Zeng, Rongping

Abstract This article provides an overview of deep-learning–based techniques in CT image reconstruction and processing (referred to as “DLR”), covering technical implementations, performance evaluation, radiation dose reduction, and future perspectives. DLR methods can be categorized into projection-space, projection-to-image-space, image-space, and various hybrid techniques, with applications such as noise reduction, artefact correction, and spatial resolution enhancement. Performance evaluations include phantom-based studies, patient image-based studies, and virtual imaging trials. These evaluation studies demonstrated that DLR can effectively reduce image noise while preserving an image texture like in traditional filtered-backprojection (FBP) images, although the extent of radiation dose reduction varies widely depending on the study and the specific diagnostic task. Challenges remain in low-contrast lesion detection and characterization, where dose reduction may still be less than 50% compared to traditional reconstruction methods. Additionally, the potential for DLR methods to generate false structures or “hallucinations,” especially at low radiation doses, emphasizes the need for effective monitoring and mitigation strategies from both technical and clinical perspectives. Quantitative, accurate, and efficient evaluation techniques, such as virtual image trial-based methods, can be explored to help optimize these algorithms for reducing radiation dose and enhancing diagnostic performance.

AbstractMulti‐energy computed tomography (MECT) offers the opportunity for advanced visualization, detection, and quantification of select elements (e.g., iodine) or materials (e.g., fat) beyond the capability of standard single‐energy computed tomography (CT). However, the use of MECT requires careful consideration as substantially different hardware and software approaches have been used by manufacturers, including different sets of user‐selected or hidden parameters that affect the performance and radiation dose of MECT. Another important consideration when designing MECT protocols is appreciation of the specific tasks being performed; for instance, differentiating between two different materials or quantifying a specific element. For a given task, it is imperative to consider both the radiation dose and task‐specific image quality requirements. Development of a quality control (QC) program is essential to ensure the accuracy and reproducibility of these MECT applications. Although standard QC procedures have been well established for conventional single‐energy CT, the substantial differences between single‐energy CT and MECT in terms of system implementations, imaging protocols, and clinical tasks warrant QC tests specific to MECT. This task group was therefore charged with developing a systematic QC program designed to meet the needs of MECT applications. In this report, we review the various MECT approaches that are commercially available, including information about hardware implementation, MECT image types, image reconstruction, and postprocessing techniques that are unique to MECT. We address the requirements for MECT phantoms, review representative commercial MECT phantoms, and offer guidance regarding homemade MECT phantoms. We discuss the development of MECT protocols, which must be designed carefully with proper consideration of MECT technology, imaging task, and radiation dose. We then outline specific recommended QC tests in terms of general image quality, radiation dose, differentiation and quantification tasks, and diagnostic and therapeutic applications.

PurposeThe task‐based assessment of image quality using model observers is increasingly used for the assessment of different imaging modalities. However, the performance computation of model observers needs standardization as well as a well‐established trust in its implementation methodology and uncertainty estimation. The purpose of this work was to determine the degree of equivalence of the channelized Hotelling observer performance and uncertainty estimation using an intercomparison exercise.Materials and MethodsImage samples to estimate model observer performance for detection tasks were generated from two‐dimensional CT image slices of a uniform water phantom. A common set of images was sent to participating laboratories to perform and document the following tasks: (a) estimate the detectability index of a well‐defined CHO and its uncertainty in three conditions involving different sized targets all at the same dose, and (b) apply this CHO to an image set where ground truth was unknown to participants (lower image dose). In addition, and on an optional basis, we asked the participating laboratories to (c) estimate the performance of real human observers from a psychophysical experiment of their choice. Each of the 13 participating laboratories was confidentially assigned a participant number and image sets could be downloaded through a secure server. Results were distributed with each participant recognizable by its number and then each laboratory was able to modify their results with justification as model observer calculation are not yet a routine and potentially error prone.ResultsDetectability index increased with signal size for all participants and was very consistent for 6 mm sized target while showing higher variability for 8 and 10 mm sized target. There was one order of magnitude between the lowest and the largest uncertainty estimation.ConclusionsThis intercomparison helped define the state of the art of model observer performance computation and with thirteen participants, reflects openness and trust within the medical imaging community. The performance of a CHO with explicitly defined channels and a relatively large number of test images was consistently estimated by all participants. In contrast, the paper demonstrates that there is no agreement on estimating the variance of detectability in the training and testing setting.