FastPathology: An Open-Source Platform for Deep Learning-Based Research and Decision Support in Digital Pathology

Pedersen, André; Valla, Marit; Bofin, Anna M.; Frutos, Javier Pérez de; Reinertsen, Ingerid; Smistad, Erik

doi:10.1109/access.2021.3072231

Cited by 17 publications

(18 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…WSIs often contain 50-90% white background, which will make the exterior class completely dominant in training. Therefore, a glass detection method was used, similarly as done in a previous study (21), and patches with <25% tissue were discarded.…”

Section: U-net Based Epithelial Segmentation Using Qupath and Deepmibmentioning

confidence: 99%

“…We defined an inference pipeline consisting of applying the trained segmentation model across the WSI in an overlapping, sliding window fashion, similarly as done in a previous study (21). The result of each patch was binarized using a threshold of 0.5, before being stitched to form a tiled, pyramidal image.…”

Section: Deployment In Fastpathologymentioning

confidence: 99%

“…This slows viewing speed, versatility, and prediction runtime. FastPathology (21) was developed to offer a user friendly direct WSI prediction viewer to pathologists. The software is free, open-source, and focused on high-performance computing to minimize memory usage and runtime.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Code-Free Development and Deployment of Deep Segmentation Models for Digital Pathology

et al. 2022

Self Cite

View full text Add to dashboard Cite

Application of deep learning on histopathological whole slide images (WSIs) holds promise of improving diagnostic efficiency and reproducibility but is largely dependent on the ability to write computer code or purchase commercial solutions. We present a code-free pipeline utilizing free-to-use, open-source software (QuPath, DeepMIB, and FastPathology) for creating and deploying deep learning-based segmentation models for computational pathology. We demonstrate the pipeline on a use case of separating epithelium from stroma in colonic mucosa. A dataset of 251 annotated WSIs, comprising 140 hematoxylin-eosin (HE)-stained and 111 CD3 immunostained colon biopsy WSIs, were developed through active learning using the pipeline. On a hold-out test set of 36 HE and 21 CD3-stained WSIs a mean intersection over union score of 95.5 and 95.3% was achieved on epithelium segmentation. We demonstrate pathologist-level segmentation accuracy and clinical acceptable runtime performance and show that pathologists without programming experience can create near state-of-the-art segmentation solutions for histopathological WSIs using only free-to-use software. The study further demonstrates the strength of open-source solutions in its ability to create generalizable, open pipelines, of which trained models and predictions can seamlessly be exported in open formats and thereby used in external solutions. All scripts, trained models, a video tutorial, and the full dataset of 251 WSIs with ~31 k epithelium annotations are made openly available at https://github.com/andreped/NoCodeSeg to accelerate research in the field.

show abstract

Section: U-net Based Epithelial Segmentation Using Qupath and Deepmibmentioning

confidence: 99%

Section: Deployment In Fastpathologymentioning

confidence: 99%

See 1 more Smart Citation

Code-Free Development and Deployment of Deep Segmentation Models for Digital Pathology

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…Most of the works in literature focus on creating tools for helping the research community to easily handle and interact with WSI's [22], [31]. However, driving a high scale automated system for production requires dealing with complexities that are not present on a scientific environment.…”

Section: Discussionmentioning

confidence: 99%

OncoPetNet: A Deep Learning based AI system for mitotic figure counting on H&E stained whole slide digital images in a large veterinary diagnostic lab setting

