scholarly journals Deep Learning Global Glomerulosclerosis in Transplant Kidney Frozen Sections

2018 ◽  
Author(s):  
Jon N. Marsh ◽  
Matthew K. Matlock ◽  
Satoru Kudose ◽  
Ta-Chiang Liu ◽  
Thaddeus S. Stappenbeck ◽  
...  
Keyword(s):  
Deep Learning ◽  
Frozen Section ◽  
Extended Model ◽  
Donor Kidney ◽  
Automated Method ◽  
Image Patches ◽  
Transplant Kidney ◽  
Global Glomerulosclerosis ◽  
Whole Slide Images

AbstractTransplantable kidneys are in very limited supply. Accurate viability assessment prior to transplantation could minimize organ discard. Rapid and accurate evaluation of intra-operative donor kidney biopsies is essential for determining which kidneys are eligible for transplantation. The criteria for accepting or rejecting donor kidneys relies heavily on pathologist determination of the percent of glomeruli (determined from a frozen section) that are normal and sclerotic. This percentage is a critical measurement that correlates with transplant outcome. Inter- and intra-observer variability in donor biopsy evaluation is, however, significant. An automated method for determination of percent global glomerulosclerosis could prove useful in decreasing evaluation variability, increasing throughput, and easing the burden on pathologists. Here, we describe the development of a deep learning model that identifies and classifies non-sclerosed and sclerosed glomeruli in whole-slide images of donor kidney frozen section biopsies. This model extends a convolutional neural network (CNN) pre-trained on a large database of digital images. The extended model, when trained on just 48 whole slide images, exhibits slide-level evaluation performance on par with expert renal pathologists. The model substantially outperforms a model trained on image patches of isolated glomeruli. Encouragingly, the model’s performance is robust to slide preparation artifacts associated with frozen section preparation. As the first model reported that identifies and classifies normal and sclerotic glomeruli in frozen kidney sections, and thus the first model reported in the literature relevant to kidney transplantation, it may become an essential part of donor kidney biopsy evaluation in the clinical setting.

Ovarian Frozen Section Diagnosis: Use of Whole-Slide Imaging Shows Excellent Correlation Between Virtual Slide and Original Interpretations in a Large Series of Cases

2010 ◽  
Vol 134 (7) ◽  
pp. 1020-1023 ◽  
Author(s):  
Margaret A. Fallon ◽  
David C. Wilbur ◽  
Manju Prasad
Keyword(s):  
Frozen Section ◽  
Virtual Slide ◽  
Granulosa Cell Tumor ◽  
Routine Practice ◽  
Corpora Lutea ◽  
Operating Characteristics ◽  
Frozen Section Diagnosis ◽  
Very High ◽  
Whole Slide Images

Abstract Context.—Whole-slide images (WSI) are a tool for remote interpretation, archiving, and teaching. Ovarian frozen sections (FS) are common and hence determination of the operating characteristics of the interpretation of these specimens using WSI is important. Objectives.—To test the reproducibility and accuracy of ovarian FS interpretation using WSI, as compared with routine analog interpretation, to understand the technology limits and unique interpretive pitfalls. Design.—A sequential series of ovarian FS slides, representative of routine practice, were converted to WSI. Whole-slide images were examined by 2 pathologists, masked to all prior results. Correlation characteristics among the WSI, the original, and the final interpretations were analyzed. Results.—A total of 52 cases, consisting of 71 FS slides, were included; 34 cases (65%) were benign, and 18 cases (35%) were malignant, borderline, and of uncertain potential (9 [17%], 7 [13%], and 2 [4%] of 52 cases, respectively). The correlation between WSI and FS interpretations was 96% (50 of 52) for each pathologist for benign versus malignant, borderline, and uncertain entities. Each pathologist undercalled 2 borderline malignant cases (4%) as benign cysts on WSI. There were no overcalls of benign cases. Specific issues within the benign and malignant groups involved endometriosis versus hemorrhagic corpora lutea, and granulosa cell tumor versus carcinoma, respectively. Conclusions.—The correlation between original FS and WSI interpretations was very high. The few discordant cases represent recognized differential diagnostic issues. Ability to examine gross pathology and real-time consultation with surgeons might be expected to improve performance. Ovarian FS diagnosis by WSI is accurate and reproducible, and thus, remote interpretation, teaching, and digital archiving of ovarian FS specimens by this method can be reliable.

