Differences in Clinical and Imaging Features between Asymptomatic and Symptomatic COVID-19 Patients.

Objectives: The clinical and imaging features of asymptomatic carriers of severe acute respiratory syndrome coronavirus 2 and symptomatic COVID-19 patients. Methods: The clinical and chest computed tomography imaging data of 47 asymptomatic carriers and 36 symptomatic COVID-19 patients were derived. All patients underwent 4-6 CT scans over a period of 2-5 days. Results: The bulk of asymptomatic carriers who developed symptoms and most of the COVID-19 patients were older than 18 years of age with a decreased lymphocyte count, abnormal hepatic and renal function, and increased D-dimer and C-reactive protein. In the early stage, the pulmonary lesion involved mostly 1-2 lobes at the peripheral area in asymptomatic carriers but more than three lobes at both the central and peripheral areas in COVID-19 patients. In the progression stage, the lesion of asymptomatic carriers extended from the peripheral to the central area, and no significant difference was found in the lesion range compared with the symptomatic control group. In early improvement stage, the lesion was rapidly absorbed, and lesions were located primarily at the peripheral area in asymptomatic carriers; contrastingly, lesions were primarily located at both the central and peripheral areas in symptomatic patients. Asymptomatic carriers reflected a significantly shorter duration from disease onset to peak progression stage compared with the symptomatic. Conclusions: Asymptomatic carriers are a potential source of transmission and may become symptomatic COVID-19 patients despite indicating less severe pulmonary damage, earlier improvement, and better prognosis. Early isolation and intervention can eliminate such carriers as potential sources of transmission and improve their prognosis.

Clinical effect of different maintenance doses of caffeine citrate in the treatment of preterm infants requiring assisted ventilation: a pilot multicenter study. / ä¸åŒç»´æŒå‰‚é‡æž¸æ©¼é ¸å’–å•¡å› å¯¹è¾ åŠ©é€šæ°”æ—©äº§å„¿çš„ç–—æ•ˆè¯„ä¼°ï¼šä¸€é¡¹åˆæ­¥å¤šä¸­å¿ƒç ”ç©¶.

OBJECTIVES: To explore the optimal maintenance dose of caffeine citrate for preterm infants requiring assisted ventilation and caffeine citrate treatment. METHODS: A retrospective analysis was performed on the medical data of 566 preterm infants (gestational age ≤34 weeks) who were treated and required assisted ventilation and caffeine citrate treatment in the neonatal intensive care unit of 30 tertiary hospitals in Jiangsu Province of China between January 1 and December 31, 2019. The 405 preterm infants receiving high-dose (10 mg/kg per day) caffeine citrate after a loading dose of 20 mg/kg within 24 hours after birth were enrolled as the high-dose group. The 161 preterm infants receiving low-dose (5 mg/kg per day) caffeine citrate were enrolled as the low-dose group. RESULTS: Compared with the low-dose group, the high-dose group had significant reductions in the need for high-concentration oxygen during assisted ventilation (P=0.044), the duration of oxygen inhalation after weaning from noninvasive ventilation (P<0.01), total oxygen inhalation time during hospitalization (P<0.01), the proportion of preterm infants requiring noninvasive ventilation again (P<0.01), the rate of use of pulmonary surfactant and budesonide (P<0.05), and the incidence rates of apnea and bronchopulmonary dysplasia (P<0.01), but the high-dose group had a significantly increased incidence rate of feeding intolerance (P=0.032). There were no significant differences between the two groups in the body weight change, the incidence rates of retinopathy of prematurity, intraventricular hemorrhage or necrotizing enterocolitis, the mortality rate, and the duration of caffeine use (P>0.05). CONCLUSIONS: This pilot multicenter study shows that the high maintenance dose (10 mg/kg per day) is generally beneficial to preterm infants in China and does not increase the incidence rate of common adverse reactions. For the risk of feeding intolerance, further research is needed to eliminate the interference of confounding factors as far as possible.

