检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Khatiwada, Aastha Wolf, Bethany J. Yilmaz, Ayse Selen Ramos, Paula S. Pietrzak, Maciej Lawson, Andrew Hunt, Kelly J. Kim, Hang J. Chung, Dongjun Department of Public Health Sciences Medical University of South Carolina CharlestonSC United States Department of Biomedical Informatics The Ohio State University ColumbusOH United States Department of Medicine Medical University of South Carolina CharlestonSC United States Division of Statistics and Data Science University of Cincinnati CincinnatiOH United States

Motivation: In spite of great success of genome-wide association studies (GWAS), multiple challenges still remain. First, complex traits are often associated with many single nucleotide polymorphisms (SNPs), each with small or moderate effect sizes. Second, our understanding of the functional mechanisms through which genetic variants are associated with complex traits is still limited. functional annotations related to risk-associated SNPs. To address these challenges, we propose GPA-Tree and it simultaneously implements association mapping and identifies key combinations of functional annotations related to risk-associated SNPs by combining a decision tree algorithm with a hierarchical modeling framework. Results: First, we implemented simulation studies to evaluate the proposed GPA-Tree method and compared its performance with existing statistical approaches. The results indicate that GPA-Tree outperforms existing statistical approaches in detecting risk-associated SNPs and identifying the true combinations of functional annotations with high accuracy. Second, we applied GPA-Tree to a systemic lupus erythematosus (SLE) GWAS and functional annotation data including GenoSkyline and GenoSkylinePlus. The results from GPA-Tree highlight the dysregulation of blood immune cells, including but not limited to primary B, memory helper T, regulatory T, neutrophils and CD8+ memory T cells in SLE. These results demonstrate that GPA-Tree can be a powerful tool that improves association mapping while facilitating understanding of the underlying genetic architecture of complex traits and potential mechanisms linking risk-associated SNPs with complex traits. © 2021, CC BY-NC-ND.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

An artificial intelligence method for vessel detection in images of cardiac catheterization

引用

informatics in Medicine Unlocked 2023年 39卷

作者： Chien, Ting-Ying Ting, Hsien-Wei Li, Hao-Wei Chang, Hsiao-Huang Department of Computer Science and Engineering Yuan Ze University 320 Taoyuan City Taiwan Graduate Program in Biomedical Informatics Yuan Ze University 320 Taoyuan City Taiwan Innovation Center for Big Data and Digital Convergence Yuan Ze University 320 Taoyuan City Taiwan Department of Neurosurgery Taipei Hospital Ministry of Health and Welfare 242 New Taipei City Taiwan Division of Cardiovascular Surgery Department of Surgery Taipei Veterans General Hospital Taipei 11217 Taiwan Department of Surgery School of Medicine College of Medicine Taipei Medical University Taipei 11031 Taiwan

Coronary artery disease (CAD) is one of the top ten leading causes of death in countries worldwide. There are several methods used by physicians to diagnose CAD. One common method is the use of X-ray angiogram (XRA) images. When employing a computer-aided automatic analysis method to locate blood vessels in XRA images, problems such as complex background noise, low contrast, and difficulty in separating blood vessels from the background are encountered, especially for blood vessels with a low contrast to the background noise. In this study, we used various image preprocessing methods to highlight blood vessels from complex backgrounds and different types of blood vessel, followed by the employment of four superpixel segmentation methods to partition an image into multiple segments, and finally the utilization of Weighted Voting to determine the best superpixel algorithm. A genetic algorithm was used to identify the best weights by which to determine the locations of blood vessels in images of cardiac catheterization. Our proposed method achieved an average F1-score of 73.4% in the analysis of five patients, which was better than the other superpixel algorithms tested. The results of this research will be helpful for future SYNTAX score analysis. © 2023

