Deep learning for predicting immunotherapeutic efficacy in advanced non-small cell lung cancer patients: a retrospective study combining progression-free survival risk and overall survival risk.

Background: Radiomics based on computed tomography (CT) images is potential in promoting individualized treatment of non-small cell lung cancer (NSCLC), however, its role in immunotherapy needs further exploration. The aim of this study was to develop a CT-based radiomics score to predict the efficacy of immune checkpoint inhibitor (ICI) monotherapy in patients with advanced NSCLC. Methods: Two hundred and thirty-six ICI-treated patients were retrospectively included and divided into a training cohort (n=188) and testing cohort (n=48) at a ratio of 8 to 2. The efficacy outcomes of ICI were evaluated based on overall survival (OS) and progression-free survival (PFS). We designed a survival network and combined it with a Cox regression model to obtain patients' OS risk score (OSRS) and PFS risk score (PFSRS). Results: Based on OSRS and PFSRS, patients were divided into high- and low-risk groups in the training cohort and the test cohort with distinctly different [training cohort, log-rank P<0.001, hazard ratio (HR): 4.14; test cohort, log-rank P=0.014, HR: 4.54] and PFS (training cohort, log-rank P<0.001, HR: 4.52; test cohort, log-rank P<0.001, HR: 6.64). Further joint evaluation of OSRS and PFSRS showed that both were significant in the Cox regression model (P<0.001), and multi-overall survival risk score (MOSRS) displayed more outstanding stratification capabilities than OSRS in both the training (P<0.001) and test cohorts (P=0.002). None of the clinical characteristics were significant in the Cox regression model, and the score that predicted the best immune response was not as good as the risk score from follow-up information in the performance of prognostic stratification. Conclusions: We developed a CT imaging-based score with the potential to become an independent prognostic factor to screen patients who would benefit from ICI treatment, which suggested that CT radiomics could be applied for individualized immunotherapy of NSCLC. Our findings should be further validated by future larger multicenter study.

Radiomics nomogram for prediction disease-free survival and adjuvant chemotherapy benefits in patients with resected stage I lung adenocarcinoma.

BACKGROUND: Robust imaging biomarkers are needed for risk stratification in stage I lung adenocarcinoma patients in order to select optimal treatment regimen. We aimed to construct and validate a radiomics nomogram for predicting the disease-free survival (DFS) of patients with resected stage I lung adenocarcinoma, and further identifying candidates benefit from adjuvant chemotherapy (ACT). METHODS: Using radiomics approach, we analyzed 554 patients' computed tomography (CT) images from three multicenter cohorts. Prognostic radiomics features were extracted from computed tomography (CT) images and selected using least absolute shrinkage and selection operator (LASSO) Cox regression model to build a radiomics signature for DFS stratification. The biological basis of radiomics was explored in the Radiogenomics dataset (n=79) by gene set enrichment analysis (GSEA). Then a nomogram that integrated the signature with these significant clinicopathologic factors in the multivariate analysis were constructed in the training cohort (n=238), and its prognostic accuracy was evaluated in the validation cohort (n=237). Finally, the predictive value of nomogram for ACT benefits was assessed. RESULTS: The radiomics signature with higher score was significantly associated with worse DFS in both the training and validation cohorts (P<0.001). The GSEA presented that the signature was highly correlated to characteristic metabolic process and immune system during cancer progression. Multivariable analysis revealed that age (P=0.031), pathologic TNM stage (P=0.043), histologic subtype (P=0.010) and the signature (P<0.001) were independently associated with patients' DFS. The integrated radiomics nomogram showed good discrimination performance, as well as good calibration and clinical utility, for DFS prediction in the validation cohort. We further found that the patients with high points (point ≥8.788) defined by the radiomics nomogram obtained a significant favorable response to ACT (P=0.04) while patients with low points (point <8.788) showed no survival difference (P=0.7). CONCLUSIONS: The radiomics nomogram could be used for prognostic prediction and ACT benefits identification for patient with resected stage I lung adenocarcinoma.

Fusion of quantitative imaging features and serum biomarkers to improve performance of computer-aided diagnosis scheme for lung cancer: A preliminary study.

