The Gap in the Thickness: Estimating Effectiveness of Pulmonary Nodule Detection in Thick- and Thin-Section CT Images with 3D Deep Neural Networks.

BACKGROUND AND OBJECTIVES: There is a noticeable gap in diagnostic evidence strength between the thick and thin scans of Low-Dose CT (LDCT) for pulmonary nodule detection. When the thin scans are needed is unknown, especially when aided with an artificial intelligence nodule detection system. METHODS: A case study is conducted with a set of 1,000 pulmonary nodule screening LDCT scans with both thick (5.0mm), and thin (1.0mm) section scans available. Pulmonary nodule detection is performed by human and artificial intelligence models for nodule detection developed using 3D convolutional neural networks (CNNs). The intra-sample consistency is evaluated with thick and thin scans, for both clinical doctor and NN (neural network) models. Free receiver operating characteristic (FROC) is used to measure the accuracy of humans and NNs. RESULTS: Trained NNs outperform humans with small nodules < 6.0mm, which is a good complement to human ability. For nodules > 6.0mm, human and NNs perform similarly while human takes a fractional advantage. By allowing a few more FPs, a significant sensitivity improvement can be achieved with NNs. CONCLUSIONS: There is a performance gap between the thick and thin scans for pulmonary nodule detection regarding both false negatives and false positives. NNs can help reduce false negatives when the nodules are small and trade off the false negatives for sensitivity. A combination of human and trained NNs is a promising way to achieve a fast and accurate diagnosis.

Prognostic Value of Albumin-to-Alkaline Phosphatase Ratio for EGFR-Mutated Advanced Non-Small-Cell Lung Cancer Patients Treated with First-Line EGFR-TKIs: A Large Population-Based Study and Literature Review.

Background: Resistance inevitably develops in epidermal growth factor receptor (EGFR)-mutated advanced non-small-cell lung cancer (NSCLC) patients after treatment of EGFR tyrosine kinase inhibitors (EGFR-TKIs). The albumin-to-alkaline phosphatase ratio (AAPR), a novel index, has been reported to be associated with survival in various cancers. In this study, we explored the prognostic value of AAPR in EGFR-mutated advanced NSCLC patients treated with first-line EGFR-TKIs. Methods: The clinical and pretreatment laboratory data were retrospectively extracted from hospital medical system. The Log-rank and Kaplan-Meier analyses were adopted to detect differences in survival between groups. Univariate and multivariate Cox's proportional hazard regression models were applied to assess the prognostic value of AAPR for progression-free survival (PFS) and overall survival (OS). Results: Totally, 598 EGFR-mutated NSCLC patients with stage IIIB-IV were enrolled into this study. The median age of all patients was 60 years, and 56.9% were women. About 97% patients had common EGFR gene mutations of deletions in exon 19 (19 del) or a point mutation in exon 21 (L858R). Using receiver operating characteristic (ROC) curve analysis and the Youden index, the optimal cut-off value of pretreatment AAPR was 0.47. Patients with high AAPR achieved longer median PFS and OS than patients with low AAPR (14.0 months vs 10.4 months, P<0.01; 58.2 months vs 36.7 months, P<0.001, respectively). The multivariate analysis by Cox's proportional hazards regression model demonstrated that AAPR was an independent prognostic factor for both PFS (HR: 0.813, 95% CI: 0.673-0.984, P=0.033) and OS (HR: 0.629, 95% CI: 0.476-0.830, P=0.001). Conclusion: Pretreatment AAPR, measured as part of routine blood biochemical test, may be a reliable prognostic indicator in EGFR-mutated advanced NSCLC patients treated with first-line first-generation EGFR-TKIs.

Mining whole-lung information by artificial intelligence for predicting EGFR genotype and targeted therapy response in lung cancer: a multicohort study.

