Deep multi-modal classification of intraductal papillary mucinous neoplasms (IPMN) with canonical correlation analysis

Sarfaraz Hussein, Pujan Kandel, Juan E. Corral, Candice W. Bolan, Michael B. Wallace, Ulas Bagci

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Pancreatic cancer has the poorest prognosis among all cancer types. Intraductal Papillary Mucinous Neoplasms (IPMNs) are radiographically identifiable precursors to pancreatic cancer; hence, early detection and precise risk assessment of IPMN are vital. In this work, we propose a Convolutional Neural Network (CNN) based computer aided diagnosis (CAD) system to perform IPMN diagnosis and risk assessment by utilizing multi-modal MRI. In our proposed approach, we use minimum and maximum intensity projections to ease the annotation variations among different slices and type of MRIs. Then, we present a CNN to obtain deep feature representation corresponding to each MRI modality (T1-weighted and T2-weighted). At the final step, we employ canonical correlation analysis (CCA) to perform a fusion operation at the feature level, leading to discriminative canonical correlation features. Extracted features are used for classification. Our results indicate significant improvements over other potential approaches to solve this important problem. The proposed approach doesn't require explicit sample balancing in cases of imbalance between positive and negative examples. To the best of our knowledge, our study is the first to automatically diagnose IPMN using multi-modal MRI.

Original languageEnglish (US)
Title of host publication2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018
PublisherIEEE Computer Society
Pages800-804
Number of pages5
Volume2018-April
ISBN (Electronic)9781538636367
DOIs
StatePublished - May 23 2018
Event15th IEEE International Symposium on Biomedical Imaging, ISBI 2018 - Washington, United States
Duration: Apr 4 2018Apr 7 2018

Other

Other15th IEEE International Symposium on Biomedical Imaging, ISBI 2018
CountryUnited States
CityWashington
Period4/4/184/7/18

Fingerprint

Magnetic resonance imaging
Risk assessment
Neoplasms
Pancreatic Neoplasms
Neural networks
Computer aided diagnosis
Neural Networks (Computer)
Fusion reactions

Keywords

  • Canonical Correlation Analysis (CCA)
  • Deep learning
  • IPMN
  • Magnetic Resonance Imaging (MRI)
  • Pancreatic cancer

ASJC Scopus subject areas

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Cite this

Hussein, S., Kandel, P., Corral, J. E., Bolan, C. W., Wallace, M. B., & Bagci, U. (2018). Deep multi-modal classification of intraductal papillary mucinous neoplasms (IPMN) with canonical correlation analysis. In 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018 (Vol. 2018-April, pp. 800-804). IEEE Computer Society. https://doi.org/10.1109/ISBI.2018.8363693

Deep multi-modal classification of intraductal papillary mucinous neoplasms (IPMN) with canonical correlation analysis. / Hussein, Sarfaraz; Kandel, Pujan; Corral, Juan E.; Bolan, Candice W.; Wallace, Michael B.; Bagci, Ulas.