OBJECTIVES: To develop and test a new multifeature-based computer-aided diagnosis (CADx) scheme of lung cancer by fusing quantitative imaging (QI) features and serum biomarkers to improve CADx performance in classifying between malignant and benign pulmonary nodules. METHODS: First, a dataset involving 173 patients was retrospectively assembled, which includes computed tomography (CT) images and five serum biomarkers extracted from blood samples. Second, a CADx scheme using a four-step-based semiautomatic segmentation method was applied to segment the targeted lung nodules, and compute 78 QI features from each segmented nodule from CT images. Third, two support vector machine (SVM) classifiers were built using QI features and serum biomarkers, respectively. SVM classifiers were trained and tested using the overall dataset with a Relief feature selection method, a synthetic minority oversampling technique and a leave-one-case-out validation method. Finally, to further improve CADx performance, an information-fusion method was used to combine the prediction scores generated by two SVM classifiers. RESULTS: Areas under receiver operating characteristic curves (AUC) generated by QI feature and serum biomarker-based SVMs were 0.81 ± 0.03 and 0.69 ± 0.05, respectively. Using an optimal weighted fusion method to combine prediction scores generated by two SVMs, AUC value significantly increased to 0.85 ± 0.03 (P < 0.05). CONCLUSIONS: This study demonstrates (a) higher CADx performance by using QI features than using the serum biomarkers and (b) feasibility of further improving CADx performance by fusion of QI features and serum biomarkers, which indicates that QI features and serum biomarkers contain the complementary classification information.

Automatic detection of pulmonary nodules in CT images by incorporating 3D tensor filtering with local image feature analysis.

Computer-aided detection (CAD) technology has been developed and demonstrated its potential to assist radiologists in detecting pulmonary nodules especially at an early stage. In this paper, we present a novel scheme for automatic detection of pulmonary nodules in CT images based on a 3D tensor filtering algorithm and local image feature analysis. We first apply a series of preprocessing steps to segment the lung volume and generate the isotropic volumetric CT data. Next, a unique 3D tensor filtering approach and local image feature analysis are used to detect nodule candidates. A 3D level set segmentation method is used to correct and refine the boundaries of nodule candidates subsequently. Then, we extract the features of the detected candidates and select the optimal features by using a CFS (Correlation Feature Selection) subset evaluator attribute selection method. Finally, a random forest classifier is trained to classify the detected candidates. The performance of this CAD scheme is validated using two datasets namely, the LUNA16 (Lung Nodule Analysis 2016) database and the ANODE09 (Automatic Nodule Detection 2009) database. By applying a 10-fold cross-validation method, the CAD scheme yielded a sensitivity of 79.3% at an average of 4 false positive detections per scan (FP/Scan) for the former dataset, and a sensitivity of 84.62% and 2.8 FP/Scan for the latter dataset, respectively. Our detection results show that the use of 3D tensor filtering algorithm combined with local image feature analysis constitutes an effective approach to detect pulmonary nodules.

Computer-aided diagnosis of lung cancer: the effect of training data sets on classification accuracy of lung nodules.

This study aims to develop a computer-aided diagnosis (CADx) scheme for classification between malignant and benign lung nodules, and also assess whether CADx performance changes in detecting nodules associated with early and advanced stage lung cancer. The study involves 243 biopsy-confirmed pulmonary nodules. Among them, 76 are benign, 81 are stage I and 86 are stage III malignant nodules. The cases are separated into three data sets involving: (1) all nodules, (2) benign and stage I malignant nodules, and (3) benign and stage III malignant nodules. A CADx scheme is applied to segment lung nodules depicted on computed tomography images and we initially computed 66 3D image features. Then, three machine learning models namely, a support vector machine, naïve Bayes classifier and linear discriminant analysis, are separately trained and tested by using three data sets and a leave-one-case-out cross-validation method embedded with a Relief-F feature selection algorithm. When separately using three data sets to train and test three classifiers, the average areas under receiver operating characteristic curves (AUC) are 0.94, 0.90 and 0.99, respectively. When using the classifiers trained using data sets with all nodules, average AUC values are 0.88 and 0.99 for detecting early and advanced stage nodules, respectively. AUC values computed from three classifiers trained using the same data set are consistent without statistically significant difference (p > 0.05). This study demonstrates (1) the feasibility of applying a CADx scheme to accurately distinguish between benign and malignant lung nodules, and (2) a positive trend between CADx performance and cancer progression stage. Thus, in order to increase CADx performance in detecting subtle and early cancer, training data sets should include more diverse early stage cancer cases.

Anti-proliferation and radiosensitization effects of chitooligosaccharides on human lung cancer line HepG2.

OBJECTIVE: To observe the anti-proliferation and radiosensitization effect of chitooligosaccharides (COS) on human lung cancer cell line HepG2. METHODS: CCK-8 assay was employed to obtain the inhibition ratio of COS on HepG2 cells at 24 h after treatment. The clonogenic assay was used to analyze the cell viability of RAY group and RAY + COS group with X-ray of 0, 1, 2, 4, 6 and 8 Gy, and the cell survival curve was used to analyze the sensitization ratio of COS. Flow cytometry was employed to detect cell cycle and apoptosis rate in control group, RAY group and RAY + COS group after 24 h treatment. RESULTS: COS inhibited the proliferation of HepG2 cells, and the inhibition rate positively correlated with the concentration of COS. The cell viability decreased with increasing exposure dose in RAY group and RAY + COS group. The cell viabilities of RAY + COS group were lower than those of RAY group at the dose of 4, 6 and 8 Gy (P < 0.05), and the sensitization ratio of COS was 1.19. There were higher percentage at G2/M phase and apoptosis rate, and lower percentage at S phase in RAY + COS group versus the other two groups (P < 0.01). CONCLUSIONS: COS can inhibit the proliferation of HepG2 cells, and enhance the radiosensitization of HepG2 cells, induce apoptosis and G2/M phase arrest.

