Quantitative computer-aided diagnostic algorithm for automated detection of peak lesion attenuation in differentiating clear cell from papillary and chromophobe renal cell carcinoma, oncocytoma, and fat-poor angiomyolipoma on multiphasic multidetector computed tomography

Heidi Coy, Jonathan R Young, Michael L. Douek, Matthew S. Brown, James Sayre, Steven S. Raman

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

Objective: To evaluate the performance of a novel, quantitative computer-aided diagnostic (CAD) algorithm on four-phase multidetector computed tomography (MDCT) to detect peak lesion attenuation to enable differentiation of clear cell renal cell carcinoma (ccRCC) from chromophobe RCC (chRCC), papillary RCC (pRCC), oncocytoma, and fat-poor angiomyolipoma (fp-AML). Materials and methods: We queried our clinical databases to obtain a cohort of histologically proven renal masses with preoperative MDCT with four phases [unenhanced (U), corticomedullary (CM), nephrographic (NP), and excretory (E)]. A whole lesion 3D contour was obtained in all four phases. The CAD algorithm determined a region of interest (ROI) of peak lesion attenuation within the 3D lesion contour. For comparison, a manual ROI was separately placed in the most enhancing portion of the lesion by visual inspection for a reference standard, and in uninvolved renal cortex. Relative lesion attenuation for both CAD and manual methods was obtained by normalizing the CAD peak lesion attenuation ROI (and the reference standard manually placed ROI) to uninvolved renal cortex with the formula [(peak lesion attenuation ROI − cortex ROI)/cortex ROI] × 100%. ROC analysis and area under the curve (AUC) were used to assess diagnostic performance. Bland–Altman analysis was used to compare peak ROI between CAD and manual method. Results: The study cohort comprised 200 patients with 200 unique renal masses: 106 (53%) ccRCC, 32 (16%) oncocytomas, 18 (9%) chRCCs, 34 (17%) pRCCs, and 10 (5%) fp-AMLs. In the CM phase, CAD-derived ROI enabled characterization of ccRCC from chRCC, pRCC, oncocytoma, and fp-AML with AUCs of 0.850 (95% CI 0.732–0.968), 0.959 (95% CI 0.930–0.989), 0.792 (95% CI 0.716–0.869), and 0.825 (95% CI 0.703–0.948), respectively. On Bland–Altman analysis, there was excellent agreement of CAD and manual methods with mean differences between 14 and 26 HU in each phase. Conclusion: A novel, quantitative CAD algorithm enabled robust peak HU lesion detection and discrimination of ccRCC from other renal lesions with similar performance compared to the manual method.

Original languageEnglish (US)
Pages (from-to)1919-1928
Number of pages10
JournalAbdominal Radiology
Volume42
Issue number7
DOIs
StatePublished - Jul 1 2017
Externally publishedYes

Fingerprint

Oxyphilic Adenoma
Angiomyolipoma
Multidetector Computed Tomography
Renal Cell Carcinoma
Fats
Kidney
Area Under Curve
ROC Curve
Cohort Studies
Databases

Keywords

  • Computed tomography (CT)
  • Computer-aided diagnosis
  • Oncocytoma
  • Quantitative imaging
  • Renal cell carcinoma

