Pattern classification of interstitial lung diseases from computed tomography images using a ResNet-based network with a split-transform-merge strategy and split attention.

In patients with interstitial lung disease (ILD), accurate pattern assessment from their computed tomography (CT) images could help track lung abnormalities and evaluate treatment efficacy. Based on excellent image classification performance, convolutional neural networks (CNNs) have been massively investigated for classifying and labeling pathological patterns in the CT images of ILD patients. However, previous studies rarely considered the three-dimensional (3D) structure of the pathological patterns of ILD and used two-dimensional network input. In addition, ResNet-based networks such as SE-ResNet and ResNeXt with high classification performance have not been used for pattern classification of ILD. This study proposed a SE-ResNeXt-SA-18 for classifying pathological patterns of ILD. The SE-ResNeXt-SA-18 integrated the multipath design of the ResNeXt and the feature weighting of the squeeze-and-excitation network with split attention. The classification performance of the SE-ResNeXt-SA-18 was compared with the ResNet-18 and SE-ResNeXt-18. The influence of the input patch size on classification performance was also evaluated. Results show that the classification accuracy was increased with the increase of the patch size. With a 32 × 32 × 16 input, the SE-ResNeXt-SA-18 presented the highest performance with average accuracy, sensitivity, and specificity of 0.991, 0.979, and 0.994. High-weight regions in the class activation maps of the SE-ResNeXt-SA-18 also matched the specific pattern features. In comparison, the performance of the SE-ResNeXt-SA-18 is superior to the previously reported CNNs in classifying the ILD patterns. We concluded that the SE-ResNeXt-SA-18 could help track or monitor the progress of ILD through accuracy pattern classification.

Quantitative assessment of pneumothorax by using Shannon entropy of lung ultrasound M-mode image and diaphragmatic excursion based on automated measurement.

Background: Lung ultrasound (LUS) and diaphragm ultrasound (DUS) are the appropriate modalities for conservative observation to those patients who are with stable pneumothorax, as well as for the timely detection of life-threatening pneumothorax at any location, due to they are portable, real-time, relatively cost effective, and most important, without radiation exposure. The absence of lung sliding on LUS M-mode images and the abnormality of diaphragmatic excursion (DE) on DUS M-mode images are the most common and novel diagnostic criteria for pneumothorax, respectively. However, visual inspection of M-mode images remains subjective and quantitative analysis of LUS and DUS M-mode images are required. Methods: Shannon entropy of LUS M-mode image (ShanEnLM) and DE based on the automated measurement (DEAM) are adapted to the objective pneumothorax diagnoses and the severity quantifications in this study. Mild, moderate, and severe pneumothoraces were induced in 24 male New Zealand rabbits through insufflation of room air (5, 10 and 15, and 25 and 40 mL/kg, respectively) into their pleural cavities. In vivo intercostal LUS and subcostal DUS M-mode images were acquired using a point-of-care system for estimating ShanEnLM and DEAM. Results: ShanEnLM and DEAM as functions of air insufflation volumes exhibited U-shaped curves and were exponentially decreasing, respectively. Either ShanEnLM or DEAM had areas under the receiver operating characteristic curves [95% confidence interval (CI)] of 1.0000 (95% CI: 1.0000-1.0000), 0.9833 (95% CI: 0.9214-1.0000), and 0.9407 (95% CI: 0.8511-1.0000) for differentiating between normal and mild pneumothorax, mild and moderate pneumothoraces, and moderate and severe pneumothoraces, respectively. Conclusions: Our findings imply that the combination of ShanEnLM and DEAM give the promising potential for pneumothorax quantitative diagnosis.

Highly Mimetic Ex Vivo Lung-Cancer Spheroid-Based Physiological Model for Clinical Precision Therapeutics.