An Aberrant Left Bronchial Artery Originating from the Proximal Ascending Aorta.

The origin of the bronchial arteries (BAs) has numerous anatomical variations. It is important to recognize these variations when performing interventional radiologic procedures in the thorax. We report the case of a 71-year-old man who underwent transarterial infusion chemotherapy for squamous cell carcinoma of the upper lobe of the left lung via a feeding left BA that originated from the proximal ascending aorta. After two cycles of transarterial infusion chemotherapy, the tumor significantly decreased in size. To the best of our knowledge, this is the first report of an aberrant BA originating from this site.

Endovascular coil embolization of a costocervical trunk pseudoaneurysm after bullectomy with pleural abrasion.

Transarterial embolization (TAE) is less invasive than surgery for the treatment of pseudoaneurysms. Costocervical trunk (CCT) pseudoaneurysms are extremely rare. We herein report an unusual case of a 45-year-old man with a CCT pseudoaneurysm caused by a bullectomy with pleural abrasion, which had been performed to manage a spontaneous pneumothorax. The patient presented with chronic chest pain and successfully underwent TAE with a metallic coil. The chest pain completely disappeared 2 weeks after the TAE, and follow-up computed tomography showed that the pseudoaneurysm had almost completely disappeared 9 months after the TAE.

Aberrant left inferior bronchial artery originating from the left gastric artery in a patient with acute massive hemoptysis.

Massive hemoptysis is a life-threatening condition, and the major source of bleeding in this condition is the bronchial circulation. Bronchial artery embolization is a safe and effective treatment for controlling hemoptysis. However, the sites of origin of the bronchial arteries (BAs) have numerous anatomical variations, which can result in a technical challenge to identify a bleeding artery. We present a rare case of a left inferior BA that originated from the left gastric artery in a patient with recurrent massive hemoptysis caused by bronchiectasis. The aberrant BA was embolized, and hemoptysis has been controlled for 8 months.

Detection of rib metastases in patients with lung cancer: a comparative study of MRI, CT and bone scintigraphy.

We retrospectively investigated the imaging findings of bone scintigraphy, chest CT and chest MRI in 55 cases of lung cancer. The sensitivity, specificity and accuracy of the detection of rib metastases were compared between imaging modalities on both a per-lesion and a per-patient basis. On a per-lesion basis, MRI sensitivity and accuracy were significantly higher than that of bone scintigraphy and CT (P<0.05). The sensitivities, specificities, and accuracy levels between CT and bone scintigraphy did not differ on either a per-lesion or per-patient basis (P>0.05). MRI appears to be superior for the detection of ribs metastases in lung cancer.

CHFR promoter hypermethylation and reduced CHFR mRNA expression in ovarian cancer.

BACKGROUND: Ovarian cancer is one of the most common cancers and can be treated with microtubule-targeting drugs. Checkpoint with forkhead and ring finger domains (CHFR) is a protein implicated in cancer sensitivity to microtubule-targeting drugs. Whereas CHFR downregulation, often with CHFR promoter hypermethylation, has been identified in a large number of tumor types, it has not been in ovarian cancer. We therefore searched for CHFR downregulation in primary ovarian tumors. METHODS: Fresh ovarian cancer tissues from 53 patients (test) and normal ovarian tissues from 21 patients (control) were tested for CHFR promoter hypermethylation and CHFR mRNA levels. RESULTS: The CHFR promoter was hypermethylated in 20.75% (11/53) of the ovarian cancers and none (0/21) of the normal controls. The normal controls had a mean mRNA level of 1.89 relative fluorescence units (RFU) with a range of 0.04-24.78 RFU. The cancer tissues had a mean mRNA level of 0.77 RFU with a range of 0.00-68.75 RFU. The median value of the cancer group was significantly lower than that of the control group (p=0.0067). Those cancer samples that had hypermethylated CHFR promoters also had low (n=3) or undetectable (n=8) CHFR mRNA levels. CONCLUSIONS: In contrast to previous reports, we found that alterations in CHFR mRNA and CHFR methylation can be frequently found in ovarian cancers. CHFR hypermethylation was strongly associated with the loss of CHFR mRNA expression. CHFR downregulation in ovarian tumors may be clinically relevant as a staging biomarker, as an indicator of sensitivity to microtubule-targeting drugs, and as a future drug target.

