MS-Net: Multi-Site Network for Improving Prostate Segmentation With Heterogeneous MRI Data

Liu, Quande; Dou, Qi; Yu, Lequan; Heng, Pheng‐Ann

doi:10.1109/tmi.2020.2974574

Cited by 236 publications

(163 citation statements)

References 46 publications

Supporting

Mentioning

162

Contrasting

Order By: Relevance

“…In knowledge transfer task (Task 3), simply fusing non-COVID-19 and COVID-19 dataset with the SOTA network could bias the model to learn more non-COVID-19 features. One can use more robust and powerful domain adaptation methods to handle heterogeneous datasets, such as self-supervised learning [43], cross-domain adaptation [44], [45].…”

Section: Accepted Articlementioning

confidence: 99%

Toward data‐efficient learning: A benchmark for COVID‐19 CT lung and infection segmentation

Wang

An³

et al. 2021

Medical Physics

214

171

View full text Add to dashboard Cite

Purpose Accurate segmentation of lung and infection in COVID‐19 computed tomography (CT) scans plays an important role in the quantitative management of patients. Most of the existing studies are based on large and private annotated datasets that are impractical to obtain from a single institution, especially when radiologists are busy fighting the coronavirus disease. Furthermore, it is hard to compare current COVID‐19 CT segmentation methods as they are developed on different datasets, trained in different settings, and evaluated with different metrics. Methods To promote the development of data‐efficient deep learning methods, in this paper, we built three benchmarks for lung and infection segmentation based on 70 annotated COVID‐19 cases, which contain current active research areas, for example, few‐shot learning, domain generalization, and knowledge transfer. For a fair comparison among different segmentation methods, we also provide standard training, validation and testing splits, evaluation metrics and, the corresponding code. Results Based on the state‐of‐the‐art network, we provide more than 40 pretrained baseline models, which not only serve as out‐of‐the‐box segmentation tools but also save computational time for researchers who are interested in COVID‐19 lung and infection segmentation. We achieve average dice similarity coefficient (DSC) scores of 97.3%, 97.7%, and 67.3% and average normalized surface dice (NSD) scores of 90.6%, 91.4%, and 70.0% for left lung, right lung, and infection, respectively. Conclusions To the best of our knowledge, this work presents the first data‐efficient learning benchmark for medical image segmentation, and the largest number of pretrained models up to now. All these resources are publicly available, and our work lays the foundation for promoting the development of deep learning methods for efficient COVID‐19 CT segmentation with limited data.

show abstract

Section: Accepted Articlementioning

confidence: 99%

Toward data‐efficient learning: A benchmark for COVID‐19 CT lung and infection segmentation

Wang

An³

et al. 2021

Medical Physics

214

171

View full text Add to dashboard Cite

show abstract

“…MS-Net [9]: This work constructs a multi-site model that incorporates domain-specific auxiliary branches to improve the feature learning capacity and an online knowledge transfer strategy to explore the robust knowledge from multiple heterogeneous prostate MRI datasets for boosted segmentation.…”

Section: Table III the P-value With Paired T-test Of Our Methods With mentioning

confidence: 99%

“…Previous studies have revealed the limited improvement or even performance degradation of simple joint training at severe data heterogeneity [9], [32]. One crucial reason is that the BN layer in joint model will suffer from an inaccurate estimation of moving average values during the training phase due to the statistical difference across datasets (as shown in Fig.…”

Section: ) Separate Batch Normalization At Data Heterogeneitymentioning

confidence: 99%

“…During testing phase, the estimated values cannot accurately represent the testing data statistics in each site and hence will lead to performance degradation. In this paper, we employ the domainspecific batch normalization (DSBN) method [9], [33], [34] by assigning an individual BN layer for each site independently to explicitly tackle the statistic discrepancy. As shown in Fig.…”

Section: ) Separate Batch Normalization At Data Heterogeneitymentioning

confidence: 99%

“…This could potentially affect the model ability to extract robust and general representations as assumed. Previous studies on other medical imaging applications [7]- [9] have frequently observed that straight-forward joint learning with such heterogeneous datasets only brings limited improvement, or even sometimes underperforming individual models trained on a single dataset.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Contrastive Cross-Site Learning With Redesigned Net for COVID-19 CT Classification

Wang

Liu

Dou

2020

IEEE J. Biomed. Health Inform.

