A 3D deep convolutional neural network approach for the automated measurement of cerebellum tracer uptake in FDG PET-CT scans.

PURPOSE The purpose of this work was to assess the potential of deep convolutional neural networks in automated measurement of cerebellum tracer uptake in FDG PET scans. METHODS Three different 3D convolutional neural network architectures (U-Net, V-Net, and modified U-Net) were implemented and compared regarding their performance in 3D cerebellum segmentation in FDG PET scans. For network training and testing, 134 PET scans with corresponding manual volumetric segmentations were utilized. For segmentation performance assessment, a five-fold cross-validation was used, and the Dice coefficient as well as signed and unsigned distance errors were calculated. In addition, SUV uptake measurement performance was assessed by means of a statistical comparison to an independent reference standard. Furthermore, a comparison to a previously reported active-shape-model-based approach was performed. RESULTS Out of the three convolutional neural networks investigated, the modified U-Net showed significantly better segmentation performance. It achieved a Dice coefficient of 0.911±0.026, a signed distance error of 0.220±0.103 mm, and an unsigned distance error of 1.048±0.340 mm. When compared to the independent reference standard, SUV uptake measurements produced with the modified U-Net showed no significant error in slope and intercept. The estimated reduction in total SUV measurement error was 95.1%. CONCLUSIONS The presented work demonstrates the potential of deep convolutional neural networks in automated SUV measurement of reference regions. While it focuses on the cerebellum, utilized methods can be generalized to other reference regions like the liver or aortic arch. Future work will focus on combining lesion and reference region analysis into one approach.

[1]  Berkman Sahiner,et al.  Deep learning in medical imaging and radiation therapy. , 2018, Medical physics.

[2]  Bram van Ginneken,et al.  A survey on deep learning in medical image analysis , 2017, Medical Image Anal..

[3]  T. Yamane,et al.  [18F]FMISO PET/CT as a preoperative prognostic factor in patients with pancreatic cancer , 2019, EJNMMI Research.

[4]  S. Jakobsen,et al.  FDG-PET reproducibility in tumor-bearing mice: comparing a traditional SUV approach with a tumor-to-brain tissue ratio approach , 2017, Acta oncologica.

[5]  Trevor Darrell,et al.  Fully Convolutional Networks for Semantic Segmentation , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Yang Lei,et al.  Ultrasound prostate segmentation based on multidirectional deeply supervised V-Net. , 2019, Medical physics.

[7]  D. Rubin,et al.  Inference from Iterative Simulation Using Multiple Sequences , 1992 .

[8]  Milan Sonka,et al.  Automated measurement of uptake in cerebellum, liver, and aortic arch in full-body FDG PET/CT scans. , 2012, Medical physics.

[9]  Nico Karssemeijer,et al.  Using deep learning to segment breast and fibroglandular tissue in MRI volumes , 2017, Medical physics.

[10]  S. Majumdar,et al.  Use of 2D U-Net Convolutional Neural Networks for Automated Cartilage and Meniscus Segmentation of Knee MR Imaging Data to Determine Relaxometry and Morphometry. , 2018, Radiology.

[11]  S. Dizdarevic,et al.  Quantification of tumour 18 F-FDG uptake: Normalise to blood glucose or scale to liver uptake? , 2015, European Radiology.

[12]  C. Rowe,et al.  Optimal Reference Region to Measure Longitudinal Amyloid-β Change with 18F-Florbetaben PET , 2017, The Journal of Nuclear Medicine.

[13]  Ethan J. Ulrich,et al.  FDG PET based prediction of response in head and neck cancer treatment: Assessment of new quantitative imaging features , 2019, PloS one.

[14]  D. Vera,et al.  Comparison of lesion-to-cerebellum uptake ratios and standardized uptake values in the evaluation of lung nodules with 18F-FDG PET , 2007, Nuclear medicine communications.

[15]  Seyed-Ahmad Ahmadi,et al.  V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation , 2016, 2016 Fourth International Conference on 3D Vision (3DV).

[16]  Ronald M. Summers,et al.  Deep Learning in Medical Imaging: Overview and Future Promise of an Exciting New Technique , 2016 .

[17]  Klaus H. Maier-Hein,et al.  Brain Tumor Segmentation and Radiomics Survival Prediction: Contribution to the BRATS 2017 Challenge , 2017, BrainLes@MICCAI.

[18]  Milan Sonka,et al.  3D Slicer as an image computing platform for the Quantitative Imaging Network. , 2012, Magnetic resonance imaging.

[19]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[20]  Thomas Brox,et al.  3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation , 2016, MICCAI.

[21]  Ethan J. Ulrich,et al.  FLT PET Radiomics for Response Prediction to Chemoradiation Therapy in Head and Neck Squamous Cell Cancer , 2019, Tomography.

[22]  Lubomir M. Hadjiiski,et al.  U‐Net based deep learning bladder segmentation in CT urography , 2019, Medical physics.

[23]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.