Artificial intelligence assisted automatic screening of opportunistic osteoporosis in computed tomography images from different scanners.

OBJECTIVES: It is feasible to evaluate bone mineral density (BMD) and detect osteoporosis through an artificial intelligence (AI)-assisted system by using quantitative computed tomography (QCT) as a reference without additional radiation exposure or cost. METHODS: A deep-learning model developed based on 3312 low-dose chest computed tomography (LDCT) scans (trained with 2337 and tested with 975) achieved a mean dice similarity coefficient of 95.8% for T1-T12, L1, and L2 vertebral body (VB) segmentation on test data. We performed a model evaluation based on 4401 LDCT scans (obtained from scanners of 3 different manufacturers as external validation data). The BMD values of all individuals were extracted from three consecutive VBs: T12 to L2. Line regression and Bland‒Altman analyses were used to evaluate the overall detection performance. Sensitivity and specificity were used to evaluate the diagnostic performance for normal, osteopenia, and osteoporosis patients. RESULTS: Compared with the QCT results as the diagnostic standard, the BMD assessed had a mean error of (- 0.28, 2.37) mg/cm3. Overall, the sensitivity of a normal diagnosis was greater than that of a diagnosis of osteopenia or osteoporosis. For the diagnosis of osteoporosis, the model achieved a sensitivity > 86% and a specificity > 98%. CONCLUSION: The developed tool is clinically applicable and helpful for the positioning and analysis of VBs, the measurement of BMD, and the screening of osteopenia and osteoporosis. CLINICAL RELEVANCE STATEMENT: The developed system achieved high accuracy for automatic opportunistic osteoporosis screening using low-dose chest CT scans and performed well on CT images collected from different scanners. KEY POINTS: Osteoporosis is a prevalent but underdiagnosed condition that can increase the risk of fractures. This system could automatically and opportunistically screen for osteoporosis using low-dose chest CT scans obtained for lung cancer screening. The developed system performed well on CT images collected from different scanners and did not differ with patient age or sex.

3D U-Net Neural Network Architecture-Assisted LDCT to Acquire Vertebral Morphology Parameters: A Vertebral Morphology Comprehensive Analysis in a Chinese Population.

To evaluate the feasibility of acquiring vertebral height from chest low-dose computed tomography (LDCT) images using an artificial intelligence (AI) system based on 3D U-Net vertebral segmentation technology and the correlation and features of vertebral morphology with sex and age of the Chinese population. Patients who underwent chest LDCT between September 2020 and April 2023 were enrolled. The Altman and Pearson's correlation analyses were used to compare the correlation and consistency between the AI software and manual measurement of vertebral height. The anterior height (Ha), middle height (Hm), posterior height (Hp), and vertebral height ratios (VHRs) (Ha/Hp and Hm/Hp) were measured from T1 to L2 using an AI system. The VHR is the ratio of Ha to Hp or the ratio of Hm to Hp of the vertebrae, which can reflect the shape of the anterior wedge and biconcave vertebrae. Changes in these parameters, particularly the VHR, were analysed at different vertebral levels in different age and sex groups. The results of the AI methods were highly consistent and correlated with manual measurements. The Pearson's correlation coefficients were 0.855, 0.919, and 0.846, respectively. The trend of VHRs showed troughs at T7 and T11 and a peak at T9; however, Hm/Hp showed slight fluctuations. Regarding the VHR, significant sex differences were found at L1 and L2 in all age bands. This innovative study focuses on vertebral morphology for opportunistic analysis in the mainland Chinese population and the distribution tendency of vertebral morphology with ageing using a chest LDCT aided by an AI system based on 3D U-Net vertebral segmentation technology. The AI system demonstrates the potential to automatically perform opportunistic vertebral morphology analyses using LDCT scans obtained during lung cancer screening. We advocate the use of age-, sex-, and vertebral level-specific criteria for the morphometric evaluation of vertebral osteoporotic fractures for a more accurate diagnosis of vertebral fractures and spinal pathologies.

