No abstract

No abstract

Background: Brain tumours are relatively rare disease but present a large medical challenge as there is currently no method for early detection of the tumour and are typically not diagnosed until patients have progressed to symptomatic stage which significantly decreases chances of survival and also minimises treatment efficacy. However, if brain cancers can be diagnosed at early stages and also if clinicians have the potential to prospectively identify patients likely to respond to specific treatments, then there is a very high potential to increase patients’ treatment efficacy and survival. In recent years, there have been several investigations to identify biomarkers for brain cancer risk assessment, early detection and diagnosis, the likelihood of identifying which group of patients will benefit from a particular treatment and monitoring patient response to treatment. Materials and methods: This paper reports on a review of 21 current clinical and emerging biomarkers used in risk assessment, screening for early detection and diagnosis, and monitoring the response of treatment of brain cancers. Conclusion: Understanding biomarkers, molecular mechanisms and signalling pathways can potentially lead to personalised and targeted treatment via therapeutic targeting of specific genetic aberrant pathways which play key roles in malignant brain tumour formation. The future holds promising for the use of biomarker analysis as a major factor for personalised and targeted brain cancer treatment, since biomarkers have the potential to measure early disease detection and diagnosis, the risk of disease development and progression, improved patient stratification for various treatment paradigms, provide accurate information of patient response to a specific treatment and inform clinicians about the likely outcome of a brain cancer diagnosis independent of the treatment received.

Tracking and identifying players is a fundamental step in computer vision-based ice hockey analytics. The data generated by tracking is used in many other downstream tasks, such as game event detection and game strategy analysis. Player tracking and identification is a challenging problem since the motion of players in hockey is fast-paced and non-linear when compared to pedestrians. There is also significant camera panning and zooming in hockey broadcast video. Identifying players in ice hockey is challenging since the players of the same team look almost identical, with the jersey number the only discriminating factor between players. In this paper, an automated system to track and identify players in broadcast NHL hockey videos is introduced. The system is composed of three components (1) Player tracking, (2) Team identification and (3) Player identification. Due to the absence of publicly available datasets, the datasets used to train the three components are annotated manually. Player tracking is performed with the help of a state of the art tracking algorithm obtaining a Multi-Object Tracking Accuracy (MOTA) score of 94.5%. For team identification, the away-team jerseys are grouped into a single class and hometeam jerseys are grouped in classes according to their jersey color. A convolutional neural network is then trained on the team identification dataset. The team identification network gets an accuracy of 97% on the test set. A novel player identification model is introduced that utilizes a temporal one-dimensional convolutional network to identify players from player bounding box sequences. The player identification model further takes advantage of the available NHL game roster data to obtain a player identification accuracy of 83%.

No abstract