Stella X. Yu : Papers / Google Scholar

Serial Dependence in Perception across Naturalistic Generative Adversarial Network-generated Mammogram
Zhihang Ren and Teresa Canas-Bajo and Cristina Ghirardo and Mauro Manassi and Stella X. Yu and David Whitney
Journal of Medical Imaging, 10(4):, 2023


Purpose: Human perception and decisions are biased toward previously seen stimuli. This phenomenon is known as serial dependence and has been extensively studied for the last decade. Recent evidence suggests that clinicians’ judgments of mammograms might also be impacted by serial dependence. However, the stimuli used in previous psychophysical experiments on this question, consisting of artificial geometric shapes and healthy tissue backgrounds, were unrealistic. We utilized realistic and controlled generative adversarial network (GAN)-generated radio-graphs that were produced by GAN to mimic images that clinicians typically encounter.

Approach: Mammograms from the digital database for screening mammography were utilized to train a GAN. This pretrained GAN was then adopted to generate a large set of authentic-looking simulated mammograms: 20 circular morph continu- ums, each with 147 images, for a total of 2940 images. Using these stimuli in a stan- dard serial dependence experiment, participants viewed a random GAN-generated mammogram on each trial and subsequently matched the GAN-generated mammo- gram encountered using a continuous report. The characteristics of serial depend- ence from each continuum were analyzed.

Results: We found that serial dependence affected the perception of all naturalistic GAN-generated mammogram morph continuums. In all cases, the perceptual judg- ments of GAN-generated mammograms were biased toward previously encoun- tered GAN-generated mammograms. On average, perceptual decisions had 7\% categorization errors that were pulled in the direction of serial dependence.

Conclusions: Serial dependence was found even in the perception of naturalistic GAN-generated mammograms created by a GAN. This supports the idea that serial dependence could, in principle, contribute to decision errors in medical image per- ception tasks.

serial dependence, generative adversarial networks, visual search, radiological screening