Pub Date : 2024-08-02DOI: 10.1038/s44303-024-00027-1
Cesare Berton, Simon Klingler, Stanislav Prytuliak, Jason P. Holland
In the context of molecularly targeted radiotherapy, dosimetry concerns in off-target tissues are a major limitation to the more wide-spread application of radiopharmaceuticals to treat diseases like cancer. Reducing off-target accumulation of radionuclides in background tissues, whilst maintaining high and specific uptake in disease sites and improving the therapeutic window, requires rethinking common radiotracer design concepts. This article explores ways in which innovative radiotracer chemistry (the making and breaking of bonds) is used to modify interactions with the host organism to control excretion profiles and dosimetry at the tissue-specific level.
{"title":"New tactics in the design of theranostic radiotracers","authors":"Cesare Berton, Simon Klingler, Stanislav Prytuliak, Jason P. Holland","doi":"10.1038/s44303-024-00027-1","DOIUrl":"10.1038/s44303-024-00027-1","url":null,"abstract":"In the context of molecularly targeted radiotherapy, dosimetry concerns in off-target tissues are a major limitation to the more wide-spread application of radiopharmaceuticals to treat diseases like cancer. Reducing off-target accumulation of radionuclides in background tissues, whilst maintaining high and specific uptake in disease sites and improving the therapeutic window, requires rethinking common radiotracer design concepts. This article explores ways in which innovative radiotracer chemistry (the making and breaking of bonds) is used to modify interactions with the host organism to control excretion profiles and dosimetry at the tissue-specific level.","PeriodicalId":501709,"journal":{"name":"npj Imaging","volume":" ","pages":"1-15"},"PeriodicalIF":0.0,"publicationDate":"2024-08-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s44303-024-00027-1.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141968561","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Cold atmospheric plasma (CAP) generates reactive oxygen species (ROS) which induce biological effects on living cells. CAP has potential applications in medicine, but its highly reactive nature can lead to adverse skin complications. A noninvasive technique to examine redox changes in skin is needed for monitoring the treatment process. This study was conducted to develop a skin-inflammation model triggered by CAP-derived ROS and to monitor its progression noninvasively by in vivo dynamic nuclear polarization-MRI (DNP-MRI). The model was successfully developed by exposing the skin to both direct and remote modes of CAP. In vivo DNP-MRI imaging revealed faster reduction rates of TEMPOL in plasma-irradiated skin-inflammation areas, particularly in the remote mode plasma-irradiated skin. MRI revealed high-intensity areas in both the superficial and deep layers of the plasma-irradiated skin. The study highlights the potential importance of DNP-MRI in imaging skin-inflammation models and could improve the use of CAP in medical treatments.
冷大气等离子体（CAP）会产生活性氧（ROS），从而对活细胞产生生物效应。CAP 具有潜在的医学应用价值，但其高反应性可能会导致不良的皮肤并发症。需要一种非侵入性技术来检测皮肤的氧化还原变化，以监测治疗过程。本研究旨在开发一种由 CAP 衍生的 ROS 引发的皮肤炎症模型，并通过体内动态核偏振-MRI（DNP-MRI）对其进展进行无创监测。通过将皮肤暴露于 CAP 的直接模式和远程模式，成功建立了该模型。活体 DNP-MRI 成像显示，在等离子照射的皮肤炎症区域，TEMPOL 的减少速度更快，尤其是在远程模式等离子照射的皮肤中。核磁共振成像显示，等离子辐照皮肤的表层和深层都有高强度区域。这项研究强调了 DNP-MRI 在皮肤炎症模型成像中的潜在重要性，并可改善 CAP 在医学治疗中的应用。
{"title":"In vivo redox imaging of plasma-induced skin-inflammation in mice","authors":"Yassien Badr, Abdelazim Elsayed Elhelaly, Fuminori Hyodo, Koki Ichihashi, Hiroyuki Tomita, Yoshifumi Noda, Hiroki Kato, Masayuki Matsuo","doi":"10.1038/s44303-024-00029-z","DOIUrl":"10.1038/s44303-024-00029-z","url":null,"abstract":"Cold atmospheric plasma (CAP) generates reactive oxygen species (ROS) which induce biological effects on living cells. CAP has potential applications in medicine, but its highly reactive nature can lead to adverse skin complications. A noninvasive technique to examine redox changes in skin is needed for monitoring the treatment process. This study was conducted to develop a skin-inflammation model triggered by CAP-derived ROS and to monitor its progression noninvasively by in vivo dynamic nuclear polarization-MRI (DNP-MRI). The model was successfully developed by exposing the skin to both direct and remote modes of CAP. In vivo DNP-MRI imaging revealed faster reduction rates of TEMPOL in plasma-irradiated skin-inflammation areas, particularly in the remote mode plasma-irradiated skin. MRI revealed high-intensity areas in both the superficial and deep layers of the plasma-irradiated skin. The study highlights the potential importance of DNP-MRI in imaging skin-inflammation models and could improve the use of CAP in medical treatments.","PeriodicalId":501709,"journal":{"name":"npj Imaging","volume":" ","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2024-08-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s44303-024-00029-z.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141968560","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-02DOI: 10.1038/s44303-024-00028-0
