Artificial intelligence(AI)is significantly advancing precision medicine,particularly in the fields of immunogenomics,radiomics,and pathomics.In immunogenomics,AI can process vast amounts of genomic and multi-omic dat...Artificial intelligence(AI)is significantly advancing precision medicine,particularly in the fields of immunogenomics,radiomics,and pathomics.In immunogenomics,AI can process vast amounts of genomic and multi-omic data to identify biomarkers associated with immunotherapy responses and disease prognosis,thus providing strong support for personalized treatments.In radiomics,AI can analyze high-dimensional features from computed tomography(CT),magnetic resonance imaging(MRI),and positron emission tomography/computed tomography(PET/CT)images to discover imaging biomarkers associated with tumor heterogeneity,treatment response,and disease progression,thereby enabling non-invasive,real-time assessments for personalized therapy.Pathomics leverages AI for deep analysis of digital pathology images,and can uncover subtle changes in tissue microenvironments,cellular characteristics,and morphological features,and offer unique insights into immunotherapy response prediction and biomarker discovery.These AI-driven technologies not only enhance the speed,accuracy,and robustness of biomarker discovery but also significantly improve the precision,personalization,and effectiveness of clinical treatments,and are driving a shift from empirical to precision medicine.Despite challenges such as data quality,model interpretability,integration of multi-modal data,and privacy protection,the ongoing advancements in AI,coupled with interdisciplinary collaboration,are poised to further enhance AI’s roles in biomarker discovery and immunotherapy response prediction.These improvements are expected to lead to more accurate,personalized treatment strategies and ultimately better patient outcomes,marking a significant step forward in the evolution of precision medicine.展开更多
Background:Bladder cancer prognosis remains suboptimal despite advancements in research.Current molecular subtyping methods are resource-intensive,highlighting the need for efficient,cost-effective approaches to predi...Background:Bladder cancer prognosis remains suboptimal despite advancements in research.Current molecular subtyping methods are resource-intensive,highlighting the need for efficient,cost-effective approaches to predict BCa molecular subtypes.Method:We developed a predictive model for BCa molecular subtypes using machine learning(ML)and pathomics derived from Hematoxylin-Eosin stained pathological slides.A cohort of 353 patients from TCGA was employed,and image features were extracted for analysis.Pathomic signatures were constructed using the LASSO Cox regression algorithm,and a pathomic-clinical nomogram was developed and validated in training and testing cohorts.Results:Seventy distinct image features were identified from 150 pathomic signatures.The model demonstrated robust predictive ability,with AUCs of 0.833 and 0.822 in the training and validation cohorts,respectively.The addition of pathomic score,N stage,and M stage improved the model’s discrimination,achieving AUCs of 0.877 and 0.794 in the training and validation cohorts.Limitations include the lack of an external validation cohort.Conclusion:Our ML-based pathomics model shows promise in predicting BCa molecular subtypes and has the potential to enhance prognosis prediction and inform treatment strategies,marking a significant step towards precision medicine for BCa.展开更多
Hepatocellular carcinoma(HCC),a leading cause of cancer mortality,faces diagnostic and therapeutic challenges due to its histopathological complexity and clinical heterogeneity.Pathomics,an emerging discipline that in...Hepatocellular carcinoma(HCC),a leading cause of cancer mortality,faces diagnostic and therapeutic challenges due to its histopathological complexity and clinical heterogeneity.Pathomics,an emerging discipline that integrates artificial intelligence(AI)with quantitative pathology image analysis,aims to decode disease heterogeneity by extracting high-dimensional features from histopathological specimens.This review highlights how AI-driven pathomics has revolutionized liver cancer management through automated analysis of whole-slide images.Pathomics integrates deep learning with histopathological features to enable precise tumour classification(e.g.,HCC vs cholangiocarcinoma),microvascular invasion(MVI)detection,recurrence risk stratification,and survival prediction.Advanced frameworks such as MVI-AI diagnostic model and CHOWDER demonstrate high accuracy in identifying prognostic biomarkers,whereas multiomics integration links morphometric patterns to molecular signatures(e.g.,EZH2 expression and immune infiltration).Despite these breakthroughs,critical bottlenecks persist,including limited multicentre validation studies,"black box"model interpretability,and clinical workflow integration.Future studies should emphasize AI-enhanced multimodal fusion(radiogenomics and liquid biopsy)and standardized platforms to bridge computational pathology and precision oncology,ultimately improving personalized therapeutic strategies for liver malignancies.This synthesis aims to guide research translation and advance personalized therapeutic strategies for liver malignancies.展开更多
