Format

Send to

Choose Destination
J Med Imaging (Bellingham). 2016 Jan;3(1):015501. doi: 10.1117/1.JMI.3.1.015501. Epub 2016 Jan 6.

Computational assessment of visual search strategies in volumetric medical images.

Author information

1
University of Texas at Austin, Department of Electrical and Computer Engineering, 107 West Dean Keeton, Austin, Texas 78712, United States; University of Texas MD Anderson Cancer Center, Department of Diagnostic Radiology, 1515 Holcombe Boulevard, Houston, Texas 77030, United States.
2
Brigham and Women's Hospital , Department of Surgery, 75 Francis Street, Boston, Massachusetts 02115, United States.
3
University of Utah , Department of Psychology, 380 S 150 E Beh S, Salt Lake City, Utah 84112, United States.
4
Brigham and Women's Hospital, Department of Surgery, 75 Francis Street, Boston, Massachusetts 02115, United States; Harvard Medical School, Department of Ophthalmology and Radiology, 64 Sidney Street, Cambridge, Massachusetts 02139, United States.
5
University of Texas MD Anderson Cancer Center , Department of Diagnostic Radiology, 1515 Holcombe Boulevard, Houston, Texas 77030, United States.
6
University of Texas at Austin, Department of Biomedical Engineering, 107 West Dean Keeton, Austin, Texas 78712, United States; University of Texas MD Anderson Cancer Center, Department of Imaging Physics, 1515 Holcombe Boulevard, Houston, Texas 77030, United States.

Abstract

When searching through volumetric images [e.g., computed tomography (CT)], radiologists appear to use two different search strategies: "drilling" (restrict eye movements to a small region of the image while quickly scrolling through slices), or "scanning" (search over large areas at a given depth before moving on to the next slice). To computationally identify the type of image information that is used in these two strategies, 23 naïve observers were instructed with either "drilling" or "scanning" when searching for target T's in 20 volumes of faux lung CTs. We computed saliency maps using both classical two-dimensional (2-D) saliency, and a three-dimensional (3-D) dynamic saliency that captures the characteristics of scrolling through slices. Comparing observers' gaze distributions with the saliency maps showed that search strategy alters the type of saliency that attracts fixations. Drillers' fixations aligned better with dynamic saliency and scanners with 2-D saliency. The computed saliency was greater for detected targets than for missed targets. Similar results were observed in data from 19 radiologists who searched five stacks of clinical chest CTs for lung nodules. Dynamic saliency may be superior to the 2-D saliency for detecting targets embedded in volumetric images, and thus "drilling" may be more efficient than "scanning."

KEYWORDS:

chest computed tomography; diagnostic error; eye tracking; saliency map; visual search

Supplemental Content

Full text links

Icon for PubMed Central
Loading ...
Support Center