Search

PurposeTo introduce a model for automatic segmentation of thoracic organs at risk (OARs), especially the esophagus, in non-small cell lung cancer radiotherapy, using a novel two-step deep learning network.Materials and methodsA total of 59 lung cancer patients’ CT images were enrolled, of which 39 patients were randomly selected as the training set, 8 patients as the validation set, and 12 patients as the testing set. The automatic segmentations of the six OARs including the esophagus were carried out. In addition, two sets of treatment plans were made on the basis of the manually delineated tumor and OARs (Plan1) as well as the manually delineated tumor and the automatically delineated OARs (Plan2). The Dice similarity coefficient (DSC), 95% Hausdorff distance (HD95), and average surface distance (ASD) of the proposed model were compared with those of U-Net as a benchmark. Next, two groups of plans were also compared according to the dose–volume histogram parameters.ResultsThe DSC, HD95, and ASD of the proposed model were better than those of U-Net, while the two groups of plans were almost the same. The highest mean DSC of the proposed method was 0.94 for the left lung, and the lowest HD95 and ASD were 3.78 and 1.16 mm for the trachea, respectively. Moreover, the DSC reached 0.73 for the esophagus.ConclusionsThe two-step segmentation method can accurately segment the OARs of lung cancer. The mean DSC of the esophagus realized preliminary clinical significance (>0.70). Choosing different deep learning networks based on different characteristics of organs offers a new option for automatic segmentation in radiotherapy.

PurposeTo explore fecal immune-related proteins that can be used for colorectal cancer (CRC) diagnosis.Patients and methodsThree independent cohorts were used in present study. In the discovery cohort, which included 14 CRC patients and 6 healthy controls (HCs), label-free proteomics was applied to identify immune-related proteins in stool that could be used for CRC diagnosis. Exploring potential links between gut microbes and immune-related proteins by 16S rRNA sequencing. The abundance of fecal immune-associated proteins was verified by ELISA in two independent validation cohorts and a biomarker panel was constructed that could be used for CRC diagnosis. The validation cohort I included 192 CRC patients and 151 HCs from 6 different hospitals. The validation cohort II included 141 CRC patients, 82 colorectal adenoma (CRA) patients, and 87 HCs from another hospital. Finally, the expression of biomarkers in cancer tissues was verified by immunohistochemistry (IHC).ResultsIn the discovery study, 436 plausible fecal proteins were identified. And among 67 differential fecal proteins (|log2 fold change| > 1, P< 0.01) that could be used for CRC diagnosis, 16 immune-related proteins with diagnostic value were identified. The 16S rRNA sequencing results showed a positive correlation between immune-related proteins and the abundance of oncogenic bacteria. In the validation cohort I, a biomarker panel consisting of five fecal immune-related proteins (CAT, LTF, MMP9, RBP4, and SERPINA3) was constructed based on the least absolute shrinkage and selection operator (LASSO) and multivariate logistic regression. The biomarker panel was found to be superior to hemoglobin in the diagnosis of CRC in both validation cohort I and validation cohort II. The IHC result showed that protein expression levels of these five immune-related proteins were significantly higher in CRC tissue than in normal colorectal tissue.ConclusionA novel biomarker panel consisting of fecal immune-related proteins can be used for the diagnosis of CRC.

PurposeTo introduce an end-to-end automatic segmentation model for organs at risk (OARs) in thoracic CT images based on modified DenseNet, and reduce the workload of radiation oncologists.Materials and MethodsThe computed tomography (CT) images of 36 lung cancer patients were included in this study, of which 27 patients’ images were randomly selected as the training set, 9 patients’ as the testing set. The validation set was generated by cross validation and 6 patients’ images were randomly selected from the training set during each epoch as the validation set. The autosegmentation task of the left and right lungs, spinal cord, heart, trachea and esophagus was implemented, and the whole training time was approximately 5 hours. Geometric evaluation metrics including the Dice similarity coefficient (DSC), 95% Hausdorff distance (HD95) and average surface distance (ASD), were used to assess the autosegmentation performance of OARs based on the proposed model and were compared with those based on U-Net as benchmarks. Then, two sets of treatment plans were optimized based on the manually contoured targets and OARs (Plan1), as well as the manually contours targets and the automatically contoured OARs (Plan2). Dosimetric parameters, including Dmax, Dmean and Vx, of OARs were obtained and compared.ResultsThe DSC, HD95 and ASD of the proposed model were better than those of U-Net. The differences in the DSC of the spinal cord and esophagus, differences in the HD95 of the spinal cord, heart, trachea and esophagus, as well as differences in the ASD of the spinal cord were statistically significant between the two models (P0.05). Moreover, compared with manual segmentation, autosegmentation significantly reduced the contouring time by nearly 40.7% (P

Southwest China, which is rich in biodiversity and a wide range of ecosystem services (ESs), is a strong support for local human wellbeing. This area is also one of the key components of the ecological security shelter (ESS) for national ecological security and biodiversity conservation. Due to the combination of man-made and natural factors, Southwest China has suffered serious ecological degradation that directly threatens ecological security which refers to the health status of ecosystems and ESs functions. Mapping ESs-based ecological security patterns (ESPs) is essential for designing conservation strategies that suitably combine regional environment conservation with sustainable utilization. We used the InVEST (Integrated Valuation of Ecosystem Services and Tradeoffs Tool) model to identify ecological conservation priority areas which integrated ecological sensitivity (soil erosion sensitivity, rock desertification sensitivity, landslide sensitivity, debris flow sensitivity, and freezing-thawing erosion sensitivity), ecological risk (drought risk, natural disaster risk, and socio-economic risk), and ecological conservation importance (soil conservation, water conservation, and biodiversity conservation importance). In this research, we summarized a new designing framework of ESs-based ESPs. We divided the study area into two zones and four belts including: (A) the alpine steppe and wetland zone, (B) Hengduan Mountain zone, (C) northern shelter belt (Daba-Micang Mountain), (D) central shelter belt (Wumeng-Wuling Mountain), (E) southern shelter belt (southern border of China), and (F) southwestern shelter belt (eastern Himalayas Mountain). Identifying distributions of the ESs-based ESPs has practical significance to improve local human wellbeing and to maintain sustainable development of natural-social ecosystems in Southwest China. Furthermore, ESs-based ESPs are necessary for local administrations to create rationalizing plans on balancing conservation and utilization of natural resources, so that policy-makers can put into place targeted prevention and control measures to limit the development of excessive consumption of natural resources and ecological damages, which is worth promoting.