Next Article in Journal
Influence of Different Arm Positions in the Localizer Radiograph(s) on Patient Dose during Exposure-Controlled CT Examinations of the Neck to Pelvis
Previous Article in Journal
A Novel Iterative MLEM Image Reconstruction Algorithm Based on Beltrami Filter: Application to ECT Images
Article

Evaluating a Machine Learning Tool for the Classification of Pathological Uptake in Whole-Body PSMA-PET-CT Scans

1
Department of Nuclear Medicine, University Hospital Bonn, 53127 Bonn, Germany
2
Department of Computer Science, University of Bonn, 53115 Bonn, Germany
3
Bonn-Aachen International Center for Information Technology (B-IT), 53115 Bonn, Germany
*
Author to whom correspondence should be addressed.
Both authors contributed in equal to the manuscript.
Academic Editor: Benjamin M. Ellingson
Tomography 2021, 7(3), 301-312; https://doi.org/10.3390/tomography7030027
Received: 28 May 2021 / Revised: 10 July 2021 / Accepted: 27 July 2021 / Published: 29 July 2021
(This article belongs to the Special Issue AI Imaging Diagnostic Tools)
The importance of machine learning (ML) in the clinical environment increases constantly. Differentiation of pathological from physiological tracer-uptake in positron emission tomography/computed tomography (PET/CT) images is considered time-consuming and attention intensive, hence crucial for diagnosis and treatment planning. This study aimed at comparing and validating supervised ML algorithms to classify pathological uptake in prostate cancer (PC) patients based on prostate-specific membrane antigen (PSMA)-PET/CT. Retrospective analysis of 68Ga-PSMA-PET/CTs of 72 PC patients resulted in a total of 77 radiomics features from 2452 manually delineated hotspots for training and labeled pathological (1629) or physiological (823) as ground truth (GT). As the held-out test dataset, 331 hotspots (path.:128, phys.: 203) were delineated in 15 other patients. Three ML classifiers were trained and ranked to assess classification performance. As a result, a high overall average performance (area under the curve (AUC) of 0.98) was achieved, especially to detect pathological uptake (0.97 mean sensitivity). However, there is still room for improvement to detect physiological uptake (0.82 mean specificity), especially for glands. The ML algorithm applied to manually delineated lesions predicts hotspot labels with high accuracy on unseen data and may be an important tool to assist in clinical diagnosis. View Full-Text
Keywords: prostate cancer (PC); prostate specific membrane antigen (PSMA); positron emission tomography (PET); computed tomography (CT); radiomics features (RFs); machine learning (ML) prostate cancer (PC); prostate specific membrane antigen (PSMA); positron emission tomography (PET); computed tomography (CT); radiomics features (RFs); machine learning (ML)
Show Figures

Figure 1

MDPI and ACS Style

Erle, A.; Moazemi, S.; Lütje, S.; Essler, M.; Schultz, T.; Bundschuh, R.A. Evaluating a Machine Learning Tool for the Classification of Pathological Uptake in Whole-Body PSMA-PET-CT Scans. Tomography 2021, 7, 301-312. https://doi.org/10.3390/tomography7030027

AMA Style

Erle A, Moazemi S, Lütje S, Essler M, Schultz T, Bundschuh RA. Evaluating a Machine Learning Tool for the Classification of Pathological Uptake in Whole-Body PSMA-PET-CT Scans. Tomography. 2021; 7(3):301-312. https://doi.org/10.3390/tomography7030027

Chicago/Turabian Style

Erle, Annette, Sobhan Moazemi, Susanne Lütje, Markus Essler, Thomas Schultz, and Ralph A. Bundschuh 2021. "Evaluating a Machine Learning Tool for the Classification of Pathological Uptake in Whole-Body PSMA-PET-CT Scans" Tomography 7, no. 3: 301-312. https://doi.org/10.3390/tomography7030027

Find Other Styles

Article Access Map by Country/Region

1
Back to TopTop