Bioinformatics Identification of Regulatory Genes and Mechanism Related to Hypoxia-Induced PD-L1 Inhibitor Resistance in Hepatocellular Carcinoma.

The combination of a PD-L1 inhibitor and an anti-angiogenic agent has become the new reference standard in the first-line treatment of non-excisable hepatocellular carcinoma (HCC) due to the survival advantage, but its objective response rate remains low at 36%. Evidence shows that PD-L1 inhibitor resistance is attributed to hypoxic tumor microenvironment. In this study, we performed bioinformatics analysis to identify genes and the underlying mechanisms that improve the efficacy of PD-L1 inhibition. Two public datasets of gene expression profiles, (1) HCC tumor versus adjacent normal tissue (N = 214) and (2) normoxia versus anoxia of HepG2 cells (N = 6), were collected from Gene Expression Omnibus (GEO) database. We identified HCC-signature and hypoxia-related genes, using differential expression analysis, and their 52 overlapping genes. Of these 52 genes, 14 PD-L1 regulator genes were further identified through the multiple regression analysis of TCGA-LIHC dataset (N = 371), and 10 hub genes were indicated in the protein-protein interaction (PPI) network. It was found that POLE2, GABARAPL1, PIK3R1, NDC80, and TPX2 play critical roles in the response and overall survival in cancer patients under PD-L1 inhibitor treatment. Our study provides new insights and potential biomarkers to enhance the immunotherapeutic role of PD-L1 inhibitors in HCC, which can help in exploring new therapeutic strategies.

Development and validation of a preoperative CT-based radiomic nomogram to predict pathology invasiveness in patients with a solitary pulmonary nodule: a machine learning approach, multicenter, diagnostic study.

OBJECTIVES: To develop and validate a preoperative CT-based nomogram combined with radiomic and clinical-radiological signatures to distinguish preinvasive lesions from pulmonary invasive lesions. METHODS: This was a retrospective, diagnostic study conducted from August 1, 2018, to May 1, 2020, at three centers. Patients with a solitary pulmonary nodule were enrolled in the GDPH center and were divided into two groups (7:3) randomly: development (n = 149) and internal validation (n = 54). The SYSMH center and the ZSLC Center formed an external validation cohort of 170 patients. The least absolute shrinkage and selection operator (LASSO) algorithm and logistic regression analysis were used to feature signatures and transform them into models. RESULTS: The study comprised 373 individuals from three independent centers (female: 225/373, 60.3%; median [IQR] age, 57.0 [48.0-65.0] years). The AUCs for the combined radiomic signature selected from the nodular area and the perinodular area were 0.93, 0.91, and 0.90 in the three cohorts. The nomogram combining the clinical and combined radiomic signatures could accurately predict interstitial invasion in patients with a solitary pulmonary nodule (AUC, 0.94, 0.90, 0.92) in the three cohorts, respectively. The radiomic nomogram outperformed any clinical or radiomic signature in terms of clinical predictive abilities, according to a decision curve analysis and the Akaike information criteria. CONCLUSIONS: This study demonstrated that a nomogram constructed by identified clinical-radiological signatures and combined radiomic signatures has the potential to precisely predict pathology invasiveness. KEY POINTS: • The radiomic signature from the perinodular area has the potential to predict pathology invasiveness of the solitary pulmonary nodule. • The new radiomic nomogram was useful in clinical decision-making associated with personalized surgical intervention and therapeutic regimen selection in patients with early-stage non-small-cell lung cancer.

Oxygen Saturation and Heart Rate Variations as Predictors of Intradialytic Hypotension.

