A deeply supervised residual network for HEp-2 cell classification via cross-modal transfer learning

Lei, Haijun; Han, Tao; Zhou, Feng; Yu, Zhen; Qin, Jing; Elazab, Ahmed; Lei, Baiying

doi:10.1016/j.patcog.2018.02.006

Cited by 102 publications

(64 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, the results do not suggest that larger datasets necessarily lead to better results -the smallest and the largest datasets lead to the best performances equally often. Lei et al (2018) address HEp-2 cell classification in the ICPR 2016 challenge as the target task (Lovell et al, 2016). Compared models include a ResNet pretrained on ImageNet, and a ResNet pretrained on data from the earlier edition of the challenge, ICPR 2012 (Foggia et al, 2013).…”

Section: Comparisons Of Source Datasetsmentioning

confidence: 99%

“…Similarity of datasets is often used to hypothesize about which source data will be best, but definitions of similarity differ. For example, Menegola et al (2017) discuss similarity in terms of visual similarities of the images, Lei et al (2018) discuss similarity in terms of feature representations. In computer vision, other definitions may be used -for example, Azizpour et al (2015) investigate transfer from ImageNet and Places to 15 other datasets, and define similarity in terms of the number and variety of the classes.…”

Section: Opportunities For Further Researchmentioning

confidence: 99%

See 1 more Smart Citation

Cats or CAT scans: Transfer learning from natural or medical image source data sets?

Cheplygina

2019

Current Opinion in Biomedical Engineering

View full text Add to dashboard Cite

Transfer learning is a widely used strategy in medical image analysis. Instead of only training a network with a limited amount of data from the target task of interest, we can first train the network with other, potentially larger source datasets, creating a more robust model. The source datasets do not have to be related to the target task. For a classification task in lung CT images, we could use both head CT images, or images of cats, as the source. While head CT images appear more similar to lung CT images, the number and diversity of cat images might lead to a better model overall. In this survey we review a number of papers that have performed similar comparisons. Although the answer to which strategy is best seems to be "it depends", we discuss a number of research directions we need to take as a community, to gain more understanding of this topic.

show abstract

Section: Comparisons Of Source Datasetsmentioning

confidence: 99%

Section: Opportunities For Further Researchmentioning

confidence: 99%

Cats or CAT scans: Transfer learning from natural or medical image source data sets?

Cheplygina

2019

Current Opinion in Biomedical Engineering

View full text Add to dashboard Cite

show abstract

“…The main advantage of transfer learning is the improvement of classifier accuracy and the acceleration of the learning process [33]. Previous studies in the literature have demonstrated that transfer learning also has the potential to reduce the problem of overfitting [34] [35]. Although the dataset is not the same, low-level features from the source dataset are generic features e.g.…”

Section: Pre-trained Dcnn Feature Extractorsmentioning

confidence: 99%

Breast Cancer Diagnosis with Transfer Learning and Global Pooling

Kassani

Wesolowski

et al. 2019

2019 International Conference on Information and Communication Technology Convergence (ICTC)

View full text Add to dashboard Cite

Breast cancer is one of the most common causes of cancer-related death in women worldwide. Early and accurate diagnosis of breast cancer may significantly increase the survival rate of patients. In this study, we aim to develop a fully automatic, deep learning-based, method using descriptor features extracted by Deep Convolutional Neural Network (DCNN) models and pooling operation for the classification of hematoxylin and eosin stain (H&E) histological breast cancer images provided as a part of the International Conference on Image Analysis and Recognition (ICIAR) 2018 Grand Challenge on BreAst Cancer Histology (BACH) Images. Different data augmentation methods are applied to optimize the DCNN performance. We also investigated the efficacy of different stain normalization methods as a pre-processing step. The proposed network architecture using a pre-trained Xception model yields 92.50% average classification accuracy.

show abstract

“…Transfer learning allows the use of labeled or, more importantly, unlabeled data to train an algorithm, and then train again on a small corpus of labeled data. For example, in any kind of image classification task, it is now commonly accepted to use a pre-trained model trained on a large labeled dataset such as Imagenet [15], and then again train that model on a smaller labeled dataset of the final task (known as fine-tuning) [16,17]. This is an example where a large corpus of labeled data is being used to augment the performance in a task where labeled data are scarce.…”

Section: Introductionmentioning

confidence: 99%

Transfer learning improves antibiotic resistance class prediction

Hamid

Friedberg²

2020

Preprint

View full text Add to dashboard Cite

Motivation: Antibiotic resistance is a growing public health problem, which affects millions of people worldwide, and if left unchecked is expected to upend many aspects of healthcare as it is practiced today. Identifying the type of antibiotic resistant genes in genome and metagenomic sample is of utmost importance in the prevention, diagnosis, and treatment of infections. Today there are multiple tools available that predict antibiotic resistance class from DNA and protein sequences, yet there is a lack of benchmarks on the performances of these tools. Results:We have developed a dataset that is curated from 15 available databases, and annotated with their antibiotic class labels. We also developed a transfer learning approach with neural networks, TRAC, that outperforms existing antiobiotic resistance prediction tools. While TRAC provides the current state-of-the-art performance, we hope our newly developed dataset will also provide the community with a much needed standardized dataset to develop novel methods that can predict antibiotic resistance class with superior prediction performance.

show abstract

A deeply supervised residual network for HEp-2 cell classification via cross-modal transfer learning

Cited by 102 publications

References 31 publications

Cats or CAT scans: Transfer learning from natural or medical image source data sets?

Cats or CAT scans: Transfer learning from natural or medical image source data sets?

Breast Cancer Diagnosis with Transfer Learning and Global Pooling

Transfer learning improves antibiotic resistance class prediction

Contact Info

Product

Resources

About