metabolic, clinical + metabolic, and clinical + metabolic + radiomics models. The discriminative ability of each model was evaluated using Harrell’s C index. The performance of each model in predicting PFS and OS for 1-, 3-, and 5-years was evaluated using the time-dependent receiver operating characteristic (ROC) curve. @*Results@#Kaplan–Meier curve analysis demonstrated that the radiomics scores effectively identified high- and low-risk patients (all P < 0.05). Multivariable Cox analysis showed that the Ann Arbor stage, maximum standardized uptake value (SUVmax), and RadPFS were independent risk factors associated with PFS. Further, β2-microglobulin, Eastern Cooperative Oncology Group performance status score, SUVmax, and RadOS were independent risk factors for OS. The clinical + metabolic + radiomics model exhibited the greatest discriminative ability for both PFS (Harrell’s C-index: 0.805 in the validation cohort) and OS (Harrell’s C-index: 0.833 in the validation cohort). The time-dependent ROC analysis indicated that the clinical + metabolic + radiomics model had the best predictive performance. @*Conclusion@#The PET/CT-based clinical + metabolic + radiomics model can enhance prognostication among patients with ENKTCL and may be a non-invasive and efficient risk stratification tool for clinical practice.
RESUMEN
Objective To observe the value of intratumoral and peritumoral radiomics based on diffusion weighted imaging(DWI)for predicting histological grade of breast cancer.Methods Preoperative DWI data of 700 patients with single breast cancer diagnosed by pathology were retrospectively analyzed.The patients were divided into training set(n= 560,including 381 of grade Ⅰ+Ⅱ and 179 of grade Ⅲ)and test set(n=140,including 95 of grade Ⅰ+Ⅱ and 45 of grade Ⅲ)at the ratio of 8∶2.Intratumoral ROI(ROIintra)was manually delineated on DWI,which was automatically expanded by 3 mm and 5 mm to decline peritumoral ROI(ROIperi,including ROI3 mm and ROI5 mm),then intratumoral-peritumoral ROI(ROIintra+3 mm,ROIintra+5 mm)were obtained.The optimal radiomics features were extracted and screened,and the radiomics model(RM)for predicting the histological grade of breast cancer were constructed.Receiver operating characteristic curves were drawn,and the areas under the curve(AUC)were calculated to evaluate the predictive efficacy of each model.Calibration curve method was used to evaluate the calibration degree,while decision curve analysis(DCA)was performed to explore the clinical practicability of each model.Results AUC of RMintra,RM+3 mm,RM+5mm,RMintra+3 mm and RMintra+5 mm was 0.750,0.724,0.749,0.833 and 0.807 in training set,while was 0.723,0.718,0.736,0.759 and 0.782 in test set,respectively.In training set,significant differences of AUC was found(all P＜0.01),while in test set,no significant difference of AUC was found among models(all P＞0.05).The calibrations of models were all high.DCA showed that taken 0.02-0.88 as the threshold,the clinical net benefit of RMintra+per were greater in training set,while taken 0.40-0.72 as the threshold,the clinical net benefit of RMintra+per was greater in test set.Conclusion Both DWI intratumoral and peritumoral radiomics could effectively predict histological grade of breast cancer.Combination of intratumoral and peritumoral radiomics was more effective.
RESUMEN
Objective:To investigate the value of the 8-channel eye surface phased array coil in improving image quality and demonstrating ocular masses on 3.0 T MR scanner.Methods:From July 2018 to January 2020, the data of orbital MRI in 692 patients with ocular masses on 6 medical centers were prospectively collected. The patients were simple randomly assigned into 8-channel eye surface phased array coil group (413 patients) or 8-channel head phased array coil group (279 patients), with the same MRI sequences. The signal to noise ratio (SNR) and contrast to noise ratio (CNR) were calculated in orbital anatomy structures and masses (eyelid mass, intraocular mass, lacrimal mass and orbital mass). The image quality scores including motion artifact, mass margin, the relationship between the mass and adjacent structures, and overall image quality were recorded. The differences of image quality between the two groups were compared by two independent sample t-test or Wilcoxon rank test. Results:The SNR and CNR were higher in eye surface coil group than those in head coil group ( P<0.05). The scores of ocular movement artifacts were higher in head coil group than those in surface coil group ( P<0.05). The scores of intraocular mass margin, the relationship between the mass and adjacent structures, and overall image quality were higher in surface coil group than those in head coil group ( P<0.001). There were no significant differences in mass margin, the relationship between the mass and adjacent structures, and overall image quality scores of eyelid, lacrimal gland, and orbital mass between the two groups ( P>0.05). Conclusion:3.0 T MR scanner combined with the 8-channel eye surface phased array coil can improve the SNR and CNR of orbital MR images, the demonstration of the intraocular mass margin and the relationship between the mass and adjacent structures.
