Machine learning-based decision support model for selecting intra-arterial therapies for unresectable hepatocellular carcinoma: A national real-world evidence-based study.

IMPORTANCE: Intra-arterial therapies(IATs) are promising options for unresectable hepatocellular carcinoma(HCC). Stratifying the prognostic risk before administering IAT is important for clinical decision-making and for designing future clinical trials. OBJECTIVE: To develop and validate a machine learning(ML)-based decision support model(MLDSM) for recommending IAT modalities for unresectable HCC. DESIGN, SETTING, AND PARTICIPANTS: Between October 2014 and October 2022, a total of 2,959 patients with HCC who underwent initial IATs were enroled retrospectively from 13 tertiary hospitals. These patients were divided into the training cohort (n = 1700), validation cohort (n = 428), and test cohort (n = 200). MAIN OUTCOMES AND MEASURES: Thirty-two clinical variables were input, and five supervised ML algorithms, including eXtreme Gradient Boosting (XGBoost), Categorical Gradient Boosting (CatBoost), Gradient Boosting Decision Tree (GBDT), Light Gradient Boosting Machine (LGBM) and Random Forest (RF), were compared using the areas under the receiver operating characteristic curve (AUC) with the DeLong test. RESULTS: A total of 1856 patients were assigned to the IAT alone Group(I-A), and 1103 patients were assigned to the IAT combination Group(I-C). The 12-month death rates were 31.9% (352/1103) in the I-A group and 50.4% (936/1856) in the I-C group. For the test cohort, in the I-C group, the CatBoost model achieved the best discrimination when 30 variables were input, with an AUC of 0.776 (95% confidence intervals [CI], 0.833-0.868). In the I-A group, the LGBM model achieved the best discrimination when 24 variables were input, with an AUC of 0.776 (95% CI, 0.833-0.868). According to the decision trees, BCLC grade, local therapy, and diameter as top three variables were used to guide clinical decisions between IAT modalities. CONCLUSIONS AND RELEVANCE: The MLDSM can accurately stratify prognostic risk for HCC patients who received IATs, thus helping physicians to make decisions about IAT and providing guidance for surveillance strategies in clinical practice.

Multimodal imaging-based prediction of recurrence for unresectable HCC after downstage and resection-cohort study.

BACKGROUND: Surgical resection (SR) following transarterial chemoembolization (TACE)-based downstaging is a promising treatment for unresectable hepatocellular carcinoma (uHCC), and identification of patients at high-risk of postoperative recurrence may assist individualized treatment. PURPOSE: To develop and externally validate pre- and postoperative prognostic models integrating multimodal CT and DSA features as well as clinico-therapeutic-pathological features for predicting disease-free survival (DFS) after TACE-based downstaging therapy. MATERIALS AND METHODS: From March 2008 to August 2022, 488 consecutive patients with BCLC A/B uHCC receiving TACE-based downstaging therapy and subsequent SR were included from four tertiary-care hospitals. All CT and DSA images were independently evaluated by two blinded radiologists. In the derivation cohort (n=390), the XGBoost algorithm was used for feature selection, and Cox regression analysis for developing nomograms for DFS (time from downstaging to postoperative recurrence or death). In the external testing cohort (n=98), model performances were compared with five major staging systems. RESULTS: The preoperative nomogram included over three tumors (HR, 1.42; P=0.003), intratumoral artery (HR, 1.38; P=0.006), TACE combined with tyrosine kinase inhibitor (HR, 0.46; P<0.001) and objective response to downstaging therapy (HR, 1.60; P<0.001); while the postoperative nomogram included over three tumors (HR, 1.43; P=0.013), intratumoral artery (HR, 1.38; P=0.020), TACE combined with tyrosine kinase inhibitor (HR, 0.48; P<0.001), objective response to downstaging therapy (HR, 1.69; P<0.001) and microvascular invasion (HR, 2.20; P<0.001). The testing dataset C-indexes of the pre- (0.651) and postoperative (0.687) nomograms were higher than all five staging systems (0.472-0.542; all P<0.001). Two prognostically distinct risk strata were identified according to these nomograms (all P<0.001). CONCLUSION: Based on 488 patients receiving TACE-based downstaging therapy and subsequent SR for BCLC A/B uHCCs, we developed and externally validated two nomograms for predicting DFS, with superior performances than five major staging systems and effective survival stratification.

