Interval breast cancers in the Screening Mammography Program of British Columbia: analysis and classification.

Burhenne, H J; Burhenne, Linda Warren; Goldberg, Franklin; Hislop, T. Gregory; Worth, Ann; Rebbeck, P.; Kan, Lisa

doi:10.2214/ajr.162.5.8165983

Cited by 113 publications

(47 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The number of calcifications/cm 2 is small (value 0); the volume (in cm 3 ) is small (value 1); the total number of calcifications is large (value 1); the irregularity in the shape of individual calcifications is marked (value 1); the variation in the shape of calcifications is marked (value 1); the variation in size of the calcifications is marked (value 1); the variation in density of the calcifications is mild (value 0); the density of the calcifications is mild (value 0); ductal orientation is not present (value 0); comparison with previous exam is "pro cancer/biopsy" (value 1); associated findings are "pro cancer/biopsy" (value 1).…”

Section: Reliability Criteriamentioning

confidence: 99%

“…Please note that the grade "small" was deliberately coded differently for the number of calcifications/cm 2 and the volume (in cm 3 ). This step allowed us to take advantage of the monotonicity property (as described later), which is of critical importance to the effectiveness of our method.…”

Section: Reliability Criteriamentioning

confidence: 99%

“…x 1 ϭ (w 1 , w 2 , w 3 ) ϭ w 2 ٚ w 1 w 3 , [3] x 2 ϭ ( y 1 , y 2 , y 3 , y 4 , y 5 ) ϭ y 1 ٚ y 2 ٚ y 3 y 4 y 5 .…”

Section: Logical Discriminant Functionsunclassified

“…The most effective tool in the battle against breast cancer is screening mammography. However, several retrospective analyses have found diagnostic error rates ranging from 20 to 43% (2,3). Also, of the breast biopsies performed due to suspicious mammograms, 70-89% will be found benign (4).…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

The Reliability Issue of Computer-Aided Breast Cancer Diagnosis

Kovalerchuk

Triantaphyllou

Ruiz

et al. 2000

Computers and Biomedical Research

View full text Add to dashboard Cite

This paper introduces a number of reliability criteria for computer-aided diagnostic systems for breast cancer. These criteria are then used to analyze some published neural network systems. It is also shown that the property of monotonicity for the data is rather natural in this medical domain, and it has the potential to significantly improve the reliability of breast cancer diagnosis while maintaining a general representation power. A central part of this paper is devoted to the representation/narrow vicinity hypothesis, upon which existing computer-aided diagnostic methods heavily rely. The paper also develops a framework for determining the validity of this hypothesis. The same framework can be used to construct a diagnostic procedure with improved reliability. ᭧

show abstract

Section: Reliability Criteriamentioning

confidence: 99%

Section: Reliability Criteriamentioning

confidence: 99%

“…x 1 ϭ (w 1 , w 2 , w 3 ) ϭ w 2 ٚ w 1 w 3 , [3] x 2 ϭ ( y 1 , y 2 , y 3 , y 4 , y 5 ) ϭ y 1 ٚ y 2 ٚ y 3 y 4 y 5 .…”

Section: Logical Discriminant Functionsunclassified

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

The Reliability Issue of Computer-Aided Breast Cancer Diagnosis

Kovalerchuk

Triantaphyllou

Ruiz

et al. 2000

Computers and Biomedical Research

View full text Add to dashboard Cite

show abstract

“…Unfortunately, the sensitivity of mammography is rather limited for detecting small lesions, and its specificity is even lower. 2,3 Over the last 7 years, we have developed a 3-dimensional (3D) fixed coordinate sonographic mammography system, 4 termed "highresolution ultrasonic transmission tomography" (HUTT), that seeks to improve the early detection of small malignant lesions and reduce the number of false-positive (FP) outcomes. The novel use of submillimeter ultrasound transducers and the pioneering use of multiband analysis of the first arrival pulses of the received signals (called "snippets") represent the key innovations of the HUTT system that endow it with 3D high-resolution and tissue differentiation capabilities.…”

mentioning

confidence: 99%

Differentiation of Cancerous Lesions in Excised Human Breast Specimens Using Multiband Attenuation Profiles From Ultrasonic Transmission Tomography

Jeong

Shin

et al. 2008

Journal of Ultrasound in Medicine

View full text Add to dashboard Cite

Objective. This study examines the tissue differentiation capability of the recently developed high-resolution ultrasonic transmission tomography (HUTT) system in the context of differentiating between benign and malignant tissue types in mastectomy specimens. Methods. Eight mastectomy patients provided breast specimens with benign and malignant lesions. The specimens were scanned by the HUTT system with a pair of either 8-or 4-MHz transducers. Multiband HUTT images over the frequency range from 2 to 10 MHz provide characteristic profiles of frequencydependent attenuation, termed "multiband profiles," at individual pixels. These features are classified through a novel algorithm of "segment-wise classification" that identifies the disjoint segments of various tissue types and subsequently classifies them into respective diagnostic categories using a measure of proximity to the respective multiband profile templates that have been previously obtained from reference data. Results. We preformed intraspecimen and interspecimen analyses of 108 slices from 8 mastectomy specimens for which "ground truth" was provided by pathology reports. The average performance indices for 2-way classification (malignant versus nonmalignant tissue) in these intraspecimen (interspecimen) specimen studies were found to be sensitivity of 81.9% (89.6%), specificity of 92.9% (92.1%), and accuracy of 89.2% (89.4%), whereas the indices for the 3-way classification were moderately lower. Conclusions. The results have shown the potential of the HUTT technology for reliable differentiation of cancerous lesions from benign changes and normal tissue in mastectomy specimens using frequencydependent ultrasound attenuation profiles.

show abstract