AIntradialytic hypotension (IDH) occurring during hemodialysis (HD) may cause severe complications and can be life-threatening. IDH is a common symptom in patients with end stage renal disease undergoing HD. Currently, no effective predictive models for IDH exist. This study analyzed data on variations in oxygen saturation (SaO2) and heart rate (HR) in 68 patients during their HD sessions by using sequence alignment and Boolean algebra. Three classifiers derived from SaO2 and HR variation data were developed as predictors for predetermining IDH occurrence within 30 minutes. The accuracy of these classifiers in predicting IDH occurrence was approximately 80%. SaO2 and HR variations can potentially be used as predictors for developing an alarm system for detecting IDH occurrence.

Disease-specific target gene expression profiling of molecular imaging probes: database development and clinical validation.

Molecular imaging probes can target abnormal gene expression patterns in patients and allow early diagnosis of disease. For selecting a suitable imaging probe, the current Molecular Imaging and Contrast Agent Database (MICAD) provides descriptive and qualitative information on imaging probe characteristics and properties. However, MICAD does not support linkage with the expression profiles of target genes. The proposed Disease-specific Imaging Probe Profiling (DIPP) database quantitatively archives and presents the gene expression profiles of targets across different diseases, anatomic regions, and subcellular locations, providing an objective reference for selecting imaging probes. The DIPP database was validated with a clinical positron emission tomography (PET) study on lung cancer and an in vitro study on neuroendocrine cancer. The retrieved records show that choline kinase beta and glucose transporters were positively and significantly associated with lung cancer among the targets of 11C-choline and [18F]fluoro-2-deoxy-2-d-glucose (FDG), respectively. Their significant overexpressions corresponded to the findings that the uptake rate of FDG increased with tumor size but that of 11C-choline remained constant. Validated with the in vitro study, the expression profiles of disease-associated targets can indicate the eligibility of patients for clinical trials of the treatment probe. A Web search tool of the DIPP database is available at http://www.polyu.edu.hk/bmi/dipp/.

Enhancing Diagnostic Images to Improve the Performance of the Segment Anything Model in Medical Image Segmentation.

Medical imaging serves as a crucial tool in current cancer diagnosis. However, the quality of medical images is often compromised to minimize the potential risks associated with patient image acquisition. Computer-aided diagnosis systems have made significant advancements in recent years. These systems utilize computer algorithms to identify abnormal features in medical images, assisting radiologists in improving diagnostic accuracy and achieving consistency in image and disease interpretation. Importantly, the quality of medical images, as the target data, determines the achievable level of performance by artificial intelligence algorithms. However, the pixel value range of medical images differs from that of the digital images typically processed via artificial intelligence algorithms, and blindly incorporating such data for training can result in suboptimal algorithm performance. In this study, we propose a medical image-enhancement scheme that integrates generic digital image processing and medical image processing modules. This scheme aims to enhance medical image data by endowing them with high-contrast and smooth characteristics. We conducted experimental testing to demonstrate the effectiveness of this scheme in improving the performance of a medical image segmentation algorithm.

Contrast-Enhanced Ultrasound-Based Radiomics for the Prediction of Axillary Lymph Nodes Status in Breast Cancer.

BACKGROUND: Breast cancer is the leading cause of cancer-related deaths in the female population. Axillary lymph nodes (ALN) are a group of the most common metastatic sites of breast cancer. Timely assessment of ALN status is of paramount clinical importance for medical decision making. AIMS: To utilize contrast-enhanced ultrasound (CEUS)-based radiomics models for noninvasive pretreatment prediction of ALN status. METHODS AND RESULTS: Clinical data and pretreatment CEUS images of primary breast tumors were retrospectively studied to build radiomics signatures for pretreatment prediction of nodal status between May 2015 and July 2021. The cases were divided into the training cohorts and test cohorts in a 9:1 ratio. The mRMR approach and stepwise forward logistic regression technique were used for feature selection, followed by the multivariate logistic regression technique for building radiomics signatures in the training cohort. The confusion matrix and receiver operating characteristic (ROC) analysis were used for accessing the prediction efficacy of the radiomics models. The radiomics models, which consist of six features, achieved predictive accuracy with the area under the ROC curve (AUC) of 0.713 in the test set for predicting lymph node metastasis. CONCLUSION: The CEUS-based radiomics is promising to be developed as a reliable noninvasive tool for predicting ALN status.

