Strategies for Training Stain Invariant CNNS

Lampert, Thomas; Merveille, Odyssée; Schmitz, Jessica; Forestier, Germain; Feuerhake, Friedrich; Wemmert, Cédric

doi:10.1109/isbi.2019.8759266

Cited by 18 publications

(22 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To mitigate the lack of data and increase the dataset diversity, we used the Augmentor [20] library to perform data augmentation on our dataset. We privilege transformations which could appear in reality due to human or mechanical manipulations as in [21]: 1 The YOLOv3 network downsamples input images by 32. Hence, the input images must be multiple of 32.…”

Section: Data Augmentationmentioning

confidence: 99%

Real-Time Detection of Glomeruli in Renal Pathology

Heckenauer

Weber

Wemmert

et al. 2020

2020 IEEE 33rd International Symposium on Computer-Based Medical Systems (CBMS)

Self Cite

View full text Add to dashboard Cite

The field of digital pathology emerged with the introduction of whole slide imaging scanners and lead to the development of new tools for analyzing histopathological slides. The availability of digital representation of the slides has motivated the development of artificial intelligence methods to automatically identify microscopic structures in order to support pathologists in their diagnosis. Unlike many existing approaches targeting the detection of microscopic structures on static images at a given and fixed magnification level, our work focuses on the real-time detection of the structures at different scales. Indeed, real-time detection at different scales brings additional challenges but also better mimics the way pathologists work as they continuously move the slides and change the magnification level during their analysis. In this paper, we focus on renal pathology and more specifically on the real-time detection of glomeruli at different scales. Our method is based on the deep learning object detection model YOLOv3 pre-trained on the COCO dataset and fine tuned to detect glomeruli. We investigate the benefits of using multiscale images to improve the network ability to detect glomeruli at variable magnification levels in real time.Index Terms-real-time glomerulus detection, digital pathology, deep convolutional networks

show abstract

Section: Data Augmentationmentioning

confidence: 99%

Real-Time Detection of Glomeruli in Renal Pathology

Heckenauer

Weber

Wemmert

et al. 2020

2020 IEEE 33rd International Symposium on Computer-Based Medical Systems (CBMS)

Self Cite

View full text Add to dashboard Cite

show abstract

“…Specifically, pathology images have stain variations 19 while MRIs are susceptible to varying magnetic fields and contrast agents 20 . Such intra- or inter-dataset variations cause the training and test dataset to have different distributions, resulting in a domain-shift which impacts model generalization 21 22 . Diversifying the training data by creating larger datasets is a possible solution, but recent medical imaging studies 21 23 24 have shown that it does not guarantee improved generalization.…”

Section: Introductionmentioning

confidence: 99%

Advancing Medical Imaging Informatics by Deep Learning-Based Domain Adaptation

Choudhary

Zhu

et al. 2020

Yearb Med Inform

View full text Add to dashboard Cite

Introduction: There has been a rapid development of deep learning (DL) models for medical imaging. However, DL requires a large labeled dataset for training the models. Getting large-scale labeled data remains a challenge, and multi-center datasets suffer from heterogeneity due to patient diversity and varying imaging protocols. Domain adaptation (DA) has been developed to transfer the knowledge from a labeled data domain to a related but unlabeled domain in either image space or feature space. DA is a type of transfer learning (TL) that can improve the performance of models when applied to multiple different datasets. Objective: In this survey, we review the state-of-the-art DL-based DA methods for medical imaging. We aim to summarize recent advances, highlighting the motivation, challenges, and opportunities, and to discuss promising directions for future work in DA for medical imaging. Methods: We surveyed peer-reviewed publications from leading biomedical journals and conferences between 2017-2020, that reported the use of DA in medical imaging applications, grouping them by methodology, image modality, and learning scenarios. Results: We mainly focused on pathology and radiology as application areas. Among various DA approaches, we discussed domain transformation (DT) and latent feature-space transformation (LFST). We highlighted the role of unsupervised DA in image segmentation and described opportunities for future development. Conclusion: DA has emerged as a promising solution to deal with the lack of annotated training data. Using adversarial techniques, unsupervised DA has achieved good performance, especially for segmentation tasks. Opportunities include domain transferability, multi-modal DA, and applications that benefit from synthetic data.

show abstract

“…However, most of the earlier efforts that utilized DL used samples obtained at a single institution and lacked independent external validation and performance comparison with a radiologist [13][14][15][16][17]. Despite the high-representative capacity of DL models, several authors have recently criticized the generalizability of DL models across datasets derived from different domains (e.g., MRI obtained with different MRI scanners or at different institutions) [20,21].…”

Section: Introductionmentioning

confidence: 99%

Inter-Vendor Performance of Deep Learning in Segmenting Acute Ischemic Lesions on Diffusion-Weighted Imaging: A Multicenter Study

Aliş

Yergin

Alış

et al. 2020

Preprint

View full text Add to dashboard Cite

There is little evidence on the applicability of deep learning (DL) in segmentation of acute ischemic lesions on diffusion-weighted imaging (DWI) between magnetic resonance imaging (MRI) scanners of different manufacturers. We retrospectively included DWI data of patients with acute ischemic lesions from six centers. Dataset A (n=2986) and B (n=3951) included data from Siemens and GE MRI scanners, respectively. The datasets were split into the training (80%), validation (10%), and internal test (10%) sets and six neuroradiologist created ground-truth masks. Models A and B were the proposed neural networks trained on datasets A and B and also fine-tuned across the datasets using their validation data. Another radiologist performed the segmentation on the test sets for comparisons. The median Dice scores of models A and B were 0.858 and 0.857 for the internal tests, which were non-inferior to the radiologist’s performance, but demonstrated lower performance than the radiologist on the external tests. Fine-tuned models A and B achieved median Dice scores of 0.832 and 0.846, which were non-inferior to the radiologist's performance on the external tests. The present work shows that inter-vendor operability of deep learning for the segmentation of ischemic lesions on DWI might be enhanced via transfer learning; thereby, their clinical applicability and generalizability could be improved.

show abstract

Strategies for Training Stain Invariant CNNS

Cited by 18 publications

References 19 publications

Real-Time Detection of Glomeruli in Renal Pathology

Real-Time Detection of Glomeruli in Renal Pathology

Advancing Medical Imaging Informatics by Deep Learning-Based Domain Adaptation

Inter-Vendor Performance of Deep Learning in Segmenting Acute Ischemic Lesions on Diffusion-Weighted Imaging: A Multicenter Study

Contact Info

Product

Resources

About