Science and practice of imaging physics through 50 years of SPIE Medical Imaging conferences

Abstract

Purpose: For 50 years now, SPIE Medical Imaging (MI) conferences have been the premier forum for disseminating and sharing new ideas, technologies, and concepts on the physics of MI.Approach: Our overarching objective is to demonstrate and highlight the major trajectories of imaging physics and how they are informed by the community and science present and presented at SPIE MI conferences from its inception to now.Results: These contributions range from the development of image science, image quality metrology, and image reconstruction to digital x-ray detectors that have revolutionized MI modalities including radiography, mammography, fluoroscopy, tomosynthesis, and computed tomography (CT). Recent advances in detector technology such as photon-counting detectors continue to enable new capabilities in MI. Conclusion:As we celebrate the past 50 years, we are also excited about what the next 50 years of SPIE MI will bring to the physics of MI.

Digital radiography image quality evaluation using various phantoms and software

“…Digital radiography (DR) offers many advantages compared to screen‐film (SF) imaging. Its better dynamic range, higher resolution (in some situations), the automatically adjustment of images to accentuate the anatomical characteristics and facilitate clinical diagnosis, the image storage and image transfer capabilities, the abolishment of chemical developers, and reduction of costs are the main reasons why DR has almost entirely displaced SF imaging in more resourced countries, despite the possible higher costs of the initial investment 1–4 …”

“…Its better dynamic range, higher resolution (in some situations), the automatically adjustment of images to accentuate the anatomical characteristics and facilitate clinical diagnosis, the image storage and image transfer capabilities, the abolishment of chemical developers, and reduction of costs are the main reasons why DR has almost entirely displaced SF imaging in more resourced countries, despite the possible higher costs of the initial investment. [1][2][3][4] DR has introduced some implications on traditional quality control (QC) testing of X-ray modalities, including the evaluation of image quality (IQ). With SF radiography, the IQ of any acquired image could not be improved, as the optical density, contrast, and latitude of any image could not be modified after film development and fixing.…”

On the Analyses of Medical Images Using Traditional Machine Learning Techniques and Convolutional Neural Networks

“…Excellent outcomes can be attained when there are massive data sets accessible. A research scientist from a top breast imaging CAD organization described to a crowded meeting hall at the SPIE Medical Imaging conference in 2016 how just a several times of experimental studies with a basic deep CNN architecture (AlexNet) prepared on the business’s patented technology database produced effectiveness that was better than what decades of designing manual feature structures had produced [ 268 ].…”