Patient-Specific Pose Estimation in Clinical Environments.

Reliable posture labels in hospital environments can augment research studies on neural correlates to natural behaviors and clinical applications that monitor patient activity. However, many existing pose estimation frameworks are not calibrated for these unpredictable settings. In this paper, we propose a semi-automated approach for improving upper-body pose estimation in noisy clinical environments, whereby we adapt and build around an existing joint tracking framework to improve its robustness to environmental uncertainties.

[Surgical treatment result of hilar cholangiocarcinoma: report of 84 patients].

Objective: To analyze the surgical treatment result and clinical characteristics of hilar cholangiocarcinoma in order to improve the rate of early diagnosis and radical resection.

Methods: Between 1986 and 2004,84 hilar cholangiocarcinoma patients underwent surgery, and their data were retrospectively reviewed.

Results: According to the Bismuth-Corlette staging system, 7 were type I, 18 type II, 22 type II a, 12 type IlI b, 20 type IV and 5 unclassified.