Gastric precancerous diseases classification using CNN with a concise model.

Gastric precancerous diseases classification using CNN with a concise model.
复制标题

使用CNN和简洁模型对胃癌前期疾病进行分类

DOI:
10.1371/journal.pone.0185508
复制
发表时间:
2017
期刊:
影响因子:
3.7
通讯作者:
Si J
Si J
中科院分区:
综合性期刊3区
文献类型:
--
作者:
Zhang X;Hu W;Chen F;Liu J;Yang Y;Wang L;Duan H;Si J

文献摘要

参考文献

被引文献

相似文献

胃癌前病变(GPD)如果误诊,可能会恶化为早期胃癌,因此帮助医生准确、快速地识别GPD非常重要。在本文中,我们使用卷积神经网络(CNN)实现了3类GPD的分类,即息肉,糜烂和溃疡,并使用称为胃癌前疾病网络(GPDNet)的简洁模型。GPDNet引入了SqueezeNet的fire模块,将模型大小和参数减少了约10倍,同时提高了快速分类的速度。为了用更少的参数保持分类精度,我们提出了一种称为迭代强化学习(IRL)的创新方法。在从头开始训练GPDNet之后,我们应用IRL来微调值接近0的参数,然后将修改后的模型作为下一次训练的预训练模型。结果表明,迭代学习算法经过6次迭代后,精度提高了9%左右。我们的GPDNet的最终分类准确率为88.90%,这是有希望的临床GPD识别。
Gastric precancerous diseases (GPD) may deteriorate into early gastric cancer if misdiagnosed, so it is important to help doctors recognize GPD accurately and quickly. In this paper, we realize the classification of 3-class GPD, namely, polyp, erosion, and ulcer using convolutional neural networks (CNN) with a concise model called the Gastric Precancerous Disease Network (GPDNet). GPDNet introduces fire modules from SqueezeNet to reduce the model size and parameters about 10 times while improving speed for quick classification. To maintain classification accuracy with fewer parameters, we propose an innovative method called iterative reinforced learning (IRL). After training GPDNet from scratch, we apply IRL to fine-tune the parameters whose values are close to 0, and then we take the modified model as a pretrained model for the next training. The result shows that IRL can improve the accuracy about 9% after 6 iterations. The final classification accuracy of our GPDNet was 88.90%, which is promising for clinical GPD recognition.
DOI: 10.1007/s10120-011-0085-6
发表时间: 2011-10
期刊: GASTRIC CANCER
影响因子: 7.4
作者:
Isobe, Yoh;Nashimoto, Atsushi;Akazawa, Kohei;Oda, Ichiro;Hayashi, Kenichi;Miyashiro, Isao;Katai, Hitoshi;Tsujitani, Shunichi;Kodera, Yasuhiro;Seto, Yasuyuki;Kaminishi, Michio
通讯作者: Kaminishi, Michio
DOI: 10.1109/tmi.2016.2521800
发表时间: 2016-05-01
影响因子: 10.6
作者:
Miao, Shun;Wang, Z. Jane;Liao, Rui
通讯作者: Liao, Rui
将从频率分布中提取的进化信息与基于序列的内核相结合以进行蛋白质远程同源性检测
DOI: 10.1093/bioinformatics/btt709
发表时间: 2014-02-15
期刊: BIOINFORMATICS
影响因子: 5.8
作者:
Liu, Bin;Zhang, Deyuan;Chou, Kuo-Chen
通讯作者: Chou, Kuo-Chen
DOI: 10.1109/tmi.2016.2535302
发表时间: 2016-05-01
影响因子: 10.6
作者:
Tajbakhsh, Nima;Shin, Jae Y.;Liang, Jianming
通讯作者: Liang, Jianming
DOI: 10.1109/tmi.2016.2536809
发表时间: 2016-05-01
影响因子: 10.6
作者:
Setio, Arnaud Arindra Adiyoso;Ciompi, Francesco;van Ginneken, Bram
通讯作者: van Ginneken, Bram