Optimization of breast mass classification using sequential forward floating selection (SFFS) and a support vector machine (SVM) model.
Optimization of breast mass classification using sequential forward floating selection (SFFS) and a support vector machine (SVM) model.
复制标题
DOI：
10.1007/s11548-014-0992-1
复制
发表时间：
2014-11
影响因子：
3
通讯作者：
Zheng, Bin
中科院分区：
文献类型：
--
作者：
Tan, Maxine;Pu, Jiantao;Zheng, Bin
提高放射科医生在恶性和良性乳腺病变分类方面的表现对于提高癌症检测灵敏度和减少假阳性召回非常重要。为此，开发计算机辅助诊断（CAD）方案近年来引起了研究兴趣。在这项研究中，我们研究了一种用于乳腺肿块分类任务的新特征选择方法。我们最初根据质量形状、毛刺、对比度、脂肪或钙化的存在、纹理、等密度和其他形态特征计算了 181 个图像特征。从这个大型图像特征池中，我们使用基于顺序前向浮动选择（SFFS）的特征选择方法来选择相关特征，并使用为分类任务训练的支持向量机（SVM）模型分析其性能。在包含 600 个良性和 600 个恶性肿块感兴趣区域 (ROI) 的数据库中，我们使用十倍交叉验证方法进行了研究。仅在训练子集上进行 SVM 参数的特征选择和优化。分类任务的受试者工作特征曲线下面积 (AUC) = 0.805±0.012。结果还表明，基于 SFFS 的算法在 10 次迭代中最常选择的特征是与肿块形状、等密度和脂肪存在相关的特征，这与放射科医生在临床环境中经常使用的肿块分类图像特征一致。该研究还表明，从投影乳房 X 光照片中准确计算肿块针状特征很困难，并且由于良性肿块区域内的组织重叠，无法很好地执行肿块分类任务。总之，这项全面的特征分析研究为优化计算机质量分类方案提供了新的有价值的信息，这些信息可能在未来的临床实践中作为“第二读者”有用。
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 (CAD) 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. 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 (ROIs), we performed the study using a ten-fold cross-validation method. Feature selection and optimization of the SVM parameters were conducted on the training subsets only. The area under the receiver operating characteristic curve (AUC) = 0.805±0.012 was obtained for the classification task. The results also showed that the most frequently-selected features by the SFFS-based algorithm in 10-fold 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. 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.
登录
查看更多内容
影响因子：
3.8
作者：
HUO, ZM;GIGER, ML;SCHMIDT, RA
通讯作者：
SCHMIDT, RA
影响因子：
4.8
作者：
Jiang, Luan;Song, Enmin;Zheng, Bin
通讯作者：
Zheng, Bin
影响因子：
19.7
作者：
Gur, D;Stalder, JS;Rockette, HE
通讯作者：
Rockette, HE
影响因子：
19.7
作者：
KEGELMEYER, WP;PRUNEDA, JM;NIPPER, ML
通讯作者：
NIPPER, ML
影响因子：
4.8
作者：
Chang, YH;Wang, XH;Gur, D
通讯作者：
Gur, D