Effective color transfer enables rapid computational microscopy for digital pathology

Context.— Pathologists may encounter extraneous pieces of tissue (tissue floaters) on glass slides because of specimen cross-contamination. Troubleshooting this problem, including performing molecular tests for tissue identification if available, is time consuming and often does not satisfactorily resolve the problem. Objective.— To demonstrate the feasibility of using an image search tool to resolve the tissue floater conundrum. Design.— A glass slide was produced containing 2 separate hematoxylin and eosin (H&E)-stained tissue floaters. This fabricated slide was digitized along with the 2 slides containing the original tumors used to create these floaters. These slides were then embedded into a dataset of 2325 whole slide images comprising a wide variety of H&E stained diagnostic entities. Digital slides were broken up into patches and the patch features converted into barcodes for indexing and easy retrieval. A deep learning-based image search tool was employed to extract features from patches via barcodes, hence enabling image matching to each tissue floater. Results.— There was a very high likelihood of finding a correct tumor match for the queried tissue floater when searching the digital database. Search results repeatedly yielded a correct match within the top 3 retrieved images. The retrieval accuracy improved when greater proportions of the floater were selected. The time to run a search was completed within several milliseconds. Conclusions.— Using an image search tool offers pathologists an additional method to rapidly resolve the tissue floater conundrum, especially for those laboratories that have transitioned to going fully digital for primary diagnosis.

Download Full-text

Spectroscopic and deep learning-based approaches to identify and quantify cerebral microhemorrhages

Scientific Reports ◽

10.1038/s41598-021-88236-1 ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Christian Crouzet ◽

Gwangjin Jeong ◽

Rachel H. Chae ◽

Krystal T. LoPresti ◽

Cody E. Dunn ◽

...

Keyword(s):

Deep Learning ◽

Prussian Blue ◽

Processing Speed ◽

Digital Pathology ◽

Ground Truth ◽

Individual Variability ◽

Rgb Images ◽

Cerebral Microhemorrhages ◽

Phasor Analysis ◽

Better Than

AbstractCerebral microhemorrhages (CMHs) are associated with cerebrovascular disease, cognitive impairment, and normal aging. One method to study CMHs is to analyze histological sections (5–40 μm) stained with Prussian blue. Currently, users manually and subjectively identify and quantify Prussian blue-stained regions of interest, which is prone to inter-individual variability and can lead to significant delays in data analysis. To improve this labor-intensive process, we developed and compared three digital pathology approaches to identify and quantify CMHs from Prussian blue-stained brain sections: (1) ratiometric analysis of RGB pixel values, (2) phasor analysis of RGB images, and (3) deep learning using a mask region-based convolutional neural network. We applied these approaches to a preclinical mouse model of inflammation-induced CMHs. One-hundred CMHs were imaged using a 20 × objective and RGB color camera. To determine the ground truth, four users independently annotated Prussian blue-labeled CMHs. The deep learning and ratiometric approaches performed better than the phasor analysis approach compared to the ground truth. The deep learning approach had the most precision of the three methods. The ratiometric approach has the most versatility and maintained accuracy, albeit with less precision. Our data suggest that implementing these methods to analyze CMH images can drastically increase the processing speed while maintaining precision and accuracy.

Download Full-text

Quality control stress test for deep learning-based diagnostic model in digital pathology

Modern Pathology ◽

10.1038/s41379-021-00859-x ◽

2021 ◽

Author(s):

Birgid Schömig-Markiefka ◽

Alexey Pryalukhin ◽

Wolfgang Hulla ◽

Andrey Bychkov ◽

Junya Fukuoka ◽

...

Keyword(s):

Deep Learning ◽

Cancer Detection ◽

Stress Testing ◽

Computational Analysis ◽

Stress Test ◽

Digital Pathology ◽

Model Performance ◽

Diagnostic Model ◽

Model Accuracy ◽

Diagnostic Models

AbstractDigital pathology provides a possibility for computational analysis of histological slides and automatization of routine pathological tasks. Histological slides are very heterogeneous concerning staining, sections’ thickness, and artifacts arising during tissue processing, cutting, staining, and digitization. In this study, we digitally reproduce major types of artifacts. Using six datasets from four different institutions digitized by different scanner systems, we systematically explore artifacts’ influence on the accuracy of the pre-trained, validated, deep learning-based model for prostate cancer detection in histological slides. We provide evidence that any histological artifact dependent on severity can lead to a substantial loss in model performance. Strategies for the prevention of diagnostic model accuracy losses in the context of artifacts are warranted. Stress-testing of diagnostic models using synthetically generated artifacts might be an essential step during clinical validation of deep learning-based algorithms.