Curcumin targets vascular endothelial growth factor via activating the PI3K/Akt signaling pathway and improves brain hypoxic-ischemic injury in neonatal rats.

This study aimed to evaluate the effect of curcumin on brain hypoxicischemic (HI) damage in neonatal rats and whether the phosphoinositide 3-kinase (PI3K)/Akt/vascular endothelial growth factor (VEGF) signaling pathway is involved. Brain HI damage models were established in neonatal rats, which received the following treatments: curcumin by intraperitoneal injection before injury, insulin-like growth factor 1 (IGF-1) by subcutaneous injection after injury, and VEGF by intracerebroventricular injection after injury. This was followed by neurological evaluation, hemodynamic measurements, histopathological assessment, TUNEL assay, flow cytometry, and western blotting to assess the expression of p-PI3K, PI3K, p-Akt, Akt, and VEGF. Compared with rats that underwent sham operation, rats with brain HI damage showed remarkably increased neurological deficits, reduced right blood flow volume, elevated blood viscosity and haematocrit, and aggravated cell damage and apoptosis; these injuries were significantly improved by curcumin pretreatment. Meanwhile, brain HI damage induced the overexpression of p-PI3K, p-Akt, and VEGF, while curcumin pretreatment inhibited the expression of these proteins. In addition, IGF-1 treatment rescued the curcumin-induced down-regulated expression of p- PI3K, p-Akt, and VEGF, and VEGF overexpression counteracted the inhibitory effect of curcumin on brain HI damage. Overall, pretreatment with curcumin protected against brain HI damage by targeting VEGF via the PI3K/Akt signaling pathway in neonatal rats.

Application value of three-dimensional arterial spin labeling perfusion imaging in investigating cerebral blood flow dynamics in normal full-term neonates.

BACKGROUND: This study aims to investigate the application value of three-dimensional arterial spin labeling (3DASL) in investigating cerebral blood flow dynamics in full-term neonates. METHODS: A total of 60 full-term neonates without known intracranial pathology were recruited for 3DASL examination. These neonates were divided into three groups: 1-3 day group, 4-7 day group, and 8-15 day group. On the cerebral blood flow (CBF) images, regions of interest (ROI) were selected from the frontal white matter, parietal white matter, basal ganglia, corona radiata, thalamus and brainstem, and the CBF values of each ROI were recorded. The CBF values of ROIs at bilaterally symmetric locations, the values of each ROI between males and females, and the values of each ROI among these three different age groups were compared. RESULTS: The difference in CBF values of the frontal white matter, parietal white matter, basal ganglia, corona radiata and thalamus at the bilateral symmetric positions were not statistically significant. There was no statistical difference in the CBF values of each brain region between the male and female groups. The CBF values at the basal ganglia region, corona radiata and parietal white matter were higher in the 8-15 day group, when compared to the 1-3 day and 4-7 day groups (P < 0.05). The CBF value at the basal ganglia region was higher in the 4-7 day group, when compared to the 1-3 day group (P < 0.05). The CBF value at the frontal white matter was lower in the 4-7 day group, when compared to the 1-3 day and 8-15 day group (P < 0.05). The CBF value at the brainstem was higher in the 4-7 day group, when compared to the 1-3 day and 8-15 day groups (P < 0.05). CONCLUSION: The 3DASL can quantitatively measure CBF, and be used to evaluate cerebral hemodynamics in neonates. The basal ganglia region and corona radiata CBF increases with the increase in neonatal diurnal age.

Perfusion Computer Tomography Assessment of the Effect of Angiotensin II On Blood Flow Distribution in Rabbits with Intrarenal VX2 Tumors.

