Artificial intelligence in prostate histopathology: where are we in 2021?

Oszwald, André; Wasinger, Gabriel; Pradère, Benjamin; Shariat, Shahrokh F.; Compérat, Éva

doi:10.1097/mou.0000000000000883

Cited by 5 publications

(8 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The application of artificial intelligence to the objective interpretation of biomedical images of all sorts, including e.g. micrographs, tomographs or endoscopies of cells 60 , tissues 61 , 62 or patients 63 , 64 , is becoming a mainstream paradigm to identify hidden patterns and support clinical decisions at any level. In the context of paper-based assays, for instance, A. Carrio et al developed a light box and a pipeline based on a multilayer perceptron artificial neural network for the classification of results from commercial lateral flow tests for the detection of drugs of abuse in the saliva 65 .…”

Section: Introductionmentioning

confidence: 99%

Paper-based genetic assays with bioconjugated gold nanorods and an automated readout pipeline

Borri

Centi

Chioccioli

et al. 2022

Sci Rep

View full text Add to dashboard Cite

Paper-based biosensors featuring immunoconjugated gold nanoparticles have gained extraordinary momentum in recent times as the platform of choice in key cases of field applications, including the so-called rapid antigen tests for SARS-CoV-2. Here, we propose a revision of this format, one that may leverage on the most recent advances in materials science and data processing. In particular, we target an amplifiable DNA rather than a protein analyte, and we replace gold nanospheres with anisotropic nanorods, which are intrinsically brighter by a factor of ~ 10, and multiplexable. By comparison with a gold-standard method for dot-blot readout with digoxigenin, we show that gold nanorods entail much faster and easier processing, at the cost of a higher limit of detection (from below 1 to 10 ppm in the case of plasmid DNA containing a target transgene, in our current setup). In addition, we test a complete workflow to acquire and process photographs of dot-blot membranes with custom-made hardware and regression tools, as a strategy to gain more analytical sensitivity and potential for quantification. A leave-one-out approach for training and validation with as few as 36 sample instances already improves the limit of detection reached by the naked eye by a factor around 2. Taken together, we conjecture that the synergistic combination of new materials and innovative tools for data processing may bring the analytical sensitivity of paper-based biosensors to approach the level of lab-grade molecular tests.

show abstract

Section: Introductionmentioning

confidence: 99%

Paper-based genetic assays with bioconjugated gold nanorods and an automated readout pipeline

Borri

Centi

Chioccioli

et al. 2022

Sci Rep

View full text Add to dashboard Cite

show abstract

“…The application of artificial intelligence to the objective interpretation of biomedical images of all sorts, including e.g. micrographs, tomographs or endoscopies of cells [56], tissues [57,58] or patients [59,60], is becoming a mainstream paradigm to identify hidden patterns and support clinical decisions at any level. In the context of paperbased assays, for instance, A. Carrio et al developed a light box and a pipeline based on a multilayer perceptron artificial neural network for the classification of results from commercial lateral flow tests for the detection of drugs of abuse in the saliva [61].…”

Section: Introductionmentioning

confidence: 99%

Paper-based genetic assays with bioconjugated gold nanorods and an automated readout pipeline

Borri¹,

Centi²,

Chioccioli³

et al. 2021

Preprint

View full text Add to dashboard Cite

BackgroundPaper-based biosensors featuring immunoconjugated gold nanoparticles have gained extraordinary momentum in recent times as the platform of choice in key cases of field applications, including the so-called rapid antigen tests for SARS-CoV-2. Here, we propose a revision of this format, one that may leverage on the most recent advances in materials science and data processing. In particular, we focus on an amplifiable DNA rather than a protein target, and we assess the replacement of gold nanospheres with anisotropic nanorods, which are about 10-fold brighter and multiplexable. ResultsBy comparison with a gold-standard method for dot-blot readout with digoxigenin, we show that gold nanorods entail much faster and easier processing, at the cost of a higher detection limit (from below 1 to 10 ppm in the case of plasmid DNA containing a target transgene). In addition, we test a complete workflow for systematic acquisition and machine-learning regression of photographs of dotblot membranes as a tool to gain more analytical sensitivity and potential for quantification. A leaveone-out strategy for training and validation with as few as 36 sample instances already improves the detection limit reached by the naked eye by a factor around 2. ConclusionsTaken together, we conjecture that the synergistic combination of new materials and innovative tools for data processing may bring the analytical sensitivity of paper-based biosensors to approach the level of lab-grade molecular tests.

show abstract

“…These virtual slides allow applications of different AI algorithms to identify different architectural patterns and other features required for the pathologic diagnosis of prostate cancer (PC). [4][5][6] PC diagnosis and Gleason grading in core needle biopsies (CNBs) of the prostate are critical for deciding further management of the patients. 7,8 Gleason grading on biopsies is a time-consuming task and suffers from poor interobserver reproducibility even among the subspecialized pathologists and results in either under-grading or over-grading of PC, [9][10][11][12][13][14][15] leading to under-treatment or over-treatment of PC patients.…”

mentioning

confidence: 99%

“…These advancements have the potential to automate multiple steps involved in the diagnosis of PC leading to quicker, more reliable, and more standardized diagnosis and hold the promise of reduced workload for pathologists. [4][5][6] This article includes an in-depth review of the current state of AI for PC diagnosis and prognosis, discuss the challenges and limitations of AI and highlights future prospect of AI in prostate pathology for improved patient care.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Artificial Intelligence-Enabled Prostate Cancer Diagnosis and Prognosis: Current State and Future Implications

Satturwar,

Parwani

2024

Advances in Anatomic Pathology

View full text Add to dashboard Cite

In this modern era of digital pathology, artificial intelligence (AI)-based diagnostics for prostate cancer has become a hot topic. Multiple retrospective studies have demonstrated the benefits of AI-based diagnostic solutions for prostate cancer that includes improved prostate cancer detection, quantification, grading, interobserver concordance, cost and time savings, and a potential to reduce pathologists’ workload and enhance pathology laboratory workflow. One of the major milestones is the Food and Drug Administration approval of Paige prostate AI for a second review of prostate cancer diagnosed using core needle biopsies. However, implementation of these AI tools for routine prostate cancer diagnostics is still lacking. Some of the limiting factors include costly digital pathology workflow, lack of regulatory guidelines for deployment of AI, and lack of prospective studies demonstrating the actual benefits of AI algorithms. Apart from diagnosis, AI algorithms have the potential to uncover novel insights into understanding the biology of prostate cancer and enable better risk stratification, and prognostication. This article includes an in-depth review of the current state of AI for prostate cancer diagnosis and highlights the future prospects of AI in prostate pathology for improved patient care.

show abstract

Artificial intelligence in prostate histopathology: where are we in 2021?

Cited by 5 publications

References 37 publications

Paper-based genetic assays with bioconjugated gold nanorods and an automated readout pipeline

Paper-based genetic assays with bioconjugated gold nanorods and an automated readout pipeline

Paper-based genetic assays with bioconjugated gold nanorods and an automated readout pipeline

Artificial Intelligence-Enabled Prostate Cancer Diagnosis and Prognosis: Current State and Future Implications

Contact Info

Product

Resources

About