Benefit of computer-aided detection analysis for the detection of subsolid and solid lung nodules on thin- and thick-section CT

Myrna C.B. Godoy; Tae Jung Kim; Charles S. White; Luca Bogoni; Patricia De Groot; Charles Florin; Nancy Obuchowski; James S. Babb; Marcos Salganicoff; David P. Naidich; Vikram Anand; Sangmin Park; Ioannis Vlahos; Jane P. Ko

doi:10.2214/AJR.11.7532

Benefit of computer-aided detection analysis for the detection of subsolid and solid lung nodules on thin- and thick-section CT

Myrna C.B. Godoy, Tae Jung Kim, Charles S. White, Luca Bogoni, Patricia De Groot, Charles Florin, Nancy Obuchowski, James S. Babb, Marcos Salganicoff, David P. Naidich, Vikram Anand, Sangmin Park, Ioannis Vlahos, Jane P. Ko

Image Guided Cancer Therapy Research Program

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

55 Scopus citations

Abstract

OBJECTIVE. The objective of our study was to evaluate the impact of computer-aided detection (CAD) on the identification of subsolid and solid lung nodules on thin- and thick-section CT. MATERIALS AND METHODS. For 46 chest CT examinations with ground-glass opacity (GGO) nodules, CAD marks computed using thin data were evaluated in two phases. First, four chest radiologists reviewed thin sections (reader thin) for nodules and subsequently CAD marks (reader _thin + CAD_thin). After 4 months, the same cases were reviewed on thick sections (reader_thick) and subsequently with CAD marks (reader_thick + CAD_thick). Sensitivities were evaluated. Additionally, reader thick sensitivity with assessment of CAD marks on thin sections was estimated (reader_thick + CAD_thin). RESULTS. For 155 nodules (mean, 5.5 mm; range, 4.0-27.5 mm) - 74 solid nodules, 22 part-solid (part-solid nodules), and 59 GGO nodules - CAD stand-alone sensitivity was 80%, 95%, and 71%, respectively, with three false-positives on average (0-12) per CT study. Reader_thin + CAD_thin sensitivities were higher than reader_thin for solid nodules (82% vs 57%, p < 0.001), part-solid nodules (97% vs 81%, p = 0.0027), and GGO nodules (82% vs 69%, p < 0.001) for all readers (p < 0.001). Respective sensitivities for reader_thick, reader_thick + CAD _thick, reader_thick + CAD_thin were 40%, 58% (p < 0.001), and 77% (p < 0.001) for solid nodules; 72%, 73% (p = 0.322), and 94% (p < 0.001) for part-solid nodules; and 53%, 58% (p = 0.008), and 79% (p < 0.001) for GGO nodules. For reader_thin, false-positives increased from 0.64 per case to 0.90 with CAD_thin (p < 0.001) but not for reader_thick; false-positive rates were 1.17, 1.19, and 1.26 per case for reader_thick, reader_thick + CAD _thick, and reader_thick + CAD_thin, respectively. CONCLUSION. Detection of GGO nodules and solid nodules is significantly improved with CAD. When interpretation is performed on thick sections, the benefit is greater when CAD marks are reviewed on thin rather than thick sections.

Original language	English (US)
Pages (from-to)	74-83
Number of pages	10
Journal	American Journal of Roentgenology
Volume	200
Issue number	1
DOIs	https://doi.org/10.2214/AJR.11.7532
State	Published - Jan 2013

Keywords

CT
Computer-aided detection
Ground-glass nodule
Lung nodule

ASJC Scopus subject areas

Radiology Nuclear Medicine and imaging

Access to Document

10.2214/AJR.11.7532

Cite this

Godoy, M. C. B., Kim, T. J., White, C. S., Bogoni, L., De Groot, P., Florin, C., Obuchowski, N., Babb, J. S., Salganicoff, M., Naidich, D. P., Anand, V., Park, S., Vlahos, I., & Ko, J. P. (2013). Benefit of computer-aided detection analysis for the detection of subsolid and solid lung nodules on thin- and thick-section CT. American Journal of Roentgenology, 200(1), 74-83. https://doi.org/10.2214/AJR.11.7532

Godoy, MCB, Kim, TJ, White, CS, Bogoni, L, De Groot, P, Florin, C, Obuchowski, N, Babb, JS, Salganicoff, M, Naidich, DP, Anand, V, Park, S, Vlahos, I & Ko, JP 2013, 'Benefit of computer-aided detection analysis for the detection of subsolid and solid lung nodules on thin- and thick-section CT', American Journal of Roentgenology, vol. 200, no. 1, pp. 74-83. https://doi.org/10.2214/AJR.11.7532

