Rapid kV-switching single-source dual-energy CT ex vivo renal calculi characterization using a multiparametric approach: refining parameters on an expanded dataset

J. Scott Kriegshauser, Robert G. Paden, Miao He, Mitchell R Humphreys, Steven I. Zell, Yinlin Fu, Teresa Wu, Mark D. Sugi, Alvin C Silva

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Purpose: We aimed to determine the best algorithms for renal stone composition characterization using rapid kV-switching single-source dual-energy computed tomography (rsDECT) and a multiparametric approach after dataset expansion and refinement of variables. Methods: rsDECT scans (80 and 140 kVp) were performed on 38 ex vivo 5- to 10-mm renal stones composed of uric acid (UA; n = 21), struvite (STR; n = 5), cystine (CYS; n = 5), and calcium oxalate monohydrate (COM; n = 7). Measurements were obtained for 17 variables: mean Hounsfield units (HU) at 11 monochromatic keV levels, effective Z, 2 iodine-water material basis pairs, and 3 mean monochromatic keV ratios (40/140, 70/120, 70/140). Analysis included using 5 multiparametric algorithms: Support Vector Machine, RandomTree, Artificial Neural Network, Naïve Bayes Tree, and Decision Tree (C4.5). Results: Separating UA from non-UA stones was 100% accurate using multiple methods. For non-UA stones, using a 70-keV mean cutoff value of 694 HU had 100% accuracy for distinguishing COM from non-COM (CYS, STR) stones. The best result for distinguishing all 3 non-UA subtypes was obtained using RandomTree (15/17, 88%). Conclusions: For stones 5 mm or larger, multiple methods can distinguish UA from non-UA and COM from non-COM stones with 100% accuracy. Thus, the choice for analysis is per the user’s preference. The best model for separating all three non-UA subtypes was 88% accurate, although with considerable individual overlap between CYS and STR stones. Larger, more diverse datasets, including in vivo data and technical improvements in material separation, may offer more guidance in distinguishing non-UA stone subtypes in the clinical setting.

Original languageEnglish (US)
Pages (from-to)1-7
Number of pages7
JournalAbdominal Radiology
DOIs
StateAccepted/In press - Sep 26 2017

Fingerprint

Kidney Calculi
Tomography
Kidney
Decision Trees
Calcium Oxalate
Cystine
Uric Acid
Iodine
Water
Datasets

Keywords

  • DECT
  • Renal stone
  • Renal stone composition
  • WEKA

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging
  • Gastroenterology
  • Urology
  • Radiological and Ultrasound Technology

Cite this

Rapid kV-switching single-source dual-energy CT ex vivo renal calculi characterization using a multiparametric approach : refining parameters on an expanded dataset. / Kriegshauser, J. Scott; Paden, Robert G.; He, Miao; Humphreys, Mitchell R; Zell, Steven I.; Fu, Yinlin; Wu, Teresa; Sugi, Mark D.; Silva, Alvin C.

In: Abdominal Radiology, 26.09.2017, p. 1-7.

Research output: Contribution to journalArticle

@article{908d0fc67bd34e26abde00e77d853d03,
title = "Rapid kV-switching single-source dual-energy CT ex vivo renal calculi characterization using a multiparametric approach: refining parameters on an expanded dataset",
abstract = "Purpose: We aimed to determine the best algorithms for renal stone composition characterization using rapid kV-switching single-source dual-energy computed tomography (rsDECT) and a multiparametric approach after dataset expansion and refinement of variables. Methods: rsDECT scans (80 and 140 kVp) were performed on 38 ex vivo 5- to 10-mm renal stones composed of uric acid (UA; n = 21), struvite (STR; n = 5), cystine (CYS; n = 5), and calcium oxalate monohydrate (COM; n = 7). Measurements were obtained for 17 variables: mean Hounsfield units (HU) at 11 monochromatic keV levels, effective Z, 2 iodine-water material basis pairs, and 3 mean monochromatic keV ratios (40/140, 70/120, 70/140). Analysis included using 5 multiparametric algorithms: Support Vector Machine, RandomTree, Artificial Neural Network, Na{\"i}ve Bayes Tree, and Decision Tree (C4.5). Results: Separating UA from non-UA stones was 100{\%} accurate using multiple methods. For non-UA stones, using a 70-keV mean cutoff value of 694 HU had 100{\%} accuracy for distinguishing COM from non-COM (CYS, STR) stones. The best result for distinguishing all 3 non-UA subtypes was obtained using RandomTree (15/17, 88{\%}). Conclusions: For stones 5 mm or larger, multiple methods can distinguish UA from non-UA and COM from non-COM stones with 100{\%} accuracy. Thus, the choice for analysis is per the user’s preference. The best model for separating all three non-UA subtypes was 88{\%} accurate, although with considerable individual overlap between CYS and STR stones. Larger, more diverse datasets, including in vivo data and technical improvements in material separation, may offer more guidance in distinguishing non-UA stone subtypes in the clinical setting.",
keywords = "DECT, Renal stone, Renal stone composition, WEKA",
author = "Kriegshauser, {J. Scott} and Paden, {Robert G.} and Miao He and Humphreys, {Mitchell R} and Zell, {Steven I.} and Yinlin Fu and Teresa Wu and Sugi, {Mark D.} and Silva, {Alvin C}",
year = "2017",
month = "9",
day = "26",
doi = "10.1007/s00261-017-1331-0",
language = "English (US)",
pages = "1--7",
journal = "Abdominal Radiology",
issn = "2366-004X",
publisher = "Springer New York",

