Applying a new computer-aided detection scheme generated imaging marker to predict short-term breast cancer risk

Seyedehnafiseh Mirniaharikandehei, Alan B. Hollingsworth, Bhavika Patel, Morteza Heidari, Hong Liu, Bin Zheng

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

This study aims to investigate the feasibility of identifying a new quantitative imaging marker based on false-positives generated by a computer-aided detection (CAD) scheme to help predict short-term breast cancer risk. An image dataset including four view mammograms acquired from 1044 women was retrospectively assembled. All mammograms were originally interpreted as negative by radiologists. In the next subsequent mammography screening, 402 women were diagnosed with breast cancer and 642 remained negative. An existing CAD scheme was applied 'as is' to process each image. From CAD-generated results, four detection features including the total number of (1) initial detection seeds and (2) the final detected false-positive regions, (3) average and (4) sum of detection scores, were computed from each image. Then, by combining the features computed from two bilateral images of left and right breasts from either craniocaudal or mediolateral oblique view, two logistic regression models were trained and tested using a leave-one-case-out cross-validation method to predict the likelihood of each testing case being positive in the next subsequent screening. The new prediction model yielded the maximum prediction accuracy with an area under a ROC curve of AUC = 0.65 ± 0.017 and the maximum adjusted odds ratio of 4.49 with a 95% confidence interval of (2.95, 6.83). The results also showed an increasing trend in the adjusted odds ratio and risk prediction scores (p < 0.01). Thus, this study demonstrated that CAD-generated false-positives might include valuable information, which needs to be further explored for identifying and/or developing more effective imaging markers for predicting short-term breast cancer risk.

Original languageEnglish (US)
Article number105005
JournalPhysics in Medicine and Biology
Volume63
Issue number10
DOIs
StatePublished - May 15 2018

Fingerprint

Breast Neoplasms
Logistic Models
Odds Ratio
Mammography
ROC Curve
Area Under Curve
Seeds
Breast
Confidence Intervals
Radiologists
Datasets

Keywords

  • breast cancer screening
  • computer-aided detection (CAD)
  • false-positive detection
  • mammography screening
  • prediction of short-term cancer risk
  • quantitative imaging marker

ASJC Scopus subject areas

  • Radiological and Ultrasound Technology
  • Radiology Nuclear Medicine and imaging

Cite this

Applying a new computer-aided detection scheme generated imaging marker to predict short-term breast cancer risk. / Mirniaharikandehei, Seyedehnafiseh; Hollingsworth, Alan B.; Patel, Bhavika; Heidari, Morteza; Liu, Hong; Zheng, Bin.

In: Physics in Medicine and Biology, Vol. 63, No. 10, 105005, 15.05.2018.

Research output: Contribution to journalArticle

Mirniaharikandehei, Seyedehnafiseh ; Hollingsworth, Alan B. ; Patel, Bhavika ; Heidari, Morteza ; Liu, Hong ; Zheng, Bin. / Applying a new computer-aided detection scheme generated imaging marker to predict short-term breast cancer risk. In: Physics in Medicine and Biology. 2018 ; Vol. 63, No. 10.
@article{453dc83d049f47d7b1fa0f9208b6533e,
title = "Applying a new computer-aided detection scheme generated imaging marker to predict short-term breast cancer risk",
abstract = "This study aims to investigate the feasibility of identifying a new quantitative imaging marker based on false-positives generated by a computer-aided detection (CAD) scheme to help predict short-term breast cancer risk. An image dataset including four view mammograms acquired from 1044 women was retrospectively assembled. All mammograms were originally interpreted as negative by radiologists. In the next subsequent mammography screening, 402 women were diagnosed with breast cancer and 642 remained negative. An existing CAD scheme was applied 'as is' to process each image. From CAD-generated results, four detection features including the total number of (1) initial detection seeds and (2) the final detected false-positive regions, (3) average and (4) sum of detection scores, were computed from each image. Then, by combining the features computed from two bilateral images of left and right breasts from either craniocaudal or mediolateral oblique view, two logistic regression models were trained and tested using a leave-one-case-out cross-validation method to predict the likelihood of each testing case being positive in the next subsequent screening. The new prediction model yielded the maximum prediction accuracy with an area under a ROC curve of AUC = 0.65 ± 0.017 and the maximum adjusted odds ratio of 4.49 with a 95{\%} confidence interval of (2.95, 6.83). The results also showed an increasing trend in the adjusted odds ratio and risk prediction scores (p < 0.01). Thus, this study demonstrated that CAD-generated false-positives might include valuable information, which needs to be further explored for identifying and/or developing more effective imaging markers for predicting short-term breast cancer risk.",
keywords = "breast cancer screening, computer-aided detection (CAD), false-positive detection, mammography screening, prediction of short-term cancer risk, quantitative imaging marker",
author = "Seyedehnafiseh Mirniaharikandehei and Hollingsworth, {Alan B.} and Bhavika Patel and Morteza Heidari and Hong Liu and Bin Zheng",
year = "2018",
month = "5",
day = "15",
doi = "10.1088/1361-6560/aabefe",
language = "English (US)",
volume = "63",
journal = "Physics in Medicine and Biology",
issn = "0031-9155",
publisher = "IOP Publishing Ltd.",
number = "10",

