Estimating effects of whole grain consumption on type 2 diabetes, colorectal cancer and cardiovascular disease: a burden of proof study.

BACKGROUND: Previous studies on whole grain consumption had inconsistent findings and lacked quantitative assessments of evidence quality. Therefore, we aimed to summarize updated findings using the Burden of Proof analysis (BPRF) to investigate the relationship of whole grain consumption on type 2 diabetes (T2D), colorectal cancer (CRC), stroke, and ischemic heart disease (IHD). METHODS: We conducted a literature search in the Medline and Web of Science up to June 12, 2023, to identify related cohort studies and systematic reviews. The mean RR (relative risk) curve and uncertainty intervals (UIs), BPRF function, risk-outcome score (ROS), and the theoretical minimum risk exposure level (TMREL) were estimated to evaluate the level of four risk-outcome pairs. RESULTS: In total, 27 prospective cohorts were included in our analysis. Consuming whole grain at the range of TMREL (118.5-148.1 g per day) was associated with lower risks: T2D (declined by 37.3%, 95% UI: 5.8 to 59.5), CRC (declined by 17.3%, 6.5 to 27.7), stroke (declined by 21.8%, 7.3 to 35.1), and IHD (declined by 36.9%, 7.1 to 58.0). For all outcomes except stroke, we observed a non-linear, monotonic decrease as whole grain consumption increased; For stroke, it followed a J-shaped curve (the greatest decline in the risk of stroke at consuming 100 g whole grain for a day). The relationships between whole grain consumption and four diseases are all two-star pairs (ROS: 0.087, 0.068, 0.062, 0.095 for T2D, CRC, stroke, and IHD, respectively). CONCLUSION: Consuming 100 g of whole grains per day offers broad protective benefits. However, exceeding this threshold may diminish the protective effects against stroke. Our findings endorse replacing refined grains with whole grains as the main source of daily carbohydrates. REGISTRY AND REGISTRY NUMBER FOR SYSTEMATIC REVIEWS OR META-ANALYSES: We have registered our research in PROSPERO, and the identifier of our meta-analyses is CRD42023447345.

Enhancing diagnosis of benign lesions and lung cancer through ensemble text and breath analysis: a retrospective cohort study.

Early diagnosis of lung cancer (LC) can significantly reduce its mortality rate. Considering the limitations of the high false positive rate and reliance on radiologists' experience in computed tomography (CT)-based diagnosis, a multi-modal early LC screening model that combines radiology with other non-invasive, rapid detection methods is warranted. A high-resolution, multi-modal, and low-differentiation LC screening strategy named ensemble text and breath analysis (ETBA) is proposed that ensembles radiology report text analysis and breath analysis. In total, 231 samples (140 LC patients and 91 benign lesions [BL] patients) were screened using proton transfer reaction-time of flight-mass spectrometry and CT screening. Participants were randomly assigned to a training set and a validation set (4:1) with stratification. The report section of the radiology reports was used to train a text analysis (TA) model with a natural language processing algorithm. Twenty-two volatile organic compounds (VOCs) in the exhaled breath and the prediction results of the TA model were used as predictors to develop the ETBA model using an extreme gradient boosting algorithm. A breath analysis model was developed based on the 22 VOCs. The BA and TA models were compared with the ETBA model. The ETBA model achieved a sensitivity of 94.3%, a specificity of 77.3%, and an accuracy of 87.7% with the validation set. The radiologist diagnosis performance with the validation set had a sensitivity of 74.3%, a specificity of 59.1%, and an accuracy of 68.1%. High sensitivity and specificity were obtained by the ETBA model compared with radiologist diagnosis. The ETBA model has the potential to provide sensitivity and specificity in CT screening of LC. This approach is rapid, non-invasive, multi-dimensional, and accurate for LC and BL diagnosis.

Advances in metabolic reprogramming of NK cells in the tumor microenvironment on the impact of NK therapy.

