YEARS

2007-2012

AUTHORS

Elizabeth S Burnside

TITLE

Machine Learning for Improved Mammography Screening

ABSTRACT

DESCRIPTION (provided by applicant): Accurate breast cancer screening demands that radiologists maintain a balance of high sensitivity and high specificity when interpreting mammography. Subspecialty-trained breast imagers perform significantly better than general radiologists by recognizing more breast cancers and minimizing benign biopsies. An automated reasoning system called a Bayesian network (BN), has the potential to improve the performance of general radiologists, who interpret the majority of mammograms, to the level of subspecialty-trained breast radiologists, who are in short supply. A BN is a probabilistic graphical model that has been used for decision support in a variety of domains, including radiology. Machine learning provides an appealing way to create and optimize BNs to perform at high levels of sensitivity and specificity. Our research group has developed a prototype, expert-defined BN that uses imaging features and demographic risk factors to classify abnormalities on mammograms as benign or malignant. Our BN can perform at a higher level than general radiologists, but our goal is for it to perform as well or better than subspecialty-trained breast radiologists. To this end, we have compiled a structured, multi-relational dataset of mammography abnormalities and pathologic outcomes from which cutting edge machine learning techniques can construct an improved BN. In the past, BNs were trained and tested on individual abnormalities in isolation. In fact, other abnormalities on the same mammogram or previous mammograms, which necessarily appear in other rows of a relational database, can further improve BN learning. We have used basic statistical relational learning (SRL) techniques to enhance Bayesian learning algorithms to leverage this important additional data. A novel SRL capability introduced by our team within the last year, called view learning, makes it possible to incorporate this related data from other parts of the database by automatically defining new database fields. In our preliminary work, we have shown a stepwise improvement in BN performance: first, with conventional BN learning;then, with basic SRL;and finally, with view learning. We now seek support to determine whether more tightly integrated SRL and view learning will significantly improve our BN's ability to accurately diagnose breast cancer. In addition, we propose to investigate whether two other promising machine learning techniques, predicate-invention and collective-classification, can optimize the BN to perform at levels significantly better than current clinical practice.

FUNDED PUBLICATIONS

  • Informatics in radiology: comparison of logistic regression and artificial neural network models in breast cancer risk estimation.
  • Pursuing optimal thresholds to recommend breast biopsy by quantifying the value of tomosynthesis.
  • Socioeconomic disparities in the decline in invasive breast cancer incidence
  • Automated identification of protein-ligand interaction features using Inductive Logic Programming: a hexose binding case study
  • The mammographic density of a mass is a significant predictor of breast cancer.
  • Predicting invasive breast cancer versus DCIS in different age groups.
  • Computer-aided diagnostic models in breast cancer screening.
  • The Effect of Budgetary Restrictions on Breast Cancer Diagnostic Decisions.
  • A comprehensive methodology for determining the most informative mammographic features.
  • Predicting invasive breast cancer versus DCIS in different age groups
  • Breast cancer risk estimation with artificial neural networks revisited: discrimination and calibration.
  • Validation of results from knowledge discovery: mass density as a predictor of breast cancer.
  • Automated identification of protein-ligand interaction features using Inductive Logic Programming: a hexose binding case study.
  • Validation of Results from Knowledge Discovery: Mass Density as a Predictor of Breast Cancer
  • Automatic classification of mammography reports by BI-RADS breast tissue composition class.
  • Combining gene expression, demographic and clinical data in modeling disease: a case study of bipolar disorder and schizophrenia.
  • Socioeconomic disparities in the decline in invasive breast cancer incidence.
  • Probabilistic computer model developed from clinical data in national mammography database format to classify mammographic findings.
  • What is the optimal threshold at which to recommend breast biopsy?
  • Optimal Policies for Reducing Unnecessary Follow-up Mammography Exams in Breast Cancer Diagnosis.
  • Predicting Malignancy from Mammography Findings and Surgical Biopsies.
  • Combining gene expression, demographic and clinical data in modeling disease: a case study of bipolar disorder and schizophrenia
  • A Comprehensive Methodology for Determining the Most Informative Mammographic Features
  • A logistic regression model based on the national mammography database format to aid breast cancer diagnosis.
  • How to use: Click on a object to move its position. Double click to open its homepage. Right click to preview its contents.