Lung cancer remains a major health problem despite the considerable research into prevention and treatment methods. Through a deeper understanding of tumors, patient-specific ex vivo spheroid models with high specificity can be used to accurately investigate the cause, metastasis, and treatment strategies for lung cancer. Biofabricate lung tumors are presented, consisting of patient-derived tumor spheroids, endothelial cells, and lung decellularized extracellular matrix, which maintain a radial oxygen gradient, as well as biophysicochemical behaviors of the native tumors for precision medicine. It is also demonstrated that the developed lung-cancer spheroid model reproduces patient responses to chemotherapeutics and targeted therapy in a co-clinical trial, with 85% accuracy, 86.7% sensitivity, and 80% specificity. RNA sequencing analysis validates that the gene expression in the spheroids replicates that in the patient's primary tumor. This model can be used as an ex vivo predictive model for personalized cancer therapy and to improve the quality of clinical care.

Alteration of oncogenic IGF-II gene methylation status associates with hepatocyte malignant transformation.

BACKGROUND: Oncogenic insulin-like growth factor-II (IGF-II) is overexpressed in hepatocellular carcinoma (HCC). The present study aimed to analyze the dynamic alteration of IGF-II CpG site methylation status and its molecular mechanism in HCC progression. METHODS: IGF-II alterations were observed in rat hepatocarcinogenesis models induced by 2-acetylaminofluorene. Liver IGF-II expression was compared by immunohistochemistry or tissue IGF-II specific concentration (nmol/mg protein). Status of human IGF-II promoter 3 (P3) or rat IGF-II P2 CpG site methylation was amplified by methylation-specific polymerase chain reaction (MSP). Serum IGF-II levels were quantitatively detected by an enzyme-linked immunosorbent assay. RESULTS: The levels of hepatic IGF-II expression were significantly elevated in the HCC group (P < 0.001). The unmethylation rate of IGF-II P3 CpG sites was 100% in the HCC-, 52.5% in the paracancerous-, and none (0%) in the distal noncancerous-tissues. Abnormal IGF-II expression was related to differentiation degree, tumor invasion, and positive HBV-DNA (all P < 0.001), with a negative correlation between P3 methylation degree and IGF-II expression. There was a positive correlation between liver IGF-II specific concentration and circulating IGF-II level (r = 0.97, P < 0.001). Significantly negative correlation was found between IGF-II P2 CpG site methylation and circulating IGF-II (rs = -0.89, P < 0.001) or liver IGF-II level (rs = -0.84, P < 0.001). CONCLUSIONS: The increase of serum IGF-II and the alteration of oncogenic gene IGF-II methylation may be biomarkers for HCC diagnosis and DNA methylation may be the therapeutic target of HCC.

[Clinical study of the application of enhanced recovery after surgery in cervical spondylotic myelopathy].

OBJECTIVE: To evaluate the role of enhanced recovery after surgery in treating cervical spondylotic myelopathy. METHODS: The clinical data of 55 patients with cervical spondylotic myelopathy underwent surgical treatment from January 2012 to December 2015 were retrospectively analyzed. There were 30 males and 25 females, age from 36 to 71 years old with an average of (45.2±3.2) years, course of disease was for 1 to 12 months with an average of (4.5±1.8) months. The concept of enhanced recovery after surgery and perioperative management were applied to surgical treatment in 35 patients (study group), and the same period, 20 patients without strategy of enhanced recovery after surgery (control group). Thirty-eight patients were treated by anterior cervical discectomy decompression and fixation(ACDF), 17 patients were treated by posterior single-open door laminoplasty decompression. The activity time out of bed, hospitalization days after surgery were compared between two groups. Japanese Orthopaedic Association (JOA) score and visual analogue score(VAS) before operation, after operation at 1, 7, 30 days and 6, 12 months was respectively used to evaluate the neurological function and pain. RESULTS: All the patients were followed up for 12 to 18 months with an average of (14.3±1.5) months. There was no significant difference in age, gender, surgical methods, preoperative VAS, JOA score between two groups (P>0.05). The activity time out of bed was 3 to 8 h with an average of (5.54±1.54) h, postoperative hospitalization time was 3 to12 d with an average of (5.62±1.59) d in study group, while in control group, the activity time out of bed was 24 to 48 h with an average of (18.80±4.78) h, and postoperative hospitalization time was 7 to 17 d with an average of (9.85±1.94) d; there was significant difference between two groups (P<0.01). There was significant difference in VAS and JOA scores between two groups at 1, 7, 30 d after operation (P<0.01), and there was no significant difference at 6, 12 months after operation(P>0.05). There were no neurologic function deterioration, hematoma, wound infection, internal fixation loosening and other complications in study group during hospitalization and following-up;there were 2 cases of superficial wound infection in the control group, who healed by dressing change for 2 weeks;there was no significant difference between two groups(P>0.05). CONCLUSIONS: The strategy of enhanced recovery after surgery in treating cervical spondylotic myelopathy can promote the early recovery, shorten the length of stay and improve the patient's degree of satisfaction.