BACKGROUND: Epidermal growth factor receptor (EGFR) genotype is crucial for treatment decision making in lung cancer, but it can be affected by tumour heterogeneity and invasive biopsy during gene sequencing. Importantly, not all patients with an EGFR mutation have good prognosis with EGFR-tyrosine kinase inhibitors (TKIs), indicating the necessity of stratifying for EGFR-mutant genotype. In this study, we proposed a fully automated artificial intelligence system (FAIS) that mines whole-lung information from CT images to predict EGFR genotype and prognosis with EGFR-TKI treatment. METHODS: We included 18 232 patients with lung cancer with CT imaging and EGFR gene sequencing from nine cohorts in China and the USA, including a prospective cohort in an Asian population (n=891) and The Cancer Imaging Archive cohort in a White population. These cohorts were divided into thick CT group and thin CT group. The FAIS was built for predicting EGFR genotype and progression-free survival of patients receiving EGFR-TKIs, and it was evaluated by area under the curve (AUC) and Kaplan-Meier analysis. We further built two tumour-based deep learning models as comparison with the FAIS, and we explored the value of combining FAIS and clinical factors (the FAIS-C model). Additionally, we included 891 patients with 56-panel next-generation sequencing and 87 patients with RNA sequencing data to explore the biological mechanisms of FAIS. FINDINGS: FAIS achieved AUCs ranging from 0·748 to 0·813 in the six retrospective and prospective testing cohorts, outperforming the commonly used tumour-based deep learning model. Genotype predicted by the FAIS-C model was significantly associated with prognosis to EGFR-TKIs treatment (log-rank p<0·05), an important complement to gene sequencing. Moreover, we found 29 prognostic deep learning features in FAIS that were able to identify patients with an EGFR mutation at high risk of TKI resistance. These features showed strong associations with multiple genotypes (p<0·05, t test or Wilcoxon test) and gene pathways linked to drug resistance and cancer progression mechanisms. INTERPRETATION: FAIS provides a non-invasive method to detect EGFR genotype and identify patients with an EGFR mutation at high risk of TKI resistance. The superior performance of FAIS over tumour-based deep learning methods suggests that genotype and prognostic information could be obtained from the whole lung instead of only tumour tissues. FUNDING: National Natural Science Foundation of China.

DeepLN: an artificial intelligence-based automated system for lung cancer screening.

BACKGROUND: Lung cancer causes more deaths worldwide than any other cancer. For early-stage patients, low-dose computed tomography (LDCT) of the chest is considered to be an effective screening measure for reducing the risk of mortality. The accuracy and efficiency of cancer screening would be enhanced by an intelligent and automated system that meets or surpasses the diagnostic capabilities of human experts. METHODS: Based on the artificial intelligence (AI) technique, i.e., deep neural network (DNN), we designed a framework for lung cancer screening. First, a semi-automated annotation strategy was used to label the images for training. Then, the DNN-based models for the detection of lung nodules (LNs) and benign or malignancy classification were proposed to identify lung cancer from LDCT images. Finally, the constructed DNN-based LN detection and identification system was named as DeepLN and confirmed using a large-scale dataset. RESULTS: A dataset of multi-resolution LDCT images was constructed and annotated by a multidisciplinary group and used to train and evaluate the proposed models. The sensitivity of LN detection was 96.5% and 89.6% in a thin section subset [the free-response receiver operating characteristic (FROC) is 0.716] and a thick section subset (the FROC is 0.699), respectively. With an accuracy of 92.46%±0.20%, a specificity of 95.93%±0.47%, and a precision of 90.46%±0.93%, an ensemble result of benign or malignancy identification demonstrated a very good performance. Three retrospective clinical comparisons of the DeepLN system with human experts showed a high detection accuracy of 99.02%. CONCLUSIONS: In this study, we presented an AI-based system with the potential to improve the performance and work efficiency of radiologists in lung cancer screening. The effectiveness of the proposed system was verified through retrospective clinical evaluation. Thus, the future application of this system is expected to help patients and society.

Risk factors for predicting mortality of COVID-19 patients: A systematic review and meta-analysis.

BACKGROUND: Early and accurate prognosis prediction of the patients was urgently warranted due to the widespread popularity of COVID-19. We performed a meta-analysis aimed at comprehensively summarizing the clinical characteristics and laboratory abnormalities correlated with increased risk of mortality in COVID-19 patients. METHODS: PubMed, Scopus, Web of Science, and Embase were systematically searched for studies considering the relationship between COVID-19 and mortality up to 4 June 2020. Data were extracted including clinical characteristics and laboratory examination. RESULTS: Thirty-one studies involving 9407 COVID-19 patients were included. Dyspnea (OR = 4.52, 95%CI [3.15, 6.48], P < 0.001), chest tightness (OR = 2.50, 95%CI [1.78, 3.52], P<0.001), hemoptysis (OR = 2.00, 95%CI [1.02, 3.93], P = 0.045), expectoration (OR = 1.52, 95%CI [1.17, 1.97], P = 0.002) and fatigue (OR = 1.27, 95%CI [1.09, 1.48], P = 0.003) were significantly related to increased risk of mortality in COVID-19 patients. Furthermore, increased pretreatment absolute leukocyte count (OR = 11.11, 95%CI [6.85,18.03], P<0.001) and decreased pretreatment absolute lymphocyte count (OR = 9.83, 95%CI [6.72, 14.38], P<0.001) were also associated with increased mortality of COVID-19. We also compared the mean value of them between survivors and non-survivors, and found that non-survivors showed significantly raise in pretreatment absolute leukocyte count (WMD: 3.27×109/L, 95%CI [2.34, 4.21], P<0.001) and reduction in pretreatment absolute lymphocyte count (WMD = -0.39×109/L, 95%CI [-0.46, -0.33], P<0.001) compared with survivors. The results of pretreatment lactate dehydrogenase (LDH), procalcitonin (PCT), D-Dimer and ferritin showed the similar trend with pretreatment absolute leukocyte count. CONCLUSIONS: Among the common symptoms of COVID-19 infections, fatigue, expectoration, hemoptysis, dyspnea and chest tightness were independent predictors of death. As for laboratory examinations, significantly increased pretreatment absolute leukocytosis count, LDH, PCT, D-Dimer and ferritin, and decreased pretreatment absolute lymphocyte count were found in non-survivors, which also have an unbeneficial impact on mortality among COVID-19 patients. Motoring these indicators during the hospitalization plays a very important role in predicting the prognosis of patients.

