Multi-instance learning for mass retrieval in digitized mammograms

Breast cancer is one of the most common malignant tumors in women. In mammogram retrieval system, the query mass is ambiguity and difficult to be described because in which the lesion and the normal tissue are physically adjacent. If the query mass can be processed as an image bag, then the ambiguity can be tackled by multi-instance learning (MIL) techniques. In this paper, we presented a preliminary study of MIL for mass retrieval in digitized mammograms, and proposed three image bag generators named J-Bag, A-Bag and K-Bag, respectively. Diverse Density (DD), EM-DD and BP-MIP were applied as MIL algorithms for mass retrieval. Experimental study was carried out on DDSM database and another database in which images were collected from the Zhejiang Cancer Hospital in China. Preliminary experiments showed that the MIL techniques can be applied to the problem of mass retrieval in digitized mammograms and the proposed bag generators A-Bag and K-Bag can achieve more efficient results than the existing bag generator SBN.

• Publication year

  2012

• Venue

  Medical Imaging

• Publication date

  2012-02-23

• Fields of study

  Medicine, Computer Science, Engineering

• Identifiers
  DOI 10.1117/12.911675
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Computer-Aided Detection and Diagnosis of Breast Cancer With Mammography: Recent Advances

  2009cited by this paper
• Image retrieval: Ideas, influences, and trends of the new age

  2008cited by this paper
• Automated detection of masses in digital mammograms based on pyramid

  2007cited by this paper
• Multi-Instance Learning Based Web Mining

  2005cited by this paper
• A method to improve visual similarity of breast masses for an interactive computer-aided diagnosis environment.

  2005cited by this paper
• Multi-Instance Learning : A Survey

  2004cited by this paper
• Spatial color descriptor for image retrieval and video segmentation

  2003cited by this paper
• Neural Networks for Multi-Instance Learning

  2002influential reference
• EM-DD: An Improved Multiple-Instance Learning Technique

  2001influential reference
• Unsupervised Segmentation of Color-Texture Regions in Images and Video

  2001influential reference
• Computational modelling of visual attention

  2001cited by this paper
• A Model of Saliency-Based Visual Attention for Rapid Scene Analysis

  1998influential reference
• Multiple-Instance Learning for Natural Scene Classification

  1998influential reference
• Learning from Ambiguity

  1998cited by this paper
• Solving the Multiple Instance Problem with Axis-Parallel Rectangles

  1997cited by this paper

• Multi-scale region selection network in deep features for full-field mammogram classification

  2024cites this paper
• Machine Learning Empowering Personalized Medicine: A Comprehensive Review of Medical Image Analysis Methods

  2023cites this paper
• Detection of Breast Cancer From Whole Slide Histopathological Images Using Deep Multiple Instance CNN

  2020cites this paper
• Mammographic Mass Retrieval Using Multi-view Information and Laplacian Score Feature Selection

  2020cites this paper
• Multiple-Instance Learning for Medical Image and Video Analysis

  2017influential citation
• Anomaly classification in digital mammography based on multiple-instance learning

  2017cites this paper
• Multiple-Instance Learning for Anomaly Detection in Digital Mammography

  2016cites this paper
• A Survey of Computer-aided Detection of Breast Cancer with Mammography

  2016cites this paper
• Multiple-instance learning for breast cancer detection in mammograms

  2015cites this paper