This comprehensive, state-of-the-art review focuses on foundational principles, technical implementation, current practice, and potential future clinical applications of photon-counting CT technology.

Using bilateral dissimilarity as a mammography marker of near-term breast cancer risk, AsymMirai, a simplified deep learning bilateral dissimilarity–based model, performed similarly to the state-of... Background Mirai, a state-of-the-art deep learning–based algorithm for predicting short-term breast cancer risk, outperforms standard clinical risk models. However, Mirai is a black box, risking ov...

Accurate segmentations in medical images are the foundations for various clinical applications. Advances in machine learning-based techniques show great potential for automatic image segmentation, but these techniques usually require a huge amount of accurately annotated reference segmentations for training. The guiding hypothesis of this paper was that crowd-algorithm collaboration could evolve as a key technique in large-scale medical data annotation. As an initial step toward this goal, we evaluated the performance of untrained individuals to detect and correct errors made by three-dimensional (3-D) medical segmentation algorithms. To this end, we developed a multistage segmentation pipeline incorporating a hybrid crowd-algorithm 3-D segmentation algorithm integrated into a medical imaging platform. In a pilot study of liver segmentation using a publicly available dataset of computed tomography scans, we show that the crowd is able to detect and refine inaccurate organ contours with a quality similar to that of experts (engineers with domain knowledge, medical students, and radiologists). Although the crowds need significantly more time for the annotation of a slice, the annotation rate is extremely high. This could render crowdsourcing a key tool for cost-effective large-scale medical image annotation.

SUMMARY: CSF-venous fistulas are an increasingly recognized type of CSF leak that can be particularly challenging to detect, even with recently improved imaging techniques. Currently, most institutions use decubitus digital subtraction myelography or dynamic CT myelography to localize CSF-venous fistulas. Photon-counting detector CT is a relatively recent advancement that has many theoretical benefits, including excellent spatial resolution, high temporal resolution, and spectral imaging capabilities. We describe 6 cases of CSF-venous fistulas detected on decubitus photon-counting detector CT myelography. In 5 of these cases, the CSF-venous fistula was previously occult on decubitus digital subtraction myelography or decubitus dynamic CT myelography using an energy-integrating detector system. All 6 cases exemplify the potential benefits of photon-counting detector CT myelography in identifying CSF-venous fistulas. We suggest that further implementation of this imaging technique will likely be valuable to improve the detection of fistulas that might otherwise be missed with currently used techniques.