dorsal/arxiv
View SchemaAn Automatic System to Discriminate Malignant from Benign Massive Lesions on Mammograms
| Authors | A. Retico, P. Delogu, M. E. Fantacci, P. Kasae |
|---|---|
| Categories | |
| ArXiv ID | physics/0701053 |
| URL | https://arxiv.org/abs/physics/0701053 |
| DOI | 10.1016/j.nima.2006.08.093 |
| Journal | Nuclear Instruments and Methods in Physics Research A 569 (2006) 596-600 |
Abstract
Mammography is widely recognized as the most reliable technique for early detection of breast cancers. Automated or semi-automated computerized classification schemes can be very useful in assisting radiologists with a second opinion about the visual diagnosis of breast lesions, thus leading to a reduction in the number of unnecessary biopsies. We present a computer-aided diagnosis (CADi) system for the characterization of massive lesions in mammograms, whose aim is to distinguish malignant from benign masses. The CADi system we realized is based on a three-stage algorithm: a) a segmentation technique extracts the contours of the massive lesion from the image; b) sixteen features based on size and shape of the lesion are computed; c) a neural classifier merges the features into an estimated likelihood of malignancy. A dataset of 226 massive lesions (109 malignant and 117 benign) has been used in this study. The system performances have been evaluated terms of the receiver-operating characteristic (ROC) analysis, obtaining A_z = 0.80+-0.04 as the estimated area under the ROC curve.
{
"annotation_id": "131faa9e-2722-4e81-a875-817b7879f030",
"date_created": "2026-03-02T18:01:14.917000Z",
"date_modified": "2026-03-02T18:01:14.917000Z",
"file_hash": "e218fe5a6681184ea634c0a99049caad2b829e3bb9010be58e947ef2f1809434",
"private": false,
"record": {
"abstract": "Mammography is widely recognized as the most reliable technique for early\ndetection of breast cancers. Automated or semi-automated computerized\nclassification schemes can be very useful in assisting radiologists with a\nsecond opinion about the visual diagnosis of breast lesions, thus leading to a\nreduction in the number of unnecessary biopsies. We present a computer-aided\ndiagnosis (CADi) system for the characterization of massive lesions in\nmammograms, whose aim is to distinguish malignant from benign masses. The CADi\nsystem we realized is based on a three-stage algorithm: a) a segmentation\ntechnique extracts the contours of the massive lesion from the image; b)\nsixteen features based on size and shape of the lesion are computed; c) a\nneural classifier merges the features into an estimated likelihood of\nmalignancy. A dataset of 226 massive lesions (109 malignant and 117 benign) has\nbeen used in this study. The system performances have been evaluated terms of\nthe receiver-operating characteristic (ROC) analysis, obtaining A_z =\n0.80+-0.04 as the estimated area under the ROC curve.",
"arxiv_id": "physics/0701053",
"authors": [
"A. Retico",
"P. Delogu",
"M. E. Fantacci",
"P. Kasae"
],
"categories": [
"physics.med-ph"
],
"doi": "10.1016/j.nima.2006.08.093",
"journal_ref": "Nuclear Instruments and Methods in Physics Research A 569 (2006)\n 596-600",
"title": "An Automatic System to Discriminate Malignant from Benign Massive Lesions on Mammograms",
"url": "https://arxiv.org/abs/physics/0701053"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "f06284a5-91cc-440f-9d59-56c92bb41389",
"id": "arXiv Dataset IDs",
"type": "Model",
"variant": "snapshot-2026-03-01",
"version": "0.1.0"
},
"user_id": 1000002
}