Spinal metastases have a high incidence among cancer patients and may later develop to metastatic spinal cord compression (MSCC). Early detection of spinal metastases is critical for optimal treatment. The diagnosis is usually facilitated with computed tomography (CT) scans, which requires considerable efforts from well-trained radiologist. In this paper, we explore automatic spinal metastases classification based on CT images. Considering the unique characteristics of spinal CT images, a novel Deep Dual-view Network is proposed which contains two branches: a X-Y Conv Branch to extract the features for each individual cross-sectional image slice, and a Z Conv Branch to capture z-direction features from neighboring images. The features from the two branches are then fused to generate the final prediction, which imitates the doctor's way of combining cross sections with sagittal or coronal sections. Considering a tumor usually presents in multiple consecutive image slices, a smooth loss is introduced to maintain the label consistency of adjacent images. To validate the proposed approach, we collect a dataset of 316 patients with spinal metastases. Experimental results on this data set have demonstrated the effectiveness and the robustness of the proposed Deep Dual-view network.

Following the advent of the digital multi-media era and the popularity of the internet, high-resolution flat-panel displays (FPDs) are becoming the central feature of many consumer products, from camcorders, mobile/smart phones, to notebook PCs. The FPD industry has been dominated by the liquid crystal displays (LCDs), which are advancing so rapidly that it seems difficult for other technologies to compete in the marketplace, despite all the enthusiasm and innovation emerging from research laboratories in both universities and industry for decades. On the other hand, with the continuous development of related materials and device architectures for efficient and stable organic light emitting diodes (OLEDs), the commercialization of active matrix organic light emitting diode (AMOLED) display products is accelerating [1]. AMOLED displays provide a set of attractive attributes to be used for high-quality video applications, such as excellent contrast ratio, ultra-fast response, vivid visual full-color appearance, and mechanically, a thinner and simpler structure compared to LCDs. AMOLEDs are rapidly expanding their market share for small-sized mobile applications since their mass production launch in 2007, and are also expected to enter the arena of larger-area displays for TVs soon [2].