Performance evaluation of ML models for preoperative prediction of HER2-low BC based on CE-CBBCT radiomic features: A prospective study.

To explore the value of machine learning (ML) models based on contrast-enhanced cone-beam breast computed tomography (CE-CBBCT) radiomics features for the preoperative prediction of human epidermal growth factor receptor 2 (HER2)-low expression breast cancer (BC). Fifty-six patients with HER2-negative invasive BC who underwent preoperative CE-CBBCT were prospectively analyzed. Patients were randomly divided into training and validation cohorts at approximately 7:3. A total of 1046 quantitative radiomic features were extracted from CE-CBBCT images and normalized using z-scores. The Pearson correlation coefficient and recursive feature elimination were used to identify the optimal features. Six ML models were constructed based on the selected features: linear discriminant analysis (LDA), random forest (RF), support vector machine (SVM), logistic regression (LR), AdaBoost (AB), and decision tree (DT). To evaluate the performance of these models, receiver operating characteristic curves and area under the curve (AUC) were used. Seven features were selected as the optimal features for constructing the ML models. In the training cohort, the AUC values for SVM, LDA, RF, LR, AB, and DT were 0.984, 0.981, 1.000, 0.970, 1.000, and 1.000, respectively. In the validation cohort, the AUC values for the SVM, LDA, RF, LR, AB, and DT were 0.859, 0.880, 0.781, 0.880, 0.750, and 0.713, respectively. Among all ML models, the LDA and LR models demonstrated the best performance. The DeLong test showed that there were no significant differences among the receiver operating characteristic curves in all ML models in the training cohort (P > .05); however, in the validation cohort, the DeLong test showed that the differences between the AUCs of LDA and RF, AB, and DT were statistically significant (P = .037, .003, .046). The AUCs of LR and RF, AB, and DT were statistically significant (P = .023, .005, .030). Nevertheless, no statistically significant differences were observed when compared to the other ML models. ML models based on CE-CBBCT radiomics features achieved excellent performance in the preoperative prediction of HER2-low BC and could potentially serve as an effective tool to assist in precise and personalized targeted therapy.

Direct and Sensitive Electrochemical Determination of Total Antioxidant Capacity in Foods Using Nanochannel-Based Enrichment of Redox Probes.

Simple and sensitive determination of total antioxidant capacity (TAC) in food samples is highly desirable. In this work, an electrochemical platform was established based on a silica nanochannel film (SNF)-modified electrode, facilitating fast and highly sensitive analysis of TAC in colored food samples. SNF was grown on low-cost and readily available tin indium oxide (ITO) electrode. Fe3+-phenanthroline complex-Fe(III)(phen)3 was applied as the probe, and underwent chemical reduction to form Fe2+-phenanthroline complex-Fe(II)(phen)3 in the presence of antioxidants. Utilizing an oxidative voltage of +1 V, chronoamperometry was employed to measure the current generated by the electrochemical oxidation of Fe(II)(phen)3, allowing for the assessment of antioxidants. As the negatively charged SNF displayed remarkable enrichment towards positively charged Fe(II)(phen)3, the sensitivity of detection can be significantly improved. When Trolox was employed as the standard antioxidant, the electrochemical sensor demonstrated a linear detection range from 0.01 µM to 1 µM and from 1 µM to 1000 µM, with a limit of detection (LOD) of 3.9 nM. The detection performance is better that that of the conventional colorimetric method with a linear de range from 1 µM to 40 µM. Owing to the anti-interfering ability of nanochannels, direct determination of TAC in colored samples including coffee, tea, and edible oils was realized.

CT-based radiomics for predicting lymph node metastasis in esophageal cancer: a systematic review and meta-analysis.

