Artificial intelligence and digital pathology: clinical promise and deployment considerations DOI Open Access
Mark D. Zarella, David S. McClintock, Harsh Vardhan Batra

et al.

Journal of Medical Imaging, Journal Year: 2023, Volume and Issue: 10(05)

Published: July 31, 2023

Artificial intelligence (AI) presents an opportunity in anatomic pathology to provide quantitative objective support a traditionally subjective discipline, thereby enhancing clinical workflows and enriching diagnostic capabilities. AI requires access digitized materials, which, at present, are most commonly generated from the glass slide using whole-slide imaging. Models developed collaboratively or sourced externally, best practices suggest validation with internal datasets closely resembling data expected practice. Although array of models that operational for improve quality capabilities has been described, them can be categorized into one more discrete types. However, their function workflow vary, as single algorithm may appropriate screening triage, assistance, virtual second opinion, other uses depending on how it is implemented validated. Despite promise AI, barriers adoption have numerous, which inclusion new stakeholders expansion reimbursement opportunities among impactful solutions.

Language: Английский

Research on Artificial-Intelligence-Assisted Medicine: A Survey on Medical Artificial Intelligence DOI Creative Commons
Fangfang Gou, Jun Liu,

Chunwen Xiao

et al.

Diagnostics, Journal Year: 2024, Volume and Issue: 14(14), P. 1472 - 1472

Published: July 9, 2024

With the improvement of economic conditions and increase in living standards, people's attention regard to health is also continuously increasing. They are beginning place their hopes on machines, expecting artificial intelligence (AI) provide a more humanized medical environment personalized services, thus greatly expanding supply bridging gap between resource demand. development IoT technology, arrival 5G 6G communication era, enhancement computing capabilities particular, application AI-assisted healthcare have been further promoted. Currently, research field assistance deepening expanding. AI holds immense value has many potential applications institutions, patients, professionals. It ability enhance efficiency, reduce costs, improve quality intelligent service experience for professionals patients. This study elaborates history timelines field, types technologies informatics, opportunities challenges medicine. The combination profound impact human life, improving levels life changing lifestyles.

Language: Английский

Citations

19
Cancer associated fibroblasts in cancer development and therapy DOI Creative Commons

Hongyuan Jia,

Xingmin Chen,

Linling Zhang

et al.

Journal of Hematology & Oncology, Journal Year: 2025, Volume and Issue: 18(1)

Published: March 28, 2025

Cancer-associated fibroblasts (CAFs) are key players in cancer development and therapy, they exhibit multifaceted roles the tumor microenvironment (TME). From their diverse cellular origins, CAFs undergo phenotypic functional transformation upon interacting with cells presence can adversely influence treatment outcomes severity of cancer. Emerging evidence from single-cell RNA sequencing (scRNA-seq) studies have highlighted heterogeneity plasticity CAFs, subtypes identifiable through distinct gene expression profiles properties. multiple mechanisms, including regulation extracellular matrix (ECM) remodeling, direct promotion growth provision metabolic support, promoting epithelial-mesenchymal transition (EMT) to enhance invasiveness growth, as well stimulating stem cell properties within tumor. Moreover, induce an immunosuppressive TME contribute therapeutic resistance. In this review, we summarize fundamental knowledge recent advances regarding focusing on sophisticated potential targets. We discuss various strategies target ECM modulation, elimination, interruption CAF-TME crosstalk, CAF normalization, approaches developing more effective treatments. An improved understanding complex interplay between is crucial for new targeted therapies

Language: Английский

Citations

2
Virtual alignment of pathology image series for multi-gigapixel whole slide images DOI Creative Commons
Chandler Gatenbee, Ann‐Marie Baker, Sandhya Prabhakaran

et al.

Nature Communications, Journal Year: 2023, Volume and Issue: 14(1)

Published: July 26, 2023

Interest in spatial omics is on the rise, but generation of highly multiplexed images remains challenging, due to cost, expertise, methodical constraints, and access technology. An alternative approach register collections whole slide (WSI), generating spatially aligned datasets. WSI registration a two-part problem, first being alignment itself second application transformations huge multi-gigapixel images. To address both challenges, we developed Virtual Alignment pathoLogy Image Series (VALIS), software which enables by aligning any number brightfield and/or immunofluorescent WSI, results can be saved ome.tiff format. Benchmarking using publicly available datasets indicates VALIS provides state-of-the-art accuracy 3D reconstruction. Leveraging existing open-source tools, written Python, providing free, fast, scalable, robust, easy-to-use pipeline for registering facilitating downstream analyses.

Language: Английский

Citations

32
Uncovering the spatial landscape of molecular interactions within the tumor microenvironment through latent spaces DOI Creative Commons
Atul Deshpande, Melanie Loth, Dimitrios N. Sidiropoulos

et al.

Cell Systems, Journal Year: 2023, Volume and Issue: 14(4), P. 285 - 301.e4

Published: April 1, 2023

Language: Английский

Citations

23
PanIN and CAF transitions in pancreatic carcinogenesis revealed with spatial data integration DOI

Alexander T.F. Bell,

Jacob T. Mitchell, Ashley Kiemen

et al.

