Maxine Tan1, Jiantao Pu2, Bin Zheng3,2. 1. School of Electrical and Computer Engineering, University of Oklahoma, Norman, OK, 73019, USA. Maxine.Y.Tan-1@ou.edu. 2. Department of Radiology, University of Pittsburgh, Pittsburgh, PA, 15213, USA. 3. School of Electrical and Computer Engineering, University of Oklahoma, Norman, OK, 73019, USA.
Abstract
PURPOSE: Improving radiologists' performance in classification between malignant and benign breast lesions is important to increase cancer detection sensitivity and reduce false-positive recalls. For this purpose, developing computer-aided diagnosis schemes has been attracting research interest in recent years. In this study, we investigated a new feature selection method for the task of breast mass classification. METHODS: We initially computed 181 image features based on mass shape, spiculation, contrast, presence of fat or calcifications, texture, isodensity, and other morphological features. From this large image feature pool, we used a sequential forward floating selection (SFFS)-based feature selection method to select relevant features and analyzed their performance using a support vector machine (SVM) model trained for the classification task. On a database of 600 benign and 600 malignant mass regions of interest, we performed the study using a tenfold cross-validation method. Feature selection and optimization of the SVM parameters were conducted on the training subsets only. RESULTS: The area under the receiver operating characteristic curve [Formula: see text] was obtained for the classification task. The results also showed that the most frequently selected features by the SFFS-based algorithm in tenfold iterations were those related to mass shape, isodensity, and presence of fat, which are consistent with the image features frequently used by radiologists in the clinical environment for mass classification. The study also indicated that accurately computing mass spiculation features from the projection mammograms was difficult, and failed to perform well for the mass classification task due to tissue overlap within the benign mass regions. CONCLUSION: In conclusion, this comprehensive feature analysis study provided new and valuable information for optimizing computerized mass classification schemes that may have potential to be useful as a "second reader" in future clinical practice.
PURPOSE: Improving radiologists' performance in classification between malignant and benign breast lesions is important to increase cancer detection sensitivity and reduce false-positive recalls. For this purpose, developing computer-aided diagnosis schemes has been attracting research interest in recent years. In this study, we investigated a new feature selection method for the task of breast mass classification. METHODS: We initially computed 181 image features based on mass shape, spiculation, contrast, presence of fat or calcifications, texture, isodensity, and other morphological features. From this large image feature pool, we used a sequential forward floating selection (SFFS)-based feature selection method to select relevant features and analyzed their performance using a support vector machine (SVM) model trained for the classification task. On a database of 600 benign and 600 malignant mass regions of interest, we performed the study using a tenfold cross-validation method. Feature selection and optimization of the SVM parameters were conducted on the training subsets only. RESULTS: The area under the receiver operating characteristic curve [Formula: see text] was obtained for the classification task. The results also showed that the most frequently selected features by the SFFS-based algorithm in tenfold iterations were those related to mass shape, isodensity, and presence of fat, which are consistent with the image features frequently used by radiologists in the clinical environment for mass classification. The study also indicated that accurately computing mass spiculation features from the projection mammograms was difficult, and failed to perform well for the mass classification task due to tissue overlap within the benign mass regions. CONCLUSION: In conclusion, this comprehensive feature analysis study provided new and valuable information for optimizing computerized mass classification schemes that may have potential to be useful as a "second reader" in future clinical practice.
Entities:
Keywords:
Breast cancer; Computer-aided diagnosis of mammograms; Feature selection; Pattern classification
Authors: Yuan-Hsiang Chang; Xiao-Hui Wang; Lara A Hardesty; Thomas S Chang; William R Poller; Walter F Good; David Gur Journal: Acad Radiol Date: 2002-08 Impact factor: 3.173
Authors: Reyer Zwiggelaar; Susan M Astley; Caroline R M Boggis; Christopher J Taylor Journal: IEEE Trans Med Imaging Date: 2004-09 Impact factor: 10.048
Authors: Bin Zheng; Joseph K Leader; Gordon Abrams; Betty Shindel; Victor Catullo; Walter F Good; David Gur Journal: AJR Am J Roentgenol Date: 2004-03 Impact factor: 3.959
Authors: Bin Zheng; Joseph K Leader; Gordon S Abrams; Amy H Lu; Luisa P Wallace; Glenn S Maitz; David Gur Journal: Med Phys Date: 2006-09 Impact factor: 4.071
Authors: P Tiwari; P Prasanna; L Wolansky; M Pinho; M Cohen; A P Nayate; A Gupta; G Singh; K J Hatanpaa; A Sloan; L Rogers; A Madabhushi Journal: AJNR Am J Neuroradiol Date: 2016-09-15 Impact factor: 3.825
Authors: Morteza Heidari; Seyedehnafiseh Mirniaharikandehei; Wei Liu; Alan B Hollingsworth; Hong Liu; Bin Zheng Journal: IEEE Trans Med Imaging Date: 2019-10-09 Impact factor: 10.048