BACKGROUND/AIMS: Unlike other organs, which only have one set of capillary network, the renal microvasculature consists of two sets of capillary network series connected by efferent arterioles. Angiotensin II constricts the efferent glomerular artery. Hence, renal tumor blood flow (BF) distribution may be different from tumors in other organs. This study aims to investigate the effects of angiotensin II on the hemodynamics of intrarenal VX2 tumors using perfusion computed tomography(CT). METHODS: Twenty-four male New Zealand white rabbits were randomly divided into three groups: groups A (blank controls), group B (negative controls), and group C (angiotensin II-treated animals). Group B and C were established to the model of intrarenal VX2 tumors. Furthermore, perfusion CT of the kidney was performed in each group. Prior to perfusion CT scan in group C, the mean arterial blood was elevated to 150-160 mmHg by angiotensin II. The BF, blood volume (BV), mean transit time (MTT), capillary permeability-surface area product (PS), and relative permeability-surface area product (RPS) of tumors and renal tissues were calculated. RESULTS: Compared with normal renal cortex tissues in group A, the BF, BV and PS values of tumors in group B were significantly lower, MTT was prolonged and RPS increased. Compared with group B, only the RPS of these tumors increased from 83.23 ± 29.17% to 120.94 ± 31.84% by angiotensin II infusion. Angiotensin II significantly increased the RPS value of the renal cortex distant from the tumor (CDT) and the right renal cortex (RRC). CONCLUSIONS: Perfusion CT can accurately observe the influence of angiotensin II on normal and tumor BF in kidneys. This clarifies the effect of angiotensin II on intrarenal tumor hemodynamics.

δ Subunit-containing GABAA receptor prevents overgeneralization of fear in adult mice.

The role of δ subunit-containing GABAA receptor (GABAA(δ)R) in fear generalization is uncertain. Here, by using mice with or without genetic deletion of GABAA(δ)R and using protocols in which the conditioned tone stimuli were cross presented with different nonconditioned stimuli, we observed that when the two tone stimuli were largely similar, both genotypes froze similarly to either of them. However, when they differed markedly, the knockout mice froze much more than their wild-type littermates to the nonconditioned but not conditioned stimuli. Thus, GABAA(δ)R may prevent inappropriate fear generalization when the incoming stimuli differ clearly from the learned threat.

Gaining and sustaining schistosomiasis control: study protocol and baseline data prior to different treatment strategies in five African countries.

BACKGROUND: The Schistosomiasis Consortium for Operational Research and Evaluation (SCORE) was established in 2008 to answer strategic questions about schistosomiasis control. For programme managers, a high-priority question is: what are the most cost-effective strategies for delivering preventive chemotherapy (PCT) with praziquantel (PZQ)? This paper describes the process SCORE used to transform this question into a harmonized research protocol, the study design for answering this question, the village eligibility assessments and data resulting from the first year of the study. METHODS: Beginning in 2009, SCORE held a series of meetings to specify empirical questions and design studies related to different schedules of PCT for schistosomiasis control in communities with high (gaining control studies) and moderate (sustaining control studies) prevalence of Schistosoma infection among school-aged children. Seven studies are currently being implemented in five African countries. During the first year, villages were screened for eligibility, and data were collected on prevalence and intensity of infection prior to randomisation and the implementation of different schemes of PZQ intervention strategies. RESULTS: These studies of different treatment schedules with PZQ will provide the most comprehensive data thus far on the optimal frequency and continuity of PCT for schistosomiasis infection and morbidity control. CONCLUSIONS: We expect that the study outcomes will provide data for decision-making for country programme managers and a rich resource of information to the schistosomiasis research community. TRIAL REGISTRATION: The trials are registered at International Standard Randomised Controlled Trial registry (identifiers: ISRCTN99401114 , ISRCTN14849830 , ISRCTN16755535 , ISRCTN14117624 , ISRCTN95819193 and ISRCTN32045736 ).

Orthostatic hypotension and right heart failure as the initial manifestation of intravenous leiomyomatosis.

A 36-year-old woman, who had a history of myomectomy, presented with lightheadedness after changing position from sitting to standing and effort-related shortness of breath. Echocardiography demonstrated a hyperechoic elongated mobile mass extending from the inferior caval vein to the right atrium. The mass was surgically removed, and histological examination established the diagnosis of intravenous leiomyomatosis. This case caught the attention of our cardiology group to consider the diagnosis when an inferior caval vein or right atrium mass is found in a patient with a history of uterine leiomyomatosis.

