Body / AbdominalAI / InformaticsResearch

Deep learning reconstruction boosts liver and kidney lesion conspicuity on abdominal CT in large patients

Radiology AI literature (PubMed)1w ago

In patients with large body habitus (mean 117 kg), DLIR-H improved hypodense liver and kidney lesion conspicuity vs ASIR-V (renal score 4.25 vs 3.75, p<0.05) and CNR (liver 8.62 vs 4.98), in a single-center retrospective study.

  • Single-center retrospective multi-reader study in 46 patients (mean weight 117 kg) with 86 hypodense lesions.
  • DLIR-M and DLIR-H increased CNR significantly (liver: 6.30 and 8.62 vs 4.98 for ASIR-V, p<0.001; renal: 13.62 and 17.79 vs 11.71, p<0.001).
  • Limitation: retrospective single-center design; results may not generalize to other vendors or patient populations.
Read the source

RadPigeon summaries are original and for information only. They are not clinical advice.