Predicting survival from colorectal cancer histology slides using deep learning: A retrospective multicenter study

PLoS Medicine, Год журнала: 2019, Номер 16(1), С. e1002730 - e1002730

Опубликована: Янв. 24, 2019

Background For virtually every patient with colorectal cancer (CRC), hematoxylin–eosin (HE)–stained tissue slides are available. These images contain quantitative information, which is not routinely used to objectively extract prognostic biomarkers. In the present study, we investigated whether deep convolutional neural networks (CNNs) can prognosticators directly from these widely available images. Methods and findings We hand-delineated single-tissue regions in 86 CRC slides, yielding more than 100,000 HE image patches, train a CNN by transfer learning, reaching nine-class accuracy of >94% an independent data set 7,180 25 patients. With this tool, performed automated decomposition representative multitissue 862 500 stage I–IV patients The Cancer Genome Atlas (TCGA) cohort, large international multicenter collection tissue. Based on output neuron activations CNN, calculated "deep stroma score," was factor for overall survival (OS) multivariable Cox proportional hazard model (hazard ratio [HR] 95% confidence interval [CI]: 1.99 [1.27–3.12], p = 0.0028), while same manual quantification stromal areas gene expression signature cancer-associated fibroblasts (CAFs) were only specific tumor stages. validated cohort 409 "Darmkrebs: Chancen der Verhütung durch Screening" (DACHS) study who recruited between 2003 2007 multiple institutions Germany. Again, score OS (HR 1.63 [1.14–2.33], 0.008), CRC-specific 2.29 [1.5–3.48], 0.0004), relapse-free (RFS; HR 1.92 [1.34–2.76], 0.0004). A prospective validation required before biomarker be implemented clinical workflows. Conclusions our retrospective show that assess human microenvironment predict prognosis histopathological

Язык: Английский

---

Cancer stemness, intratumoral heterogeneity, and immune response across cancers

Proceedings of the National Academy of Sciences, Год журнала: 2019, Номер 116(18), С. 9020 - 9029

Опубликована: Апрель 17, 2019

Significance The exclusion of immune cells from the tumor microenvironment has been associated with poor prognosis in majority cancers. We report that when considering 21 solid cancer types, cell is widely presence a stem cell-like phenotype tumors (“stemness”). Stemness positively correlates higher intratumoral heterogeneity, possibly by protecting antigenic clones elimination system. activation stemness program appears to limit antitumor responses via cell-intrinsic silencing endogenous retrovirus expression, repression type I interferon signaling, and up-regulation immunosuppressive checkpoints. Our work suggests targeting will promote T infiltration render more responsive control.

Язык: Английский

---

Application of bibliometrics in medicine: a historical bibliometrics analysis

Health Information & Libraries Journal, Год журнала: 2020, Номер 38(2), С. 125 - 138

Опубликована: Янв. 29, 2020

Abstract Background The application of bibliometrics in medicine enables one to analyse vast amounts publications and their production patterns on macroscopic microscopic levels. Objectives aim the study was historical perspective research literature regarding medicine. Methods Publications related from 1970 2018 were harvested Scopus bibliographic database. Reference Publication Year Spectroscopy triangulated with VOSViewer identify roots evolution topics clinical areas. Results search resulted 6557 publications. trend positive. Historical analysis identified 33 16 areas where applied. Discussion increase productivity might be attributed increased use quantitative metrics evaluation, publish or perish phenomenon evidence‐based Conclusion Medicine forefront knowledge development bibliometrics. reference publication year spectroscopy proved an accurate method which able most roots.

Язык: Английский

---

Spatial architecture of the immune microenvironment orchestrates tumor immunity and therapeutic response

Journal of Hematology & Oncology, Год журнала: 2021, Номер 14(1)

Опубликована: Июнь 25, 2021

Tumors are not only aggregates of malignant cells but also well-organized complex ecosystems. The immunological components within tumors, termed the tumor immune microenvironment (TIME), have long been shown to be strongly related development, recurrence and metastasis. However, conventional studies that underestimate potential value spatial architecture TIME unable completely elucidate its complexity. As innovative high-flux high-dimensional technologies emerge, researchers can more feasibly accurately detect depict TIME. These findings improved our understanding complexity role in biology. In this review, we first epitomized some representative emerging study categorized description methods used characterize these structures. Then, determined functions biology effects gradient extracellular nonspecific chemicals (ENSCs) on We discussed clinical architectures TIME, as well current limitations future prospects novel field. This review will bring an dimension ecosystem research, attention promote application research practice.

