RESUMO
Serial Dependence is a ubiquitous visual phenomenon in which sequentially viewed images appear more similar than they actually are, thus facilitating an efficient and stable perceptual experience in human observers. Although serial dependence is adaptive and beneficial in the naturally autocorrelated visual world, a smoothing perceptual experience, it might turn maladaptive in artificial circumstances, such as medical image perception tasks, where visual stimuli are randomly sequenced. Here, we analyzed 758,139 skin cancer diagnostic records from an online app, and we quantified the semantic similarity between sequential dermatology images using a computer vision model as well as human raters. We then tested whether serial dependence in perception occurs in dermatological judgments as a function of image similarity. We found significant serial dependence in perceptual discrimination judgments of lesion malignancy. Moreover, the serial dependence was tuned to the similarity in the images, and it decayed over time. The results indicate that relatively realistic store-and-forward dermatology judgments may be biased by serial dependence. These findings help in understanding one potential source of systematic bias and errors in medical image perception tasks and hint at useful approaches that could alleviate the errors due to serial dependence.
RESUMO
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 radiographs to mimic images that clinicians typically encounter. Approach: Mammograms from the digital database for screening mammography (DDSM) 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 continuums, each with 147 images, for a total of 2940 images. Using these stimuli in a standard serial dependence experiment, participants viewed a random GAN-generated mammogram on each trial and subsequently matched the GAN-generated mammogram encountered using a continuous report. The characteristics of serial dependence 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 judgments of GAN-generated mammograms were biased toward previously encountered 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 perception tasks.
RESUMO
Medical image data is critically important for a range of disciplines, including medical image perception research, clinician training programs, and computer vision algorithms, among many other applications. Authentic medical image data, unfortunately, is relatively scarce for many of these uses. Because of this, researchers often collect their own data in nearby hospitals, which limits the generalizabilty of the data and findings. Moreover, even when larger datasets become available, they are of limited use because of the necessary data processing procedures such as de-identification, labeling, and categorizing, which requires significant time and effort. Thus, in some applications, including behavioral experiments on medical image perception, researchers have used naive artificial medical images (e.g., shapes or textures that are not realistic). These artificial medical images are easy to generate and manipulate, but the lack of authenticity inevitably raises questions about the applicability of the research to clinical practice. Recently, with the great progress in Generative Adversarial Networks (GAN), authentic images can be generated with high quality. In this paper, we propose to use GAN to generate authentic medical images for medical imaging studies. We also adopt a controllable method to manipulate the generated image attributes such that these images can satisfy any arbitrary experimenter goals, tasks, or stimulus settings. We have tested the proposed method on various medical image modalities, including mammogram, MRI, CT, and skin cancer images. The generated authentic medical images verify the success of the proposed method. The model and generated images could be employed in any medical image perception research.
RESUMO
Introduction: Radiologists routinely make life-altering decisions. Optimizing these decisions has been an important goal for many years and has prompted a great deal of research on the basic perceptual mechanisms that underlie radiologists' decisions. Previous studies have found that there are substantial individual differences in radiologists' diagnostic performance (e.g., sensitivity) due to experience, training, or search strategies. In addition to variations in sensitivity, however, another possibility is that radiologists might have perceptual biases-systematic misperceptions of visual stimuli. Although a great deal of research has investigated radiologist sensitivity, very little has explored the presence of perceptual biases or the individual differences in these. Methods: Here, we test whether radiologists' have perceptual biases using controlled artificial and Generative Adversarial Networks-generated realistic medical images. In Experiment 1, observers adjusted the appearance of simulated tumors to match the previously shown targets. In Experiment 2, observers were shown with a mix of real and GAN-generated CT lesion images and they rated the realness of each image. Results: We show that every tested individual radiologist was characterized by unique and systematic perceptual biases; these perceptual biases cannot be simply explained by attentional differences, and they can be observed in different imaging modalities and task settings, suggesting that idiosyncratic biases in medical image perception may widely exist. Discussion: Characterizing and understanding these biases could be important for many practical settings such as training, pairing readers, and career selection for radiologists. These results may have consequential implications for many other fields as well, where individual observers are the linchpins for life-altering perceptual decisions.
RESUMO
Radiologists and pathologists frequently make highly consequential perceptual decisions. For example, visually searching for a tumor and recognizing whether it is malignant can have a life-changing impact on a patient. Unfortunately, all human perceivers-even radiologists-have perceptual biases. Because human perceivers (medical doctors) will, for the foreseeable future, be the final judges of whether a tumor is malignant, understanding and mitigating human perceptual biases is important. While there has been research on perceptual biases in medical image perception tasks, the stimuli used for these studies were highly artificial and often critiqued. Realistic stimuli have not been used because it has not been possible to generate or control them for psychophysical experiments. Here, we propose to use Generative Adversarial Networks (GAN) to create vivid and realistic medical image stimuli that can be used in psychophysical and computer vision studies of medical image perception. Our model can generate tumor-like stimuli with specified shapes and realistic textures in a controlled manner. Various experiments showed the authenticity of our GAN-generated stimuli and the controllability of our model.
RESUMO
In radiological screening, clinicians scan myriads of radiographs with the intent of recognizing and differentiating lesions. Even though they are trained experts, radiologists' human search engines are not perfect: average daily error rates are estimated around 3-5%. A main underlying assumption in radiological screening is that visual search on a current radiograph occurs independently of previously seen radiographs. However, recent studies have shown that human perception is biased by previously seen stimuli; the bias in our visual system to misperceive current stimuli towards previous stimuli is called serial dependence. Here, we tested whether serial dependence impacts radiologists' recognition of simulated lesions embedded in actual radiographs. We found that serial dependence affected radiologists' recognition of simulated lesions; perception on an average trial was pulled 13% toward the 1-back stimulus. Simulated lesions were perceived as biased towards the those seen in the previous 1 or 2 radiographs. Similar results were found when testing lesion recognition in a group of untrained observers. Taken together, these results suggest that perceptual judgements of radiologists are affected by previous visual experience, and thus some of the diagnostic errors exhibited by radiologists may be caused by serial dependence from previously seen radiographs.