Association of serum AFP trajectories and hepatocellular carcinoma outcomes after hepatic arterial infusion chemotherapy: A longitudinal, multicenter study.

AIM: This study aims to investigate α-fetoprotein (AFP) trajectories for prediction of survival outcomes after hepatic arterial infusion chemotherapy (HAIC) treatment in large hepatocellular carcinoma (HCC). METHODS: From May 2014 to June 2020, 889 eligible patients with large HCC underwent HAIC were retrospectively enrolled from five hospitals. A latent class growth mixed (LCGM) model was applied to distinguish potential AFP level dynamic changing trajectories. Inverse-probability-of-treatment weighted (IPTW) analyses were performed to eliminate unmeasured confounders through marginal structural models. Multivariate Cox proportional hazard regression analyses were used to determine the overall survival (OS) in patients with large HCC. Performance of these serum markers for survival prediction was compared by areas under receiver operating characteristic analysis with the Delong test. RESULTS: The median follow-up time was 23.7 (interquartile range, 3.8-115.3). A total of 1009 patients with large HCC, who underwent HAIC with AFP repeatedly measured 3-10 times, were enrolled in the study. Three distinct trajectories of these serum AFP were identified using the LCGM model: high stable (37.0%; n = 373), low stable (15.7%; n = 159), and sharp-falling (47.3%; n = 477). Multivariate Cox proportional hazard regression analyses found that ALBI stage 2-3, BCLC-C stage and high-stable AFP trajectories were associated with OS. AFP trajectories yield the optimal predictive performance in all risk factors. CONCLUSIONS: The AFP trajectories based on longitudinal AFP change showed outstanding performance for predicting survival outcomes after HAIC treatment in large HCC, which provide a potential monitoring tool for improving clinical decision-making.

Pseudo-capsulated Hepatocellular Carcinoma: Hepatic Arterial Infusion Chemotherapy Versus Transcatheter Arterial Chemoembolization.

RATIONALE AND OBJECTIVES: The effectiveness and safety of hepatic arterial infusion chemotherapy (HAIC) or transarterial chemoembolization (TACE) for cases with single pseudo-capsuled hepatocellular carcinoma (pHCC), as well as their survival outcomes, were investigated. MATERIALS AND METHODS: A total of 196 cases with single pHCC (diameter >5 cm) receiving initial HAIC (n = 92) and TACE (n = 104) were enrolled. The propensity score match (PSM) approach based on Cox models was employed to tune any possible imbalance in treatment assignment. The overall survival (OS), objective response rate (ORR), progression-free survival (PFS), and partial response rate (PRR) of the subjects were investigated using the log-rank test. The independent risk factors for outcomes were investigated by univariate and multivariate analyses, and the results were analyzed using the Cox regression model. RESULTS: The median follow-up of the subjects was 22.3 months. After PSM, no significant difference was found in the OS of the HAIC and TACE groups (OS, 12.0 vs. 16.8 months; P = .267), while the median PFS of the TACE group was prolonged compared with the HAIC group (PFS, 5.7 vs. 2.8 months; P = .003). Moreover, PRR and ORR of the TACE group were prolonged compared with the HAIC group (PRR, 34.6% vs. 21.7%; P = .046; ORR, 35.6% vs. 21.7%; P = .033). The nomogram model showed high predictive accuracy and significant discrimination. CONCLUSION: TACE therapy could delay tumor progression compared with HAIC for cases with a single pHCC.

Camrelizumab (a PD-1 inhibitor) plus apatinib (an VEGFR-2 inhibitor) and hepatic artery infusion chemotherapy for hepatocellular carcinoma in Barcelona Clinic Liver Cancer stage C (TRIPLET): a phase II study.

Hepatic arterial infusion chemotherapy (HAIC) using a combination of oxaliplatin, fluorouracil, and leucovorin (FOLFOX) has shown promise for hepatocellular carcinoma (HCC) patients classified under Barcelona Clinic Liver Cancer (BCLC) stage C. In China, the combined therapy of camrelizumab and apatinib is now an approved first-line approach for inoperable HCC. This study (NCT04191889) evaluated the benefit of combining camrelizumab and apatinib with HAIC-FOLFOX for HCC patients in BCLC stage C. Eligible patients were given a maximum of six cycles of HAIC-FOLFOX, along with camrelizumab and apatinib, until either disease progression or intolerable toxicities emerged. The primary outcome measured was the objective response rate (ORR) based on the Response Evaluation Criteria in Solid Tumors (RECIST) v1.1. Thirty-five patients were enrolled. Based on RECIST v1.1 criteria, the confirmed ORR stood at 77.1% (95% CI: 59.9% to 89.6%), with a disease control rate of 97.1% (95% CI: 85.1% to 99.9%). The median progression-free survival was 10.38 months (95% CI: 7.79 to 12.45). Patient quality of life had a transient deterioration within four cycles of treatment, and generally recovered thereafter. The most frequent grade ≥3 or above treatment-related adverse events included reduced lymphocyte count (37.1%) and diminished neutrophil count (34.3%). The combination of camrelizumab, apatinib, and HAIC demonstrated encouraging results and manageable safety concerns for HCC at BCLC stage C.