scholarly journals Breast Tumor Cellularity Assessment using Deep Neural Networks

2019 ◽  
Author(s):  
Alexander Rakhlin ◽  
Aleksei Tiulpin ◽  
Alexey A. Shvets ◽  
Alexandr A. Kalinin ◽  
Vladimir I. Iglovikov ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Deep Learning ◽  
Automatic Assessment ◽  
Appropriate Treatment ◽  
Image Patches ◽  
Expert Pathologist ◽  
Hematoxylin And Eosin ◽  
Treated Breast ◽  
Intra Class Correlation Coefficient ◽  
Whole Slide Images

AbstractBreast cancer is one of the main causes of death world-wide. Histopathological cellularity assessment of residual tumors in post-surgical tissues is used to analyze a tumor’s response to a therapy. Correct cellularity assessment increases the chances of getting an appropriate treatment and facilitates the patient’s survival. In current clinical practice, tumor cellularity is manually estimated by pathologists; this process is tedious and prone to errors or low agreement rates between assessors. In this work, we evaluated three strong novel Deep Learning-based approaches for automatic assessment of tumor cellularity from post-treated breast surgical specimens stained with hematoxylin and eosin. We validated the proposed methods on the BreastPathQ SPIE challenge dataset that consisted of 2395 image patches selected from whole slide images acquired from 64 patients. Compared to expert pathologist scoring, our best performing method yielded the Cohen’s kappa coefficient of 0.69 (vs. 0.42 previously known in literature) and the intra-class correlation coefficient of 0.89 (vs. 0.83). Our results suggest that Deep Learning-based methods have a significant potential to alleviate the burden on pathologists, enhance the diagnostic workflow, and, thereby, facilitate better clinical outcomes in breast cancer treatment.

scholarly journals Predicting Primary Site of Secondary Liver Cancer with a Neural Estimator of Metastatic Origin (NEMO)

2019 ◽  
Author(s):  
Geoffrey F. Schau ◽  
Erik A. Burlingame ◽  
Guillaume Thibault ◽  
Tauangtham Anekpuritanang ◽  
Ying Wang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Liver Cancer ◽  
Clinical Information ◽  
Structural Features ◽  
Tissue Sections ◽  
Liver Cancers ◽  
Hematoxylin And Eosin ◽  
Whole Slide Images ◽  
Clinical Determination

AbstractPathologists rely on clinical information, tissue morphology, and sophisticated molecular diagnostics to accurately infer the metastatic origin of secondary liver cancer. In this paper, we introduce a deep learning approach to identify spatially localized regions of cancerous tumor within hematoxylin and eosin stained tissue sections of liver cancer and to generate predictions of the cancer’s metastatic origin. Our approach achieves an accuracy of 90.2% when classifying metastatic origin of whole slide images into three distinct classes, which compares favorably to an established clinical benchmark by three board-certified pathologists whose accuracies ranged from 90.2% to 94.1% on the same prediction task. This approach illustrates the potential impact of deep learning systems to leverage morphological and structural features of H&E stained tissue sections to guide pathological and clinical determination of the metastatic origin of secondary liver cancers.

