Pulmonary cancer is considered as one of the major causes of death worldwide. For the detection of lung cancer, computer-assisted diagnosis (CADx) systems have been designed. Internet-of-Things (IoT) has enabled ubiquitous internet access to biomedical datasets and techniques; in result, the progress in CADx is significant. Unlike the conventional CADx, deep learning techniques have the basic advantage of an automatic exploitation feature as they have the ability to learn mid and high level image representations. We proposed a Computer-Assisted Decision Support System in Pulmonary Cancer by using the novel deep learning based model and metastasis information obtained from MBAN (Medical Body Area Network). The proposed model, DFCNet, is based on the deep fully convolutional neural network (FCNN) which is used for classification of each detected pulmonary nodule into four lung cancer stages. The performance of proposed work is evaluated on different datasets with varying scan conditions. Comparison of proposed classifier is done with the existing CNN techniques. Overall accuracy of CNN and DFCNet was 77.6% and 84.58%, respectively. Experimental results illustrate the effectiveness of proposed method for the detection and classification of lung cancer nodules. These results demonstrate the potential for the proposed technique in helping the radiologists in improving nodule detection accuracy with efficiency.

The aim of this study was to explore the relationship between abnormality on susceptibility-weighted imaging (SWI) and newly-developed depression after mild traumatic brain injury. The study registered 200 patients with closed TBI and normal finding at CT and conventional MRI. All patients underwent MRI including conventional MR sequences and SWI. The number and volume of microbleed lesions were semi-automatically outlined and manually counted. All patients were followed up with the Structured Clinical Interview for DSM-IV Axis I Disorders (SCID-IV) within 1 year after TBI. The difference in microbleed lesions on SWI was compared between the depressive and non-depressive groups. The depressive group had a higher rate of abnormality on SWI than did the non-depressive group (p < 0.001). Among patients that had exhibited microbleed lesions, the number and volume of lesions were greater in the depressive group than the non-depressive group (both p < 0.001). These differences in numbers and volume of lesions were found only at the frontal, parietal and temporal lobes (all p < 0.001). Among patients that had exhibited microbleed lesions, the number and volume of lesions in other areas were not significantly different between the depressive and non-depressive groups (all p > 0.05). In conclusion, SWI was useful to identify the microbleed lesions after mild TBI. The distribution range and location of microbleed lesions were correlated with depression after TBI.

To understand the dynamics of brain edema in different areas after traumatic brain injury (TBI) in rabbit, we used dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) and diffusion-weighted imaging (DWI) to monitor blood-brain barrier (BBB) permeability and cytotoxic brain edema after weight drop-induced TBI in rabbit. The dynamics of BBB permeability and brain edema were quantified using K(trans) and apparent diffusion coefficient (ADC) in the focal and perifocal lesion areas, as well as the area contralateral to the lesion. In the focal lesion area, K(trans) began to increase at 3 h post-TBI, peaked at 3 days, and decreased gradually while remaining higher than sham injury animals at 7 and 30 days. ADC was more variable, increased slightly at 3 h, decreased to its lowest value at 7 days, then increased to a peak at 30 days. In the perifocal lesion area, K(trans) began to increase at 1 day, peaked at 3-7 days, and returned to control level by 30 days. ADC showed a trend to increase at 1 day, followed by a continuous increase thereafter. In the contralateral area, no changes in K(trans) and ADC were observed at any time-point. These data demonstrate that different types of brain edema predominate in the focal and perifocal lesion areas. Specifically cytotoxic edema was predominant in the focal lesion area while vasogenic edema predominated in the perifocal area in acute phase. Furthermore, secondary opening of the BBB after TBI may appear if secondary injury is not controlled. BBB damage may be a driving force for cytotoxic brain edema and could be a new target for TBI intervention.