Comparative Analysis of Repeatability in CT Radiomics and Dosiomics Features under Image Perturbation: A Study in Cervical Cancer Patients.

This study aims to evaluate the repeatability of radiomics and dosiomics features via image perturbation of patients with cervical cancer. A total of 304 cervical cancer patients with planning CT images and dose maps were retrospectively included. Random translation, rotation, and contour randomization were applied to CT images and dose maps before radiomics feature extraction. The repeatability of radiomics and dosiomics features was assessed using intra-class correlation of coefficient (ICC). Pearson correlation coefficient (r) was adopted to quantify the correlation between the image characteristics and feature repeatability. In general, the repeatability of dosiomics features was lower compared with CT radiomics features, especially after small-sigma Laplacian-of-Gaussian (LoG) and wavelet filtering. More repeatable features (ICC > 0.9) were observed when extracted from the original, Large-sigma LoG filtered, and LLL-/LLH-wavelet filtered images. Positive correlations were found between image entropy and high-repeatable feature number in both CT and dose (r = 0.56, 0.68). Radiomics features showed higher repeatability compared to dosiomics features. These findings highlight the potential of radiomics features for robust quantitative imaging analysis in cervical cancer patients, while suggesting the need for further refinement of dosiomics approaches to enhance their repeatability.

Advanced technologies for studying circulating tumor cells at the protein level.

Metastasis is the main cause of cancer death. As the tumor progresses, cells from the primary tumor site are shed into the bloodstream as circulating tumor cells (CTCs). Eventually, these cells colonize other organs and form distant metastases. It is therefore imperative that we gain a better understanding of the biological characteristics of CTCs for development of novel treatment modalities to minimize metastasis-associated cancer deaths. In recent years, rapid developments in technologies for the study of CTCs have taken place. We now have a variety of tools for the isolation and examination of CTCs which were not available before. This review introduces some commonly used protein markers in CTC investigations and summarizes a few advanced technologies which have been successfully applied for studying CTC biology at the protein level.

Synergistic markers based on inter-covariate association estimate treatment option with lower propensity to covariates.

Background: Propensity constitutes a common problem in identifying clinical outcome prediction model whose covariates include the treatment option, which is assumed to be randomly assigned but indeed dependent of other covariates in the training data. The genuine effect of treatment option cannot be elucidated under the influence of propensity. Existing approaches, such as matched-pairs study design, still cannot solve the problem for imbalanced or small datasets. Methods: This work proposed an anti-propensity estimate of treatment option, which is generated by support vector classifier based on two synergistic markers that represent the lower and upper limits of inter-covariate association level. The algorithm for generating the synergistic markers was illustrated and the performance was evaluated on a public dataset of gene expression levels, which were obtained from surgically excised tumor samples in non-small cell lung cancer (NSCLC) patients where treatment option, i.e., adjuvant therapy or not, was known. Results: Six covariates represented by the expression levels of ZNF217, ERCC3, PMS1, PIK3CB, BARD1, and MAPK1, were selected to generate two synergistic markers and classifier for estimating the adjuvant therapy option with substantially attenuated propensity. The estimation accuracy attained an area under the receiver-operating characteristics curve, 0.78, in the test set. Conclusions: The proposed synergistic markers demonstrated a parsimonious and anti-propensity estimation of treatment option, which is ready for the further evaluation and application in the clinical outcome prediction model.

MDM-U-Net: A novel network for renal cancer structure segmentation.