RESUMEN
Objective:To explore the feasibility of 60 kV tube voltage combined with reduced contrast medium in CT pulmonary angiography (CTPA).Methods:Totally 60 outpatients and inpatients with a body mass index (BMI) of less than 25 kg/m 2 who had suspected pulmonary embolism and were arranged for CTPA examination were enrolled in this study. They were divided into a control group and an test group according to the random number table method. A protocol with a conventional dose was adopted in the control group. This scheme consisted of 100 kV tube voltage and injection of 50 ml of contrast medium at the rate of 4.5 ml/s. A scheme with a low dose was employed in the experimental group. Specifically, this scheme involved 60 kV tube voltage scheme and injection of 30 ml of contrast medium mixed with 20 ml of normal saline at a rate of 4.5 ml/s. The objective image quality was assessed by measuring the Hounsfield units (HU) of five regions of interest (ROIs), i. e., pulmonary trunk, right and left pulmonary arteries, and right and left lower lobar arteries, and the signal-to-noise ratio (SNR) and the contrast-to-noise ratio (CNR) were calculated. Moreover, the radiation doses were recorded. The subjective image quality was assessed by radiologists using a 5-point scale based on the overall image quality and the enhancement homogeneity of pulmonary arteries. The noise, SNR, CNR, and radiation dose of the two groups were compared using the Mann-Whitney U test, and the differences in the subjective image quality between the two groups were compared using the χ2 test. Results:All images met the requirements for clinical diagnosis. The two groups did not show significant differences in the overall subjective quality of CTPA images and enhancement scores ( P > 0.05), and in the average attenuation values of the pulmonary trunk and the left and right lower lobar arteries ( P > 0.05), but exhibited statistical differences in the average attenuation values of the left and right pulmonary arteries ( t = 2.75, 3.91, P < 0.05). There was no significant difference in the average background noise between the two groups ( P > 0.05). The test group had higher CNR of the left pulmonary artery and higher SNR and CNR of the right pulmonary artery than the control group, with statistically significant differences ( t = 0.04, 2.41, 3.08, P < 0.05). There was no significant difference in the SNR and CNR of other pulmonary artery branches between the two groups ( P > 0.05). The test group had an average effective dose of 1.24 mSv for CTPA, which was about one-third of that of the control group, with statistically significant differences ( t = 21.65, P < 0.05). Conclusions:The scheme of 60 kV tube voltage and reduced contrast medium for CTPA is feasible for patients with BMI < 25 kg/m 2. Using this scheme, the radiation and iodine dose can be reduced without affecting image quality.
RESUMEN
Objective:To investigate the value of intratumoral and peritumoral radiomics features of multi-parameter MRI in evaluation of the status of human epithelial growth factor receptor 2 in breast cancer.Methods:The clinical, pathological and imaging data of 340 patients with pathologically confirmed breast cancer in Henan Provincial People′s Hospital from September 2019 to December 2020 were retrospectively collected. All patients were female, 48 (42, 55) years old. All patients underwent multi-parameter breast MRI before surgery, including dynamic contrast-enhanced T 1WI (DCE-T 1WI), fat-suppressed T 2WI (T 2WI) and diffusion-weighted imaging (DWI). The region of interest (ROI) for lesions were manually delineated and the segmented ROIs were zoomed in ring shape by 4 mm to acquire ROI intra and ROI prei, respectively. Then six sets of radiomics features were extracted from ROI intra and ROI prei of DCE-T 1WI, T 2WI and DWI. The cases were divided into a training set (272 cases) and a test set (68 cases) by stratified sampling at a ratio of 4∶1. The Mann-Whitney U test, Select K Best and minimum absolute contraction and selection operator were used for feature selection of the 6 sets of radiomics features. The feature subsets after reduction were used to construct independent and combined radiomics signatures with support vector machine algorithm to predict the HER2 status of breast cancer. Receiver operating characteristic curve was generated and area under curve (AUC) was calculated to compare the prediction performance of different models. Results:Of the 340 patients, 80 were HER2-positive and 260 were HER2-negative. Among the radiomics signatures based on single sequence, the DWI peri showed the best performance in predicting HER2 status of breast cancer, with an AUC of 0.678 for the test set. Among the combination of intratumoral and peritumoral radiomics signatures based on same sequence, the DWI intra+DWI peri had the highest prediction value, achieving an AUC of 0.774 for the testing set. Among the intratumoral or peritumoral radiomics signatures derived from two different sequences, the DCE-T 1WI intra+DWI intra and T 2WI peri+DWI peri showed the best predictive performance, yielding AUC of 0.766 and 0.769 in the testing set, respectively. Among the combination of intratumoral or peritumoral radiomics signatures derived from all 3 sequences or combinations of all features, the DCE-T 1WI intra+T 2WI intra+DWI intra+DCE-T 1WI peri+T 2WI peri+DWI peri obtained the highest prediction efficiency, with an AUC of 0.913 for the testing set. Conclusion:The radiomics features of intratumoral and peritumoral regions based on multi-parameter MRI have a certain value in non-invasive evaluation of HER2 status of breast cancer, which can help clinicians to provide scientific basis for decision-making of targeted therapy in patients with breast cancer.
