Premium
Computer‐aided detection of breast cancers using Haar‐like features in automated 3D breast ultrasound
Author(s) -
Tan Tao,
Mordang JanJurre,
Zelst Jan,
Grivegnée André,
GubernMérida Albert,
Melendez Jaime,
Mann Ritse M.,
Zhang Wei,
Platel Bram,
Karssemeijer Nico
Publication year - 2015
Publication title -
medical physics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.473
H-Index - 180
eISSN - 2473-4209
pISSN - 0094-2405
DOI - 10.1118/1.4914162
Subject(s) - false positive paradox , haar like features , computer science , artificial intelligence , pattern recognition (psychology) , breast cancer , breast ultrasound , feature (linguistics) , receiver operating characteristic , stage (stratigraphy) , false positive rate , voxel , mammography , cancer , medicine , machine learning , paleontology , linguistics , face detection , facial recognition system , biology , philosophy
Purpose: Automated 3D breast ultrasound (ABUS) has gained interest in breast imaging. Especially for screening women with dense breasts, ABUS appears to be beneficial. However, since the amount of data generated is large, the risk of oversight errors is substantial. Computer aided detection (CADe) may be used as a second reader to prevent oversight errors. When CADe is used in this fashion, it is essential that small cancers are detected, while the number of false positive findings should remain acceptable. In this work, the authors improve their previously developed CADe system in the initial candidate detection stage. Methods: The authors use a large number of 2D Haar‐like features to differentiate lesion structures from false positives. Using a cascade of GentleBoost classifiers that combines these features, a likelihood score, highly specific for small cancers, can be efficiently computed. The likelihood scores are added to the previously developed voxel features to improve detection. Results: The method was tested in a dataset of 414 ABUS volumes with 211 cancers. Cancers had a mean size of 14.72 mm. Free‐response receiver operating characteristic analysis was performed to evaluate the performance of the algorithm with and without using the aforementioned Haar‐like feature likelihood scores. After the initial detection stage, the number of missed cancer was reduced by 18.8% after adding Haar‐like feature likelihood scores. Conclusions: The proposed technique significantly improves our previously developed CADe system in the initial candidate detection stage.