Investigation of viewing procedures for interpretation of breast tomosynthesis image volumes: a detection-task study with eye tracking

Abstract

Objectives: To evaluate the efficiency of different methods of reading breast tomosynthesis (BT) image volumes.

Methods: All viewing procedures consisted of free scroll volume browsing and three were combined with initial cine loops at three different frame rates (9, 14 and 25 fps). The presentation modes consisted of vertically and horizontally orientated BT image volumes. Fifty-five normal BT image volumes in mediolateral oblique view were collected. In these, simulated lesions were inserted, creating four unique image sets, one for each viewing procedure. Four observers interpreted the cases in a free-response task. Time efficiency, visual attention and search were investigated using eye tracking.

Results: Horizontally orientated BT image volumes were read faster than vertically when using free scroll browsing only and when combined with fast cine loop. Cine loops at slow frame rates were ruled out as inefficient.

Conclusions: In general, horizontally oriented BT image volumes were read more efficiently. All viewing procedures except for slow frame rates were promising when assuming equivalent detection performance.

Fig. 1

Reconstructed slices of simulated lesions presented within the circle: (a) mass and (b) microcalcification cluster

Fig. 2

Eye tracking setup in action

Fig. 3

a The ViewDEX user interface with the task panel on the right hand side. This breast tomosynthesis (BT) case is presented in a vertical position. b A BT volume slice shown in a horizontal position, now with the task panel at the top. Reprinted from Lång K. et al. Proc. SPIE 7966:796606.1-12, 2011

Fig. 4

Schematic illustration of the BT image volumes showing the position of the lesion, the ROI and the c-ROI. Reprinted from Lång K. et al. Proc. SPIE 7966:796602.1-11, 2011

Fig. 5

Results from JAFROC analysis. JAFROC FOM and CI₉₅ for all conditions. The bars are gathered per viewing procedure, including both detection in the initial cine loop (−FS) and combined with free scroll browsing (+FS). The two rightmost bars indicate the free scroll viewing procedures

Fig. 6

The median total analysis time (and quartiles) for all observers and conditions for all case types combined. The leftmost data (in white) is the time spent in the initial cine loop, whereas the rightmost data (in black) is the total analysis time

Fig. 7

Normalised boxplots of the median total dwell time per viewing condition (excluding free scroll browsing) for the ROI (leftmost) and the c-ROI (rightmost)

Fig. 8

Median entry time (and associated quartiles) for all the conditions tested

Fig. 9

Median transition lengths (and associated quartiles) for all conditions (excluding free scroll browsing)