Improved Osteoporosis Prediction in Breast Cancer Patients Using a Novel Semi-Foundational Model.

Small cohorts of certain disease states are common especially in medical imaging. Despite the growing culture of data sharing, information safety often precludes open sharing of these datasets for creating generalizable machine learning models. To overcome this barrier and maintain proper health inf...

Full description

Bibliographic Details
Published in:Journal of Imaging Informatics in Medicine Vol. 38; no. 4; pp. 2063 - 2071
Main Authors: Mayfield, John, Tibbetts, Katherine Quesada, Rehman, Aziz, Levin, Millena, Goltz, Dayna, Prakash, Neelesh
Format: diagnostic images research tables/charts Journal Article
Published: Springer Nature Aug2025
Online Access:View this record in EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=187278974&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 187278974
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        29482925
        NR3A
      jtl: Journal of Imaging Informatics in Medicine
      issn: 29482925
      maglogo: N
    pubinfo:
      dt: Aug2025
      vid: 38
      iid: 4
      pid: 237
      pub: Springer Nature
      place: New York, New York
    artinfo:
      ui:
        187278974
        187278974
        187278974
        10.1007/s10278-024-01337-x
        187278974
      ppf: 2063
      ppct: 8
      formats:
        fmt:
          – @attributes:
              type: T
          – @attributes:
              type: P
      tig:
        atl: Improved Osteoporosis Prediction in Breast Cancer Patients Using a Novel Semi-Foundational Model.
      aug:
        au:
          Mayfield, John
          Tibbetts, Katherine Quesada
          Rehman, Aziz
          Levin, Millena
          Goltz, Dayna
          Prakash, Neelesh
        affil: https://ror.org/04tk2gy88 Department of Radiology, USF Health, Tampa, USA
      sug:
        subj:
          Breast Neoplasms Radiography
          Osteoporosis Risk Factors
          Prediction Models
          Machine Learning
          Natural Language Processing
          Positron Emission Tomography Computed Tomography
          Risk Assessment
          Human
          Female
          Adult
          Middle Age
          Aged
          Retrospective Design
          Record Review
          Cancer Patients
          Deep Learning
          Bone Density
          Lumbar Vertebrae
          Analysis of Variance
          P-Value
          Artificial Intelligence
          Diagnosis, Computer Assisted
          T-Tests
          Convolutional Neural Networks
          Bone Diseases, Metabolic
          Learning Methods
          Radiography, Thoracic
          COVID-19
          Magnetic Resonance Imaging
          Adult: 19-44 years
          Middle Aged: 45-64 years
          Aged: 65+ years
          Female
      ab: Small cohorts of certain disease states are common especially in medical imaging. Despite the growing culture of data sharing, information safety often precludes open sharing of these datasets for creating generalizable machine learning models. To overcome this barrier and maintain proper health information protection, foundational models are rapidly evolving to provide deep learning solutions that have been pretrained on the native feature spaces of the data. Although this has been optimized in Large Language Models (LLMs), there is still a sparsity of foundational models for computer vision tasks. It is in this space that we provide an investigation into pretraining Visual Geometry Group (VGG)-16, Residual Network (ResNet)-50, and Dense Network (DenseNet)-121 on an unrelated dataset of 8500 chest CTs which was subsequently fine-tuned to classify bone mineral density (BMD) in 199 breast cancer patients using the L1 vertebra on CT. These semi-foundational models showed significant improved ternary classification into mild, moderate, and severe demineralization in comparison to ground truth Hounsfield Unit (HU) measurements in trabecular bone with the semi-foundational ResNet50 architecture demonstrating the best relative performance. Specifically, the holdout testing AUC was 0.99 (p-value < 0.05, ANOVA versus no pretraining versus ImageNet transfer learning) and F1-score 0.99 (p-value < 0.05) for the holdout testing set. In this study, the use of a semi-foundational model trained on the native feature space of CT provided improved classification in a completely disparate disease state with different window levels. Future implementation with these models may provide better generalization despite smaller numbers of a disease state to be classified.
      pubtype: Academic Journal
      doctype:
        diagnostic images
        research
        tables/charts
        Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N