Objective: We aimed to evaluate the diagnostic effectiveness of computed tomography (CT)-based radiomics for predicting lymph node metastasis (LNM) in patients diagnosed with esophageal cancer (EC). Methods: The present study conducted a comprehensive search by accessing the following databases: PubMed, Embase, Cochrane Library, and Web of Science, with the aim of identifying relevant studies published until July 10th, 2023. The diagnostic accuracy was summarized using the pooled sensitivity, specificity, positive likelihood ratio (PLR), negative likelihood ratio (NLR), diagnostic odds ratio (DOR), and area under the curve (AUC). The researchers utilized Spearman's correlation coefficient for assessing the threshold effect, besides performing meta-regression and subgroup analysis for the exploration of possible heterogeneity sources. The quality assessment was conducted using the Quality Assessment of Diagnostic Accuracy Studies-2 and the Radiomics Quality Score (RQS). Results: The meta-analysis included six studies conducted from 2018 to 2022, with 483 patients enrolled and LNM rates ranging from 27.2% to 59.4%. The pooled sensitivity, specificity, PLR, NLR, DOR, and AUC, along with their corresponding 95% CI, were 0.73 (0.67, 0.79), 0.76 (0.69, 0.83), 3.1 (2.3, 4.2), 0.35 (0.28, 0.44), 9 (6, 14), and 0.78 (0.74, 0.81), respectively. The results demonstrated the absence of significant heterogeneity in sensitivity, while significant heterogeneity was observed in specificity; no threshold effect was detected. The observed heterogeneity in the specificity was attributed to the sample size and CT-scan phases (P < 0.05). The included studies exhibited suboptimal quality, with RQS ranging from 14 to 16 out of 36. However, most of the enrolled studies exhibited a low-risk bias and minimal concerns relating to applicability. Conclusion: The present meta-analysis indicated that CT-based radiomics demonstrated a favorable diagnostic performance in predicting LNM in EC. Nevertheless, additional high-quality, large-scale, and multicenter trials are warranted to corroborate these findings. Systematic Review Registration: Open Science Framework platform at https://osf.io/5zcnd.

CT-Based Radiomics and Machine Learning for Differentiating Benign, Borderline, and Early-Stage Malignant Ovarian Tumors.

To explore the value of CT-based radiomics model in the differential diagnosis of benign ovarian tumors (BeOTs), borderline ovarian tumors (BOTs), and early malignant ovarian tumors (eMOTs). The retrospective research was conducted with pathologically confirmed 258 ovarian tumor patients from January 2014 to February 2021. The patients were randomly allocated to a training cohort (n = 198) and a test cohort (n = 60). By providing a three-dimensional (3D) characterization of the volume of interest (VOI) at the maximum level of images, 4238 radiomic features were extracted from the VOI per patient. The Wilcoxon-Mann-Whitney (WMW) test, least absolute shrinkage and selection operator (LASSO), and support vector machine (SVM) were employed to select the radiomic features. Five machine learning (ML) algorithms were applied to construct three-class diagnostic models. Leave-one-out cross-validation (LOOCV) was implemented to evaluate the performance of the radiomics models. The test cohort was used to verify the generalization ability of the radiomics models. The receiver-operating characteristic (ROC) was used to evaluate diagnostic performance of radiomics model. Global and discrimination performance of five models was evaluated by average area under the ROC curve (AUC). The average ROC indicated that random forest (RF) diagnostic model in training cohort demonstrated the best diagnostic performance (micro/macro average AUC, 0.98/0.99), which was then confirmed with by LOOCV (micro/macro average AUC, 0.89/0.88) and external validation (test cohort) (micro/macro average AUC, 0.81/0.79). Our proposed CT-based radiomics diagnostic models may effectively assist in preoperatively differentiating BeOTs, BOTs, and eMOTs.

Regional lymph node density-based nomogram predicts prognosis in nasopharyngeal carcinoma patients without distant metastases.

BACKGROUND: Nasopharyngeal carcinoma (NPC) is a relatively common type of cancer in Southern China, with local recurrence or distant metastases even after radical treatment; consequently, it is critical to identify the patients at higher risk for these events beforehand. This study aimed to assess the prognostic value of regional lymph node density (RLND) associated nomograms in NPC and to evaluate the utility of nomograms in risk stratification. METHODS: A total of 610 NPC patients without distant metastases (425 in the training and 185 in the validation cohort) were enrolled. The MRI-identified nodal features and clinical characteristics were documented, and the RLND was calculated. Cox analyses were conducted to identify prognostic-associated factors. Nomograms were generated based on the multivariate analysis results. The predictive accuracy and discriminative ability of the nomogram models were determined using the concordance index (C-index), receiver operating characteristic (ROC) curve, and calibration curve; the results were compared with those of the tumor-node-metastasis (TNM) classification. Decision curve analysis (DCA) and C-index were used to assess the prognostic effect and added discriminative ability of RLND. We also estimated the optimal RLND-based nomogram score cut-off values for survival prediction. RESULTS: RLND was an independent predictor of overall survival (OS) and disease-free survival (DFS), with hazard ratios of 1.36 and 1.30, respectively. RLND was utilized in the construction of nomograms, alongside other independent prognostic factors. The RLND-based nomogram models presented a more effective discriminative ability than the TNM classification for predicting OS (C-index, 0.711 vs. 0.680) and DFS (C-index, 0.681 vs. 0.669), with favorable calibration and consistency. The comparison of C-index values between the nomogram models with and without RLND provided substantiation of the crucial role RLND plays in these models. DCA confirmed the satisfactory clinical practicability of RLND. Moreover, the nomograms were used to categorize the patients into three groups (high-, middle-, and low-risk), and the Kaplan-Meier curves showed significant differences in prognosis between them (p < 0.05). These results were verified in the validation cohort. CONCLUSION: RLND stands as a robust prognostic factor in NPC. The RLND-based nomograms excel in predicting survival, surpassing the TNM classification.

