A New Ensemble Learning Approach for Microcalcification Clusters Detection

Abstract

<span style="font-family: "Times New Roman"; font-size: 10pt; mso-fareast-font-family: 宋体; mso-ansi-language: EN-US; mso-fareast-language: EN-US; mso-bidi-language: AR-SA;" lang="EN-US">A new microcalcification clusters (MCs) detection method in mammograms is proposed, which is based on a new ensemble learning method. </span><span style="font-family: "Times New Roman"; font-size: 10pt; mso-fareast-font-family: 宋体; mso-ansi-language: EN-US; mso-fareast-language: ZH-CN; mso-bidi-language: AR-SA;" lang="EN-US">In this paper, , we propose a bagging with adaptive cost adjustment ensemble algorithm; and a new ensemble strategy, called boosting with relevance feedback, by embedding the relevance feedback technique into the heterogenous base learner training, and meanwhile carefully design an effectively systematical feedback scheme, which promise the preventing of overfitting. </span><span style="font-family: "Times New Roman"; font-size: 10pt; mso-fareast-font-family: 宋体; mso-ansi-language: EN-US; mso-fareast-language: EN-US; mso-bidi-language: AR-SA;" lang="EN-US">The ground truth of MCs is assumed to be known as a priori. In our algorithm, each MCs is enhanced by a well designed high-pass filter. Then the 116 dimentional image features are extracted by the feature extractor and fed to the ensemble decision model. In image feature domain, the MCs detection procedure is formulated as a supervised learning and classification problem, and the trained ensemble model is used as a classifier to decide the presence of MCs or not. Case study on microcalcification clusters detection for breast cancer diagnosis illustrates that the proposed algorithm is not only effective but also efficient.</span

Methods Used in Computer-Aided Diagnosis for Breast Cancer Detection Using Mammograms: A Review

“…is is followed by another iteration of computing weights and this sequence is repeated until a termination condition is reached. e most popular version of boosting techniques is AdaBoost (stands for Adaptive Boosting) algorithm [207][208][209] which classifies the data instance as a weighted sum of the output of other weak classifiers. It is considered adaptive because the weights of the weak classifiers are changed adaptively based on their performance.…”

Clasificación automática de nódulos mamográficos basada en fusión de información visual multi-vista

“…• Base de datos DDSM: la base de datos digitalizada para tamizaje de mamografía (DDSM) [52] es una base de datos con imágenes mamográficas ampliamente usada en esta área de investigación como punto de referencia de evaluación [53,54,55]. Esta base de datos de libre acceso está constituida por imágenes digitalizadas de películas mamográficas con su infor- 43.5μm píxeles y con un rango dinámico de intensidades de = 4096 niveles de tono de grises.…”