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Open-Source Knowledge Graph Ecosystem for the Life sciences

arXiv

引用

arXiv 2023年

作者： Callahan, Tiffany J. Tripodi, Ignacio J. Stefanski, Adrianne L. Cappelletti, Luca Taneja, Sanya B. Wyrwa, Jordan M. Casiraghi, Elena Matentzoglu, Nicolas A. Reese, Justin Silverstein, Jonathan C. Hoyt, Charles Tapley Boyce, Richard D. Malec, Scott A. Unni, Deepak R. Joachimiak, Marcin P. Robinson, Peter N. Mungall, Christopher J. Cavalleri, Emanuele Fontana, Tommaso Valentini, Giorgio Mesiti, Marco Gillenwater, Lucas A. Santangelo, Brook Vasilevsky, Nicole A. Hoehndorf, Robert Bennett, Tellen D. Ryan, Patrick B. Hripcsak, George Kahn, Michael G. Bada, Michael Baumgartner, William A. Hunter, Lawrence E. Computational Bioscience Program University of Colorado Anschutz Medical Campus AuroraCO80045 United States Department of Biomedical Informatics Columbia University Irving Medical Center New YorkNY10032 United States Computer Science Department Interdisciplinary Quantitative Biology University of Colorado Boulder BoulderCO80301 United States AnacletoLab Computer Science Department University of Milan 20122 Italy Intelligent Systems Program University of Pittsburgh PittsburghPA15260 United States Department of Physical Medicine and Rehabilitation School of Medicine University of Colorado Anschutz Medical Campus AuroraCO80045 United States Division of Environmental Genomics and Systems Biology Lawrence Berkeley National Laboratory BerkeleyCA94720 United States Semanticly Ltd Athens Greece Department of Biomedical Informatics University of Pittsburgh School of Medicine PittsburghPA15206 United States Laboratory of Systems Pharmacology Harvard Medical School BostonMA02115 United States Division of Translational Informatics University of New Mexico School of Medicine AlbuquerqueNM87131 United States SIB Swiss Institute of Bioinformatics Basel Switzerland Berlin Institute of Health at Charité-Universitatsmedizin Berlin10117 Germany ELLIS European Laboratory for Learning and Intelligent Systems Germany Department of Biomedical Informatics University of Colorado School of Medicine AuroraCO80045 United States Data Collaboration Center Critical Path Institute 1840 E River Rd. Suite 100 TucsonAZ85718 United States Computer Electrical and Mathematical Sciences & Engineering Division Computational Bioscience Research Center King Abdullah University of Science and Technology Thuwal23955-6900 Saudi Arabia Department of Pediatrics University of Colorado School of Medicine AuroraCO80045 United States Janssen Research and Development RaritanNJ08869 United States Division of General Internal Medicine University of Colorado School of Medicine A

Translational research requires data at multiple scales of biological organization. Advancements in sequencing and multi-omics technologies have increased the availability of these data, but researchers face significant integration challenges. Knowledge graphs (KGs) are used to model complex phenomena, and methods exist to construct them automatically. However, tackling complex biomedical integration problems requires flexibility in the way knowledge is modeled. Moreover, existing KG construction methods provide robust tooling at the cost of fixed or limited choices among knowledge representation models. PheKnowLator (Phenotype Knowledge Translator) is a semantic ecosystem for automating the FAIR (Findable, Accessible, Interoperable, and Reusable) construction of ontologically grounded KGs with fully customizable knowledge representation. The ecosystem includes KG construction resources (e.g., data preparation APIs), analysis tools (e.g., SPARQL endpoints and abstraction algorithms), and benchmarks (e.g., prebuilt KGs and embeddings). We evaluated the ecosystem by systematically comparing it to existing open-source KG construction methods and by analyzing its computational performance when used to construct 12 large-scale KGs. With flexible knowledge representation, PheKnowLator enables fully customizable KGs without compromising performance or usability. © 2023, CC BY.