Diagnostic value of a CT-based radiomics nomogram for discrimination of benign and early stage malignant ovarian tumors.

BACKGROUND: This study aimed to identify the diagnostic value of models constructed using computed tomography-based radiomics features for discrimination of benign and early stage malignant ovarian tumors. METHODS: The imaging and clinicopathological data of 197 cases of benign and early stage malignant ovarian tumors (FIGO stage I/II), were retrospectively analyzed. The patients were randomly assigned into training data set and validation data set. Radiomics features were extracted from images of plain computed tomography scan and contrast-enhanced computed tomography scan, were then screened in the training data set, and a radiomics model was constructed. Multivariate logistic regression analysis was used to construct a radiomic nomogram, containing the traditional diagnostic model and the radiomics model. Moreover, the decision curve analysis was used to assess the clinical application value of the radiomics nomogram. RESULTS: Six textural features with the greatest diagnostic efficiency were finally screened. The value of the area under the receiver operating characteristic curve showed that the radiomics nomogram was superior to the traditional diagnostic model and the radiomics model (P < 0.05) in the training data set. In the validation data set, the radiomics nomogram was superior to the traditional diagnostic model (P < 0.05), but there was no statistically significant difference compared to the radiomics model (P > 0.05). The calibration curve and the Hosmer-Lemeshow test revealed that the three models all had a great degree of fit (All P > 0.05). The results of decision curve analysis indicated that utilization of the radiomics nomogram to distinguish benign and early stage malignant ovarian tumors had a greater clinical application value when the risk threshold was 0.4-1.0. CONCLUSIONS: The computed tomography-based radiomics nomogram could be a non-invasive and reliable imaging method to discriminate benign and early stage malignant ovarian tumors.

Vertically ordered mesoporous silica film-assisted electrochemical cytosensor for the sensitive detection of HeLa cells.

Designing fast and simple quantitative methods on cheap and disposable electrodes for the early detection of HeLa cells is highly desirable for clinical diagnostics and public health. In this work, we developed a label-free and sensitive electrochemical cytosensor for HeLa cell detection based on the gated molecular transport across vertically ordered mesoporous silica films (VMSFs) on the disposable indium tin oxide (ITO) electrode. As high affinity for a folate receptor existed on the membrane of HeLa cancer cells, folic acid (FA) functionalized VMSF could regulate the transport of electrochemical probe (Fe(CN)6 3-) by the specific recognition and adhesion of HeLa cells toward the VMSF surface. In addition, VMSF, served as a solid skeleton, is able to effectively prevent the direct contact of cells with the underlying electrode, remaining the underlying electrode activity and favoring the diffusion of Fe(CN)6 3-. Once specific adhesion of HeLa cells to the VMSF surface happens, Fe(CN)6 3- redox probe exhibits impeded transport in the silica nanochannels, ultimately resulting in the decreased electrochemical responses and realizing the quantitative determination of HeLa cells with a broad linear range (101-105 cells/mL) and a low limit of detection (4 cells/mL). The proposed electrochemical cytosensor shows a great potential application for the early diagnosis of cervical cancer.

CT values of contrast-enhanced CBBCT: A useful diagnostic tool for benign and malignant breast lesions.