Increased cancers among residents living in the neighborhood of a petrochemical complex: A 12-year retrospective cohort study.

This study investigates whether cancers are increased for residents living in the vicinity of a petrochemical complex with coal power plants and refineries. We recruited a residential cohort of 2388 long-term residents aged above 35 years in 2009-2012 who lived within a 40 km radius of the complex. We measured their internal exposure biomarkers of urinary carcinogenic metals and retrospectively compared cancer incidences between those who lived fewer than 10 km from the complex (high exposure, HE) and those who lived more than 10 km from the complex (low exposure, LE). Residents had lived in their respective areas for 12 years, since the complex began operating in mid-1999. This included two periods of operation: 0-9 years and 10-12 years. Crude cumulative incident rates (CIRs) of all cancers were calculated for new cancer cases (ICD-9: 140-165, 170-176, 179-208) recorded in the Taiwan Health Insurance Database over total person-years at risk in each study period. Poisson regression was applied to estimate relative risks for the CIRs of all cancers between HE and LE areas during the 10-12 years since the beginning of the complex's operation, adjusting for age, gender, body mass index, smoking, hepatitis C, and occupational exposure. We found that our study subjects in HE areas had higher urinary carcinogenic metal levels, including As, Cd, Hg, Pb, and V, and higher prevalence rates of hepatitis C than those in LE areas. After the complex had been operating for 10-12 years, SIRs per 1000 person-years for all cancers in HE and LE areas were 4.44 vs. 2.48 for all subjects, 15.2 vs. 4.86 for elder subjects aged above 60 years, and 2.94 vs. 2.71 for female subjects. Correspondingly, the adjusted relative risks of CIRs for all cancers between HE and LE areas were 1.29 (95% CI: 0.99-1.68) for all subjects, 1.52 (1.04-2.22) for elder subjects, 1.41 (1.00-1.97) for female subjects, and 1.91 (1.15-3.19) for female elderly subjects. We conclude that elder and female residents living within 10 km of a petrochemical complex had higher carcinogenic exposure and cancers than those living farther away from the complex after the complex had been operating for 10 years.

Carotid Intima-Media Thickness and Long-Term Exposure to Traffic-Related Air Pollution in Middle-Aged Residents of Taiwan: A Cross-Sectional Study.

BACKGROUND: Associations between long-term exposure to air pollution and carotid intima-media thickness (CIMT) have inconsistent findings. OBJECTIVES: In this study we aimed to evaluate association between 1-year average exposure to traffic-related air pollution and CIMT in middle-aged adults in Asia. METHODS: CIMT was measured in Taipei, Taiwan, between 2009 and 2011 in 689 volunteers 35-65 years of age who were recruited as the control subjects of an acute coronary heart disease cohort study. We applied land-use regression models developed by the European Study of Cohorts for Air Pollution Effects (ESCAPE) to estimate each subject's 1-year average exposure to traffic-related air pollutants with particulate matter diameters ≤ 10 µm (PM10) and ≤ 2.5 µm (PM2.5) and the absorbance levels of PM2.5 (PM2.5abs), nitrogen dioxide (NO2), and nitrogen oxides (NOx) in the urban environment. RESULTS: One-year average air pollution exposures were 44.21 ± 4.19 µg/m3 for PM10, 27.34 ± 5.12 µg/m3 for PM2.5, and (1.97 ± 0.36) × 10-5/m for PM2.5abs. Multivariate regression analyses showed average percentage increases in maximum left CIMT of 4.23% (95% CI: 0.32, 8.13) per 1.0 × 10-5/m increase in PM2.5abs; 3.72% (95% CI: 0.32, 7.11) per 10-µg/m3 increase in PM10; 2.81% (95% CI: 0.32, 5.31) per 20-µg/m3 increase in NO2; and 0.74% (95% CI: 0.08, 1.41) per 10-µg/m3 increase in NOx. The associations were not evident for right CIMT, and PM2.5 mass concentration was not associated with the outcomes. CONCLUSIONS: Long-term exposures to traffic-related air pollution of PM2.5abs, PM10, NO2, and NOx were positively associated with subclinical atherosclerosis in middle-aged adults.

