当前位置: X-MOL 学术Comput. Math. Method Med. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Using Convolutional Neural Network with Cheat Sheet and Data Augmentation to Detect Breast Cancer in Mammograms
Computational and Mathematical Methods in Medicine Pub Date : 2020-10-28 , DOI: 10.1155/2020/9523404
Saleem Z Ramadan 1
Affiliation  

The American Cancer Society expected to diagnose 276,480 new cases of invasive breast cancer in the USA and 48,530 new cases of noninvasive breast cancer among women in 2020. Early detection of breast cancer, followed by appropriate treatment, can reduce the risk of death from this disease. DL through CNN can assist imaging specialists in classifying the mammograms accurately. Accurate classification of mammograms using CNN needs a well-trained CNN by a large number of labeled mammograms. Unfortunately, a large number of labeled mammograms are not always available. In this study, a novel procedure to aid imaging specialists in detecting normal and abnormal mammograms has been proposed. The procedure supplied the designed CNN with a cheat sheet for some classical attributes extracted from the ROI and an extra number of labeled mammograms through data augmentation. The cheat sheet aided the CNN through encoding easy-to-recognize artificial patterns in the mammogram before passing it to the CNN, and the data augmentation supported the CNN with more labeled data points. Fifteen runs of 4 different modified datasets taken from the MIAS dataset were conducted and analyzed. The results showed that the cheat sheet, along with data augmentation, enhanced CNN’s accuracy by at least 12.2% and enhanced the precision of the CNN by at least 2.2. The mean accuracy, sensitivity, and specificity obtained using the proposed procedure were 92.1, 91.4, and 96.8, respectively, while the average area under the ROC curve was 94.9.

中文翻译:


使用带有备忘单和数据增强的卷积神经网络来检测乳房 X 光检查中的乳腺癌



美国癌症协会预计,2020 年美国将诊断出 276,480 例新的浸润性乳腺癌病例,以及 48,530 例女性非浸润性乳腺癌新病例。早期发现乳腺癌并进行适当的治疗,可以降低这种疾病的死亡风险。通过 CNN 的深度学习可以帮助成像专家对乳房 X 光照片进行准确分类。使用 CNN 对乳房 X 线照片进行准确分类需要通过大量标记的乳房 X 线照片来训练有素的 CNN。不幸的是,大量标记的乳房X光照片并不总是可用。在这项研究中,提出了一种新的程序来帮助成像专家检测正常和异常的乳房X线照片。该过程为设计的 CNN 提供了一份备忘单,用于从 ROI 中提取一些经典属性,并通过数据增强提供额外数量的标记乳房 X 光照片。备忘单通过在将乳房 X 光照片传递给 CNN 之前对易于识别的人工模式进行编码来帮助 CNN,并且数据增强通过更多标记的数据点来支持 CNN。对取自 MIAS 数据集的 4 个不同修改数据集进行了 15 次运行并进行了分析。结果表明,备忘单与数据增强一起将 CNN 的准确性提高了至少 12.2%,并将 CNN 的精度提高了至少 2.2。使用所提出的程序获得的平均准确度、灵敏度和特异性分别为 92.1、91.4 和 96.8,而 ROC 曲线下的平均面积为 94.9。
更新日期:2020-10-30
down
wechat
bug