Measuring digital pathology throughput and tissue dropouts

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

Deep bilinear features for Her2 scoring in digital pathology

Current Directions in Biomedical Engineering ◽

10.1515/cdbme-2017-0171 ◽

2017 ◽

Vol 3 (2) ◽

pp. 811-814 ◽

Cited By ~ 4

Author(s):

Erik Rodner ◽

Marcel Simon ◽

Joachim Denzler

Keyword(s):

Digital Pathology ◽

Training Data ◽

Large Set ◽

Second Order Statistics ◽

Over Expression ◽

Point Of Interest ◽

Winning Team ◽

Image Patches ◽

Parameterized Model ◽

The University

AbstractWe present an automated approach for rating HER2 over-expressions in given whole-slide images of breast cancer histology slides. The slides have a very high resolution and only a small part of it is relevant for the rating.Our approach is based on Convolutional Neural Networks (CNN), which are directly modelling the whole computer vision pipeline, from feature extraction to classification, with a single parameterized model. CNN models have led to a significant breakthrough in a lot of vision applications and showed promising results for medical tasks. However, the required size of training data is still an issue. Our CNN models are pre-trained on a large set of datasets of non-medical images, which prevents over-fitting to the small annotated dataset available in our case. We assume the selection of the probe in the data with just a single mouse click defining a point of interest. This is reasonable especially for slices acquired together with another sample. We sample image patches around the point of interest and obtain bilinear features by passing them through a CNN and encoding the output of the last convolutional layer with its second-order statistics.Our approach ranked second in the Her2 contest held by the University of Warwick achieving 345 points compared to 348 points of the winning team. In addition to pure classification, our approach would also allow for localization of parts of the slice relevant for visual detection of Her2 over-expression.

Download Full-text

The Artificial Intelligence in Digital Pathology and Digital Radiology: Where Are We?

Healthcare ◽

10.3390/healthcare9010030 ◽

2020 ◽

Vol 9 (1) ◽

pp. 30

Author(s):

Daniele Giansanti

Keyword(s):

Artificial Intelligence ◽

Information And Communication Technology ◽

Communication Technology ◽

Mobile Health ◽

Digital Pathology ◽

Digital Radiology ◽

Cellular Diagnostics ◽

Information And Communication ◽

Electronic Health ◽

New Applications

Thanks to the incredible changes promoted by Information and Communication Technology (ICT) conveyed today by electronic-health (eHealth) and mobile-health (mHealth), many new applications of both organ and cellular diagnostics are now possible [...]

Download Full-text

Overcoming Educational Challenges and Impact of COVID-19 in a Pathology Residency Program

Academic Pathology ◽

10.1177/2374289521994235 ◽

2021 ◽

Vol 8 ◽

pp. 237428952199423

Author(s):

Andres E. Mindiola Romero ◽

Candice C. Black ◽

Christopher R. Jackson

Keyword(s):

New Hampshire ◽

Medical Center ◽

Digital Pathology ◽

Clinical Pathology ◽

Daily Basis ◽

Medical Examiner ◽

Learning Needs ◽

Digital Platforms ◽

Social Distancing ◽

Personal Learning

Our program in is a 4-year combined anatomic pathology (AP) and clinical pathology (CP) program located in New Hampshire. Prior to the novel coronavirus (COVID-19) pandemic, double-headed sign-outs and multi-headed scope didactic conferences took place daily. On the autopsy service, cases were performed in-house under attending supervision, and forensic cases were performed at the off-site Office of the Medical Examiner. In CP, residents engaged in weekly didactic CP lectures and engaged in in-person resident-attending discussions, laboratory rounds, and direct patient contact on a daily basis. Institutional Universal Guidelines from the Emergency Order from New Hampshire were imposed at the beginning of the pandemic. These included exposure mitigation and employee screening strategies. Changes to resident rotations and didactic sessions, strategies to maintain resident wellness, and the program director perspectives are described. Amid the pandemic, digital pathology, teleconferencing platforms, and social media became important resources for pathology education. Digital platforms allowed groups of people to communicate and watch live presentations while social distancing. In AP, whole slide imaging allowed both attendings and residents to scan slides for personal learning, slide conferences, and didactic learning sessions. Following these measures, we supported the clinical needs of our medical center and learning needs of our residents while enacting social distancing and prevention guidelines early in the pandemic. Although the full impact of COVID-19 on pathology residency programs is still unknown, we incorporated new facets of communication technologies. These were immensely helpful in maintaining social distancing and helping to reduce the spread of disease.

Download Full-text

A deep-learning-based prognostic nomogram integrating microscopic digital pathology and macroscopic magnetic resonance images in nasopharyngeal carcinoma: a multi-cohort study

Therapeutic Advances in Medical Oncology ◽

10.1177/1758835920971416 ◽

2020 ◽

Vol 12 ◽

pp. 175883592097141

Author(s):

Fan Zhang ◽

Lian-Zhen Zhong ◽

Xun Zhao ◽

Di Dong ◽

Ji-Jin Yao ◽

...

Keyword(s):

Deep Learning ◽

Magnetic Resonance ◽

Nasopharyngeal Carcinoma ◽

Treatment Failure ◽

Digital Pathology ◽

Imaging Features ◽

Multi Scale ◽

External Test ◽

Whole Slide Images ◽

Independent Cohort

Background: To explore the prognostic value of radiomics-based and digital pathology-based imaging biomarkers from macroscopic magnetic resonance imaging (MRI) and microscopic whole-slide images for patients with nasopharyngeal carcinoma (NPC). Methods: We recruited 220 NPC patients and divided them into training ( n = 132), internal test ( n = 44), and external test ( n = 44) cohorts. The primary endpoint was failure-free survival (FFS). Radiomic features were extracted from pretreatment MRI and selected and integrated into a radiomic signature. The histopathological signature was extracted from whole-slide images of biopsy specimens using an end-to-end deep-learning method. Incorporating two signatures and independent clinical factors, a multi-scale nomogram was constructed. We also tested the correlation between the key imaging features and genetic alternations in an independent cohort of 16 patients (biological test cohort). Results: Both radiomic and histopathologic signatures presented significant associations with treatment failure in the three cohorts (C-index: 0.689–0.779, all p < 0.050). The multi-scale nomogram showed a consistent significant improvement for predicting treatment failure compared with the clinical model in the training (C-index: 0.817 versus 0.730, p < 0.050), internal test (C-index: 0.828 versus 0.602, p < 0.050) and external test (C-index: 0.834 versus 0.679, p < 0.050) cohorts. Furthermore, patients were stratified successfully into two groups with distinguishable prognosis (log-rank p < 0.0010) using our nomogram. We also found that two texture features were related to the genetic alternations of chromatin remodeling pathways in another independent cohort. Conclusion: The multi-scale imaging features showed a complementary value in prognostic prediction and may improve individualized treatment in NPC.

Download Full-text