Predicting major adverse cardiac events using radiomics nomogram of pericoronary adipose tissue based on CCTA: A multi-center study.

BACKGROUND: The evolution of coronary atherosclerotic heart disease (CAD) is intricately linked to alterations in the pericoronary adipose tissue (PCAT). In recent epochs, characteristics of the PCAT have progressively ascended as focal points of research in CAD risk stratification and individualized clinical decision-making. Harnessing radiomic methodologies allows for the meticulous extraction of imaging features from these adipose deposits. Coupled with machine learning paradigms, we endeavor to establish predictive models for the onset of major adverse cardiovascular events (MACE). PURPOSE: To appraise the predictive utility of radiomic features of PCAT derived from coronary computed tomography angiography (CCTA) in forecasting MACE. METHODS: We retrospectively incorporated data from 314 suspected or confirmed CAD patients admitted to our institution from June 2019 to December 2022. An additional cohort of 242 patients from two external institutions was encompassed for external validation. The endpoint under consideration was the occurrence of MACE after a 1-year follow-up. MACE was delineated as cardiovascular mortality, newly diagnosed myocardial infarction, hospitalization (or re-hospitalization) for heart failure, and coronary target vessel revascularization occurring more than 30 days post-CCTA examination. All enrolled patients underwent CCTA scanning. Radiomic features were meticulously extracted from the optimal diastolic phase axial slices of CCTA images. Feature reduction was achieved through a composite feature selection algorithm, laying the groundwork for the radiomic signature model. Both univariate and multivariate analyses were employed to assess clinical variables. A multifaceted logistic regression analysis facilitated the crafting of a clinical-radiological-radiomic combined model (or nomogram). Receiver operating characteristic (ROC) curves, calibration, and decision curve analyses (DCA) were delineated, with the area under the ROC curve (AUCs) computed to gauge the predictive prowess of the clinical model, radiomic model, and the synthesized ensemble. RESULTS: A total of 12 radiomic features closely associated with MACE were identified to establish the radiomic model. Multivariate logistic regression results demonstrated that smoking, age, hypertension, and dyslipidemia were significantly correlated with MACE. In the integrated nomogram, which amalgamated clinical, imaging, and radiomic parameters, the diagnostic performance was as follows: 0.970 AUC, 0.949 accuracy (ACC), 0.833 sensitivity (SEN), 0.981 specificity (SPE), 0.926 positive predictive value (PPV), and 0.955 negative predictive value (NPV). The calibration curve indicated a commendable concordance of the nomogram, and the decision curve analysis underscored its superior clinical utility. CONCLUSIONS: The integration of radiomic signatures from PCAT based on CCTA, clinical indices, and imaging parameters into a nomogram stands as a promising instrument for prognosticating MACE events.

Role of dietary nutrients and metabolism in colorectal cancer.

Colorectal cancer (CRC) is one of the most common malignancies and the leading causes of cancer related deaths worldwide. The development of CRC is driven by a combination of genetic and environmental factors. There is growing evidence that changes in dietary nutrition may modulate the CRC risk, and protective effects on the risk of developing CRC have been advocated for specific nutrients such as glucose, amino acids, lipid, vitamins, micronutrients and prebiotics. Metabolic crosstalk between tumor cells, tumor microenvironment components and intestinal flora further promote proliferation, invasion and metastasis of CRC cells and leads to treatment resistance. This review summarizes the research progress on CRC prevention, pathogenesis, and treatment by dietary supplementation or deficiency of glucose, amino acids, lipids, vitamins, micronutri-ents, and prebiotics, respectively. The roles played by different nutrients and dietary crosstalk in the tumor microenvironment and metabolism are discussed, and nutritional modulation is inspired to be beneficial in the prevention and treatment of CRC.

Conventional dendritic cells 2, the targeted antigen-presenting-cell, induces enhanced type 1 immune responses in mice immunized with CVC1302 in oil formulation.