Efficacy and Safety of Gabapentin vs. Carbamazepine in the Treatment of Trigeminal Neuralgia: A Meta-Analysis.

To evaluate the safety and efficacy of gabapentin in comparison with carbamazepine in the treatment of trigeminal neuralgia, a meta-analysis of randomized controlled trials was performed. Two reviewers independently selected studies, assessed study quality, and extracted data. Sixteen randomized controlled trials that included 1,331 patients were assessed. The meta-analysis showed that the total effective rate of gabapentin therapy group was similar with carbamazepine therapy group (OR = 1.600, 95% CI 1.185, 2.161, P = 0.002). While the effective rate of gabapentin therapy for 4 weeks was higher than that of carbamazepine therapy (OR = 1.495, 95% CI 1.061, 2.107, P = 0.022, heterogeneity: x2 = 7.12, P = 0.625, I2 = 0.0%), the life satisfaction improvement is also better in the gabapentin therapy group after a 4-week treatment (SMD = 0.966, 95% CI 0.583, 1.348, P < 0.001). Furthermore, our meta-analysis suggested that the adverse reaction rate of gabapentin therapy group was significantly lower than that of carbamazepine therapy group (OR = 0.312, 95% CI 0.240, 0.407, P < 0.001). In conclusion, present trials comparing gabapentin with carbamazepine are all poor in terms of methodological quality. Based on the available evidence, it is not possible to draw conclusions regarding the efficacy and side effects of gabapentin being superior to carbamazepine.

Catalytic functionalization of tertiary alcohols to fully substituted carbon centres.

The catalytic nucleophilic substitution of tertiary alcohols using carbon or heteroatom based nucleophiles is a versatile methodology for the efficient, diverse and atom economical construction of fully substituted carbon centres, including both quaternary carbons and heteroatom substituted tetrasubstituted carbons, which only produces water as the by-product. This review summarizes the recent progress in this field, including the catalytic asymmetric studies and their application in the natural product synthesis, briefly discusses the reaction mechanism and challenges, and outlines synthetic opportunities that are still open.

Asymmetric triple relay catalysis: enantioselective synthesis of spirocyclic indolines through a one-pot process featuring an asymmetric 6π electrocyclization.

A rare example of a one-pot process that involves asymmetric triple relay catalysis is reported. The key step is an asymmetric [1,5] electrocyclic reaction of functionalized ketimines. The substrates for this process were obtained in situ in a two-step process that involved the hydrogenation of nitroarenes with a Pd/C catalyst to yield aryl amines and their subsequent coupling with isatin derivatives in a Brønsted acid catalyzed ketimine formation reaction. The electrocyclization was catalyzed by a bifunctional chiral Brønsted base/hydrogen bond donor catalyst. The one-pot process gave the desired products in good yields and with excellent enantioselectivity.

Moyamoya syndrome may result from psoriasis: Four case reports.

BACKGROUND: Moyamoya syndrome (MMS) is a group of diseases that involves more than one underlying disease and is accompanied by moyamoya vascular phenomena. Psoriasis is a chronic immune skin disease closely linked to high blood pressure and heart disease. However, psoriasis-related MMS has not been reported. CASE SUMMARY: We collected data on patients with stroke due to MMS between January 2017 and December 2019 and identified four cases of psoriasis. Case histories, imaging, and hematological data were collected. The average age of the initial stroke onset was 58.25 ± 11.52 years; three cases of hemorrhagic and one case of ischemic stroke were included. The average duration from psoriasis confirmation to the initial MMS-mediated stroke onset was 17 ± 3.56 years. All MMS-related stenoses involved the bilateral cerebral arteries: Suzuki grade III in one case, grade IV in two cases, and grade V in one case. Abnormally elevated plasma interleukin-6 levels were observed in four patients. Two patients had abnormally elevated immunoglobulin E levels, and two had thrombocytosis. All four patients received medication instead of surgery. With an average follow-up time of 2 years, two causing transient ischemic attacks occurred in two patients, and no hemorrhagic events occurred. CONCLUSION: Psoriasis may be a potential risk factor for MMS. Patients with psoriasis should be screened for MMS when they present with neurological symptoms.

