Quantitative evaluation of automatic methods for lesions detection in breast ultrasound images

Ultrasound (US) is a useful diagnostic tool to distinguish benign from malignant breast masses, providing more detailed evaluation in dense breasts. Due to the subjectivity in the images interpretation, computer-aid diagnosis (CAD) schemes have been developed, increasing the mammography analysis process to include ultrasound images as complementary exams. As one of most important task in the evaluation of this kind of images is the mass detection and its contours interpretation, automated segmentation techniques have been investigated in order to determine a quite suitable procedure to perform such an analysis. Thus, the main goal in this work is investigating the effect of some processing techniques used to provide information on the determination of suspicious breast lesions as well as their accurate boundaries in ultrasound images. In tests, 80 phantom and 50 clinical ultrasound images were preprocessed, and 5 segmentation techniques were tested. By using quantitative evaluation metrics the results were compared to a reference image delineated by an experienced radiologist. A self-organizing map artificial neural network has provided the most relevant results, demonstrating high accuracy and low error rate in the lesions representation, corresponding hence to the segmentation process for US images in our CAD scheme under tests.

[1]  W. Moon,et al.  Computer‐aided diagnosis using morphological features for classifying breast lesions on ultrasound , 2008, Ultrasound in obstetrics & gynecology : the official journal of the International Society of Ultrasound in Obstetrics and Gynecology.

[2]  Tryphon T. Georgiou,et al.  A new distribution metric for image segmentation , 2008, SPIE Medical Imaging.

[3]  Shengzhou Xu,et al.  Segmentation of the breast region in mammograms using marker-controlled watershed transform , 2010, The 2nd International Conference on Information Science and Engineering.

[4]  Fabrice Mériaudeau,et al.  Lesion Segmentation in Breast Sonography , 2010, Digital Mammography / IWDM.

[5]  Rosalina Abdul Salam,et al.  Adaptation of K-Means Algorithm for Image Segmentation , 2009 .

[6]  Karem D. Marcomini,et al.  Nodules Segmentation in Breast Ultrasound using the Artificial Neural Network Self-Organizing Map , 2022 .

[7]  Liliane Ventura,et al.  A prototype of mammography CADx scheme integrated to imaging quality evaluation techniques , 2011, Medical Imaging.

[8]  M. A. von Kruger,et al.  Breast ultrasound phantom for image segmentation assessment , 2009, 2009 IEEE International Ultrasonics Symposium.

[9]  Yan Xu,et al.  Image decomposition based ultrasound image segmentation by using fuzzy clustering , 2009, 2009 IEEE Symposium on Industrial Electronics & Applications.

[10]  Eran A. Edirisinghe,et al.  Object Boundary Detection in Ultrasound Images , 2006, The 3rd Canadian Conference on Computer and Robot Vision (CRV'06).

[11]  Tom Fawcett,et al.  An introduction to ROC analysis , 2006, Pattern Recognit. Lett..

[12]  Jeong-Won Lee,et al.  Automatic lesion detection and segmentation algorithm on 2D breast ultrasound images , 2011, Medical Imaging.

[13]  G. Ravindran,et al.  A complete automatic region growing method for segmentation of masses on ultrasound images , 2006, 2006 International Conference on Biomedical and Pharmaceutical Engineering.