Accurate segmentation of the renal cancer structure, including the kidney, renal tumors, veins, and arteries, has great clinical significance, which can assist clinicians in diagnosing and treating renal cancer. For accurate segmentation of the renal cancer structure in contrast-enhanced computed tomography (CT) images, we proposed a novel encoder-decoder structure segmentation network named MDM-U-Net comprising a multi-scale anisotropic convolution block, dual activation attention block, and multi-scale deep supervision mechanism. The multi-scale anisotropic convolution block was used to improve the feature extraction ability of the network, the dual activation attention block as a channel-wise mechanism was used to guide the network to exploit important information, and the multi-scale deep supervision mechanism was used to supervise the layers of the decoder part for improving segmentation performance. In this study, we developed a feasible and generalizable MDM-U-Net model for renal cancer structure segmentation, trained the model from the public KiPA22 dataset, and tested it on the KiPA22 dataset and an in-house dataset. For the KiPA22 dataset, our method ranked first in renal cancer structure segmentation, achieving state-of-the-art (SOTA) performance in terms of 6 of 12 evaluation metrics (3 metrics per structure). For the in-house dataset, our method achieves SOTA performance in terms of 9 of 12 evaluation metrics (3 metrics per structure), demonstrating its superiority and generalization ability over the compared networks in renal structure segmentation from contrast-enhanced CT scans.

Diagnostic efficiency on ultrasound shear wave elastography in evaluation of steatosis severity for non-alcoholic fatty liver disease: a rat model.

BACKGROUND: The pathological feature of steatosis affects the elasticity values measured by shear wave elastography (SWE) is still controversial in non-alcoholic fatty liver disease (NAFLD). The aim of this study is to demonstrate the influence of steatosis on liver stiffness measured by SWE on a rat model with NAFLD and analyze feasibility of SWE for grading steatosis in absence of fibrosis. METHODS: Sixty-six rats were fed with methionine choline deficient diet or standard diet to produce various stages of steatosis; 48 rats were available for final analysis. Rats underwent abdominal ultrasound SWE examination and pathological assessment. Liver histopathology was analyzed to assess the degree of steatosis, inflammation, ballooning, and fibrosis according to the non-alcoholic fatty liver disease activity score. The diagnostic performance of SWE for differentiating steatosis stages was estimated according to the receiver operating characteristic (ROC) curve. Decision curve analysis (DCA) was conducted to determine clinical usefulness and the areas under DCA (AUDCAs) calculated. RESULTS: In multivariate analysis, steatosis was an independent factor affecting the mean elastic modules (B = 1.558, P < 0.001), but not inflammation (B = - 0.031, P = 0.920) and ballooning (B = 0.216, P = 0.458). After adjusting for inflammation and ballooning, the AUROC of the mean elasticity for identifying S ≥ S1 was 0.956 (95%CI: 0.872-0.998) and the AUDCA, 0.621. The AUROC for distinguishing S ≥ S2 and S = S3 was 0.987 (95%CI: 0.951-1.000) and 0.920 (95%CI: 0.816-0.986) and the AUDCA was 0.506 and 0.256, respectively. CONCLUSIONS: Steatosis is associated with liver stiffness and SWE may have the feasibility to be introduced as an assistive technology in grading steatosis for patients with NAFLD in absence of fibrosis.

CT-based methods for assessment of metabolic dysfunction associated with fatty liver disease.

Metabolic dysfunction-associated fatty liver disease (MAFLD), previously called metabolic nonalcoholic fatty liver disease, is the most prevalent chronic liver disease worldwide. The multi-factorial nature of MAFLD severity is delineated through an intricate composite analysis of the grade of activity in concert with the stage of fibrosis. Despite the preeminence of liver biopsy as the diagnostic and staging reference standard, its invasive nature, pronounced interobserver variability, and potential for deleterious effects (encompassing pain, infection, and even fatality) underscore the need for viable alternatives. We reviewed computed tomography (CT)-based methods for hepatic steatosis quantification (liver-to-spleen ratio; single-energy "quantitative" CT; dual-energy CT; deep learning-based methods; photon-counting CT) and hepatic fibrosis staging (morphology-based CT methods; contrast-enhanced CT biomarkers; dedicated postprocessing methods including liver surface nodularity, liver segmental volume ratio, texture analysis, deep learning methods, and radiomics). For dual-energy and photon-counting CT, the role of virtual non-contrast images and material decomposition is illustrated. For contrast-enhanced CT, normalized iodine concentration and extracellular volume fraction are explained. The applicability and salience of these approaches for clinical diagnosis and quantification of MAFLD are discussed.Relevance statementCT offers a variety of methods for the assessment of metabolic dysfunction-associated fatty liver disease by quantifying steatosis and staging fibrosis.Key points• MAFLD is the most prevalent chronic liver disease worldwide and is rapidly increasing.• Both hardware and software CT advances with high potential for MAFLD assessment have been observed in the last two decades.• Effective estimate of liver steatosis and staging of liver fibrosis can be possible through CT.

