No abstract

Accurate lung nodule segmentation from computed tomography (CT) images is of great importance for image-driven lung cancer analysis. However, the heterogeneity of lung nodules and the presence of similar visual characteristics between nodules and their surroundings make it difficult for robust nodule segmentation. In this study, we propose a data-driven model, termed the Central Focused Convolutional Neural Networks (CF-CNN), to segment lung nodules from heterogeneous CT images. Our approach combines two key insights: 1) the proposed model captures a diverse set of nodule-sensitive features from both 3-D and 2-D CT images simultaneously; 2) when classifying an image voxel, the effects of its neighbor voxels can vary according to their spatial locations. We describe this phenomenon by proposing a novel central pooling layer retaining much information on voxel patch center, followed by a multi-scale patch learning strategy. Moreover, we design a weighted sampling to facilitate the model training, where training samples are selected according to their degree of segmentation difficulty. The proposed method has been extensively evaluated on the public LIDC dataset including 893 nodules and an independent dataset with 74 nodules from Guangdong General Hospital (GDGH). We showed that CF-CNN achieved superior segmentation performance with average dice scores of 82.15% and 80.02% for the two datasets respectively. Moreover, we compared our results with the inter-radiologists consistency on LIDC dataset, showing a difference in average dice score of only 1.98%.

• Machine learning can be used for auxiliary distinguish in lung cancer. • Radiomic signature can discriminate lung ADC from SCC. • Radiomics can help to achieve precision medical treatment.

• Key features were extracted from CT images of the primary colorectal tumour. • The proposed radiomics signature was significantly associated with KRAS/NRAS/BRAF mutations. • In the primary cohort, the proposed radiomics signature predicted mutations. • Clinical background, tumour staging, and histological differentiation were unable to predict mutations.

BackgroundCalcium phosphate cement (CPC) can be molded or injected to form a scaffold in situ, which intimately conforms to complex bone defects. Bioactive glass (BG) is known for its unique ability to bond to living bone and promote bone growth. However, it was not until recently that literature was available regarding CPC-BG applied as an injectable graft. In this paper, we reported a novel injectable CPC-BG composite with improved properties caused by the incorporation of BG into CPC.Materials and MethodsThe novel injectable bioactive cement was evaluated to determine its composition, microstructure, setting time, injectability, compressive strength and behavior in a simulated body fluid (SBF). The in vitro cellular responses of osteoblasts and in vivo tissue responses after the implantation of CPC-BG in femoral condyle defects of rabbits were also investigated.ResultsCPC-BG possessed a retarded setting time and markedly better injectability and mechanical properties than CPC. Moreover, a new Ca-deficient apatite layer was deposited on the composite surface after immersing immersion in SBF for 7 days. CPC-BG samples showed significantly improved degradability and bioactivity compared to CPC in simulated body fluid (SBF). In addition, the degrees of cell attachment, proliferation and differentiation on CPC-BG were higher than those on CPC. Macroscopic evaluation, histological evaluation, and micro-computed tomography (micro-CT) analysis showed that CPC-BG enhanced the efficiency of new bone formation in comparison with CPC.ConclusionsA novel CPC-BG composite has been synthesized with improved properties exhibiting promising prospects for bone regeneration.

3 Technical Efficacy: Stage 2 J. MAGN. RESON. IMAGING 2018.

PurposeTo investigate the association between imaging features and low-grade gliomas (LGG) related epilepsy, and to propose a radiomics-based model for the prediction of LGG-associated epilepsy.MethodsThis retrospective study consecutively enrolled 286 patients with LGGs (194 in the primary cohort and 92 in the validation cohort). T2-weighted MR images (T2WI) were used to characterize risk factors for LGG-related epilepsy: Tumor location features and 3-D imaging features were determined, following which the interactions between these two kinds of features were analyzed. Elastic net was applied to generate a radiomics signature combining key imaging features associated with the LGG-related epilepsy with the primary cohort, and then a nomogram incorporating radiomics signature and clinical characteristics was developed. The radiomics signature and nomogram were validated in the validation cohort.ResultsA total of 475 features associated with LGG-related epilepsy were obtained for each patient. A radiomics signature with eleven selected features allowed for discriminating patients with epilepsy or not was detected, which performed better than location and 3-D imaging features. The nomogram incorporating radiomics signature and clinical characteristics achieved a high degree of discrimination with area under receiver operating characteristic (ROC) curve (AUC) at 0.8769 in the primary cohort and 0.8152 in the validation cohort. The nomogram also allowed for good calibration in the primary cohort.ConclusionWe developed and validated an effective prediction model for LGG-related epilepsy. Our results suggested that radiomics analysis may enable more precise and individualized prediction of LGG-related epilepsy.

No abstract