关键词： Ecosystems

来源：评论

学校读者我要写书评

暂无评论

P046 A multinomial approach to prediction of methotrexate treatment response and discontinuation due to adverse events in rheumatoid arthritis

引用

Rheumatology 2023年第SUPPLEMENT_2期62卷

作者： Gehringer, Celina K Martin, Glen P Hyrich, Kimme L Verstappen, Suzanne M M Sergeant, Jamie C Centre for Epidemiology Versus Arthritis Division of Musculoskeletal and Dermatological Sciences Manchester Academic Health Science Centre University of Manchester Manchester United Kingdom Centre for Biostatistics Manchester Academic Health Science Centre University of Manchester Manchester United Kingdom Centre for Health Informatics Division of Informatics Imaging and Data Sciences University of Manchester Manchester United Kingdom NIHR Manchester Biomedical Research Centre Manchester NHS Foundation Trust Manchester Academic Health Science Centre University of Manchester Manchester United Kingdom

来源：评论

学校读者我要写书评

暂无评论

Current and future directions in network biology

arXiv

引用

arXiv 2023年

作者： Zitnik, Marinka Li, Michelle M. Wells, Aydin Glass, Kimberly Gysi, Deisy Morselli Krishnan, Arjun Murali, T.M. Radivojac, Predrag Roy, Sushmita Baudot, Anaïs Bozdag, Serdar Chen, Danny Z. Cowen, Lenore Devkota, Kapil Gitter, Anthony Gosline, Sara Gu, Pengfei Guzzi, Pietro H. Huang, Heng Jiang, Meng Kesimoglu, Ziynet Nesibe Koyuturk, Mehmet Ma, Jian Pico, Alexander R. Pržulj, Nataša Przytycka, Teresa M. Raphael, Benjamin J. Ritz, Anna Sharan, Roded Shen, Yang Singh, Mona Slonim, Donna K. Tong, Hanghang Yang, Xinan Holly Yoon, Byung-Jun Yu, Haiyuan Milenković, Tijana Department of Biomedical Informatics Harvard University United States Department of Computer Science and Engineering University of Notre Dame United States Lucy Family Institute for Data and Society University of Notre Dame United States Eck Institute for Global Health University of Notre Dame United States Channing Division of Network Medicine Brigham and Women’s Hospital Harvard Medical School United States Department of Statistics Federal University of Paraná Brazil Department of Physics Northeastern University United States Department of Biomedical Informatics University of Colorado United States Department of Computer Science Virginia Tech United States Khoury College of Computer Sciences Northeastern University United States Department of Biostatistics and Medical Informatics University of Wisconsin-Madison United States Wisconsin Institute for Discovery United States Aix Marseille Université INSERM MMG Marseille France Department of Computer Science and Engineering University of North Texas United States Department of Mathematics University of North Texas United States Department of Computer Science Tufts University United States Morgridge Institute for Research United States Pacific Northwest National Laboratory United States Department of Medical and Surgical Sciences University Magna Graecia of Catanzaro Italy Department of Computer Science University of Maryland College Park United States National Center of Biotechnology Information National Library of Medicine National Institutes of Health Department of Computer and Data Sciences Case Western Reserve University United States Computational Biology Department School of Computer Science Carnegie Mellon University United States Institute of Data Science and Biotechnology Gladstone Institutes Department of Computer Science University College London United Kingdom ICREA Catalan Institution for Research and Advanced Studies Spain Department of Computer Science Princeton University United States Departmen

Network biology is an interdisciplinary field bridging computational and biological sciences that has proved pivotal in advancing the understanding of cellular functions and diseases across biological systems and scales. Although the field has been around for two decades, it remains nascent. It has witnessed rapid evolution, accompanied by emerging challenges. These challenges stem from various factors, notably the growing complexity and volume of data together with the increased diversity of data types describing different tiers of biological organization. We discuss prevailing research directions in network biology and highlight areas of inference and comparison of biological networks, multimodal data integration and heterogeneous networks, higher-order network analysis, machine learning on networks, and network-based personalized medicine. Following the overview of recent breakthroughs across these five areas, we offer a perspective on the future directions of network biology. Additionally, we offer insights into scientific communities, educational initiatives, and the importance of fostering diversity within the field. This paper establishes a roadmap for an immediate and long-term vision for network biology. © 2023, CC BY.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Assessing the Potential of GPT-4 to Annotate Medical Notes Across Different Languages and Countries: A Model Evaluation Study

