Mass Description for Breast Cancer Recognition

Cheikhouhou, Imene; Djemal, Khalifa; Maaref, Hichem

doi:10.1007/978-3-642-13681-8_67

Cited by 1 publication

(1 citation statement)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This evaluation is in order to preserve pertinent descriptors and to propose improvements for the others. We have proposed microcalcification evaluation that brings to improve the rectangularity formulation [15] and hence, the classification accuracy.…”

Section: Introductionmentioning

confidence: 99%

Empirical Descriptors Evaluation for Mass Malignity Recognition

Sellami-Masmoudi¹,

Maaref²,

Cheikhrouhou³

et al. 2009

Proceedings of the 1st International Workshop on Medical Image Analysis and Description for Diagnosis Systems

View full text Add to dashboard Cite

In breast cancer field, radiologists and researchers aim to discriminate between masses due to benign breast diseases and tumors due to breast cancer. In general, benign masses have circumscribed contours, whereas, malignant tumors appear with spiculated and irregular boundaries. Recently, we proposed an original mass description based on three morphological mass descriptors, which are SPICULation (SPICUL), Contour Derivative Variation (CDV) and Skeleton End Points (SEP). In this paper, we detail an empirical mass evaluation based on these morphological descriptors which intend to distinguish between malignant and benign lesions. This evaluation is, first, assured by following descriptors evolution in two independent data sets: Alberta and MIAS. Secondly, for these two data sets, the Receiver Operating Characteristics (ROC) analysis is applied. A comparison between the classic use of Area (A) and Perimeter (P) descriptors only, and a combination with our three original evaluated descriptors is done. Obtained results proves that classification accuracy of the descriptors combination including: SPICUL, SEP, CDV, A and P outperforms that of the classic descriptors: A and P. Indeed, our original mass description provides the best Area under ROC Az = 0.986 for Alberta data set and Az = 0.9792 for the MIAS data set. Therefore, we affirm that our three original descriptors can serve as good shape descriptors for the benign-versus-malignant classification of breast masses on mammograms.

show abstract

Section: Introductionmentioning

confidence: 99%