Tomographic Sparse View Selection Using the View Covariance Loss

Jingsong Lin; Amirkoushyar Ziabari; Singanallur V. Venkatakrishnan; Obaidullah Rahman; Gregery T. Buzzard; Charles A. Bouman

doi:10.1109/TPAMI.2025.3600072

Tomographic Sparse View Selection Using the View Covariance Loss

Jingsong Lin
, Amirkoushyar Ziabari
, Singanallur V. Venkatakrishnan
, Obaidullah Rahman
, Gregery T. Buzzard
, Charles A. Bouman

Multimodal Sensor Analytics

Research output: Contribution to journal › Article › peer-review

Abstract

Standard computed tomography (CT) reconstruction algorithms such as filtered back projection (FBP) and Feldkamp-Davis-Kress (FDK) require many views for producing high-quality reconstructions, which can slow image acquisition and increase cost in non-destructive evaluation (NDE) applications. Over the past 20 years, a variety of methods have been developed for computing high-quality CT reconstructions from sparse views. However, the problem of how to select the best views for CT reconstruction remains open. In this paper, we present a novel view covariance loss (VCL) function that measures the joint information of a set of views by approximating the normalized mean squared error (NMSE) of the reconstruction. We present fast algorithms for computing the VCL along with an algorithm for selecting a subset of views that approximately minimizes its value. Our experiments on simulated and measured data indicate that for a fixed number of views our proposed view covariance loss selection (VCLS) algorithm results in reconstructions with lower NRMSE, fewer artifacts, and greater accuracy than current alternative approaches.

Original language	English
Journal	IEEE Transactions on Pattern Analysis and Machine Intelligence
DOIs	https://doi.org/10.1109/TPAMI.2025.3600072
State	Accepted/In press - 2025

Funding

This work was co-authored by UT-Battelle, LLC under contract DE-AC05-00OR22725 with the US Department of Energy (DOE) and supported by the DOE Office of Energy Efficiency and Renewable Energy (EERE), Advanced Materials & Manufacturing Technologies Office (AMMTO). The US government retains and the publisher, by accepting the article for publication, acknowledges that the US government retains a nonexclusive, paid-up, irrevocable, world-wide license to publish or reproduce the published form of this manuscript, or allow others to do so, for US government purposes. DOE will provide public access to these results of federally sponsored research in accordance with the DOE Public Access Plan (http://energy.gov/downloads/doe-public-access-plan) C. Bouman was partially supported by the Showalter Trust.

Keywords

MBIR
sparse -view CT
tomography
view selection

Access to Document

10.1109/TPAMI.2025.3600072

Cite this

@article{d9f890d462e34609983bbd65bbba9fc7,

title = "Tomographic Sparse View Selection Using the View Covariance Loss",

abstract = "Standard computed tomography (CT) reconstruction algorithms such as filtered back projection (FBP) and Feldkamp-Davis-Kress (FDK) require many views for producing high-quality reconstructions, which can slow image acquisition and increase cost in non-destructive evaluation (NDE) applications. Over the past 20 years, a variety of methods have been developed for computing high-quality CT reconstructions from sparse views. However, the problem of how to select the best views for CT reconstruction remains open. In this paper, we present a novel view covariance loss (VCL) function that measures the joint information of a set of views by approximating the normalized mean squared error (NMSE) of the reconstruction. We present fast algorithms for computing the VCL along with an algorithm for selecting a subset of views that approximately minimizes its value. Our experiments on simulated and measured data indicate that for a fixed number of views our proposed view covariance loss selection (VCLS) algorithm results in reconstructions with lower NRMSE, fewer artifacts, and greater accuracy than current alternative approaches.",

keywords = "MBIR, sparse -view CT, tomography, view selection",

author = "Jingsong Lin and Amirkoushyar Ziabari and Venkatakrishnan, \{Singanallur V.\} and Obaidullah Rahman and Buzzard, \{Gregery T.\} and Bouman, \{Charles A.\}",

note = "Publisher Copyright: {\textcopyright} IEEE. 1979-2012 IEEE.",

year = "2025",

doi = "10.1109/TPAMI.2025.3600072",

language = "English",

journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",

issn = "0162-8828",

publisher = "Institute of Electrical and Electronics Engineers",

}

TY - JOUR

T1 - Tomographic Sparse View Selection Using the View Covariance Loss

AU - Lin, Jingsong

AU - Ziabari, Amirkoushyar

AU - Venkatakrishnan, Singanallur V.

AU - Rahman, Obaidullah

AU - Buzzard, Gregery T.

AU - Bouman, Charles A.

PY - 2025

Y1 - 2025

N2 - Standard computed tomography (CT) reconstruction algorithms such as filtered back projection (FBP) and Feldkamp-Davis-Kress (FDK) require many views for producing high-quality reconstructions, which can slow image acquisition and increase cost in non-destructive evaluation (NDE) applications. Over the past 20 years, a variety of methods have been developed for computing high-quality CT reconstructions from sparse views. However, the problem of how to select the best views for CT reconstruction remains open. In this paper, we present a novel view covariance loss (VCL) function that measures the joint information of a set of views by approximating the normalized mean squared error (NMSE) of the reconstruction. We present fast algorithms for computing the VCL along with an algorithm for selecting a subset of views that approximately minimizes its value. Our experiments on simulated and measured data indicate that for a fixed number of views our proposed view covariance loss selection (VCLS) algorithm results in reconstructions with lower NRMSE, fewer artifacts, and greater accuracy than current alternative approaches.

AB - Standard computed tomography (CT) reconstruction algorithms such as filtered back projection (FBP) and Feldkamp-Davis-Kress (FDK) require many views for producing high-quality reconstructions, which can slow image acquisition and increase cost in non-destructive evaluation (NDE) applications. Over the past 20 years, a variety of methods have been developed for computing high-quality CT reconstructions from sparse views. However, the problem of how to select the best views for CT reconstruction remains open. In this paper, we present a novel view covariance loss (VCL) function that measures the joint information of a set of views by approximating the normalized mean squared error (NMSE) of the reconstruction. We present fast algorithms for computing the VCL along with an algorithm for selecting a subset of views that approximately minimizes its value. Our experiments on simulated and measured data indicate that for a fixed number of views our proposed view covariance loss selection (VCLS) algorithm results in reconstructions with lower NRMSE, fewer artifacts, and greater accuracy than current alternative approaches.

KW - MBIR

KW - sparse -view CT

KW - tomography

KW - view selection

UR - https://www.scopus.com/pages/publications/105013642667

U2 - 10.1109/TPAMI.2025.3600072

DO - 10.1109/TPAMI.2025.3600072

M3 - Article

AN - SCOPUS:105013642667

SN - 0162-8828

JO - IEEE Transactions on Pattern Analysis and Machine Intelligence

JF - IEEE Transactions on Pattern Analysis and Machine Intelligence

ER -

Tomographic Sparse View Selection Using the View Covariance Loss

Abstract

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this