Pretreatment radiomic biomarker for immunotherapy responder prediction in stage IB-IV NSCLC (LCDigital-IO Study): a multicenter retrospective study.

BACKGROUND: The predictive efficacy of current biomarker of immune checkpoint inhibitors (ICIs) is not sufficient. This study investigated the causality between radiomic biomarkers and immunotherapy response status in patients with stage IB-IV non-small cell lung cancer (NSCLC), including its biological context for ICIs treatment response prediction. METHODS: CT images from 319 patients with pretreatment NSCLC receiving immunotherapy between January 2015 and November 2021 were retrospectively collected and composed a discovery (n=214), independent validation (n=54), and external test cohort (n=51). A set of 851 features was extracted from tumorous and peritumoral volumes of interest (VOIs). The reference standard is the durable clinical benefit (DCB, sustained disease control for more than 6 months assessed via radiological evaluation). The predictive value of combined radiomic signature (CRS) for pathological response was subsequently assessed in another cohort of 98 patients with resectable NSCLC receiving ICIs preoperatively. The association between radiomic features and tumor immune landscape on the online data set (n=60) was also examined. A model combining clinical predictor and radiomic signatures was constructed to improve performance further. RESULTS: CRS discriminated DCB and non-DCB patients well in the training and validation cohorts with an area under the curve (AUC) of 0.82, 95% CI: 0.75 to 0.88, and 0.75, 95% CI: 0.64 to 0.87, respectively. In this study, the predictive value of CRS was better than programmed cell death ligand-1 (PD-L1) expression (AUC of PD-L1 subset: 0.59, 95% CI: 0.50 to 0.69) or clinical model (AUC: 0.66, 95% CI: 0.51 to 0.81). After combining the clinical signature with CRS, the predictive performance improved further with an AUC of 0.837, 0.790 and 0.781 in training, validation and D2 cohorts, respectively. When predicting pathological response, CRS divided patients into a major pathological response (MPR) and non-MPR group (AUC: 0.76, 95% CI: 0.67 to 0.81). Moreover, CRS showed a promising stratification ability on overall survival (HR: 0.49, 95% CI: 0.27 to 0.89; p=0.020) and progression-free survival (HR: 0.43, 95% CI: 0.26 to 0.74; p=0.002). CONCLUSION: By analyzing both tumorous and peritumoral regions of CT images in a radiomic strategy, we developed a non-invasive biomarker for distinguishing responders of ICIs therapy and stratifying their survival outcome efficiently, which may support the clinical decisions on the use of ICIs in advanced as well as patients with resectable NSCLC.

Deep learning attention-guided radiomics for COVID-19 chest radiograph classification.