BACKGROUND: Computed tomography (CT) value studies of cone-beam breast CT (CBBCT) mainly focus on the enhancement value or enhancement rate, and there has been no study on the CT value (Hounsfield units [HU]) of the lesion itself. PURPOSE: To investigate the CT values under contrast-enhanced CBBCT (CE-CBBCT) and non-contrast-enhanced CBBCT (NC-CBBCT) in scanning for the differential diagnosis of benign and malignant breast lesions. MATERIAL AND METHODS: A retrospective analysis was performed on 189 cases of mammary glandular tissues that underwent NC-CBBCT and CE-CBBCT examination. The qualitative CT values of the lesions, standardized Δ(L-A), standardized Δ*(L - G), standardized Δ(L-A) (Post 1st-Pre), and standardized Δ*(L-G) (Post 2nd-Post 1st) between the benign and malignant groups were compared. Prediction performance was evaluated using receiver operating characteristic (ROC) curves. RESULTS: In total, 58 cases were included in the benign group, 79 cases were included in the malignant group, and 52 cases were included in the normal group. The best diagnostic thresholds of CT values for L (Post 1st-Pre), Δ(L-A) (Post 1st-Pre), and Δ*(L-G) (Post 1st-Pre) were 49.5, 44, and 64.8 HU, respectively. The Δ(L-A) Post-1st rate values of CBBCT had medium diagnostic efficacy (AUC = 0.74, sensitivity = 76.6%, specificity = 69.4%). CONCLUSION: CE-CBBCT can improve the diagnostic efficiency of breast lesions compared with NC-CBBCT. The CT values (HU) of lesions do not need to be standardized with fat and can be directly used in clinical differential diagnosis. The first contrast phase (60 s) is recommended to reduce the radiation exposure.

Integrated bioinformatics and machine-learning screening for immune-related genes in diagnosing non-alcoholic fatty liver disease with ischemic stroke and RRS1 pan-cancer analysis.

Background: The occurrence of ischemic stroke (IS) is associated with nonalcoholic fatty liver disease (NAFLD). The cancer burden of NAFLD complicated by IS also warrants attention. This study aimed to identify candidate immune biomarkers linked to NAFLD and IS and analyze their association with cancer. Methods: Two of each of the NAFLD and IS datasets were downloaded, differentially expressed genes (DEGs) were identified, and module genes were screened via weighted gene coexpression network analysis (WGCNA). Subsequently, utilizing machine learning (least absolute shrinkage and selection operator regression, random forest and support vector machine-recursive feature elimination) and immune cell infiltration analysis, immune-related candidate biomarkers for NAFLD with IS were determined. Simultaneously, a nomogram was established, the diagnostic efficacy was assessed, and the role of candidate biomarkers in cancer was ascertained through pan-cancer analyses. Results: In this study, 117 and 98 DEGs were identified from the combined NAFLD and IS datasets, respectively, and 279 genes were obtained from the most significant modules of NAFLD. NAFLD module genes and IS DEGs were intersected to obtain nine genes, which were enriched in the inflammatory response and immune regulation. After overlapping the results of the three machine learning algorithms, six candidate genes were obtained, based on which a nomogram was constructed. The calibration curve demonstrated good accuracy, and the candidate genes had high diagnostic values. The genes were found to be related to the immune dysregulation of stroke, and RRS1 was strongly associated with the prognosis, immune cell infiltration, microsatellite instability (MSI), and tumor mutation burden (TMB). Conclusion: Six common candidate immune-related genes (PTGS2, FCGR1A, MMP9, VNN3, S100A12, and RRS1) of NAFLD and IS were identified, and a nomogram for diagnosing NAFLD with IS was established. RRS1 may serve as a candidate gene for predicting the prognosis of patients with cancer who have NAFLD complicated by IS, which could aid in their diagnosis and treatment.

Reference Range of CT Value in NC-CBBCT Based on Female Breast Structure.

BACKGROUND: As a new high-resolution three-dimensional CT imaging technology, the essential reference range of CT values in Cone-beam breast computed tomography (CBBCT) has not been established to date. PURPOSE: To determine the reference range of computed tomography (CT) values in CBBCT for clinical breast examination. MATERIALS AND METHODS: In total, 913 cases (1167 lateral) were subject to CBBCT. CT values of the glandular tissue, fat and different quadrants and different distances of CBBCT images were analyzed. The nipple and muscle were also evaluated. RESULTS: A total of 672 lateral breasts were included in the normal group for investigation. The reference range of the absolute CT value of the chest wall muscle is -136.68~43.36 HU. The reference range of the absolute CT value of the nipple is 176.39~334.02 HU. The reference range of the absolute CT value of fat is -190.4~-63.67HU, and of glandular tissue is -12.2~199.07HU. CONCLUSION: Our results firstly established the baseline CT values of Non-contrast CBBCT in female breasts, which will benefit cancer screening and lesion locating. The closer the normal breast fat and glandular tissue is to the nipple, the greater the CT value. The older the age, the lower the density. The CT values of fat are unstable in a distance of less than 5 cm, and the CT values of glandular tissues are relatively stable. The difference between the upper and lower quadrants is significant in the same lateral breast and the same section.

