CoChat
Sign Up
Cited by 127Radiomics and Machine Learning in Medical ImagingPancreatic and Hepatic Oncology ResearchMRI in cancer diagnosis

Combining radiomic features with a miRNA classifier may improve prediction of malignant pathology for pancreatic intraductal papillary mucinous neoplasms

Open access
Permuth, Jennifer B., the Florida Pancreas Collaborative, Choi, Jung, Balarunathan, Yoganand, Kim, Jongphil, Chen, Dung-Tsa, Chen, Lu, Orcutt, Sonia +14 more·2016·Oncotarget
DOI 10.18632/oncotarget.11768PMC PMC5349874
Open this paper in CoChat — free accountOpen PDF

Abstract

// Jennifer B. Permuth 1,2 , Jung Choi 3 , Yoganand Balarunathan 4 , Jongphil Kim 5 , Dung-Tsa Chen 5 , Lu Chen 5 , Sonia Orcutt 2 , Matthew P. Doepker 11 , Kenneth Gage 3 , Geoffrey Zhang 4,6 , Kujtim Latifi 4,6 , Sarah Hoffe 2,6 , Kun Jiang 7 , Domenico Coppola 7 , Barbara A. Centeno 7 , Anthony Magliocco 7 , Qian Li 4,8 , Jose Trevino 9 , Nipun Merchant 10 , Robert Gillies 4 and Mokenge Malafa 2 on behalf of the Florida Pancreas Collaborative 1 Cancer Epidemiology, Moffitt Cancer Center and Research Institute, Tampa, Florida, USA 2 Gastrointestinal Oncology, Moffitt Cancer Center and Research Institute, Tampa, Florida, USA 3 Diagnostic Imaging and Interventional Radiology, Moffitt Cancer Center and Research Institute, Tampa, Florida, USA 4 Cancer Imaging and Metabolism, Moffitt Cancer Center and Research Institute, Tampa, Florida, USA 5 Biostatistics and Bioinformatics, Moffitt Cancer Center and Research Institute, Tampa, Florida, USA 6 Radiation Oncology, Moffitt Cancer Center and Research Institute, Tampa, Florida, USA 7 Anatomic Pathology, Moffitt Cancer Center and Research Institute, Tampa, Florida, USA 8 Department of Radiology, Tianjin Medical University Cancer Institute and Hospital, Tianjin, China 9 Department of Surgery, Division of General Surgery, University of Florida Health Sciences Center, Gainesville, Florida, USA 10 Department of Surgery, Sylvester Comprehensive Cancer Center at the University of Miami Miller School of Medicine, Miami, Florida, USA 11 Department of Clinical Surgery/Surgical Oncology, Palmetto Health/USC School of Medicine, Columbia, South Carolina, USA Correspondence to: Jennifer B. Permuth, email: // Keywords : radiomics, miRNA, risk stratification, pre-malignant lesions, pancreas Received : July 06, 2016 Accepted : July 14, 2016 Published : August 31, 2016 Abstract Intraductal papillary mucinous neoplasms (IPMNs) are pancreatic cancer precursors incidentally discovered by cross-sectional imaging. Consensus guidelines for IPMN management rely on standard radiologic features to predict pathology, but they lack accuracy. Using a retrospective cohort of 38 surgically-resected, pathologically-confirmed IPMNs (20 benign; 18 malignant) with preoperative computed tomography (CT) images and matched plasma-based ‘miRNA genomic classifier (MGC)’ data, we determined whether quantitative ‘radiomic’ CT features (+/- the MGC) can more accurately predict IPMN pathology than standard radiologic features ‘high-risk’ or ‘worrisome’ for malignancy. Logistic regression, principal component analyses, and cross-validation were used to examine associations. Sensitivity, specificity, positive and negative predictive value (PPV, NPV) were estimated. The MGC, ‘high-risk,’ and ‘worrisome’ radiologic features had area under the receiver operating characteristic curve (AUC) values of 0.83, 0.84, and 0.54, respectively. Fourteen radiomic features differentiated malignant from benign IPMNs (p<0.05) and collectively had an AUC=0.77. Combining radiomic features with the MGC revealed an AUC=0.92 and superior sensitivity (83%), specificity (89%), PPV (88%), and NPV (85%) than other models. Evaluation of uncertainty by 10-fold cross-validation retained an AUC>0.80 (0.87 (95% CI:0.84-0.89)). This proof-of-concept study suggests a noninvasive radiogenomic approach may more accurately predict IPMN pathology than ‘worrisome’ radiologic features considered in consensus guidelines.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.18632/oncotarget.11768

Cites

50 of 50 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Permuth et al. (2016) found that texture analysis of CT images identified malignant IPMNs with an AUC of 0.77, improving to 0.92 with the inclusion of microRNA genomic data (sensitivity 83%, specificity 89%).

