Hey everyone!
\nI wanted to start a papers thread and build on it, and hope others share as well, papers to gain domain knowledge. I have no domain knowledge in this area so I have downloaded papers that appeared to be relevant after reading their abstracts. I'll be reading these over the coming days and commenting more as I go through all of them. Hope this helps!
\nResearch Papers:
\nAn automatic framework to study the tissue micro-environment of renal glomeruli in differently stained consecutive digital whole slide images - This article presents an automatic image processing framework to extract quantitative high-level information describing the micro-environment of glomeruli in consecutive whole slide images (WSIs) processed with different staining modalities of patients with chronic kidney rejection after kidney transplantation.
Instance Segmentation for Whole Slide Imaging: End-to-End or Detect-Then-Segment - In this paper, we assess if the end-to-end instance segmentation framework is optimal for high-resolution WSI objects by comparing Mask-RCNN with our proposed detect-then-segment framework.
MSA-MIL: A deep residual multiple instance learning model based on multi-scale annotation for classification and visualization of glomerular spikes - In this paper, we establish a visualized classification model based on the multi-scale annotation multi-instance learning (MSA-MIL) to achieve glomerular classification and spikes visualization.
Neural Network Segmentation of Interstitial Fibrosis, Tubular Atrophy, and Glomerulosclerosis in Renal Biopsies - In this work, we apply convolutional neural networks for the segmentation of glomerulosclerosis and IFTA in periodic acid-Schiff stained renal biopsies. The convolutional network approach achieves high performance in intra-institutional holdout data, and achieves moderate performance in inter-intuitional holdout data, which the network had never seen in training.
Classification of glomerular hypercellularity using convolutional features and support vector machine - Our proposed method introduces a novel architecture of a convolutional neural network (CNN) along with a support vector machine, achieving near perfect average results with the FIOCRUZ data set in a binary classification (lesion or normal).
Cross-stained Segmentation from Renal Biopsy Images Using Multi-level Adversarial Learning - In this paper, we design a robust and flexible model for cross-stained segmentation.
To What Extent Does Downsampling, Compression, and Data Scarcity Impact Renal Image Analysis? - To this end, we first examine image downsampling rates in terms of their effect on detection accuracy. Second, we examine the impact of image compression.
EasierPath: An Open-source Tool for Human-in-the-loop Deep Learning of Renal Pathology - From the experiments, the EasierPath saved 57 % of the annotation efforts to curate 8,833 glomeruli during the second loop. Meanwhile, the average precision of glomerular detection was leveraged from 0.504 to 0.620. The EasierPath software has been released as open-source to enable the large-scale glomerular prototyping.
Hey everyone!
\nI wanted to start a papers thread and build on it, and hope others share as well, papers to gain domain knowledge. I have no domain knowledge in this area so I have downloaded papers that appeared to be relevant after reading their abstracts. I'll be reading these over the coming days and commenting more as I go through all of them. Hope this helps!
\nResearch Papers:
\nAn automatic framework to study the tissue micro-environment of renal glomeruli in differently stained consecutive digital whole slide images - This article presents an automatic image processing framework to extract quantitative high-level information describing the micro-environment of glomeruli in consecutive whole slide images (WSIs) processed with different staining modalities of patients with chronic kidney rejection after kidney transplantation.
Instance Segmentation for Whole Slide Imaging: End-to-End or Detect-Then-Segment - In this paper, we assess if the end-to-end instance segmentation framework is optimal for high-resolution WSI objects by comparing Mask-RCNN with our proposed detect-then-segment framework.
MSA-MIL: A deep residual multiple instance learning model based on multi-scale annotation for classification and visualization of glomerular spikes - In this paper, we establish a visualized classification model based on the multi-scale annotation multi-instance learning (MSA-MIL) to achieve glomerular classification and spikes visualization.
Neural Network Segmentation of Interstitial Fibrosis, Tubular Atrophy, and Glomerulosclerosis in Renal Biopsies - In this work, we apply convolutional neural networks for the segmentation of glomerulosclerosis and IFTA in periodic acid-Schiff stained renal biopsies. The convolutional network approach achieves high performance in intra-institutional holdout data, and achieves moderate performance in inter-intuitional holdout data, which the network had never seen in training.
Classification of glomerular hypercellularity using convolutional features and support vector machine - Our proposed method introduces a novel architecture of a convolutional neural network (CNN) along with a support vector machine, achieving near perfect average results with the FIOCRUZ data set in a binary classification (lesion or normal).
Cross-stained Segmentation from Renal Biopsy Images Using Multi-level Adversarial Learning - In this paper, we design a robust and flexible model for cross-stained segmentation.
To What Extent Does Downsampling, Compression, and Data Scarcity Impact Renal Image Analysis? - To this end, we first examine image downsampling rates in terms of their effect on detection accuracy. Second, we examine the impact of image compression.
