Department of Electrical and Computer Engineering, University of Washington, Seattle, WA, USA.
Medical & Imaging Informatics, Department of Radiological Sciences, David Geffen School of Medicine at UCLA, Los Angeles, CA, USA.
Comput Biol Med. 2022 Jul;146:105504. doi: 10.1016/j.compbiomed.2022.105504. Epub 2022 Apr 8.
Amorphous calcifications noted on mammograms (i.e., small and indistinct calcifications that are difficult to characterize) are associated with high diagnostic uncertainty, often leading to biopsies. Yet, only 20% of biopsied amorphous calcifications are cancer. We present a quantitative approach for distinguishing between benign and actionable (high-risk and malignant) amorphous calcifications using a combination of local textures, global spatial relationships, and interpretable handcrafted expert features.
Our approach was trained and validated on a set of 168 2D full-field digital mammography exams (248 images) from 168 patients. Within these 248 images, we identified 276 image regions with segmented amorphous calcifications and a biopsy-confirmed diagnosis. A set of local (radiomic and region measurements) and global features (distribution and expert-defined) were extracted from each image. Local features were grouped using an unsupervised k-means clustering algorithm. All global features were concatenated with clustered local features and used to train a LightGBM classifier to distinguish benign from actionable cases.
On the held-out test set of 60 images, our approach achieved a sensitivity of 100%, specificity of 35%, and a positive predictive value of 38% when the decision threshold was set to 0.4. Given that all of the images in our test set resulted in a recommendation of a biopsy, the use of our algorithm would have identified 15 images (25%) that were benign, potentially reducing the number of breast biopsies.
Quantitative analysis of full-field digital mammograms can extract subtle shape, texture, and distribution features that may help to distinguish between benign and actionable amorphous calcifications.
乳腺 X 光片中出现的不定形钙化（即小而不明显的钙化，难以定性）与高度诊断不确定性相关，通常导致活检。然而，只有 20%的活检不定形钙化是癌症。我们提出了一种使用局部纹理、全局空间关系和可解释的手工制作的专家特征来区分良性和可操作（高风险和恶性）不定形钙化的定量方法。
我们的方法在一组来自 168 名患者的 168 个 2D 全视野数字乳腺摄影检查（248 张图像）上进行了训练和验证。在这 248 张图像中，我们确定了 276 个带有分割不定形钙化和活检证实诊断的图像区域。从每张图像中提取了一组局部（放射组学和区域测量值）和全局特征（分布和专家定义的特征）。局部特征使用无监督的 k-均值聚类算法进行分组。所有全局特征都与聚类的局部特征连接，并用于训练 LightGBM 分类器，以区分良性和可操作病例。
在 60 张保留的测试图像集中，当决策阈值设置为 0.4 时，我们的方法在 100%的敏感性、35%的特异性和 38%的阳性预测值方面表现良好。鉴于我们测试集中的所有图像都建议进行活检，我们算法可以识别出 15 张（25%）良性图像，从而可能减少乳腺活检的数量。
全视野数字乳腺 X 光片的定量分析可以提取细微的形状、纹理和分布特征，有助于区分良性和可操作的不定形钙化。
Zotero 插件