Язык: Английский

---

Advancing Patient Care: How Artificial Intelligence Is Transforming Healthcare

Journal of Personalized Medicine, Год журнала: 2023, Номер 13(8), С. 1214 - 1214

Опубликована: Июль 31, 2023

Artificial Intelligence (AI) has emerged as a transformative technology with immense potential in the field of medicine. By leveraging machine learning and deep learning, AI can assist diagnosis, treatment selection, patient monitoring, enabling more accurate efficient healthcare delivery. The widespread implementation role to revolutionize patients' outcomes transform way is practiced, leading improved accessibility, affordability, quality care. This article explores diverse applications reviews current state adoption healthcare. It concludes by emphasizing need for collaboration between physicians experts harness full AI.

Язык: Английский

---

Cross-talk between cuproptosis and ferroptosis regulators defines the tumor microenvironment for the prediction of prognosis and therapies in lung adenocarcinoma

Frontiers in Immunology, Год журнала: 2023, Номер 13

Опубликована: Янв. 17, 2023

Cuproptosis, a newly identified form of programmed cell death, plays vital roles in tumorigenesis. However, the interconnectivity cuproptosis and ferroptosis is poorly understood. In our study, we explored genomic alterations 1162 lung adenocarcinoma (LUAD) samples from The Cancer Genome Atlas (TCGA) Gene Expression Omnibus (GEO) cohort to comprehensively evaluate regulators. We systematically performed pancancer analysis by depicting molecular correlations between regulators 33 cancer types, indicating cross-talk at multiomic level. successfully three distinct clusters based on regulators, termed CuFeclusters, as well cuproptosis/ferroptosis gene subsets. tumor microenvironment cell-infiltrating characteristics CuFeclusters were highly consistent with immune phenotypes tumors. Furthermore, CuFescore was constructed validated predict pathways individuals response chemotherapeutic drugs immunotherapy. significantly associated expression miRNA regulation post-transcription. Thus, research established an applied scoring scheme, identify LUAD patients who are candidates for immunotherapy patient sensitivity drugs.

Язык: Английский

---

CellCharter reveals spatial cell niches associated with tissue remodeling and cell plasticity

Nature Genetics, Год журнала: 2023, Номер 56(1), С. 74 - 84

Опубликована: Дек. 8, 2023

Язык: Английский

---

Single-cell and spatial profiling identify three response trajectories to pembrolizumab and radiation therapy in triple negative breast cancer

Cancer Cell, Год журнала: 2024, Номер 42(1), С. 70 - 84.e8

Опубликована: Янв. 1, 2024

Язык: Английский

---

Pan‐Cancer Single‐Cell and Spatial‐Resolved Profiling Reveals the Immunosuppressive Role of APOE+ Macrophages in Immune Checkpoint Inhibitor Therapy

Advanced Science, Год журнала: 2024, Номер 11(23)

Опубликована: Апрель 3, 2024

Abstract The heterogeneity of macrophages influences the response to immune checkpoint inhibitor (ICI) therapy. However, few studies explore impact APOE + on ICI therapy using single‐cell RNA sequencing (scRNA‐seq) and machine learning methods. scRNA‐seq bulk RNA‐seq data are Integrated construct an M.Sig model for predicting based distinct molecular signatures macrophage algorithms. Comprehensive analysis as well in vivo vitro experiments applied potential mechanisms affecting response. shows clear advantages efficacy prognosis pan‐cancer patients. proportion is higher non‐responders triple‐negative breast cancer compared with responders, interaction longer distance between CD8 exhausted T (Tex) cells confirmed by multiplex immunohistochemistry. In a 4T1 tumor‐bearing mice model, combined treatment best efficacy. real‐world immunotherapy accurately predicts pan‐cancer, which may be associated Tex cells.

Язык: Английский

---

Artificial intelligence—the third revolution in pathology

Histopathology, Год журнала: 2018, Номер 74(3), С. 372 - 376

Опубликована: Окт. 1, 2018

Histopathology has undergone major changes firstly with the introduction of Immunohistochemistry, and latterly Genomic Medicine.We argue that a third revolution is underway: Artificial Intelligence (AI).Coming on back Digital Pathology (DP), AI potential to both challenge traditional practice provide totally new realm for pathology diagnostics.Hereby we stress importance certified pathologists having learned from experience previous revolutions be willing accept such disruptive technologies, ready innovate actively engage in creation, application validation technologies oversee safe into diagnostic practice.

Язык: Английский

---