PHF23 promotes NSCLC proliferation, metastasis, and chemoresistance via stabilization of ACTN4 and activation of the ERK pathway.

At present, non-small cell lung cancer (NSCLC) is still one of the leading causes of cancer-related deaths. Chemotherapy remains the standard treatment for NSCLC. However, the emergence of chemoresistance is one of the major obstacles to lung cancer treatment. Plant homologous structural domain finger protein 23 (PHF23) plays crucial roles in multiple cell fates. However, the clinical significance and biological role of PHF23 in NSCLC remain elusive. The Cancer Genome Atlas data mining, NCBI/GEO data mining, and western blotting analysis were employed to characterize the expression of PHF23 in NSCLC cell lines and tissues. Statistical analysis of immunohistochemistry and the Kaplan-Meier Plotter database were used to investigate the clinical significance of PHF23. A series of in vivo and in vitro assays, including assays for colony formation, cell viability, 5-ethynyl-2'-deoxyuridine (EDU incorporation) and Transwell migration, flow cytometry, RT-PCR, gene set enrichment analysis, co-immunoprecipitation analysis, and a xenograft tumor model, were performed to demonstrate the effects of PHF23 on the chemosensitivity of NSCLC cells and to clarify the underlying molecular mechanisms. PHF23 is overexpressed in NSCLC cell lines and tissues. High PHF23 levels correlate with short survival times and a poor response to chemotherapy in NSCLC patients. PHF23 overexpression facilitates cell proliferation, migration and sensitizes NSCLC cells to Cisplatin and Docetaxel by promoting DNA damage repair. Alpha-actinin-4 (ACTN4), as a downstream regulator, interacts with PHD domain of PHF23. Moreover, PHF23 is involved in ACTN4 stabilization by inhibiting its ubiquitination level. These results show that PHF23 plays an important role in the development and progression of NSCLC and suggest that PHF23 may serve as a therapeutic target in NSCLC patients.

Focus prediction of medical microscopic images based on Lightweight Densely Connected with Squeeze-and-Excitation Network.

Due to the demand for sample observation, optical microscopy has become an essential tool in the fields of biology and medicine. In addition, it is impossible to maintain the living sample in focus over long-time observation. Rapid focus prediction which involves moving a microscope stage along a vertical axis to find an optimal focus position, is a critical step for high-quality microscopic imaging of specimens. Current focus prediction algorithms, which are time-consuming, cannot support high frame rate imaging of dynamic living samples, and may introduce phototoxicity and photobleaching on the samples. In this paper, we propose Lightweight Densely Connected with Squeeze-and-Excitation Network (LDSE-NET). The results of the focusing algorithm are demonstrated on a public dataset and a self-built dataset. A complete evaluation system was constructed to compare and analyze the effectiveness of LDSE-NET, BotNet, and ResNet50 models in multi-region and multi-multiplier prediction. Experimental results show that LDSE-NET is reduced to 1E-05 of the root mean square error. The accuracy of the predicted focal length of the image is increased by 1 ~ 2 times. Training time is reduced by 33.3%. Moreover, the volume of the model only reaches the KB level, which has the characteristics of being lightweight.

Global incidence, prevalence and disease burden of silicosis: 30 years' overview and forecasted trends.