Ring finger protein 126 promotes breast cancer metastasis and serves as a potential target to improve the therapeutic sensitivity of ATR inhibitors.

BACKGROUND/AIMS: This study explores the relationship between the E3 ubiquitin ligase Ring finger protein 126 (RNF126) and early breast cancer metastasis and tests the hypothesis that RNF126 determines the efficacy of inhibitors targeting Ataxia telangiectasia mutated and Rad3-related kinase (ATR). METHODS: Various metastasis-related genes were identified by univariable Cox proportional hazards regression analysis based on the GSE11121 dataset. The RNF126-related network modules were identified by WGCNA, whereas cell viability, invasion, and migration assays were performed to evaluate the biological characteristics of breast cancer cells with or without RNF126 knockdown. MTT, immunoblotting, immunofluorescence, and DNA fiber assays were conducted to determine the efficiency of ATR inhibitor in cells with or without RNF126 knockdown. RESULTS: RNF126 was associated with early breast cancer metastasis. RNF126 promoted breast cancer cell proliferation, growth, migration, and invasion. ATR inhibitors were more effective at killing breast cancer cells with intact RNF126 due to replication stress compared with the corresponding cells with RNF126 knockdown. Cyclin-dependent kinase 2 (CDK2) was involved in regulating replication stress in breast cancer cells with intact RNF126. CONCLUSION: A high level of expression of RNF126 in early breast cancer patients without lymph node metastases may indicate a high-risk type of metastatic disease, possibly due to RNF126, which may increase breast cancer cell proliferation and invasion. RNF126-expressing breast cancer cells exhibit CDK2-mediated replication stress that makes them potential targets for ATR inhibitors.

A Clinical-Radiomics Nomogram Based on Magnetic Resonance Imaging for Predicting Progression-Free Survival After Induction Chemotherapy in Nasopharyngeal Carcinoma.

Purpose: This paper aimed to establish and verify a radiomics model based on magnetic resonance imaging (MRI) for predicting the progression-free survival of nasopharyngeal carcinoma (NPC) after induction chemotherapy (IC). Materials and Methods: This cohort consists of 288 patients with clinical pathologically confirmed NPC, which was collected from January 2015 to December 2018. All NPC patients were randomly divided into two cohorts: training (n=202) and validation (n=86). Radiomics features from the MRI images of NPC patients were extracted and selected before IC. The patients were classified into high- and low-risk groups according to the median of Radscores. The significant imaging features and clinical variables in the univariate analysis were constructed for progression-free survival (PFS) using the multivariate Cox regression model. A survival analysis was performed using Kaplan-Meier with log-rank test and then each model's stratification ability was evaluated. Results: Epstein-Barr virus (EBV) DNA before treatment was an independent predictor for PFS (p < 0.05). Based on the pyradiomic platform, we extracted 1,316 texture parameters in total. Finally, 16 texture features were used to build the model. The clinical radiomics-based model had good prediction capability for PFS, with a C-index of 0.827. The survival curve revealed that the PFS of the high-risk group was poorer than that of the low-risk group. Conclusion: This research presents a nomogram that merges the radiomics signature and the clinical feature of the plasma EBV DNA load, which may improve the ability of preoperative prediction of progression-free survival and facilitate individualization of treatment in NPC patients before IC.

MRI-based random survival Forest model improves prediction of progression-free survival to induction chemotherapy plus concurrent Chemoradiotherapy in Locoregionally Advanced nasopharyngeal carcinoma.