Deep Learning in Toxicologic Pathology: A New Approach to Evaluate Rodent Retinal Atrophy

2020 ◽  
pp. 019262332098067
Author(s):  
Maria Cristina De Vera Mudry ◽  
Jim Martin ◽  
Vanessa Schumacher ◽  
Raghavan Venugopal
Keyword(s):  
Deep Learning ◽  
Hybrid Approach ◽  
Computational Method ◽  
New Approach ◽  
Image Patches ◽  
Retinal Atrophy ◽  
Safety Studies ◽  
Hematoxylin Eosin ◽  
Whole Slide Images

Quantification of retinal atrophy, caused by therapeutics and/or light, by manual measurement of retinal layers is labor intensive and time-consuming. In this study, we explored the role of deep learning (DL) in automating the assessment of retinal atrophy, particularly of the outer and inner nuclear layers, in rats. Herein, we report our experience creating and employing a hybrid approach, which combines conventional image processing and DL to quantify rodent retinal atrophy. Utilizing a DL approach based upon the VGG16 model architecture, models were trained, tested, and validated using 10,746 image patches scanned from whole slide images (WSIs) of hematoxylin-eosin stained rodent retina. The accuracy of this computational method was validated using pathologist annotated WSIs throughout and used to separately quantify the thickness of the outer and inner nuclear layers of the retina. Our results show that DL can facilitate the evaluation of therapeutic and/or light-induced atrophy, particularly of the outer retina, efficiently in rodents. In addition, this study provides a template which can be used to train, validate, and analyze the results of toxicologic pathology DL models across different animal species used in preclinical efficacy and safety studies.

scholarly journals Successful Identification of Nasopharyngeal Carcinoma in Nasopharyngeal Biopsies Using Deep Learning

Cancers ◽  
2020 ◽  
Vol 12 (2) ◽  
pp. 507
Author(s):  
Wen-Yu Chuang ◽  
Shang-Hung Chang ◽  
Wei-Hsiang Yu ◽  
Cheng-Kun Yang ◽  
Chi-Ju Yeh ◽  
...  
Keyword(s):  
Deep Learning ◽  
Nasopharyngeal Carcinoma ◽  
Characteristic Curve ◽  
Receiver Operator Characteristic Curve ◽  
Image Patches ◽  
Validation Set ◽  
First Time ◽  
Level Training ◽  
Activation Mapping ◽  
Whole Slide Images

Pathologic diagnosis of nasopharyngeal carcinoma (NPC) can be challenging since most cases are nonkeratinizing carcinoma with little differentiation and many admixed lymphocytes. Our aim was to evaluate the possibility to identify NPC in nasopharyngeal biopsies using deep learning. A total of 726 nasopharyngeal biopsies were included. Among them, 100 cases were randomly selected as the testing set, 20 cases as the validation set, and all other 606 cases as the training set. All three datasets had equal numbers of NPC cases and benign cases. Manual annotation was performed. Cropped square image patches of 256 × 256 pixels were used for patch-level training, validation, and testing. The final patch-level algorithm effectively identified NPC patches, with an area under the receiver operator characteristic curve (AUC) of 0.9900. Using gradient-weighted class activation mapping, we demonstrated that the identification of NPC patches was based on morphologic features of tumor cells. At the second stage, whole-slide images were sequentially cropped into patches, inferred with the patch-level algorithm, and reconstructed into images with a smaller size for training, validation, and testing. Finally, the AUC was 0.9848 for slide-level identification of NPC. Our result shows for the first time that deep learning algorithms can identify NPC.

scholarly journals Deep Learning Segmentation of Glomeruli on Kidney Donor Frozen Sections

2021 ◽  
Author(s):  
Richard C. Davis ◽  
Xiang Li ◽  
Yuemei Xu ◽  
Zehan Wang ◽  
Nao Souma ◽  
...  
Keyword(s):  
Deep Learning ◽  
Standard Of Care ◽  
Dice Similarity Coefficient ◽  
Manual Segmentation ◽  
Frozen Sections ◽  
Donor Kidney ◽  
Automatic Quantification ◽  
Testing Dataset ◽  
Computational Image Analysis ◽  
Whole Slide Images

