Canonical text (the exact bytes fingerprinted)

TRUVACE RECORD VERSION
record: TRV-2026-0827
version: 1
kind: certified
reason: Certified into the record
timestamp: 2026-08-18T06:06:15.742822Z
status: published
lens: g_space
sector: health
headline: Evaluation of gastric cancer using artificial intelligence iterative reconstruction on abdominal CT: image quality and diagnostic accuracy
dek: To investigate the clinical performance of a novel deep-learning based image reconstruction algorithm, namely artificial intelligence iterative reconstruction (AIIR), for assessing gastric cancer (GC) on CT. We prospectively enrolled 132 GC patients without history of treatment, all of whom subsequently underwent surgical resection or staging laparoscopy. All patients underwent preoperative abdominal contrast-enhanced CT examinations, and images were reconstructed with both hybrid iterative reconstruction (HIR)…
gain_title: Deep-learning based AIIR reconstruction improved CT image quality and diagnostic accuracy for gastric cancer, increasing tumor conspicuity and raising AUC for detecting serosal invasion compared to hybrid iterative reconstruction.
problem_title: (none)
trace_subject: (none)
gain_reading: Deep-learning based AIIR reconstruction improved CT image quality and diagnostic accuracy for gastric cancer, increasing tumor conspicuity and raising AUC for detecting serosal invasion compared to hybrid iterative reconstruction.
gain_evidence: AIIR achieved a significantly higher area under the ROC curve than HIR in detecting gastric serosal invasion [0.89 (95%CI: 0.83-0.94) vs. 0.78 (95%CI: 0.70-0.85), p< 0.001]
problem_reading: (none)
problem_evidence: (none)
quick_read: Researchers prospectively tested a deep-learning based artificial intelligence iterative reconstruction algorithm against conventional hybrid iterative reconstruction in 132 gastric cancer patients undergoing preoperative abdominal CT before surgery or staging laparoscopy. By August 2026, they reported higher Likert scores for tumor margin and enhancement, higher contrast-to-noise ratios in arterial and portal venous phases, and higher AUC for detecting serosal invasion with AIIR.

Better conspicuity and CNR translating to improved detection of serosal invasion matters for preoperative staging and surgical planning in gastric cancer, where invasion status guides treatment decisions. What remains uncertain from this single-cohort report is generalizability beyond 132 patients at the study sites, impact on patient outcomes, and performance at lower radiation doses.
limitation: 
tag: Evidence-backed gain
key_points: Prospective study of 132 untreated gastric cancer patients who underwent preoperative contrast-enhanced abdominal CT and subsequent surgical resection or staging laparoscopy as reference standard. | Images reconstructed with both hybrid iterative reconstruction and deep-learning based artificial intelligence iterative reconstruction were compared on qualitative Likert scores and quantitative contrast-to-noise ratio. | Mean effective dose was 15.3 7 4.5 mSv, with CNR significantly higher on AIIR than HIR in both arterial and portal venous phases.
rundown: 132 patients with untreated gastric cancer underwent preoperative abdominal contrast-enhanced CT, with images reconstructed using both HIR and the novel deep-learning AIIR algorithm for direct comparison.

Qualitative assessment used a 5-point Likert scale for tumor margin and enhancement pattern, quantitative assessment used CNR, and diagnostic performance for serosal invasion was measured by ROC analysis against operative findings.
sources:
- peer_reviewed | Abdominal Radiology | https://doi.org/10.1007/s00261-026-05741-5 | 2026-08-17
prev: 0000000000000000000000000000000000000000000000000000000000000000

sha256

f3e6ac8f84ace87f207051210d97722410c0cebf7b5fe05054fc17f6a7c8ce26

previous

0000000000000000000000000000000000000000000000000000000000000000