In the last decade,the focus of computational pathology research community has shifted from replicating the pathological examination for diagnosis done by pathologists to unlocking and discovering"sub-visual"...In the last decade,the focus of computational pathology research community has shifted from replicating the pathological examination for diagnosis done by pathologists to unlocking and discovering"sub-visual"prognostic image cues from the histopathological image.While we are getting more knowledge and experience in digital pathology,the emerging goal is to integrate other-omics or modalities that will contribute for building a better prognostic assay.In this paper,we provide a brief review of representative works that focus on integrating pathomics with radiomics and genomics for cancer prognosis.It includes:correlation of pathomics and genomics;fusion of pathomics and genomics;fusion of pathomics and radiomics.We also present challenges,potential opportunities,and avenues for future work.展开更多
To the Editor:Lung cancer,specifically lung adenocarcinoma(LUAD),is one of the primary cause of cancer-related mortality globally.[1,2]Nevertheless,only a small subset of individuals with LUAD have derived clinical be...To the Editor:Lung cancer,specifically lung adenocarcinoma(LUAD),is one of the primary cause of cancer-related mortality globally.[1,2]Nevertheless,only a small subset of individuals with LUAD have derived clinical benefits from chemoimmunotherapy in either first-line or subsequent treatment settings.Both programmed death-ligand 1(PDL1)expression and tumor mutational burden(TMB)have proven inadequate in accurately predicting treatment outcomes in these scenarios.[3]Consequently,there exists a pressing necessity to identify a reliable biomarker to inform treatment decisions.展开更多
Kirsten rat sarcoma viral oncogene homolog(namely KRAS)is a key biomarker for prognostic analysis and targeted therapy of colorectal cancer.Recently,the advancement of machine learning,especially deep learning,has gre...Kirsten rat sarcoma viral oncogene homolog(namely KRAS)is a key biomarker for prognostic analysis and targeted therapy of colorectal cancer.Recently,the advancement of machine learning,especially deep learning,has greatly promoted the development of KRAS mutation detection from tumor phenotype data,such as pathology slides or radiology images.However,there are still two major problems in existing studies:inadequate single-modal feature learning and lack of multimodal phenotypic feature fusion.In this paper,we propose a Disentangled Representation-based Multimodal Fusion framework integrating Pathomics and Radiomics(DRMF-PaRa)for KRAS mutation detection.Specifically,the DRMF-PaRa model consists of three parts:(1)the pathomics learning module,which introduces a tissue-guided Transformer model to extract more comprehensive and targeted pathological features;(2)the radiomics learning module,which captures the generic hand-crafted radiomics features and the task-specific deep radiomics features;(3)the disentangled representation-based multimodal fusion module,which learns factorized subspaces for each modality and provides a holistic view of the two heterogeneous phenotypic features.The proposed model is developed and evaluated on a multi modality dataset of 111 colorectal cancer patients with whole slide images and contrast-enhanced CT.The experimental results demonstrate the superiority of the proposed DRMF-PaRa model with an accuracy of 0.876 and an AUC of 0.865 for KRAS mutation detection.展开更多
The integration of artificial intelligence(AI)and multiomics has transformed clinical and life sciences,enabling precision medicine and redefining disease understanding.Scientific publications grew significantly from ...The integration of artificial intelligence(AI)and multiomics has transformed clinical and life sciences,enabling precision medicine and redefining disease understanding.Scientific publications grew significantly from 2.1 million in 2012 to 3.3 million in 2022,with AI research tripling during this period.Multiomics fields,including genomics and proteomics,also advanced,exemplified by the Human Proteome Project achieving a 90%complete blueprint by 2021.This growth highlights opportunities and challenges in integrating AI and multiomics into clinical reporting.A review of studies and case reports was conducted to evaluate AI and multiomics integration.Key areas analyzed included diagnostic accuracy,predictive modeling,and personalized treatment approaches driven by AI tools.Case examples were studied to assess impacts on clinical decision-making.AI and multiomics enhanced data integration,predictive insights,and treatment personalization.Fields like radiomics,genomics,and proteomics improved diagnostics and guided therapy.For instance,the“AI