Towards visual-search model observers for mass detection in breast tomosynthesis

Abstract

We are investigating human-observer models that perform clinically realistic detection and localization tasks as a means of making reliable assessments of digital breast tomosynthesis images. The channelized non-prewhitening (CNPW) observer uses the background known exactly task for localization and detection. Visual-search observer models attempt to replicate the search patterns of trained radiologists. The visual-search observer described in this paper utilizes a two-phase approach, with an initial holistic search followed by directed analysis and decision making. Gradient template matching is used for the holistic search, and the CNPW observer is used for analysis and decision making. Spherical masses were embedded into anthropomorphic breast phantoms, and simulated projections were made using ray-tracing and a serial cascade model. A localization ROC study was performed on these images using the visual-search model observer and the CNPW observer. Observer performance from the two computer observers was compared to human observer performance. The visual-search observer was able to produce area under the LROC curve values similar to those from human observers; however, more research is needed to increase the robustness of the algorithm.

Efficient visual-search model observers for PET

“…The basic blob search treated in this article offers a canonical process that imposes no additional training requirements yet is applicable for a variety of imaging applications (e.g. Das and Gifford 29 and Lau et al 30 ). However, the non-specificity of the search is a limitation-a more-selective search process driven by both target and background features might improve concordance between the VS and human observers while overcoming the need for reference images.…”

Visual‐search observers for assessing tomographic x‐ray image quality

“…A number of nonsearch studies with the CH observer have analyzed how DBT image quality depends on the angular range (or acquisition arc) of the x-ray source and the number of projections, [16][17][18] but a definitive approach to using model observers for this problem has proved elusive. Lau et al 19 presented our initial results comparing the lesiondetection performance of human observers with that of the scanning CNPW and CNPW-based VS observers as a function of projection number for a fixed acquisition arc. Herein, we investigate alternatives to the quasi-BKE task for VS observers.…”

Design of a model observer to evaluate calcification detectability in breast tomosynthesis and application to smoothing prior optimization

“…This observer was shown to predict human observer performance when combined with a separate holistic search step 15 . In cases where the background structure and noise are stationary, it is possible to use frequency domain observers instead of the CHO and CNPW which are applied in the image domain.…”

“…14 and Lau et al 15 which they used to examine the effect of the number of projection views on detectability. This observer was shown to predict human observer performance when combined with a separate holistic search step 15 .…”

“…Das et al used the same visual search CNPW as Lau et al 15 and applied it to compare the detectability of microcalcifications in FBP and penalized ML reconstructions 20 and to evaluate the effect of the cutoff frequency of a Butterworth filter in FBP reconstruction 21 . Hu and Zhao 22 applied a frequency domain prewithening observer to demonstrate the effects of angular dose distribution on the detection of microcalcifications, and Sidky et al 23 used the same type of model observer and task to optimize a total variation smoothing prior.…”