BACKGROUND: The present study aimed to explore the application value of random survival forest (RSF) model and Cox model in predicting the progression-free survival (PFS) among patients with locoregionally advanced nasopharyngeal carcinoma (LANPC) after induction chemotherapy plus concurrent chemoradiotherapy (IC + CCRT). METHODS: Eligible LANPC patients underwent magnetic resonance imaging (MRI) scan before treatment were subjected to radiomics feature extraction. Radiomics and clinical features of patients in the training cohort were subjected to RSF analysis to predict PFS and were tested in the testing cohort. The performance of an RSF model with clinical and radiologic predictors was assessed with the area under the receiver operating characteristic (ROC) curve (AUC) and Delong test and compared with Cox models based on clinical and radiologic parameters. Further, the Kaplan-Meier method was used for risk stratification of patients. RESULTS: A total of 294 LANPC patients (206 in the training cohort; 88 in the testing cohort) were enrolled and underwent magnetic resonance imaging (MRI) scans before treatment. The AUC value of the clinical Cox model, radiomics Cox model, clinical + radiomics Cox model, and clinical + radiomics RSF model in predicting 3- and 5-year PFS for LANPC patients was [0.545 vs 0.648 vs 0.648 vs 0.899 (training cohort), and 0.566 vs 0.736 vs 0.730 vs 0.861 (testing cohort); 0.556 vs 0.604 vs 0.611 vs 0.897 (training cohort), and 0.591 vs 0.661 vs 0.676 vs 0.847 (testing cohort), respectively]. Delong test showed that the RSF model and the other three Cox models were statistically significant, and the RSF model markedly improved prediction performance (P < 0.001). Additionally, the PFS of the high-risk group was lower than that of the low-risk group in the RSF model (P < 0.001), while comparable in the Cox model (P > 0.05). CONCLUSION: The RSF model may be a potential tool for prognostic prediction and risk stratification of LANPC patients.

A Dual-Mode Imaging Nanoparticle Probe Targeting PD-L1 for Triple-Negative Breast Cancer.

Chemotherapy has remained the mainstay of treatment of triple-negative breast cancer; however, it is significantly limited by the associated side effects. PD-1/PD-L1 immune checkpoint inhibition therapy (ICI) has been a breakthrough for this patient population in recent years. PD-L1 expression is crucial in immunotherapy since it is a major predictor of PD-1/PD-L1 antibody response, emphasizing the significance of monitoring PD-L1 expression. Nonetheless, it is hard to assess the expression of PD-L1 before surgery, which has highlighted the urgency for a precise and noninvasive approach. Herein, we prepared a dual-mode imaging nanoparticle probe to detect PD-L1. The particle size, zeta potential, biocompatibility, and imaging ability of NPs were characterized. The synthesized NPs showed slight cytotoxicity and good T2 relaxivity. The targeted NPs accumulated more in 4T1 cells than nontargeted NPs in vitro. The in vivo experiment further demonstrated the distribution of targeted NPs in tumor tissues, with changes in NIRF and MR signals observed. Our study indicated that SPIO-aPD-L1-Cy5.5 NPs can be used to monitor PD-L1 expression in breast cancer as NIRF/MR contrast agents.

Contrast-Enhanced Cone-Beam Breast CT: An Analysis of Diagnostic Value in Predicting Breast Lesion With Rim Enhancement Malignancy.

Background: The objective of the current study was to investigate the diagnostic value of contrast-enhanced cone-beam breast computed tomography (CE-CBBCT) for breast lesion with rim enhancement (RE). Methods: All 36 patients were examined by non-contrast (NC-CBBCT) and contrast-enhanced CBBCT (CE-CBBCT) after contrast media (CM) injection. Qualitative morphological enhancement parameters and quantitative enhancement parameters were compared between malignant and benign groups. Multivariable logistic regression analysis was performed to identify independent factors that could predict breast lesion with RE malignancy. Receiver operating curve (ROC) was used to evaluate prediction performance. Results: A total of 36 patients with 40 lesions underwent breast CE-CBBCT were enrolled. There were significant differences in most qualitative morphological enhancement parameters between the two groups. A multivariate logistic regression model showed that △standardized HU (INRphase 2-INRpreCM) [odds ratio (OR) = 1.148, 95% CI = 1.034-1.276, p = 0.01] and △standardized HU (RPphase 2 - RPphase 1) (OR = 0.891, 95% CI = 0.814-0.976, p = 0.013) were independent indicators in predicting breast lesion with RE malignancy. △standardized HU (INRphase 2 - INRpreCM) combined with △standardized HU (RPphase 2 - RPphase 1) showed significant larger area under the receiver operating curve (AUC) and higher sensitivity than each alone (p < 0.001, AUC = 0.932, sensitivity = 92.59%, specificity = 92.31%). The regression equation of the prediction model was as follows: Logit (p) = 0.351 + 0.138X × â–³standardized HU (INRphase 2 - INRpreCM) - 0.115 × â–³standardized HU (RPphase 2 - RPphase 1). Conclusion: With the observation of qualitative morphological enhancement parameters and the comparison of quantitative enhancement parameters of CBBCT, a reliable basis for the diagnostic accuracy in predicting breast lesion with RE could be provided. These conclusions should be verified in large, well-designed studies.

