TY - JOUR
T1 - Sensitivity of an AI method for [18F]FDG PET/CT outcome prediction of diffuse large B-cell lymphoma patients to image reconstruction protocols
AU - Ferrández, Maria C.
AU - Golla, Sandeep S. V.
AU - Eertink, Jakoba J.
AU - de Vries, Bart M.
AU - Wiegers, Sanne E.
AU - Zwezerijnen, Gerben J. C.
AU - Pieplenbosch, Simone
AU - Schilder, Louise
AU - Heymans, Martijn W.
AU - Zijlstra, Josée M.
AU - Boellaard, Ronald
N1 - Funding Information: This work was financially supported by the Hanarth Fonds Fund and the Dutch Cancer Society. The sponsor had no role in gathering, analyzing or interpreting the data. The authors thank all the patients who participated in the trial. Funding Information: This work is financially supported by the Hanarth Fonds Fund and the Dutch Cancer Society (#VU-2018–11648). Publisher Copyright: © 2023, Springer-Verlag GmbH Germany, part of Springer Nature.
PY - 2023
Y1 - 2023
N2 - Background: Convolutional neural networks (CNNs), applied to baseline [18F]-FDG PET/CT maximum intensity projections (MIPs), show potential for treatment outcome prediction in diffuse large B-cell lymphoma (DLBCL). The aim of this study is to investigate the robustness of CNN predictions to different image reconstruction protocols. Baseline [18F]FDG PET/CT scans were collected from 20 DLBCL patients. EARL1, EARL2 and high-resolution (HR) protocols were applied per scan, generating three images with different image qualities. Image-based transformation was applied by blurring EARL2 and HR images to generate EARL1 compliant images using a Gaussian filter of 5 and 7 mm, respectively. MIPs were generated for each of the reconstructions, before and after image transformation. An in-house developed CNN predicted the probability of tumor progression within 2 years for each MIP. The difference in probabilities per patient was then calculated between both EARL2 and HR with respect to EARL1 (delta probabilities or ΔP). We compared these to the probabilities obtained after aligning the data with ComBat using the difference in median and interquartile range (IQR). Results: CNN probabilities were found to be sensitive to different reconstruction protocols (EARL2 ΔP: median = 0.09, interquartile range (IQR) = [0.06, 0.10] and HR ΔP: median = 0.1, IQR = [0.08, 0.16]). Moreover, higher resolution images (EARL2 and HR) led to higher probability values. After image-based and ComBat transformation, an improved agreement of CNN probabilities among reconstructions was found for all patients. This agreement was slightly better after image-based transformation (transformed EARL2 ΔP: median = 0.022, IQR = [0.01, 0.02] and transformed HR ΔP: median = 0.029, IQR = [0.01, 0.03]). Conclusion: Our CNN-based outcome predictions are affected by the applied reconstruction protocols, yet in a predictable manner. Image-based harmonization is a suitable approach to harmonize CNN predictions across image reconstruction protocols.
AB - Background: Convolutional neural networks (CNNs), applied to baseline [18F]-FDG PET/CT maximum intensity projections (MIPs), show potential for treatment outcome prediction in diffuse large B-cell lymphoma (DLBCL). The aim of this study is to investigate the robustness of CNN predictions to different image reconstruction protocols. Baseline [18F]FDG PET/CT scans were collected from 20 DLBCL patients. EARL1, EARL2 and high-resolution (HR) protocols were applied per scan, generating three images with different image qualities. Image-based transformation was applied by blurring EARL2 and HR images to generate EARL1 compliant images using a Gaussian filter of 5 and 7 mm, respectively. MIPs were generated for each of the reconstructions, before and after image transformation. An in-house developed CNN predicted the probability of tumor progression within 2 years for each MIP. The difference in probabilities per patient was then calculated between both EARL2 and HR with respect to EARL1 (delta probabilities or ΔP). We compared these to the probabilities obtained after aligning the data with ComBat using the difference in median and interquartile range (IQR). Results: CNN probabilities were found to be sensitive to different reconstruction protocols (EARL2 ΔP: median = 0.09, interquartile range (IQR) = [0.06, 0.10] and HR ΔP: median = 0.1, IQR = [0.08, 0.16]). Moreover, higher resolution images (EARL2 and HR) led to higher probability values. After image-based and ComBat transformation, an improved agreement of CNN probabilities among reconstructions was found for all patients. This agreement was slightly better after image-based transformation (transformed EARL2 ΔP: median = 0.022, IQR = [0.01, 0.02] and transformed HR ΔP: median = 0.029, IQR = [0.01, 0.03]). Conclusion: Our CNN-based outcome predictions are affected by the applied reconstruction protocols, yet in a predictable manner. Image-based harmonization is a suitable approach to harmonize CNN predictions across image reconstruction protocols.
KW - Convolutional neural networks
KW - Diffuse large B-cell lymphoma
KW - PET
KW - Reconstruction
UR - http://www.scopus.com/inward/record.url?scp=85173098301&partnerID=8YFLogxK
U2 - https://doi.org/10.1186/s13550-023-01036-8
DO - https://doi.org/10.1186/s13550-023-01036-8
M3 - Article
C2 - 37758869
SN - 2191-219X
VL - 13
JO - EJNMMI Research
JF - EJNMMI Research
IS - 1
M1 - 88
ER -