RESUMEN
Objective:To explore the detection and segmentation of ischemic core infarct volume of the acute stroke in diffusion weighted imaging (DWI) images using cascaded VB-Net.Methods:MRI data of 1 500 patients (2 456 lesions) with acute ischemic stroke in Henan Provincial People′s Hospital from December 2016 to December 2018 were retrospectively analyzed. Firstly, manual segmentation of ischemic core was performed on DWI images (b=1 000 s/mm 2), and then all data were divided into training set, validation set and independent test set by 8∶1∶1. Then, the cascaded VB-Net was constructed, and the core infarct was automatically detected and segmented in the test set. Interclass correlation coefficient (ICC) was used to evaluate the consistency of volume size measured by manual segmentation and cascaded VB-Net. The patients were divided into large ischemic core lesion group (ischemic core volume ≥10 ml) and small ischemic core lesion group (ischemic core volume<10 ml), and the Dice coefficient difference between the two groups was compared using Mann-Whitney U test. Results:In independent test set, cascaded model had the detection rate of 94.6% (243/257) with Dice coefficient of 0.76 (0.68, 0.84). The agreement of cacade VB-Net segmented [4.19(1.21,14.13)ml] and manual segmented ischemic core infarct volume [4.08(1.19,17.92)ml] was high (ICC=0.97, P<0.001). There was no significant difference in Dice coefficient between large and small lesion groups [0.76 (0.69, 0.85), 0.76 (0.67, 0.84), Z=-0.44, P=0.657]. Conclusions:The cascaded VB-Net model provided a tool to realize automatic detection, segmentation, and calculation of ischemic core infarct volume. It has good segmentation accuracy and high consistency with manual segmentation, which can provide an auxiliary decision-making tool for the selection of treatment plans.
RESUMEN
Objective:To investigate the MRI and pathological features of intramuscular fibro-adipose vascular anomaly (FAVA).Methods:The clinical and imaging data of 44 patients with intramuscular FAVA confirmed by pathology from December 2012 to March 2021 in Henan Province People′s Hospital were retrospectively analyzed. Twenty-five females and 19 males were included, with the age of (15±6), from 5 to 29 years old. The clinical and MRI features including the type, location, boundary, signal intensity, enhancement mode and degree, and the vascular flow voids in the lesion were summarized and compared with pathological results.Results:The thigh and calf muscles were involved in 1 patient simultaneously, and 1 site was involved in 43 patients, including 20 calf muscles, 15 thigh muscles, 5 forearm muscles, 1 upper arm muscle, 1 gluteal muscle, and 1 shoulder muscle. The gastrocnemius muscle of lower leg was most commonly involved (13/44), followed by soleus muscle (10/44) and quadriceps femoris muscle (9/44). All the lesions were solid on MRI, including 24 cases of focal mass type, 15 cases of diffuse infiltration type and 5 cases of local infiltration type. The long axis of all the lesions were consistent with the long axis of the muscles. All lesions showed inhomogeneously moderate hyperintensity on T 1WI and T 2WI, and significantly hyperintensity on fat suppression T 2WI. All lesions showed tortuous and dilated abnormal vessels, of which 18 cases showed vascular flow voids. Thrombosis was found in 10 cases. On contrast-enhanced imaging, the lesions showed moderate to obvious inhomogeneous enhancement. Pathologically, the diseased skeletal muscle was infiltrated by fibrous tissue, fat components, irregular abnormal veins and vessels, which led to inhomogeneous MRI signals. Among the 7 patients who underwent human PIK3CA gene mutation detection, and 6 were mutant. Conclusions:Intramuscular FAVA has certain characteristics in clinic, MRI imaging and histopathology, and its MRI signal characteristics can reflect its complex pathological components.