}

TY - JOUR

T1 - Applying a new computer-aided detection scheme generated imaging marker to predict short-term breast cancer risk

AU - Mirniaharikandehei, Seyedehnafiseh

AU - Hollingsworth, Alan B.

AU - Patel, Bhavika

AU - Heidari, Morteza

AU - Liu, Hong

AU - Zheng, Bin

PY - 2018/5/15

Y1 - 2018/5/15

N2 - This study aims to investigate the feasibility of identifying a new quantitative imaging marker based on false-positives generated by a computer-aided detection (CAD) scheme to help predict short-term breast cancer risk. An image dataset including four view mammograms acquired from 1044 women was retrospectively assembled. All mammograms were originally interpreted as negative by radiologists. In the next subsequent mammography screening, 402 women were diagnosed with breast cancer and 642 remained negative. An existing CAD scheme was applied 'as is' to process each image. From CAD-generated results, four detection features including the total number of (1) initial detection seeds and (2) the final detected false-positive regions, (3) average and (4) sum of detection scores, were computed from each image. Then, by combining the features computed from two bilateral images of left and right breasts from either craniocaudal or mediolateral oblique view, two logistic regression models were trained and tested using a leave-one-case-out cross-validation method to predict the likelihood of each testing case being positive in the next subsequent screening. The new prediction model yielded the maximum prediction accuracy with an area under a ROC curve of AUC = 0.65 ± 0.017 and the maximum adjusted odds ratio of 4.49 with a 95% confidence interval of (2.95, 6.83). The results also showed an increasing trend in the adjusted odds ratio and risk prediction scores (p < 0.01). Thus, this study demonstrated that CAD-generated false-positives might include valuable information, which needs to be further explored for identifying and/or developing more effective imaging markers for predicting short-term breast cancer risk.

AB - This study aims to investigate the feasibility of identifying a new quantitative imaging marker based on false-positives generated by a computer-aided detection (CAD) scheme to help predict short-term breast cancer risk. An image dataset including four view mammograms acquired from 1044 women was retrospectively assembled. All mammograms were originally interpreted as negative by radiologists. In the next subsequent mammography screening, 402 women were diagnosed with breast cancer and 642 remained negative. An existing CAD scheme was applied 'as is' to process each image. From CAD-generated results, four detection features including the total number of (1) initial detection seeds and (2) the final detected false-positive regions, (3) average and (4) sum of detection scores, were computed from each image. Then, by combining the features computed from two bilateral images of left and right breasts from either craniocaudal or mediolateral oblique view, two logistic regression models were trained and tested using a leave-one-case-out cross-validation method to predict the likelihood of each testing case being positive in the next subsequent screening. The new prediction model yielded the maximum prediction accuracy with an area under a ROC curve of AUC = 0.65 ± 0.017 and the maximum adjusted odds ratio of 4.49 with a 95% confidence interval of (2.95, 6.83). The results also showed an increasing trend in the adjusted odds ratio and risk prediction scores (p < 0.01). Thus, this study demonstrated that CAD-generated false-positives might include valuable information, which needs to be further explored for identifying and/or developing more effective imaging markers for predicting short-term breast cancer risk.

KW - breast cancer screening

KW - computer-aided detection (CAD)

KW - false-positive detection

KW - mammography screening

KW - prediction of short-term cancer risk

KW - quantitative imaging marker

UR - http://www.scopus.com/inward/record.url?scp=85048015081&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85048015081&partnerID=8YFLogxK

U2 - 10.1088/1361-6560/aabefe

DO - 10.1088/1361-6560/aabefe

M3 - Article

C2 - 29667606

AN - SCOPUS:85048015081

VL - 63

JO - Physics in Medicine and Biology

JF - Physics in Medicine and Biology

SN - 0031-9155

IS - 10

M1 - 105005

ER -