Background: Accurate assessment of coronavirus disease 2019 (COVID-19) lung involvement through chest radiograph plays an important role in effective management of the infection. This study aims to develop a two-step feature merging method to integrate image features from deep learning and radiomics to differentiate COVID-19, non-COVID-19 pneumonia and normal chest radiographs (CXR). Methods: In this study, a deformable convolutional neural network (deformable CNN) was developed and used as a feature extractor to obtain 1,024-dimensional deep learning latent representation (DLR) features. Then 1,069-dimensional radiomics features were extracted from the region of interest (ROI) guided by deformable CNN's attention. The two feature sets were concatenated to generate a merged feature set for classification. For comparative experiments, the same process has been applied to the DLR-only feature set for verifying the effectiveness of feature concatenation. Results: Using the merged feature set resulted in an overall average accuracy of 91.0% for three-class classification, representing a statistically significant improvement of 0.6% compared to the DLR-only classification. The recall and precision of classification into the COVID-19 class were 0.926 and 0.976, respectively. The feature merging method was shown to significantly improve the classification performance as compared to using only deep learning features, regardless of choice of classifier (P value <0.0001). Three classes' F1-score were 0.892, 0.890, and 0.950 correspondingly (i.e., normal, non-COVID-19 pneumonia, COVID-19). Conclusions: A two-step COVID-19 classification framework integrating information from both DLR and radiomics features (guided by deep learning attention mechanism) has been developed. The proposed feature merging method has been shown to improve the performance of chest radiograph classification as compared to the case of using only deep learning features.

Consensus Statements on Precision Oncology in the China Greater Bay Area.

BACKGROUND: Next-generation sequencing comprehensive genomic panels (NGS CGPs) have enabled the delivery of tailor-made therapeutic approaches to improve survival outcomes in patients with cancer. Within the China Greater Bay Area (GBA), territorial differences in clinical practices and health care systems and strengthening collaboration warrant a regional consensus to consolidate the development and integration of precision oncology (PO). Therefore, the Precision Oncology Working Group (POWG) formulated standardized principles for the clinical application of molecular profiling, interpretation of genomic alterations, and alignment of actionable mutations with sequence-directed therapy to deliver clinical services of excellence and evidence-based care to patients with cancer in the China GBA. METHODS: Thirty experts used a modified Delphi method. The evidence extracted to support the statements was graded according to the GRADE system and reported according to the Revised Standards for Quality Improvement Reporting Excellence guidelines, version 2.0. RESULTS: The POWG reached consensus in six key statements: harmonization of reporting and quality assurance of NGS; molecular tumor board and clinical decision support systems for PO; education and training; research and real-world data collection, patient engagement, regulations, and financial reimbursement of PO treatment strategies; and clinical recommendations and implementation of PO in clinical practice. CONCLUSION: POWG consensus statements standardize the clinical application of NGS CGPs, streamline the interpretation of clinically significant genomic alterations, and align actionable mutations with sequence-directed therapies. The POWG consensus statements may harmonize the utility and delivery of PO in China's GBA.

The feasibility and accuracy of machine learning in improving safety and efficiency of thrombolysis for patients with stroke: Literature review and proposed improvements.

In the treatment of ischemic stroke, timely and efficient recanalization of occluded brain arteries can successfully salvage the ischemic brain. Thrombolysis is the first-line treatment for ischemic stroke. Machine learning models have the potential to select patients who could benefit the most from thrombolysis. In this study, we identified 29 related previous machine learning models, reviewed the models on the accuracy and feasibility, and proposed corresponding improvements. Regarding accuracy, lack of long-term outcome, treatment option consideration, and advanced radiological features were found in many previous studies in terms of model conceptualization. Regarding interpretability, most of the previous models chose restrictive models for high interpretability and did not mention processing time consideration. In the future, model conceptualization could be improved based on comprehensive neurological domain knowledge and feasibility needs to be achieved by elaborate computer science algorithms to increase the interpretability of flexible algorithms and shorten the processing time of the pipeline interpreting medical images.

Augmented Features Synergize Radiomics in Post-Operative Survival Prediction and Adjuvant Therapy Recommendation for Non-Small Cell Lung Cancer.