RESUMEN
Objective:To investigate the value of periodically rotated overlapping parallel lines with enhanced reconstruction (PROPELLER) in improving ability of demonstrating ocular masses on 3.0 T MR scanner.Methods:This study was a multi-center prospective study involving 6 centers. From July 2018 to January 2020, totally 413 patients with ocular masses from 6 centers were prospectively enrolled, and all of them underwent T 1WI and T 2WI, PROPELLER T 1 FLAIR and T 2WI, and contrast-enhanced scans. The signal intensity of eyelid, vitreous body, lacrimal gland, intraorbital segment of optic nerve, and orbital masses of eyelid, intraocular, lacrimal gland and retrobulbar were measured by two radiologists, and the signal to noise ratio (SNR) and contrast noise ratio (CNR) were calculated. The 5-point scoring method was used to evaluate the motion artefacts, tumor edges and the relationship between the tumor and adjacent structures, and the overall score of image quality was calculated. Paired t-test or Wilcoxon signed rank test was used to compare the image quality between PROPELLER and non-PROPELLER images. Results:The SNR and CNR of PROPELLER T 2WI were higher than those of non-PROPELLER T 2WI (all P<0.001). The SNR and CNR of PROPELLER T 1 FLAIR were lower than those of non-PROPELLER T 1WI (all P<0.05). The scores of artefacts and overall image quality in PROPELLER images were higher than those in non-PROPELLER images (all P<0.001). The tumor edge and the relationship between the tumor and adjacent structures scores of eyelid, intraocular, and lacrimal gland masses in PROPELLER images were higher than those in non-PROPELLER images (all P<0.001),while compared to non-PROPELLER images, retro-global masses in PROPELLER images showed no significant differences (all P>0.05). Conclusion:PROPELLER can reduce ocular motion artefacts, effectively improve image quality and ability of demonstrating anterior (eyelid, intraocular, and lacrimal gland) masses.
RESUMEN
Objective:To assess the role of arterial spin labeling (ASL) in detecting the blood-brain barrier (BBB) permeability of cerebral infarction lesions in patients with anterior circulation subacute ischemic stroke (SIS), and to evaluate the value of ASL in predicting hemorrhagic transformation (HT) of SIS patients after endovascular recanalization.Methods:A prospective analysis was performed. Patients with anterior circulation SIS who received endovascular treatment (EVT) in our hospital from January 2021 to September 2021 were enrolled. At 24 h before EVT and immediately after EVT, MRI scans of ASL sequences and dynamic contrast-enhanced magnetic resonance (DCE) sequence were completed, and Xper CT was performed; accordingly, imaging typing was performed. Head CT scan was performed 24-48 h after EVT to observe HT; according to the presence or absence of HT, these patients were divided into HT group and non-HT group; the relative cerebral blood flow (rCBF) values of ASL sequence parameters, volume transfer constant (K trans) of DCE sequence parameters and the differences of ASL, DCE and Xper CT imaging types between the two groups were compared. The weighted Kappa coefficient was used to test the consistency among ASL, DCE and Xper CT imaging types. Results:Among 22 eligible patients, 5 patients occurred HT (5/22, 22.72%). As compared with those in the non-HT group (1.14±0.04; 0.032[0.024, 0.039]/min), patients in the HT group had significantly higher rCBF value (1.57±0.18) and K trans (0.072[0.0455, 0.117]/min, P<0.05). There were significant differences in the distribution of ASL, DCE and Xper CT imaging types between the two groups ( P<0.05); among them, 4 out of 6 patients with ASL imaging type III, 4 out of 6 patients with DCE imaging type III, and 4 out of 5 patients with Xper CT imaging type III had HT. ASL sequence and DCE sequence had a high consistency in the imaging types (Kappa coefficient=0.941, 95%CI: 0.862-1.020, P<0.001). Conclusion:ASL can effectively evaluate the BBB permeability of cerebral infarction lesions in patients with anterior circulation SIS; patients with ASL imaging type III have a relatively high risk of HT.