Radhika Narain, Ian Nessler, Paul L. Richardson, Jamie E. Erickson, Yuzhen Wang, Jacqueline Ferri, Heather L. Knight, Shaughn H. Bryant, Lucy A. Phillips, Liang Zhang, Soumya Mitra
In this work, the impact of physicochemical modifications on pharmacokinetics and in vivo targeting of a small molecule fibroblast activation protein inhibitor (FAPI) imaging ligand in a murine model of rheumatoid arthritis was evaluated. While similar ligands have been well-reported in oncology for molecular imaging and radiotherapy, there are limited reports of FAPI derivatives in targeted applications in immunology. As inflammation may increase both specific and non-specific delivery of targeted agents in general, we sought to identify the optimal targeted molecular imaging probe characteristics for efficient cell surface engagement. A series of FAPI derivatives were synthesized and their physicochemical properties modified via conjugation of fluorescent dyes and/or an albumin-binding small molecule. The impact of these modifications on cell surface binding affinity was assessed using an overexpressing cell line. Additionally, a thorough mechanistic characterization of fibroblast activation protein (FAP) cell surface internalization was evaluated in both overexpressing and endogenously expressing cells. Lastly, the pharmacokinetics and in vivo uptake in inflamed arthritic paws were characterized via near-infrared (NIR) imaging. All targeted molecular imaging agents tested maintained strong nanomolar binding affinity to cell surface FAP independent of chemical modification. The murine fibroblast-like synoviocytes expressed lower absolute cell-surface FAP compared to a transfected line, and the net internalization half-life measured for the transfected cells via flow cytometry was 7.2 h. The unmodified FAPI ligand exhibited the poorest in vivo targeting, likely resulting from its large apparent volume of distribution (62.7 ml) and rapid systemic clearance (t1/2 = 0.5 h). Conjugation of a charged, hydrophilic AF647 fluorophore decreased systemic clearance (t1/2 = 2.1 h) and demonstrated a 2-fold improvement in blocking FAPI-800CW engagement of FAP in vivo when compared to blocking of FAPI-800CW with FAPI with up to 2.8-fold improvements noted for the equivalent albumin binding construct comparison.
{"title":"Increased imaging ligand hydrophilicity and improved pharmacokinetic properties provides enhanced in vivo targeting of fibroblast activation protein","authors":"Radhika Narain, Ian Nessler, Paul L. Richardson, Jamie E. Erickson, Yuzhen Wang, Jacqueline Ferri, Heather L. Knight, Shaughn H. Bryant, Lucy A. Phillips, Liang Zhang, Soumya Mitra","doi":"10.1038/s44303-024-00028-0","DOIUrl":"10.1038/s44303-024-00028-0","url":null,"abstract":"In this work, the impact of physicochemical modifications on pharmacokinetics and in vivo targeting of a small molecule fibroblast activation protein inhibitor (FAPI) imaging ligand in a murine model of rheumatoid arthritis was evaluated. While similar ligands have been well-reported in oncology for molecular imaging and radiotherapy, there are limited reports of FAPI derivatives in targeted applications in immunology. As inflammation may increase both specific and non-specific delivery of targeted agents in general, we sought to identify the optimal targeted molecular imaging probe characteristics for efficient cell surface engagement. A series of FAPI derivatives were synthesized and their physicochemical properties modified via conjugation of fluorescent dyes and/or an albumin-binding small molecule. The impact of these modifications on cell surface binding affinity was assessed using an overexpressing cell line. Additionally, a thorough mechanistic characterization of fibroblast activation protein (FAP) cell surface internalization was evaluated in both overexpressing and endogenously expressing cells. Lastly, the pharmacokinetics and in vivo uptake in inflamed arthritic paws were characterized via near-infrared (NIR) imaging. All targeted molecular imaging agents tested maintained strong nanomolar binding affinity to cell surface FAP independent of chemical modification. The murine fibroblast-like synoviocytes expressed lower absolute cell-surface FAP compared to a transfected line, and the net internalization half-life measured for the transfected cells via flow cytometry was 7.2 h. The unmodified FAPI ligand exhibited the poorest in vivo targeting, likely resulting from its large apparent volume of distribution (62.7 ml) and rapid systemic clearance (t1/2 = 0.5 h). Conjugation of a charged, hydrophilic AF647 fluorophore decreased systemic clearance (t1/2 = 2.1 h) and demonstrated a 2-fold improvement in blocking FAPI-800CW engagement of FAP in vivo when compared to blocking of FAPI-800CW with FAPI with up to 2.8-fold improvements noted for the equivalent albumin binding construct comparison.","PeriodicalId":501709,"journal":{"name":"npj Imaging","volume":" ","pages":"1-11"},"PeriodicalIF":0.0,"publicationDate":"2024-08-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s44303-024-00028-0.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141968562","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-25DOI: 10.1038/s44303-024-00022-6
