Literature DB >> 34888191

Deep learning-based bone suppression in chest radiographs using CT-derived features: a feasibility study.

Ge Ren1, Haonan Xiao1, Sai-Kit Lam1, Dongrong Yang1, Tian Li1, Xinzhi Teng1, Jing Qin2, Jing Cai1.   

Abstract

BACKGROUND: Bone suppression of chest X-ray holds the potential to improve the accuracy of target localization in image-guided radiation therapy (IGRT). However, the training dataset for bone suppression is limited because of the scarcity of bone-free radiographs. This study aims to develop a deep learning-based bone suppression method using CT-derived features to reduce the reliance on the bone-free dataset.
METHODS: In this study, 59 high-resolution lung CT scans were processed to generate the lung digital radiographs (DRs), bone DRs, and bone-free DRs, for the training and internal validation of the proposed cascade convolutional neural network (CCNN). A three-stage image processing framework (CT segmentation, DR simulation, and feature expansion) was developed to expand simulated lung DRs with different weightings of bone intensity. The CCNN consists of a bone detection network and a bone suppression network. In external validation, the trained CCNN was evaluated using 30 chest radiographs. The synthesized bone-suppressed radiographs were compared with the bone-suppressed reference in terms of peak signal-to-noise ratio (PSNR), mean absolute error (MAE), structural similarity index measure (SSIM), and Spearman's correlation coefficient. Furthermore, the effectiveness of the proposed feature expansion method and CCNN model were assessed via the ablation experiment and replacement experiment, respectively.
RESULTS: Evaluation on real chest radiographs showed that the bone-suppressed chest radiographs closely matched with the bone-suppressed reference, achieving an accuracy of MAE =0.0087±0.0030, SSIM =0.8458±0.0317, correlation of 0.9554±0.0170, and PNSR of 20.86±1.60. After removing the feature expansion from the CCNN model, the performance decreased in terms of MAE (0.0294±0.0093, -237.9%), SSIM (0.7747±0.0.0416, -8.4%), correlation (0.8772±0.0271, -8.2%), and PSNR (15.53±1.42, -25.5%) metrics.
CONCLUSIONS: We successfully demonstrated a novel deep learning-based bone suppression method using CT-derived features to reduce the reliance on the bone-free dataset. Implementation of the feature expansion procedures resulted in a remarkable reinforcement of the model performance. For the application of target localization in IGRT, the clinical testing of the proposed method in the context of radiation therapy is a necessary procedure to move from theory into practice. 2021 Quantitative Imaging in Medicine and Surgery. All rights reserved.

Entities:  

Keywords:  Bone suppression; cascade neural network; chest X-ray; chest radiograph; deep learning

Year:  2021        PMID: 34888191      PMCID: PMC8611463          DOI: 10.21037/qims-20-1230

Source DB:  PubMed          Journal:  Quant Imaging Med Surg        ISSN: 2223-4306


  24 in total

1.  Image quality assessment: from error visibility to structural similarity.

Authors:  Zhou Wang; Alan Conrad Bovik; Hamid Rahim Sheikh; Eero P Simoncelli
Journal:  IEEE Trans Image Process       Date:  2004-04       Impact factor: 10.856

Review 2.  A review of image-guided radiotherapy.

Authors:  George T Y Chen; Gregory C Sharp; Shinichiro Mori
Journal:  Radiol Phys Technol       Date:  2008-12-16

3.  Image-processing technique for suppressing ribs in chest radiographs by means of massive training artificial neural network (MTANN).

Authors:  Kenji Suzuki; Hiroyuki Abe; Heber MacMahon; Kunio Doi
Journal:  IEEE Trans Med Imaging       Date:  2006-04       Impact factor: 10.048

4.  Filter learning: application to suppression of bony structures from chest radiographs.

Authors:  M Loog; B van Ginneken; A M R Schilham
Journal:  Med Image Anal       Date:  2006-07-21       Impact factor: 8.545

5.  Separation of bones from chest radiographs by means of anatomically specific multiple massive-training ANNs combined with total variation minimization smoothing.

Authors:  Kenji Suzuki
Journal:  IEEE Trans Med Imaging       Date:  2013-10-11       Impact factor: 10.048

6.  Evaluating variability in tumor measurements from same-day repeat CT scans of patients with non-small cell lung cancer.

Authors:  Binsheng Zhao; Leonard P James; Chaya S Moskowitz; Pingzhen Guo; Michelle S Ginsberg; Robert A Lefkowitz; Yilin Qin; Gregory J Riely; Mark G Kris; Lawrence H Schwartz
Journal:  Radiology       Date:  2009-07       Impact factor: 11.105

7.  The contrast-to-noise ratio for image quality evaluation in scanning electron microscopy.

Authors:  F Timischl
Journal:  Scanning       Date:  2014-12-22       Impact factor: 1.932

8.  The Cancer Imaging Archive (TCIA): maintaining and operating a public information repository.

Authors:  Kenneth Clark; Bruce Vendt; Kirk Smith; John Freymann; Justin Kirby; Paul Koppel; Stephen Moore; Stanley Phillips; David Maffitt; Michael Pringle; Lawrence Tarbox; Fred Prior
Journal:  J Digit Imaging       Date:  2013-12       Impact factor: 4.056

9.  Towards clinical implementation of ultrafast combined kV-MV CBCT for IGRT of lung cancer : Evaluation of registration accuracy based on phantom study.

Authors:  Anna Arns; Manuel Blessing; Jens Fleckenstein; Dzmitry Stsepankou; Judit Boda-Heggemann; Anna Simeonova-Chergou; Jürgen Hesser; Frank Lohr; Frederik Wenz; Hansjörg Wertz
Journal:  Strahlenther Onkol       Date:  2016-02-10       Impact factor: 3.621

10.  Missed non-small cell lung cancer: radiographic findings of potentially resectable lesions evident only in retrospect.

Authors:  Priya Kumar Shah; John H M Austin; Charles S White; Pavni Patel; Linda B Haramati; Gregory D N Pearson; Maria C Shiau; Yahya M Berkmen
Journal:  Radiology       Date:  2003-01       Impact factor: 11.105

View more
  1 in total

1.  Development and validation of bone-suppressed deep learning classification of COVID-19 presentation in chest radiographs.

Authors:  Ngo Fung Daniel Lam; Hongfei Sun; Liming Song; Dongrong Yang; Shaohua Zhi; Ge Ren; Pak Hei Chou; Shiu Bun Nelson Wan; Man Fung Esther Wong; King Kwong Chan; Hoi Ching Hailey Tsang; Feng-Ming Spring Kong; Yì Xiáng J Wáng; Jing Qin; Lawrence Wing Chi Chan; Michael Ying; Jing Cai
Journal:  Quant Imaging Med Surg       Date:  2022-07
  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.