Purpose Extracting the high-level feature representation by using deep neural networks for detection of prostate cancer, and then based on high-level feature representation constructing hierarchical classification to refine the detection results. Methods High-level feature representation is first learned by a deep learning network, where multi-parametric MR images are used as the input data. Then, based on the learned high-level features, a hierarchical classification method is developed, where multiple random forest classifiers are iteratively constructed to refine the detection results of prostate cancer. Results The experiments were carried on 21 real patient subjects, and the proposed method achieves an averaged section-based evaluation (SBE) of 89.90%, an averaged sensitivity of 91.51%, and an averaged specificity of 88.47%. Conclusions The high-level features learned from our proposed method can achieve better performance than the conventional handcrafted features (e.g., LBP and Haar-like features) in detecting prostate cancer regions, also the context features obtained from the proposed hierarchical classification approach are effective in refining cancer detection result.

With the development of multimedia technology, intelligent monitoring systems, etc. smart classrooms emerged, people want to get involved through multimedia and smart technology, and thus the teachers with intelligent monitoring can get the students' attention time, points of interest , attendance , and exam invigilation and other activities more effectively, through the student movement of the head shoulder trajectory tracking and judgment and improve the efficiency of the teacher's work and strengthen the interaction between teachers and students to improve students' learning efficiency. In this paper, we use the multimedia technology on the student's head and shoulders trajectory tracking and analysis, so as to solve the above problems, mainly divided into three phases: firstly is human face recognition, using Ababoost; secondly is to get the head and shoulders' pose, analysis to determine the effective head and shoulder trajectory; analysis and judgment on the results after using Camshift for tracking. The experimental results show that this method has strong real-time, when the head with a partially occluded or background interference it still can get better target trajectory and movement direction for us to make better judgment and analysis.

Abstract

No abstract