BACKGROUND: Globally, silicosis accounts for 90% of all pneumoconiosis cases and is a serious public health issue. It is characterized by progressive inflammation and irreversible pulmonary fibrosis. A comprehensive analysis at temporal, spatial and population levels with the most updated data from GBD 2019 is provided in this study to estimate the disease burden of silicosis from 1990 to 2019 and make predictions to 2029. METHODS: We delineated silicosis data on incidence, prevalence, and disability-adjusted life years (DALYs) as well as age-standardized rates (ASRs) across 30 years from GBD 2019. Joinpoint regression analysis was employed to detect temporal changes and estimate annual percentage change (APC) of each trend segment. Measures were stratified by time, location, age, and sociodemographic index (SDI). Back propagation artificial neural network (BP-ANN) model was applied to elaborate ASR trends from 1990 to 2019 and projections to the next 10 years. RESULTS: Globally, silicosis incident, prevalent cases, and DALYs increased by 64.6%, 91.4%, and 20.8%, respectively. However, all the corresponding ASRs showed overall downward trends with an estimated average APC (AAPC) of -0.5(-0.7 to -0.3), -0.2(-0.5 to 0.0), and - 2.0(-2.2 to -1.8), respectively. Middle and high-middle SDI regions carried the heaviest disease burden. The highest disease burden of silicosis was mainly transferred to the older from 1990 to 2019. The trend of ASRs demonstrated a rapid decline between 2005 and 2019, followed by a continuous decline until 2029. CONCLUSION: Though disease burden of silicosis has been on a decline in general from 1990 to 2019, which shows a promising prospect but cannot be ignored. We should pay more attention to implementing preventive tactics and improving the life quality of present sufferers.

Systematic analysis and prediction for disease burden of ovarian cancer attributable to hyperglycemia: a comparative study between China and the world from 1990 to 2019.

Background: Ovarian cancer is one of the most common female malignancies worldwide, and metabolic factors, such as hyperglycemia, are becoming potential risk factors. This study aimed to analyze the disease burden and its changing trend of ovarian cancer attributable to hyperglycemia in the Chinese population from 1990 to 2019. Methods: Using the data released by the Global Burden of Disease study 2019 (GBD 2019), we analyze the disease burden of ovarian cancer attributable to hyperglycemia in Chinese from 1990 to 2019 via morbidity, death, disability-adjusted life years (DALY); compare it with the global population; and predict the incidence and death trend in Chinese women for the next 10 years (2020-2029). Results: The incidence, death cases, and DALY numbers of ovarian cancer attributable to hyperglycemia in Chinese in 2019 were 2,751, 1,758, and 44,615 person-years, respectively, with an increase of 352.5%, 356.6%, and 329.0% compared with 1990, and the growth rate was higher than the global level. The age-standardized incidence rate (ASIR), age-standardized mortality rate (ASMR), and age-standardized DALY rate (ASDR) in 2019 were 0.270/100,000, 0.164/100,000, and 4.103/100,000, respectively. Moreover, the average annual percent changes (AAPCs) were 2.3%, 2.0%, and 2.0%, respectively, all higher than the global average. The disease burden of ovarian cancer attributable to hyperglycemia increased with age, reaching a peak in the 45-75 age group. The prediction of the neural network model showed that the incidence and death of the disease would remain high and rise in the next 10 years. Conclusion: The disease burden caused by ovarian cancer attributable to hyperglycemia in Chinese accounts for a large proportion globally, and the ASIR, ASMR, and ASDR are increasing year by year. We should continue to pay attention to the role of metabolic factors, such as hyperglycemia, in the occurrence and development of ovarian cancer, perform a good job in tertiary prevention, and strive to reduce health losses.

Development and validation of prognostic nomograms for large hepatocellular carcinoma after HAIC.