Predicting overall survival and prophylactic cranial irradiation benefit in small-cell lung cancer with CT-based deep learning: A retrospective multicenter study.

BACKGROUND AND PURPOSE: To develop a computed tomography (CT)-based deep learning model to predict overall survival (OS) among small-cell lung cancer (SCLC) patients and identify patients who could benefit from prophylactic cranial irradiation (PCI) based on OS signature risk stratification. MATERIALS AND METHODS: This study retrospectively included 556 SCLC patients from three medical centers. The training, internal validation, and external validation cohorts comprised 309, 133, and 114 patients, respectively. The OS signature was built using a unified fully connected neural network. A deep learning model was developed based on the OS signature. Clinical and combined models were developed and compared with a deep learning model. Additionally, the benefits of PCI were evaluated after stratification using an OS signature. RESULTS: Within the internal and external validation cohorts, the deep learning model (concordance index [C-index] 0.745, 0.733) was far superior to the clinical model (C-index: 0.635, 0.630) in predicting OS, but slightly worse than the combined model (C-index: 0.771, 0.770). Additionally, the deep learning model had excellent calibration, clinical usefulness, and improved accuracy in classifying survival outcomes. Remarkably, patients at high risk had a survival benefit from PCI in both the limited and extensive stages (all P < 0.05), whereas no significant association was observed in patients at low risk. CONCLUSIONS: The CT-based deep learning model exhibited promising performance in predicting the OS of SCLC patients. The OS signature may aid in individualized treatment planning to select patients who may benefit from PCI.

Radiomics nomogram based on optimal VOI of multi-sequence MRI for predicting microvascular invasion in intrahepatic cholangiocarcinoma.

OBJECTIVE: Microvascular invasion (MVI) is a significant adverse prognostic indicator of intrahepatic cholangiocarcinoma (ICC) and affects the selection of individualized treatment regimens. This study sought to establish a radiomics nomogram based on the optimal VOI of multi-sequence MRI for predicting MVI in ICC tumors. METHODS: 160 single ICC lesions with MRI scanning confirmed by postoperative pathology were randomly separated into training and validation cohorts (TC and VC). Multivariate analysis identified independent clinical and imaging MVI predictors. Radiomics features were obtained from images of 6 MRI sequences at 4 different VOIs. The least absolute shrinkage and selection operator algorithm was performed to enable the derivation of robust and effective radiomics features. Then, the best three sequences and the optimal VOI were obtained through comparison. The MVI prediction nomogram combined the independent predictors and optimal radiomics features, and its performance was evaluated via the receiver operating characteristics, calibration, and decision curves. RESULTS: Tumor size and intrahepatic ductal dilatation are independent MVI predictors. Radiomics features extracted from the best three sequences (T1WI-D, T1WI, DWI) with VOI10mm (including tumor and 10 mm peritumoral region) showed the best predictive performance, with AUCTC = 0.987 and AUCVC = 0.859. The MVI prediction nomogram obtained excellent prediction efficacy in both TC (AUC = 0.995, 95%CI 0.987-1.000) and VC (AUC = 0.867, 95%CI 0.798-0.921) and its clinical significance was further confirmed by the decision curves. CONCLUSION: A nomogram combining tumor size, intrahepatic ductal dilatation, and the radiomics model of MRI multi-sequence fusion at VOI10mm may be a predictor of preoperative MVI status in ICC patients.

Deep learning-assisted knee osteoarthritis automatic grading on plain radiographs: the value of multiview X-ray images and prior knowledge.

