This paper presents a comparison study between 10 automatic and six interactive methods for liver segmentation from contrast-enhanced CT images. It is based on results from the "MICCAI 2007 Grand Challenge" workshop, where 16 teams evaluated their algorithms on a common database. A collection of 20 clinical images with reference segmentations was provided to train and tune algorithms in advance. Participants were also allowed to use additional proprietary training data for that purpose. All teams then had to apply their methods to 10 test datasets and submit the obtained results. Employed algorithms include statistical shape models, atlas registration, level-sets, graph-cuts and rule-based systems. All results were compared to reference segmentations five error measures that highlight different aspects of segmentation accuracy. All measures were combined according to a specific scoring system relating the obtained values to human expert variability. In general, interactive methods reached higher average scores than automatic approaches and featured a better consistency of segmentation quality. However, the best automatic methods (mainly based on statistical shape models with some additional free deformation) could compete well on the majority of test images. The study provides an insight in performance of different segmentation approaches under real-world conditions and highlights achievements and limitations of current image analysis techniques.

To assess the use of a synchronized video-based motion tracking device for objective, instant, and automated assessment of laparoscopic skill in the operating room. The assessment of technical skills is fundamental to recognition of proficient surgical practice. It is necessary to demonstrate the validity, reliability, and feasibility of any tool to be applied for objective measurement of performance. Nineteen subjects, divided into 13 experienced (performed >100 laparoscopic cholecystectomies) and 6 inexperienced (performed <10 LCs) surgeons completed LCs on 53 patients who all had a diagnosis of biliary colic. Each procedure was recorded with the ROVIMAS video-based motion tracking device to provide an objective measure of the surgeon's dexterity. Each video was also rated by 2 experienced observers on a previously validated operative assessment scale. There were significant differences for motion tracking parameters between the 2 groups of surgeons for the Calot triangle dissection part of procedure for time taken (P = 0.002), total path length (P = 0.026), and number of movements (P = 0.005). Both motion tracking and video-based assessment displayed intertest reliability, and there were good correlations between the 2 modes of assessment (r = 0.4 to 0.7, P < 0.01). An instant, objective, valid, and reliable mode of assessment of laparoscopic performance in the operating room has been defined. This may serve to reduce the time taken for technical skills assessment, and subsequently lead to accurate and efficient audit and credentialing of surgeons for independent practice.