Hayri E. Balcioglu, Rebecca Wijers, Marcel Smid, Dora Hammerl, Anita M. Trapman-Jansen, Astrid Oostvogels, Mieke Timmermans, John W. M. Martens, Reno Debets
Spatial distribution of intra-tumoral immune cell populations is considered a critical determinant of tumor evolution and response to therapy. The accurate and systemic search for contexture-based predictors would be accelerated by methods that allow interactive visualization and interrogation of tumor micro-environments (TME), independent of image acquisition platforms. To this end, we have developed the TME-Analyzer, a new image analysis tool, which we have benchmarked against 2 software tools regarding densities and networks of immune effector cells using multiplexed immune-fluorescent images of triple negative breast cancer (TNBC). With the TME-Analyzer we have identified a 10-parameter classifier, predominantly featuring cellular distances, that significantly predicted overall survival, and which was validated using multiplexed ion beam time of flight images from an independent cohort. In conclusion, the TME-Analyzer enabled accurate interactive analysis of the spatial immune phenotype from different imaging platforms as well as enhanced utility and aided the discovery of contextual predictors towards the survival of TNBC patients.
{"title":"TME-analyzer: a new interactive and dynamic image analysis tool that identified immune cell distances as predictors for survival of triple negative breast cancer patients","authors":"Hayri E. Balcioglu, Rebecca Wijers, Marcel Smid, Dora Hammerl, Anita M. Trapman-Jansen, Astrid Oostvogels, Mieke Timmermans, John W. M. Martens, Reno Debets","doi":"10.1038/s44303-024-00022-6","DOIUrl":"10.1038/s44303-024-00022-6","url":null,"abstract":"Spatial distribution of intra-tumoral immune cell populations is considered a critical determinant of tumor evolution and response to therapy. The accurate and systemic search for contexture-based predictors would be accelerated by methods that allow interactive visualization and interrogation of tumor micro-environments (TME), independent of image acquisition platforms. To this end, we have developed the TME-Analyzer, a new image analysis tool, which we have benchmarked against 2 software tools regarding densities and networks of immune effector cells using multiplexed immune-fluorescent images of triple negative breast cancer (TNBC). With the TME-Analyzer we have identified a 10-parameter classifier, predominantly featuring cellular distances, that significantly predicted overall survival, and which was validated using multiplexed ion beam time of flight images from an independent cohort. In conclusion, the TME-Analyzer enabled accurate interactive analysis of the spatial immune phenotype from different imaging platforms as well as enhanced utility and aided the discovery of contextual predictors towards the survival of TNBC patients.","PeriodicalId":501709,"journal":{"name":"npj Imaging","volume":" ","pages":"1-16"},"PeriodicalIF":0.0,"publicationDate":"2024-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s44303-024-00022-6.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141803913","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-25DOI: 10.1038/s44303-024-00023-5
Susanne Fleig, Zuzanna Anna Magnuska, Patrick Koczera, Jannine Salewski, Sonja Djudjaj, Georg Schmitz, Fabian Kiessling
Chronic kidney disease (CKD) affects 850 million people worldwide and is associated with significant cardiovascular morbidity and mortality. Routine laboratory tests do not reflect early stages of microcirculatory changes and vascular rarefaction that characterise kidney fibrosis, the common endpoint of CKD. Imaging techniques that detect CKD in early stages could promote timely treatment with new drugs like SGLT2 inhibitors, thus, decreasing CKD progression and the cardiovascular disease burden. Ultrasound is the most used imaging modality in CKD, as it is non-invasive and radiation free. Initially, ultrasound imaging was applied to assess kidney macro-morphology and to rule out ureteral obstruction. The development of higher frequency probes allowed for more detailed imaging of