{
  "annotation_id": "ad6e03b6-e476-4ebf-a2a6-e7c40a604688",
  "date_created": "2026-03-02T18:00:46.916000Z",
  "date_modified": "2026-03-02T18:00:46.916000Z",
  "file_hash": "aa2198a832a077b21976f79dcf6e48492363c0a912efd6707fe1143421cdc115",
  "private": false,
  "record": {
    "abstract": "The CALMA (Computer Assisted Library for MAmmography) project is a five years\nplan developed in a physics research frame in collaboration between INFN\n(Istituto Nazionale di Fisica Nucleare) and many Italian hospitals. At present\na large database of digitized mammographic images (more than 6000) was\ncollected and a software based on neural network algorithms for the search of\nsuspicious breast lesions was developed. Two tools are available: a\nmicrocalcification clusters hunter, based on supervised and unsupervised\nfeedforward neural network, and a massive lesions searcher, based on a hibrid\napproach. Both the algorithms analyzed preprocessed digitized images by high\nfrequency filters. Clinical tests were performed to evaluate sensitivity and\nspecificity of the system, considering the system as alone and as secon reader.\nResults show that the system is ready to be implemented by medical industry.\nThe CALMA project, just ended, has its natural development in the GPCALMA (Grid\nPlatform for CALMA) project, where distributed users join common resources\n(images, tools, statistical analysis).",
    "arxiv_id": "physics/0307099",
    "authors": [
      "A. Lauria",
      "R. Palmiero",
      "G. Forni",
      "P. Cerello",
      "B. Golosio",
      "F. Fauci",
      "R. Magro",
      "G. Raso",
      "S. Tangaro",
      "P. L. Indovina"
    ],
    "categories": [
      "physics.med-ph"
    ],
    "doi": "10.1016/j.nima.2003.11.031",
    "title": "The CALMA system: an artificial neural network method for detecting   masses and microcalcifications in digitized mammograms",
    "url": "https://arxiv.org/abs/physics/0307099"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "dbc2f30c-2608-477b-a691-5c6e65b7e70b",
    "id": "arXiv Dataset IDs",
    "type": "Model",
    "variant": "snapshot-2026-03-01",
    "version": "0.1.0"
  },
  "user_id": 1000002
}