Multifunctional CD4+ T helper 1 (Th1) cells, producing IFN-γ, TNF-α and IL-2, define a correlate of vaccine-mediated protection against intracellular infection. In our previous study, we found that CVC1302 in oil formulation promoted the differentiation of IFN-γ+/TNF-α+/IL-2+Th1 cells. In order to extend the application of CVC1302 in oil formulation, this study aimed to elucidate the mechanism of action in improving the Th1 immune response. Considering the signals required for the differentiation of CD4+ T cells to Th1 cells, we detected the distribution of innate immune cells and the model antigen OVA-FITC in lymph node (LN), as well as the quantity of cytokines produced by the innate immune cells. The results of these experiments show that, cDC2 and OVA-FITC localized to interfollicular region (IFR) of the draining lymph nodes, inflammatory monocytes localized to both IFR and T cell zone, which mainly infiltrate from the blood. In this inflammatory niche within LN, CD4+ T cells were attracted into IFR by CXCL10, secreted by inflammatory monocytes, then activated by cDC2, secreting IL-12. Above all, CVC1302 in oil formulation, on the one hand, targeted antigen and inflammatory monocytes into the LN IFR in order to attract CD4+ T cells, on the other hand, targeted cDC2 to produce IL-12 in order to promote optimal Th1 differentiation. The new finding will provide a blueprint for application of immunopotentiators in optimal formulations.

Multi-omics and Multi-VOIs to predict esophageal fistula in esophageal cancer patients treated with radiotherapy.

OBJECTIVE: This study aimed to develop a prediction model for esophageal fistula (EF) in esophageal cancer (EC) patients treated with intensity-modulated radiation therapy (IMRT), by integrating multi-omics features from multiple volumes of interest (VOIs). METHODS: We retrospectively analyzed pretreatment planning computed tomographic (CT) images, three-dimensional dose distributions, and clinical factors of 287 EC patients. Nine groups of features from different combination of omics [Radiomics (R), Dosiomics (D), and RD (the combination of R and D)], and VOIs [esophagus (ESO), gross tumor volume (GTV), and EG (the combination of ESO and GTV)] were extracted and separately selected by unsupervised (analysis of variance (ANOVA) and Pearson correlation test) and supervised (Student T test) approaches. The final model performance was evaluated using five metrics: average area under the receiver-operator-characteristics curve (AUC), accuracy, precision, recall, and F1 score. RESULTS: For multi-omics using RD features, the model performance in EG model shows: AUC, 0.817 ± 0.031; 95% CI 0.805, 0.825; p < 0.001, which is better than single VOI (ESO or GTV). CONCLUSION: Integrating multi-omics features from multi-VOIs enables better prediction of EF in EC patients treated with IMRT. The incorporation of dosiomics features can enhance the model performance of the prediction.

Multi-omics fusion with soft labeling for enhanced prediction of distant metastasis in nasopharyngeal carcinoma patients after radiotherapy.

Omics fusion has emerged as a crucial preprocessing approach in medical image processing, significantly assisting several studies. One of the challenges encountered in integrating omics data is the unpredictability arising from disparities in data sources and medical imaging equipment. Due to these differences, the distribution of omics futures exhibits spatial heterogeneity, diminishing their capacity to enhance subsequent tasks. To overcome this challenge and facilitate the integration of their joint application to specific medical objectives, this study aims to develop a fusion methodology for nasopharyngeal carcinoma (NPC) distant metastasis prediction to mitigate the disparities inherent in omics data. The multi-kernel late-fusion method can reduce the impact of these differences by mapping the features using the most suiTable single-kernel function and then combining them in a high-dimensional space that can effectively represent the data. The proposed approach in this study employs a distinctive framework incorporating a label-softening technique alongside a multi-kernel-based Radial basis function (RBF) neural network to address these limitations. An efficient representation of the data may be achieved by utilizing the multi-kernel to map the inherent features and then merging them in a space with many dimensions. However, the inflexibility of label fitting poses a constraint on using multi-kernel late-fusion methods in complex NPC datasets, hence affecting the efficacy of general classifiers in dealing with high-dimensional characteristics. The label softening increases the disparity between the two cohorts, providing a more flexible structure for allocating labels. The proposed model is evaluated on multi-omics datasets, and the results demonstrate its strength and effectiveness in predicting distant metastasis of NPC patients.

A novel clinical model for risk prediction and stratification of new-onset diabetes mellitus after distal pancreatectomy.