kidney parenchyma, and advances in Doppler ultrasound provided insights into segmental arterial flow patterns including resistive indices as an indirect measure of microcirculatory impedance, elevated values of which correlated with progressive organ failure and fibrosis. Today, low-flow detection methods and matrix probes better resolve organ parenchyma and smaller vascular beds, and contrast-enhanced ultrasound allows perfusion measurement. Particularly, super-resolution ultrasound imaging, a technology currently being in clinical translation, can characterise the microcirculation morphologically and functionally in unrivalled detail. This is accompanied by rapid developments in radiomics and machine learning supporting ultrasound image acquisition and processing, as well as lesion detection and characterisation. This perspective article introduces emerging ultrasound methods for the diagnosis of CKD and discusses how the promising technical and analytical advancements can improve disease management after successful translation to clinical application.
{"title":"Advanced ultrasound methods to improve chronic kidney disease diagnosis","authors":"Susanne Fleig, Zuzanna Anna Magnuska, Patrick Koczera, Jannine Salewski, Sonja Djudjaj, Georg Schmitz, Fabian Kiessling","doi":"10.1038/s44303-024-00023-5","DOIUrl":"10.1038/s44303-024-00023-5","url":null,"abstract":"Chronic kidney disease (CKD) affects 850 million people worldwide and is associated with significant cardiovascular morbidity and mortality. Routine laboratory tests do not reflect early stages of microcirculatory changes and vascular rarefaction that characterise kidney fibrosis, the common endpoint of CKD. Imaging techniques that detect CKD in early stages could promote timely treatment with new drugs like SGLT2 inhibitors, thus, decreasing CKD progression and the cardiovascular disease burden. Ultrasound is the most used imaging modality in CKD, as it is non-invasive and radiation free. Initially, ultrasound imaging was applied to assess kidney macro-morphology and to rule out ureteral obstruction. The development of higher frequency probes allowed for more detailed imaging of kidney parenchyma, and advances in Doppler ultrasound provided insights into segmental arterial flow patterns including resistive indices as an indirect measure of microcirculatory impedance, elevated values of which correlated with progressive organ failure and fibrosis. Today, low-flow detection methods and matrix probes better resolve organ parenchyma and smaller vascular beds, and contrast-enhanced ultrasound allows perfusion measurement. Particularly, super-resolution ultrasound imaging, a technology currently being in clinical translation, can characterise the microcirculation morphologically and functionally in unrivalled detail. This is accompanied by rapid developments in radiomics and machine learning supporting ultrasound image acquisition and processing, as well as lesion detection and characterisation. This perspective article introduces emerging ultrasound methods for the diagnosis of CKD and discusses how the promising technical and analytical advancements can improve disease management after successful translation to clinical application.","PeriodicalId":501709,"journal":{"name":"npj Imaging","volume":" ","pages":"1-9"},"PeriodicalIF":0.0,"publicationDate":"2024-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s44303-024-00023-5.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141968559","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-17DOI: 10.1038/s44303-024-00025-3
Hua Zhang, Kelly H. Lu, Malik Ebbini, Penghsuan Huang, Haiyan Lu, Lingjun Li
The recent upswing in the integration of spatial multi-omics for conducting multidimensional information measurements is opening a new chapter in biological research. Mapping the landscape of various biomolecules including metabolites, proteins, nucleic acids, etc., and even deciphering their functional interactions and pathways is believed to provide a more holistic and nuanced exploration of the molecular intricacies within living systems. Mass spectrometry imaging (MSI) stands as a forefront technique for spatially mapping the metabolome, lipidome, and proteome within diverse tissue and cell samples. In this review, we offer a systematic survey delineating different MSI techniques for spatially resolved multi-omics analysis, elucidating their principles, capabilities, and limitations. Particularly, we focus on the advancements in methodologies aimed at augmenting the molecular sensitivity and specificity of MSI; and depict the burgeoning integration of MSI-based spatial metabolomics, lipidomics, and proteomics, encompassing the synergy with other imaging modalities. Furthermore, we offer speculative insights into the potential trajectory of MSI technology in the future.
