A5082073517- Radiomics and Machine Learning in Medical Imaging
- AI in cancer detection
- Prostate Cancer Diagnosis and Treatment
- Prostate Cancer Treatment and Research
- Lung Cancer Treatments and Mutations
- Air Quality Monitoring and Forecasting
- Cancer, Lipids, and Metabolism
- Data-Driven Disease Surveillance
- Colorectal Cancer Screening and Detection
- Renal and related cancers
- Nutrition, Genetics, and Disease
- Artificial Intelligence in Healthcare and Education
- Estrogen and related hormone effects
- Species Distribution and Climate Change
- Health Systems, Economic Evaluations, Quality of Life
- Hormonal and reproductive studies
- Statistical Methods in Clinical Trials
- Developmental Biology and Gene Regulation
- Meta-analysis and systematic reviews
- Science, Research, and Medicine
- Biomedical Text Mining and Ontologies
- Cancer Genomics and Diagnostics
- Cell Image Analysis Techniques
- Global Cancer Incidence and Screening
- Conservation Techniques and Studies
Nanjing University of Chinese Medicine
2025
Google (United States)
2019-2024
Amsterdam University Medical Centers
2021
Science Exchange (United States)
2014-2015
Prostate Cancer Foundation
2015
Movember Foundation
2015
Indiana University – Purdue University Indianapolis
2012-2014
Stanford University
2013
Howard Hughes Medical Institute
2013
Swarthmore College
2005
For prostate cancer patients, the Gleason score is one of most important prognostic factors, potentially determining treatment independent stage. However, scoring based on subjective microscopic examination tumor morphology and suffers from poor reproducibility. Here we present a deep learning system (DLS) for whole-slide images prostatectomies. Our was developed using 112 million pathologist-annotated image patches 1226 slides, evaluated an validation dataset 331 slides. Compared to...
Abstract Artificial intelligence (AI) has shown promise for diagnosing prostate cancer in biopsies. However, results have been limited to individual studies, lacking validation multinational settings. Competitions be accelerators medical imaging innovations, but their impact is hindered by lack of reproducibility and independent validation. With this mind, we organized the PANDA challenge—the largest histopathology competition date, joined 1,290 developers—to catalyze development...
It is widely believed that research builds upon previously published findings has reproduced the original work. However, it rare for researchers to perform or publish direct replications of existing results. The Reproducibility Project: Cancer Biology an open investigation reproducibility in preclinical cancer biology research. We have identified 50 high impact articles period 2010-2012, and plan replicate a subset experimental results from each article. A Registered Report detailing...
<h3>Importance</h3> For prostate cancer, Gleason grading of the biopsy specimen plays a pivotal role in determining case management. However, is associated with substantial interobserver variability, resulting need for decision support tools to improve reproducibility routine clinical practice. <h3>Objective</h3> To evaluate ability deep learning system (DLS) grade diagnostic specimens. <h3>Design, Setting, and Participants</h3> The DLS was evaluated using 752 deidentified digitized images...
Deriving interpretable prognostic features from deep-learning-based histopathology models remains a challenge. In this study, we developed deep learning system (DLS) for predicting disease specific survival stage II and III colorectal cancer using 3,652 cases (27,300 slides). When evaluated on two validation datasets containing 1,239 (9,340 slides) 738 (7,140 respectively, the DLS achieved 5-year disease-specific AUC of 0.70 (95%CI 0.66-0.73) 0.69 0.64-0.72), added significant predictive...
The transcriptional control of primary cilium formation and ciliary motility are beginning to be understood, but little is known about the programs that number other structural functional specializations. One most intriguing specializations occurs in multiciliated cells (MCCs), which amplify their centrioles nucleate hundreds cilia per cell, instead usual monocilium. Here we report transcription factor MYB, promotes S phase drives cycling a variety progenitor cells, expressed postmitotic...
Breast cancer management depends on biomarkers including estrogen receptor, progesterone and human epidermal growth factor receptor 2 (ER/PR/HER2). Though existing scoring systems are widely used well-validated, they can involve costly preparation variable interpretation. Additionally, discordances between histology expected biomarker findings prompt repeat testing to address biological, interpretative, or technical reasons for unexpected results.We developed three independent deep learning...
<h3>Importance</h3> Expert-level artificial intelligence (AI) algorithms for prostate biopsy grading have recently been developed. However, the potential impact of integrating such into pathologist workflows remains largely unexplored. <h3>Objective</h3> To evaluate an expert-level AI-based assistive tool when used by pathologists biopsies. <h3>Design, Setting, and Participants</h3> This diagnostic study a fully crossed multiple-reader, multiple-case design to grading. Retrospective core...
