Artificial Intelligence in CT Imaging: A Systematic Review of Diagnostic Accuracy, Clinical Decision–Support Impact, and Integration Pathways
Bibliographic record
Abstract
ABSTRACT Artificial intelligence (AI) is rapidly transforming radiology and computed tomography (CT) imaging by enabling automated image analysis, improved diagnostic accuracy, and clinical decision–support. We performed a systematic review of peer‐reviewed studies published between January 1, 2010 and March 31, 2025 to quantify reported gains in diagnostic performance and workflow efficiency, to evaluate clinical decision–support benefits and risks, and to identify integration priorities. We searched PubMed, IEEE Xplore, Scopus, ScienceDirect, and Google Scholar and screened 128 records; 26 studies met the inclusion criteria. Extracted data included study design, AI architecture, sample size, and quantitative performance metrics; study quality was assessed using Newcastle–Ottawa Scales (NOS), Cochrane RoB 2, or AMSTAR 2 as appropriate. Across included studies, AI applications in CT showed consistent improvements in sensitivity, specificity, and time‐to‐diagnosis in specific tasks (notably lung‐nodule detection and intracranial hemorrhage triage), with reported detection‐rate increases up to ∼20% and reduced turnaround times in several real‐world implementations. Barriers include dataset bias, limited external validation, interpretability (“black‐box”) concerns, workflow integration challenges, and evolving regulatory issues. Economic analyses suggest potentially favorable return on investment (ROI) in high‐volume settings but are sensitive to licensing and infrastructure costs. To realize AI's benefits in CT imaging, rigorous multi‐center validation, transparent reporting, human‐centered workflow design, and post‐deployment surveillance are essential.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.027 | 0.131 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.008 | 0.010 |
| Bibliometrics | 0.015 | 0.017 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.004 | 0.003 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".