Natural killer (NK) cells are unique from other immune cells in that they can rapidly kill multiple neighboring cells without the need for antigenic pre-sensitization once the cells display surface markers associated with oncogenic transformation. Given the dynamic role of NK cells in tumor surveillance, NK cell-based immunotherapy is rapidly becoming a "new force" in tumor immunotherapy. However, challenges remain in the use of NK cell immunotherapy in the treatment of solid tumors. Many metabolic features of the tumor microenvironment (TME) of solid tumors, including oxygen and nutrient (e.g., glucose, amino acids) deprivation, accumulation of specific metabolites (e.g., lactate, adenosine), and limited availability of signaling molecules that allow for metabolic reorganization, multifactorial shaping of the immune-suppressing TME impairs tumor-infiltrating NK cell function. This becomes a key barrier limiting the success of NK cell immunotherapy in solid tumors. Restoration of endogenous NK cells in the TME or overt transfer of functionally improved NK cells holds great promise in cancer therapy. In this paper, we summarize the metabolic biology of NK cells, discuss the effects of TME on NK cell metabolism and effector functions, and review emerging strategies for targeting metabolism-improved NK cell immunotherapy in the TME to circumvent these barriers to achieve superior efficacy of NK cell immunotherapy.

Research progress on the role of tumor­associated macrophages in tumor development and their use as molecular targets (Review).

The tumor microenvironment (TME) is a complex system composed mainly of tumor cells, mesenchymal cells and immune cells. Macrophages, also known as tumor­associated macrophages (TAMs), among innate immune cells, are some of the most abundant components of the TME. They may influence tumor growth and metastasis through interactions with other cell populations in the TME and have been associated with poor prognosis in a variety of tumors. Therefore, a better understanding of the role of TAMs in the TME may provide new insight into tumor therapy. In the present review, the origin and classification of TAMs in the TME were outlined and their polarization and dual effects on tumor cells, as well as emerging strategies for cancer therapies targeting TAMs, were discussed.

Case Report: Replacement of PD-1 inhibitors with PD-L1 inhibitors in the treatment of squamous non-small-cell lung carcinoma.

Background: Immune checkpoint inhibitor (ICI)-associated cardiotoxicity is a relatively uncommon immune-related adverse effects (irAEs) with a high mortality rate. There are few recommendations for the replacement of different immune checkpoint inhibitors in domestic and international reports. Case presentation: We report a case of a patient with squamous non-small cell lung carcinoma (squamous NSCLC) who developed cardiotoxicity after being treated with a programmed death-1 (PD-1) inhibitor and then changed to a PD-L1 inhibitor to continue the treatment. A significant benefit was observed after four cycles of immunotherapy, and no further cardiotoxicity occurred after the treatment was started. Conclusion: This case demonstrates that myocardial damage induced by tislelizumab (PD-1 inhibitor) can be improved after switching to sugemalimab (PD-L1 inhibitor) and that antitumor immunotherapy is effective. This result may have important implications for optimizing immunotherapy management regimens in cancer patients.

Associations of chest X-ray trajectories, smoking, and the risk of lung cancer in two population-based cohort studies.

Objectives: Despite the increasing use of computed tomography (CT), chest X-ray (CXR) remains the first-line investigation for suspected lung cancer (LC) in primary care. However, the associations of CXR trajectories, smoking and LC risk remain unknown. Methods: A total of 52,486 participants from the PLCO and 22,194 participants from the NLST were included. The associations of CXR trajectories with LC risk were evaluated with multivariable COX regression models and pooled with meta-analyses. Further analyses were conducted to explore the stratified associations by smoking status and the factors associated with progression and regression in CXR. Results: Compared to stable negative CXR (CXRSN), HRs (95%CIs) of LC incidence were 2.88(1.50-5.52), 3.86(2.03-7.35), and 1.08(0.80-1.46) for gain of positive CXR (CXRGP), stable positive CXR (CXRSP), and loss of positive CXR (CXRLP), while the risk of LC mortality were 1.58(1.33-1.87), 2.56(1.53-4.29), and 1.05(0.89-1.25). Similar trends were observed across different smoking status. However, LC risk with CXRGP overweighed that with CXRSP among ever smokers [2.95(2.25-3.88) vs. 2.59(1.33-5.02)] and current smokers [2.33(1.70-3.18) vs. 2.26(1.06-4.83)]. Moreover, compared to CXRSN among never smokers, even no progression in CXR, the HRs(95%CIs) of LC incidence were 7.39(5.60-9.75) and 31.45(23.58-41.95) for ever and current smokers, while risks of LC mortality were 6.30(5.07-7.81) and 27.17(21.65-34.11). If participants gained positive CXR, LC incidence risk significantly climbed to 22.04(15.37-31.60) and 71.97(48.82-106.09) for ever and current smokers, while LC mortality risk climbed to 11.90(8.58-16.50) and 38.92(27.04-56.02). CXRLP was associated with decreased LC risk. However, even smokers lost their positive CXR, and the increased risks of LC incidence and mortality did not decrease to non-significant level. Additionally, smoking was significantly associated with increased risk of CXRGP but not CXRLP. Conclusion: LC risk differed across CXR trajectories and would be modified by smoking status. Comprehensive intervention incorporating CXR trajectories and smoking status should be recommended to reduce LC risk.

