Your browser doesn't support javascript.
loading
Deep Learning-Based Denoising Enables High-Quality, Fully Diagnostic Neuroradiological Trauma CT at 25% Radiation Dose.
Gohla, Georg; Estler, Arne; Zerweck, Leonie; Knoppik, Jessica; Ruff, Christer; Werner, Sebastian; Nikolaou, Konstantin; Ernemann, Ulrike; Afat, Saif; Brendlin, Andreas.
Afiliación
  • Gohla G; Department of Diagnostic and Interventional Neuroradiology, Eberhard Karls-University Tuebingen, D-72076 Tuebingen, Germany (G.G., A.E., L.Z., J.K., C.R., U.E.). Electronic address: georg.gohla@med.uni-tuebingen.de.
  • Estler A; Department of Diagnostic and Interventional Neuroradiology, Eberhard Karls-University Tuebingen, D-72076 Tuebingen, Germany (G.G., A.E., L.Z., J.K., C.R., U.E.).
  • Zerweck L; Department of Diagnostic and Interventional Neuroradiology, Eberhard Karls-University Tuebingen, D-72076 Tuebingen, Germany (G.G., A.E., L.Z., J.K., C.R., U.E.).
  • Knoppik J; Department of Diagnostic and Interventional Neuroradiology, Eberhard Karls-University Tuebingen, D-72076 Tuebingen, Germany (G.G., A.E., L.Z., J.K., C.R., U.E.).
  • Ruff C; Department of Diagnostic and Interventional Neuroradiology, Eberhard Karls-University Tuebingen, D-72076 Tuebingen, Germany (G.G., A.E., L.Z., J.K., C.R., U.E.).
  • Werner S; Department of Diagnostic and Interventional Radiology, Eberhard Karls-University Tuebingen, D-72076 Tuebingen, Germany (S.W., K.N., S.A., A.B.).
  • Nikolaou K; Department of Diagnostic and Interventional Radiology, Eberhard Karls-University Tuebingen, D-72076 Tuebingen, Germany (S.W., K.N., S.A., A.B.).
  • Ernemann U; Department of Diagnostic and Interventional Neuroradiology, Eberhard Karls-University Tuebingen, D-72076 Tuebingen, Germany (G.G., A.E., L.Z., J.K., C.R., U.E.).
  • Afat S; Department of Diagnostic and Interventional Radiology, Eberhard Karls-University Tuebingen, D-72076 Tuebingen, Germany (S.W., K.N., S.A., A.B.).
  • Brendlin A; Department of Diagnostic and Interventional Radiology, Eberhard Karls-University Tuebingen, D-72076 Tuebingen, Germany (S.W., K.N., S.A., A.B.).
Acad Radiol ; 2024 Sep 17.
Article en En | MEDLINE | ID: mdl-39294053
ABSTRACT
RATIONALE AND

OBJECTIVES:

Traumatic neuroradiological emergencies necessitate rapid and accurate diagnosis, often relying on computed tomography (CT). However, the associated ionizing radiation poses long-term risks. Modern artificial intelligence reconstruction algorithms have shown promise in reducing radiation dose while maintaining image quality. Therefore, we aimed to evaluate the dose reduction capabilities of a deep learning-based denoising (DLD) algorithm in traumatic neuroradiological emergency CT scans. MATERIALS AND

METHODS:

This retrospective single-center study included 100 patients with neuroradiological trauma CT scans. Full-dose (100%) and low-dose (25%) simulated scans were processed using iterative reconstruction (IR2) and DLD. Subjective and objective image quality assessments were performed by four neuroradiologists alongside clinical endpoint analysis. Bayesian sensitivity and specificity were computed with 95% credible intervals.

RESULTS:

Subjective analysis showed superior scores for 100% DLD compared to 100% IR2 and 25% IR2 (p < 0.001). No significant differences were observed between 25% DLD and 100% IR2. Objective analysis revealed no significant CT value differences but higher noise at 25% dose for DLD and IR2 compared to 100% (p < 0.001). DLD exhibited lower noise than IR2 at both dose levels (p < 0.001). Clinical endpoint analysis indicated equivalence to 100% IR2 in fracture detection for all datasets, with sensitivity losses in hemorrhage detection at 25% IR2. DLD (25% and 100%) maintained comparable sensitivity to 100% IR2. All comparisons demonstrated robust specificity.

CONCLUSIONS:

The evaluated algorithm enables high-quality, fully diagnostic CT scans at 25% of the initial radiation dose and improves patient care by reducing unnecessary radiation exposure.
Palabras clave
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Idioma: En Revista: Acad Radiol Asunto de la revista: RADIOLOGIA Año: 2024 Tipo del documento: Article Pais de publicación: Estados Unidos
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Idioma: En Revista: Acad Radiol Asunto de la revista: RADIOLOGIA Año: 2024 Tipo del documento: Article Pais de publicación: Estados Unidos