@article{3d4327f0543c40b5b97c4ac365f88be6,

title = "Benefit of computer-aided detection analysis for the detection of subsolid and solid lung nodules on thin- and thick-section CT",

abstract = "OBJECTIVE. The objective of our study was to evaluate the impact of computer-aided detection (CAD) on the identification of subsolid and solid lung nodules on thin- and thick-section CT. MATERIALS AND METHODS. For 46 chest CT examinations with ground-glass opacity (GGO) nodules, CAD marks computed using thin data were evaluated in two phases. First, four chest radiologists reviewed thin sections (reader thin) for nodules and subsequently CAD marks (reader thin + CADthin). After 4 months, the same cases were reviewed on thick sections (readerthick) and subsequently with CAD marks (readerthick + CADthick). Sensitivities were evaluated. Additionally, reader thick sensitivity with assessment of CAD marks on thin sections was estimated (readerthick + CADthin). RESULTS. For 155 nodules (mean, 5.5 mm; range, 4.0-27.5 mm) - 74 solid nodules, 22 part-solid (part-solid nodules), and 59 GGO nodules - CAD stand-alone sensitivity was 80%, 95%, and 71%, respectively, with three false-positives on average (0-12) per CT study. Readerthin + CADthin sensitivities were higher than readerthin for solid nodules (82% vs 57%, p < 0.001), part-solid nodules (97% vs 81%, p = 0.0027), and GGO nodules (82% vs 69%, p < 0.001) for all readers (p < 0.001). Respective sensitivities for readerthick, readerthick + CAD thick, readerthick + CADthin were 40%, 58% (p < 0.001), and 77% (p < 0.001) for solid nodules; 72%, 73% (p = 0.322), and 94% (p < 0.001) for part-solid nodules; and 53%, 58% (p = 0.008), and 79% (p < 0.001) for GGO nodules. For readerthin, false-positives increased from 0.64 per case to 0.90 with CADthin (p < 0.001) but not for readerthick; false-positive rates were 1.17, 1.19, and 1.26 per case for readerthick, readerthick + CAD thick, and readerthick + CADthin, respectively. CONCLUSION. Detection of GGO nodules and solid nodules is significantly improved with CAD. When interpretation is performed on thick sections, the benefit is greater when CAD marks are reviewed on thin rather than thick sections.",

keywords = "CT, Computer-aided detection, Ground-glass nodule, Lung nodule",

author = "Godoy, {Myrna C.B.} and Kim, {Tae Jung} and White, {Charles S.} and Luca Bogoni and {De Groot}, Patricia and Charles Florin and Nancy Obuchowski and Babb, {James S.} and Marcos Salganicoff and Naidich, {David P.} and Vikram Anand and Sangmin Park and Ioannis Vlahos and Ko, {Jane P.}",

year = "2013",

month = jan,

doi = "10.2214/AJR.11.7532",

language = "English (US)",

volume = "200",

pages = "74--83",

journal = "American Journal of Roentgenology",

issn = "0361-803X",

publisher = "American Roentgen Ray Society",

number = "1",

}

TY - JOUR

T1 - Benefit of computer-aided detection analysis for the detection of subsolid and solid lung nodules on thin- and thick-section CT

AU - Godoy, Myrna C.B.

AU - Kim, Tae Jung

AU - White, Charles S.

AU - Bogoni, Luca

AU - De Groot, Patricia

AU - Florin, Charles

AU - Obuchowski, Nancy

AU - Babb, James S.

AU - Salganicoff, Marcos

AU - Naidich, David P.

AU - Anand, Vikram

AU - Park, Sangmin

AU - Vlahos, Ioannis

AU - Ko, Jane P.