MSCS-DeepLN: Evaluating lung nodule malignancy using multi-scale cost-sensitive neural networks.

The accurate identification of malignant lung nodules using computed tomography (CT) screening images is vital for the early detection of lung cancer. It also offers patients the best chance of cure, because non-invasive CT imaging has the ability to capture intra-tumoral heterogeneity. Deep learning methods have obtained promising results for the malignancy identification problem; however, two substantial challenges still remain. First, small datasets cannot insufficiently train the model and tend to overfit it. Second, category imbalance in the data is a problem. In this paper, we propose a method called MSCS-DeepLN that evaluates lung nodule malignancy and simultaneously solves these two problems. Three light models are trained and combined to evaluate the malignancy of a lung nodule. Three-dimensional convolutional neural networks (CNNs) are employed as the backbone of each light model to extract the lung nodule features from CT images and preserve lung nodule spatial heterogeneity. Multi-scale input cropped from CT images enables the sub-networks to learn the multi-level contextual features and preserve diverse. To tackle the imbalance problem, our proposed method employs an AUC approximation as the penalty term. During training, the error in this penalty term is generated from each major and minor class pair, so that negatives and positives can contribute equally to updating this model. Based on these methods, we obtain state-of-the-art results on the LIDC-IDRI dataset. Furthermore, we constructed a new dataset collected from a grade-A tertiary hospital and annotated using biopsy-based cytological analysis to verify the performance of our method in clinical practice.

Diminishing microbiome richness and distinction in the lower respiratory tract of lung cancer patients: A multiple comparative study design with independent validation.

OBJECTIVES: Current evidence suggests that microorganisms are associated with neoplastic diseases; however, the role of the airway microbiome in lung cancer remains unknown. To investigate the taxonomic profiles of the lower respiratory tract (LRT) microbiome in patients with lung cancer. MATERIALS AND METHODS: BALF samples were collected in a discovery set comprising 150 individuals, including 91 patients with lung cancer, 29 patients with nonmalignant pulmonary diseases and 30 healthy subjects, and an independent validation set including 85 participants. The samples were assessed by metagenomics analysis. Random forest regression analysis was performed to select a diagnostic panel. RESULTS: In the discovery set, richness was reduced in lung cancer patients compared with that in healthy subjects, and the microbiome of patients with nonmalignant diseases resembled that of patients with lung cancer. Interestingly, Bradyrhizobium japonicum was only found in patients with lung cancer, whereas Acidovorax was found in patients with cancer and nonmalignant pulmonary diseases. A microbiota-related diagnostic model consisting of age, pack year of smoking and eleven types of bacteria was built, and the area under the curve (AUC) for discriminating the patients with cancer was 0.882 (95%CI: 0.807-0.957) in the training set and 0.796 (95%CI: 0.673-0.920) in the independent validation set. CONCLUSION: Our study demonstrates that the LRT microbiome richness is diminished in lung cancer patients compared with that in healthy subjects and that microbiota-specific biomarkers may be useful for diagnosing patients for whom lung biopsy is not feasible.

A New Approach to Predict Progression-free Survival in Stage IV EGFR-mutant NSCLC Patients with EGFR-TKI Therapy.