radiomics,geno-mics,oncopathomics,and surgomics project”combined radiomics and genomics for surgical decision-making,enabling preoperative,intraoperative,and post-operative interventions.AI applications in case reports predicted conditions like postoperative delirium and monitored cancer progression using genomic and imaging data.AI and multiomics enable standardized data analysis,dynamic updates,and predictive modeling in case reports.Traditional reports often lack objectivity,but AI enhances reproducibility and decision-making by processing large datasets.Challenges include data standardization,biases,and ethical concerns.Overcoming these barriers is vital for optimizing AI applications and advancing personalized medicine.AI and multiomics integration is revolutionizing clinical research and practice.Standardizing data reporting and addressing challenges in ethics and data quality will unlock their full potential.Emphasizing collaboration and transparency is essential for leveraging these tools to improve patient care and scientific communication.展开更多
This paper aims to develop an understanding of the undergraduate students＇ learning by applying Kolb＇s （1984） learning concepts and theories. This research aims： （1） to study the visitors＇ learning experience;...This paper aims to develop an understanding of the undergraduate students＇ learning by applying Kolb＇s （1984） learning concepts and theories. This research aims： （1） to study the visitors＇ learning experience; （2） to compare the learning process of visitors; and （3） to design learning process development for the visitors of the Phra Pathom Chedi National Museum. The quantitative methodology was used for data collection. The population was focused on group samplings of 300 participants and the selection method was a non-probability and purposive sampling. The research instrument was the structured questionnaire. Descriptive statistics, T-test, F-test （one-way analysis of variance （ANOVA））, and regression analysis were used for data analysis. According to the first objective, the study revealed that most of visitors were female, at the age of 19 years old, had a bachelor degree, and had income less than 5,000 baht. Their learning levels at the Phra Pathom Chedi National Museum were high. According to the second objective, the study found that there was no correlation between gender and income to the visitors＇ learning process related to the theoretical four learning processes which are： （1） before learning; （2） learning behavior; （3） while learning; and （4） the best ways of learning that create the most understanding. However, age and education varied the level of visitors＇ leaming process. According to the third objective regarding the four models of learning process development design, the study presented that： （1） For the accommodators, the visitors should be male, at a young age, and have a bachelor degree; （2） For the divergers, the visitors should be at a young age and have a bachelor degree; （3） For the convergers, the visitors should be at a young age, have a bachelor degree, and not with high income; and （4） For the assimilators, the visitors should be at a young age, have a bachelor degree, and with high income.展开更多
The advent of multi-omics approaches has revolutionized the field of oncology by enabling a comprehensive understanding of cancer biology through the integration of diverse biological data.This review aims to explore ...The advent of multi-omics approaches has revolutionized the field of oncology by enabling a comprehensive understanding of cancer biology through the integration of diverse biological data.This review aims to explore the synergy between three key omics domains:radiomics,genoproteomics,and pathomics.Radiomics involves extracting high-dimensional data from medical images,providing valuable insights into tumor heterogeneity and treatment response.Genoproteomics,encompassing both genomic and proteomic analyses,delves into the molecular mechanisms driving cancer progression and therapeutic resistance.Pathomics leverages advanced digital pathology techniques to quantitatively analyze tissue architecture and cellular morphology.We provide an in-depth overview of the methodologies and tools employed in each omics field,highlighting their specific applications in oncology,including cancer diagnosis,biomarker discovery,and prediction of treatment outcomes.Furthermore,we discuss the integration of multi-omics data,addressing the challenges and innovative solutions for harmonizing these complex datasets.Through an examination of recent advancements and case studies,we underscore the critical role of multi-omics in advancing our understanding of cancer and paving the way for more effective and personalized therapeutic strategies.展开更多
基金supported by grants from the National Natural Science Foundation of China(Grant No.82272008)The Science&Technology Development Fund of Tianjin Education Commission for Higher Education(Grant No.2021KJ194)Tianjin Key Medical Discipline(Specialty)Construction Project(Grant No.TJYXZDXK-009A).
