Advancing Operational Efficiency in CT with AI

Operational efficiency in CT imaging has become a central concern for health systems navigating technologist shortages, rising patient volumes, and increasing clinical complexity.

In a recent conversation with Applied Radiology, Tonya Altmann, Diagnostic Imaging Manager at Door County Medical Center, and Reza Forghani, MD, Chief Medical Information Officer for Imaging at AdventHealth and a practicing neuroradiologist, discussed how users report that AI-driven tools are helping CT departments address these pressures while maintaining image quality and patient-centered care.

For Tonya Altmann, the challenges begin with staffing. She described staffing as “a huge part of what is holding people back. When you don’t have the staff, it’s harder to train.” CT, she noted, can be an intimidating modality because of its pace and complexity. Departments must balance efficiency with quality, often while onboarding newer technologists into busy, fast-moving environments. Identifying tools that streamline workflow while building confidence has therefore become essential.

Dr Forghani echoed those concerns from a broader health system perspective. Technologist shortages, he said, are not new and have only intensified over time. The impact extends beyond simply filling shifts. In fast-paced CT environments, where throughput expectations are high and patient experience remains a priority, staffing gaps can create downstream effects.

When technologists are rushed or less familiar with complex systems, variability can emerge in positioning, tools to support dose management workflows, and image quality. In some instances, that variability may result in suboptimal studies or even repeat imaging.

AI-enabled workflow tools are increasingly designed to address that variability. Dr Forghani emphasized that while diagnostic AI often receives attention, operational AI may provide some of the most immediate benefits. Automated positioning, tools that support dose management, and intuitive user interfaces can simplify complex systems.

He noted that when technology becomes more intuitive, users report that it may simplify certain tasks  and supports consistency across technologists with varying experience levels.

Altmann described the impact in practical terms. “AI is almost like having another CT tech back there for us,” she said. At her facility, automation supports technologists rather than replaces them. Each exam is still reviewed by a technologist, but tools such as 3D landmarks and automated anatomical detection may support more consistent positioning decisions. She observed that seasoned technologists and those newer to CT are now producing comparable image quality, reinforcing both confidence and training.

Automation has also reduced time spent on manual post-processing. Tasks that previously required technologists to return to the console and manually generate reconstructions are now completed automatically. In some cases, Altmann noted, this can streamline workflow steps before images reach the radiologist. While appointment lengths may remain the same, that regained time allows technologists to focus more directly on patient interaction, improving the overall experience.

From the radiologist’s perspective, reconstruction advancements are equally significant. Dr Forghani pointed to deep learning–based reconstruction as a key contributor to both image quality and operational efficiency. These algorithms. enhance image clarity and, in many cases, support dose optimization. Just as important, automated reconstructions may reduce  time-intensive manual steps that once slowed workflow. In time-sensitive scenarios such as stroke imaging, faster reconstruction  may help turnaround time and downstream clinical management.

Both speakers emphasized that AI should be viewed as a partnership. Dr Forghani noted that computers excel at tasks such as precision positioning and standardized protocol execution, but technologist oversight remains essential. The goal is to support human expertise, not replace it. By reducing repetitive tasks and variability, AI tools allow technologists to focus on clinical judgment and patient care.

Workforce sustainability is another important dimension. Altmann highlighted the role of technology in recruitment and retention. Cross-training technologists across modalities becomes more feasible when systems are consistent and intuitive. Providing tools that help technologists feel confident and successful in their roles contributes to morale and long-term stability within departments.

When discussing return on investment, both leaders emphasized the importance of measurable goals. Dr  Forghani  recommended aligning new technologies with specific performance indicators such as turnaround time, staffing support, and quality consistency. Some returns may be indirect, including improved retention and reduced repeat imaging, while others may be measurable in operational throughput as reported by some sites.

Altmann added that the benefits of improved CT workflow extend beyond radiology. Faster, more consistent imaging supports emergency departments, specialty services, and inpatient care teams by accelerating access to diagnostic information. Ultimately, improved operational efficiency contributes to smoother patient care pathways.

As technologist shortages and volume pressures persist, AI-enabled CT workflows are emerging as practical tools that address real-world challenges. By improving consistency, supporting technologists, and streamlining processes without compromising quality, automation helps departments adapt to evolving operational demands while maintaining their focus on patient care.

References

1. Results and experiences reported in this article reflect the individual experiences of the users; actual results may vary.