Background and aims: Hepatic arterial infusion chemotherapy (HAIC) using the FOLFOX regimen (oxaliplatin plus fluorouracil and leucovorin) is a promising option for large hepatocellular carcinoma (HCC). However, post-HAIC prognosis can vary in different patients due to tumor heterogeneity. Herein, we established two nomogram models to assess the survival prognosis of patients after HAIC combination therapy. Methods: A total of 1082 HCC patients who underwent initial HAIC were enrolled between February 2014 and December 2021. We built two nomogram models for survival prediction: the preoperative nomogram (pre-HAICN) using preoperative clinical data and the postoperative nomogram (post-HAICN) based on pre-HAICN and combination therapy. The two nomogram models were internally validated in one hospital and externally validated in four hospitals. A multivariate Cox proportional hazards model was used to identify risk factors for overall survival (OS). The performance outcomes of all models were compared by area under the receiver operating characteristic curve (AUC) analysis with the DeLong test. Results: Multivariable analysis identified larger tumor size, vascular invasion, metastasis, high albumin-bilirubin grade, and high alpha-fetoprotein as indicators for poor prognosis. With these variables, the pre-HAICN provided three risk strata for OS in the training cohort: low risk (5-year OS, 44.9%), middle risk (5-year OS, 20.6%), and high risk (5-year OS, 4.9%). The discrimination of the three strata was improved significantly in the post-HAICN, which included the above-mentioned factors and number of sessions, combination with immune checkpoint inhibitors, tyrosine kinase inhibitors, and local therapy (AUC, 0.802 versus 0.811, p < 0.001). Conclusions: The nomogram models are essential to identify patients with large HCC suitable for treatment with HAIC combination therapy and may potentially benefit personalized decision-making. Lay summary: Hepatic arterial infusion chemotherapy (HAIC) provides sustained higher concentrations of chemotherapy agents in large hepatocellular carcinoma (HCC) by hepatic intra-arterial, result in better objective response outperformed the intravenous administration. HAIC is significantly correlated with favorable survival outcome and obtains extensive support in the effective and safe treatment of intermediate advanced-stage HCC. In view of the high heterogeneity of HCC, there is no consensus regarding the optimal tool for risk stratification before HAIC alone or HAIC combined with tyrosine kinase inhibitors or immune checkpoint inhibitors treatment in HCC. In this large collaboration, we established two nomogram models to estimate the prognosis and evaluate the survival benefits with different HAIC combination therapy. It could help physicians in decision-making before HAIC and comprehensive treatment for large HCC patients in clinical practice and future trials.

Postprogression treatment of lenvatinib plus PD-1 inhibitor in advanced hepatocellular carcinoma refractory to hepatic arterial infusion chemotherapy.

PURPOSE: This study compares the efficacy and safety of lenvatinib and programmed cell death protein (PD)-1 versus lenvatinib alone for advanced hepatocellular carcinoma (Ad-HCC) refractory to hepatic arterial infusion chemotherapy (HAIC). METHODS: From April 2016 to September 2021, 145 patients with Ad-HCC refractory to HAIC based on modified Response Evaluation Criteria in Solid Tumors criteria were enrolled by two radiologists and classified into the HAIC-lenvatinib group (H-L, n = 87) and HAIC-lenvatinib-PD-1 group (H-L-P, n = 58). A propensity score-matching method was used to reduce selective bias. The overall survival (OS) and postprogression-free survival (PPS) rates were compared using the Kaplan-Meier method with log-rank test. Multivariable analyses of independent prognostic factors were evaluated by means of the forward stepwise Cox regression model. RESULTS: After propensity score matching 1:1, the median OS was 43.6 months in the H-L-P group and was significantly longer than that (18.9 months) of the H-L group (p = .009). The median PPS was 35.6 months in the H-L-P group and was significantly longer than that (9.4 months) of the H-L group (p = .009). Multivariate analyses showed that the factors that significantly affected the OS were α-fetoprotein (hazard ratio [HR], 2.14; 95% CI, 1.26-3.98; p = .006), early response to HAIC (HR, 0.44; 95% CI, 1.20-3.85; p = .009), and H-L treatment (HR, 0.52; 95% CI, 0.30-0.86; p = .012). Modified albumin-bilirubin grade (HR, 1.32; 95% CI, 1.03-1.70; p = .026), early response to HAIC (HR, 0.44; 95% CI, 0.25-0.77; p = .004), and H-L (HR, 0.47 ; 95% CI, 0.28-0.78; p = .003) significantly affected the PPS. CONCLUSIONS: This combination therapy of PD-1 inhibitors plus lenvatinib has promising survival benefits in the management of patients with Ad-HCC refractory to HAIC. PLAIN LANGUAGE SUMMARY: Lenvatinib plus programmed death 1 inhibitor is an effective and safe postprogression treatment and improved significantly overall survival and postprogression-free survival compared with lenvatinib alone in patients with advanced hepatocellular carcinoma refractory to hepatic arterial infusion chemotherapy.

Impact of engineering renovation on dynamic health risk assessment of mercury in a thermometer enterprise.