Purpose: We established a CT-derived approach to achieve accurate progression-free survival (PFS) prediction to EGFR tyrosine kinase inhibitors (TKI) therapy in multicenter, stage IV EGFR-mutated non-small cell lung cancer (NSCLC) patients.Experimental Design: A total of 1,032 CT-based phenotypic characteristics were extracted according to the intensity, shape, and texture of NSCLC pretherapy images. On the basis of these CT features extracted from 117 stage IV EGFR-mutant NSCLC patients, a CT-based phenotypic signature was proposed using a Cox regression model with LASSO penalty for the survival risk stratification of EGFR-TKI therapy. The signature was validated using two independent cohorts (101 and 96 patients, respectively). The benefit of EGFR-TKIs in stratified patients was then compared with another stage-IV EGFR-mutant NSCLC cohort only treated with standard chemotherapy (56 patients). Furthermore, an individualized prediction model incorporating the phenotypic signature and clinicopathologic risk characteristics was proposed for PFS prediction, and also validated by multicenter cohorts.Results: The signature consisted of 12 CT features demonstrated good accuracy for discriminating patients with rapid and slow progression to EGFR-TKI therapy in three cohorts (HR: 3.61, 3.77, and 3.67, respectively). Rapid progression patients received EGFR TKIs did not show significant difference with patients underwent chemotherapy for progression-free survival benefit (P = 0.682). Decision curve analysis revealed that the proposed model significantly improved the clinical benefit compared with the clinicopathologic-based characteristics model (P < 0.0001).Conclusions: The proposed CT-based predictive strategy can achieve individualized prediction of PFS probability to EGFR-TKI therapy in NSCLCs, which holds promise of improving the pretherapy personalized management of TKIs. Clin Cancer Res; 24(15); 3583-92. ©2018 AACR.

Development and clinical application of radiomics in lung cancer.

Since the discovery of X-rays at the end of the 19th century, medical imageology has progressed for 100 years, and medical imaging has become an important auxiliary tool for clinical diagnosis. With the launch of the human genome project (HGP) and the development of various high-throughput detection techniques, disease exploration in the post-genome era has extended beyond investigations of structural changes to in-depth analyses of molecular abnormalities in tissues, organs and cells, on the basis of gene expression and epigenetics. These techniques have given rise to genomics, proteomics, metabolomics and other systems biology subspecialties, including radiogenomics. Radiogenomics is an important revolution in the traditional visually identifiable imaging technology and constitutes a new branch, radiomics. Radiomics is aimed at extracting quantitative imaging features automatically and developing models to predict lesion phenotypes in a non-invasive manner. Here, we summarize the advent and development of radiomics, the basic process and challenges in clinical practice, with a focus on applications in pulmonary nodule evaluations, including diagnostics, pathological and molecular classifications, treatment response assessments and prognostic predictions, especially in radiotherapy.

Hyperphosphorylation of RPS6KB1, rather than overexpression, predicts worse prognosis in non-small cell lung cancer patients.

RPS6KB1 is the kinase of ribosomal protein S6 which is 70 kDa and is required for protein translation. Although the abnormal activation of RPS6KB1 has been found in types of diseases, its role and clinical significance in non-small cell lung cancer (NSCLC) has not been fully investigated. In this study, we identified that RPS6KB1 was over-phosphorylated (p-RPS6KB1) in NSCLC and it was an independent unfavorable prognostic marker for NSCLC patients. In spite of the frequent expression of total RPS6KB1 and p-RPS6KB1 in NSCLC specimens by immunohistochemical staining (IHC), only p-RPS6KB1 was associated with the clinicopathologic characteristics of NSCLC subjects. Kaplan-Meier survival analysis revealed that the increased expression of p-RPS6KB1 indicated a poorer 5-year overall survival (OS) for NSCLC patients, while the difference between the positive or negative RPS6KB1 group was not significant. Univariate and multivariate Cox regression analysis was then used to confirm the independent prognostic value of p-RPS6KB1. To illustrate the underlying mechanism of RPS6KB1 phosphorylation in NSCLC, LY2584702 was employed to inhibit the RPS6KB1 phosphorylation specifically both in lung adenocarcinoma cell line A549 and squamous cell carcinoma cell line SK-MES-1. As expected, RPS6KB1 dephosphorylation remarkably suppressed cells proliferation in CCK-8 test, and promoted more cells arresting in G0-G1 phase by cell cycle analysis. Moreover, apoptotic A549 cells with RPS6KB1 dephosphorylation increased dramatically, with an elevating trend in SK-MES-1, indicating a potential involvement of RPS6KB1 phosphorylation in inducing apoptosis. In conclusion, our data suggest that RPS6KB1 is over-activated as p-RPS6KB1 in NSCLC, rather than just the total protein overexpressing. The phosphorylation level of RPS6KB1 might be used as a novel prognostic marker for NSCLC patients.