}

TY - JOUR

T1 - Rapid kV-switching single-source dual-energy CT ex vivo renal calculi characterization using a multiparametric approach

T2 - refining parameters on an expanded dataset

AU - Kriegshauser, J. Scott

AU - Paden, Robert G.

AU - He, Miao

AU - Humphreys, Mitchell R

AU - Zell, Steven I.

AU - Fu, Yinlin

AU - Wu, Teresa

AU - Sugi, Mark D.

AU - Silva, Alvin C

PY - 2017/9/26

Y1 - 2017/9/26

N2 - Purpose: We aimed to determine the best algorithms for renal stone composition characterization using rapid kV-switching single-source dual-energy computed tomography (rsDECT) and a multiparametric approach after dataset expansion and refinement of variables. Methods: rsDECT scans (80 and 140 kVp) were performed on 38 ex vivo 5- to 10-mm renal stones composed of uric acid (UA; n = 21), struvite (STR; n = 5), cystine (CYS; n = 5), and calcium oxalate monohydrate (COM; n = 7). Measurements were obtained for 17 variables: mean Hounsfield units (HU) at 11 monochromatic keV levels, effective Z, 2 iodine-water material basis pairs, and 3 mean monochromatic keV ratios (40/140, 70/120, 70/140). Analysis included using 5 multiparametric algorithms: Support Vector Machine, RandomTree, Artificial Neural Network, Naïve Bayes Tree, and Decision Tree (C4.5). Results: Separating UA from non-UA stones was 100% accurate using multiple methods. For non-UA stones, using a 70-keV mean cutoff value of 694 HU had 100% accuracy for distinguishing COM from non-COM (CYS, STR) stones. The best result for distinguishing all 3 non-UA subtypes was obtained using RandomTree (15/17, 88%). Conclusions: For stones 5 mm or larger, multiple methods can distinguish UA from non-UA and COM from non-COM stones with 100% accuracy. Thus, the choice for analysis is per the user’s preference. The best model for separating all three non-UA subtypes was 88% accurate, although with considerable individual overlap between CYS and STR stones. Larger, more diverse datasets, including in vivo data and technical improvements in material separation, may offer more guidance in distinguishing non-UA stone subtypes in the clinical setting.

AB - Purpose: We aimed to determine the best algorithms for renal stone composition characterization using rapid kV-switching single-source dual-energy computed tomography (rsDECT) and a multiparametric approach after dataset expansion and refinement of variables. Methods: rsDECT scans (80 and 140 kVp) were performed on 38 ex vivo 5- to 10-mm renal stones composed of uric acid (UA; n = 21), struvite (STR; n = 5), cystine (CYS; n = 5), and calcium oxalate monohydrate (COM; n = 7). Measurements were obtained for 17 variables: mean Hounsfield units (HU) at 11 monochromatic keV levels, effective Z, 2 iodine-water material basis pairs, and 3 mean monochromatic keV ratios (40/140, 70/120, 70/140). Analysis included using 5 multiparametric algorithms: Support Vector Machine, RandomTree, Artificial Neural Network, Naïve Bayes Tree, and Decision Tree (C4.5). Results: Separating UA from non-UA stones was 100% accurate using multiple methods. For non-UA stones, using a 70-keV mean cutoff value of 694 HU had 100% accuracy for distinguishing COM from non-COM (CYS, STR) stones. The best result for distinguishing all 3 non-UA subtypes was obtained using RandomTree (15/17, 88%). Conclusions: For stones 5 mm or larger, multiple methods can distinguish UA from non-UA and COM from non-COM stones with 100% accuracy. Thus, the choice for analysis is per the user’s preference. The best model for separating all three non-UA subtypes was 88% accurate, although with considerable individual overlap between CYS and STR stones. Larger, more diverse datasets, including in vivo data and technical improvements in material separation, may offer more guidance in distinguishing non-UA stone subtypes in the clinical setting.

KW - DECT

KW - Renal stone

KW - Renal stone composition

KW - WEKA

UR - http://www.scopus.com/inward/record.url?scp=85029896644&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85029896644&partnerID=8YFLogxK

U2 - 10.1007/s00261-017-1331-0

DO - 10.1007/s00261-017-1331-0

M3 - Article

C2 - 28952007

AN - SCOPUS:85029896644

SP - 1

EP - 7

JO - Abdominal Radiology

JF - Abdominal Radiology

SN - 2366-004X

ER -