EasierPath: An Open-source Tool for Human-in-the-loop Deep Learning of Renal Pathology - From the experiments, the EasierPath saved 57 % of the annotation efforts to curate 8,833 glomeruli during the second loop. Meanwhile, the average precision of glomerular detection was leveraged from 0.504 to 0.620. The EasierPath software has been released as open-source to enable the large-scale glomerular prototyping.
Also see https://www.kaggle.com/leahscherschel/glomeruli-detection-related-works
", "rawMarkdown": "Also see https://www.kaggle.com/leahscherschel/glomeruli-detection-related-works", "votes": null }, { "id": "1228677", "postDate": "03/06/2021 16:33:20", "content": "Hi,
\nAdding some more.
Thanks
", "rawMarkdown": "Hi,\nAdding some more.\n1. https://www.sciencedirect.com/science/article/pii/S246802491930155X\n2. https://jasn.asnjournals.org/content/30/10/1968\n\nThanks", "votes": null } ], "comments": [ { "id": 1083267, "author_name": "leahscherschel", "author_url": "", "post_date": "11/18/2020 19:23:46", "content": "Also see https://www.kaggle.com/leahscherschel/glomeruli-detection-related-works
", "votes": null, "replies": [] }, { "id": 1228677, "author_name": "kritidoneria", "author_url": "", "post_date": "03/06/2021 16:33:20", "content": "Hi,
\nAdding some more.
Thanks
", "votes": null, "replies": [] } ], "raw_markdown_by_id": { "1081965": "Hey everyone!\n\nI wanted to start a papers thread and build on it, and hope others share as well, papers to gain domain knowledge. I have no domain knowledge in this area so I have downloaded papers that appeared to be relevant after reading their abstracts. I'll be reading these over the coming days and commenting more as I go through all of them. Hope this helps!\n\nResearch Papers:\n\n* [An automatic framework to study the tissue micro-environment of renal glomeruli in differently stained consecutive digital whole slide images](https://arxiv.org/abs/2008.13050) - This article presents an automatic image processing framework to extract quantitative high-level information describing the micro-environment of glomeruli in consecutive whole slide images (WSIs) processed with different staining modalities of patients with chronic kidney rejection after kidney transplantation. \n\n* [Instance Segmentation for Whole Slide Imaging: End-to-End or Detect-Then-Segment](https://arxiv.org/abs/2007.03593) - In this paper, we assess if the end-to-end instance segmentation framework is optimal for high-resolution WSI objects by comparing Mask-RCNN with our proposed detect-then-segment framework.\n\n* [MSA-MIL: A deep residual multiple instance learning model based on multi-scale annotation for classification and visualization of glomerular spikes](https://arxiv.org/abs/2007.00858) - In this paper, we establish a visualized classification model based on the multi-scale annotation multi-instance learning (MSA-MIL) to achieve glomerular classification and spikes visualization. \n\n* [Neural Network Segmentation of Interstitial Fibrosis, Tubular Atrophy, and Glomerulosclerosis in Renal Biopsies](https://arxiv.org/abs/2002.12868) - In this work, we apply convolutional neural networks for the segmentation of glomerulosclerosis and IFTA in periodic acid-Schiff stained renal biopsies. The convolutional network approach achieves high performance in intra-institutional holdout data, and achieves moderate performance in inter-intuitional holdout data, which the network had never seen in training.\n\n* [Classification of glomerular hypercellularity using convolutional features and support vector machine](https://arxiv.org/abs/1907.00028) - Our proposed method introduces a novel architecture of a convolutional neural network (CNN) along with a support vector machine, achieving near perfect average results with the FIOCRUZ data set in a binary classification (lesion or normal).\n\n* [Cross-stained Segmentation from Renal Biopsy Images Using Multi-level Adversarial Learning](https://arxiv.org/abs/2002.08587) - In this paper, we design a robust and flexible model for cross-stained segmentation.\n\n* [To What Extent Does Downsampling, Compression, and Data Scarcity Impact Renal Image Analysis?](https://arxiv.org/abs/1909.09945) - To this end, we first examine image downsampling rates in terms of their effect on detection accuracy. Second, we examine the impact of image compression.\n\n* [EasierPath: An Open-source Tool for Human-in-the-loop Deep Learning of Renal Pathology](https://arxiv.org/abs/2007.13952) - From the experiments, the EasierPath saved 57 % of the annotation efforts to curate 8,833 glomeruli during the second loop. Meanwhile, the average precision of glomerular detection was leveraged from 0.504 to 0.620. The EasierPath software has been released as open-source to enable the large-scale glomerular prototyping.", "1083267": "Also see https://www.kaggle.com/leahscherschel/glomeruli-detection-related-works", "1228677": "Hi,\nAdding some more.\n1. https://www.sciencedirect.com/science/article/pii/S246802491930155X\n2. https://jasn.asnjournals.org/content/30/10/1968\n\nThanks" }, "source": "meta" }