PY - 2013/1

Y1 - 2013/1

N2 - OBJECTIVE. The objective of our study was to evaluate the impact of computer-aided detection (CAD) on the identification of subsolid and solid lung nodules on thin- and thick-section CT. MATERIALS AND METHODS. For 46 chest CT examinations with ground-glass opacity (GGO) nodules, CAD marks computed using thin data were evaluated in two phases. First, four chest radiologists reviewed thin sections (reader thin) for nodules and subsequently CAD marks (reader thin + CADthin). After 4 months, the same cases were reviewed on thick sections (readerthick) and subsequently with CAD marks (readerthick + CADthick). Sensitivities were evaluated. Additionally, reader thick sensitivity with assessment of CAD marks on thin sections was estimated (readerthick + CADthin). RESULTS. For 155 nodules (mean, 5.5 mm; range, 4.0-27.5 mm) - 74 solid nodules, 22 part-solid (part-solid nodules), and 59 GGO nodules - CAD stand-alone sensitivity was 80%, 95%, and 71%, respectively, with three false-positives on average (0-12) per CT study. Readerthin + CADthin sensitivities were higher than readerthin for solid nodules (82% vs 57%, p < 0.001), part-solid nodules (97% vs 81%, p = 0.0027), and GGO nodules (82% vs 69%, p < 0.001) for all readers (p < 0.001). Respective sensitivities for readerthick, readerthick + CAD thick, readerthick + CADthin were 40%, 58% (p < 0.001), and 77% (p < 0.001) for solid nodules; 72%, 73% (p = 0.322), and 94% (p < 0.001) for part-solid nodules; and 53%, 58% (p = 0.008), and 79% (p < 0.001) for GGO nodules. For readerthin, false-positives increased from 0.64 per case to 0.90 with CADthin (p < 0.001) but not for readerthick; false-positive rates were 1.17, 1.19, and 1.26 per case for readerthick, readerthick + CAD thick, and readerthick + CADthin, respectively. CONCLUSION. Detection of GGO nodules and solid nodules is significantly improved with CAD. When interpretation is performed on thick sections, the benefit is greater when CAD marks are reviewed on thin rather than thick sections.

AB - OBJECTIVE. The objective of our study was to evaluate the impact of computer-aided detection (CAD) on the identification of subsolid and solid lung nodules on thin- and thick-section CT. MATERIALS AND METHODS. For 46 chest CT examinations with ground-glass opacity (GGO) nodules, CAD marks computed using thin data were evaluated in two phases. First, four chest radiologists reviewed thin sections (reader thin) for nodules and subsequently CAD marks (reader thin + CADthin). After 4 months, the same cases were reviewed on thick sections (readerthick) and subsequently with CAD marks (readerthick + CADthick). Sensitivities were evaluated. Additionally, reader thick sensitivity with assessment of CAD marks on thin sections was estimated (readerthick + CADthin). RESULTS. For 155 nodules (mean, 5.5 mm; range, 4.0-27.5 mm) - 74 solid nodules, 22 part-solid (part-solid nodules), and 59 GGO nodules - CAD stand-alone sensitivity was 80%, 95%, and 71%, respectively, with three false-positives on average (0-12) per CT study. Readerthin + CADthin sensitivities were higher than readerthin for solid nodules (82% vs 57%, p < 0.001), part-solid nodules (97% vs 81%, p = 0.0027), and GGO nodules (82% vs 69%, p < 0.001) for all readers (p < 0.001). Respective sensitivities for readerthick, readerthick + CAD thick, readerthick + CADthin were 40%, 58% (p < 0.001), and 77% (p < 0.001) for solid nodules; 72%, 73% (p = 0.322), and 94% (p < 0.001) for part-solid nodules; and 53%, 58% (p = 0.008), and 79% (p < 0.001) for GGO nodules. For readerthin, false-positives increased from 0.64 per case to 0.90 with CADthin (p < 0.001) but not for readerthick; false-positive rates were 1.17, 1.19, and 1.26 per case for readerthick, readerthick + CAD thick, and readerthick + CADthin, respectively. CONCLUSION. Detection of GGO nodules and solid nodules is significantly improved with CAD. When interpretation is performed on thick sections, the benefit is greater when CAD marks are reviewed on thin rather than thick sections.

KW - CT

KW - Computer-aided detection

KW - Ground-glass nodule

KW - Lung nodule

UR - http://www.scopus.com/inward/record.url?scp=84871863453&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84871863453&partnerID=8YFLogxK

U2 - 10.2214/AJR.11.7532

DO - 10.2214/AJR.11.7532

M3 - Article

C2 - 23255744

AN - SCOPUS:84871863453

SN - 0361-803X

VL - 200

SP - 74

EP - 83

JO - American Journal of Roentgenology

JF - American Journal of Roentgenology

IS - 1

ER -

Benefit of computer-aided detection analysis for the detection of subsolid and solid lung nodules on thin- and thick-section CT

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this