文摘Artificial intelligence(AI)is significantly advancing precision medicine,particularly in the fields of immunogenomics,radiomics,and pathomics.In immunogenomics,AI can process vast amounts of genomic and multi-omic data to identify biomarkers associated with immunotherapy responses and disease prognosis,thus providing strong support for personalized treatments.In radiomics,AI can analyze high-dimensional features from computed tomography(CT),magnetic resonance imaging(MRI),and positron emission tomography/computed tomography(PET/CT)images to discover imaging biomarkers associated with tumor heterogeneity,treatment response,and disease progression,thereby enabling non-invasive,real-time assessments for personalized therapy.Pathomics leverages AI for deep analysis of digital pathology images,and can uncover subtle changes in tissue microenvironments,cellular characteristics,and morphological features,and offer unique insights into immunotherapy response prediction and biomarker discovery.These AI-driven technologies not only enhance the speed,accuracy,and robustness of biomarker discovery but also significantly improve the precision,personalization,and effectiveness of clinical treatments,and are driving a shift from empirical to precision medicine.Despite challenges such as data quality,model interpretability,integration of multi-modal data,and privacy protection,the ongoing advancements in AI,coupled with interdisciplinary collaboration,are poised to further enhance AI’s roles in biomarker discovery and immunotherapy response prediction.These improvements are expected to lead to more accurate,personalized treatment strategies and ultimately better patient outcomes,marking a significant step forward in the evolution of precision medicine.
基金supported by the Guangzhou Municipal Basic Research Program Jointly Funded by City,University,and Enterprise Special Project(2024A03J0907)the Natural Science Foundation of Guangdong Province(2024A1515013201)+1 种基金the National Natural Science Foundation of China(82203720,82203188,82002682,81972731,81773026,81972383)the Science and Technology Project of Zhongshan Municipality(No.2024B1032).
文摘Background:Bladder cancer prognosis remains suboptimal despite advancements in research.Current molecular subtyping methods are resource-intensive,highlighting the need for efficient,cost-effective approaches to predict BCa molecular subtypes.Method:We developed a predictive model for BCa molecular subtypes using machine learning(ML)and pathomics derived from Hematoxylin-Eosin stained pathological slides.A cohort of 353 patients from TCGA was employed,and image features were extracted for analysis.Pathomic signatures were constructed using the LASSO Cox regression algorithm,and a pathomic-clinical nomogram was developed and validated in training and testing cohorts.Results:Seventy distinct image features were identified from 150 pathomic signatures.The model demonstrated robust predictive ability,with AUCs of 0.833 and 0.822 in the training and validation cohorts,respectively.The addition of pathomic score,N stage,and M stage improved the model’s discrimination,achieving AUCs of 0.877 and 0.794 in the training and validation cohorts.Limitations include the lack of an external validation cohort.Conclusion:Our ML-based pathomics model shows promise in predicting BCa molecular subtypes and has the potential to enhance prognosis prediction and inform treatment strategies,marking a significant step towards precision medicine for BCa.
基金Supported by Wenzhou Municipal Science and Technology Bureau,No.Y20240109.
文摘Hepatocellular carcinoma(HCC),a leading cause of cancer mortality,faces diagnostic and therapeutic challenges due to its histopathological complexity and clinical heterogeneity.Pathomics,an emerging discipline that integrates artificial intelligence(AI)with quantitative pathology image analysis,aims to decode disease heterogeneity by extracting high-dimensional features from histopathological specimens.This review highlights how AI-driven pathomics has revolutionized liver cancer management through automated analysis of whole-slide images.Pathomics integrates deep learning with histopathological features to enable precise tumour classification(e.g.,HCC vs cholangiocarcinoma),microvascular invasion(MVI)detection,recurrence risk stratification,and survival prediction.Advanced frameworks such as MVI-AI diagnostic model and CHOWDER demonstrate high accuracy in identifying prognostic biomarkers,whereas multiomics integration links morphometric patterns to molecular signatures(e.g.,EZH2 expression and immune infiltration).Despite these breakthroughs,critical bottlenecks persist,including limited multicentre validation studies,"black box"model interpretability,and clinical workflow integration.Future studies should emphasize AI-enhanced multimodal fusion(radiogenomics and liquid biopsy)and standardized platforms to bridge computational pathology and precision oncology,ultimately improving personalized therapeutic strategies for liver malignancies.This synthesis aims to guide research translation and advance personalized therapeutic strategies for liver malignancies.