Background: The incidence of new-onset diabetes mellitus (NODM) after distal pancreatectomy (DP) remains high. Few studies have focused on NODM in patients with pancreatic benign or low-grade malignant lesions (PBLML). This study aimed to develop and validate an effective clinical model for risk prediction and stratification of NODM after DP in patients with PBLML. Methods: A follow-up survey was conducted to investigate NODM in patients without preoperative DM who underwent DP. Four hundred and forty-eight patients from Peking Union Medical College Hospital (PUMCH) and 178 from Guangdong Provincial People's Hospital (GDPH) met the inclusion criteria. They constituted the training cohort and the validation cohort, respectively. Univariate and multivariate Cox regression, as well as least absolute shrinkage and selection operator (LASSO) analyses, were used to identify the independent risk factors. The nomogram was constructed and verified. Concordance index (C-index), receiver operating characteristic (ROC) curve, calibration curves, and decision curve analysis (DCA) were applied to assess its predictive performance and clinical utility. Accordingly, the optimal cut-off point was determined by maximally selected rank statistics method, and the cumulative risk curves for the high- and low-risk populations were plotted to evaluate the discrimination ability of the nomogram. Results: The median follow-up duration was 42.8 months in the PUMCH cohort and 42.9 months in the GDPH cohort. The postoperative cumulative 5-year incidences of DM were 29.1% and 22.1%, respectively. Age, body mass index (BMI), length of pancreatic resection, intraoperative blood loss, and concomitant splenectomy were significant risk factors. The nomogram demonstrated significant predictive utility for post-pancreatectomy DM. The C-indexes of the nomogram were 0.739 and 0.719 in the training and validation cohorts, respectively. ROC curves demonstrated the predictive accuracy of the nomogram, and the calibration curves revealed that prediction results were in general agreement with the actual results. The considerable clinical applicability of the nomogram was certified by DCA. The optimal cut-off point for risk prediction value was 2.88, and the cumulative risk curves of each cohort showed significant differences between the high- and low-risk groups. Conclusions: The nomogram could predict and identify the NODM risk population, and provide guidance to physicians in monitoring and controlling blood glucose levels in PBLML patients after DP.

Laboratory scoring system to predict hepatic indocyanine green clearance ability during fluorescence imaging-guided laparoscopic hepatectomy.

BACKGROUND: Indocyanine green (ICG) fluorescence played an important role in tumor localization and margin delineation in hepatobiliary surgery. However, the preoperative regimen of ICG administration was still controversial. Factors associated with tumor fluorescence staining effect were unclear. AIM: To investigate the preoperative laboratory indexes corelated with ICG fluorescence staining effect and establish a novel laboratory scoring system to screen specifical patients who need ICG dose adjustment. METHODS: To investigate the predictive indicators of ICG fluorescence characteristics in patients undergoing laparoscopic hepatectomy from January 2018 to January 2021 were included. Blood laboratory tests were completed within 1 wk before surgery. All patients received 5 mg ICG injection 24 h before surgery for preliminary tumor imaging. ImageJ software was used to measure the fluorescence intensity values of regions of interest. Correlation analysis was used to identify risk factors. A laboratory risk model was established to identify individuals at high risk for high liver background fluorescence. RESULTS: There were 110 patients who were enrolled in this study from January 2019 to January 2021. The mean values of fluorescence intensity of liver background (FI-LB), fluorescence intensity of gallbladder, and fluorescence intensity of target area were 18.87 ± 17.06, 54.84 ± 33.29, and 68.56 ± 36.11, respectively. The receiver operating characteristic (ROC) curve showed that FI-LB was a good indicator for liver clearance ability [area under the ROC curve (AUC) = 0.984]. Correlation analysis found pre-operative aspartate aminotransferase, alanine aminotransferase, gamma-glutamyl transpeptidase, adenosine deaminase, and lactate dehydrogenase were positively associated with FI-LB and red blood cell, cholinesterase, and were negatively associated with FI-LB. Total laboratory risk score (TLRS) was calculated according to ROC curve (AUC = 0.848, sensitivity = 0.773, specificity = 0.885). When TLRS was greater than 6.5, the liver clearance ability of ICG was considered as poor. CONCLUSION: Preoperative laboratory blood indicators can predict hepatic ICG clearance ability. Surgeons can adjust the dose and timing of ICG preoperatively to achieve better liver fluorescent staining.

Artificial intelligence-driven radiomics study in cancer: the role of feature engineering and modeling.