{"title":"Mass spectrometry imaging for spatially resolved multi-omics molecular mapping","authors":"Hua Zhang, Kelly H. Lu, Malik Ebbini, Penghsuan Huang, Haiyan Lu, Lingjun Li","doi":"10.1038/s44303-024-00025-3","DOIUrl":"10.1038/s44303-024-00025-3","url":null,"abstract":"The recent upswing in the integration of spatial multi-omics for conducting multidimensional information measurements is opening a new chapter in biological research. Mapping the landscape of various biomolecules including metabolites, proteins, nucleic acids, etc., and even deciphering their functional interactions and pathways is believed to provide a more holistic and nuanced exploration of the molecular intricacies within living systems. Mass spectrometry imaging (MSI) stands as a forefront technique for spatially mapping the metabolome, lipidome, and proteome within diverse tissue and cell samples. In this review, we offer a systematic survey delineating different MSI techniques for spatially resolved multi-omics analysis, elucidating their principles, capabilities, and limitations. Particularly, we focus on the advancements in methodologies aimed at augmenting the molecular sensitivity and specificity of MSI; and depict the burgeoning integration of MSI-based spatial metabolomics, lipidomics, and proteomics, encompassing the synergy with other imaging modalities. Furthermore, we offer speculative insights into the potential trajectory of MSI technology in the future.","PeriodicalId":501709,"journal":{"name":"npj Imaging","volume":" ","pages":"1-15"},"PeriodicalIF":0.0,"publicationDate":"2024-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s44303-024-00025-3.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141639658","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-08DOI: 10.1038/s44303-024-00026-2
Okyaz Eminaga, Fred Saad, Zhe Tian, Ulrich Wolffgang, Pierre I. Karakiewicz, Véronique Ouellet, Feryel Azzi, Tilmann Spieker, Burkhard M. Helmke, Markus Graefen, Xiaoyi Jiang, Lei Xing, Jorn H. Witt, Dominique Trudel, Sami-Ramzi Leyh-Bannurah
{"title":"Author Correction: Artificial intelligence unravels interpretable malignancy grades of prostate cancer on histology images","authors":"Okyaz Eminaga, Fred Saad, Zhe Tian, Ulrich Wolffgang, Pierre I. Karakiewicz, Véronique Ouellet, Feryel Azzi, Tilmann Spieker, Burkhard M. Helmke, Markus Graefen, Xiaoyi Jiang, Lei Xing, Jorn H. Witt, Dominique Trudel, Sami-Ramzi Leyh-Bannurah","doi":"10.1038/s44303-024-00026-2","DOIUrl":"10.1038/s44303-024-00026-2","url":null,"abstract":"","PeriodicalId":501709,"journal":{"name":"npj Imaging","volume":" ","pages":"1-1"},"PeriodicalIF":0.0,"publicationDate":"2024-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s44303-024-00026-2.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141561182","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-01DOI: 10.1038/s44303-024-00018-2
Fan Fan, Georgia Martinez, Thomas DeSilvio, John Shin, Yijiang Chen, Jackson Jacobs, Bangchen Wang, Takaya Ozeki, Maxime W. Lafarge, Viktor H. Koelzer, Laura Barisoni, Anant Madabhushi, Satish E. Viswanath, Andrew Janowczyk
Batch effects (BEs) refer to systematic technical differences in data collection unrelated to biological variations whose noise is shown to negatively impact machine learning (ML) model generalizability. Here we release CohortFinder ( http://cohortfinder.com ), an open-source tool aimed at mitigating BEs via data-driven cohort partitioning. We demonstrate CohortFinder improves ML model performance in downstream digital pathology and medical image processing tasks. CohortFinder is freely available for download at cohortfinder.com.
