Next-Generation Digital Histopathology of the Tumor Microenvironment DOI Open Access
Felicitas Mungenast,

Achala Fernando,

Robert Nica

и другие.

Genes, Год журнала: 2021, Номер 12(4), С. 538 - 538

Опубликована: Апрель 7, 2021

Progress in cancer research is substantially dependent on innovative technologies that permit a concerted analysis of the tumor microenvironment and cellular phenotypes resulting from somatic mutations post-translational modifications. In view large number genes, multiplied by differential splicing as well protein modifications, ability to identify quantify actual individual cell populations situ, i.e., their tissue environment, has become prerequisite for understanding tumorigenesis progression. The need quantitative analyses led renaissance optical instruments imaging techniques. With emergence precision medicine, automated constantly increasing markers measurement spatial context have increasingly necessary understand molecular mechanisms lead different pathways disease progression patients. this review, we summarize joint effort academia industry undertaken establish methods protocols profiling immunophenotyping tissues next-generation digital histopathology—which characterized use whole-slide (brightfield, widefield fluorescence, confocal, multispectral, and/or multiplexing technologies) combined with state-of-the-art image cytometry advanced machine deep learning.

Язык: Английский

Explainable artificial intelligence (XAI) in deep learning-based medical image analysis DOI Creative Commons
Bas H. M. van der Velden, Hugo J. Kuijf, Kenneth G. A. Gilhuijs

и другие.

Medical Image Analysis, Год журнала: 2022, Номер 79, С. 102470 - 102470

Опубликована: Май 4, 2022

With an increase in deep learning-based methods, the call for explainability of such methods grows, especially high-stakes decision making areas as medical image analysis. This survey presents overview eXplainable Artificial Intelligence (XAI) used A framework XAI criteria is introduced to classify analysis methods. Papers on techniques are then surveyed and categorized according anatomical location. The paper concludes with outlook future opportunities

Язык: Английский

Процитировано

685
DeepImageJ: A user-friendly environment to run deep learning models in ImageJ DOI
Estibaliz Gómez‐de‐Mariscal,

Carlos García-López-de-Haro,

Wei Ouyang

и другие.

Nature Methods, Год журнала: 2021, Номер 18(10), С. 1192 - 1195

Опубликована: Сен. 30, 2021

Язык: Английский

Процитировано

195
Medical image data augmentation: techniques, comparisons and interpretations DOI Open Access
Evgin Göçeri

Artificial Intelligence Review, Год журнала: 2023, Номер 56(11), С. 12561 - 12605

Опубликована: Март 20, 2023

Язык: Английский

Процитировано

190
A survey on applications of deep learning in microscopy image analysis DOI
Zhichao Liu, Luhong Jin, Jincheng Chen

и другие.

Computers in Biology and Medicine, Год журнала: 2021, Номер 134, С. 104523 - 104523

Опубликована: Май 29, 2021

Язык: Английский

Процитировано

126
The Cell Tracking Challenge: 10 years of objective benchmarking DOI Creative Commons
Martin Maška, Vladimír Ulman, Pablo Delgado-Rodriguez

и другие.

Nature Methods, Год журнала: 2023, Номер 20(7), С. 1010 - 1020

Опубликована: Май 18, 2023

Abstract The Cell Tracking Challenge is an ongoing benchmarking initiative that has become a reference in cell segmentation and tracking algorithm development. Here, we present significant number of improvements introduced the challenge since our 2017 report. These include creation new segmentation-only benchmark, enrichment dataset repository with datasets increase its diversity complexity, silver standard corpus based on most competitive results, which will be particular interest for data-hungry deep learning-based strategies. Furthermore, up-to-date leaderboards, in-depth analysis relationship between performance state-of-the-art methods properties annotations, two novel, insightful studies about generalizability reusability top-performing methods. provide critical practical conclusions both developers users traditional machine algorithms.

Язык: Английский

Процитировано

103
AI‐organoid integrated systems for biomedical studies and applications DOI Creative Commons

Sudhiksha Maramraju,

Andrew Kowalczewski,

Anirudh Kaza

и другие.