Background: Knee osteoarthritis (OA) is harmful to people's health. Effective treatment depends on accurate diagnosis and grading. This study aimed to assess the performance of a deep learning (DL) algorithm based on plain radiographs in detecting knee OA and to investigate the effect of multiview images and prior knowledge on diagnostic performance. Methods: In total, 4,200 paired knee joint X-ray images from 1,846 patients (July 2017 to July 2020) were retrospectively analyzed. Kellgren-Lawrence (K-L) grading was used as the gold standard for knee OA evaluation by expert radiologists. The DL method was used to analyze the performance of anteroposterior and lateral plain radiographs combined with prior zonal segmentation to diagnose knee OA. Four groups of DL models were established according to whether they adopted multiview images and automatic zonal segmentation as the DL prior knowledge. Receiver operating curve analysis was used to assess the diagnostic performance of 4 different DL models. Results: The DL model with multiview images and prior knowledge obtained the best classification performance among the 4 DL models in the testing cohort, with a microaverage area under the receiver operating curve (AUC) and macroaverage AUC of 0.96 and 0.95, respectively. The overall accuracy of the DL model with multiview images and prior knowledge was 0.96 compared to 0.86 for an experienced radiologist. The combined use of anteroposterior and lateral images and prior zonal segmentation affected diagnostic performance. Conclusions: The DL model accurately detected and classified the K-L grading of knee OA. Additionally, multiview X-ray images and prior knowledge improved classification efficacy.

CTE-Based Radiomics Models Can Identify Mucosal Healing in Patients with Crohn's Disease.

RATIONALE AND OBJECTIVES: To develop computed tomography enterography (CTE)-based radiomics models to assess mucosal healing (MH) in patients with Crohn's disease (CD). MATERIALS AND METHODS: CTE images were retrospectively collected from 92 confirmed cases of CD at the post-treatment review. Patients were randomly divided into developing (n = 73) and testing (n = 19) groups. Radiomics features were extracted from the enteric phase images, and the least absolute shrinkage and selection operator (LASSO) logistic regression was applied for feature selection using 5-fold cross-validation on the developing group. The selected features were further identified from the top-ranked features and used to create improved radiomics models. Machine learning models were constructed to compare radiomics models with different radiomics features. The area under the ROC curve (AUC) was calculated to assess the predictive performance for identifying MH in CD. RESULTS: Among the 92 CD patients included in our study, 36 patients achieved MH. The AUC of the radiomics model 1, which was based on the 26 selected radiomics features, was 0.976 for evaluating MH in the testing cohort. The AUCs of radiomics models 2 and 4, based on the top 10 and top 5 positive and negative radiomics features, were 0.974 and 0.952 in the testing cohort, respectively. The AUC of the radiomics model 3, built by removing features with r > 0.5, was 0.956 in the testing cohort. The clinical utility of the clinical radiomics nomogram was confirmed by the decision curve analysis (DCA). CONCLUSION: The CTE-based radiomics models have demonstrated favorable performance in assessing MH in patients with CD. Radiomics features can be used as a promising imaging biomarker for MH.

Isolated gastric variceal bleeding related to non-cirrhotic portal hypertension following oxaliplatin-based chemotherapy: A case report.

BACKGROUND: Sinusoidal obstruction syndrome has been reported after oxaliplatin-based chemotherapy, but liver fibrosis and non-cirrhotic portal hypertension (NCPH) are rarely reported. CASE SUMMARY: Here, we describe the case of a 64-year-old woman who developed isolated gastric variceal bleeding 16 mo after completing eight cycles of oxaliplatin combined with capecitabine chemotherapy after colon cancer resection. Surprisingly, splenomegaly and thrombocytopenia were not accompanied by variceal bleeding, which has been reported to have predictive value for gastric variceal formation. However, a liver biopsy showed fibrosis in the portal area, suggesting NCPH. The patient underwent endoscopic treatment and experienced no further symptoms. CONCLUSION: It is necessary to guard against long-term complications after oxaliplatin-based chemotherapy. Sometimes splenic size and platelet level may not always accurately predict the occurrence of portal hypertension.

USP5 promotes epithelial-mesenchymal transition by stabilizing SLUG in hepatocellular carcinoma.

