RECORD
GPCALMA: A Tool For Mammography With A GRID-Connected Distributed Database
Medical Physics · Submitted 13 Oct 2004
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim GPCALMA has built a large distributed database of digitised mammographic images (about 5500 images corresponding to 1650 patients) and developed a CAD (Computer Aided Detection) software which is integrated in a station that can also be used for acquire new images, as archive and to perform statistical analysis.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
The GPCALMA (Grid Platform for Computer Assisted Library for MAmmography) collaboration involves several departments of physics, INFN sections, and italian hospitals. The aim of this collaboration is developing a tool that can help radiologists in early detection of breast cancer. GPCALMA has built a large distributed database of digitised mammographic images (about 5500 images corresponding to 1650 patients) and developed a CAD (Computer Aided Detection) software which is integrated in a station that can also be used for acquire new images, as archive and to perform statistical analysis. The images are completely described: pathological ones have a consistent characterization with radiologist's diagnosis and histological data, non pathological ones correspond to patients with a follow up at least three years. The distributed database is realized throught the connection of all the hospitals and research centers in GRID tecnology. In each hospital local patients digital images are stored in the local database. Using GRID connection, GPCALMA will allow each node to work on distributed database data as well as local database data. Using its database the GPCALMA tools perform several analysis. A texture analysis, i.e. an automated classification on adipose, dense or glandular texture, can be provided by the system. GPCALMA software also allows classification of pathological features, in particular massive lesions analysis and microcalcification clusters analysis. The performance of the GPCALMA system will be presented in terms of the ROC (Receiver Operating Characteristic) curves. The results of GPCALMA system as "second reader" will also be presented.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | The GPCALMA (Grid Platform for Computer Assisted Library for MAmmography) collaboration involves several departments of physics, INFN sections, and italian hospitals. | background 0.92 | 0.29 | 0.02 | asserted 1.00 |
| s1 | The aim of this collaboration is developing a tool that can help radiologists in early detection of breast cancer. | background 0.70 | 0.28 | 0.04 | asserted 0.98 |
| s2 | GPCALMA has built a large distributed database of digitised mammographic images (about 5500 images corresponding to 1650 patients) and developed a CAD (Computer Aided Detection) software which is integrated in a station that can also be used for acquire new images, as archive and to perform statistical analysis. | contribution 0.77 | 0.91 | 0.10 | asserted 1.00 |
| s3 | The images are completely described: pathological ones have a consistent characterization with radiologist's diagnosis and histological data, non pathological ones correspond to patients with a follow up at least three years. | method 0.97 | 0.72 | 0.03 | asserted 0.99 |
| s4 | The distributed database is realized throught the connection of all the hospitals and research centers in GRID tecnology. | method 0.98 | 0.80 | 0.04 | asserted 1.00 |
| s5 | In each hospital local patients digital images are stored in the local database. | method 0.99 | 0.52 | 0.02 | asserted 1.00 |
| s6 | Using GRID connection, GPCALMA will allow each node to work on distributed database data as well as local database data. | method 0.88 | 0.50 | 0.05 | hedged possibility 0.53 |
| s7 | Using its database the GPCALMA tools perform several analysis. | method 0.68 | 0.60 | 0.04 | asserted 0.99 |
| s8 | A texture analysis, i.e. an automated classification on adipose, dense or glandular texture, can be provided by the system. | method 0.65 | 0.73 | 0.04 | hedged possibility 0.68 |
| s9 | GPCALMA software also allows classification of pathological features, in particular massive lesions analysis and microcalcification clusters analysis. | method 0.52 | 0.79 | 0.05 | asserted 0.96 |
| s10 | The performance of the GPCALMA system will be presented in terms of the ROC (Receiver Operating Characteristic) curves. | method 0.68 | 0.74 | 0.07 | asserted 0.86 |
| s11 | The results of GPCALMA system as "second reader" will also be presented. | contribution 0.48 | 0.78 | 0.10 | asserted 0.84 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
The GPCALMA (Grid Platform for Computer Assisted Library for MAmmography) collaboration involves several departments of physics, INFN sections, and italian hospitals. The aim of this collaboration is developing a tool that can help radiologists in early detection of breast cancer. GPCALMA has built a large distributed database of digitised mammographic images (about 5500 images corresponding to 1650 patients) and developed a CAD (Computer Aided Detection) software which is integrated in a station that can also be used for acquire new images, as archive and to perform statistical analysis. The images are completely described: pathological ones have a consistent characterization with radiologist's diagnosis and histological data, non pathological ones correspond to patients with a follow up at least three years. The distributed database is realized throught the connection of all the hospitals and research centers in GRID tecnology. In each hospital local patients digital images are stored in the local database. Using GRID connection, GPCALMA will allow each node to work on distributed database data as well as local database data. Using its database the GPCALMA tools perform several analysis. A texture analysis, i.e. an automated classification on adipose, dense or glandular texture, can be provided by the system. GPCALMA software also allows classification of pathological features, in particular massive lesions analysis and microcalcification clusters analysis. The performance of the GPCALMA system will be presented in terms of the ROC (Receiver Operating Characteristic) curves. The results of GPCALMA system as "second reader" will also be presented.
Human review
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.