{"title":"CohortFinder: an open-source tool for data-driven partitioning of digital pathology and imaging cohorts to yield robust machine-learning models","authors":"Fan Fan, Georgia Martinez, Thomas DeSilvio, John Shin, Yijiang Chen, Jackson Jacobs, Bangchen Wang, Takaya Ozeki, Maxime W. Lafarge, Viktor H. Koelzer, Laura Barisoni, Anant Madabhushi, Satish E. Viswanath, Andrew Janowczyk","doi":"10.1038/s44303-024-00018-2","DOIUrl":"10.1038/s44303-024-00018-2","url":null,"abstract":"Batch effects (BEs) refer to systematic technical differences in data collection unrelated to biological variations whose noise is shown to negatively impact machine learning (ML) model generalizability. Here we release CohortFinder ( http://cohortfinder.com ), an open-source tool aimed at mitigating BEs via data-driven cohort partitioning. We demonstrate CohortFinder improves ML model performance in downstream digital pathology and medical image processing tasks. CohortFinder is freely available for download at cohortfinder.com.","PeriodicalId":501709,"journal":{"name":"npj Imaging","volume":" ","pages":"1-7"},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s44303-024-00018-2.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141489084","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-01DOI: 10.1038/s44303-024-00020-8
Jan-Philipp Redlich, Friedrich Feuerhake, Joachim Weis, Nadine S. Schaadt, Sarah Teuber-Hanselmann, Christoph Buck, Sabine Luttmann, Andrea Eberle, Stefan Nikolin, Arno Appenzeller, Andreas Portmann, André Homeyer
In recent years, the diagnosis of gliomas has become increasingly complex. Analysis of glioma histopathology images using artificial intelligence (AI) offers new opportunities to support diagnosis and outcome prediction. To give an overview of the current state of research, this review examines 83 publicly available research studies that have proposed AI-based methods for whole-slide histopathology images of human gliomas, covering the diagnostic tasks of subtyping (23/83), grading (27/83), molecular marker prediction (20/83), and survival prediction (29/83). All studies were reviewed with regard to methodological aspects as well as clinical applicability. It was found that the focus of current research is the assessment of hematoxylin and eosin-stained tissue sections of adult-type diffuse gliomas. The majority of studies (52/83) are based on the publicly available glioblastoma and low-grade glioma datasets from The Cancer Genome Atlas (TCGA) and only a few studies employed other datasets in isolation (16/83) or in addition to the TCGA datasets (15/83). Current approaches mostly rely on convolutional neural networks (63/83) for analyzing tissue at 20x magnification (35/83). A new field of research is the integration of clinical data, omics data, or magnetic resonance imaging (29/83). So far, AI-based methods have achieved promising results, but are not yet used in real clinical settings. Future work should focus on the independent validation of methods on larger, multi-site datasets with high-quality and up-to-date clinical and molecular pathology annotations to demonstrate routine applicability.
{"title":"Applications of artificial intelligence in the analysis of histopathology images of gliomas: a review","authors":"Jan-Philipp Redlich, Friedrich Feuerhake, Joachim Weis, Nadine S. Schaadt, Sarah Teuber-Hanselmann, Christoph Buck, Sabine Luttmann, Andrea Eberle, Stefan Nikolin, Arno Appenzeller, Andreas Portmann, André Homeyer","doi":"10.1038/s44303-024-00020-8","DOIUrl":"10.1038/s44303-024-00020-8","url":null,"abstract":"In recent years, the diagnosis of gliomas has become increasingly complex. Analysis of glioma histopathology images using artificial intelligence (AI) offers new opportunities to support diagnosis and outcome prediction. To give an overview of the current state of research, this review examines 83 publicly available research studies that have proposed AI-based methods for whole-slide histopathology images of human gliomas, covering the diagnostic tasks of subtyping (23/83), grading (27/83), molecular marker prediction (20/83), and survival prediction (29/83). All studies were reviewed with regard to methodological aspects as well as clinical applicability. It was found that the focus of current research is the assessment of hematoxylin and eosin-stained tissue sections of adult-type diffuse gliomas. The majority of studies (52/83) are based on the publicly available glioblastoma and low-grade glioma datasets from The Cancer Genome Atlas (TCGA) and only a few studies employed other datasets in isolation (16/83) or in addition to the TCGA datasets (15/83). Current approaches mostly rely on convolutional neural networks (63/83) for analyzing tissue at 20x magnification (35/83). A new field of research is the integration of clinical data, omics data, or magnetic resonance imaging (29/83). So far, AI-based methods have achieved promising results, but are not yet used in real clinical settings. Future work should focus on the independent validation of methods on larger, multi-site datasets with high-quality and up-to-date clinical and molecular pathology annotations to demonstrate routine applicability.","PeriodicalId":501709,"journal":{"name":"npj Imaging","volume":" ","pages":"1-16"},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s44303-024-00020-8.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141489086","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：