School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China.
Guangdong Province Key Laboratory of Computational Science, Sun Yat-sen University, Guangzhou, China.
Med Phys. 2022 Jun;49(6):3749-3768. doi: 10.1002/mp.15631. Epub 2022 Apr 5.
In 2020, breast cancer becomes the most leading diagnosed cancer all over the world. The burden is increasing in the prevention and treatment of breast cancer. Accurately detecting breast lesions in screening images is important for early detection of cancer. Architectural distortion (AD) is one of the breast lesions that need to be detected.
To develop a deep-learning-based computer-aided detection (CADe) model for AD in digital breast tomosynthesis (DBT). This model uses the superior-inferior directional context of DBT and anatomic prior knowledge to reduce false positive (FP). It can identify some negative samples that cannot be distinguished by deep learning features.
The proposed CADe model consists of three steps. In the first step, a deep learning detection network detects two-dimensional (2D) candidates of ADs in DBT slices with the inputs preprocessed by Gabor filters and convergence measure. In the second step, three-dimensional (3D) candidates are obtained by stacking 2D candidates along superior-inferior direction. In the last step, FP reduction for 3D candidates is implemented based on superior-inferior directional context and anatomic prior knowledge of breast. DBT data from 99 cases with AD were used as the training set to train the CADe model, and data from 208 cases were used as an independent test set (including 108 cases with AD and 100 cases without AD as the control group). The free-response receiver operating characteristic and mean true positive fraction (MTPF) in the range of 0.05-2.0 FPs per volume are used to evaluate the model.
Compared with the baseline model based on convergence measure, our proposed method demonstrates significant improvement (MTPF: 0.2826 ± 0.0321 vs. 0.6640 ± 0.0399). Results of an ablation study show that our proposed context- and anatomy-based FP reduction methods improve the detection performance. The number of FPs per DBT volume reduces from 2.47 to 1.66 at 80% sensitivity after employing these two schemes.
The deep learning model demonstrates practical value for AD detection. The results indicate that introducing superior-inferior directional context and anatomic prior knowledge into model can indeed reduce FPs and improve the performance of CADe model.
2020 年，乳腺癌成为全球最常见的诊断癌症。乳腺癌的防治负担日益加重。在筛查图像中准确检测乳腺病变对于癌症的早期发现至关重要。结构扭曲（AD）是需要检测的乳腺病变之一。
开发一种基于深度学习的计算机辅助检测（CADe）模型，用于数字乳腺断层合成（DBT）中的 AD。该模型利用 DBT 的上下方向上下文和解剖学先验知识来减少假阳性（FP）。它可以识别一些无法通过深度学习特征区分的负样本。
所提出的 CADe 模型由三个步骤组成。在第一步中，深度学习检测网络使用经过 Gabor 滤波器和收敛度量预处理的输入来检测 DBT 切片中的二维（2D）AD 候选物。在第二步中，通过沿上下方向堆叠 2D 候选物来获得 3D 候选物。在最后一步，基于上下方向上下文和乳腺解剖学先验知识对 3D 候选物进行 FP 减少。使用 99 例 AD 病例的 DBT 数据作为训练集来训练 CADe 模型，使用 208 例数据作为独立测试集（包括 108 例 AD 病例和 100 例作为对照组的无 AD 病例）。使用 0.05-2.0 FP/体积范围内的自由响应接收器工作特性和平均真阳性分数（MTPF）来评估模型。
与基于收敛度量的基线模型相比，我们提出的方法显示出显著的改善（MTPF：0.2826±0.0321 与 0.6640±0.0399）。消融研究的结果表明，我们提出的基于上下文和解剖学的 FP 减少方法提高了检测性能。在采用这两种方案后，DBT 体积的 FP 数量从 2.47 减少到 1.66，灵敏度为 80%。
深度学习模型在 AD 检测方面具有实际价值。结果表明，将上下方向上下文和解剖学先验知识引入模型确实可以减少 FP 并提高 CADe 模型的性能。
