Semi-automated location identification of catheters in digital chest radiographs

Brad M. Keller; Anthony P. Reeves; Matthew D. Cham; Claudia I. Henschke; David F. Yankelevitz

doi:10.1117/12.707769

Semi-automated location identification of catheters in digital chest radiographs

Brad M. Keller, Anthony P. Reeves, Matthew D. Cham, Claudia I. Henschke, David F. Yankelevitz

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

16 Scopus citations

Abstract

Localization of catheter tips is the most common task in intensive care unit imaging. In this work, catheters appearing in digital chest radiographs acquired by portable chest x-rays were tracked using a semi-automatic method. Due to the fact that catheters are synthetic objects, its profile does not vary drastically over its length. Therefore, we use forward looking registration with normalized cross-correlation in order to take advantage of a priori information of the catheter profile. The registration is accomplished with a two-dimensional template representative of the catheter to be tracked generated using two seed points given by the user. To validate catheter tracking with this method, we look at two metrics: accuracy and precision. The algorithms results are compared to a ground truth established by catheter midlines marked by expert radiologists. Using 12 objects of interest comprised of naso-gastric, endo-tracheal tubes, and chest tubes, and PICC and central venous catheters, we find that our algorithm can fully track 75% of the objects of interest, with a average tracking accuracy and precision of 85.0%, 93.6% respectively using the above metrics. Such a technique would be useful for physicians wishing to verify the positioning of catheter tips using chest radiographs.

Original language	English
Title of host publication	Medical Imaging 2007
Subtitle of host publication	Computer-Aided Diagnosis
Edition	PART 1
DOIs	https://doi.org/10.1117/12.707769
State	Published - 2007
Externally published	Yes
Event	Medical Imaging 2007: Computer-Aided Diagnosis - San Diego, CA, United States Duration: 20 Feb 2007 → 22 Feb 2007

Publication series

Name	Progress in Biomedical Optics and Imaging - Proceedings of SPIE
Number	PART 1
Volume	6514
ISSN (Print)	1605-7422

Conference

Conference	Medical Imaging 2007: Computer-Aided Diagnosis
Country/Territory	United States
City	San Diego, CA
Period	20/02/07 → 22/02/07

Keywords

Catheter
Computer aided detection
Digital radiographs
Match filtering
Template matching
Tip identification
Tracking

Access to Document

10.1117/12.707769

Cite this

Keller, B. M., Reeves, A. P., Cham, M. D., Henschke, C. I., & Yankelevitz, D. F. (2007). Semi-automated location identification of catheters in digital chest radiographs. In Medical Imaging 2007: Computer-Aided Diagnosis (PART 1 ed.). Article 65141O (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 6514, No. PART 1). https://doi.org/10.1117/12.707769

@inproceedings{542108090d0a49198b8a35ae59e4e6c3,

title = "Semi-automated location identification of catheters in digital chest radiographs",

abstract = "Localization of catheter tips is the most common task in intensive care unit imaging. In this work, catheters appearing in digital chest radiographs acquired by portable chest x-rays were tracked using a semi-automatic method. Due to the fact that catheters are synthetic objects, its profile does not vary drastically over its length. Therefore, we use forward looking registration with normalized cross-correlation in order to take advantage of a priori information of the catheter profile. The registration is accomplished with a two-dimensional template representative of the catheter to be tracked generated using two seed points given by the user. To validate catheter tracking with this method, we look at two metrics: accuracy and precision. The algorithms results are compared to a ground truth established by catheter midlines marked by expert radiologists. Using 12 objects of interest comprised of naso-gastric, endo-tracheal tubes, and chest tubes, and PICC and central venous catheters, we find that our algorithm can fully track 75% of the objects of interest, with a average tracking accuracy and precision of 85.0%, 93.6% respectively using the above metrics. Such a technique would be useful for physicians wishing to verify the positioning of catheter tips using chest radiographs.",

keywords = "Catheter, Computer aided detection, Digital radiographs, Match filtering, Template matching, Tip identification, Tracking",

author = "Keller, {Brad M.} and Reeves, {Anthony P.} and Cham, {Matthew D.} and Henschke, {Claudia I.} and Yankelevitz, {David F.}",

year = "2007",

doi = "10.1117/12.707769",

language = "English",

isbn = "0819466328",

series = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",

number = "PART 1",

booktitle = "Medical Imaging 2007",

edition = "PART 1",

note = "Medical Imaging 2007: Computer-Aided Diagnosis ; Conference date: 20-02-2007 Through 22-02-2007",

