Department of Radiological Sciences, University of California, Irvine, California; Department of Radiation Oncology, Rutgers-Cancer Institute of New Jersey, Robert Wood Johnson Medical School, New Brunswick, New Jersey.
Department of Radiological Sciences, University of California, Irvine, California.
Acad Radiol. 2023 Sep;30 Suppl 2(Suppl 2):S161-S171. doi: 10.1016/j.acra.2022.12.038. Epub 2023 Jan 10.
Diagnosis of breast cancer on MRI requires, first, the identification of suspicious lesions; second, the characterization to give a diagnostic impression. We implemented Mask Reginal-Convolutional Neural Network (R-CNN) to detect abnormal lesions, followed by ResNet50 to estimate the malignancy probability.
Two datasets were used. The first set had 176 cases, 103 cancer, and 73 benign. The second set had 84 cases, 53 cancer, and 31 benign. For detection, the pre-contrast image and the subtraction images of left and right breasts were used as inputs, so the symmetry could be considered. The detected suspicious area was characterized by ResNet50, using three DCE parametric maps as inputs. The results obtained using slice-based analyses were combined to give a lesion-based diagnosis.
In the first dataset, 101 of 103 cancers were detected by Mask R-CNN as suspicious, and 99 of 101 were correctly classified by ResNet50 as cancer, with a sensitivity of 99/103 = 96%. 48 of 73 benign lesions and 131 normal areas were identified as suspicious. Following classification by ResNet50, only 16 benign and 16 normal areas remained as malignant. The second dataset was used for independent testing. The sensitivity was 43/53 = 81%. Of the total of 121 identified non-cancerous lesions, only 6 of 31 benign lesions and 22 normal tissues were classified as malignant.
ResNet50 could eliminate approximately 80% of false positives detected by Mask R-CNN. Combining Mask R-CNN and ResNet50 has the potential to develop a fully-automatic computer-aided diagnostic system for breast cancer on MRI.
在 MRI 上诊断乳腺癌，首先需要识别可疑病变；其次，对病变进行特征描述，给出诊断印象。我们采用 Mask Reginal-Convolutional Neural Network (R-CNN) 来检测异常病变，然后采用 ResNet50 来估计恶性概率。
使用了两个数据集。第一个数据集包含 176 例，其中 103 例为癌症，73 例为良性。第二个数据集包含 84 例，其中 53 例为癌症，31 例为良性。在检测方面，使用了左、右乳房的对比前图像和减影图像作为输入，从而可以考虑对称性。使用 ResNet50 对检测到的可疑区域进行特征描述，使用三个 DCE 参数图作为输入。使用基于切片的分析得到的结果进行组合，给出基于病变的诊断。
在第一个数据集中，Mask R-CNN 检测到 103 例癌症中的 101 例为可疑，ResNet50 将 101 例中的 99 例正确分类为癌症，敏感性为 99/103 = 96%。73 例良性病变和 131 个正常区域被识别为可疑。经 ResNet50 分类后，只有 16 例良性和 16 例正常区域仍为恶性。第二个数据集用于独立测试。敏感性为 43/53 = 81%。在总共 121 例非癌性病变中，仅 31 例良性病变中的 6 例和 22 例正常组织被归类为恶性。
ResNet50 可以消除 Mask R-CNN 检测到的大约 80%的假阳性。将 Mask R-CNN 和 ResNet50 相结合，有可能开发出一种用于 MRI 乳腺癌的全自动计算机辅助诊断系统。
