Background: Determining the origin of bone metastatic cancer (OBMC) is of great significance to clinical therapeutics. It is challenging for pathologists to determine the OBMC with limited clinical information and bone biopsy.
Methods: We designed a regional multiple-instance learning algorithm to predict the OBMC based on hematoxylin-eosin (H&E) staining slides alone. We collected 1041 cases from eight different hospitals and labeled 26,431 regions of interest to train the model. The performance of the model was assessed by ten-fold cross validation and external validation. Under the guidance of top3 predictions, we conducted an IHC test on 175 cases of unknown origins to compare the consistency of the results predicted by the model and indicated by the IHC markers. We also applied the model to identify whether there was tumor or not in a region, as well as distinguishing squamous cell carcinoma, adenocarcinoma, and neuroendocrine tumor.
Findings: In the within-cohort, our model achieved a top1-accuracy of 91.35% and a top3-accuracy of 97.75%. In the external cohort, our model displayed a good generalizability with a top3-accuracy of 97.44%. The top1 consistency between the results of the model and the immunohistochemistry markers was 83.90% and the top3 consistency was 94.33%. The model obtained an accuracy of 98.98% to identify whether there was tumor or not and an accuracy of 93.85% to differentiate three types of cancers.
Interpretation: Our model demonstrated good performance to predict the OBMC from routine histology and had great potential for assisting pathologists with determining the OBMC accurately.
Funding: National Science Foundation of China (61875102 and 61975089), Natural Science Foundation of Guangdong province (2021A15-15012379 and 2022A1515 012550), Science and Technology Research Program of Shenzhen City (JCYJ20200109110606054 and WDZC20200821141349001), and Tsinghua University Spring Breeze Fund (2020Z99CFZ023).
Download full-text PDF |
Source |
---|---|
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC9803701 | PMC |
http://dx.doi.org/10.1016/j.ebiom.2022.104426 | DOI Listing |
BMC Biol
January 2025
Cancer Research Program, Research Institute of the McGill University Health Centre, Montreal, QC, Canada.
Background: Uveal melanoma (UM) is the most common intraocular tumor in adults, arises either de novo from normal choroidal melanocytes (NCMs) or from pre-existing nevi that stem from NCMs and are thought to harbor UM-initiating mutations, most commonly in GNAQ or GNA11. However, there are no commercially available NCM cell lines, nor is there a detailed protocol for developing an oncogene-mutated CM line (MutCM) to study UM development. This study aimed to establish and characterize premalignant CM models from human donor eyes to recapitulate the cell populations at the origin of UM.
View Article and Find Full Text PDFMicrobiome
January 2025
Key Laboratory of Urban Environment and Health, Ningbo Observation and Research Station, Institute of Urban Environment, Chinese Academy of Sciences, Xiamen, 361021, China.
Background: Huge phages (genome size ≥ 200 kb) have been detected in diverse habitats worldwide, infecting a variety of prokaryotes. However, their evolution and adaptation strategy in soils remain poorly understood due to the scarcity of soil-derived genomes.
Results: Here, we conduct a size-fractioned (< 0.
J Exp Clin Cancer Res
January 2025
Key Laboratory of Xinjiang Endemic and Ethnic Diseases, Shihezi University School of Medicine, Shihezi, Xinjiang, China.
Background: Triggering receptor expressed on myeloid cells 2 (TREM2), a surface receptor predominantly expressed on myeloid cells, is a major hub gene in pathology-induced immune signaling. However, its function in hepatocellular carcinoma (HCC) remains controversial. This study aimed to evaluate the role of TREM2 in the tumor microenvironment in the context of HCC progression.
View Article and Find Full Text PDFPilot Feasibility Stud
January 2025
Center for Healthcare Organization and Implementation Research, VA , Boston Healthcare System, 150 South Huntington Avenue, Boston, 02130, USA.
Background: Drug use trends change rapidly among youth, leaving intervention experts struggling to respond promptly. Delays in responses can lead to preventable morbidity and mortality. The COVID-19 pandemic underscored the need for implementation science to facilitate rapid, equitable responses using existing treatment and prevention efforts.
View Article and Find Full Text PDFBMC Med
January 2025
Med-X Center for Informatics, Sichuan University, Chengdu, China.
Background: Adverse life experiences have been associated with increased susceptibilities to psychopathology in later life. However, their impact on psychological responses following physical trauma remains largely unexplored.
Methods: Based on the China Severe Trauma Cohort, we conducted a cohort study of 2937 patients who were admitted to the Trauma Medical Center of West China Hospital between June 2020 and August 2023.
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!