dorsal/arxiv
View SchemaCADe tools for early detection of breast cancer
| Authors | U. Bottigli, P. G. Cerello, P. Delogu, M. E. Fantacci, F. Fauci, G. Forni, B. Golosio, A. Lauria, E. Lopez, R. Magro, G. L. Masala, P. Oliva, R. Palmiero, G. Raso, A. Retico, S. Stumbo, S. Tangaro |
|---|---|
| Categories | |
| ArXiv ID | physics/0410082 |
| URL | https://arxiv.org/abs/physics/0410082 |
Abstract
A breast neoplasia is often marked by the presence of microcalcifications and massive lesions in the mammogram: hence the need for tools able to recognize such lesions at an early stage. Our collaboration, among italian physicists and radiologists, has built a large distributed database of digitized mammographic images and has developed a Computer Aided Detection (CADe) system for the automatic analysis of mammographic images and installed it in some Italian hospitals by a GRID connection. Regarding microcalcifications, in our CADe digital mammogram is divided into wide windows which are processed by a convolution filter; after a self-organizing map analyzes each window and produces 8 principal components which are used as input of a neural network (FFNN) able to classify the windows matched to a threshold. Regarding massive lesions we select all important maximum intensity position and define the ROI radius. From each ROI found we extract the parameters which are used as input in a FFNN to distinguish between pathological and non-pathological ROI. We present here a test of our CADe system, used as a second reader and a comparison with another (commercial) CADe system.
{
"annotation_id": "53350859-8c23-434f-a4d3-f7f77c279eb7",
"date_created": "2026-03-02T18:00:53.419000Z",
"date_modified": "2026-03-02T18:00:53.419000Z",
"file_hash": "bedf63e06d6b4de7f5906cf2d08f0dd1d78efa98b5de9555dd054fba901a6723",
"private": false,
"record": {
"abstract": "A breast neoplasia is often marked by the presence of microcalcifications and\nmassive lesions in the mammogram: hence the need for tools able to recognize\nsuch lesions at an early stage. Our collaboration, among italian physicists and\nradiologists, has built a large distributed database of digitized mammographic\nimages and has developed a Computer Aided Detection (CADe) system for the\nautomatic analysis of mammographic images and installed it in some Italian\nhospitals by a GRID connection. Regarding microcalcifications, in our CADe\ndigital mammogram is divided into wide windows which are processed by a\nconvolution filter; after a self-organizing map analyzes each window and\nproduces 8 principal components which are used as input of a neural network\n(FFNN) able to classify the windows matched to a threshold. Regarding massive\nlesions we select all important maximum intensity position and define the ROI\nradius. From each ROI found we extract the parameters which are used as input\nin a FFNN to distinguish between pathological and non-pathological ROI. We\npresent here a test of our CADe system, used as a second reader and a\ncomparison with another (commercial) CADe system.",
"arxiv_id": "physics/0410082",
"authors": [
"U. Bottigli",
"P. G. Cerello",
"P. Delogu",
"M. E. Fantacci",
"F. Fauci",
"G. Forni",
"B. Golosio",
"A. Lauria",
"E. Lopez",
"R. Magro",
"G. L. Masala",
"P. Oliva",
"R. Palmiero",
"G. Raso",
"A. Retico",
"S. Stumbo",
"S. Tangaro"
],
"categories": [
"physics.med-ph"
],
"title": "CADe tools for early detection of breast cancer",
"url": "https://arxiv.org/abs/physics/0410082"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "8168ed65-32ec-4d93-b9f7-d4525c254457",
"id": "arXiv Dataset IDs",
"type": "Model",
"variant": "snapshot-2026-03-01",
"version": "0.1.0"
},
"user_id": 1000002
}