Header

UZH-Logo

Maintenance Infos

Artificial intelligence for detecting small FDG-positive lung nodules in digital PET/CT: impact of image reconstructions on diagnostic performance


Schwyzer, Moritz; Martini, Katharina; Benz, Dominik C; Burger, Irene A; Ferraro, Daniela A; Kudura, Ken; Treyer, Valerie; von Schulthess, Gustav K; Kaufmann, Philipp A; Huellner, Martin W; Messerli, Michael (2020). Artificial intelligence for detecting small FDG-positive lung nodules in digital PET/CT: impact of image reconstructions on diagnostic performance. European Radiology, 30(4):2031-2040.

Abstract

OBJECTIVES

To evaluate the diagnostic performance of a deep learning algorithm for automated detection of small $^{18}$F-FDG-avid pulmonary nodules in PET scans, and to assess whether novel block sequential regularized expectation maximization (BSREM) reconstruction affects detection accuracy as compared to ordered subset expectation maximization (OSEM) reconstruction.

METHODS

Fifty-seven patients with 92 $^{18}$F-FDG-avid pulmonary nodules (all ≤ 2 cm) undergoing PET/CT for oncological (re-)staging were retrospectively included and a total of 8824 PET images of the lungs were extracted using OSEM and BSREM reconstruction. Per-slice and per-nodule sensitivity of a deep learning algorithm was assessed, with an expert readout by a radiologist/nuclear medicine physician serving as standard of reference. Receiver-operator characteristic (ROC) curve of OSEM and BSREM were assessed and the areas under the ROC curve (AUC) were compared. A maximum standardized uptake value (SUV$_{max}$)-based sensitivity analysis and a size-based sensitivity analysis with subgroups defined by nodule size was performed.

RESULTS

The AUC of the deep learning algorithm for nodule detection using OSEM reconstruction was 0.796 (CI 95%; 0.772-0.869), and 0.848 (CI 95%; 0.828-0.869) using BSREM reconstruction. The AUC was significantly higher for BSREM compared to OSEM (p = 0.001). On a per-slice analysis, sensitivity and specificity were 66.7% and 79.0% for OSEM, and 69.2% and 84.5% for BSREM. On a per-nodule analysis, the overall sensitivity of OSEM was 81.5% compared to 87.0% for BSREM.

CONCLUSIONS

Our results suggest that machine learning algorithms may aid detection of small $^{18}$F-FDG-avid pulmonary nodules in clinical PET/CT. AI performed significantly better on images with BSREM than OSEM.

KEY POINTS

• The diagnostic value of deep learning for detecting small lung nodules (≤ 2 cm) in PET images using BSREM and OSEM reconstruction was assessed. • BSREM yields higher SUV $_{max}$of small pulmonary nodules as compared to OSEM reconstruction. • The use of BSREM translates into a higher detectability of small pulmonary nodules in PET images as assessed with artificial intelligence.

Abstract

OBJECTIVES

To evaluate the diagnostic performance of a deep learning algorithm for automated detection of small $^{18}$F-FDG-avid pulmonary nodules in PET scans, and to assess whether novel block sequential regularized expectation maximization (BSREM) reconstruction affects detection accuracy as compared to ordered subset expectation maximization (OSEM) reconstruction.

METHODS

Fifty-seven patients with 92 $^{18}$F-FDG-avid pulmonary nodules (all ≤ 2 cm) undergoing PET/CT for oncological (re-)staging were retrospectively included and a total of 8824 PET images of the lungs were extracted using OSEM and BSREM reconstruction. Per-slice and per-nodule sensitivity of a deep learning algorithm was assessed, with an expert readout by a radiologist/nuclear medicine physician serving as standard of reference. Receiver-operator characteristic (ROC) curve of OSEM and BSREM were assessed and the areas under the ROC curve (AUC) were compared. A maximum standardized uptake value (SUV$_{max}$)-based sensitivity analysis and a size-based sensitivity analysis with subgroups defined by nodule size was performed.

RESULTS

The AUC of the deep learning algorithm for nodule detection using OSEM reconstruction was 0.796 (CI 95%; 0.772-0.869), and 0.848 (CI 95%; 0.828-0.869) using BSREM reconstruction. The AUC was significantly higher for BSREM compared to OSEM (p = 0.001). On a per-slice analysis, sensitivity and specificity were 66.7% and 79.0% for OSEM, and 69.2% and 84.5% for BSREM. On a per-nodule analysis, the overall sensitivity of OSEM was 81.5% compared to 87.0% for BSREM.

CONCLUSIONS

Our results suggest that machine learning algorithms may aid detection of small $^{18}$F-FDG-avid pulmonary nodules in clinical PET/CT. AI performed significantly better on images with BSREM than OSEM.

KEY POINTS

• The diagnostic value of deep learning for detecting small lung nodules (≤ 2 cm) in PET images using BSREM and OSEM reconstruction was assessed. • BSREM yields higher SUV $_{max}$of small pulmonary nodules as compared to OSEM reconstruction. • The use of BSREM translates into a higher detectability of small pulmonary nodules in PET images as assessed with artificial intelligence.

Statistics

Citations

Dimensions.ai Metrics
1 citation in Web of Science®
3 citations in Scopus®
Google Scholar™

Altmetrics

Additional indexing

Item Type:Journal Article, refereed, original work
Communities & Collections:04 Faculty of Medicine > University Hospital Zurich > Clinic for Diagnostic and Interventional Radiology
04 Faculty of Medicine > University Hospital Zurich > Clinic for Nuclear Medicine
Dewey Decimal Classification:610 Medicine & health
Scopus Subject Areas:Health Sciences > Radiology, Nuclear Medicine and Imaging
Language:English
Date:1 April 2020
Deposited On:17 Jan 2020 12:40
Last Modified:29 Jul 2020 12:44
Publisher:Springer
ISSN:0938-7994
OA Status:Closed
Publisher DOI:https://doi.org/10.1007/s00330-019-06498-w
PubMed ID:31822970

Download

Full text not available from this repository.
View at publisher

Get full-text in a library