Modern medicine is reliant on various medical imaging technologies for non-invasively observing patients' anatomy. However, the interpretation of medical images can be highly subjective and dependent on the expertise of clinicians. Moreover, some potentially useful quantitative information in medical images, especially that which is not visible to the naked eye, is often ignored during clinical practice. In contrast, radiomics performs high-throughput feature extraction from medical images, which enables quantitative analysis of medical images and prediction of various clinical endpoints. Studies have reported that radiomics exhibits promising performance in diagnosis and predicting treatment responses and prognosis, demonstrating its potential to be a non-invasive auxiliary tool for personalized medicine. However, radiomics remains in a developmental phase as numerous technical challenges have yet to be solved, especially in feature engineering and statistical modeling. In this review, we introduce the current utility of radiomics by summarizing research on its application in the diagnosis, prognosis, and prediction of treatment responses in patients with cancer. We focus on machine learning approaches, for feature extraction and selection during feature engineering and for imbalanced datasets and multi-modality fusion during statistical modeling. Furthermore, we introduce the stability, reproducibility, and interpretability of features, and the generalizability and interpretability of models. Finally, we offer possible solutions to current challenges in radiomics research.

Multimodal Data Integration to Predict Severe Acute Oral Mucositis of Nasopharyngeal Carcinoma Patients Following Radiation Therapy.

(1) Background: Acute oral mucositis is the most common side effect for nasopharyngeal carcinoma patients receiving radiotherapy. Improper or delayed intervention to severe AOM could degrade the quality of life or survival for NPC patients. An effective prediction method for severe AOM is needed for the individualized management of NPC patients in the era of personalized medicine. (2) Methods: A total of 242 biopsy-proven NPC patients were retrospectively recruited in this study. Radiomics features were extracted from contrast-enhanced CT (CECT), contrast-enhanced T1-weighted (cT1WI), and T2-weighted (T2WI) images in the primary tumor and tumor-related area. Dosiomics features were extracted from 2D or 3D dose-volume histograms (DVH). Multiple models were established with single and integrated data. The dataset was randomized into training and test sets at a ratio of 7:3 with 10-fold cross-validation. (3) Results: The best-performing model using Gaussian Naive Bayes (GNB) (mean validation AUC = 0.81 ± 0.10) was established with integrated radiomics and dosiomics data. The GNB radiomics and dosiomics models yielded mean validation AUC of 0.6 ± 0.20 and 0.69 ± 0.14, respectively. (4) Conclusions: Integrating radiomics and dosiomics data from the primary tumor area could generate the best-performing model for severe AOM prediction.

Multi-omics to predict acute radiation esophagitis in patients with lung cancer treated with intensity-modulated radiation therapy.

PURPOSE: The study aimed to predict acute radiation esophagitis (ARE) with grade ≥ 2 for patients with locally advanced lung cancer (LALC) treated with intensity-modulated radiation therapy (IMRT) using multi-omics features, including radiomics and dosiomics. METHODS: 161 patients with stage IIIA-IIIB LALC who received chemoradiotherapy (CRT) or radiotherapy by IMRT with a prescribed dose from 45 to 70 Gy from 2015 to 2019 were enrolled retrospectively. All the toxicity gradings were given following the Common Terminology Criteria for Adverse Events V4.0. Multi-omics features, including radiomics, dosiomics (including dose-volume histogram dosimetric parameters), were extracted based on the planning CT image and three-dimensional dose distribution. All data were randomly divided into training cohorts (N = 107) and testing cohorts (N = 54). In the training cohorts, features with reliably high outcome relevance and low redundancy were selected under random patient subsampling. Four classification models (using clinical factors (CF) only, using radiomics features (RFs) only, dosiomics features (DFs) only, and the hybrid features (HFs) containing clinical factors, radiomics and dosiomics) were constructed employing the Ridge classifier using two-thirds of randomly selected patients as the training cohort. The remaining patient was treated as the testing cohort. A series of models were built with 30 times training-testing splits. Their performances were assessed using the area under the ROC curve (AUC) and accuracy. RESULTS: Among all patients, 51 developed ARE grade ≥ 2, with an incidence of 31.7%. Next, 8990 radiomics and 213 dosiomics features were extracted, and 3, 6, 12, and 13 features remained after feature selection in the CF, DF, RF and DF models, respectively. The RF and HF models achieved similar classification performance, with the training and testing AUCs of 0.796 ± 0.023 (95% confidence interval (CI [0.79, 0.80])/0.744 ± 0.044 (95% CI [0.73, 0.76]) and 0.801 ± 0.022 (95% CI [0.79, 0.81]) (p = 0.74), respectively. The model performances using CF and DF features were poorer, with training and testing AUCs of 0.573 ± 0.026 (95% CI [0.56, 0.58])/ 0.509 ± 0.072 (95% CI [0.48, 0.53]) and 0.679 ± 0.027 (95% CI [0.67, 0.69])/0.604 ± 0.041 (95% CI [0.53, 0.63]) compared with the above two models (p < 0.001), respectively. CONCLUSIONS: In LALC patients treated with CRT IMRT, the ARE grade ≥ 2 can be predicted using the pretreatment radiotherapy image features. To predict ARE, the multi-omics features had similar predictability with radiomics features; however, the dosiomics features and clinical factors had a limited classification performance.

