Deep learning classification of deep ultraviolet fluorescence images toward intra-operative margin assessment in breast cancer.
Deep learning classification of deep ultraviolet fluorescence images toward intra-operative margin assessment in breast cancer.
复制标题
DOI：
10.3389/fonc.2023.1179025
复制
发表时间：
2023
影响因子：
4.7
通讯作者：
Ye, Dong Hye
中科院分区：
文献类型：
--
作者：
To, Tyrell;Lu, Tongtong;Jorns, Julie M.;Patton, Mollie;Schmidt, Taly Gilat;Yen, Tina;Yu, Bing;Ye, Dong Hye
保乳手术的目的是去除所有癌细胞，同时尽量减少健康组织的损失。为了确保在完全切除肿瘤和保护健康组织之间取得平衡，有必要在手术过程中评估切除标本的边缘。深紫外（DUV）荧光扫描显微镜提供了切除组织的快速全表面成像（WSI），恶性和正常/良性组织之间的显着对比。DUV图像的术中边缘评估将受益于自动乳腺癌分类方法。深度学习在乳腺癌分类方面已经显示出有希望的结果，但有限的DUV图像数据集带来了过度拟合的挑战，以训练一个强大的网络。为了克服这一挑战，DUV-WSI图像被分成小块，并使用预先训练的卷积神经网络提取特征，然后，梯度提升树对这些特征进行训练，以进行块级分类。集成学习方法合并块级分类结果和区域重要性，以确定边缘状态。一种可解释的人工智能方法计算区域重要性值。所提出的方法的能力，以确定DUV WSI是95%的准确度高。100%的灵敏度表明，该方法可以有效地检测恶性病例。该方法还可以准确地定位包含恶性或正常/良性组织的区域。所提出的方法在DUV乳腺手术样本上的性能优于标准的深度学习分类方法。结果表明，它可以用来提高分类性能和识别癌区域更有效。
Breast-conserving surgery is aimed at removing all cancerous cells while minimizing the loss of healthy tissue. To ensure a balance between complete resection of cancer and preservation of healthy tissue, it is necessary to assess themargins of the removed specimen during the operation. Deep ultraviolet (DUV) fluorescence scanning microscopy provides rapid whole-surface imaging (WSI) of resected tissues with significant contrast between malignant and normal/benign tissue. Intra-operative margin assessment with DUV images would benefit from an automated breast cancer classification method. Deep learning has shown promising results in breast cancer classification, but the limited DUV image dataset presents the challenge of overfitting to train a robust network. To overcome this challenge, the DUV-WSI images are split into small patches, and features are extracted using a pre-trained convolutional neural network—afterward, a gradient-boosting tree trains on these features for patch-level classification. An ensemble learning approach merges patch-level classification results and regional importance to determine the margin status. An explainable artificial intelligence method calculates the regional importance values. The proposed method’s ability to determine the DUV WSI was high with 95% accuracy. The 100% sensitivity shows that the method can detect malignant cases efficiently. The method could also accurately localize areas that contain malignant or normal/benign tissue. The proposed method outperforms the standard deep learning classification methods on the DUV breast surgical samples. The results suggest that it can be used to improve classification performance and identify cancerous regions more effectively.
登录
查看更多内容
影响因子：
16.9
作者：
Kummerow, Kristy L.;Du, Liping;Hooks, Mary A.
通讯作者：
Hooks, Mary A.
DOI：
10.1016/j.jamcollsurg.2019.02.051
发表时间：
2019-07-01
影响因子：
5.2
作者：
Kantor, Olga;Pesce, Catherine;Yao, Katharine
通讯作者：
Yao, Katharine
影响因子：
4.6
作者：
Shokry A;Khalil M;Ibrahim H;Soliman M;Ebrahim S
通讯作者：
Ebrahim S
影响因子：
3.4
作者：
Lu, T. O. N. G. T. O. N. G.;Jorns, Julie M.;Yu, B. I. N. G.
通讯作者：
Yu, B. I. N. G.
DOI：
10.1038/s43856-021-00013-3
发表时间：
2021
期刊：
COMMUNICATIONS MEDICINE
影响因子：
--
作者：
Gamble, Paul;Jaroensri, Ronnachai;Wang, Hongwu;Tan, Fraser;Moran, Melissa;Brown, Trissia;Flament-Auvigne, Isabelle;Rakha, Emad A.;Toss, Michael;Dabbs, David J.;Regitnig, Peter;Olson, Niels;Wren, James H.;Robinson, Carrie;Corrado, Greg S.;Peng, Lily H.;Liu, Yun;Mermel, Craig H.;Steiner, David F.;Chen, Po-Hsuan Cameron
通讯作者：
Chen, Po-Hsuan Cameron