    Download the RDF metadata as:   json-ld nt turtle xml License info


    41 TRIPLES      17 PREDICATES      42 URIs      9 LITERALS

    Subject Predicate Object
    1 grants:a34c71972c5406d69b8e05dbbec40b5a sg:abstract DESCRIPTION (provided by applicant): Accurate breast cancer screening demands that radiologists maintain a balance of high sensitivity and high specificity when interpreting mammography. Subspecialty-trained breast imagers perform significantly better than general radiologists by recognizing more breast cancers and minimizing benign biopsies. An automated reasoning system called a Bayesian network (BN), has the potential to improve the performance of general radiologists, who interpret the majority of mammograms, to the level of subspecialty-trained breast radiologists, who are in short supply. A BN is a probabilistic graphical model that has been used for decision support in a variety of domains, including radiology. Machine learning provides an appealing way to create and optimize BNs to perform at high levels of sensitivity and specificity. Our research group has developed a prototype, expert-defined BN that uses imaging features and demographic risk factors to classify abnormalities on mammograms as benign or malignant. Our BN can perform at a higher level than general radiologists, but our goal is for it to perform as well or better than subspecialty-trained breast radiologists. To this end, we have compiled a structured, multi-relational dataset of mammography abnormalities and pathologic outcomes from which cutting edge machine learning techniques can construct an improved BN. In the past, BNs were trained and tested on individual abnormalities in isolation. In fact, other abnormalities on the same mammogram or previous mammograms, which necessarily appear in other rows of a relational database, can further improve BN learning. We have used basic statistical relational learning (SRL) techniques to enhance Bayesian learning algorithms to leverage this important additional data. A novel SRL capability introduced by our team within the last year, called view learning, makes it possible to incorporate this related data from other parts of the database by automatically defining new database fields. In our preliminary work, we have shown a stepwise improvement in BN performance: first, with conventional BN learning;then, with basic SRL;and finally, with view learning. We now seek support to determine whether more tightly integrated SRL and view learning will significantly improve our BN's ability to accurately diagnose breast cancer. In addition, we propose to investigate whether two other promising machine learning techniques, predicate-invention and collective-classification, can optimize the BN to perform at levels significantly better than current clinical practice.
    2 sg:endYear 2012
    3 sg:fundingAmount 1411215.0
    4 sg:fundingCurrency USD
    5 sg:hasContribution contributions:69b66c52c87f0cae567ec9d3e4ec6859
    6 sg:hasFieldOfResearchCode anzsrc-for:08
    7 anzsrc-for:0801
    8 sg:hasFundedPublication articles:047cf4e5d1a5b2d7e48150ed1201a9b4
    9 articles:09fec7d3dbaa1417384c23912f428568
    10 articles:0e1941cd4584823b53022acefe0fc6e5
    11 articles:111290ad2e10d55beb6439ddf45b6307
    12 articles:220fbda4acdabb0bf060373563b10750
    13 articles:31acebab5d64a67d8af469a7f05ebb18
    14 articles:3247dc684dc9ddd947110cdd7a90df9a
    15 articles:3e8e8d38e9d3571a32720c2b810a6de8
    16 articles:44a5739af34c4bd3f728b84e2df3374f
    17 articles:47a6c034000c9c2ca7ee9c728a574787
    18 articles:5068f878569e157da16027d69bfef955
    19 articles:516f6175c1e67f8a87a15496238fca05
    20 articles:55592dc42fa7cdb8d6a57174948ab717
    21 articles:6ffd2f441bb16fd1794f937b2a6f47af
    22 articles:7bd9e6ade4d4e1b139425c824778ffc7
    23 articles:853197c2d5f9e8088da6009ef7240632
    24 articles:8d7f4033439caf48a4fe145406dba67d
    25 articles:989acba89bb1365d9ad5bc54688b0e42
    26 articles:a4955fd094313d1adf7326a1f70db91c
    27 articles:abf90f154c80867fbd9d10cd60a54e1a
    28 articles:ac5ba3164c8baea22a33a654579a19de
    29 articles:c3caed51d45d10b15eb0a012aa2e08e8
    30 articles:c6b8b6f63c0b4078fe5d2a4dbfbdebb3
    31 articles:f215197aaab3b94513975d69810e964e
    32 sg:hasFundingOrganization grid-institutes:grid.48336.3a
    33 sg:hasRecipientOrganization grid-institutes:grid.14003.36
    34 sg:language English
    35 sg:license http://scigraph.springernature.com/explorer/license/
    36 sg:scigraphId a34c71972c5406d69b8e05dbbec40b5a
    37 sg:startYear 2007
    38 sg:title Machine Learning for Improved Mammography Screening
    39 sg:webpage http://projectreporter.nih.gov/project_info_description.cfm?aid=7776970
    40 rdf:type sg:Grant
    41 rdfs:label Grant: Machine Learning for Improved Mammography Screening
    HOW TO GET THIS DATA PROGRAMMATICALLY:

    JSON-LD is a popular JSON format for linked data.

    curl -H 'Accept: application/ld+json' 'http://scigraph.springernature.com/things/grants/a34c71972c5406d69b8e05dbbec40b5a'

    N-Triples is a line-based linked data format ideal for batch operations .

    curl -H 'Accept: application/n-triples' 'http://scigraph.springernature.com/things/grants/a34c71972c5406d69b8e05dbbec40b5a'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'http://scigraph.springernature.com/things/grants/a34c71972c5406d69b8e05dbbec40b5a'

    RDF/XML is a standard XML format for linked data.

    curl -H 'Accept: application/rdf+xml' 'http://scigraph.springernature.com/things/grants/a34c71972c5406d69b8e05dbbec40b5a'






    Preview window. Press ESC to close (or click here)


    ...