Peripheral Th and NK cells are associated with response to lenvatinib plus PD-1 inhibitor in unresectable hepatocellular carcinoma.

The value of peripheral blood lymphocyte subpopulations in predicting responses to lenvatinib combination with programmed death-1 (PD-1) inhibitors in unresectable hepatocellular carcinoma (HCC) was investigated. Fifteen patients received objective responses (OR) and sixteen patients had non-objective responses (NOR) were analyzed. The counts of peripheral blood lymphocyte subpopulations from patients were measured before treatment, second (at week 3), and third doses (at week 6) of the PD-1 inhibitor administration, and correlated with responses. Helper T (Th) cells and natural killers (NK) cells were more abundant in the OR group and found to be important predictors of OR in a stepwise multivariate logistic regression analysis. These cutoff values of Th and NK cells could help to distinguish OR from NOR cases accurately and provide clinical benefits.

The characteristics of Laennec's capsule around the hepatic veins: A histological study based on 71 liver surgical specimens.

Background: Laennec's capsule is a fibrous membrane attached to the surface of the liver, which is independent of the hepatic veins. However, the presence of Laennec's capsule surrounding the peripheral hepatic veins is controversial. This study aims to describe the characteristic of Laennec's capsule around the hepatic veins at all levels. Methods: Seventy-one hepatic surgical specimens were collected along the cross and longitudinal sections of the hepatic vein. Tissue sections of 3-4 mm were cut and stained with hematoxylin and eosin (H&E), resorcinol-fuchsin (R&F), and Victoria blue (V&B). Elastic fibers were observed around the hepatic veins. They were measured using K-Viewer software. Results: Morphologically, we observed a thin, dense fibrous layer (so-called Laennec's capsule) around the hepatic veins at all levels, which was different from the thick elastic fibers of the hepatic vein wall. Therefore, there was a potential gap between Laennec's capsule and the hepatic veins. Laennec's capsule was visualized significantly better with R&F and V&B staining compared to H&E staining. The thickness of Laennec's capsule around the main, first, and secondary branches of the hepatic vein were 79.86 ± 24.20 µm, 48.41 ± 18.25 µm, and 23.56 ± 10.03 µm in the R&F staining, and 80.15 ± 21.85 µm, 49.46 ± 17.52 µm, and 25.05 ± 11.03 µm in the V&B staining, respectively. They were significantly different from each other (P < .001). Conclusion: The hepatic veins were surrounded by Laennec's capsule at all levels, including the peripheral hepatic veins. However, it is thinner along the vein branches. The gap between the Laennec's capsule and hepatic veins shows potential supplemental value for liver surgery.

Radiomic feature repeatability and its impact on prognostic model generalizability: A multi-institutional study on nasopharyngeal carcinoma patients.

BACKGROUND AND PURPOSE: To investigate the radiomic feature (RF) repeatability via perturbation and its impact on cross-institutional prognostic model generalizability in Nasopharyngeal Carcinoma (NPC) patients. MATERIALS AND METHODS: 286 and 183 NPC patients from two institutions were included for model training and validation. Perturbations with random translations and rotations were applied to contrast-enhanced T1-weighted (CET1-w) MR images. RFs were extracted from primary tumor volume under a wide range of image filtering and discretization settings. RF repeatability was assessed by intraclass correlation coefficient (ICC), which was used to equally separate the RFs into low- and high-repeatable groups by the median value. After feature selection, multivariate Cox regression and Kaplan-Meier analysis were independently employed to develop and analyze prognostic models. Concordance index (C-index) and P-value from log-rank test were used to assess model performance. RESULTS: Most textural RFs from high-pass wavelet-filtered images were susceptible to image perturbations. It was more prominent when a smaller discretization bin number was used (e.g., 8, mean ICC = 0.69). Using high-repeatable RFs for model development yielded a significantly higher C-index (0.63) in the validation cohort than when only low-repeatable RFs were used (0.57, P = 0.024), suggesting higher model generalizability. Besides, significant risk stratification in the validation cohort was observed only when high-repeatable RFs were used (P < 0.001). CONCLUSION: Repeatability of RFs from high-pass wavelet-filtered CET1-w MR images of primary NPC tumor was poor, particularly when a smaller bin number was used. Exclusive use of high-repeatable RFs is suggested to safeguard model generalizability for wide-spreading clinical utilization.