2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018. Vol. 2018-April IEEE Computer Society, 2018. p. 800-804.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Hussein, S, Kandel, P, Corral, JE, Bolan, CW, Wallace, MB & Bagci, U 2018, Deep multi-modal classification of intraductal papillary mucinous neoplasms (IPMN) with canonical correlation analysis. in 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018. vol. 2018-April, IEEE Computer Society, pp. 800-804, 15th IEEE International Symposium on Biomedical Imaging, ISBI 2018, Washington, United States, 4/4/18. https://doi.org/10.1109/ISBI.2018.8363693
Hussein S, Kandel P, Corral JE, Bolan CW, Wallace MB, Bagci U. Deep multi-modal classification of intraductal papillary mucinous neoplasms (IPMN) with canonical correlation analysis. In 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018. Vol. 2018-April. IEEE Computer Society. 2018. p. 800-804 https://doi.org/10.1109/ISBI.2018.8363693
Hussein, Sarfaraz ; Kandel, Pujan ; Corral, Juan E. ; Bolan, Candice W. ; Wallace, Michael B. ; Bagci, Ulas. / Deep multi-modal classification of intraductal papillary mucinous neoplasms (IPMN) with canonical correlation analysis. 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018. Vol. 2018-April IEEE Computer Society, 2018. pp. 800-804
@inproceedings{39ec5d6308834005a4dedea0a6e8fcf5,
title = "Deep multi-modal classification of intraductal papillary mucinous neoplasms (IPMN) with canonical correlation analysis",
abstract = "Pancreatic cancer has the poorest prognosis among all cancer types. Intraductal Papillary Mucinous Neoplasms (IPMNs) are radiographically identifiable precursors to pancreatic cancer; hence, early detection and precise risk assessment of IPMN are vital. In this work, we propose a Convolutional Neural Network (CNN) based computer aided diagnosis (CAD) system to perform IPMN diagnosis and risk assessment by utilizing multi-modal MRI. In our proposed approach, we use minimum and maximum intensity projections to ease the annotation variations among different slices and type of MRIs. Then, we present a CNN to obtain deep feature representation corresponding to each MRI modality (T1-weighted and T2-weighted). At the final step, we employ canonical correlation analysis (CCA) to perform a fusion operation at the feature level, leading to discriminative canonical correlation features. Extracted features are used for classification. Our results indicate significant improvements over other potential approaches to solve this important problem. The proposed approach doesn't require explicit sample balancing in cases of imbalance between positive and negative examples. To the best of our knowledge, our study is the first to automatically diagnose IPMN using multi-modal MRI.",
keywords = "Canonical Correlation Analysis (CCA), Deep learning, IPMN, Magnetic Resonance Imaging (MRI), Pancreatic cancer",
author = "Sarfaraz Hussein and Pujan Kandel and Corral, {Juan E.} and Bolan, {Candice W.} and Wallace, {Michael B.} and Ulas Bagci",
year = "2018",
month = "5",
day = "23",
doi = "10.1109/ISBI.2018.8363693",
language = "English (US)",
volume = "2018-April",
pages = "800--804",
booktitle = "2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Deep multi-modal classification of intraductal papillary mucinous neoplasms (IPMN) with canonical correlation analysis

AU - Hussein, Sarfaraz

AU - Kandel, Pujan

AU - Corral, Juan E.

AU - Bolan, Candice W.

AU - Wallace, Michael B.

AU - Bagci, Ulas

PY - 2018/5/23

Y1 - 2018/5/23

N2 - Pancreatic cancer has the poorest prognosis among all cancer types. Intraductal Papillary Mucinous Neoplasms (IPMNs) are radiographically identifiable precursors to pancreatic cancer; hence, early detection and precise risk assessment of IPMN are vital. In this work, we propose a Convolutional Neural Network (CNN) based computer aided diagnosis (CAD) system to perform IPMN diagnosis and risk assessment by utilizing multi-modal MRI. In our proposed approach, we use minimum and maximum intensity projections to ease the annotation variations among different slices and type of MRIs. Then, we present a CNN to obtain deep feature representation corresponding to each MRI modality (T1-weighted and T2-weighted). At the final step, we employ canonical correlation analysis (CCA) to perform a fusion operation at the feature level, leading to discriminative canonical correlation features. Extracted features are used for classification. Our results indicate significant improvements over other potential approaches to solve this important problem. The proposed approach doesn't require explicit sample balancing in cases of imbalance between positive and negative examples. To the best of our knowledge, our study is the first to automatically diagnose IPMN using multi-modal MRI.

AB - Pancreatic cancer has the poorest prognosis among all cancer types. Intraductal Papillary Mucinous Neoplasms (IPMNs) are radiographically identifiable precursors to pancreatic cancer; hence, early detection and precise risk assessment of IPMN are vital. In this work, we propose a Convolutional Neural Network (CNN) based computer aided diagnosis (CAD) system to perform IPMN diagnosis and risk assessment by utilizing multi-modal MRI. In our proposed approach, we use minimum and maximum intensity projections to ease the annotation variations among different slices and type of MRIs. Then, we present a CNN to obtain deep feature representation corresponding to each MRI modality (T1-weighted and T2-weighted). At the final step, we employ canonical correlation analysis (CCA) to perform a fusion operation at the feature level, leading to discriminative canonical correlation features. Extracted features are used for classification. Our results indicate significant improvements over other potential approaches to solve this important problem. The proposed approach doesn't require explicit sample balancing in cases of imbalance between positive and negative examples. To the best of our knowledge, our study is the first to automatically diagnose IPMN using multi-modal MRI.

KW - Canonical Correlation Analysis (CCA)

KW - Deep learning

KW - IPMN

KW - Magnetic Resonance Imaging (MRI)

KW - Pancreatic cancer

UR - http://www.scopus.com/inward/record.url?scp=85048093596&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85048093596&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2018.8363693

DO - 10.1109/ISBI.2018.8363693

M3 - Conference contribution

AN - SCOPUS:85048093596

VL - 2018-April

SP - 800

EP - 804

BT - 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018

PB - IEEE Computer Society

ER -