Lung Cancer Segmentation With Transfer Learning: Usefulness of a Pretrained Model Constructed From an Artificial Dataset Generated Using a Generative Adversarial Network

Purpose: The purpose of this study was to develop and evaluate lung cancer segmentation with a pretrained model and transfer learning. The pretrained model was constructed from an artificial dataset generated using a generative adversarial network (GAN). Materials and Methods: Three public datasets containing images of lung nodules/lung cancers were used: LUNA16 dataset, Decathlon lung dataset, and NSCLC radiogenomics. The LUNA16 dataset was used to generate an artificial dataset for lung cancer segmentation with the help of the GAN and 3D graph cut. Pretrained models were then constructed from the artificial dataset. Subsequently, the main segmentation model was constructed from the pretrained models and the Decathlon lung dataset. Finally, the NSCLC radiogenomics dataset was used to evaluate the main segmentation model. The Dice similarity coefficient (DSC) was used as a metric to evaluate the segmentation performance. Results: The mean DSC for the NSCLC radiogenomics dataset improved overall when using the pretrained models. At maximum, the mean DSC was 0.09 higher with the pretrained model than that without it. Conclusion: The proposed method comprising an artificial dataset and a pretrained model can improve lung cancer segmentation as confirmed in terms of the DSC metric. Moreover, the construction of the artificial dataset for the segmentation using the GAN and 3D graph cut was found to be feasible.

[1]  Mizuho Nishio,et al.  Automatic classification between COVID-19 pneumonia, non-COVID-19 pneumonia, and the healthy on chest X-ray image: combination of data augmentation methods , 2020, Scientific Reports.

[2]  Olivier Gevaert,et al.  Non-small cell lung cancer: identifying prognostic imaging biomarkers by leveraging public gene expression microarray data--methods and preliminary results. , 2012, Radiology.

[3]  Ronald M. Summers,et al.  Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning , 2016, IEEE Transactions on Medical Imaging.

[4]  Hao Chen,et al.  Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images: The LUNA16 challenge , 2016, Medical Image Anal..

[5]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[6]  Hans Meine,et al.  Automatic liver tumor segmentation in CT with fully convolutional neural networks and object-based postprocessing , 2018, Scientific Reports.

[7]  Hongyi Zhang,et al.  mixup: Beyond Empirical Risk Minimization , 2017, ICLR.

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

[9]  Klaus H. Maier-Hein,et al.  nnU-Net: Self-adapting Framework for U-Net-Based Medical Image Segmentation , 2018, Bildverarbeitung für die Medizin.

[10]  M. Kris,et al.  Comparison of CT volumetric measurement with RECIST response in patients with lung cancer. , 2016, European journal of radiology.

[11]  Hoo-Chang Hoo-Chang Shin Shin,et al.  Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning , 2016, Ieee Transactions on Medical Imaging.

[12]  Bin Yang,et al.  MedGAN: Medical Image Translation using GANs , 2018, Comput. Medical Imaging Graph..

[13]  Georg Langs,et al.  Automatic lung segmentation in routine imaging is primarily a data diversity problem, not a methodology problem , 2020, European Radiology Experimental.

[14]  Chisako Muramatsu,et al.  Improving breast mass classification by shared data with domain transformation using a generative adversarial network , 2020, Comput. Biol. Medicine.

[15]  Stephen M. Moore,et al.  The Cancer Imaging Archive (TCIA): Maintaining and Operating a Public Information Repository , 2013, Journal of Digital Imaging.

[16]  Mizuho Nishio,et al.  Automatic segmentation of the uterus on MRI using a convolutional neural network , 2019, Comput. Biol. Medicine.

[17]  Harald Kittler,et al.  Domain-specific classification-pretrained fully convolutional network encoders for skin lesion segmentation , 2019, Comput. Biol. Medicine.

[18]  Ronald Boellaard,et al.  PET segmentation of bulky tumors: Strategies and workflows to improve inter-observer variability , 2020, PloS one.

[19]  Mizuho Nishio,et al.  Attribute-guided image generation of three-dimensional computed tomography images of lung nodules using a generative adversarial network , 2020, Comput. Biol. Medicine.

[20]  Wei Zeng,et al.  Deep Learning with Lung Segmentation and Bone Shadow Exclusion Techniques for Chest X-Ray Analysis of Lung Cancer , 2017, ArXiv.

[21]  Paul Babyn,et al.  Generative Adversarial Network in Medical Imaging: A Review , 2018, Medical Image Anal..

[22]  Boqiang Liu,et al.  HSN: Hybrid Segmentation Network for Small Cell Lung Cancer Segmentation , 2019, IEEE Access.

[23]  M. Zelezný,et al.  IMAGE SEGMENTATION IN MEDICAL IMAGING VIA GRAPH-CUTS , 2014 .

[24]  Mizuho Nishio,et al.  Bone segmentation on whole-body CT using convolutional neural network with novel data augmentation techniques , 2020, Comput. Biol. Medicine.

[25]  Hiroshi Fujita,et al.  Automated Pulmonary Nodule Classification in Computed Tomography Images Using a Deep Convolutional Neural Network Trained by Generative Adversarial Networks , 2019, BioMed research international.

[26]  Changhee Han,et al.  Synthesizing Diverse Lung Nodules Wherever Massively: 3D Multi-Conditional GAN-Based CT Image Augmentation for Object Detection , 2019, 2019 International Conference on 3D Vision (3DV).

[27]  Youbao Tang,et al.  CT-Realistic Lung Nodule Simulation from 3D Conditional Generative Adversarial Networks for Robust Lung Segmentation , 2018, MICCAI.

[28]  Olivier Gevaert,et al.  A radiogenomic dataset of non-small cell lung cancer , 2018, Scientific Data.

[29]  Erlend Hodneland,et al.  Automated segmentation of endometrial cancer on MR images using deep learning , 2021, Scientific Reports.

[30]  Tian Liu,et al.  Automatic multiorgan segmentation in thorax CT images using U-net-GAN. , 2019, Medical physics.

[31]  Jie Yang,et al.  Class-Aware Adversarial Lung Nodule Synthesis In CT Images , 2019, 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019).

[32]  Seong Joon Oh,et al.  CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[33]  Ronald M. Summers,et al.  DeepOrgan: Multi-level Deep Convolutional Networks for Automated Pancreas Segmentation , 2015, MICCAI.

[34]  Andrew J Buckler,et al.  Measurement of tumor volumes improves RECIST-based response assessments in advanced lung cancer. , 2012, Translational oncology.

[35]  Kazuyoshi Imaizumi,et al.  Multiplanar analysis for pulmonary nodule classification in CT images using deep convolutional neural network and generative adversarial networks , 2019, International Journal of Computer Assisted Radiology and Surgery.

[36]  F. Yang,et al.  Impact of contouring variability on oncological PET radiomics features in the lung , 2020, Scientific Reports.

[37]  Vicky Goh,et al.  The effects of segmentation algorithms on the measurement of 18F-FDG PET texture parameters in non-small cell lung cancer , 2017, EJNMMI Research.