Conversion surgery for advanced hepatocellular carcinoma after combination treatment of lenvatinib and camrelizumab: a case report.

BACKGROUND: Hepatocellular carcinoma (HCC) is an aggressive malignancy with high morbidity and mortality. Conversion therapy can improve surgical resection rate and prolong survival time for patients with advanced HCC. We show that combination therapy with lenvatinib and camrelizumab is a novel approach to downstage unresectable HCC. CASE PRESENTATION: A 49-year-old man was diagnosed with massive HCC with hilar lymph node and lung metastases. Since radical resection was not feasible, lenvatinib and camrelizumab were administered as first-line therapy. After 10 cycles of camrelizumab and continuous oral administration of lenvatinib, the tumor exhibited striking shrinkage in volume indicating a partial radiological response, accompanied by a reduction in the alpha-fetoprotein levels, followed by salvage resection. Intriguingly, an improvement in predictive biomarkers, like lactate dehydrogenase (LDH) and neutrophil-to-lymphocyte ratio (NLR), was observed. Notably, the pathological examination found high levels of necrosis in the resected tumor, and flow cytometry analysis indicated a significant increase in the ratio of CD5+ and CD5- B lymphocytes in the peripheral blood. After the treatment, the overall survival period was over 24 months, and no recurrence was observed 17-month post-surgery. CONCLUSIONS: A combination of lenvatinib and camrelizumab may be a new conversion therapy for initially unresectable HCC to resectable HCC, thus contributing to improve the disease prognosis. In addition, the combination regimen could cause an activated immune response, and LDH, NLR, and CD5+ B-cell levels might be predictors for immunotherapy efficacy.

Lung Subregion Partitioning by Incremental Dose Intervals Improves Omics-Based Prediction for Acute Radiation Pneumonitis in Non-Small-Cell Lung Cancer Patients.

Purpose: To evaluate the effectiveness of features obtained from our proposed incremental-dose-interval-based lung subregion segmentation (IDLSS) for predicting grade ≥ 2 acute radiation pneumonitis (ARP) in lung cancer patients upon intensity-modulated radiotherapy (IMRT). (1) Materials and Methods: A total of 126 non-small-cell lung cancer patients treated with IMRT were retrospectively analyzed. Five lung subregions (SRs) were generated by the intersection of the whole lung (WL) and five sub-regions receiving incremental dose intervals. A total of 4610 radiomics features (RF) from pre-treatment planning computed tomographic (CT) and 213 dosiomics features (DF) were extracted. Six feature groups, including WL-RF, WL-DF, SR-RF, SR-DF, and the combined feature sets of WL-RDF and SR-RDF, were generated. Features were selected by using a variance threshold, followed by a Student t-test. Pearson's correlation test was applied to remove redundant features. Subsequently, Ridge regression was adopted to develop six models for ARP using the six feature groups. Thirty iterations of resampling were implemented to assess overall model performance by using the area under the Receiver-Operating-Characteristic curve (AUC), accuracy, precision, recall, and F1-score. (2) Results: The SR-RDF model achieved the best classification performance and provided significantly better predictability than the WL-RDF model in training cohort (Average AUC: 0.98 ± 0.01 vs. 0.90 ± 0.02, p < 0.001) and testing cohort (Average AUC: 0.88 ± 0.05 vs. 0.80 ± 0.04, p < 0.001). Similarly, predictability of the SR-DF model was significantly stronger than that of the WL-DF model in training cohort (Average AUC: 0.88 ± 0.03 vs. 0.70 ± 0.030, p < 0.001) and in testing cohort (Average AUC: 0.74 ± 0.08 vs. 0.65 ± 0.06, p < 0.001). By contrast, the SR-RF model significantly outperformed the WL-RF model only in the training set (Average AUC: 0.93 ± 0.02 vs. 0.85 ± 0.03, p < 0.001), but not in the testing set (Average AUC: 0.79 ± 0.05 vs. 0.77 ± 0.07, p = 0.13). (3) Conclusions: Our results demonstrated that the IDLSS method improved model performance for classifying ARP with grade ≥ 2 when using dosiomics or combined radiomics-dosiomics features.

