- 3D volume segmentation is a fundamental process in many scientific and medical applications. Producing accurate segmentations, in an efficient way, is challenging, in part due to low imaging data quality (e.g., noise and low image resolution), and ambiguity in the data that can only be resolved with higher-level knowledge of the structure. Automatic algorithms do exist, but there are many use cases where they fail. The gold standard is still manual segmentation or review. Unfortunately, even for an expert, manual segmentation is laborious, time consuming, and prone to errors. Existing 3D segmentation tools are often designed based on the underlying algorithm, and do not take into account human mental models, their lower-level perception abilities, and higher-level cognitive tasks.
In this research, we analyzed manual segmentation as a human-computer interaction paradigm to gain a better understanding of both low-level (perceptual) actions, and higher-level tasks and decision-making processes. We initially employed formative field studies using our novel hybrid protocol that blends observation, surveys, and eye-tracking. We then developed, and validated, data coding schemes to discern segmenters' low-level actions, higher-level tasks, and overall task structures. Using these methods, we successfully identified different segmentation strategies utilized by the segmenters. In addition, formative study results showed that the ability to understand 2D cross-sections of 3D structures is a necessary skill in 3D volume segmentation that can be improved through practice and training.
We used the results of our formative studies to introduce a domain-agnostic 2D cross-section training strategy for 3D volume segmentation and developed an interactive training tool to help novices correctly identify 2D cross-sections of 3D structures.
To evaluate the effectiveness of our training tool, we designed a novel 2D cross-section test instrument based on various spatial ability factors. We then conducted user studies and used the test instrument to measure participants' performance before and after the training. Study results show that the training tool is effective in improving participants' 2D cross-section understanding skills, which then can be used to perform a more accurate 3D volume segmentation.