The occupational health risk assessments (OHRA) of inorganic mercury (Hg) are rarely reported. We conducted an internal and external exposure monitoring of employees in a thermometer enterprise which experienced the renovation of occupational health engineering, followed by an evaluation on the health risks of Hg exposure with four OHRA methods in order to find out a most suitable model. The results showed that the concentrations of airborne and urinary Hg in all testing positions and subjects obviously decreased after the engineering renovation, meeting the occupational exposure limits (OELs) of China. Subsequently, four OHRA models, namely the models from US Environmental Protection Agency (EPA), Ministry of Manpower (MOM), International Council on Mining and Metals (ICMM), and Classification of occupational hazards at workplaces Part 2: Occupational exposure to chemicals (GBZ/T 229.2-2010) were applied in the qualitative risk assessment. And the evaluation results of different methods were standardized by risk ratio (RR), which indicated MOM, ICMM risk rating, and GBZ/T 229.2 models were consistent with the order of inherent risk levels in those working processes. The order of RR between four models was: RR EPA > RR ICMM > RR MOM> RR GBZ/T229.2 (P < 0.05). Based on the strict limits of Hg, GBZ/T 229.2, and MOM methods may have more potentials in practical application. Though the working environment has been significantly improved via engineering renovation, it is strongly suggested that the thermometer company conduct more effective risk management covering all production processes to minimize Hg exposure levels and health risk ratings.

Susceptibility Loci in SLC15A1, UGT1A3, and CWC27 Genes Associated with Bladder Cancer in the Northeast Chinese Population.

Bladder cancer (BCa) is an increasingly severe clinical and public health issue. Therefore, we aim to investigate BCa susceptibility loci in the Chinese population. In this study, 487 BCa patients and 563 controls were recruited from the First Affiliated Hospital of China Medical University from July 2015 to September 2020. A total of ten single-nucleotide polymorphisms (SNPs) in solute carrier family 15 member 1 (SLC15A1), CWC27 spliceosome associated cyclophilin (CWC27), or UDP glucuronosyltransferase family 1 member A3 (UGT1A3) genes were genotyped. The associations between the candidate SNPs and BCa were analyzed using genotype and haplotype analysis. The results demonstrated that Rs4646227 of SLC15A1 has a significant association with BCa. The patients with CG (OR =2.513, p < 0.05) and GG (OR =2.859, p < 0.05) genotypes had an increasing risk of BCa compared with the CC genotype. For the CWC27 gene, genotypic frequency analysis revealed that the GT or TT genotype of rs2042329 and the CT or TT genotype of rs1870437 were more frequent in BCa patients than those in the control group, indicating that these genotypes were associated with a higher risk of BCa (all p < 0.05). Haplotypes of SLC15A1, UGT1A3, and CWC27 genes found that the C-C-C haplotype of SLC15A1 was associated with a lower risk of BCa while the C-G-C haplotype was associated with a higher risk. For the UGT1A3 gene, a moderate protective effect was observed with the most frequent T-T-C haplotype, and for the CWC27 gene, most of the haplotypes showed no association with BCa, except the G-G-C-T haplotype (order of SNPs: rs2042329-rs7735338-rs1870437-rs2278351, OR =0.81, p =0.038). In sum, this study indicated that rs2042329 and rs1870437 in the CWC27 gene and rs4646227 in the SLC15A1 gene are independent indicators for BCa risk in Chinese people. Further large-scale studies are required to validate these findings. Also, this study provided the theoretical basis for developing new therapeutic drug targeting of BCa.

Correction: Systemic Delivery of MicroRNA-101 Potently Inhibits Hepatocellular Carcinoma In Vivo by Repressing Multiple Targets.

[This corrects the article DOI: 10.1371/journal.pgen.1004873.].

Distinguishing benign and malignant lesions on contrast-enhanced breast cone-beam CT with deep learning neural architecture search.

PURPOSE: To utilize a neural architecture search (NAS) approach to develop a convolutional neural network (CNN) method for distinguishing benign and malignant lesions on breast cone-beam CT (BCBCT). METHOD: 165 patients with 114 malignant and 86 benign lesions were collected by two institutions from May 2012 to August 2014. The NAS method autonomously generated a CNN model using one institution's dataset for training (patients/lesions: 71/91) and validation (patients/lesions: 20/23). The model was externally tested on another institution's dataset (patients/lesions: 74/87), and its performance was compared with fine-tuned ResNet-50 models and two breast radiologists who independently read the lesions in the testing dataset without knowing lesion diagnosis. RESULTS: The lesion diameters (mean ± SD) were 18.8 ± 12.9 mm, 22.7 ± 10.5 mm, and 20.0 ± 11.8 mm in the training, validation, and external testing set, respectively. Compared to the best ResNet-50 model, the NAS-generated CNN model performed three times faster and, in the external testing set, achieved a higher (though not statistically different) AUC, with sensitivity (95% CI) and specificity (95% CI) of 0.727, 80% (66-90%), and 60% (42-75%), respectively. Meanwhile, the performances of the NAS-generated CNN and the two radiologists' visual ratings were not statistically different. CONCLUSIONS: Our preliminary results demonstrated that a CNN autonomously generated by NAS performed comparably to pre-trained ResNet models and radiologists in predicting malignant breast lesions on contrast-enhanced BCBCT. In comparison to ResNet, which must be designed by an expert, the NAS approach may be used to automatically generate a deep learning architecture for medical image analysis.