Quantitative analysis of hepatic hypoxia-inducible factor-1alpha and its abnormal gene expression during the formation of hepatocellular carcinoma.

BACKGROUND: Hepatic hypoxia-inducible factor-1 (HIF-1) is activated in the progression of hepatocellular carcinoma (HCC). This study aimed to investigate the dynamic alterations of HIF-1alpha and its gene expression so as to explore the relationship between HIF-1alpha expression and hepatocarcinogenesis at the early stage of HCC. METHODS: A hepatoma model was made with 2-fluorenyl-acetamide (2-FAA) in male Sprague-Dawley rats. Morphological changes of rat hepatocytes were assessed pathologically (HE staining). The dynamic expression of hepatic and circulating HIF-1alpha was quantitatively analyzed by ELISA. The gene fragments of hepatic HIF-1alpha mRNA were amplified by RT-PCR and confirmed by sequencing. The cellular distribution of hepatic HIF-1alpha expression was confirmed by immunohistochemistry. RESULTS: Histological examination confirmed granule-like degeneration to atypical hyperplasia and HCC development in rat hepatocytes and progressive increases in the levels of hepatic and circulating HIF-1alpha and its gene expression during the course. The levels of HIF-1alpha expression in the liver and blood of rats with hepatoma were significantly higher than those in normal rats and those with degeneration. Immunohistochemical analysis confirmed the positive expression and hepatocyte distribution of HIF-1alpha in the development of rat hepatoma. A positive relationship was found between HIF-1alpha expression in the liver and blood (P<0.01). CONCLUSIONS: The above observations support the hypothesis that the overexpression of HIF-1alpha and its gene are closely associated with the malignant transformation of hepatocytes and play an important role at the stage of hepatocarcinogenesis.

[Dynamic expression and quantitative analysis of hepatic nuclear factor-kappa B and its gene during the development of hepatocellular carcinoma].

OBJECTIVE: To investigate the kinetic expression and alteration of nuclear transcription factor-kappa B (NF-kappaB) and its gene in hepatocellular carcinoma (HCC) development. METHODS: A hepatoma model was established with N-(2-fluorenyl) acetamide (2-FAA) using male SD rats. Morphological changes and dynamic alterations of NF-kappaB and NF-kappaB mRNA of the rat livers at different stages of HCC development were observed by pathological examinations. The liver specimens from HCC patients were collected by self-control method. The expression of NF-kappaB was quantitatively analyzed by ELISA. RESULTS: Hepatocytes showed vacuole-like denaturation, atypical hyperplasia, and transformation into highly differentiated cancerous hepatocytes with increasing tendencies of liver NF-kappaB and NF-kappaB mRNA expressions. The NF-kappaB positive material was granule-like and stained brown, with dot-nest-like staining localized in the nuclei and cytoplasm of HCC cells, but only in the cytoplasm of the cells of park cancer tissues. Its expression in HCC cells was stronger than that in their surrounding tissues (chi2 = 13.1, P less than 0.01). No positive relationship was found between NF-kappaB expression and histological grades, the number of tumors, or size of the tumors. CONCLUSION: The expression of NF-kappaB and its gene are associated with the development of HCC. To inhibit the expression may be useful to HCC therapy.