Meta-Analysis of the Application Effect of Different Modalities of Thermal Ablation and Surgical Treatment in Papillary Thyroid Microcarcinoma.

Background: Papillary thyroid microcarcinoma (PTMC) refers to papillary thyroid carcinoma (PTC) with a maximum diameter of 10 mm. Thermal ablation, including radiofrequency ablation (RFA), microwave ablation (MWA), and laser ablation (LA), has been applied in the treatment of benign thyroid nodules and captured extensive attention. At present, the application of thermal ablation in PTMC has been extensively reported, but outcomes such as volume reduction rate (VRR), complete remission rate (CRR), and adverse reaction rate (ARR) vary considerably. Therefore, this meta-analysis was performed to evaluate the safety and efficacy of different treatment methods of PTMC. Methods: We did a systematic review and network meta-analysis. We searched PubMed, EMBase, and Cochrane-Library from the date of inception to January 10, 2022, to retrieve the VRR, CRR, and ARR of MWA, RFA, LA and surgical treatment of PTMC, and a meta-analysis was performed using the R meta-package. Odds ratios (ORs) and 95% confidence intervals (CIs) were calculated, and sensitivity analyses, cumulative meta-analyses, and publication bias were also performed. Relevant literature was retrieved with keywords; the eligible cohort studies were screened based on the established inclusion and exclusion criteria. Results: A total of 1515 patients were included in the 12-month follow-up. The overall VRR was 86.25% (95% CI: 77.89, 94.60), and the VRR was RFA > WMA > LA, but the differences were not significant. A total of 1483 patients were included in the last follow-up. The overall VRR was 99.41% (95% CI: 99.11, 99.72), and the VRR was RFA > WMA > LA, but the differences were not significant. A total of 1622 patients showed complete remission at the last follow-up, and the overall CRR was 0.63 (95% CI: 0.46, 0.79). The CRR was RFA > LA > WMA, but the differences were not significant. A total of 1883 patients had adverse reactions at the last follow-up, and the overall ARR was 0.06 (95% CI: 0.03, 0.08). The ARR at the last follow-up was RFA = Surg < LA < WMA. The ARR of the RFA and Surg subgroups was significantly lower than that of the WMA subgroup. Conclusions: Similar good efficacy and safety profiles were observed in WMA, RFA, LA, and surgical treatment in PTMC, among which RFA showed the best volume reduction, complete remission rate, and adverse reaction reduction. However, there is a slight bias in the limited literature included in this study, and we did not conduct or refer to mechanistic studies to confirm its specific mechanism of action. Clinicians are advised to use their discretion in the choice of treatment.

Improving radiomic model reliability using robust features from perturbations for head-and-neck carcinoma.

Background: Using high robust radiomic features in modeling is recommended, yet its impact on radiomic model is unclear. This study evaluated the radiomic model's robustness and generalizability after screening out low-robust features before radiomic modeling. The results were validated with four datasets and two clinically relevant tasks. Materials and methods: A total of 1,419 head-and-neck cancer patients' computed tomography images, gross tumor volume segmentation, and clinically relevant outcomes (distant metastasis and local-regional recurrence) were collected from four publicly available datasets. The perturbation method was implemented to simulate images, and the radiomic feature robustness was quantified using intra-class correlation of coefficient (ICC). Three radiomic models were built using all features (ICC > 0), good-robust features (ICC > 0.75), and excellent-robust features (ICC > 0.95), respectively. A filter-based feature selection and Ridge classification method were used to construct the radiomic models. Model performance was assessed with both robustness and generalizability. The robustness of the model was evaluated by the ICC, and the generalizability of the model was quantified by the train-test difference of Area Under the Receiver Operating Characteristic Curve (AUC). Results: The average model robustness ICC improved significantly from 0.65 to 0.78 (P< 0.0001) using good-robust features and to 0.91 (P< 0.0001) using excellent-robust features. Model generalizability also showed a substantial increase, as a closer gap between training and testing AUC was observed where the mean train-test AUC difference was reduced from 0.21 to 0.18 (P< 0.001) in good-robust features and to 0.12 (P< 0.0001) in excellent-robust features. Furthermore, good-robust features yielded the best average AUC in the unseen datasets of 0.58 (P< 0.001) over four datasets and clinical outcomes. Conclusions: Including robust only features in radiomic modeling significantly improves model robustness and generalizability in unseen datasets. Yet, the robustness of radiomic model has to be verified despite building with robust radiomic features, and tightly restricted feature robustness may prevent the optimal model performance in the unseen dataset as it may lower the discrimination power of the model.

