A new mass classification system derived from multiple features and a trained MLP model

Maxine Tan, Jiantao Pu, Bin Zheng

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

2 Citations (Scopus)

Abstract

High false-positive recall rate is an important clinical issue that reduces efficacy of screening mammography. Aiming to help improve accuracy of classification between the benign and malignant breast masses and then reduce false-positive recalls, we developed and tested a new computer-aided diagnosis (CAD) scheme for mass classification using a database including 600 verified mass regions. The mass regions were segmented from regions of interest (ROIs) with a fixed size of 512×512 pixels. The mass regions were first segmented by an automated scheme, with manual corrections to the mass boundary performed if there was noticeable segmentation error. We randomly divided the 600 ROIs into 400 ROIs (200 malignant and 200 benign) for training, and 200 ROIs (100 malignant and 100 benign) for testing. We computed and analyzed 124 shape, texture, contrast, and spiculation based features in this study. Combining with previously computed 27 regional and shape based features for each of the ROIs in our database, we built an initial image feature pool. From this pool of 151 features, we extracted 13 features by applying the Sequential Forward Floating Selection algorithm on the ROIs in the training dataset. We then trained a multilayer perceptron model using these 13 features, and applied the trained model to the ROIs in the testing dataset. Receiver operating characteristic (ROC) analysis was used to evaluate classification accuracy. The area under the ROC curve was 0.8814±0.025 for the testing dataset. The results show a higher CAD mass classification performance, which needs to be validated further in a more comprehensive study.

Original languageEnglish
Title of host publicationMedical Imaging 2014
Subtitle of host publicationComputer-Aided Diagnosis
PublisherSPIE - International Society for Optical Engineering
ISBN (Print)9780819498281
DOIs
Publication statusPublished - 2014
Externally publishedYes
EventConference on Medical Imaging - Computer-Aided Diagnosis 2014 - San Diego, United States of America
Duration: 18 Feb 201420 Feb 2014
https://www.spiedigitallibrary.org/conference-proceedings-of-spie/9035.toc (Proceedings)

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume9035
ISSN (Print)1605-7422

Conference

ConferenceConference on Medical Imaging - Computer-Aided Diagnosis 2014
Country/TerritoryUnited States of America
CitySan Diego
Period18/02/1420/02/14
Internet address

Keywords

  • Breast cancer
  • Computer-aided diagnosis of mammograms
  • Feature selection
  • Pattern classification

Cite this