Rationale: The role of SLUG in epithelial-mesenchymal transition during tumor progression has been thoroughly studied, but its precise regulation remains poorly explored. Methods: The affinity purification, mass spectrometry and CO-IP were performed to identify the interaction between SLUG and ubiquitin-specific protease 5 (USP5). Cycloheximide chase assays and deubiquitination assays confirmed that the effect of USP5 on the deubiquitin of SLUG. The dual-luciferase reporter and chromatin immunoprecipitation assays were employed to observe the direct transcriptional regulation of E-cadherin by SLUG effected by USP5. EMT related markers was detected by western blotting and immunofluorescence. Molecular docking, SPR sensor (biacore) and co-location were detected to prove Formononetin targets USP5. Bioinformatics analysis was used to study the relation of USP5 and SLUG to malignancy degree of HCC. Cell migration, invasion in HCC cells and xenografts model in nude mouse were conducted to detect the promotion of USP5 and the inhibition of Formononetin on EMT. Results: USP5 interacts with and stabilizes SLUG to regulate its abundance through USP5 deubiquitination activities in epithelial-mesenchymal transition (EMT) of hepatocellular carcinoma (HCC). USP5 is highly expressed and positively correlated with SLUG expression in HCC with high malignancy. Knockdown of USP5 inhibits SLUG deubiquitination and inhibits HCC cells proliferation, metastasis, and invasion, while overexpression of USP5 promotes SLUG stability and EMT in vitro and in vivo. Through virtual screening, we found that Formononetin exhibits excellent binding to USP5. Moreover, Formononetin inhibits deubiquitinating activities of USP5 to SLUG and consequently impedes the EMT and malignant progression of HCC. Conclusion: Our findings reveal that USP5 serve as a potential target for tumor intervention and provide a preliminary antitumor therapy for inhibit EMT by targeting USP5 or its interaction with SLUG in HCC.

SND1 acts as an anti-apoptotic factor via regulating the expression of lncRNA UCA1 in hepatocellular carcinoma.

Multifunctional SND1 (staphylococcal nuclease and tudor domain containing 1) protein is reportedly associated with different types of RNA molecules, including mRNA, miRNA, pre-miRNA, and dsRNA. SND1 has been implicated in a number of biological processes in eukaryotic cells, including cell cycle, DNA damage repair, proliferation, and apoptosis. However, the specific molecular mechanism regarding the anti-apoptotic role of SND1 in mammalian cells remains largely elusive. In this study, the analysis of the online HPA (human protein atlas) and TCGA (the cancer genome atlas) databases showed the significantly high expression of SND1 in liver cancer patients. We found that the downregulation or complete depletion of SND1 enhanced the apoptosis levels of HepG2 and SMMC-7721 cells upon stimulation with 5-Fu (5-fluorouracil), a chemotherapeutic drug for HCC (hepatocellular carcinoma). SND1 affected the 5-Fu-induced apoptosis levels of HCC cells by modulating the expression of UCA1 (urothelial cancer associated 1), which is a lncRNA (long non-coding RNA). Moreover, MYB (MYB proto-oncogene, transcription factor) may be involved in the regulation of SND1 in UCA1 expression. In summary, our study identified SND1 as an anti-apoptotic factor in hepatocellular carcinoma cells via the modulation of lncRNA UCA1, which sheds new light on the relationship between SND1 protein and lncRNA.

Polyphyllin I suppresses the formation of vasculogenic mimicry via Twist1/VE-cadherin pathway.

Vasculogenic mimicry (VM) is a functional microcirculation pattern formed by aggressive tumor cells and is related to the metastasis and poor prognosis of many cancer types, including hepatocellular carcinoma (HCC). Thus far, no effective drugs have been developed to target VM. In this study, patients with liver cancer exhibited reduced VM in tumor tissues after treatment with Rhizoma Paridis. Polyphyllin I (PPI), which is the main component of Rhizoma Paridis, inhibited VM formation in HCC lines and transplanted hepatocellular carcinoma cells. Molecular mechanism analysis showed that PPI impaired VM formation by blocking the PI3k-Akt-Twist1-VE-cadherin pathway. PPI also displayed dual effects on Twist1 by inhibiting the transcriptional activation of the Twist1 promoter and interfering with the ability of Twist1 to bind to the promoter of VE-cadherin, resulting in VM blocking. This study is the first to report on the clinical application of the VM inhibitor. Results may contribute to the development of novel anti-VM drugs in clinical therapeutics.