基金supported by the DoD Breast Cancer Research Program Breakthrough Level 1 Award W81XWH-19-1-0668,NIH-NCI R21 CA253108-01DoD Prostate Cancer Research Program Idea Development Award W81XWH-18-1-0524+2 种基金Key R&D Program of Guangdong Province,China(No.2021B0101420006)National Science Fund for Distinguished Young Scholars,China(No.81925023)National Natural Science Foundation of China(No.62002082,62102103,61906050,81771912)。
文摘In the last decade,the focus of computational pathology research community has shifted from replicating the pathological examination for diagnosis done by pathologists to unlocking and discovering"sub-visual"prognostic image cues from the histopathological image.While we are getting more knowledge and experience in digital pathology,the emerging goal is to integrate other-omics or modalities that will contribute for building a better prognostic assay.In this paper,we provide a brief review of representative works that focus on integrating pathomics with radiomics and genomics for cancer prognosis.It includes:correlation of pathomics and genomics;fusion of pathomics and genomics;fusion of pathomics and radiomics.We also present challenges,potential opportunities,and avenues for future work.
基金National Natural Science Foundation of China(Nos.82373425 and 82372722)Medical Innovation Research Special Project of the Science and Technology Commission of Shanghai Municipality(No.23Y11904200)+3 种基金Shanghai Innovative Medical Device Application Demonstration Project 2023(No.23SHS02600)"Science and Technology Innovation Action Plan"Medical Innovation Research Special Project of Shanghai(No.21Y11913500)key project of the Medical and Health Technology Development Research Center of the National Health Commission(No.WKZX2023CX030003)Shanghai Key Laboratory Open Project(No.STCSM 22DZ2229005)
文摘To the Editor:Lung cancer,specifically lung adenocarcinoma(LUAD),is one of the primary cause of cancer-related mortality globally.[1,2]Nevertheless,only a small subset of individuals with LUAD have derived clinical benefits from chemoimmunotherapy in either first-line or subsequent treatment settings.Both programmed death-ligand 1(PDL1)expression and tumor mutational burden(TMB)have proven inadequate in accurately predicting treatment outcomes in these scenarios.[3]Consequently,there exists a pressing necessity to identify a reliable biomarker to inform treatment decisions.
基金supported by the National Natural Science Foundation of China(Nos.61932018,32241027,62072441,62272326,62132015,and U22A2037)the Beijing Municipal Administration of Hospitals Incubating Program(No.PX2021013).
文摘Kirsten rat sarcoma viral oncogene homolog(namely KRAS)is a key biomarker for prognostic analysis and targeted therapy of colorectal cancer.Recently,the advancement of machine learning,especially deep learning,has greatly promoted the development of KRAS mutation detection from tumor phenotype data,such as pathology slides or radiology images.However,there are still two major problems in existing studies:inadequate single-modal feature learning and lack of multimodal phenotypic feature fusion.In this paper,we propose a Disentangled Representation-based Multimodal Fusion framework integrating Pathomics and Radiomics(DRMF-PaRa)for KRAS mutation detection.Specifically,the DRMF-PaRa model consists of three parts:(1)the pathomics learning module,which introduces a tissue-guided Transformer model to extract more comprehensive and targeted pathological features;(2)the radiomics learning module,which captures the generic hand-crafted radiomics features and the task-specific deep radiomics features;(3)the disentangled representation-based multimodal fusion module,which learns factorized subspaces for each modality and provides a holistic view of the two heterogeneous phenotypic features.The proposed model is developed and evaluated on a multi modality dataset of 111 colorectal cancer patients with whole slide images and contrast-enhanced CT.The experimental results demonstrate the superiority of the proposed DRMF-PaRa model with an accuracy of 0.876 and an AUC of 0.865 for KRAS mutation detection.