SSRN

引用

SSRN 2024年

作者： Saad Menezes, Maria Clara Hoffman, Alexander F. Tan, Amelia L.M. Nalbandyan, Mariné Omenn, Gilbert S. Mazzotti, Diego R. Hernández-Arango, Alejandro Visweswaran, Shyam Venkatesh, Shruthi Mandl, Kenneth D. Bourgeois, Florence T. Lee, James W.K. Makmur, Andrew Hanauer, David A. Semanik, Michael G. Kerivan, Lauren T. Hill, Terra Forero, Julian Restrepo Castro, Carlos Andrés C.R. Vigna, Matteo Ceriana, Piero Abu-El-rub, Noor Avillach, Paul Bellazzi, Riccardo Callaci, Thomas Gutiérrez-Sacristán, Alba Malovini, Alberto Mathew, Jomol P. Morris, Michele Murthy, Venkatesh Parimbelli, Enea Patel, Lav P. Sáez, Carlos Samayamuthu, Malarkodi Jebathilagam Thompson, Jeffrey A. Tibollo, Valentina Xia, Zongqi Kohane, Isaac S. Harvard Medical School Department of Biomedical Informatics 10 Shattuck Street BostonMA02115 United States School of Medicine and Public Health University of Wisconsin-Madison Office of Informatics and Information Technology 750 Highland Ave MadisonWI53705 United States University of Michigan Department of Computational Medicine & Bioinformatics Internal Medicine Human Genetics Environmental Health 100 Washtenaw Avenue Ann ArborMI48109 United States University of Kansas Medical Center Division of Medical Informatics Division of Pulmonary Critical Care and Sleep Medicine Department of Internal Medicine 3901 Rainbow Blvd Kansas CityKS66160 United States University of Antioquia Hospital Alma Máter de Antioquia Department of Internal Medicine Calle 64 N°51 D - 154 Medellín Colombia University of Pittsburgh Department of Biomedical Informatics 5607 Baum Blvd PittsburghPA15206 United States University of Pittsburgh Department of Neurology 3501 5th Avenue PittsburghPA15206 United States Boston Children's Hospital Computational Health Informatics Program 300 Longwood Avenue BostonMA02115 United States Boston Children's Hospital Department of Pediatrics 300 Longwood Avenue BostonMA02115 United States National University Health System Department of Surgery 1E Kent Ridge Rd Singapore119228 Singapore National University Health System Department of Diagnostic Imaging 1E Kent Ridge Rd Singapore119228 Singapore University of Michigan Department of Learning Health Sciences NCRC 100 2800 Plymouth Road Ann ArborMI48109 United States University of Kansas Medical Center Department of Surgery 3901 Rainbow Blvd Kansas CityKS66160 United States Istituti Clinici Scientifici Maugeri IRCCS Respiratory rehabilitation unit Via Maugeri 10 Pavia27100 Italy University of Kansas Medical Center 3901 Rainbow Blvd Kansas CityKS66160 United States University of Pavia Department of Electrical Computer and Biomedical Engineering via Ferrata 5 Pavia2710

Background: Physicians invest hours creating patient notes, which are rich in information but difficult for computers to analyze due to their unstructured format. GPT-4 reshaped our ability to process text, yet it is unknown how well this model can handle medical notes. This project aims to compare GPT-4’s ability to annotate medical notes against experienced physicians across three different languages at multiple institutions and countries. Methods: This study included eight sites from four countries - the United States, Colombia, Singapore, and Italy. Each site contributed seven de-identified notes (admission, progress, or consult) from hospitalized patients. GPT-4 assessed each note by answering 14 questions, including demographic information, clinical judgments, data quality, and patients’ eligibility for a hypothetical study enrollment. For validation, two physicians from each site independently evaluated GPT-4's responses. Findings: Overall, 56 medical notes, written in English, Italian, and Spanish, were analyzed. A total of 784 responses from GPT-4 were generated. Both physicians agreed with GPT-4’s response 79% of the time (622/784, 95%CI 76-82%). Only one of the two physicians agreed with GPT-4’s response 10% of the time (82/784, 95%CI 8-13%). Neither physician agreed with GPT-4’s response 10% of the time (80/784, 95%CI 8-13%). Both physicians agreed with GPT-4 more often in notes written in Spanish and Italian than in English, with agreement rates of 88% (86/98, 95%CI 79-93%), 84% (82/98, 95%CI 75-90%), and 77% (454/588, 95%CI 74-80%), respectively. Hallucinations were rare (10/784, 95%CI 0-2%). GPT-4 correctly selected patients for a hypothetical study enrollment based on three criteria 90% of the time (95%CI 81-98%). Interpretation: The findings indicate that GPT-4 annotations demonstrated a high agreement rate with physicians across all languages. We also demonstrate GPT-4's potential to assist in patient selection for studies. Funding: None. Declarati