Use of MRI Radiomics Models in Evaluating the Low HER2 Expression in Breast Cancer.

OBJECTIVE: To investigate the magnetic resonance imaging (MRI) radiomics models in evaluating the human epidermal growth factor receptor 2(HER2) expression in breast cancer.

Materials and Methods: The MRI data of 161 patients with invasive ductal carcinoma (non-special type) of breast cancer were retrospectively collected, and the MRI radiomics models were established based on the MRI imaging features of the fat suppression T2 weighted image (T2WI) sequence, dynamic contrast-enhanced (DCE)-T1WIsequence and joint sequences. The T-test and the least absolute shrinkage and selection operator (LASSO) algorithm were used for feature dimensionality reduction and screening, respectively, and the random forest (RF) algorithm was used to construct the classification model.

Results: The model established by the LASSO-RF algorithm was used in the ROC curve analysis. In predicting the low expression state of HER2 in breast cancer, the radiomics models of the fat suppression T2WI sequence, DCE-T1WI sequence, and the combination of the two sequences showed better predictive efficiency. In the receiver operating characteristic (ROC) curve analysis for the verification set of low, negative, and positive HER2 expression, the area under the ROC curve (AUC) value was 0.81, 0.72, and 0.62 for the DCE-T1WI sequence model, 0.79, 0.65 and 0.77 for the T2WI sequence model, and 0.84, 0.73 and 0.66 for the joint sequence model, respectively. The joint sequence model had the highest AUC value.

Conclusions: The MRI radiomics models can be used to effectively predict the HER2 expression in breast cancer and provide a non-invasive and early assistant method for clinicians to formulate individualized and accurate treatment plans.

Optimizing the image quality of peripancreatic blood vessels through the clinical application of single-energy spectral computed tomography (CT) imaging.

Background: With the increase of pancreatic tumor patients in recent years, there is an urgent need to find a way to treat pancreatic tumors. Surgery is one of the best methods for the treatment of pancreatic tumors, the success of which depends on the evaluation of peripancreatic vessels before surgery. Computed tomography (CT), as a non-invasive, fast, and economical auxiliary examination method, is undoubtedly one of the best means of clinical auxiliary examination. In this study, we investigated the impact of single-energy spectral CT imaging on the image quality of peripancreatic blood vessels and the clinical value of low-keV imaging in enhancing the image quality of peripancreatic arteriovenous vessels. Methods: We prospectively enrolled 103 patients who underwent abdominal vascular-enhanced CT examinations at the Affiliated Hospital of Hebei University between December 2022 and May 2023 and who were all scanned with the dual-energy feature on the United Imaging ATLAS scanner. The images were reconstructed at 70 keV, mixed energy, and optimized single energy in the post-processing station of United Imaging Healthcare Technology Co., Ltd. The CT value and contrast-to-noise ratio (CNR) of the superior mesenteric artery (SMA), gastroduodenal artery (GDA), inferior pancreaticoduodenal artery (IPDA), and superior mesenteric vein (SMV) were compared across energy levels, and then the image quality was subjectively evaluated. One-way analysis of variance and rank-sum tests were utilized for the statistical analysis. Results: The CT values of SMA, GDA, IPDA, and SMV in the optimal single energy group were 358.37±70.24, 323.36±88.23, 300.76±76.27, and 257.74±20.56 Hounsfield unit (HU), respectively, which were superior to those in the mixed energy (241.66±47.69, 235.17±53.71, 207.36±45.17, and 187.39±23.21 HU) and 70 keV groups (260.89±54.27, 252.41±58.87, 223.17±43.65, and 203.18±18.17 HU) (P<0.05). The diagnostic efficacy was greater in the optimal single energy group than in the other 2 groups (4.63±0.50, 3.91±0.57, and 4.23±0.83) (P<0.05). Conclusions: The optimal single energy for showing peripancreatic blood vessels is 62±7 keV when utilizing single-energy spectral CT imaging.