Application Value of Machine Learning Method in Measuring Gray Matter Volume of AIDS Patients.

Background: To investigate the role of gray matter (GM) volume in the identification of HIV-positive patients with HIV-associated neurocognitive impairment (HAND) using a machine learning approach from normal healthy controls. Methods: Twenty-seven HIV-infected patients and 14 healthy controls were enrolled in our study. Each set of BRAVO images was postprocessed using DPARSF3.1 to coregister all brains on the MNI template, and volume extraction of 90 brain regions was performed using custom-designed code. The machine learning method was performed using PRoNTo2.1.1 toolbox. The differences in brain volume between the HAND and non-HAND groups were analyzed. Results: GM volume effectively distinguished HIV-positive patients from healthy subjects with an AUC equals to 0.73. The sensitivity, specificity, and accuracy of the established classification were 85.19%, 42.86%, and 70.73%, respectively. GM volume value of the top ten brain regions was related to digit symbols, trail making test, digit span, vocabulary fluency, stroop C time, stroop CW time, CD4, and neuropsychological group. Conclusions: A machine learning approach facilitates early diagnosis of HAND in HIV patients by MRI-based GM volume measurement.

Survival among subgroups of patients with stage II nasopharyngeal carcinoma.

To assess survival between subgroups (T1N1, T2N0, and T2N1) of patients with stage II nasopharyngeal carcinoma (NPC). This retrospective cohort study evaluated pathologically confirmed stage II NPC patients from The Surveillance, Epidemiology, and End Results (SEER) database from 2004 to 2016. The included patients were divided into three subgroups: T1N1, T2N0, and T2N1. Overall survival (OS) and cancer-specific survival (CSS) were assessed using the Kaplan-Meier method among the three subgroups. This study investigated 836 patients: 383 (45.8%) patients were in the T1N1 subgroup, 175 (20.9%) patients were in the T2N0 subgroup, and 278 (33.3%) patients were in the T2N1 subgroup. The 5-year OS (75.7%, 68.6%, and 75.7%) and CSS (85.3%, 83.4%, and 84.5%) were similar among the T1N1, T2N0, and T2N1 subgroups. Univariate and multivariate regression analyses revealed that the subgroup (T1N1, T2N0, and T2N1) of stage II NPC was not an independent prognostic factor for OS or CSS. Survival was comparable among subgroups (T1N1, T2N0, and T2N1) of stage II NPC patients. However, patients with T1N1, T2N0, and T2N1 stage disease who receive different treatments might have different prognoses.

Ultrasound and magnetic resonance imaging of cyclic arginine glycine aspartic acid-gadopentetic acid-polylactic acid in human breast cancer by targeting αvß3 in xenograft-bearing nude mice.

Effective early detection shows the potential to reduce breast cancer mortality. This study aimed to establish a targeted contrast agent for Magnetic Resonance Imaging (MRI)/ultrasound dual-modality molecular radiography for breast cancer. The cyclic arginine-glycine-aspartate-gadopentetic acid-polylactic acid (cRGD and Gd-DTPA) coated by multi-functional blank poly (lactic-co-glycolic acid) (PLGA) nanoparticles) was successfully constructed by chemical synthesis method with high stability. The safety of cRGD-Gd-DTPA-PLGA was demonstrated in vitro and in vivo, and their affinity to breast cancer cells was revealed. Moreover, MRI/ultrasound dual-modality molecular radiography in vitro showed that as the concentration of contrast agent increased, the echo enhancement and signal intensity of MRI imaging were also elevated. The mouse models of human breast cancer also indicated significant target enhancements of cRGD-Gd-DTPA-PLGA magnetic nanoparticles in the mouse tumor. Thus, cRGD-Gd-DTPA-PLGA magnetic nanoparticles were suggested as qualified MRI/ultrasound dual-modality molecular radiography contrast agent. We further explored the targeting mechanism of cRGD-Gd-DTPA-PLGA in breast cancer. The results showed that αvß3 was highly expressed in breast cancer tissues, and cRGD-Gd-DTPA-PLGA used for MRI/ultrasound dual-modality molecular radiography by targeting αvß3. Additionally, we found that the signal-to-noise ratio of MRI was positively correlated with microvessel density (MVD). The cRGD-Gd-DTPA-PLGA dynamicly and quantitatively monitored breast cancer by monitoring the state of neovascularization. In conclusion, in the present study, we successfully constructed the cRGD-Gd-DTPA-PLGA magnetic nanoparticles for MRI/ultrasound dual-modality molecular radiography. The cRGD-Gd-DTPA-PLGA showed potential in early detection and diagnosis of metastasis, and dynamic evaluation of the efficacy of molecular targeted therapy of integrin αvß3.