Consensus of Minimally Invasive and Multidisciplinary Comprehensive Treatment for Hepatocellular Carcinoma - 2020 Guangzhou Recommendations.

In China, the majority of patients with hepatocellular carcinoma (HCC) result from long-term infection of hepatitis B. Pathologically, HCC is characterized by rich blood supply, multicentric origins, early vascular invasion and intrahepatic metastasis. Therefore, HCC is not a local disease but a systemic disease at the beginning of its occurrence. For this reason, a comprehensive treatment strategy should be adopted in the management of HCC, including local treatments (such as surgical resection, radiofrequency ablation, microwave ablation, chemical ablation and cryoablation, etc.), organ-level treatments [such as transcatheter arterial infusion of chemotherapy and transcatheter arterial chemoembolization (TACE)], and systemic treatments (such as immunotherapy, antiviral therapy and molecular targeted therapy, etc.). This consensus sets forth the minimally-invasive and multidisciplinary comprehensive guideline of HCC, focusing on the following eight aspects (1) using hepaticarteriography, CT hepatic arteriography (CTHA), CT arterial portography (CTAP), lipiodol CT (Lp-CT), TACE-CT to find the intrahepatic lesion and make precise staging (2) TACE combined with ablation or ablation as the first choice of treatment for early stage or small HCC, while other therapies are considered only when ablation is not applicable (3) infiltrating HCC should be regarded as an independent subtype of HCC (4) minimally-invasive comprehensive treatment could be adopted in treating metastatic lymph nodes (5) multi-level subdivision of M-staging should be used for individualized treatment and predicting prognosis (6) HCC with severe hepatic decompensation is the only candidate criterion for liver transplantation (7) bio-immunotherapy, traditional Chinese medicine therapy, antiviral therapy, and psychosocial and psychopharmacological interventions should be advocated through the whole course of HCC treatment (8) implementation of multicenter randomized controlled trials of minimally-invasive therapy versus surgery for early and intermediate stage HCC is recommended.

Chinese expert consensus of image-guided irreversible electroporation for pancreatic cancer.

Pancreatic cancer (PC) is a lethal disease with extremely high mortality. Although surgical resection is the optimal therapeutic approach for PC, about 30%-40% of those patients are not candidates for surgical resection when diagnosed. Chemotherapy and radiotherapy also could not claim a desirable effect on PC. The application of interventional radiology approaches is limited by unavoidable damage to the surrounding vessels or organs. By the superiority of mechanism and technology, IRE could ablate the tumor by creating irreversible pores on the membrane of PC cells with other tissues like vessels and pancreatic ducts untouched. This consensus gathers the theoretical basis and clinical experience from multiple Chinese medical centers, to provide the application principles and experience from Chinese experts in the IRE field.

Construction of an immune-related gene signature to predict survival and treatment outcome in gastric cancer.

Immune cells have emerged as key regulators in the occurrence and development of multiple tumor types. However, it is unclear whether immune-related genes (IRGs) and the tumor immune microenvironment can predict prognosis for patients with gastric cancer (GC). The mRNA expression data in GC tissues (n = 368) were obtained from The Cancer Genome Atlas (TCGA) database. Differentially expressed IRGs in patients with GC were determined using a computational difference algorithm. A prognostic signature was constructed using COX regression and random survival forest (RSF) analyses. In addition, datasets related to "gemcitabine resistance" and "trastuzumab resistance" (GSE58118 and GSE77346) were obtained for GEO database, and DEGs associated with drug-resistance were screened. Then, we analyzed correlations between gene expression and cancer immune infiltrates via Tumor Immune Estimation Resource (TIMER) site. The cBioportal database was used to analyze drug-resistant gene mutation status and survival. One hundred and fifty-five differentially expressed IRGs were screened between GC and normal tissues, and a prognostic signature consisting of four IRGs (NRP1, PPP3R1, IL17RA, and FGF16) was closely related to the overall survival (OS). According to cutoff value of risk score, patients were divided into high-risk and low-risk group. Patients in the high-risk group had shorter OS compared to the low-risk group in both the training (p < 0.0001) and testing sets (p = 0.0021). In addition, we developed a 5-IRGs (LGR6, DKK1, TNFRSF1B, NRP1, and CXCR4) signature which may participate in drug resistance processes in GC. Survival analysis showed that patients with drug-resistant gene mutations had shorter OS (p = 0.0459) and DFS (p < 0.001). We constructed four survival-related IRGs and five IRGs related to drug resistance which may contribute to predict the prognosis of GC.

