Hallucination at low radiation dose: evaluation of two deep-learning reconstruction methods in high-resolution chest CT

Authors:
  • ZZZhongxing Zhou
    Zhongxing Zhou
  • ABAlex Bratt
    Alex Bratt
  • CKChi Wan Koo
    Chi Wan Koo
  • PMPatricia J. Mergo
    Patricia J. Mergo
  • PRPrabhakar Rajiah
    Prabhakar Rajiah
  • CLCatherine Liang
    Catherine Liang
  • SHScott S. Hsieh
    Scott S. Hsieh
  • CMCynthia H. McCollough
    Cynthia H. McCollough
Publisher website
Google Scholar
Abstract
Deep learning reconstruction (DLR) methods can generate false anatomical structures (“hallucinations”) by interpreting noise or artifacts, especially at low radiation doses. This study assessed how dose reduction affects hallucinations in two DLR algorithms (DLR1 and DLR2) for high-resolution chest CT scans, specifically for interstitial lung disease (ILD). Full-dose projection data from a photon-counting detector CT scanner were simulated at 25% and 8% dose levels, with 8% approaching chest X-ray doses. Thirty image series (5 patients × 3 doses × 2 DLRs) were independently assessed by four thoracic radiologists under two references: routine reconstruction with a medium-sharp kernel (Qr56-IR3) and the sharpest quantitative kernel (Qr89-IR4). Images were rated on 5-point Likert scales for hallucination presence. DLR2 showed superior hallucination suppression versus DLR1 at 25% and 8% doses (p < 0.01), with comparable hallucination scores at full dose. Radiation dose reduction induces hallucinations in DLR images, with effects depending on algorithm. DLR2 consistently minimized hallucinations better than DLR1 at reduced doses.

This publication has 6 references indexed in Scilit: