Learning-based cell detection in digital pathology

This is a description of a novel combination of chromogenic multiplex immunohistochemistry, digital pathology, computer-aided cell detection and topographical analysis of tumor tissue to allow a detailed study of the immune infiltrate. This is applied to a rare clinical case, where a tumor sample is available from an infant with metastatic neuroblastoma at the point of spontaneous regression. This allowed detailed analysis of the immune infiltrate, including spatial distribution and phenotype of lymphoid and myeloid populations, with a distinction between heterogeneous areas within the intra- and extra- tumoral immune microenvironments. The mechanism of spontaneous regression in congenital neuroblastoma is poorly understood, but the data obtained suggested an immune-mediated phenomenon, characterised by an adaptive T cell driven response with a significant delayed-type hypersensitivity (granulomatous) component.

Download Full-text

Automatic ganglion cell detection for improving the efficiency and accuracy of hirschprung disease diagnosis

Scientific Reports ◽

10.1038/s41598-021-82869-y ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Ariel Greenberg ◽

Asaf Aizic ◽

Asia Zubkov ◽

Sarah Borsekofsky ◽

Rami R. Hagege ◽

...

Keyword(s):

Validation Cohort ◽

Ganglion Cells ◽

Digital Pathology ◽

Disease Diagnosis ◽

Cell Detection ◽

Expert Consultation ◽

Normal Colon ◽

Histopathologic Diagnosis ◽

Improve Accuracy ◽

And Training

AbstractHistopathologic diagnosis of Hirschsprung's disease (HSCR) is time consuming and requires expertise. The use of artificial intelligence (AI) in digital pathology is actively researched and may improve the diagnosis of HSCR. The purpose of this research was to develop an algorithm capable of identifying ganglion cells in digital pathology slides and implement it as an assisting tool for the pathologist in the diagnosis of HSCR. Ninety five digital pathology slides were used for the construction and training of the algorithm. Fifty cases suspected for HSCR (727 slides) were used as a validation cohort. Image sets suspected to contain ganglion cells were chosen by the algorithm and then reviewed and scored by five pathologists, one HSCR expert and 4 non-experts. The algorithm was able to identify ganglion cells with 96% sensitivity and 99% specificity (in normal colon) as well as to correctly identify a case previously misdiagnosed as non-HSCR. The expert was able to achieve perfectly accurate diagnoses based solely on the images suggested by the algorithm, with over 95% time saved. Non-experts would require expert consultation in 20–58% of the cases to achieve similar results. The use of AI in the diagnosis of HSCR can greatly reduce the time and effort required for diagnosis and improve accuracy.

Download Full-text

The future of artificial intelligence in digital pathology - results of a survey across stakeholder groups

10.1101/2021.12.16.472990 ◽

2021 ◽

Author(s):

Celine N Heinz ◽

Amelie Echle ◽

Sebastian Foersch ◽

Andrey Bychkov ◽

Jakob Nikolas Kather

Keyword(s):

Artificial Intelligence ◽

Treatment Response ◽

Online Survey ◽

Digital Pathology ◽

Genetic Alterations ◽

Future Application ◽

Cell Detection ◽

Tissue Segmentation ◽

Computational Pathology ◽

Near Future

Artificial intelligence (AI) provides a powerful tool to extract information from digitized histopathology whole slide images. In the last five years, academic and commercial actors have developed new technical solutions for a diverse set of tasks, including tissue segmentation, cell detection, mutation prediction, prognostication and prediction of treatment response. In the light of limited overall resources, it is presently unclear for researchers, practitioners and policymakers which of these topics are stable enough for clinical use in the near future and which topics are still experimental, but worth investing time and effort into. To identify potentially promising applications of AI in pathology, we performed an anonymous online survey of 75 computational pathology domain experts from academia and industry. Participants enrolled in 2021 were queried about their subjective opinion on promising and appealing sub-fields of computational pathology with a focus on solid tumors. The results of this survey indicate that the prediction of treatment response directly from routine pathology slides is regarded as the most promising future application. This item was ranked highest in the overall analysis and in sub-groups by age and professional background. Furthermore, prediction of genetic alterations, gene expression and survival directly from routine pathology images scored consistently high across subgroups. Together, these data demonstrate a possible direction for the development of computational pathology systems in clinical, academic and industrial research in the near future.

Download Full-text

Advances in digital pathology

International Journal of Emerging Trends in Health Sciences ◽

10.18844/ijeths.v1i2.3107 ◽

2018 ◽

Vol 1 (2) ◽

pp. 33-39

Author(s):

Evgin Goceri

Keyword(s):

Digital Pathology ◽

Computer Assisted ◽

Cell Detection ◽

Tissue Samples ◽

Nuclei Segmentation ◽

New Ideas ◽

Assisted Diagnosis ◽

Tissue Specimens ◽

Validation Of Results

Characterization of cancer diseases and preparation of diagnostic reports after analyzing tissue specimens and several cell samples are provided by pathologists. One of the most successful strategies in pathology is to divide tumors into different subtypes and to adapt the treatment for each tumor. However, this approach has put a big burden on pathologists, who are reviewing tissue samples under the light of the microscope. Because, tumors have about 200 subtypes and pathologies are facing a growing demand for accurate and fast diagnosis and also patient safety. Therefore, digital pathology has been important and growing rapidly. Advances in computer technology such as computing power, faster networks and cheaper storage have enabled pathologists to manage images more easily than in the last decade. Novel pathology tools have a potential for automated and faster diagnosis and also better management of data. Moreover, it enables re-reducibility, validation of results, quality assurance and sharing of new ideas at anywhere and anytime. Advances in digital pathology have been reviewed in this paper. It seems that innovations in technologies will not only provide important improvements in pathology service, but also they will change healthcare and research fundamentally despite some challenges. Keywords: Cell detection, computer assisted diagnosis, digital pathology, image analysis, nuclei segmentation, tissue classification.

Download Full-text

Insulin-induced internalization of the insulin receptor in the isolated rat adipose cell. Detection of both major receptor subunits following their biosynthetic labeling in culture

Diabetes ◽

10.2337/diabetes.33.1.13 ◽

1984 ◽

Vol 33 (1) ◽

pp. 13-18 ◽

Cited By ~ 5

Author(s):

I. A. Simpson ◽

J. A. Hedo ◽

S. W. Cushman

Keyword(s):

Insulin Receptor ◽

Cell Detection ◽

Adipose Cell ◽

Isolated Rat

Download Full-text

Leukemic Stem Cell Detection in Bone Marrow for CML Patients With MMR Undergoing TKIs

Case Medical Research ◽

10.31525/ct1-nct04104035 ◽

2019 ◽

Author(s):

Keyword(s):

Bone Marrow ◽

Stem Cell ◽

Cell Detection ◽

Leukemic Stem Cell

Download Full-text

Neutrophil/lymphocyte Ratio after Flow Citometry Periferic Blood Cell Detection - Predictive Marker of Anastomotic Fistula in Colorectal Cancer Surgery

Revista de Chimie ◽

10.37358/rc.20.6.8195 ◽

2020 ◽

Vol 71 (6) ◽

pp. 295-306

Author(s):

Dumitru Radulescu ◽

Vlad Dumitru Baleanu ◽

Andrei Nicolaescu ◽

Marius Lazar ◽

Marius Bica ◽

...

Keyword(s):

Colorectal Cancer ◽

Cancer Patients ◽

Rectal Surgery ◽

Predictive Marker ◽

Fistula Formation ◽

Cell Detection ◽

Colon And Rectal Surgery ◽

Optimal Value ◽

Anastomotic Fistula ◽

Colorectal Cancer Patients

Anastomotic fistula is a dreadful complication of colon and rectal surgery that can put life into danger, being common after colorectal surgery. The preoperative lymphocyte neutrophil ratio (NLR) is known as a prognostic marker for colorectal cancer patients. The existence of a predictive marker of anastomotic fistula in colorectal cancer patients is not fully undestood, so we proposed to investigate the utility of preoperative NLR as a predictor of anastomotic fistula formation. This study the Neutrophils and lymphocytes were detected from periferic blood using flow citometry. We retrospectively evaluated 161 patients with colorectal cancer, who were treated curatively, in which at least one anastomosis was performed, comparing NLR values between patients who had fistula and those with normal healing, then comparing the group with low NLR, with the group with increased NLR, after finding the optimal value of NLR using the ROC curve.The optimal value of the NLR after establishing the cutoff value was 3.07. Between the low NLR group (n=134) and the high NLR group (n=27), were observed statistically significant differences in fistula (p [0.001) and death (p=0.001). The odds ratio for failure in the group with increased NLR was 10.37, which means that patients with NLR]3.54 have a chance of developing anastomotic fistula greater than 10.37 comparable to patients with lower NLR. We suggest the preoperative use of NLR can be used as a predictive marker of anastomotic fistula than can increase the quality of preoperative preparation and therefore the establishment of the optimal surgical technique that can lead to anastomotic fistula risk decrease.

Download Full-text

A Digital Pathology Solution to Resolve the Tissue Floater Conundrum

Archives of Pathology & Laboratory Medicine ◽

10.5858/arpa.2020-0034-oa ◽

2020 ◽

Author(s):

Liron Pantanowitz ◽

Pamela Michelow ◽

Scott Hazelhurst ◽

Shivam Kalra ◽

Charles Choi ◽

...

Keyword(s):

Digital Pathology ◽

Primary Diagnosis ◽

Image Search ◽

Molecular Tests ◽

Tissue Identification ◽

Digital Database ◽

Glass Slides ◽

Search Tool ◽

Hematoxylin And Eosin ◽

Whole Slide Images

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