Bufalin serves as a pharmaceutic that mitigates drug resistance.

Intrinsic or acquired drug resistance of tumor cells is the main cause of tumor chemotherapy failure and tumor-related death. Bufalin (BF) is the main active monomer component extracted from the Traditional Chinese Medicine Toad venom (secretions of glands behind the ears and epidermis of bufo gargarizans and Bufo Melanostictus Schneider). It is a cardiotonic steroid with broad-spectrum anti-cancer effects and has been widely used against various malignant tumors in clinical practice. Pharmacological studies also found that BF has the effect of reversing drug resistance, which provides a new perspective for the application of Traditional Chinese Medicine as a chemosensitizer in cancer therapy. This article provides an extensive search and summary of published research on mitigating drug resistance to BF and reviews its potential mechanisms.

Prospective role of PD-1/PD-L1 immune checkpoint inhibitors in GI cancer.

One of the mechanisms by which tumor cells can evade the immune system is over activation of the programmed cell death protein-1 (PD-1) / programmed death-ligand 1 (PD-L1) pathway. The binding of PD-1 to its ligand PD-L1 can trigger an inhibitory signal for reducing T-cell proliferation, inhibiting the anticancer effect of T cells, and limiting the anti-tumor immunity of effectors T cell responses to protect tissues from immune-mediated tissue damage in the tumor microenvironment (TME). PD-1/PD-L1 immune checkpoint inhibitors have created a new pattern in cancer immunotherapy and can increase T cell- surveillance; therefore, the development of better clinical application of PD-1/PD-L1 inhibitors can significantly enhance antitumor immunity and prolong survival in GI cancer patients.

Prediction of histologic types in solid lung lesions using preoperative contrast-enhanced CT.

OBJECTIVES: This study aimed to develop and validate a predicting model for the histologic classification of solid lung lesions based on preoperative contrast-enhanced CT. METHODS: A primary dataset of 1012 patients from Tianjin Medical University Cancer Institute and Hospital (TMUCIH) was randomly divided into a development cohort (708) and an internal validation cohort (304). Patients from the Second Hospital of Shanxi Medical University (SHSMU) were set as an external validation cohort (212). Two clinical factors (age, gender) and twenty-one characteristics on contrast-enhanced CT were used to construct a multinomial multivariable logistic regression model for the classification of seven common histologic types of solid lung lesions. The area under the receiver operating characteristic curve was used to assess the diagnostic performance of the model in the development and validation cohorts, separately. RESULTS: Multivariable analysis showed that two clinical factors and twenty-one characteristics on contrast-enhanced CT were predictive in lung lesion histologic classification. The mean AUC of the proposed model for histologic classification was 0.95, 0.94, and 0.92 in the development, internal validation, and external validation cohort, respectively. When determining the malignancy of lung lesions based on histologic types, the mean AUC of the model was 0.88, 0.86, and 0.90 in three cohorts. CONCLUSIONS: We demonstrated that by utilizing both clinical and CT characteristics on contrast-enhanced CT images, the proposed model could not only effectively stratify histologic types of solid lung lesions, but also enabled accurate assessment of lung lesion malignancy. Such a model has the potential to avoid unnecessary surgery for patients and to guide clinical decision-making for preoperative treatment. KEY POINTS: • Clinical and CT characteristics on contrast-enhanced CT could be used to differentiate histologic types of solid lung lesions. • Predicting models using preoperative contrast-enhanced CT could accurately assessment of tumor malignancy based on predicted histologic types.

Effects of Exosomes on Tumor Bioregulation and Diagnosis.

Exosomes are lipid bilayer vesicles in biological fluids, which can participate in biological processes by mediating intercellular communication and activating intracellular signaling pathways, especially cancerogenic processes, such as proliferation, metastasis, invasion, and immune regulation of cancer cells. Besides, cancer-derived exosomes are also involved in tumor diagnosis and therapy as biomarkers and nanotransport devices. This article reviews the latest research progress on the biological regulation and disease diagnosis of exosomes in tumors, with the aim of providing new ideas for the clinical treatment of cancers.