Twist1 Regulates Vimentin through Cul2 Circular RNA to Promote EMT in Hepatocellular Carcinoma.

Twist is a critical epithelial-mesenchymal transition (EMT)-inducing transcription factor that increases expression of vimentin. How Twist1 regulates this expression remains unclear. Here, we report that Twist1 regulates Cullin2 (Cul2) circular RNA to increase expression of vimentin in EMT. Twist1 bound the Cul2 promoter to activate its transcription and to selectively promote expression of Cul2 circular RNA (circ-10720), but not mRNA. circ-10720 positively correlated with Twist1, tumor malignance, and poor prognosis in hepatocellular carcinoma (HCC). Twist1 promoted vimentin expression by increasing levels of circ-10720, which can absorb miRNAs that target vimentin. circ-10720 knockdown counteracted the tumor-promoting activity of Twist1 in vitro and in patient-derived xenograft and diethylnitrosamine-induced TetOn-Twist1 transgenic mouse HCC models. These data unveil a mechanism by which Twist1 regulates vimentin during EMT. They also provide potential therapeutic targets for HCC treatment and provide new insight for circular RNA (circRNA)-based diagnostic and therapeutic strategies.Significance: A circRNA-based mechanism drives Twist1-mediated regulation of vimentin during EMT and provides potential therapeutic targets for treatment of HCC.Graphical Abstract: http://cancerres.aacrjournals.org/content/canres/78/15/4150/F1.large.jpg Cancer Res; 78(15); 4150-62. ©2018 AACR.

Association between the HFE C282Y, H63D Polymorphisms and the Risks of Non-Alcoholic Fatty Liver Disease, Liver Cirrhosis and Hepatocellular Carcinoma: An Updated Systematic Review and Meta-Analysis of 5,758 Cases and 14,741 Controls.

BACKGROUND: Conflicting results have been obtained for the association between two common polymorphisms (C282Y, H63D) of human HFE (hereditary hemochromatosis) gene and the risks of the liver diseases, including non-alcoholic fatty liver disease (NAFLD), liver cirrhosis and hepatocellular carcinoma (HCC). METHODS: An updated systematic review and meta-analysis was conducted to evaluate the potential role of HFE polymorphisms in the susceptibility to NAFLD, liver cirrhosis and HCC. After retrieving articles from online databases, eligible studies were enrolled according to the selection criteria. Stata/SE 12.0 software was utilized to perform the statistical analysis. RESULTS: In total, 43 articles with 5,758 cases and 14,741 controls were selected. Compared with the control group, a significantly increased risk of NAFLD was observed for the C282Y polymorphism in the Caucasian population under all genetic models and for the H63D polymorphism under the allele, heterozygote and dominant models (all OR>1, Passociation<0.05). However, no significant difference between liver cirrhosis cases and the control group was observed for HFE C282Y and H63D (all Passociation>0.05). In addition, we found that HFE C282Y was statistically associated with increased HCC susceptibility in the overall population, while H63D increased the odds of developing non-cirrhotic HCC in the African population (all OR>1, Passociation<0.05). Moreover, a positive association between compound heterozygosity for C282Y/H63D and the risk of NAFLD and HCC, but not liver cirrhosis, was observed. CONCLUSION: Our meta-analysis provides evidence that the HFE C282Y and H63D polymorphisms confer increased genetic susceptibility to NAFLD and HCC but not liver cirrhosis. Additional well-powered studies are required to confirm our conclusion.