Predicting Risk Stratification in Early-Stage Endometrial Carcinoma: Significance of Multiparametric MRI Radiomics Model.

Endometrial carcinoma (EC) risk stratification prior to surgery is crucial for clinical treatment. In this study, we intend to evaluate the predictive value of radiomics models based on magnetic resonance imaging (MRI) for risk stratification and staging of early-stage EC. The study included 155 patients who underwent MRI examinations prior to surgery and were pathologically diagnosed with early-stage EC between January, 2020, and September, 2022. Three-dimensional radiomics features were extracted from segmented tumor images captured by MRI scans (including T2WI, CE-T1WI delayed phase, and ADC), with 1521 features extracted from each of the three modalities. Then, using five-fold cross-validation and a multilayer perceptron algorithm, these features were filtered using Pearson's correlation coefficient to develop a prediction model for risk stratification and staging of EC. The performance of each model was assessed by analyzing ROC curves and calculating the AUC, accuracy, sensitivity, and specificity. In terms of risk stratification, the CE-T1 sequence demonstrated the highest predictive accuracy of 0.858 ± 0.025 and an AUC of 0.878 ± 0.042 among the three sequences. However, combining all three sequences resulted in enhanced predictive accuracy, reaching 0.881 ± 0.040, with a corresponding increase in the AUC to 0.862 ± 0.069. In the context of staging, the utilization of a combination involving T2WI with CE-T1WI led to a notably elevated predictive accuracy of 0.956 ± 0.020, surpassing the accuracy achieved when employing any singular feature. Correspondingly, the AUC was 0.979 ± 0.022. When incorporating all three sequences concurrently, the predictive accuracy reached 0.956 ± 0.000, accompanied by an AUC of 0.986 ± 0.007. It is noteworthy that this level of accuracy surpassed that of the radiologist, which stood at 0.832. The MRI radiomics model has the potential to accurately predict the risk stratification and early staging of EC.

Quantitative radiomics analysis of imaging features in adults and children Mycoplasma pneumonia.

Purpose: This study aims to explore the value of clinical features, CT imaging signs, and radiomics features in differentiating between adults and children with Mycoplasma pneumonia and seeking quantitative radiomic representations of CT imaging signs. Materials and methods: In a retrospective analysis of 981 cases of mycoplasmal pneumonia patients from November 2021 to December 2023, 590 internal data (adults:450, children: 140) randomly divided into a training set and a validation set with an 8:2 ratio and 391 external test data (adults:121; children:270) were included. Using univariate analysis, CT imaging signs and clinical features with significant differences (p < 0.05) were selected. After segmenting the lesion area on the CT image as the region of interest, 1,904 radiomic features were extracted. Then, Pearson correlation analysis (PCC) and the least absolute shrinkage and selection operator (LASSO) were used to select the radiomic features. Based on the selected features, multivariable logistic regression analysis was used to establish the clinical model, CT image model, radiomic model, and combined model. The predictive performance of each model was evaluated using ROC curves, AUC, sensitivity, specificity, accuracy, and precision. The AUC between each model was compared using the Delong test. Importantly, the radiomics features and quantitative and qualitative CT image features were analyzed using Pearson correlation analysis and analysis of variance, respectively. Results: For the individual model, the radiomics model, which was built using 45 selected features, achieved the highest AUCs in the training set, validation set, and external test set, which were 0.995 (0.992, 0.998), 0.952 (0.921, 0.978), and 0.969 (0.953, 0.982), respectively. In all models, the combined model achieved the highest AUCs, which were 0.996 (0.993, 0.998), 0.972 (0.942, 0.995), and 0.986 (0.976, 0.993) in the training set, validation set, and test set, respectively. In addition, we selected 11 radiomics features and CT image features with a correlation coefficient r greater than 0.35. Conclusion: The combined model has good diagnostic performance for differentiating between adults and children with mycoplasmal pneumonia, and different CT imaging signs are quantitatively represented by radiomics.