Anlotinib combined with TAS-102 as the third-line treatment for a patient with metastatic colon cancer: A case report.

Chemotherapy combined with targeted therapy is a first-line and second-line treatment for metastatic colorectal cancer(mCRC), which has brought survival benefits to mCRC patients, however, disease progression is inevitable. More than 60% of patients still needed third-line treatment after the progress of second-line treatment. After the failure of second-line chemotherapy, treatment compliance and the physical tolerance of patients both decrease. Therefore, choosing an appropriate third-line treatment regimen is key to prolonging survival and improving quality of life. As a novel cytotoxic antitumor drug, trifluridine/tipiracil (TAS-102) is composed of trifluridine (FTD) and tipiracil hydrochloride (TPI). FTD can directly bind to the DNA of cancer cells to cause DNA dysfunction, thereby exerting antitumor effects. TPI can inhibit the degradation of FTD, thereby increasing its cytotoxicity. The few side effects of TAS-102 has become an important reason why clinicians present it as a treatment option to the patient for consideration, clinical trial data for progression free survival are lacking. The exploration of third-line treatment regimens with drug combinations has attracted much attention. This article reports a case of metastatic colon cancer (RAS/BRAF wild type, pMMR/Non-MSI-H), after failure of first-line and second-line therapies, the patient was eventually treated with anlotinib combined with TAS-102 as the third-line treatment. The treatment has shown good efficacy, with a long PFS benefit for more than 20 months and mild adverse reactions. This case reports demonstrates that anlotinib combined with TAS-102 is a promising third-line treatment regimen for refractory mCRC, and provides proof-of-concept for the clinical exploration of optimal third-line combination treatment regimens.

VLDLR disturbs quiescence of breast cancer stem cells in a ligand-independent function.

Breast cancer stem cells are responsible for cancer initiation, progression, and drug resistance. However, effective targeting strategies against the cell subpopulation are still limited. Here, we unveil two splice variants of very-low-density lipoprotein receptor, VLDLR-I and -II, which are highly expressed in breast cancer stem cells. In breast cancer cells, VLDLR silencing suppresses sphere formation abilities in vitro and tumor growth in vivo. We find that VLDLR knockdown induces transition from self-renewal to quiescence. Surprisingly, ligand-binding activity is not involved in the cancer-promoting functions of VLDLR-I and -II. Proteomic analysis reveals that citrate cycle and ribosome biogenesis-related proteins are upregulated in VLDLR-I and -II overexpressed cells, suggesting that VLDLR dysregulation is associated with metabolic and anabolic regulation. Moreover, high expression of VLDLR in breast cancer tissues correlates with poor prognosis of patients. Collectively, these findings indicate that VLDLR may be an important therapeutic target for breast cancer treatment.

Establishment and Validation of a Nomogram Prognostic Model for Epithelioid Hemangioendothelioma.

Background: Epithelioid hemangioendothelioma (EHE) is an ultrarare vascular sarcoma. At present, the epidemiological and clinical characteristics and prognostic factors are still unclear. Our study attempted to describe clinical features, investigate the prognostic indicators, and establish the nomogram prediction model based on the Surveillance, Epidemiology, and End Results (SEER) database for EHE patients. Methods: The patients diagnosed with EHE from 1986 to 2018 were collected from the SEER database and were randomly divided into a training group and a validation group at a ratio of 7 : 3. The Cox proportional hazard models were used to determine the independent factors affecting prognosis and establish a nomogram prognostic model to predict the survival rates for patients with EHE. The accuracy and discriminative ability of the model were measured using the concordance index, receiver operating characteristic curves, and calibration curves. The clinical applicability and application value of the model were evaluated by decision curve analysis. Results: The overall age-adjusted incidence of EHE was 0.31 patients per 1,000,000 individuals, with a statistically significant difference per year. Overall survival at 1, 5, and 10 years for all patients was 76.5%, 57.4%, and 48.2%, respectively. Multivariate Cox regression analysis identified age, tumour stage, degree of tissue differentiation, surgical treatment, chemotherapy, and radiotherapy as independent factors affecting prognosis (P < 0.05). The C-index values for our nomogram model of training group and validation group were 0.752 and 0.753, respectively. The calibration curve was in good agreement with the actual observation results, suggesting that the prediction model has good accuracy. The decision curve analysis indicated a relatively large net benefit. Conclusions: The nomogram model may play an important role in predicting the survival rate for EHE patients, with good concordance and accuracy, and can be applied in clinical practice.