Infiltrative Hepatocellular Carcinoma: Transcatheter Arterial Chemoembolization Versus Hepatic Arterial Infusion Chemotherapy.

AIMS: To compare the effectiveness, safety, and survival outcomes in patients with infiltrative hepatocellular carcinoma (HCC) who underwent hepatic arterial infusion chemotherapy (HAIC) and transarterial chemoembolization (TACE). METHODS: A total of 160 patients with infiltrative HCCs who underwent initial TACE (n = 68) and HAIC (n = 92) treatment from January 2016 to March 2020. We applied the propensity score matching (PSM) to adjust for potential imbalances. The overall survival (OS), progression-free survival (PFS), objective response rate (ORR) and disease control rate (DCR) were compared between two groups. Multivariate analysis was evaluated through the forward stepwise Cox regression model and ß coefficients was applied for the nomogram construction. RESULTS: The median follow-up duration for the study population was 20.8 months. After PSM, the median OS and PFS in the HAIC group were significantly higher than those in the TACE group (OS, 13.3 vs 10.8 months; p = 0.043; PFS, 7.8 vs 4.0 months; p = 0.035) and the ORR and DCR in the HAIC group were significantly higher than those in the TACE group (ORR, 34.8% vs 11.8%; p = 0.001; DCR, 54.3% vs 36.8%; p = 0.028). A nomogram model comprising albumin-bilirubin grade, treatment responses, sessions, and treatment modalities, showed good predictive accuracy and discrimination (training set, concordance index [C-index] of 0.789; validation set, C-index of 0.757), which outperformed other staging systems and conventional indices. CONCLUSION: HAIC improve significantly survival compared to TACE in patients with infiltrative HCC. A prospective randomized trial is ongoing to confirm this finding.

Bioinformatic analysis and in vitro validation of a five-microRNA signature as a prognostic biomarker of hepatocellular carcinoma.

BACKGROUND: Existing research has identified correlations between numerous microRNAs (miRNAs) and the prognosis of hepatocellular carcinoma (HCC). However, the role of a combination of miRNAs in predicting HCC survival requires further elucidation. METHODS: miRNA expression profiles and clinical data from HCC patients were downloaded from The Cancer Genome Atlas (TCGA). Differentially expressed (DE) miRNAs in tumor versus normal samples were identified. All HCC patients were randomly assigned to a training cohort or a validation cohort at a ratio of 1 to 1. A least absolute shrinkage and selection operator (LASSO) Cox regression model was subsequently employed to establish the miRNA signature. The constructed miRNA signature was then developed and validated. RESULTS: In total, 127 DE miRNAs were detected between HCC and paracancerous tissue using HCC RNA sequencing (RNA-Seq) data extracted from TCGA database. LASSO Cox regression generated a five-miRNA signature consisting of has-mir-105-2, has-mir-9-3, has-mir-137, has-mir-548f-1, and has-mir-561 in the training cohort. This risk model was significantly related to survival (P=5.682e-6). Log-rank tests and multivariate Cox regression analyses revealed the five-miRNA signature as an independent prognostic indicator [HR =3.285, 95% confidence interval (CI): 1.737-6.213], with the area under curve (AUC) of the miRNA signature being 0.728. The effects of the miRNA signature were further confirmed in the validation cohort and in the OncomiR Cancer Database and Gene Expression Omnibus (GEO) dataset. Functional enrichment analysis revealed the potential effects of the five-miRNA signature in tumor-related biological pathways and processes. Cell Counting Kit-8, Transwell, and wound healing assays, were used to evaluate the role of has-mir-137 in HCC cell proliferation and migration in vitro. CONCLUSIONS: We established a novel five-miRNA signature which reliably predicted prognosis in HCC patients and which could be used to assist in both strategic counseling and personalized management in HCC.