Systematic Review on COVID-19 Readmission and Risk Factors: Future of Machine Learning in COVID-19 Readmission Studies.

In this review, current studies on hospital readmission due to infection of COVID-19 were discussed, compared, and further evaluated in order to understand the current trends and progress in mitigation of hospital readmissions due to COVID-19. Boolean expression of ("COVID-19" OR "covid19" OR "covid" OR "coronavirus" OR "Sars-CoV-2") AND ("readmission" OR "re-admission" OR "rehospitalization" OR "rehospitalization") were used in five databases, namely Web of Science, Medline, Science Direct, Google Scholar and Scopus. From the search, a total of 253 articles were screened down to 26 articles. In overall, most of the research focus on readmission rates than mortality rate. On the readmission rate, the lowest is 4.2% by Ramos-Martínez et al. from Spain, and the highest is 19.9% by Donnelly et al. from the United States. Most of the research (n = 13) uses an inferential statistical approach in their studies, while only one uses a machine learning approach. The data size ranges from 79 to 126,137. However, there is no specific guide to set the most suitable data size for one research, and all results cannot be compared in terms of accuracy, as all research is regional studies and do not involve data from the multi region. The logistic regression is prevalent in the research on risk factors of readmission post-COVID-19 admission, despite each of the research coming out with different outcomes. From the word cloud, age is the most dominant risk factor of readmission, followed by diabetes, high length of stay, COPD, CKD, liver disease, metastatic disease, and CAD. A few future research directions has been proposed, including the utilization of machine learning in statistical analysis, investigation on dominant risk factors, experimental design on interventions to curb dominant risk factors and increase the scale of data collection from single centered to multi centered.

Building reliable radiomic models using image perturbation.

Radiomic model reliability is a central premise for its clinical translation. Presently, it is assessed using test-retest or external data, which, unfortunately, is often scarce in reality. Therefore, we aimed to develop a novel image perturbation-based method (IPBM) for the first of its kind toward building a reliable radiomic model. We first developed a radiomic prognostic model for head-and-neck cancer patients on a training (70%) and evaluated on a testing (30%) cohort using C-index. Subsequently, we applied the IPBM to CT images of both cohorts (Perturbed-Train and Perturbed-Test cohort) to generate 60 additional samples for both cohorts. Model reliability was assessed using intra-class correlation coefficient (ICC) to quantify consistency of the C-index among the 60 samples in the Perturbed-Train and Perturbed-Test cohorts. Besides, we re-trained the radiomic model using reliable RFs exclusively (ICC > 0.75) to validate the IPBM. Results showed moderate model reliability in Perturbed-Train (ICC: 0.565, 95%CI 0.518-0.615) and Perturbed-Test (ICC: 0.596, 95%CI 0.527-0.670) cohorts. An enhanced reliability of the re-trained model was observed in Perturbed-Train (ICC: 0.782, 95%CI 0.759-0.815) and Perturbed-Test (ICC: 0.825, 95%CI 0.782-0.867) cohorts, indicating validity of the IPBM. To conclude, we demonstrated capability of the IPBM toward building reliable radiomic models, providing community with a novel model reliability assessment strategy prior to prospective evaluation.

A Novel Deep Learning Network and Its Application for Pulmonary Nodule Segmentation.

Pulmonary nodules are the early manifestation of lung cancer, which appear as circular shadow of no more than 3 cm on the computed tomography (CT) image. Accurate segmentation of the contours of pulmonary nodules can help doctors improve the efficiency of diagnosis. Deep learning has achieved great success in computer vision. In this study, we propose a novel network for pulmonary nodule segmentation from CT images based on U-NET. The proposed network has two merits: one is that it introduces dense connection to transfer and utilize features. Additionally, the problem of gradient disappearance can be avoided. The second is that it introduces a new loss function which is tolerance on the pixels near the borders of the nodule. Experimental results show that the proposed network at least achieves 1% improvement compared with other state-of-art networks in terms of different criteria.