1972
DOI: 10.1002/1097-0142(197210)30:4<1025::aid-cncr2820300425>3.0.co;2-7
|View full text |Cite
|
Sign up to set email alerts
|

Breast lesion classification by computer and xeroradiograph

Abstract: One hundred and twenty pathologically proven lesions were digitized by computer and recorded on film. Four measures of malignancy, calcification, spiculation, roughness, and area‐to‐perimeter ratio then were mathematically extracted from the digitized xeroradiograph lesions. Using three methods of classification, these were identified by the computer as malignant and benign. Two radiologists then classified the photographed lesions. Comparison of the computer classification and the radiologists' classification… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
9
1
8

Year Published

1974
1974
2013
2013

Publication Types

Select...
5
2

Relationship

0
7

Authors

Journals

citations
Cited by 66 publications
(18 citation statements)
references
References 6 publications
0
9
1
8
Order By: Relevance
“…In 1967, the difficulty of viewing and analyzing large amounts of data in screening mammograms was recognized, and computer-aided image analysis algorithms were suggested [3]. There were also early attempts to identify lesions such as malignant tumors using detection algorithms [4].…”
Section: Introductionmentioning
confidence: 99%
“…In 1967, the difficulty of viewing and analyzing large amounts of data in screening mammograms was recognized, and computer-aided image analysis algorithms were suggested [3]. There were also early attempts to identify lesions such as malignant tumors using detection algorithms [4].…”
Section: Introductionmentioning
confidence: 99%
“…Respecto a los trabajos previos al FIWDM dirigidos hacia la detecci on y an alisis de masas o tumores 2,108,69,13,73,137,62], el promedio alcanzado en la detecci on es del 90%, pero al igual que en microcalci caciones todav a es necesario reducir el n umero de falsos positivos y contrastar los resultados con bases de datos mucho m as extensas de las utilizadas en las publicaciones. En las masas presentes en mamograf a la taxonom a que se puede realizar consiste en dos clases, las bien de nidas 13, 69] y las mal de nidas 62].…”
Section: Detecci On De Masasunclassified
“…Neto et al 31] implementan su trabajo con Morfolog a Matem atica, concretamente con la herramienta l nea divisoria de aguas 2 . Justi ca su elecci on en que es una herramienta potente de segmentaci on que no necesita de ajustes o par ametros heur sticos.…”
Section: Tiwdmunclassified
See 2 more Smart Citations