Histologic grading of breast cancer involves review and scoring three well-established morphologic features: mitotic count, nuclear pleomorphism, tubule formation. Taken together, these features form the basis Nottingham Grading System which is used to inform characterization prognosis. In this study, we develop deep learning models perform histologic all components using digitized hematoxylin eosin-stained slides containing invasive carcinoma. We first evaluate model performance...
BackgroundArtificial intelligence (AI) has repeatedly been shown to encode historical inequities in healthcare. We aimed develop a framework quantitatively assess the performance equity of health AI technologies and illustrate its utility via case study.MethodsHere, we propose methodology whether prioritise for patient populations experiencing worse outcomes, that is complementary existing fairness metrics. developed Health Equity Assessment machine Learning (HEAL) designed four-step...
Presence of lymph node metastasis (LNM) influences prognosis and clinical decision-making in colorectal cancer. However, detection LNM is variable depends on a number external factors. Deep learning has shown success computational pathology, but struggled to boost performance when combined with known predictors.Machine-learned features are created by clustering deep embeddings small patches tumor cancer via k-means, then selecting the top clusters that add predictive value logistic...
We propose a two-step model for the evolutionary origin of turtle shell. show here that carapacial ridge (CR) is critical entry ribs into dorsal dermis. Moreover, we demonstrate maintenance CR and its ability to attract migrating rib precursor cells depend upon fibroblast growth factor (FGF) signaling. Inhibitors FGF allow degenerate, with consequent migration along ventral body wall. Beads containing FGF10 can rearrange in chick, suggesting plays an important role attracting rudiments. The...
Abstract Both histologic subtypes and tumor mutation burden (TMB) represent important biomarkers in lung cancer, with implications for patient prognosis treatment decisions. Typically, TMB is evaluated by comprehensive genomic profiling but this requires use of finite tissue specimens costly, time-consuming laboratory processes. Histologic subtype classification represents an established component adenocarcinoma histopathology, can be challenging associated substantial inter-pathologist...
Gleason grading of prostate cancer is an important prognostic factor, but suffers from poor reproducibility, particularly among non-subspecialist pathologists. Although artificial intelligence (A.I.) tools have demonstrated on-par with expert pathologists, it remains open question whether and to what extent A.I. translates better prognostication.In this study, we developed a system predict cancer-specific mortality via A.I.-based subsequently evaluated its ability risk-stratify patients on...
Aim: Lung adenocarcinoma (LUAD), the most prevalent subtype of non-small cell lung cancer (NSCLC), presents significant clinical challenges due to its high mortality and limited therapeutic options. The molecular heterogeneity development resistance further complicate treatment, underscoring need for a more comprehensive understanding cellular characteristics. This study sought delineate novel subpopulations subtypes LUAD, identify critical biomarkers, explore potential targets enhance...
The incidence of thyroid cancer (TC) increases year by year. It is necessary to construct a prognostic model for risk stratification and management TC patients. Glutamine metabolism essential tumor progression the microenvironment. present study aimed develop predictive using glutamine gene set. Differentially expressed genes in cells with high levels from single cell RNA‑sequencing data were compared differentially between normal tissues Cancer Genome Atlas Program data. Through Boruta...
SUMMARY The transcriptional control of primary cilium formation and ciliary motility are beginning to be understood, but little is known about the programs that number other structural functional specializations. One most intriguing specializations occurs in multiciliated cells (MCCs), which amplify their centrioles nucleate hundreds cilia per cell, instead usual monocilium. Here we report transcription factor MYB, promotes S phase drives cycling a variety progenitor cells, expressed...
Metadata are general characteristics of the data in a well-curated and condensed format, have been proven to be useful for decision making, knowledge discovery, also heterogeneous organization biobank. Among all types biobank, pathology is key component biobank serves as gold standard diagnosis. To maximize utility allow rapid progress biomedical science, it essential organize with well-populated metadata. However, manual annotation such information tedious time-consuming. In study, we...
The Prostate Cancer Foundation-Movember Foundation Reproducibility Initiative seeks to address growing concerns about reproducibility in scientific research by conducting replications of recent papers the field prostate cancer. This Registered Report describes proposed replication plan key experiments from "Androgen Receptor Splice Variants Determine Taxane Sensitivity Cancer" Thadani-Mulero and colleagues (2014) published Research 2014. experiment that will be replicated is reported Fig....
The Prostate Cancer Foundation-Movember Foundation Reproducibility Initiative (PCFMFRI) seeks to address growing concerns about reproducibility in scientific research by conducting replications of recent papers the field prostate cancer. This Registered Report describes proposed replication plan key experiments from "The Androgen Receptor Induces a Distinct Transcriptional Program Castration-Resistant Man" Sharma and colleagues (2013), published Cell 2013. Of thousands targets for androgen...