}

Keller, BM, Reeves, AP, Cham, MD, Henschke, CI & Yankelevitz, DF 2007, Semi-automated location identification of catheters in digital chest radiographs. in Medical Imaging 2007: Computer-Aided Diagnosis. PART 1 edn, 65141O, Progress in Biomedical Optics and Imaging - Proceedings of SPIE, no. PART 1, vol. 6514, Medical Imaging 2007: Computer-Aided Diagnosis, San Diego, CA, United States, 20/02/07. https://doi.org/10.1117/12.707769

Semi-automated location identification of catheters in digital chest radiographs. / Keller, Brad M.; Reeves, Anthony P.; Cham, Matthew D. et al.
Medical Imaging 2007: Computer-Aided Diagnosis. PART 1. ed. 2007. 65141O (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 6514, No. PART 1).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Semi-automated location identification of catheters in digital chest radiographs

AU - Keller, Brad M.

AU - Reeves, Anthony P.

AU - Cham, Matthew D.

AU - Henschke, Claudia I.

AU - Yankelevitz, David F.

PY - 2007

Y1 - 2007

N2 - Localization of catheter tips is the most common task in intensive care unit imaging. In this work, catheters appearing in digital chest radiographs acquired by portable chest x-rays were tracked using a semi-automatic method. Due to the fact that catheters are synthetic objects, its profile does not vary drastically over its length. Therefore, we use forward looking registration with normalized cross-correlation in order to take advantage of a priori information of the catheter profile. The registration is accomplished with a two-dimensional template representative of the catheter to be tracked generated using two seed points given by the user. To validate catheter tracking with this method, we look at two metrics: accuracy and precision. The algorithms results are compared to a ground truth established by catheter midlines marked by expert radiologists. Using 12 objects of interest comprised of naso-gastric, endo-tracheal tubes, and chest tubes, and PICC and central venous catheters, we find that our algorithm can fully track 75% of the objects of interest, with a average tracking accuracy and precision of 85.0%, 93.6% respectively using the above metrics. Such a technique would be useful for physicians wishing to verify the positioning of catheter tips using chest radiographs.

AB - Localization of catheter tips is the most common task in intensive care unit imaging. In this work, catheters appearing in digital chest radiographs acquired by portable chest x-rays were tracked using a semi-automatic method. Due to the fact that catheters are synthetic objects, its profile does not vary drastically over its length. Therefore, we use forward looking registration with normalized cross-correlation in order to take advantage of a priori information of the catheter profile. The registration is accomplished with a two-dimensional template representative of the catheter to be tracked generated using two seed points given by the user. To validate catheter tracking with this method, we look at two metrics: accuracy and precision. The algorithms results are compared to a ground truth established by catheter midlines marked by expert radiologists. Using 12 objects of interest comprised of naso-gastric, endo-tracheal tubes, and chest tubes, and PICC and central venous catheters, we find that our algorithm can fully track 75% of the objects of interest, with a average tracking accuracy and precision of 85.0%, 93.6% respectively using the above metrics. Such a technique would be useful for physicians wishing to verify the positioning of catheter tips using chest radiographs.

KW - Catheter

KW - Computer aided detection

KW - Digital radiographs

KW - Match filtering

KW - Template matching

KW - Tip identification

KW - Tracking

UR - http://www.scopus.com/inward/record.url?scp=35248867498&partnerID=8YFLogxK

U2 - 10.1117/12.707769

DO - 10.1117/12.707769

M3 - Conference contribution

AN - SCOPUS:35248867498

SN - 0819466328

SN - 9780819466327

T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

BT - Medical Imaging 2007

T2 - Medical Imaging 2007: Computer-Aided Diagnosis

Y2 - 20 February 2007 through 22 February 2007

ER -

Semi-automated location identification of catheters in digital chest radiographs

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this