ASJC Scopus subject areas

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

Cite this

@article{33d9efe07cf947edb40ef7b0b3c0fab9,
title = "Quantitative computer-aided diagnostic algorithm for automated detection of peak lesion attenuation in differentiating clear cell from papillary and chromophobe renal cell carcinoma, oncocytoma, and fat-poor angiomyolipoma on multiphasic multidetector computed tomography",
abstract = "Objective: To evaluate the performance of a novel, quantitative computer-aided diagnostic (CAD) algorithm on four-phase multidetector computed tomography (MDCT) to detect peak lesion attenuation to enable differentiation of clear cell renal cell carcinoma (ccRCC) from chromophobe RCC (chRCC), papillary RCC (pRCC), oncocytoma, and fat-poor angiomyolipoma (fp-AML). Materials and methods: We queried our clinical databases to obtain a cohort of histologically proven renal masses with preoperative MDCT with four phases [unenhanced (U), corticomedullary (CM), nephrographic (NP), and excretory (E)]. A whole lesion 3D contour was obtained in all four phases. The CAD algorithm determined a region of interest (ROI) of peak lesion attenuation within the 3D lesion contour. For comparison, a manual ROI was separately placed in the most enhancing portion of the lesion by visual inspection for a reference standard, and in uninvolved renal cortex. Relative lesion attenuation for both CAD and manual methods was obtained by normalizing the CAD peak lesion attenuation ROI (and the reference standard manually placed ROI) to uninvolved renal cortex with the formula [(peak lesion attenuation ROI − cortex ROI)/cortex ROI] × 100{\%}. ROC analysis and area under the curve (AUC) were used to assess diagnostic performance. Bland–Altman analysis was used to compare peak ROI between CAD and manual method. Results: The study cohort comprised 200 patients with 200 unique renal masses: 106 (53{\%}) ccRCC, 32 (16{\%}) oncocytomas, 18 (9{\%}) chRCCs, 34 (17{\%}) pRCCs, and 10 (5{\%}) fp-AMLs. In the CM phase, CAD-derived ROI enabled characterization of ccRCC from chRCC, pRCC, oncocytoma, and fp-AML with AUCs of 0.850 (95{\%} CI 0.732–0.968), 0.959 (95{\%} CI 0.930–0.989), 0.792 (95{\%} CI 0.716–0.869), and 0.825 (95{\%} CI 0.703–0.948), respectively. On Bland–Altman analysis, there was excellent agreement of CAD and manual methods with mean differences between 14 and 26 HU in each phase. Conclusion: A novel, quantitative CAD algorithm enabled robust peak HU lesion detection and discrimination of ccRCC from other renal lesions with similar performance compared to the manual method.",
keywords = "Computed tomography (CT), Computer-aided diagnosis, Oncocytoma, Quantitative imaging, Renal cell carcinoma",
author = "Heidi Coy and Young, {Jonathan R} and Douek, {Michael L.} and Brown, {Matthew S.} and James Sayre and Raman, {Steven S.}",
year = "2017",
month = "7",
day = "1",
doi = "10.1007/s00261-017-1095-6",
language = "English (US)",
volume = "42",
pages = "1919--1928",
journal = "Abdominal Radiology",
issn = "2366-004X",
publisher = "Springer New York",
number = "7",

}

TY - JOUR

T1 - Quantitative computer-aided diagnostic algorithm for automated detection of peak lesion attenuation in differentiating clear cell from papillary and chromophobe renal cell carcinoma, oncocytoma, and fat-poor angiomyolipoma on multiphasic multidetector computed tomography

AU - Coy, Heidi

AU - Young, Jonathan R

AU - Douek, Michael L.

AU - Brown, Matthew S.

AU - Sayre, James

AU - Raman, Steven S.