Purpose: Recent advances in computational image analysis offer the opportunity to develop automatic quantification of histologic parameters as aid tools for practicing pathologists. This work aims to develop deep learning (DL) models to quantify non-sclerotic and sclerotic glomeruli on frozen sections from donor kidney biopsies. Approach: A total of 258 whole slide images (WSI) from cadaveric donor kidney biopsies performed at our institution (n=123) and at external institutions (n=135) were used in this study. WSIs from our institution were divided at the patient level into training and validation datasets (Ratio: 0.8:0.2) and external WSIs were used as an independent testing dataset. Non-sclerotic (n=22767) and sclerotic (n=1366) glomeruli were manually annotated by study pathologists on all WSIs. A 9-layer convolutional neural network based on the common U-Net architecture was developed and tested for the segmentation of non-sclerotic and sclerotic glomeruli. DL-derived, manual segmentation and reported glomerular count (standard of care) were compared. Results: The average Dice Similarity Coefficient testing was 0.90 and 0.83. and the F1, Recall, and Precision scores were 0.93, 0.96, and 0.90, and 0.87, 0.93, and 0.81, for non-sclerotic and sclerotic glomeruli, respectively. DL-derived and manual segmentation derived glomerular counts were comparable, but statistically different from reported glomerular count. Conclusions: DL segmentation is a feasible and robust approach for automatic quantification of glomeruli. This work represents the first step toward new protocols for the evaluation of donor kidney biopsies.

scholarly journals Deep Learning Global Glomerulosclerosis in Transplant Kidney Frozen Sections

2018 ◽  
Vol 37 (12) ◽  
pp. 2718-2728 ◽  
Author(s):  
Jon N. Marsh ◽  
Matthew K. Matlock ◽  
Satoru Kudose ◽  
Ta-Chiang Liu ◽  
Thaddeus S. Stappenbeck ◽  
...  
Keyword(s):  
Deep Learning ◽  
Frozen Sections ◽  
Transplant Kidney ◽  
Global Glomerulosclerosis

An Automated Method for the Determination of Serum Calcium with Glyoxal Bis (2-Hydroxyanil)

1967 ◽  
Vol 13 (6) ◽  
pp. 515-520 ◽  
Author(s):  
Genevieve Farese ◽  
Janice L Schmidt ◽  
Milton Mager
Keyword(s):  
Serum Calcium ◽  
Automated Analysis ◽  
Automated Method ◽  
Good Agreement

Abstract A completely automated analysis is described for the determination of serum calcium with glyoxal bis (2-hydroxyanil) solution (GBHA). The method is simple and precise, and the data obtained are in good agreement with results obtained by the manual GBHA procedure.

scholarly journals Predicting gastric cancer outcome from resected lymph node histopathology images using deep learning

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Xiaodong Wang ◽  
Ying Chen ◽  
Yunshu Gao ◽  
Huiqing Zhang ◽  
Zehui Guan ◽  
...  
Keyword(s):  
Gastric Cancer ◽  
Deep Learning ◽  
Lymph Node ◽  
Lymph Nodes ◽  
Main Method ◽  
Learning Framework ◽  
Prognostic Assessment ◽  
N Stage ◽  
Cancer Outcome ◽  
Whole Slide Images

AbstractN-staging is a determining factor for prognostic assessment and decision-making for stage-based cancer therapeutic strategies. Visual inspection of whole-slides of intact lymph nodes is currently the main method used by pathologists to calculate the number of metastatic lymph nodes (MLNs). Moreover, even at the same N stage, the outcome of patients varies dramatically. Here, we propose a deep-learning framework for analyzing lymph node whole-slide images (WSIs) to identify lymph nodes and tumor regions, and then to uncover tumor-area-to-MLN-area ratio (T/MLN). After training, our model’s tumor detection performance was comparable to that of experienced pathologists and achieved similar performance on two independent gastric cancer validation cohorts. Further, we demonstrate that T/MLN is an interpretable independent prognostic factor. These findings indicate that deep-learning models could assist not only pathologists in detecting lymph nodes with metastases but also oncologists in exploring new prognostic factors, especially those that are difficult to calculate manually.

Sign in / Sign up

Export Citation Format

Share Document