Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
Improved method for automatic identification of lung regions on chest radiographs
Autore:
Li, LH; Zheng, Y; Kallergi, M; Clark, RA;
Indirizzi:
Univ S Florida, Coll Med, H Lee Moffitt Canc Ctr & Res Inst, Dept Radiol, Tampa, FL 33612 USA Univ S Florida Tampa FL USA 33612 Inst, Dept Radiol, Tampa, FL 33612 USA
Titolo Testata:
ACADEMIC RADIOLOGY
fascicolo: 7, volume: 8, anno: 2001,
pagine: 629 - 638
SICI:
1076-6332(200107)8:7<629:IMFAIO>2.0.ZU;2-3
Fonte:
ISI
Lingua:
ENG
Soggetto:
COMPUTER-AIDED DIAGNOSIS; IMAGE FEATURE ANALYSIS; SEGMENTATION;
Keywords:
computers, diagnostic aid; lung, radiography;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
Clinical Medicine
Citazioni:
12
Recensione:
Indirizzi per estratti:
Indirizzo: Li, LH Univ S Florida, Coll Med, H Lee Moffitt Canc Ctr & Res Inst, Dept Radiol, 12901 Bruce B Downs Blvd,Box 17, Tampa, FL 33612 USA Univ S Florida 12901 Bruce B Downs Blvd,Box 17 Tampa FL USA 33612 A
Citazione:
L.H. Li et al., "Improved method for automatic identification of lung regions on chest radiographs", ACAD RADIOL, 8(7), 2001, pp. 629-638

Abstract

Rationale and Objectives. The authors performed this study to evaluate an algorithm developed to help identify lungs on chest radiographs. Materials and Methods. Forty clinical posteroanterior chest radiographs obtained in adult patients were digitized to 12-bit gray-scale resolution. Inthe proposed algorithm, the authors simplified the current approach of edge detection with derivatives by using only the first derivative of the horizontal and/or vertical image profiles. In addition to the derivative method, pattern classification and image feature analysis were used to determine the region of interest and lung boundaries. Instead of using the traditional curve-fitting method to delineate the lung, the authors applied an iterative contour-smoothing algorithm to each of the four detected boundary segments (costal, mediastinal, lung apex, and hemidiaphragm edges) to form a smooth lung boundary. Results. The algorithm had an average accuracy of 96.0% for the right lungand 95.2% for the left lung and was especially useful in the delineation of hemidiaphragm edges. In addition, it took about 0.775 second per image toidentify the lung boundaries, which is much faster than that of other algorithms noted in the literature. Conclusion. The computer-generated segmentation results can be used directly in the detection and compensation of rib structures and in lungs nodule detection.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 28/09/20 alle ore 13:22:42