当前位置: X-MOL 学术Comput. Biol. 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.)
A transfer learning with structured filter pruning approach for improved breast cancer classification on point-of-care devices
Computers in Biology and Medicine ( IF 7.7 ) Pub Date : 2021-04-30 , DOI: 10.1016/j.compbiomed.2021.104432
Tejalal Choudhary 1 , Vipul Mishra 1 , Anurag Goswami 1 , Jagannathan Sarangapani 2
Affiliation  

Background and objective

A significant progress has been made in automated medical diagnosis with the advent of deep learning methods in recent years. However, deploying a deep learning model for mobile and small-scale, low-cost devices is a major bottleneck. Further, breast cancer is more prevalent currently, and ductal carcinoma being its most common type. Although many machine/deep learning methods have already been investigated, still, there is a need for further improvement.

Method

This paper proposes a novel deep convolutional neural network (CNN) based transfer learning approach complemented with structured filter pruning for histopathological image classification, and to bring down the run-time resource requirement of the trained deep learning models. In the proposed method, first, the less important filters are pruned from the convolutional layers and then the pruned models are trained on the histopathological image dataset.

Results

We performed extensive experiments using three popular pre-trained CNNs, VGG19, ResNet34, and ResNet50. With VGG19 pruned model, we achieved an accuracy of 91.25% outperforming earlier methods on the same dataset and architecture while reducing 63.46% FLOPs. Whereas, with the ResNet34 pruned model, the accuracy increases to 91.80% with 40.63% fewer FLOPs. Moreover, with the ResNet50 model, we achieved an accuracy of 92.07% with 30.97% less FLOPs.

Conclusion

The experimental results reveal that the pre-trained model's performance complemented with filter pruning exceeds original pre-trained models. Another important outcome of the research is that the pruned model with reduced resource requirements can be deployed in point-of-care devices for automated diagnosis applications with ease.



中文翻译:

通过结构化过滤器修剪方法进行的转移学习,可改善即时医疗设备上的乳腺癌分类

背景和目标

近年来,随着深度学习方法的出现,在自动化医学诊断中取得了重大进展。但是,为移动和小型低成本设备部署深度学习模型是一个主要瓶颈。此外,乳腺癌目前更普遍,导管癌是其最常见的类型。尽管已经研究了许多机器/深度学习方法,但是仍需要进一步的改进。

方法

本文提出了一种新颖的基于深度卷积神经网络(CNN)的转移学习方法,并结合结构化滤波器修剪对组织病理学图像进行分类,从而降低了训练有素的深度学习模型的运行时资源需求。在提出的方法中,首先从卷积层中修剪不太重要的过滤器,然后在组织病理学图像数据集上训练修剪的模型。

结果

我们使用三种流行的经过预先训练的CNN,VGG19,ResNet34和ResNet50进行了广泛的实验。使用VGG19修剪模型,在相同的数据集和体系结构上,我们的精度达到了91.25%,优于早期方法,同时减少了63.46%的FLOP。而使用ResNet34修剪模型,精度提高到91.80%,FLOP减少了40.63%。此外,使用ResNet50模型,我们的精度达到92.07%,而FLOP减少了30.97%。

结论

实验结果表明,预训练模型的性能与过滤修剪相辅相成,超过了原始的预训练模型。该研究的另一个重要成果是,可以将资源需求减少的修剪模型轻松部署在即时诊断设备中,以用于自动诊断应用。

更新日期:2021-05-06
down
wechat
bug