A combined radiomics and cyst fluid inflammatory markers model to predict preoperative risk in pancreatic cystic lesions

Travis L. Williams; Kate A. Harrington; Sharon A. Lawrence; Jayasree Chakraborty; Mohammad A. Al Efishat; Marc A. Attiyeh; Gokce Askan; Yuting Chou; Alessandra Pulvirenti; Caitlin A. Mcintyre; Mithat Gonen; Olca Basturk; Vinod P. Balachandran; T. Peter Kingham; Michael I. D'angelica; Williarm R. Jarnagin; Jeffrey A. Drebin; Richard K.G. Do; Peter J. Allen; Amber L. Simpson

doi:10.1117/12.2566425

A combined radiomics and cyst fluid inflammatory markers model to predict preoperative risk in pancreatic cystic lesions

Travis L. Williams, Kate A. Harrington, Sharon A. Lawrence, Jayasree Chakraborty, Mohammad A. Al Efishat, Marc A. Attiyeh, Gokce Askan, Yuting Chou, Alessandra Pulvirenti, Caitlin A. Mcintyre, Mithat Gonen, Olca Basturk, Vinod P. Balachandran, T. Peter Kingham, Michael I. D'angelica, Williarm R. Jarnagin, Jeffrey A. Drebin, Richard K.G. Do, Peter J. Allen, Amber L. Simpson

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

1 Scopus citations

Abstract

This paper contributes to the burgeoning field of surgical data science. Specifically, multi-modal integration of relevant patient data is used to determine who should undergo a complex pancreatic resection. Intraductal papillary mucinous neoplasms (IPMNs) represent cystic precursor lesions of pancreatic cancer with varying risk for malignancy. We combine radiomic analysis of diagnostic computed tomography (CT) with protein markers extracted from the cyst fluid to create a unified prediction model to identify high-risk IPMNs. Patients with high-risk IPMN would be sent for resection, whereas patients with low-risk cystic lesions would be spared an invasive procedure. We extracted radiomic features from CT scans and combined this with cyst-fluid markers. The cyst fluid model yielded an area under the curve (AUC) of 0.74. Adding the QI model improved performance with an AUC of 0.88. Radiomic analysis of routinely acquired CT scans combined with cyst fluid inflammatory markers provides accurate prediction of risk of pancreatic cancer progression.

Original language	English (US)
Title of host publication	Medical Imaging 2020
Subtitle of host publication	Image-Guided Procedures, Robotic Interventions, and Modeling
Editors	Baowei Fei, Cristian A. Linte
Publisher	SPIE
ISBN (Electronic)	9781510633971
DOIs	https://doi.org/10.1117/12.2566425
State	Published - 2020
Externally published	Yes
Event	Medical Imaging 2020: Image-Guided Procedures, Robotic Interventions, and Modeling - Houston, United States Duration: Feb 16 2020 → Feb 19 2020

Publication series

Name	Proceedings of SPIE - The International Society for Optical Engineering
Volume	11315
ISSN (Print)	0277-786X
ISSN (Electronic)	1996-756X

Conference

Conference	Medical Imaging 2020: Image-Guided Procedures, Robotic Interventions, and Modeling
Country/Territory	United States
City	Houston
Period	2/16/20 → 2/19/20

Keywords

Cyst fiuid
Intraductal papillary mucinous neoplasms
Pancreas
Quantitative image analysis
Radiomics

ASJC Scopus subject areas

Electronic, Optical and Magnetic Materials
Condensed Matter Physics
Computer Science Applications
Applied Mathematics
Electrical and Electronic Engineering

Access to Document

10.1117/12.2566425

Cite this

Williams, T. L., Harrington, K. A., Lawrence, S. A., Chakraborty, J., Al Efishat, M. A., Attiyeh, M. A., Askan, G., Chou, Y., Pulvirenti, A., Mcintyre, C. A., Gonen, M., Basturk, O., Balachandran, V. P., Kingham, T. P., D'angelica, M. I., Jarnagin, W. R., Drebin, J. A., Do, R. K. G., Allen, P. J., & Simpson, A. L. (2020). A combined radiomics and cyst fluid inflammatory markers model to predict preoperative risk in pancreatic cystic lesions. In B. Fei, & C. A. Linte (Eds.), Medical Imaging 2020: Image-Guided Procedures, Robotic Interventions, and Modeling Article 113151Q (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 11315). SPIE. https://doi.org/10.1117/12.2566425

A combined radiomics and cyst fluid inflammatory markers model to predict preoperative risk in pancreatic cystic lesions. / Williams, Travis L.; Harrington, Kate A.; Lawrence, Sharon A. et al.
Medical Imaging 2020: Image-Guided Procedures, Robotic Interventions, and Modeling. ed. / Baowei Fei; Cristian A. Linte. SPIE, 2020. 113151Q (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 11315).