Comparison of Machine Learning Models Using Diffusion-Weighted Images for Pathological Grade of Intrahepatic Mass-Forming Cholangiocarcinoma.

Is the radiomic approach, utilizing diffusion-weighted imaging (DWI), capable of predicting the various pathological grades of intrahepatic mass-forming cholangiocarcinoma (IMCC)? Furthermore, which model demonstrates superior performance among the diverse algorithms currently available? The objective of our study is to develop DWI radiomic models based on different machine learning algorithms and identify the optimal prediction model. We undertook a retrospective analysis of the DWI data of 77 patients with IMCC confirmed by pathological testing. Fifty-seven patients initially included in the study were randomly assigned to either the training set or the validation set in a ratio of 7:3. We established four different classifier models, namely random forest (RF), support vector machines (SVM), logistic regression (LR), and gradient boosting decision tree (GBDT), by manually contouring the region of interest and extracting prominent radiomic features. An external validation of the model was performed with the DWI data of 20 patients with IMCC who were subsequently included in the study. The area under the receiver operating curve (AUC), accuracy (ACC), precision (PRE), sensitivity (REC), and F1 score were used to evaluate the diagnostic performance of the model. Following the process of feature selection, a total of nine features were retained, with skewness being the most crucial radiomic feature demonstrating the highest diagnostic performance, followed by Gray Level Co-occurrence Matrix lmc1 (glcm-lmc1) and kurtosis, whose diagnostic performances were slightly inferior to skewness. Skewness and kurtosis showed a negative correlation with the pathological grading of IMCC, while glcm-lmc1 exhibited a positive correlation with the IMCC pathological grade. Compared with the other three models, the SVM radiomic model had the best diagnostic performance with an AUC of 0.957, an accuracy of 88.2%, a sensitivity of 85.7%, a precision of 85.7%, and an F1 score of 85.7% in the training set, as well as an AUC of 0.829, an accuracy of 76.5%, a sensitivity of 71.4%, a precision of 71.4%, and an F1 score of 71.4% in the external validation set. The DWI-based radiomic model proved to be efficacious in predicting the pathological grade of IMCC. The model with the SVM classifier algorithm had the best prediction efficiency and robustness. Consequently, this SVM-based model can be further explored as an option for a non-invasive preoperative prediction method in clinical practice.

Efficiency of CT radiomics model in assessing the microsatellite instability of colorectal cancer liver metastasis.

OBJECTIVE: This study aims to investigate the efficiency of a radiomics model in identifying high-frequency microsatellite instability (MSI-H) and microsatellite stability (MSS) of colorectal liver metastasis (CRLM) according to machine learning radiomics features of enhanced CT liver images. MATERIALS AND METHODS: A total of 12 patients with MSI-H CRLM and 96 patients with MSS CRLM were randomly divided into the training group and internal validation group according to the ratio of 7: 3 (training: 75 cases, validation: 33 cases). From the enhanced CT (portal phase) image data of patients, 788 radiomics features were extracted, and a random forest model was established with the optimal features selected. The receiver operating characteristics (ROC) curve analysis was performed to assess the model's diagnostic efficacy. RESULTS: The training group comprised 8 patients with MSI-H CRLM and 67 patients with MSS CRLM, and the internal validation group included 4 patients with MSI-H CRLM and 29 patients with MSS CRLM. After feature selection, 7 radiomics features good for distinguishing MSI-H CRLM and MSS CRLM were screened out. The ROC curve analysis demonstrated that the random forest model had the AUC (area under the ROC curve) value 0.88, accuracy 0.85, sensitivity 0.85, specificity 0.92, and F1 score 0.88 in the training group. The model had an AUC value of 0.75, accuracy of 0.74, sensitivity of 0.81, specificity of 0.85, and F1_score of 0.78 in the internal validation group in identifying the MSI-H from the MSS CRLM. In order to evaluate the robustness of the overall model, the 788 features obtained were all applied to the 5-fold cross-validation, with the model being built on the random forest and analyzed with the ROC curve analysis. The AUC value of the model was 0.86 (P＜0.05), accuracy value 0.91, sensitivity 0.60, and specificity 0.95. CONCLUSION: The random forest prediction model built on the radiometric features extracted from enhanced CT images can be used to identify the MSI-H from the MSS CRLM and may provide effective guidance for clinical immunotherapy of CRLM patients with unknown MSI status.