BACKGROUND: Owing to the cytotoxic effect, it is challenging for clinicians to decide whether post-operative adjuvant therapy is appropriate for a non-small cell lung cancer (NSCLC) patient. Radiomics has proven its promising ability in predicting survival but research on its actionable model, particularly for supporting the decision of adjuvant therapy, is limited. METHODS: Pre-operative contrast-enhanced CT images of 123 NSCLC cases were collected, including 76, 13, 16, and 18 cases from R01 and AMC cohorts of The Cancer Imaging Archive (TCIA), Jiangxi Cancer Hospital and Guangdong Provincial People's Hospital respectively. From each tumor region, 851 radiomic features were extracted and two augmented features were derived therewith to estimate the likelihood of adjuvant therapy. Both Cox regression and machine learning models with the selected main and interaction effects of 853 features were trained using 76 cases from R01 cohort, and their test performances on survival prediction were compared using 47 cases from the AMC cohort and two hospitals. For those cases where adjuvant therapy was unnecessary, recommendations on adjuvant therapy were made again by the outperforming model and compared with those by IBM Watson for Oncology (WFO). RESULTS: The Cox model outperformed the machine learning model in predicting survival on the test set (C-Index: 0.765 vs. 0.675). The Cox model consists of 5 predictors, interestingly 4 of which are interactions with augmented features facilitating the modulation of adjuvant therapy option. While WFO recommended no adjuvant therapy for only 13.6% of cases that received unnecessary adjuvant therapy, the same recommendations by the identified Cox model were extended to 54.5% of cases (McNemar's test p = 0.0003). CONCLUSIONS: A Cox model with radiomic and augmented features could predict survival accurately and support the decision of adjuvant therapy for bettering the benefit of NSCLC patients.

Development and validation of bone-suppressed deep learning classification of COVID-19 presentation in chest radiographs.

Background: Coronavirus disease 2019 (COVID-19) is a pandemic disease. Fast and accurate diagnosis of COVID-19 from chest radiography may enable more efficient allocation of scarce medical resources and hence improved patient outcomes. Deep learning classification of chest radiographs may be a plausible step towards this. We hypothesize that bone suppression of chest radiographs may improve the performance of deep learning classification of COVID-19 phenomena in chest radiographs. Methods: Two bone suppression methods (Gusarev et al. and Rajaraman et al.) were implemented. The Gusarev and Rajaraman methods were trained on 217 pairs of normal and bone-suppressed chest radiographs from the X-ray Bone Shadow Suppression dataset (https://www.kaggle.com/hmchuong/xray-bone-shadow-supression). Two classifier methods with different network architectures were implemented. Binary classifier models were trained on the public RICORD-1c and RSNA Pneumonia Challenge datasets. An external test dataset was created retrospectively from a set of 320 COVID-19 positive patients from Queen Elizabeth Hospital (Hong Kong, China) and a set of 518 non-COVID-19 patients from Pamela Youde Nethersole Eastern Hospital (Hong Kong, China), and used to evaluate the effect of bone suppression on classifier performance. Classification performance, quantified by sensitivity, specificity, negative predictive value (NPV), accuracy and area under the receiver operating curve (AUC), for non-suppressed radiographs was compared to that for bone suppressed radiographs. Some of the pre-trained models used in this study are published at (https://github.com/danielnflam). Results: Bone suppression of external test data was found to significantly (P<0.05) improve AUC for one classifier architecture [from 0.698 (non-suppressed) to 0.732 (Rajaraman-suppressed)]. For the other classifier architecture, suppression did not significantly (P>0.05) improve or worsen classifier performance. Conclusions: Rajaraman suppression significantly improved classification performance in one classification architecture, and did not significantly worsen classifier performance in the other classifier architecture. This research could be extended to explore the impact of bone suppression on classification of different lung pathologies, and the effect of other image enhancement techniques on classifier performance.

Primary Tumor Radiomic Model for Identifying Extrahepatic Metastasis of Hepatocellular Carcinoma Based on Contrast Enhanced Computed Tomography.