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

Williams, TL, Harrington, KA, Lawrence, SA, Chakraborty, J, Al Efishat, MA, Attiyeh, MA, Askan, G, Chou, Y, Pulvirenti, A, Mcintyre, CA, Gonen, M, Basturk, O, Balachandran, VP, Kingham, TP, D'angelica, MI, Jarnagin, WR, Drebin, JA, Do, RKG, Allen, PJ & Simpson, AL 2020, A combined radiomics and cyst fluid inflammatory markers model to predict preoperative risk in pancreatic cystic lesions. in B Fei & CA Linte (eds), Medical Imaging 2020: Image-Guided Procedures, Robotic Interventions, and Modeling., 113151Q, Proceedings of SPIE - The International Society for Optical Engineering, vol. 11315, SPIE, Medical Imaging 2020: Image-Guided Procedures, Robotic Interventions, and Modeling, Houston, United States, 2/16/20. https://doi.org/10.1117/12.2566425

Williams TL, Harrington KA, Lawrence SA, Chakraborty J, Al Efishat MA, Attiyeh MA et al. A combined radiomics and cyst fluid inflammatory markers model to predict preoperative risk in pancreatic cystic lesions. In Fei B, Linte CA, editors, Medical Imaging 2020: Image-Guided Procedures, Robotic Interventions, and Modeling. SPIE. 2020. 113151Q. (Proceedings of SPIE - The International Society for Optical Engineering). doi: 10.1117/12.2566425

Williams, Travis L. ; Harrington, Kate A. ; Lawrence, Sharon A. et al. / A combined radiomics and cyst fluid inflammatory markers model to predict preoperative risk in pancreatic cystic lesions. Medical Imaging 2020: Image-Guided Procedures, Robotic Interventions, and Modeling. editor / Baowei Fei ; Cristian A. Linte. SPIE, 2020. (Proceedings of SPIE - The International Society for Optical Engineering).

@inproceedings{f1461b252646472ca660221f53a318cb,

title = "A combined radiomics and cyst fluid inflammatory markers model to predict preoperative risk in pancreatic cystic lesions",

abstract = "This paper contributes to the burgeoning field of surgical data science. Specifically, multi-modal integration of relevant patient data is used to determine who should undergo a complex pancreatic resection. Intraductal papillary mucinous neoplasms (IPMNs) represent cystic precursor lesions of pancreatic cancer with varying risk for malignancy. We combine radiomic analysis of diagnostic computed tomography (CT) with protein markers extracted from the cyst fluid to create a unified prediction model to identify high-risk IPMNs. Patients with high-risk IPMN would be sent for resection, whereas patients with low-risk cystic lesions would be spared an invasive procedure. We extracted radiomic features from CT scans and combined this with cyst-fluid markers. The cyst fluid model yielded an area under the curve (AUC) of 0.74. Adding the QI model improved performance with an AUC of 0.88. Radiomic analysis of routinely acquired CT scans combined with cyst fluid inflammatory markers provides accurate prediction of risk of pancreatic cancer progression.",

keywords = "Cyst fiuid, Intraductal papillary mucinous neoplasms, Pancreas, Quantitative image analysis, Radiomics",

author = "Williams, {Travis L.} and Harrington, {Kate A.} and Lawrence, {Sharon A.} and Jayasree Chakraborty and {Al Efishat}, {Mohammad A.} and Attiyeh, {Marc A.} and Gokce Askan and Yuting Chou and Alessandra Pulvirenti and Mcintyre, {Caitlin A.} and Mithat Gonen and Olca Basturk and Balachandran, {Vinod P.} and Kingham, {T. Peter} and D'angelica, {Michael I.} and Jarnagin, {Williarm R.} and Drebin, {Jeffrey A.} and Do, {Richard K.G.} and Allen, {Peter J.} and Simpson, {Amber L.}",