文摘The integration of artificial intelligence(AI)and multiomics has transformed clinical and life sciences,enabling precision medicine and redefining disease understanding.Scientific publications grew significantly from 2.1 million in 2012 to 3.3 million in 2022,with AI research tripling during this period.Multiomics fields,including genomics and proteomics,also advanced,exemplified by the Human Proteome Project achieving a 90%complete blueprint by 2021.This growth highlights opportunities and challenges in integrating AI and multiomics into clinical reporting.A review of studies and case reports was conducted to evaluate AI and multiomics integration.Key areas analyzed included diagnostic accuracy,predictive modeling,and personalized treatment approaches driven by AI tools.Case examples were studied to assess impacts on clinical decision-making.AI and multiomics enhanced data integration,predictive insights,and treatment personalization.Fields like radiomics,genomics,and proteomics improved diagnostics and guided therapy.For instance,the“AI radiomics,geno-mics,oncopathomics,and surgomics project”combined radiomics and genomics for surgical decision-making,enabling preoperative,intraoperative,and post-operative interventions.AI applications in case reports predicted conditions like postoperative delirium and monitored cancer progression using genomic and imaging data.AI and multiomics enable standardized data analysis,dynamic updates,and predictive modeling in case reports.Traditional reports often lack objectivity,but AI enhances reproducibility and decision-making by processing large datasets.Challenges include data standardization,biases,and ethical concerns.Overcoming these barriers is vital for optimizing AI applications and advancing personalized medicine.AI and multiomics integration is revolutionizing clinical research and practice.Standardizing data reporting and addressing challenges in ethics and data quality will unlock their full potential.Emphasizing collaboration and transparency is essential for leveraging these tools to improve patient care and scientific communication.
文摘This paper aims to develop an understanding of the undergraduate students＇ learning by applying Kolb＇s （1984） learning concepts and theories. This research aims： （1） to study the visitors＇ learning experience; （2） to compare the learning process of visitors; and （3） to design learning process development for the visitors of the Phra Pathom Chedi National Museum. The quantitative methodology was used for data collection. The population was focused on group samplings of 300 participants and the selection method was a non-probability and purposive sampling. The research instrument was the structured questionnaire. Descriptive statistics, T-test, F-test （one-way analysis of variance （ANOVA））, and regression analysis were used for data analysis. According to the first objective, the study revealed that most of visitors were female, at the age of 19 years old, had a bachelor degree, and had income less than 5,000 baht. Their learning levels at the Phra Pathom Chedi National Museum were high. According to the second objective, the study found that there was no correlation between gender and income to the visitors＇ learning process related to the theoretical four learning processes which are： （1） before learning; （2） learning behavior; （3） while learning; and （4） the best ways of learning that create the most understanding. However, age and education varied the level of visitors＇ leaming process. According to the third objective regarding the four models of learning process development design, the study presented that： （1） For the accommodators, the visitors should be male, at a young age, and have a bachelor degree; （2） For the divergers, the visitors should be at a young age and have a bachelor degree; （3） For the convergers, the visitors should be at a young age, have a bachelor degree, and not with high income; and （4） For the assimilators, the visitors should be at a young age, have a bachelor degree, and with high income.
文摘The advent of multi-omics approaches has revolutionized the field of oncology by enabling a comprehensive understanding of cancer biology through the integration of diverse biological data.This review aims to explore the synergy between three key omics domains:radiomics,genoproteomics,and pathomics.Radiomics involves extracting high-dimensional data from medical images,providing valuable insights into tumor heterogeneity and treatment response.Genoproteomics,encompassing both genomic and proteomic analyses,delves into the molecular mechanisms driving cancer progression and therapeutic resistance.Pathomics leverages advanced digital pathology techniques to quantitatively analyze tissue architecture and cellular morphology.We provide an in-depth overview of the methodologies and tools employed in each omics field,highlighting their specific applications in oncology,including cancer diagnosis,biomarker discovery,and prediction of treatment outcomes.Furthermore,we discuss the integration of multi-omics data,addressing the challenges and innovative solutions for harmonizing these complex datasets.Through an examination of recent advancements and case studies,we underscore the critical role of multi-omics in advancing our understanding of cancer and paving the way for more effective and personalized therapeutic strategies.
