Deep learning based sparse view x-ray CT reconstruction for checked baggage screening

Sagar Mandava, Amit Ashok, Ali Bilgin

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

X-ray computed tomography is widely used in security applications. With growing interest in view-limited systems, which have increased throughput, there is a significant interest in constrained image reconstruction techniques that allows high fidelity reconstruction from limited data. These image reconstruction techniques are commonly characterized by their intense computational requirements making their deployment in real-time imaging applications challenging. Recent success of deep learning techniques in various signal and image processing applications has sparked an interest in using these techniques for image reconstruction problems. In this work, we explore the use of deep learning techniques for reconstruction of baggage CT data and compare these techniques to constrained reconstruction methods.

Original languageEnglish (US)
Title of host publicationAnomaly Detection and Imaging with X-Rays (ADIX) III
PublisherSPIE
Volume10632
ISBN (Electronic)9781510617759
DOIs
StatePublished - Jan 1 2018
EventAnomaly Detection and Imaging with X-Rays (ADIX) III 2018 - Orlando, United States
Duration: Apr 17 2018Apr 18 2018

Other

OtherAnomaly Detection and Imaging with X-Rays (ADIX) III 2018
CountryUnited States
CityOrlando
Period4/17/184/18/18

Fingerprint

baggage
image reconstruction
Image reconstruction
learning
Screening
screening
X rays
Image Reconstruction
x rays
Tomography
image processing
signal processing
Signal processing
Image processing
tomography
Throughput
Imaging techniques
X-ray Tomography
requirements
Computed Tomography

Keywords

  • Compressed sensing
  • Constrained reconstruction
  • CT reconstruction
  • Deep learning
  • Security screening
  • Sparse view
  • Transportation security
  • X-ray computed tomography

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Cite this

Mandava, S., Ashok, A., & Bilgin, A. (2018). Deep learning based sparse view x-ray CT reconstruction for checked baggage screening. In Anomaly Detection and Imaging with X-Rays (ADIX) III (Vol. 10632). [1063204] SPIE. https://doi.org/10.1117/12.2309509

Deep learning based sparse view x-ray CT reconstruction for checked baggage screening. / Mandava, Sagar; Ashok, Amit; Bilgin, Ali.

Anomaly Detection and Imaging with X-Rays (ADIX) III. Vol. 10632 SPIE, 2018. 1063204.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Mandava, S, Ashok, A & Bilgin, A 2018, Deep learning based sparse view x-ray CT reconstruction for checked baggage screening. in Anomaly Detection and Imaging with X-Rays (ADIX) III. vol. 10632, 1063204, SPIE, Anomaly Detection and Imaging with X-Rays (ADIX) III 2018, Orlando, United States, 4/17/18. https://doi.org/10.1117/12.2309509
Mandava S, Ashok A, Bilgin A. Deep learning based sparse view x-ray CT reconstruction for checked baggage screening. In Anomaly Detection and Imaging with X-Rays (ADIX) III. Vol. 10632. SPIE. 2018. 1063204 https://doi.org/10.1117/12.2309509
Mandava, Sagar ; Ashok, Amit ; Bilgin, Ali. / Deep learning based sparse view x-ray CT reconstruction for checked baggage screening. Anomaly Detection and Imaging with X-Rays (ADIX) III. Vol. 10632 SPIE, 2018.
@inproceedings{a33ce90e20724c88a7b5a016c676780c,
title = "Deep learning based sparse view x-ray CT reconstruction for checked baggage screening",
abstract = "X-ray computed tomography is widely used in security applications. With growing interest in view-limited systems, which have increased throughput, there is a significant interest in constrained image reconstruction techniques that allows high fidelity reconstruction from limited data. These image reconstruction techniques are commonly characterized by their intense computational requirements making their deployment in real-time imaging applications challenging. Recent success of deep learning techniques in various signal and image processing applications has sparked an interest in using these techniques for image reconstruction problems. In this work, we explore the use of deep learning techniques for reconstruction of baggage CT data and compare these techniques to constrained reconstruction methods.",
keywords = "Compressed sensing, Constrained reconstruction, CT reconstruction, Deep learning, Security screening, Sparse view, Transportation security, X-ray computed tomography",
author = "Sagar Mandava and Amit Ashok and Ali Bilgin",
year = "2018",
month = "1",
day = "1",
doi = "10.1117/12.2309509",
language = "English (US)",
volume = "10632",
booktitle = "Anomaly Detection and Imaging with X-Rays (ADIX) III",
publisher = "SPIE",

}

TY - GEN

T1 - Deep learning based sparse view x-ray CT reconstruction for checked baggage screening

AU - Mandava, Sagar

AU - Ashok, Amit

AU - Bilgin, Ali

PY - 2018/1/1

Y1 - 2018/1/1

N2 - X-ray computed tomography is widely used in security applications. With growing interest in view-limited systems, which have increased throughput, there is a significant interest in constrained image reconstruction techniques that allows high fidelity reconstruction from limited data. These image reconstruction techniques are commonly characterized by their intense computational requirements making their deployment in real-time imaging applications challenging. Recent success of deep learning techniques in various signal and image processing applications has sparked an interest in using these techniques for image reconstruction problems. In this work, we explore the use of deep learning techniques for reconstruction of baggage CT data and compare these techniques to constrained reconstruction methods.

AB - X-ray computed tomography is widely used in security applications. With growing interest in view-limited systems, which have increased throughput, there is a significant interest in constrained image reconstruction techniques that allows high fidelity reconstruction from limited data. These image reconstruction techniques are commonly characterized by their intense computational requirements making their deployment in real-time imaging applications challenging. Recent success of deep learning techniques in various signal and image processing applications has sparked an interest in using these techniques for image reconstruction problems. In this work, we explore the use of deep learning techniques for reconstruction of baggage CT data and compare these techniques to constrained reconstruction methods.

KW - Compressed sensing

KW - Constrained reconstruction

KW - CT reconstruction

KW - Deep learning

KW - Security screening

KW - Sparse view

KW - Transportation security

KW - X-ray computed tomography

UR - http://www.scopus.com/inward/record.url?scp=85049866264&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85049866264&partnerID=8YFLogxK

U2 - 10.1117/12.2309509

DO - 10.1117/12.2309509

M3 - Conference contribution

AN - SCOPUS:85049866264

VL - 10632

BT - Anomaly Detection and Imaging with X-Rays (ADIX) III

PB - SPIE

ER -