Prior studies have shown positive effects of perceptual training (PT), however there is a paucity of literature regarding the long-term retention. The goal of this study is to assess the degree of long term retention three months after an initial PT training session. Eight first year residents underwent perceptual training with repeat training 87 days later. Comparison of their performance showed that though their performance was lower compared to the initial training, this was not statistically significant, suggesting some degree of retention of PT.

Physicians interpreting medical images are expected to adjust display parameters on a routine basis, a skill which is generally not explicitly taught. This study examines the effects of perceptual training (PT) on windowing and leveling images and subject ability to identify pulmonary nodules on chest radiographs. Subjects were also given surveys on the perceived value of the PT. There was a statistically significant improvement in nodule identification for both control and experimental groups. Survey results were significantly positive for all questions. These results suggest there is a role for PT on windowing and leveling medical images.

Over the past three decades, many multiple-detector, tomographic nuclear-medicine imaging systems have been developed and deployed clinically. These systems are always built around a single detector technology that is duplicated and surrounds the patient. The choice of detector technology in nuclear medicine is one of considering the tradeoffs between 2D spatial resolution, energy resolution, stopping power, detector area, count-rate capability, depth-of-interaction resolution, and sensitivity. No single detector type has emerged that achieves high performance in all of these categories. In this paper, we derive observer-performance metrics for imaging systems that utilize combinations of two or more detector technologies and show that it is mathematically possible to achieve improved observer performance when the varying detector technologies used have disparate strengths and weaknesses.

First presentation for workshop on three-dimensional tracking of eye movements was recorded at SPIE Medical Imaging held in San Diego, California, United States 2022.

Eye tracking and volumetric cases was recorded at SPIE Medical Imaging held in San Diego, California, United States 2022.

Texture features have been explored and studied over the last decades providing technical insights that have helped improve a wide variety of fields involving medical and other types of imaging. However there remains a need to examine estimation details, and robustness as significant and new information could be uncovered. Understanding the interactions of imaging system variation and object features in texture formation can provide a corner stone in the advancement of new image processing techniques and acquisition technologies. In this work, we evaluate these questions for digital breast tomosynthesis (DBT) a partial angle tomographic breast imaging system. Recently, our group showed for the first time a correlation between second order texture features and human observer detection performance in digital images. We also showed that second order texture features commonly used as “radiomic” metrics can change with multiple acquisition and reconstruction methods. Here we focus on issues related to robustness in estimating these features. Specifically, we aim to understand how Haralick’s GLCM texture features, used in radiomic models as predictors, change under different estimation conditions in simulated DBT images. We attempt to understand and analyze the effects that different breast densities, pixel distance offsets, ROI window sizes and filtering have on GLCM texture features calculations.