Cell Systems, Journal Year: 2024, Volume and Issue: 15(8), P. 753 - 769.e5

Published: Aug. 1, 2024

Language: Английский

Citations

13
Mapping cell-to-tissue graphs across human placenta histology whole slide images using deep learning with HAPPY DOI Creative Commons
Claudia Vanea, Jelisaveta Džigurski, Valentina Rukins

et al.

Nature Communications, Journal Year: 2024, Volume and Issue: 15(1)

Published: March 28, 2024

Abstract Accurate placenta pathology assessment is essential for managing maternal and newborn health, but the placenta’s heterogeneity temporal variability pose challenges histology analysis. To address this issue, we developed ‘Histology Analysis Pipeline.PY’ (HAPPY), a deep learning hierarchical method quantifying of cells micro-anatomical tissue structures across whole slide images. HAPPY differs from patch-based features or segmentation approaches by following an interpretable biological hierarchy, representing cellular communities within tissues at single-cell resolution We present set quantitative metrics healthy term placentas as baseline future assessments health show how these deviate in with clinically significant placental infarction. HAPPY’s cell predictions closely replicate those independent clinical experts biology literature.

Language: Английский

Citations

12
AI-driven 3D bioprinting for regenerative medicine: From bench to bedside DOI
Huajin Zhang, Xianhao Zhou, Yongcong Fang

et al.

Bioactive Materials, Journal Year: 2024, Volume and Issue: 45, P. 201 - 230

Published: Nov. 23, 2024

Language: Английский

Citations

11
High‐Resolution 3D Printing of Pancreatic Ductal Microanatomy Enabled by Serial Histology DOI
Ashley Kiemen,

André Forjaz,

Ricardo Sousa

et al.

Advanced Materials Technologies, Journal Year: 2024, Volume and Issue: 9(6)

Published: Jan. 20, 2024

Abstract Pancreatic ductal adenocarcinoma (PDAC) is a deadly cancer that can develop from pancreatic intraepithelial neoplasia (PanIN), microscopic lesion in the system. PanIN and PDAC are conventionally studied 2D via histological tissue sections. As such, their true structure poorly understood due to inability image them 3D. CODA, recently developed technique for reconstruction of tissues at cellular resolution, used study 3D morphology pancreas. Here, CODA extended through printing normal ducts, PanIN, cm‐scale µm resolution. A methodology presented create printable files anatomical maps generated serial images show detailed validation accuracy this method. Existing workflows utilizing medical derived computerized tomography (CT), X‐ray, magnetic resonance imaging (MRI) scientifically proven be useful whole organ‐scale structures with sub‐mm using sections, it demonstrated higher‐resolution also possible. Finally, models PDAC, marked changes human pancreas during tumorigenesis revealed.

Language: Английский

Citations

10
Spatial landmark detection and tissue registration with deep learning DOI Creative Commons
Markus Ekvall,

Ludvig Bergenstråhle,

Alma Andersson

et al.

Nature Methods, Journal Year: 2024, Volume and Issue: 21(4), P. 673 - 679

Published: March 4, 2024

Abstract Spatial landmarks are crucial in describing histological features between samples or sites, tracking regions of interest microscopy, and registering tissue within a common coordinate framework. Although other studies have explored unsupervised landmark detection, existing methods not well-suited for image data as they often require large number images to converge, unable handle nonlinear deformations sections ineffective z -stack alignment, modalities beyond multimodal data. We address these challenges by introducing effortless new detection registration method using neural-network-guided thin-plate splines. Our proposed is evaluated on diverse range datasets including histology spatially resolved transcriptomics, demonstrating superior performance both accuracy stability compared approaches.

Language: Английский

Citations

10
Exploring chronic and transient tumor hypoxia for predicting the efficacy of hypoxia-activated pro-drugs DOI Creative Commons
Shreya Mathur,

Shannon Chen,

Katarzyna A. Rejniak

et al.

npj Systems Biology and Applications, Journal Year: 2024, Volume and Issue: 10(1)

Published: Jan. 5, 2024

Abstract Hypoxia, a low level of oxygen in the tissue, arises due to an imbalance between vascular supply and demand by surrounding cells. Typically, hypoxia is viewed as negative marker patients’ survival, because its implication development aggressive tumors tumor resistance. Several drugs that specifically target hypoxic cells have been developed, providing opportunity for exploiting improve cancer treatment. Here, we consider combinations hypoxia-activated pro-drugs (HAPs) two compounds transiently increase intratumoral hypoxia: vasodilator metabolic sensitizer. To effectively design treatment protocols with multiple used mathematical micro-pharmacology modeling determined schedules take advantage heterogeneous dynamically changing oxygenation tissue. Our model was based on data from murine pancreatic cancers treated evofosfamide (as HAP) either hydralazine vasodilator), or pyruvate sensitizer). Subsequently, this identify optimal different combinations. simulations showed HAPs had bimodal distribution, while sensitizer elongated plateau. All were more successful than HAP monotherapy. The three-compound combination three local optima, depending clearance tissue interstitium, each two-fold effective baseline study indicates therapy administered defined order will response designing complex could benefit use modeling.

Language: Английский

Citations

9