关键词： Medical computing

来源：评论

学校读者我要写书评

暂无评论

Novel integration of governmental data sources using machine learning to identify super-utilization among U.S. counties

引用

Intelligence-Based Medicine 2023年 7卷 100093-100093页

作者： Ricket, Iben M. Matheny, Michael E. MacKenzie, Todd A. Emond, Jennifer A. Ailawadi, Kusum L. Brown, Jeremiah R. Department of Epidemiology Dartmouth Geisel School of Medicine at Dartmouth Hanover NH United States Department of Biomedical Informatics Vanderbilt University Medical Center Nashville TN United States Department of Biostatistics Vanderbilt University Medical Center Nashville TN United States Division of General Internal Medicine Vanderbilt University Medical Center Nashville TN United States Geriatric Research Education and Clinical Care Center Tennessee Valley Healthcare System VA Nashville TN United States Department of Biomedical Data Science Geisel School of Medicine at Dartmouth Lebanon NH United States Norris Cotton Cancer Center Geisel School of Medicine at Dartmouth Lebanon NH United States Tuck School of Business at Dartmouth Hanover NH United States

Background: Super-utilizers consume the greatest share of resource intensive healthcare (RIHC) and reducing their utilization remains a crucial challenge to healthcare systems in the United States (U.S.). The objective of this study was to predict RIHC among U.S. counties, using routinely collected data from the U.S. government, including information on consumer spending, offering an alternative method for identifying super-utilization among population units rather than individuals. Methods: Cross-sectional data from 5 governmental sources in 2017 were used in a machine learning pipeline, where target-prediction features were selected and used in 4 distinct algorithms. Outcome metrics of RIHC utilization came from the American Hospital Association and included yearly: (1) emergency rooms visit, (2) inpatient days, and (3) hospital expenditures. Target-prediction features included: 149 demographic characteristics from the U.S. Census Bureau, 151 adult and child health characteristics from the Centers for Disease Control and Prevention, 151 community characteristics from the American Community Survey, and 571 consumer expenditures from the Bureau of Labor Statistics. SHAP analysis identified important target-prediction features for 3 RIHC outcome metrics. Results: 2475 counties with emergency rooms and 2491 counties with hospitals were included. The median yearly emergency room visits per capita was 0.450 [IQR:0.318, 0.618], the median inpatient days per capita was 0.368 [IQR: 0.176, 0.826], and the median hospital expenditures per capita was $2104 [IQR: $1299.93, 3362.97]. The coefficient of determination (R²), calculated on the test set, ranged between 0.267 and 0.447. Demographic and community characteristics were among the important predictors for all 3 RIHC outcome metrics. Conclusions: Integrating diverse population characteristics from numerous governmental sources, we predicted 3-outcome metrics of RIHC among U.S. counties with good performance, off

关键词： Machine learning Population prediction models Resource intensive healthcare utilization Super-utilizers