RESUMEN
Objective:To assess the role of arterial spin labeling (ASL) in detecting the blood-brain barrier (BBB) permeability of cerebral infarction lesions in patients with anterior circulation subacute ischemic stroke (SIS), and to evaluate the value of ASL in predicting hemorrhagic transformation (HT) of SIS patients after endovascular recanalization.Methods:A prospective analysis was performed. Patients with anterior circulation SIS who received endovascular treatment (EVT) in our hospital from January 2021 to September 2021 were enrolled. At 24 h before EVT and immediately after EVT, MRI scans of ASL sequences and dynamic contrast-enhanced magnetic resonance (DCE) sequence were completed, and Xper CT was performed; accordingly, imaging typing was performed. Head CT scan was performed 24-48 h after EVT to observe HT; according to the presence or absence of HT, these patients were divided into HT group and non-HT group; the relative cerebral blood flow (rCBF) values of ASL sequence parameters, volume transfer constant (K trans) of DCE sequence parameters and the differences of ASL, DCE and Xper CT imaging types between the two groups were compared. The weighted Kappa coefficient was used to test the consistency among ASL, DCE and Xper CT imaging types. Results:Among 22 eligible patients, 5 patients occurred HT (5/22, 22.72%). As compared with those in the non-HT group (1.14±0.04; 0.032[0.024, 0.039]/min), patients in the HT group had significantly higher rCBF value (1.57±0.18) and K trans (0.072[0.0455, 0.117]/min, P<0.05). There were significant differences in the distribution of ASL, DCE and Xper CT imaging types between the two groups ( P<0.05); among them, 4 out of 6 patients with ASL imaging type III, 4 out of 6 patients with DCE imaging type III, and 4 out of 5 patients with Xper CT imaging type III had HT. ASL sequence and DCE sequence had a high consistency in the imaging types (Kappa coefficient=0.941, 95%CI: 0.862-1.020, P<0.001). Conclusion:ASL can effectively evaluate the BBB permeability of cerebral infarction lesions in patients with anterior circulation SIS; patients with ASL imaging type III have a relatively high risk of HT.
RESUMEN
Objective@#To evaluate the radiological tumor response patterns and compare the response assessments based on immunebased therapeutics Response Evaluation Criteria in Solid Tumors (iRECIST) and RECIST 1.1 in metastatic clear-cell renal cell carcinoma (mccRCC) patients treated with programmed cell death-1 (PD-1) inhibitors. @*Materials and Methods@#All mccRCC patients treated with PD-1 inhibitors at Henan Cancer Hospital, China, between January 2018 and April 2019, were retrospectively studied. A total of 30 mccRCC patients (20 males and 10 females; mean age, 55.6 years; age range, 37–79 years) were analyzed. The target lesions were quantified on consecutive CT scans during therapy using iRECIST and RECIST 1.1. The tumor growth rate was calculated before and after therapy initiation. The response patterns were analyzed, and the differences in tumor response assessments of the two criteria were compared. The intra- and inter-observer variabilities of iRECIST and RECIST 1.1 were also analyzed. @*Results@#The objective response rate throughout therapy was 50% (95% confidence interval [CI]: 32.1–67.9) based on iRECIST and 30% (95% CI: 13.6–46.4) based on RECIST 1.1. The time-to-progression (TTP) based on iRECIST was longer than that based on RECIST 1.1 (median TTP: not reached vs. 170 days, p = 0.04). iRECIST and RECIST 1.1 were discordant in 8 cases, which were evaluated as immune-unconfirmed PD based on iRECIST and PD based on RECIST 1.1. Six patients (20%, 6/30) had pseudoprogression based on iRECIST, of which four demonstrated early pseudoprogression and two had delayed pseudoprogression.Significant differences in the tumor response assessments based on the two criteria were observed (p < 0.001). No patients demonstrated hyperprogression during the study period. @*Conclusion@#Our study confirmed that the iRECIST criteria are more capable of capturing immune-related atypical responses during immunotherapy, whereas conventional RECIST 1.1 may underestimate the benefit of PD-1 inhibitors. Pseudoprogression is not rare in mccRCC patients during PD-1 inhibitor therapy, and it may last for more than the recommended maximum of 8 weeks, indicating a limitation of the current strategy for immune response monitoring.
RESUMEN
Objective:To investigate the value of serum miR-143 level combined with MRI in predicting the early response to concurrent chemoradiotherapy (CCRT) in cervical cancer.Methods:A total of 85 patients with pathologically confirmed cervical cancer underwent conventional MRI, intravoxel incoherent motion diffusion-weighted imaging (IVIM-DWI), and dynamic contrast-enhanced MRI (DCE-MRI) before CCRT. The biopsy tissues and serum samples were collected. The differential expression of miRNA in the biopsy tissues was determined by microarray chip. The expression level of miR-143 in the serum samples was analyzed by qRT-PCR. All patients were divided into the non-residual and residual tumor groups according to post-treatment MRI. Pre-treatment clinical factors, MRI parameters and miR-143 between two groups were statistically analyzed by the univariate and multivariate analyses. The optimal thresholds and predictive performance for post-treatment incidence of residual tumors were estimated by drawing the ROC curve.Results:At one month after CCRT, there were 52 patients in the non-residual tumor group and 33 patients in the residual tumor group. In the residual tumor group, pre-treatment FIGO staging, apparent diffusion coefficient (ADC), D and V e were significantly higher (all P<0.05), whereas K trans value was significantly lower ( P<0.001) when compared to those in the non-residual tumor group. The miRNA array analysis showed that there were 16 miRNAs with differential expression levels between two groups (all P<0.05). Among them, the increase of miR-143 was the most significant in the residual tumor group. Compared with the residual tumor group, the expression level of serum miR-143 was significantly down-regulated in the non-residual tumor group ( P=0.002). Compared with the SiHa cells, the expression level of miR-143 in the SiHa-R cells was significantly up-regulated ( P<0.05). Multivariate analysis showed that only miR-143, D, K trans and V e were the independent prognostic factors. The combination of multi-parametric MRI and miR-143 exhibited the highest predictive performance (AUC=0.975), with a sensitivity of 84.8% and a specificity of 96.2%. Conclusion:The combination of multi-parametric MRI with miR-143 further improves the predictive performance for residual tumors after CCRT, which contributes to the personalized treatment of cervical cancer.