Download Full-text

Genetic Perturbation of Pyruvate Dehydrogenase Kinase 1 Modulates Growth, Angiogenesis and Metabolic Pathways in Ovarian Cancer Xenografts

Cells ◽

10.3390/cells10020325 ◽

2021 ◽

Vol 10 (2) ◽

pp. 325

Author(s):

Carolina Venturoli ◽

Ilaria Piga ◽

Matteo Curtarello ◽

Martina Verza ◽

Giovanni Esposito ◽

...

Keyword(s):

Ovarian Cancer ◽

Cancer Cells ◽

Pyruvate Dehydrogenase ◽

Metabolic Pathways ◽

Negative Impact ◽

Digital Pathology ◽

Pyruvate Dehydrogenase Kinase ◽

Ovarian Cancer Cells ◽

Pyruvate Dehydrogenase Kinase 1

Pyruvate dehydrogenase kinase 1 (PDK1) blockade triggers are well characterized in vitro metabolic alterations in cancer cells, including reduced glycolysis and increased glucose oxidation. Here, by gene expression profiling and digital pathology-mediated quantification of in situ markers in tumors, we investigated effects of PDK1 silencing on growth, angiogenesis and metabolic features of tumor xenografts formed by highly glycolytic OC316 and OVCAR3 ovarian cancer cells. Notably, at variance with the moderate antiproliferative effects observed in vitro, we found a dramatic negative impact of PDK1 silencing on tumor growth. These findings were associated with reduced angiogenesis and increased necrosis in the OC316 and OVCAR3 tumor models, respectively. Analysis of viable tumor areas uncovered increased proliferation as well as increased apoptosis in PDK1-silenced OVCAR3 tumors. Moreover, RNA profiling disclosed increased glucose catabolic pathways—comprising both oxidative phosphorylation and glycolysis—in PDK1-silenced OVCAR3 tumors, in line with the high mitotic activity detected in the viable rim of these tumors. Altogether, our findings add new evidence in support of a link between tumor metabolism and angiogenesis and remark on the importance of investigating net effects of modulations of metabolic pathways in the context of the tumor microenvironment.

Download Full-text

A30 Tumor-Infiltrating Lymphocytes (TILs) Found Elevated in Lung Adenocarcinomas (LUAD) Using Automated Digital Pathology Masks Derived from Deep-Learning Models

Journal of Thoracic Oncology ◽

10.1016/j.jtho.2019.12.059 ◽

2020 ◽

Vol 15 (2) ◽

pp. S22

Author(s):

M.I. Jaber ◽

L. Beziaeva ◽

S.C. Benz ◽

S.K. Reddy ◽

S. Rabizadeh ◽

...

Keyword(s):

Deep Learning ◽

Digital Pathology ◽

Tumor Infiltrating Lymphocytes ◽

Learning Models ◽

Lung Adenocarcinomas ◽

Infiltrating Lymphocytes

Download Full-text

Two Ensemble-CNN Approaches for Colorectal Cancer Tissue Type Classification

Journal of Imaging ◽

10.3390/jimaging7030051 ◽

2021 ◽

Vol 7 (3) ◽

pp. 51

Author(s):

Emanuela Paladini ◽

Edoardo Vantaggiato ◽

Fares Bougourzi ◽

Cosimo Distante ◽

Abdenour Hadid ◽

...

Keyword(s):

Colorectal Cancer ◽

Deep Learning ◽

Digital Pathology ◽

Texture Features ◽

Tissue Type ◽

Cancer Tissue ◽

Learning Methods ◽

Feature Based ◽

Type Classification ◽

Whole Slide Images

In recent years, automatic tissue phenotyping has attracted increasing interest in the Digital Pathology (DP) field. For Colorectal Cancer (CRC), tissue phenotyping can diagnose the cancer and differentiate between different cancer grades. The development of Whole Slide Images (WSIs) has provided the required data for creating automatic tissue phenotyping systems. In this paper, we study different hand-crafted feature-based and deep learning methods using two popular multi-classes CRC-tissue-type databases: Kather-CRC-2016 and CRC-TP. For the hand-crafted features, we use two texture descriptors (LPQ and BSIF) and their combination. In addition, two classifiers are used (SVM and NN) to classify the texture features into distinct CRC tissue types. For the deep learning methods, we evaluate four Convolutional Neural Network (CNN) architectures (ResNet-101, ResNeXt-50, Inception-v3, and DenseNet-161). Moreover, we propose two Ensemble CNN approaches: Mean-Ensemble-CNN and NN-Ensemble-CNN. The experimental results show that the proposed approaches outperformed the hand-crafted feature-based methods, CNN architectures and the state-of-the-art methods in both databases.

Download Full-text