PY - 2017/7/1

Y1 - 2017/7/1

N2 - Objective: To evaluate the performance of a novel, quantitative computer-aided diagnostic (CAD) algorithm on four-phase multidetector computed tomography (MDCT) to detect peak lesion attenuation to enable differentiation of clear cell renal cell carcinoma (ccRCC) from chromophobe RCC (chRCC), papillary RCC (pRCC), oncocytoma, and fat-poor angiomyolipoma (fp-AML). Materials and methods: We queried our clinical databases to obtain a cohort of histologically proven renal masses with preoperative MDCT with four phases [unenhanced (U), corticomedullary (CM), nephrographic (NP), and excretory (E)]. A whole lesion 3D contour was obtained in all four phases. The CAD algorithm determined a region of interest (ROI) of peak lesion attenuation within the 3D lesion contour. For comparison, a manual ROI was separately placed in the most enhancing portion of the lesion by visual inspection for a reference standard, and in uninvolved renal cortex. Relative lesion attenuation for both CAD and manual methods was obtained by normalizing the CAD peak lesion attenuation ROI (and the reference standard manually placed ROI) to uninvolved renal cortex with the formula [(peak lesion attenuation ROI − cortex ROI)/cortex ROI] × 100%. ROC analysis and area under the curve (AUC) were used to assess diagnostic performance. Bland–Altman analysis was used to compare peak ROI between CAD and manual method. Results: The study cohort comprised 200 patients with 200 unique renal masses: 106 (53%) ccRCC, 32 (16%) oncocytomas, 18 (9%) chRCCs, 34 (17%) pRCCs, and 10 (5%) fp-AMLs. In the CM phase, CAD-derived ROI enabled characterization of ccRCC from chRCC, pRCC, oncocytoma, and fp-AML with AUCs of 0.850 (95% CI 0.732–0.968), 0.959 (95% CI 0.930–0.989), 0.792 (95% CI 0.716–0.869), and 0.825 (95% CI 0.703–0.948), respectively. On Bland–Altman analysis, there was excellent agreement of CAD and manual methods with mean differences between 14 and 26 HU in each phase. Conclusion: A novel, quantitative CAD algorithm enabled robust peak HU lesion detection and discrimination of ccRCC from other renal lesions with similar performance compared to the manual method.

AB - Objective: To evaluate the performance of a novel, quantitative computer-aided diagnostic (CAD) algorithm on four-phase multidetector computed tomography (MDCT) to detect peak lesion attenuation to enable differentiation of clear cell renal cell carcinoma (ccRCC) from chromophobe RCC (chRCC), papillary RCC (pRCC), oncocytoma, and fat-poor angiomyolipoma (fp-AML). Materials and methods: We queried our clinical databases to obtain a cohort of histologically proven renal masses with preoperative MDCT with four phases [unenhanced (U), corticomedullary (CM), nephrographic (NP), and excretory (E)]. A whole lesion 3D contour was obtained in all four phases. The CAD algorithm determined a region of interest (ROI) of peak lesion attenuation within the 3D lesion contour. For comparison, a manual ROI was separately placed in the most enhancing portion of the lesion by visual inspection for a reference standard, and in uninvolved renal cortex. Relative lesion attenuation for both CAD and manual methods was obtained by normalizing the CAD peak lesion attenuation ROI (and the reference standard manually placed ROI) to uninvolved renal cortex with the formula [(peak lesion attenuation ROI − cortex ROI)/cortex ROI] × 100%. ROC analysis and area under the curve (AUC) were used to assess diagnostic performance. Bland–Altman analysis was used to compare peak ROI between CAD and manual method. Results: The study cohort comprised 200 patients with 200 unique renal masses: 106 (53%) ccRCC, 32 (16%) oncocytomas, 18 (9%) chRCCs, 34 (17%) pRCCs, and 10 (5%) fp-AMLs. In the CM phase, CAD-derived ROI enabled characterization of ccRCC from chRCC, pRCC, oncocytoma, and fp-AML with AUCs of 0.850 (95% CI 0.732–0.968), 0.959 (95% CI 0.930–0.989), 0.792 (95% CI 0.716–0.869), and 0.825 (95% CI 0.703–0.948), respectively. On Bland–Altman analysis, there was excellent agreement of CAD and manual methods with mean differences between 14 and 26 HU in each phase. Conclusion: A novel, quantitative CAD algorithm enabled robust peak HU lesion detection and discrimination of ccRCC from other renal lesions with similar performance compared to the manual method.

KW - Computed tomography (CT)

KW - Computer-aided diagnosis

KW - Oncocytoma

KW - Quantitative imaging

KW - Renal cell carcinoma

UR - http://www.scopus.com/inward/record.url?scp=85014695617&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85014695617&partnerID=8YFLogxK

U2 - 10.1007/s00261-017-1095-6

DO - 10.1007/s00261-017-1095-6

M3 - Article

VL - 42

SP - 1919

EP - 1928

JO - Abdominal Radiology

JF - Abdominal Radiology

SN - 2366-004X

IS - 7

ER -