Deep learning for predicting the human epidermal growth factor receptor 2 status of breast cancer liver metastases based on contrast-enhanced computed tomography: a development and validation study.

Background: This study investigated the value of a deep learning (DL) model based on computed tomography (CT) enhancement for predicting human epidermal growth factor receptor 2 (HER2) expression in patients with liver metastasis from breast cancer. Methods: Data were collected for 151 female patients with liver metastasis from breast cancer who underwent abdominal enhanced CT examination in the Department of Radiology at the Affiliated Hospital of Hebei University between January 2017 and March 2022. Liver metastases were confirmed in all patients by pathology. The HER2 status of the liver metastases was assessed and enhanced CT examinations were performed before treatment. Of the 151 patients, 93 were HER2 negative and 58 were HER2 positive. Liver metastases were manually labeled with rectangular frames, layer by layer, and the labeled data were processed. Five basic networks (ResNet34, ResNet50, ResNet101, ResNeXt50, and Swim Transformer) were used for training and optimization, and the model's performance was tested. Receiver operating characteristic (ROC) curves were used to analyze the area under the curve (AUC), as well as the accuracy, sensitivity, and specificity of the networks in predicting HER2 expression in breast cancer liver metastases. Results: Overall, ResNet34 demonstrated the best prediction efficiency. The accuracy of the validation and test set models in predicting HER2 expression in liver metastases was 87.4% and 80.5%, respectively. The AUC, sensitivity, and specificity of the test set model in predicting HER2 expression in liver metastases were 0.778, 77.0%, and 84.0%, respectively. Conclusions: Our DL model based on CT enhancement has good stability and diagnostic efficacy, and is a potential non-invasive method for identifying HER2 expression in liver metastases from breast cancer.

Radiomics model based on multi-sequence MRI for preoperative prediction of ki-67 expression levels in early endometrial cancer.

To validate a radiomics model based on multi-sequence magnetic resonance imaging (MRI) in predicting the ki-67 expression levels in early-stage endometrial cancer, 131 patients with early endometrial cancer who had undergone pathological examination and preoperative MRI scan were retrospectively enrolled and divided into two groups based on the ki-67 expression levels. The radiomics features were extracted from the T2 weighted imaging (T2WI), dynamic contrast enhanced T1 weighted imaging (DCE-T1WI), and apparent diffusion coefficient (ADC) map and screened using the Pearson correlation coefficients (PCC). A multi-layer perceptual machine and fivefold cross-validation were used to construct the radiomics model. The receiver operating characteristic (ROC) curves analysis, calibration curves, and decision curve analysis (DCA) were used to assess the models. The combined multi-sequence radiomics model of T2WI, DCE-T1WI, and ADC map showed better discriminatory powers than those using only one sequence. The combined radiomics models with multi-sequence fusions achieved the highest area under the ROC curve (AUC). The AUC value of the validation set was 0.852, with an accuracy of 0.827, sensitivity of 0.844, specificity of 0.773, and precision of 0.799. In conclusion, the combined multi-sequence MRI based radiomics model enables preoperative noninvasive prediction of the ki-67 expression levels in early endometrial cancer. This provides an objective imaging basis for clinical diagnosis and treatment.