Rectal Cancer Treatment Management: Deep-Learning Neural Network Based on Photoacoustic Microscopy Image Outperforms Histogram-Feature-Based Classification.
Rectal Cancer Treatment Management: Deep-Learning Neural Network Based on Photoacoustic Microscopy Image Outperforms Histogram-Feature-Based Classification.
复制标题
直肠癌治疗管理：基于光声显微镜图像的深度学习神经网络优于基于直方图 - 特征分类。
DOI：
10.3389/fonc.2021.715332
复制
发表时间：
2021
影响因子：
4.7
通讯作者：
Zhu Q
中科院分区：
文献类型：
--
作者：
Leng X;Amidi E;Kou S;Cheema H;Otegbeye E;Chapman WJ;Mutch M;Zhu Q
我们已经开发了一种新型的光声显微镜/超声（PAM/US）内窥镜成像治疗后的直肠癌放疗和化疗后残留肿瘤的手术管理。与深度学习卷积神经网络（CNN）配对，PAM图像准确地区分了病理完全反应者（pCR）和不完全反应者。然而，与传统的基于直方图特征的分类器相比，CNN的作用需要进一步探索。在这项工作中，我们在24个离体标本和10个体内患者检查中比较了CNN模型与广义线性模型（GLM）的性能。从PAM和US图像的直方图中提取一阶统计特征来训练、验证和测试GLM模型，而PAM和US图像直接用于训练、验证和测试CNN模型。PAM-CNN模型的AUC为0.96（95% CI：0.95-0.98），优于使用峰度AUC为0.82（95% CI：0.82-0.83）的最佳PAM-GLM模型。我们还发现，来自光声数据的CNN和GLM都优于单独使用超声的那些。我们的结论是，深度学习神经网络与光声图像配对是确定经治疗的人类直肠中是否存在残留癌症的最佳分析框架。
We have developed a novel photoacoustic microscopy/ultrasound (PAM/US) endoscope to image post-treatment rectal cancer for surgical management of residual tumor after radiation and chemotherapy. Paired with a deep-learning convolutional neural network (CNN), the PAM images accurately differentiated pathological complete responders (pCR) from incomplete responders. However, the role of CNNs compared with traditional histogram-feature based classifiers needs further exploration. In this work, we compare the performance of the CNN models to generalized linear models (GLM) across 24 ex vivo specimens and 10 in vivo patient examinations. First order statistical features were extracted from histograms of PAM and US images to train, validate and test GLM models, while PAM and US images were directly used to train, validate, and test CNN models. The PAM-CNN model performed superiorly with an AUC of 0.96 (95% CI: 0.95-0.98) compared to the best PAM-GLM model using kurtosis with an AUC of 0.82 (95% CI: 0.82-0.83). We also found that both CNN and GLMs derived from photoacoustic data outperformed those utilizing ultrasound alone. We conclude that deep-learning neural networks paired with photoacoustic images is the optimal analysis framework for determining presence of residual cancer in the treated human rectum.
登录
查看更多内容
DOI：
10.1146/annurev-bioeng-071516-044442
发表时间：
2017-06-21
影响因子：
9.7
作者：
Shen D;Wu G;Suk HI
通讯作者：
Suk HI
影响因子：
4.3
作者：
Cong, Bing;Qiu, Chen;Liu, Chengbo
通讯作者：
Liu, Chengbo
影响因子：
19.7
作者：
Leng, Xiandong;Uddin, K. M. Shihab;Zhu, Quing
通讯作者：
Zhu, Quing
使用灵敏紧凑的手持式经直肠阵列光声探头对犬前列腺进行体内经直肠成像，用于前列腺癌的早期诊断
影响因子：
3.4
作者：
Liu, Chengbo;Xing, Muyue;Song, Liang
通讯作者：
Song, Liang
影响因子：
5.9
作者：
Beets-Tan RGH;Lambregts DMJ;Maas M;Bipat S;Barbaro B;Curvo-Semedo L;Fenlon HM;Gollub MJ;Gourtsoyianni S;Halligan S;Hoeffel C;Kim SH;Laghi A;Maier A;Rafaelsen SR;Stoker J;Taylor SA;Torkzad MR;Blomqvist L
通讯作者：
Blomqvist L