note = "Publisher Copyright: {\textcopyright} 2020 SPIE.; Medical Imaging 2020: Image-Guided Procedures, Robotic Interventions, and Modeling ; Conference date: 16-02-2020 Through 19-02-2020",

year = "2020",

doi = "10.1117/12.2566425",

language = "English (US)",

series = "Proceedings of SPIE - The International Society for Optical Engineering",

publisher = "SPIE",

editor = "Baowei Fei and Linte, {Cristian A.}",

booktitle = "Medical Imaging 2020",

}

TY - GEN

T1 - A combined radiomics and cyst fluid inflammatory markers model to predict preoperative risk in pancreatic cystic lesions

AU - Williams, Travis L.

AU - Harrington, Kate A.

AU - Lawrence, Sharon A.

AU - Chakraborty, Jayasree

AU - Al Efishat, Mohammad A.

AU - Attiyeh, Marc A.

AU - Askan, Gokce

AU - Chou, Yuting

AU - Pulvirenti, Alessandra

AU - Mcintyre, Caitlin A.

AU - Gonen, Mithat

AU - Basturk, Olca

AU - Balachandran, Vinod P.

AU - Kingham, T. Peter

AU - D'angelica, Michael I.

AU - Jarnagin, Williarm R.

AU - Drebin, Jeffrey A.

AU - Do, Richard K.G.

AU - Allen, Peter J.

AU - Simpson, Amber L.

PY - 2020

Y1 - 2020

N2 - This paper contributes to the burgeoning field of surgical data science. Specifically, multi-modal integration of relevant patient data is used to determine who should undergo a complex pancreatic resection. Intraductal papillary mucinous neoplasms (IPMNs) represent cystic precursor lesions of pancreatic cancer with varying risk for malignancy. We combine radiomic analysis of diagnostic computed tomography (CT) with protein markers extracted from the cyst fluid to create a unified prediction model to identify high-risk IPMNs. Patients with high-risk IPMN would be sent for resection, whereas patients with low-risk cystic lesions would be spared an invasive procedure. We extracted radiomic features from CT scans and combined this with cyst-fluid markers. The cyst fluid model yielded an area under the curve (AUC) of 0.74. Adding the QI model improved performance with an AUC of 0.88. Radiomic analysis of routinely acquired CT scans combined with cyst fluid inflammatory markers provides accurate prediction of risk of pancreatic cancer progression.

AB - This paper contributes to the burgeoning field of surgical data science. Specifically, multi-modal integration of relevant patient data is used to determine who should undergo a complex pancreatic resection. Intraductal papillary mucinous neoplasms (IPMNs) represent cystic precursor lesions of pancreatic cancer with varying risk for malignancy. We combine radiomic analysis of diagnostic computed tomography (CT) with protein markers extracted from the cyst fluid to create a unified prediction model to identify high-risk IPMNs. Patients with high-risk IPMN would be sent for resection, whereas patients with low-risk cystic lesions would be spared an invasive procedure. We extracted radiomic features from CT scans and combined this with cyst-fluid markers. The cyst fluid model yielded an area under the curve (AUC) of 0.74. Adding the QI model improved performance with an AUC of 0.88. Radiomic analysis of routinely acquired CT scans combined with cyst fluid inflammatory markers provides accurate prediction of risk of pancreatic cancer progression.

KW - Cyst fiuid

KW - Intraductal papillary mucinous neoplasms

KW - Pancreas

KW - Quantitative image analysis

KW - Radiomics

UR - http://www.scopus.com/inward/record.url?scp=85085247265&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85085247265&partnerID=8YFLogxK

U2 - 10.1117/12.2566425

DO - 10.1117/12.2566425

M3 - Conference contribution

AN - SCOPUS:85085247265

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - Medical Imaging 2020

A2 - Fei, Baowei

A2 - Linte, Cristian A.

PB - SPIE

T2 - Medical Imaging 2020: Image-Guided Procedures, Robotic Interventions, and Modeling

Y2 - 16 February 2020 through 19 February 2020

ER -

A combined radiomics and cyst fluid inflammatory markers model to predict preoperative risk in pancreatic cystic lesions

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this