RESUMEN
Coronavirus disease 2019 (COVID-19) has spread globally, and medical resources become insufficient in many regions. Fast diagnosis of COVID-19, and finding high-risk patients with worse prognosis for early prevention and medical resources optimization is important. Here, we proposed a fully automatic deep learning system for COVID-19 diagnostic and prognostic analysis by routinely used computed tomography. We retrospectively collected 5372 patients with computed tomography images from 7 cities or provinces. Firstly, 4106 patients with computed tomography images and gene information were used to pre-train the DL system, making it learn lung features. Afterwards, 1266 patients (924 with COVID-19, and 471 had follow-up for 5+ days; 342 with other pneumonia) from 6 cities or provinces were enrolled to train and externally validate the performance of the deep learning system. In the 4 external validation sets, the deep learning system achieved good performance in identifying COVID-19 from other pneumonia (AUC=0.87 and 0.88) and viral pneumonia (AUC=0.86). Moreover, the deep learning system succeeded to stratify patients into high-risk and low-risk groups whose hospital-stay time have significant difference (p=0.013 and 0.014). Without human-assistance, the deep learning system automatically focused on abnormal areas that showed consistent characteristics with reported radiological findings. Deep learning provides a convenient tool for fast screening COVID-19 and finding potential high-risk patients, which may be helpful for medical resource optimization and early prevention before patients show severe symptoms. Take-home messageFully automatic deep learning system provides a convenient method for COVID-19 diagnostic and prognostic analysis, which can help COVID-19 screening and finding potential high-risk patients with worse prognosis.
RESUMEN
Objective:To investigate the imaging and pathology features of rosette-forming glioneuronal tumor (RGNT).Methods:From January 2010 to September 2019, 7 patients with pathologically conformed RGNT in our hospital were chosen, the imaging findings were analyzed retrospectively and compared with corresponding pathological features.Results:Six patients showed single lesion: 4 located in the vermis and its surrounding areas, in which 2 involved the pineal region and the tectum; the other 2 lesions located in the fourth ventricle. One patient had multiple lesions, which located in the third ventricle and the lateral ventricle respectively. Cystic-solid masses mainly with cystic changes were noted in these 7 patients, lesions in the vermis of cerebellum and its surrounding areas were polycystic while lesions in the ventricles were single cystic. The cystic areas of masses showed low density on plain CT scan and slightly long T 1 and long T 2 signal on MR imaging. The imaging findings were compared with the pathological findings: the density/signal changes were corresponded to the cystoid changes, hemorrhage and calcification, as seen in the postoperative specimens; the signal changes of the cystic areas were corresponded to the mucus matrix components and old hemorrhage; the characteristics of tumor enhancement were closely related to the distribution of solid components and degrees of blood supply. Conclusion:The imaging features of RGNT may partly reflect its pathological manifestations; combined with the specific location, imaging examinations may help make a correct preoperative diagnosis.