[Pulmonary sarcoidosis: CT features and the changes after glucocorticoid therapy].

OBJECTIVE: To investigate the CT features of pulmonary sarcoidosis and to follow the changes after glucocorticoid therapy. METHODS: CT scans and clinical data of 90 patients with histologically confirmed pulmonary sarcoidosis were retrospectively reviewed. CT follow-up was carried out 5-30 d following therapy in 43 cases. The follow-up lasted 3-48 months. RESULTS: The main CT finding of pulmonary sarcoidosis was nodules which were present in 69 cases (77%), mostly distributed around bronchovascular bundles (n = 37, 41%). Other abnormalities included consolidation (n = 31, 34%), ground-grass ( n = 39, 43%), thickening of bronchovascular bundles (n = 30, 33%) interlobular septal lines (n = 58, 64%), fibrosis (n = 17, 19%), air-trapping (n = 3, 3%) bronchial narrowing (n = 8, 9%), pleural thickening (n = 42, 47%), hilar and mediastinal adenopathy (n =76, 84%). Two or more radiological patterns were present in 83 cases. Twenty-five cases of nodules (25/30), 9 cases of consolidation (9/15), 11 cases of ground-grass (11/16), 10 cases of thickening of bronchovascular bundles (10/12) were improved after therapy. Ten cases of interlobular septa (10/22), 1 case of diffuse linear changes (1/3), but no bronchial distortion (0/4) and honeycombing (0/2), were improved. CONCLUSIONS: The CT manifestations of pulmonary sarcoidosis are varied, with some specific radiographic features. The radiological diagnosis and the effect of glucocorticoid therapy can be evaluated by repeated CT scanning. Nodules, consolidation, ground-grass, and thickening of bronchovascular bundles can be improved markedly after glucocorticoid therapy, but bronchial distortion, linear changes and honeycombing can not.

[The interaction between microsomal epoxide hydrolase polymorphisms and indoor pollution in non small cell lung cancer].

OBJECTIVE: To determine the interaction between indoor air pollution and mEH gene polymorphisms. METHODS: Blood samples from 222 non small cell lung cancer patients and 222 healthy people were characterized by PCR and PCR-RFLP methods. The interaction coefficients were determined through unconditional logistic regression model. RESULTS: Significant differences in the positive rate of mEH-exon3 mutant and the heterozygote were found between case and control groups (chi(2) = 7.046, P = 0.030). But no significant difference was found in mEH-exon4 non-wild-type between groups (chi(2) = 2.674, P = 0.263). mEH-exon3 mutant (OR = 1.99; 95% CI = 1.21, 3.25) could significantly increase the risk of lung cancer. After adjusted by confounding variables, significant interactions were found between the use of coal-wall stove and the non-wild type mEH gene. The interaction coefficients were increased with the duration of exposure and quantity of coal consumed. The super multiplication models were established between non-wild type mEH gene and the exposure to soot or oil fume during cooking. The interaction coefficients were 2.75 and 7.34 respectively for exon3 and exon4. No interaction was found between non-wild type mEH gene and irritation of eye or throat during cooking. CONCLUSION: Through the molecular epidemiological techniques, we confirmed indoor air pollution that caused by coal burning was a noticeable lung cancer risk factor. The interaction between the polymorphisms of mEH gene and the indoor air pollution plays an important role in the carcinogenesis of lung.

Downregulation of MDM2 expression by RNAi inhibits LoVo human colorectal adenocarcinoma cells growth and the treatment of LoVo cells with mdm2siRNA3 enhances the sensitivity to cisplatin.

To investigate the biological effect of mdm2 in human colorectal adenocarcinoma LoVo cells, three mdm2siRNA constructions were recombined and transient transfected into human colorectal adenocarcinoma LoVo cells with low differentiation character in vitro. The results showed that mdm2siRNA3 reduced mRNA level of mdm2 and protein level of mdm2, leading to proliferation inhibition on LoVo cells, and reduced tumor growth in nude mice. It was found that depletion of MDM2 in this pattern promoted apoptosis of LoVo cells and Cisplatin (DDP) treated in the mdm2siRNA3 transfected cell population would result in a substantial decrease by MTT colorimetry. Decreasing the MDM2 protein level in LoVo cells by RNAi could significantly inhibit tumor growth both in vitro and in vivo, which indicated that mdm2 gene played a definite role in the development and aggressiveness of human colon carcinoma. It also could be a therapeutic target in colorectal carcinoma. The synergistic activation of RNAi and cell toxicity agents indicated that the combination of chemotherapy and gene therapy will be a promising approach in the future.