来源：评论

学校读者我要写书评

暂无评论

MedAlign: A Clinician-Generated dataset for Instruction Following with Electronic Medical Records

arXiv

引用

arXiv 2023年

作者： Fleming, Scott L. Lozano, Alejandro Haberkorn, William J. Jindal, Jenelle A. Reis, Eduardo Thapa, Rahul Blankemeier, Louis Genkins, Julian Z. Steinberg, Ethan Nayak, Ashwin Patel, Birju Chiang, Chia-Chun Callahan, Alison Huo, Zepeng Gatidis, Sergios Adams, Scott Fayanju, Oluseyi Shah, Shreya J. Savage, Thomas Goh, Ethan Chaudhari, Akshay S. Aghaeepour, Nima Sharp, Christopher Pfeffer, Michael A. Liang, Percy Chen, Jonathan H. Morse, Keith E. Brunskill, Emma P. Fries, Jason A. Shah, Nigam H. Department of Biomedical Data Science Stanford School of Medicine StanfordCA United States Department of Computer Science Stanford School of Engineering StanfordCA United States Department of Anesthesiology Peri-operative and Pain Medicine Stanford School of Medicine StanfordCA United States Department of Pediatrics Stanford School of Medicine StanfordCA United States Stanford Center for Biomedical Informatics Research Stanford University StanfordCA United States Department of Radiology Stanford School of Medicine StanfordCA United States Stanford University StanfordCA United States Hospital Israelita Albert Einstein SP Sao Paulo Brazil Technology and Digital Solutions Stanford Health Care Palo AltoCA United States Department of Electrical Enginering Stanford School of Engineering StanfordCA United States Department of Medicine Vanderbilt University School of Medicine NashvilleTN United States Department of Biomedical Informatics Vanderbilt University Medical Center NashvilleTN United States Department of Medicine Stanford School of Medicine StanfordCA United States Department of Neurology Mayo Clinic RochesterMN United States Human-Centered Artificial Intelligence Institute Stanford University StanfordCA United States Division of Hospital Medicine Stanford University StanfordCA United States Clinical Excellence Research Center Stanford School of Medicine StanfordCA United States

The ability of large language models (LLMs) to follow natural language instructions with human-level fluency suggests many opportunities in healthcare to reduce administrative burden and improve quality of care. However, evaluating LLMs on realistic text generation tasks for healthcare remains challenging. Existing question answering datasets for electronic health record (EHR) data fail to capture the complexity of information needs and documentation burdens experienced by clinicians. To address these challenges, we introduce MedAlign, a benchmark dataset of 983 natural language instructions for EHR data. MedAlign is curated by 15 clinicians (7 specialities), includes clinician-written reference responses for 303 instructions, and provides 276 longitudinal EHRs for grounding instruction-response pairs. We used MedAlign to evaluate 6 general domain LLMs, having clinicians rank the accuracy and quality of each LLM response. We found high error rates, ranging from 35% (GPT-4) to 68% (MPT-7B-Instruct), and 8.3% drop in accuracy moving from 32k to 2k context lengths for GPT-4. Finally, we report correlations between clinician rankings and automated natural language generation metrics as a way to rank LLMs without human review. MedAlign is provided under a research data use agreement1 to enable LLM evaluations on tasks aligned with clinician needs and preferences. © 2023, CC BY.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Generative Artificial Intelligence in Clinical Medicine and Impact on Gastroenterology

引用

Gastroenterology 2025年

作者： Ali Soroush Mauro Giuffrè Sunny Chung Dennis L Shung Division of Data-Driven and Digital Medicine (D3M) Icahn School of Medicine at Mount Sinai Henry D. Janowitz Division of Gastroenterology Icahn School of Medicine at Mount Sinai Charles Bronfman Institute for Personalized Medicine Icahn School of Medicine at Mount Sinai. Section of Digestive Diseases Department of Medicine Yale School of Medicine. Section of Digestive Diseases Department of Medicine Yale School of Medicine Department of Biomedical Informatics & Data Science Yale School of Medicine. Electronic address: dennis.shung@yale.edu.