    “In a 2016 proof-of-concept study, Permuth et al. demonstrated the potential of texture analysis of CT images to identify malignant IPMNs with an AUC of 0.77 [53]. This improved to 0.92 with the inclusion of microRNA genomic data (sensitivity 83%, specificity 89%).”

    From Artificial Intelligence in the Diagnosis and Treatment of Pancreatic Cystic Lesions and Adenocarcinoma (2023) · cites this paper as [53]

    The Abstract reports an AUC of 0.77 for CT radiomic features, rising to 0.92 when combined with the miRNA classifier, with 83% sensitivity and 89% specificity. However, the Results (Analysis of radiomic data) specify that the 0.77 AUC came from 14 features, including three non-textural size-and-shape features; it was not a result for texture features alone. (LLM, conf=0.87)

    Experimental — accuracy not yet measured

  • Worrisome features as defined by consensus guidelines yielded an AUC of only 0.54.

    “In comparison, “worrisome features”, as defined by consensus guidelines (main duct dilation, cyst size > 3 cm, cyst wall thickening, mural nodules, or acute pancreatitis), yielded an AUC of only 0.54.”

    From Artificial Intelligence in the Diagnosis and Treatment of Pancreatic Cystic Lesions and Adenocarcinoma (2023) · cites this paper as [53]

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 1

  1. [48]Adsay NV FT Hruban RH Klimstra DS Kloppel G Intraductal Papillary Mucinous Neoplasm of the Pancreas Bosman FT Carneiro F Hruban RH Theise ND WHO classification of tumors of the digestive system Lyon WHO Press 2010 304 313

Cited by

Sorted by citations

Related

Authors
Permuth, J. B., Collaborative, T. F. P., Choi, J., Balarunathan, Y., Kim, J., Chen, D.-T., Chen, L., Orcutt, S., Doepker, M. P., Gage, K., Zhang, G., Latifi, K., Hoffe, S., Jiang, K., Coppola, D., Centeno, B. A., Magliocco, A., Li, Q., Trevino, J., Merchant, N., Gillies, R., & Malafa, M.
Affiliations
  • Moffitt Cancer Center (US)
  • University of South Carolina (US)
  • Tianjin Medical University Cancer Institute and Hospital (CN)
  • University of Florida Health (US)
  • University of Miami (US)
Corresponding author
Permuth, Jennifer B.
ORCID
Venue
Oncotarget
Publisher
Impact Journals, LLC
Published
2016-08-31
Volume
7
Issue
52
Pages
85785-85797
ISSN
1949-2553 (ISSN-L)
DOI
10.18632/oncotarget.11768
PMC
PMC5349874
OpenAlex
W2510667250
Cited by
127
References
50
Citations by year
2026: 10 · 2025: 3 · 2024: 2 · 2023: 15 · 2022: 16 · 2021: 14 · 2020: 27 · 2019: 15 · 2018: 10 · 2017: 12 · 2016: 3
FWCI
11.58
Type
journal article
Language
en
Open access
Licence
cc-by
Locations
  • Oncotarget (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
Funders
  • American Cancer Society (93-032-16)
  • Moffitt Cancer Center (P30CA076292, CA076292)
  • National Cancer Institute (CA076292, P30CA076292)
  • State of Florida
Topics
  • Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Radiomics and Machine Learning in Medical Imaging
  • Health Sciences › Medicine › Oncology › Pancreatic and Hepatic Oncology Research
  • Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › MRI in cancer diagnosis
Keywords
intraductal papillary mucinous neoplasm, pancreatic cancer precursors, radiomics, malignant transformation prediction, risk stratification, microRNA expression, miRNA classifier
MeSH terms
Aged, Aged, 80 and over, Adenocarcinoma, Mucinous, Carcinoma, Papillary, Female, Humans, Male, Middle Aged, Pancreatic Neoplasms, Tomography, X-Ray Computed, Carcinoma, Pancreatic Ductal, MicroRNAs

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review