This study aimed to identify radiomic features of primary tumor and develop a model for indicating extrahepatic metastasis of hepatocellular carcinoma (HCC). Contrast-enhanced computed tomographic (CT) images of 177 HCC cases, including 26 metastatic (MET) and 151 non-metastatic (non-MET), were retrospectively collected and analyzed. For each case, 851 radiomic features, which quantify shape, intensity, texture, and heterogeneity within the segmented volume of the largest HCC tumor in arterial phase, were extracted using Pyradiomics. The dataset was randomly split into training and test sets. Synthetic Minority Oversampling Technique (SMOTE) was performed to augment the training set to 145 MET and 145 non-MET cases. The test set consists of six MET and six non-MET cases. The external validation set is comprised of 20 MET and 25 non-MET cases collected from an independent clinical unit. Logistic regression and support vector machine (SVM) models were identified based on the features selected using the stepwise forward method while the deep convolution neural network, visual geometry group 16 (VGG16), was trained using CT images directly. Grey-level size zone matrix (GLSZM) features constitute four of eight selected predictors of metastasis due to their perceptiveness to the tumor heterogeneity. The radiomic logistic regression model yielded an area under receiver operating characteristic curve (AUROC) of 0.944 on the test set and an AUROC of 0.744 on the external validation set. Logistic regression revealed no significant difference with SVM in the performance and outperformed VGG16 significantly. As extrahepatic metastasis workups, such as chest CT and bone scintigraphy, are standard but exhaustive, radiomic model facilitates a cost-effective method for stratifying HCC patients into eligibility groups of these workups.

A Multi-Center Study of CT-Based Neck Nodal Radiomics for Predicting an Adaptive Radiotherapy Trigger of Ill-Fitted Thermoplastic Masks in Patients with Nasopharyngeal Carcinoma.

Significant lymph node shrinkage is common in patients with nasopharyngeal carcinoma (NPC) throughout radiotherapy (RT) treatment, causing ill-fitted thermoplastic masks (IfTMs). To deal with this, an ad hoc adaptive radiotherapy (ART) may be required to ensure accurate and safe radiation delivery and to maintain treatment efficacy. Presently, the entire procedure for evaluating an eligible ART candidate is time-consuming, resource-demanding, and highly inefficient. In the artificial intelligence paradigm, the pre-treatment identification of NPC patients at risk for IfTMs has become greatly demanding for achieving efficient ART eligibility screening, while no relevant studies have been reported. Hence, we aimed to investigate the capability of computed tomography (CT)-based neck nodal radiomics for predicting IfTM-triggered ART events in NPC patients via a multi-center setting. Contrast-enhanced CT and the clinical data of 124 and 58 NPC patients from Queen Elizabeth Hospital (QEH) and Queen Mary Hospital (QMH), respectively, were retrospectively analyzed. Radiomic (R), clinical (C), and combined (RC) models were developed using the ridge algorithm in the QEH cohort and evaluated in the QMH cohort using the median area under the receiver operating characteristics curve (AUC). Delong's test was employed for model comparison. Model performance was further assessed on 1000 replicates in both cohorts separately via bootstrapping. The R model yielded the highest "corrected" AUC of 0.784 (BCa 95%CI: 0.673-0.859) and 0.723 (BCa 95%CI: 0.534-0.859) in the QEH and QMH cohort following bootstrapping, respectively. Delong's test indicated that the R model performed significantly better than the C model in the QMH cohort (p < 0.0001), while demonstrating no significant difference compared to the RC model (p = 0.5773). To conclude, CT-based neck nodal radiomics was capable of predicting IfTM-triggered ART events in NPC patients in this multi-center study, outperforming the traditional clinical model. The findings of this study provide valuable insights for future study into developing an effective screening strategy for ART eligibility in NPC patients in the long run, ultimately alleviating the workload of clinical practitioners, streamlining ART procedural efficiency in clinics, and achieving personalized RT for NPC patients in the future.