Bioengineering & Translational Medicine, Год журнала: 2024, Номер 9(2)

Опубликована: Янв. 20, 2024

Abstract In this review, we explore the growing role of artificial intelligence (AI) in advancing biomedical applications human pluripotent stem cell (hPSC)‐derived organoids. Stem cell‐derived organoids, these miniature organ replicas, have become essential tools for disease modeling, drug discovery, and regenerative medicine. However, analyzing vast intricate datasets generated from organoids can be inefficient error‐prone. AI techniques offer a promising solution to efficiently extract insights make predictions diverse data types microscopy images, transcriptomics, metabolomics, proteomics. This review offers brief overview organoid characterization fundamental concepts while focusing on comprehensive exploration organoid‐based modeling evaluation. It provides into future possibilities enhancing quality control fabrication, label‐free recognition, three‐dimensional image reconstruction complex structures. presents challenges potential solutions AI‐organoid integration, establishment reliable model decision‐making processes standardization research.

Язык: Английский

Процитировано

19
Advanced imaging and labelling methods to decipher brain cell organization and function DOI
Daniel Choquet, Matthieu Sainlos, Jean‐Baptiste Sibarita

и другие.

Nature reviews. Neuroscience, Год журнала: 2021, Номер 22(4), С. 237 - 255

Опубликована: Март 12, 2021

Язык: Английский

Процитировано

95
VoxelEmbed: 3D Instance Segmentation and Tracking with Voxel Embedding based Deep Learning DOI
Mengyang Zhao, Quan Liu,

Aadarsh Jha

и другие.

Lecture notes in computer science, Год журнала: 2021, Номер unknown, С. 437 - 446

Опубликована: Янв. 1, 2021

Язык: Английский

Процитировано

85
Open-source deep-learning software for bioimage segmentation DOI
Alice Lucas, Pearl V. Ryder, Bin Li

и другие.

Molecular Biology of the Cell, Год журнала: 2021, Номер 32(9), С. 823 - 829

Опубликована: Апрель 19, 2021

Microscopy images are rich in information about the dynamic relationships among biological structures. However, extracting this complex can be challenging, especially when structures closely packed, distinguished by texture rather than intensity, and/or low intensity relative to background. By learning from large amounts of annotated data, deep accomplish several previously intractable bioimage analysis tasks. Until past few years, however, most deep-learning workflows required significant computational expertise applied. Here, we survey new open-source software tools that aim make deep-learning–based image segmentation accessible biologists with limited experience. These take many different forms, such as web apps, plug-ins for existing imaging software, and preconfigured interactive notebooks pipelines. In addition surveying these tools, overview challenges remain field. We hope expand awareness powerful available analysis.

Язык: Английский

Процитировано

64
Beauty Is in the AI of the Beholder: Are We Ready for the Clinical Integration of Artificial Intelligence in Radiography? An Exploratory Analysis of Perceived AI Knowledge, Skills, Confidence, and Education Perspectives of UK Radiographers DOI Creative Commons
Clare Rainey, Tracy O’Regan, Jacqueline Matthew

и другие.

Frontiers in Digital Health, Год журнала: 2021, Номер 3

Опубликована: Ноя. 11, 2021

Introduction: The use of artificial intelligence (AI) in medical imaging and radiotherapy has been met with both scepticism excitement. However, clinical integration AI is already well-underway. Many authors have recently reported on the knowledge perceptions radiologists/medical staff students however there a paucity information regarding radiographers. Published literature agrees that likely to significant impact radiology practice. As radiographers are at forefront service delivery, an awareness current level their perceived knowledge, skills, confidence essential identify any educational needs necessary for successful adoption into Aim: aim this survey was determine amongst UK highlight priorities provisions support digital healthcare ecosystem. Methods: A created Qualtrics® promoted via social media (Twitter®/LinkedIn®). This open all radiographers, including retired Participants were recruited by convenience, snowball sampling. Demographic gathered as well data perceived, self-reported, respondents. Insight what participants understand term "AI" gained means free text response. Quantitative analysis performed using SPSS® qualitative thematic NVivo®. Results: Four hundred eleven responses collected (80% from diagnostic radiography 20% background), broadly representative workforce distribution UK. Although many respondents stated they understood concept general (78.7% 52.1% therapeutic respondents, respectively) notable lack sufficient principles, understanding terminology, technology. participants, 57% 49% do not feel adequately trained implement setting. Furthermore 52% 64%, respectively, said developed skill whilst 62% 55%, enough training majority indicate urgent need further education (77.4% 73.9% feeling had adequate AI), stating educate themselves gain some basic skills. Notable correlations between working gender, age, highest qualification reported. Conclusion: Knowledge applications practitioners applications. results applying solutions but also underline formalised prepare prospective upcoming healthcare, safely efficiently navigate future. Focus should be given different learners depending ensure optimal integration.

Язык: Английский

Процитировано

62