RESUMEN
Objective:To explore the application value of three dimensional T 1 weighted sampling perfection with application-optimized contrasts by using different flip angle evolutions (3D T 1-SPACE) combined with three dimensional time of flight MR angiography (3D-TOF MRA) in the follow-up of stent-assisted coil embolization for intracranial aneurysm. Methods:From December 2017 to October 2018, 25 patients with intracranial aneurysm who underwent stent-assisted coil embolization in Henan Provincial People′s Hospital were enrolled. All of them had wide neck intracranial aneurysms and were followed up for 6 to 10 months after endovascular treatment using 3D-TOF MRA, 3D T 1-SPACE sequence and DSA. The DSA and 3D-TOF MRA were performed to evaluate aneurysm remnants using Raymond grade scale. Meanwhile, 3D-TOF MRA and 3D T 1-SPACE sequence were performed to evaluate in-stent lumen visibility using the 4-point scale. The paired sample Wilcoxon test was used to evaluate the aneurysm remnants and the parent artery patency. DSA was used as the gold standard to calculate the specificity and accuracy of the aneurysm remnants evaluated by 3D-TOF MRA. Results:Six to ten months′ follow up after the procedure, for aneurysm occlusion, the Raymond grade scale of the 25 patients evaluated by DSA indicated grade 1 in 23 patients, 2 in 1 and 3 in 1. For patients evaluated by 3D-TOF MRA, the results demonstrated grade 1 in 21 patients, 2 in 3 and 3 in 1. There was no difference between the 2 methods ( Z=-0.557, P=0.577). The in-stent lumens of parent vessel evaluated by 3D-TOF MRA showed that there were 14 patients with grade 3, 8 patients with grade 2 and 3 patients with grade 1. However, 3D T 1-SPACE demonstrated that all 25 patients were grade 4. The 3D T 1-SPACE was superior to evaluate the in-stent lumens than 3D-TOF MRA ( Z=-4.484, P<0.001). Taking DSA as standard, the specificity and accuracy of the aneurysm remnants evaluated by 3D-TOF MRA were 86.9% (20/23) and 84.0% (21/25), respectively. Conclusion:3.0 T 3D T 1-SPACE MR sequence can be used to assess parent artery patency, with in-stent lumen being clearly visible. 3D-TOF MRA can evaluate intracranial aneurysm remnants. The combination of these two MRI imaging techniques can be used as an optional follow-up evaluation after the endovascular treatment of intracranial aneurysms.
RESUMEN
Objective:To explore the value of mammography-based radiomics for preoperative prediction of axillary lymph node metastasis in breast carcinoma.Methods:The clinical and X-ray data of female patients with pathologically confirmed breast cancer in Henan People′s Hospital from June 2013 to July 2017 were analyzed retrospectively. A total of 214 patients, aged 30-85 (53±11) years, were randomly divided into training set ( n=153) and verification set ( n=61) according to the ratio of 3∶1. According to pathological findings of the axillary lymph node metastasis, 99 cases were divided into positive group and 115 cases into negative group. The lesions were segmented and extracted in X-ray images of mediolateral oblique (MLO) and cranial caudal (CC). Three, nine and seven axillary lymph node metastasis related histologic features were selected from the high dimensional features of CC, MLO and CC combined MLO images by lasso regression model. According to the characteristics of imaging and clinical characteristics, the prediction model was constructed. The prediction ability of the model was verified by 10% cross validation. Results:The lymph node in positive group was larger than negative groups, the difference was statistically significant ( t=2.611, P<0.05). In the validation set, the area under curve (AUC) values of CC, MLO, CC combined with MLO images, clinical features and clinical features combined with CC and MLO images were 0.680, 0.723, 0.740, 0.558 and 0.714, respectively. Among them, CC combined with MLO images had the highest prediction efficiency, and AUC values were higher than CC alone, MLO images and CC combined with MLO images. Conclusions:Quantitative radiomics features of breast tumor extracted from digital mammograms are helpful for preoperatively predicting axillary lymph node metastasis. Future larger studies are needed to further evaluate these findings.
RESUMEN
Objective:To explore the value of radiomics features extracted from multi-parameter MRI (mp-MRI) in preoperative prediction of triple negative breast cancer (TNBC) and non triple negative breast cancer (NTNBC).Methods:The clinical and preoperative-MRI data of 371 patients with breast cancer confirmed by surgical pathology from January 2017 to July 2019 in Henan Provincial People′s Hospital were retrospectively analyzed. Based on the results of immunohistochemistry (IHC) and fluorescence in situ hybridization (FISH) from postoperative pathological specimens, the cancer was classified as TNBC and NTNBC. Patients were randomly assigned to a training set ( n=250) and a validation set ( n=121). Quantitative radiomics features were extracted from three-dimensional lesions based on dynamic contrast enhanced-T 1WI (DCE-T 1WI) and fat-suppressed T 2WI sequences, and 32 quantitative radiomics features were selected by Mann-Whitney U test, elastic network, and support vector machine recursive feature elimination. Three radiomics signatures were constructed by using the algorithm of support vector machine based on the quantitative radiomics features extracted from fat-suppressed T 2WI, DCE-T 1WI and the mp-MRI of their combination. The prediction performances were evaluated by receiver operating characteristic (ROC) curve and the area under the ROC curve, accuracy, sensitivity, and specificity were calculated. Results:There were 61 patients with TNBC and 310 patients with NTNBC. The clinicopathological characteristics between NTNBC and TNBC were statistically different in the pathological grade (χ2=24.544, P<0.001). Other clinicopathological characteristics (age, maximum diameter of mass, vascular tumor thrombus, axillary lymph nodes) were not statistically differences between NTNBC and TNBC ( P>0.05). The radiomics signature presenting the best performance for predictive TNBC and NTNBC were based on mp-MRI radiomics features. The area under the ROC curve, accuracy, sensitivity, and specificity were 0.91[95% confidence interval (CI) 0.881-0.932], 86.0%, 84.4% and 86.3% in training set, and 0.84 (95%CI 0.807-0.868), 75.2%, 68.7% and 76.1%, in validation set, respectively. Conclusion:Radiomics based on mp-MRI features can be a effectively potential tool for predictive TNBC and NTNBC breast cancer and provide scientific basis for clinicians to make treatment decisions.