Self Cite

173

142

View full text Add to dashboard Cite

The pandemic of coronavirus disease 2019 (COVID-19) has lead to a global public health crisis spreading hundreds of countries. With the continuous growth of new infections, developing automated tools for COVID-19 identification with CT image is highly desired to assist the clinical diagnosis and reduce the tedious workload of image interpretation. To enlarge the datasets for developing machine learning methods, it is essentially helpful to aggregate the cases from different medical systems for learning robust and generalizable models. This paper proposes a novel joint learning framework to perform accurate COVID-19 identification by effectively learning with heterogeneous datasets with distribution discrepancy. We build a powerful backbone by redesigning the recently proposed COVID-Net in aspects of network architecture and learning strategy to improve the prediction accuracy and learning efficiency. On top of our improved backbone, we further explicitly tackle the cross-site domain shift by conducting separate feature normalization in latent space. Moreover, we propose to use a contrastive training objective to enhance the domain invariance of semantic embeddings for boosting the classification performance on each dataset. We develop and evaluate our method with two public large-scale COVID-19 diagnosis datasets made up of CT images. Extensive experiments show that our approach consistently improves the performanceson both datasets, outperforming the original COVID-Net trained on each dataset by 12.16% and 14.23% in AUC respectively, also exceeding existing state-of-the-art multi-site learning methods.

show abstract

Clinical application and improvement of a CNN‐based autosegmentation model for clinical target volumes in cervical cancer radiotherapy

Chang

Zhi

Zhao

et al. 2021

J Applied Clin Med Phys

View full text Add to dashboard Cite

Objective: Clinical target volume (CTV) autosegmentation for cervical cancer is desirable for radiation therapy. Data heterogeneity and interobserver variability (IOV) limit the clinical adaptability of such methods. The adaptive method is proposed to improve the adaptability of CNN-based autosegmentation of CTV contours in cervical cancer. Methods: This study included 400 cervical cancer treatment planning cases with CTV delineated by radiation oncologists from three hospitals. The datasets were divided into five subdatasets (80 cases each). The cases in datasets 1, 2, and 3 were delineated by physicians A, B, and C, respectively. The cases in datasets 4 and 5 were delineated by multiple physicians. Dataset 1 was divided into training (50 cases), validation (10 cases), and testing (20 cases) cohorts, and they were used to construct the pretrained model. Datasets 2-5 were regarded as host datasets to evaluate the accuracy of the pretrained model. In the adaptive process, the pretrained model was fine-tuned to measure improvements by gradually adding more training cases selected from the host datasets. The accuracy of the autosegmentation model on each host dataset was evaluated using the corresponding test cases. The Dice similarity coefficient (DSC) and 95% Hausdorff distance (HD_95) were used to evaluate the accuracy. Results: Before and after adaptive improvements, the average DSC values on the host datasets were 0.818 versus 0.882, 0.763 versus 0.810, 0.727 versus 0.772, and 0.679 versus 0.789, which are improvements of 7.82%, 6.16%, 6.19%, and 16.05%, respectively. The average HD_95 values were 11.143 mm versus 6.853 mm,22.402 mm versus 14.076 mm,28.145 mm versus 16.437 mm, and 33.034 mm versus 16.441 mm,which are improvements of 37.94%,37.17%, 41.60%, and 50.23%, respectively. Conclusion:The proposed method improved the adaptability of the CNNbased autosegmentation model when applied to host datasets.

show abstract

MS-Net: Multi-Site Network for Improving Prostate Segmentation With Heterogeneous MRI Data

Cited by 236 publications

References 46 publications

Toward data‐efficient learning: A benchmark for COVID‐19 CT lung and infection segmentation

Toward data‐efficient learning: A benchmark for COVID‐19 CT lung and infection segmentation

Contrastive Cross-Site Learning With Redesigned Net for COVID-19 CT Classification

Clinical application and improvement of a CNN‐based autosegmentation model for clinical target volumes in cervical cancer radiotherapy

Contact Info

Product

Resources

About