A functional liver imaging score for preoperative prediction of liver failure after hepatocellular carcinoma resection.

OBJECTIVES: Posthepatectomy liver failure (PHLF) is a challenging complication after resection to treat hepatocellular carcinoma (HCC), and it is associated with high mortality. Preoperative prediction of PHLF may improve patient subsequent and reduce such mortality. This study examined whether a functional liver imaging score (FLIS) based on preoperative gadoxetic acid-enhanced magnetic resonance imaging (MRI) could predict PHLF. MATERIALS AND METHODS: The study included 502 patients who underwent preoperative gadoxetic acid-enhanced MRI, followed by HCC resection. Significant preoperative predictors of PHLF were identified using logistic regression analysis. The ability of FLIS to predict PHLF was evaluated using receiver operating characteristic curves, and its predictive power was compared to that of the model for end-stage liver disease (MELD) score, albumin-bilirubin (ALBI) score, and indocyanine green 15-min retention rate (ICG-R15). RESULTS: In multivariate analysis, PHLF was independently associated with FLIS (OR 0.452, 95% CI 0.361 to 0.568, p < 0.001) and major resection (OR 1.898, 95% CI 1.057 to 3.408, p = 0.032). FLIS was associated with a higher area under the receiver operating characteristic curve (0.752) than the MELD score (0.557), ALBI score (0.609), or ICG-R15 (0.605) (all p < 0.05). Patients with FLIS ≤ 4 who underwent major resection were at 9.4-fold higher risk of PHLF than patients with lower FLIS who underwent minor resection. CONCLUSION: FLIS is an independent predictor of PHLF, and it may perform better than the MELD score, ALBI score, and ICG-R15 clearance. We propose treating elevated FLIS and major resection as risk factors for PHLF. KEY POINTS: • A functional liver imaging score can independently predict posthepatectomy liver failure in patients with HCC. • The score may predict such failure better than MELD and ALBI scores and ICG-R15. • Patients with scores ≤ 4 who undergo major hepatic resection may be at nearly tenfold higher risk of posthepatectomy liver failure.

Dual-energy CT-based radiomics nomogram in predicting histological differentiation of head and neck squamous carcinoma: a multicenter study.

PURPOSE: To develop and validate a dual-energy CT (DECT)-based radiomics nomogram from multicenter trials for predicting the histological differentiation of head and neck squamous cell carcinoma (HNSCC). METHODS: A total of 178 patients (112 in the training and 66 in the validation cohorts) from eight institutions with histologically proven HNSCCs were included in this retrospective study. Radiomics-signature models were constructed from features extracted from virtual monoenergetic images (VMI) and iodine-based material decomposition images (IMDI), reconstructed from venous-phase DECT images. Clinical factors were also assessed to build a clinical model. Multivariate logistic regression analysis was used to develop a nomogram combining the radiomics signature models and clinical model for predicting poorly differentiated HNSCC and moderately well-differentiated HNSCC. The predictive performance of the clinical model, radiomics signature models, and nomogram was compared. The calibration degree of the nomogram was also assessed. RESULTS: The tumor location, VMI-signature, and IMDI-signature were associated with the degree of HNSCC differentiation, and areas under the ROC curves (AUCs) were 0.729, 0.890, and 0.833 in the training cohort and 0.627, 0.859, and 0.843 in the validation cohort, respectively. The nomogram incorporating tumor location and two radiomics-signature models yielded the best performance in training (AUC = 0.987) and validation (AUC = 0.968) cohorts with a good calibration degree. CONCLUSION: The nomogram that integrated the DECT-based radiomics-signature models and tumor location showed good performance in predicting histological differentiation degree of HNSCC, providing a novel combination for predicting HNSCC differentiation.