RESUMEN
No abstract available.
Asunto(s)
Stents Liberadores de Fármacos , Stents , Arteria Vertebral , Insuficiencia VertebrobasilarRESUMEN
Objective To investigate the safety of endovascular thrombectomy in acute ischemic stroke patients with pre-existing intracranial aneurysms. Methods Seven patients with acute ischemic stroke combined with intracranial aneurysms, admitted to and received endovascular treatment in our hospital from January 2014 to December 2016, were chosen. The clinical data and safety were analyzed retrospectively. Results All patients with pre-existing intracranial aneurysms suffered acute large artery occlusion achieved successful endovascular re-canalization, and one patient suffered subarachnoid hemorrhage due to the rupture of aneurysm during the procedure. Three patients had grading 2b of Thrombolysis in Cerebral Infarction (TICI), and 4 had grading 3 of TICI. Four patients had 0-2 scores of modified Rankin Scale (mRS), one had 3 scores, and two died. Conclusion Endovascular thrombectomy in acute ischemic stroke patients with pre-existing intracranial aneurysms is safe.
RESUMEN
Objective To explore the value of various diffusion parameters obtained from monoexponential, biexponential and stretched exponential diffusion-weighted imaging models in assessing hepatic fibrosis in chronic hepatitis B(CHB). Methods A total of 52 patients who were diagnosed hepatitis B by the markers of hepatitis and were confirmed by liver biopsy pathology were prospectively recruited between June 2014 and May 2016 in People's Hospital of Henan Province. Concomitantly, 30 healthy volunteers who had no history of hepatitis B and liver dysfunction were enrolled in the control group. All patients underwent multi-b values DWI on a 3.0 T MRI unit. ADC was calculated by using the monoexponential model. True diffusion coefficient(Dt),pseudo diffusion coefficient(Dp)and fraction of perfusion(f)were calculated by using the biexponential model.Distributed diffusion coefficient(DDC)and water molecular diffusion heterogeneity index(α)were calculated by using the stretched exponential model. Liver biopsy specimens were staged according to the degree of hepatic fibrosis (S0 to S4). The Kruskal-Wallis test was employed for the comparison of each parameter among the control group and the fibrosis stage groups. The Mann-Whitney U test was adopted to compare each parameter between fibrosis stage≤S1and≥S2,between≤S2 and≥S3.Spearman rank correlation coefficients were obtained to assess the correlation of the parameters with the fibrosis stages.ROC analysis was used to evaluate the performance of various parameters in predicting stage≥S2 and≥S3.Results The hepatic fibrosis stage distributions were as follows:1 cases with S0,9 cases with S1,22 cases with S2,11 cases with S3,9 cases with S4.ADC,Dt,f and DDC values all showed significant difference among the control group and groups S1,S2,S3,S4(all P<0.05), while Dp and α values showed no significant difference(P>0.05). Dt, DDC and ADC showed a moderate negative correlation with the fibrosis stage(r=-0.630,-0.603 and-0.464,respectively,all P<0.01),and f showed a mild negative correlation with the fibrosis stage(r=-0.379,P<0.05),while Dp and α values showed no correlation with the fibrosis stages(all P>0.05).The ADC, Dt, f and DDC values all showed significant difference between stage≥S2 and≤S1,between stage≥S3 and≤S2(all P<0.05),and the parameter values of the former were greater than those of the latter. While Dp and α values showed no significant difference among both groups(all P>0.05).The AUCs of ADC,Dt,f and DDC values for detecting fibrosis stage ≥S2 were 0.738,0.835,0.740 and 0.831, and the AUCs of ADC, Dt, f and DDC values for detecting fibrosis stage≥S3 were 0.716, 0.811, 0.672 and 0.798. Conclusion The Dt derived from biexponential and DDC derived from stretched exponential DWI could be useful for the staging of hepatic fibrosis in CHB.