Fitzke¹,

Whitley²,

Yau³

et al. 2021

Preprint

View full text Add to dashboard Cite

Background: Histopathology is an important modality for the diagnosis and management of many diseases in modern healthcare, and plays a particularly critical role in cancer care. Pathology samples can be large and require multi-site sampling, leading to upwards of 20 slides for a single tumor, and the human-expert tasks of site selection and and quantitative assessment of mitotic figures are time consuming and subjective, particularly in highly mitotically active tumors.Automating these tasks in the setting of a digital pathology service presents significant opportunities to improve workflow efficiency and augment human experts in practice, yet major technical challenges remain that limit achieving use of these systems at scale in clinical workflows.Approach: Multiple state-of-the-art deep learning techniques for whole slide histopathology image classification and mitotic figure detection were used in the development of OncoPet-Net. Additionally, model-free approaches were used to increase speed and accuracy in real-time deployment. The robust and scalable inference engine leverages Pytorch's performance optimizations as well as specifically developed speed up techniques in inference.Results: The proposed deep-learning system, OncoPetNet, demonstrated significantly improved mitotic counting performance for 41 cancer cases across 14 cancer types compared to human expert baselines. Further, in 21.9% of cases use of the OncoPetNet led to change in tumor grading compared to human expert evaluation. In deployment, an effective 0.27 min/slide inference was achieved in a high throughput multi-site veterinary diagnostic pathology service across 2 centers processing 3,323 digital whole slide images daily.Conclusion: This work represents the first successful automated deployment of deep learning systems for real-time expert-level performance on important histopathology tasks at scale in a high volume clinical practice. The resulting impact outlines important considerations for model development, deployment, clinical decision making, and informs best practices for implementation of deep learning systems in digital histopathology practices.

show abstract

“…(3) A novel approach where a cascaded CNN combines highresolution and global information in histopathological images, producing superior performance over singleresolution approaches. (4) The proposed pipeline and trained models are made openly available for use in FastPathology (27).…”

Section: Introductionmentioning

confidence: 99%

H2G-Net: A multi-resolution refinement approach for segmentation of breast cancer region in gigapixel histopathological images

et al. 2022

Self Cite

View full text Add to dashboard Cite

Over the past decades, histopathological cancer diagnostics has become more complex, and the increasing number of biopsies is a challenge for most pathology laboratories. Thus, development of automatic methods for evaluation of histopathological cancer sections would be of value. In this study, we used 624 whole slide images (WSIs) of breast cancer from a Norwegian cohort. We propose a cascaded convolutional neural network design, called H2G-Net, for segmentation of breast cancer region from gigapixel histopathological images. The design involves a detection stage using a patch-wise method, and a refinement stage using a convolutional autoencoder. To validate the design, we conducted an ablation study to assess the impact of selected components in the pipeline on tumor segmentation. Guiding segmentation, using hierarchical sampling and deep heatmap refinement, proved to be beneficial when segmenting the histopathological images. We found a significant improvement when using a refinement network for post-processing the generated tumor segmentation heatmaps. The overall best design achieved a Dice similarity coefficient of 0.933±0.069 on an independent test set of 90 WSIs. The design outperformed single-resolution approaches, such as cluster-guided, patch-wise high-resolution classification using MobileNetV2 (0.872±0.092) and a low-resolution U-Net (0.874±0.128). In addition, the design performed consistently on WSIs across all histological grades and segmentation on a representative × 400 WSI took ~ 58 s, using only the central processing unit. The findings demonstrate the potential of utilizing a refinement network to improve patch-wise predictions. The solution is efficient and does not require overlapping patch inference or ensembling. Furthermore, we showed that deep neural networks can be trained using a random sampling scheme that balances on multiple different labels simultaneously, without the need of storing patches on disk. Future work should involve more efficient patch generation and sampling, as well as improved clustering.

show abstract

FastPathology: An Open-Source Platform for Deep Learning-Based Research and Decision Support in Digital Pathology

Cited by 17 publications

References 29 publications

Code-Free Development and Deployment of Deep Segmentation Models for Digital Pathology

Code-Free Development and Deployment of Deep Segmentation Models for Digital Pathology

OncoPetNet: A Deep Learning based AI system for mitotic figure counting on H&E stained whole slide digital images in a large veterinary diagnostic lab setting

H2G-Net: A multi-resolution refinement approach for segmentation of breast cancer region in gigapixel histopathological images

Contact Info

Product

Resources

About