Collimator detection remains a challenging task in X-ray systems with unreliable or non-available information about the detectors position relative to the source. This paper presents a physically motivated image processing pipeline for simulating the characteristics of collimator shadows in X-ray images. By generating randomized labels for collimator shapes and locations, incorporating scattered radiation simulation, and including Poisson noise, the pipeline enables the expansion of limited datasets for training deep neural networks. We validate the proposed pipeline by a qualitative and quantitative comparison against real collimator shadows. Furthermore, it is demonstrated that utilizing simulated data within our deep learning framework not only serves as a suitable substitute for actual collimators but also enhances the generalization performance when applied to real-world data.

The Israeli medical imaging vendor Nanox says it has a vision for the future of healthcare to address health disparities and lack of access to care. It envisions a new business model and plans to leverage a package of new technologies, including cold-cathode X-ray technology to help reduce costs, coupled with a new and inexpensive imaging system that combines teleradiology with artificial intelligence (AI). The business model is to enable any clinic or hospital in the developing world or rural areas to access its technology and no upfront costs using a pay-per-exam fee. The exams will be read by remote teleradiologists, including subspecialists, and AI will help augment clinical staff and radiologists to offer additional health screenings for all patients scanned. After a few years of talk, the vendor now appears on the edge of making this a reality.

When my son was a toddler, he went to his pediatrician for a routine CAT scan. He'd be awake and finished in a jiffy. He lay there on the clinic table, unresponsive, his vitals slowly falling. The clinic had no ability to diagnose his condition. Five minutes later, he was in the back of an ambulance.

The Food and Drug Administration has cleared a new artificial intelligence-powered X-ray device that maker GE Healthcare says reduces the time to detect a collapsed lung from eight hours to as little as 15 minutes, the company announced Thursday. The device, called the Critical Care Suite, uses AI algorithms to scan X-ray images and detect pneumothorax, a deadly condition more commonly known as a collapsed lung that affects roughly 74,000 Americans each year. "The health-care industry is producing huge amounts of data from images to digital health records," GE Healthcare CEO Kieran Murphy said in an interview with CNBC ahead of the announcement. "We strongly believe that you have to turn that data into information and insight to improve outcomes." GE Healthcare, a dominant player in hospital and lab equipment, said its goal is to integrate AI into every aspect of the health-care system to ultimately "improve patient outcomes, reduce waste and inefficiencies, and eliminate costly errors."