Impact of retraining a deep learning algorithm for improving guideline-compliant aortic diameter measurements on non-gated chest CT.

Journal: European journal of radiology
Published Date: Nov 1, 2023

Abstract

PURPOSE/OBJECTIVE: Reliable detection of thoracic aortic dilatation (TAD) is mandatory in clinical routine. For ECG-gated CT angiography, automated deep learning (DL) algorithms are established for diameter measurements according to current guidelines. For non-ECG gated CT (contrast enhanced (CE) and non-CE), however, only a few reports are available. In these reports, classification as TAD is frequently unreliable with variable result quality depending on anatomic location with the aortic root presenting with the worst results. Therefore, this study aimed to explore the impact of re-training on a previously evaluated DL tool for aortic measurements in a cohort of non-ECG gated exams.

Authors

  • Francesca Lo Piccolo
    Department of Radiology, University Hospital Basel, University of Basel, Petersgraben 4, 4031 Basel, Switzerland. Electronic address: francescalp89@gmail.com.
  • Daniel Hinck
    Department of Radiology, University Hospital Basel, University of Basel, Petersgraben 4, 4031 Basel, Switzerland. Electronic address: daniel.hinck@outlook.com.
  • Martin Segeroth
    Clinic of Radiology and Nuclear Medicine, University Hospital Basel, Petersgraben 4, 4031, Basel, Switzerland.
  • Jonathan Sperl
    Siemens Healthineers, Princeton, NJ, USA.
  • Joshy Cyriac
    Clinic of Radiology and Nuclear Medicine, University Hospital Basel, Petersgraben 4, 4031, Basel, Switzerland.
  • Shan Yang
    Clinic of Radiology and Nuclear Medicine, University Hospital Basel, Petersgraben 4, 4031, Basel, Switzerland.
  • Saikiran Rapaka
    From the Division of Cardiovascular Imaging, Department of Radiology and Radiological Science (C.T., C.N.D.C., S.B., M.R., T.W.M., T.M.D., R.R.B., U.J.S.), and Division of Cardiology, Department of Medicine (R.R.B., D.H.S., U.J.S.), Medical University of South Carolina, Ashley River Tower, 25 Courtenay Dr, Charleston, SC 29425-2260; Department of Computed Tomography-Research & Development, Siemens Healthcare GmbH, Forchheim, Germany (K.L.G., C.C., C.S., M.S.); Department of Corporate Technology, Siemens SRL, Brasov, Romania (L.M.I.); and Department of Medical Imaging Technologies, Siemens Healthcare, Princeton, NJ (S.R., P.S.).
  • Jens Bremerich
    University Hospital Basel, Clinic of Radiology & Nuclear Medicine, University of Basel, Petersgraben 4, 4031 Basel, Switzerland.
  • Alexander W Sauter
    University of Basel, University Hospital Basel, Radiology and Nuclear Medicine Clinic, Basel, Switzerland.
  • Maurice Pradella
    Department of Radiology, University Hospital Basel, University of Basel, Basel, Switzerland.

Keywords

External Resources

Popular Topics
Recent Journals