The pace of artificial intelligence (AI) integration into healthcare has accelerated with rapid advances in generative AI (GenAI). Gastroenterology and hepatology in particular will be transformed due to the multimodal workflows that integrate endoscopic video, radiologic imaging, tabular data, and unstructured note text. GenAI will impact the entire spectrum of clinical experience, from administrative tasks, diagnostic guidance and treatment recommendations. Unlike traditional machine learning approaches, GenAI is more flexible, with one platform able to be used across multiple tasks. Initial evidence suggests benefit in lower-level administrative tasks such as clinical documentation, medical billing and scheduling, and information tasks such as patient education and summarization of the medical literature. No evidence exists for GenAI solutions for more complex tasks relevant to clinical care, such as clinical reasoning for diagnostic and treatment decisions that may affect patient outcomes. Challenges of output reliability, data privacy, and useful integration remain, with potential solutions include robust validation, regulatory oversight, and "human-AI teaming" strategies to ensure safe, effective deployment. We remain optimistic in the potential of GenAI to augment clinical expertise due to the adaptability of GenAI to handle multiple data modalities to obtain and focus relevant information flows and the human-friendly interfaces that facilitate ease of use. We believe that the potential of GenAI for dynamic human-algorithmic interactions may allow for a degree of clinician-directed customization to enhance human presence.

关键词： AI Safety Gastroenterology Generative Artificial Intelligence Human-AI Collaboration

来源：评论

学校读者我要写书评

暂无评论

Weakly Supervised AI for Efficient Analysis of 3D Pathology Samples

arXiv

引用

arXiv 2023年

作者： Song, Andrew H. Williams, Mane Williamson, Drew F.K. Jaume, Guillaume Zhang, Andrew Chen, Bowen Serafin, Robert Liu, Jonathan T.C. Baras, Alex Parwani, Anil V. Mahmood, Faisal Department of Pathology Brigham and Women’s Hospital Harvard Medical School BostonMA United States Department of Pathology Massachusetts General Hospital Harvard Medical School BostonMA United States Cancer Program Broad Institute of Harvard and MIT CambridgeMA United States Data Science Program Dana-Farber Cancer Institute BostonMA United States Department of Biomedical Informatics Harvard Medical School BostonMA United States Harvard-MIT Division of Health Sciences and Technology Massachusetts Institute of Technology CambridgeMA United States Department of Mechanical Engineering Bioengineering Laboratory Medicine & Pathology University of Washington SeattleWA United States Department of Pathology Johns Hopkins Hospital BaltimoreMD United States Department of Biomedical Engineering Johns Hopkins Hospital BaltimoreMD United States Department of Pathology The Ohio State University ColumbusOH United States

Human tissue consists of complex structures that display a diversity of morphologies, forming a tissue microenvironment that is, by nature, three-dimensional (3D). However, the current standard-of-care involves slicing 3D tissue specimens into two-dimensional (2D) sections and selecting a few for microscopic evaluation1,2, with concomitant risks of sampling bias and misdiagnosis3–6. To this end, there have been intense efforts to capture 3D tissue morphology and transition to 3D pathology, with the development of multiple high-resolution 3D imaging modalities7–18. However, these tools have had little translation to clinical practice as manual evaluation of such large data by pathologists is impractical and there is a lack of computational platforms that can efficiently process the 3D images and provide patient-level clinical insights. Here we present Modality-Agnostic Multiple instance learning for volumetric Block Analysis (MAMBA), a deep-learning-based platform for processing 3D tissue images from diverse imaging modalities and predicting patient outcomes. Archived prostate cancer specimens were imaged with open-top light-sheet microscopy12–14 or microcomputed tomography15,16 and the resulting 3D datasets were used to train risk-stratification networks based on 5-year biochemical recurrence outcomes via MAMBA. With the 3D block-based approach, MAMBA achieves an area under the receiver operating characteristic curve (AUC) of 0.86 and 0.74, superior to 2D traditional single-slice-based prognostication (AUC of 0.79 and 0.57), suggesting superior prognostication with 3D morphological features. Further analyses reveal that the incorporation of greater tissue volume improves prognostic performance and mitigates risk prediction variability from sampling bias, suggesting that there is value in capturing larger extents of spatially heterogeneous 3D morphology. With the rapid growth and adoption of 3D spatial biology and pathology techniques by researchers and clinicians, M

关键词： Pathology

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：