Corrigendum: Successful treatment of a patient with multiple-line relapsed extensive-stage small-cell lung cancer receiving penpulimab combined with anlotinib: A case report.

[This corrects the article DOI: 10.3389/fonc.2022.846597.].

Multidimensional Feature Optimization Based Eye Blink Detection Under Epileptiform Discharges.

OBJECTIVES: Eye blink artifact detection in scalp electroencephalogram (EEG) of epilepsy patients is challenging due to its similar waveforms to epileptiform discharges. Developing an accurate detection method is urgent and critical. METHODS: In this paper, we proposed a novel multi-dimensional feature optimization based eye blink artifact detection algorithm for EEGs containing rich epileptiform discharges. An unsupervised clustering algorithm based on smoothed nonlinear energy operator (SNEO) and variational mode extraction (VME) is proposed to detect epileptiform discharges in the frontal leads. Then, multi-dimensional time/frequency EEG features extracted from forehead electrodes (FP1 and FP2 channels) combining with the improved VME (IVME) threshold are derived for EEG representation. A variance filtering method is further applied for discriminative feature selection and a machine learning model is finally learned to perform detection. RESULTS: Experiments on EEGs of 16 subjects from the Children's Hospital of Zhejiang University School of Medicine (CHZU) show that our method achieves the highest average sensitivity, specificity and accuracy of 95.04, 89.52, and 93.01, respectively. That outperforms 5 recent and state-of-the-art (SOTA) eye blink detection algorithms. SIGNIFICANCE: The proposed method is robust in eye blink artifact detection for EEGs containing high-frequency epileptiform discharges. It is also effective in dealing with individual differences in EEGs, which is usually ignored in conventional methods.

Research Progress in Immunotherapy of NSCLC With EGFR-Sensitive Mutations.

Lung cancer is a malignant tumor with high incidence and mortality across the world. The use of immune checkpoint inhibitors for lung cancer has improved the prognosis of some lung cancer patients to a greater extent and provided a new direction for the clinical treatment of lung cancer. Immunotherapy still has limitations in terms of its appropriate population and adverse reactions. Particularly for non-small cell lung cancer (NSCLC) patients with epidermal growth factor receptor (EGFR) mutation, there has been no major breakthrough in current immunotherapy. Whether immunotherapy can bring new benefits after drug resistance is induced by tyrosine kinase inhibitor-targeted therapy and whether the combination of immunotherapy with other treatments can improve the prognosis remain to be studied in depth. In this article, we provide a detailed review of the relevant characteristics of the tumor microenvironment of NSCLC with EGFR mutation and the current research on immunotherapy for NSCLC with EGFR mutation.

The Research Progress of Bufalin in the Treatment of Hepatocellular Carcinoma.

Hepatocellular carcinoma (HCC) is one of the deadliest cancers in the world with a five-year survival rate of less than 20%. Nonetheless, selecting an appropriate therapeutic agent to inhibit the development of hepatoma cells is still a challenge. Bufalin, a component of the traditional Chinese medicine Chansu, has been shown to inhibit the proliferation, invasion and metastasis of HCC through various signaling pathways. In addition, bufalin and sorafenib demonstrate a synergistic effect in cancer therapeutics. This review highlighted on several focal signaling pathways involved in the inhibitory effects of bufalin on HCC and its synergistic mechanisms with sorafenib. The immunotherapy effect of bufalin has also been discussed as a novel property.

Deep feature fusion based childhood epilepsy syndrome classification from electroencephalogram.

Accurate classification of the children's epilepsy syndrome is vital to the diagnosis and treatment of epilepsy. But existing literature mainly focuses on seizure detection and few attention has been paid to the children's epilepsy syndrome classification. In this paper, we present a study on the classification of two most common epilepsy syndromes: the benign childhood epilepsy with centro-temporal spikes (BECT) and the infantile spasms (also known as the WEST syndrome), recorded from the Children's Hospital, Zhejiang University School of Medicine (CHZU). A novel feature fusion model based on the deep transfer learning and the conventional time-frequency representation of the scalp electroencephalogram (EEG) is developed for the epilepsy syndrome characterization. A fully connected network is constructed for the feature learning and syndrome classification. Experiments on the CHZU database show that the proposed algorithm can offer an average of 92.35% classification accuracy on the BECT and WEST syndromes and their corresponding normal cases.

Successful Treatment of a Patient With Multiple-Line Relapsed Extensive-Stage Small-Cell Lung Cancer Receiving Penpulimab Combined With Anlotinib: A Case Report.

Small-cell lung cancer (SCLC) is a highly malignant, rapidly developing group of diseases with poor biological behavior. Most patients have extensive-stage SCLC (ES-SCLC) when they are first diagnosed. Standard chemotherapy is prone to relapse in a short period of time, and the patients' median overall survival (OS) can reach only 13 months when chemotherapy is given in combination with PD-L1 inhibitors. To date, no studies have verified the efficacy and safety of the composite treatment of ES-SCLC with penpulimab and anlotinib despite some recognized data and advantages related to this regimen. Penpulimab, a novel PD-1 inhibitor with an IgG1 subtype, has a structural modification of the Fc segment which can prevent the immune cells from being phagocytosed or killed and can steadily avoid tumor immune escape. This case report describes a 71-year-old man who had ES-SCLC for 7 years which progressed after receiving standard systemic chemotherapy combined with radiotherapy. The third-line treatment of four cycles of anlotinib and carilizumab was discontinued because of grade 2 immune-related pneumonia despite the efficacy being evaluated as stable disease. After maintaining 22 months of progression-free survival, the patient relapsed and switched to a safer regimen of penpulimab combined with anlotinib to continue the treatment for four cycles. Partial response evaluation was confirmed twice, and the patient remained in good general condition. The combination of penpulimab and anlotinib can positively regulate the therapeutic effect by simultaneously acting on the tumor microenvironment and promoting blood vessel normalization. In general, this case provides support for the successful possibility of a rechallenge with immune checkpoint inhibitors, the better clinical efficacy of cross-line therapy with anlotinib, and the drug safety of penpulimab, suggesting a beneficial therapy for the clinical treatment of ES-SCLC.

Performance of a deep learning-based lung nodule detection system as an alternative reader in a Chinese lung cancer screening program.

OBJECTIVE: To evaluate the performance of a deep learning-based computer-aided detection (DL-CAD) system in a Chinese low-dose CT (LDCT) lung cancer screening program. MATERIALS AND METHODS: One-hundred-and-eighty individuals with a lung nodule on their baseline LDCT lung cancer screening scan were randomly mixed with screenees without nodules in a 1:1 ratio (total: 360 individuals). All scans were assessed by double reading and subsequently processed by an academic DL-CAD system. The findings of double reading and the DL-CAD system were then evaluated by two senior radiologists to derive the reference standard. The detection performance was evaluated by the Free Response Operating Characteristic curve, sensitivity and false-positive (FP) rate. The senior radiologists categorized nodules according to nodule diameter, type (solid, part-solid, non-solid) and Lung-RADS. RESULTS: The reference standard consisted of 262 nodules ≥ 4 mm in 196 individuals; 359 findings were considered false positives. The DL-CAD system achieved a sensitivity of 90.1% with 1.0 FP/scan for detection of lung nodules regardless of size or type, whereas double reading had a sensitivity of 76.0% with 0.04 FP/scan (P = 0.001). The sensitivity for detection of nodules ≥ 4 - ≤ 6 mm was significantly higher with DL-CAD than with double reading (86.3% vs. 58.9% respectively; P = 0.001). Sixty-three nodules were only identified by the DL-CAD system, and 27 nodules only found by double reading. The DL-CAD system reached similar performance compared to double reading in Lung-RADS 3 (94.3% vs. 90.0%, P = 0.549) and Lung-RADS 4 nodules (100.0% vs. 97.0%, P = 1.000), but showed a higher sensitivity in Lung-RADS 2 (86.2% vs. 65.4%, P < 0.001). CONCLUSIONS: The DL-CAD system can accurately detect pulmonary nodules on LDCT, with an acceptable false-positive rate of 1 nodule per scan and has higher detection performance than double reading. This DL-CAD system may assist radiologists in nodule detection in LDCT lung cancer screening.