Using digital pathology to standardize and automate histological evaluations of environmental samples DOI Creative Commons
Philip Tanabe, Daniel Schlenk, Kristy L. Forsgren

et al.

Environmental Toxicology and Chemistry, Journal Year: 2025, Volume and Issue: 44(2), P. 306 - 317

Published: Jan. 6, 2025

Histological evaluations of tissues are commonly used in environmental monitoring studies to assess the health and fitness status populations or even whole ecosystems. Although traditional histology can be cost-effective, there is a shortage proficient histopathologists results often subjective between operators, leading variance. Digital pathology powerful diagnostic tool that has already significantly transformed research human but rarely been applied studies. analyses slide images introduce possibilities highly standardized histopathological evaluations, as well use artificial intelligence for novel analyses. Furthermore, incorporation digital into using bioindicator species groups such bivalves fish greatly improve accuracy, reproducibility, efficiency This review aims readers how it includes guidelines sample preparation, potential sources error, comparisons

Language: Английский

Multistain deep learning for prediction of prognosis and therapy response in colorectal cancer DOI
Sebastian Foersch,

Christina Glasner,

Ann-Christin Woerl

et al.

Nature Medicine, Journal Year: 2023, Volume and Issue: 29(2), P. 430 - 439

Published: Jan. 9, 2023

Language: Английский

Citations

146
A guide to artificial intelligence for cancer researchers DOI
Raquel Pérez-López, Narmin Ghaffari Laleh, Faisal Mahmood

et al.

Nature reviews. Cancer, Journal Year: 2024, Volume and Issue: 24(6), P. 427 - 441

Published: May 16, 2024

Language: Английский

Citations

67
Generalizable biomarker prediction from cancer pathology slides with self-supervised deep learning: A retrospective multi-centric study DOI Creative Commons
J. Niehues, Philip Quirke, Nicholas P. West

et al.

Cell Reports Medicine, Journal Year: 2023, Volume and Issue: 4(4), P. 100980 - 100980

Published: March 22, 2023

Deep learning (DL) can predict microsatellite instability (MSI) from routine histopathology slides of colorectal cancer (CRC). However, it is unclear whether DL also other biomarkers with high performance and predictions generalize to external patient populations. Here, we acquire CRC tissue samples two large multi-centric studies. We systematically compare six different state-of-the-art architectures pathology slides, including MSI mutations in BRAF, KRAS, NRAS, PIK3CA. Using a validation cohort provide realistic evaluation setting, show that models using self-supervised, attention-based multiple-instance consistently outperform previous approaches while offering explainable visualizations the indicative regions morphologies. While prediction BRAF reaches clinical-grade performance, mutation PIK3CA, NRAS was clinically insufficient.

Language: Английский

Citations

61
An MRI Deep Learning Model Predicts Outcome in Rectal Cancer DOI
Xiaofeng Jiang, Hengyu Zhao, Oliver Lester Saldanha

et al.

Radiology, Journal Year: 2023, Volume and Issue: 307(5)

Published: June 1, 2023

Background Deep learning (DL) models can potentially improve prognostication of rectal cancer but have not been systematically assessed. Purpose To develop and validate an MRI DL model for predicting survival in patients with based on segmented tumor volumes from pretreatment T2-weighted scans. Materials Methods were trained validated retrospectively collected scans diagnosed between August 2003 April 2021 at two centers. Patients excluded the study if there concurrent malignant neoplasms, prior anticancer treatment, incomplete course neoadjuvant therapy, or no radical surgery performed. The Harrell C-index was used to determine best model, which applied internal external test sets. stratified into high- low-risk groups a fixed cutoff calculated training set. A multimodal also assessed, model-computed risk score carcinoembryonic antigen level as input. Results set included 507 (median age, 56 years [IQR, 46-64 years]; 355 men). In validation (n = 218; median 55 47-63 144 men), algorithm reached 0.82 overall survival. hazard ratios 3.0 (95% CI: 1.0, 9.0) high-risk group 112; 60 52-70 76 men) 2.3 5.4) 58; 57 50-67 38 further improved performance, 0.86 0.67 set, respectively. Conclusion preoperative able predict cancer. could be stratification tool. Published under CC BY 4.0 license. Supplemental material is available this article. See editorial by Langs issue.

Language: Английский

Citations

53
An overview and a roadmap for artificial intelligence in hematology and oncology DOI Creative Commons
Wiebke Rösler, Michael Altenbuchinger, Bettina Baeßler

et al.

Journal of Cancer Research and Clinical Oncology, Journal Year: 2023, Volume and Issue: 149(10), P. 7997 - 8006

Published: March 15, 2023

Artificial intelligence (AI) is influencing our society on many levels and has broad implications for the future practice of hematology oncology. However, medical professionals researchers, it often remains unclear what AI can cannot do, are promising areas a sensible application in Finally, limits perils using oncology not obvious to healthcare professionals.

Language: Английский

Citations

49
Explainability and causability in digital pathology DOI Creative Commons
Markus Plass, Michaela Kargl, Tim‐Rasmus Kiehl

et al.

The Journal of Pathology Clinical Research, Journal Year: 2023, Volume and Issue: 9(4), P. 251 - 260

Published: April 12, 2023

Abstract The current move towards digital pathology enables pathologists to use artificial intelligence (AI)‐based computer programmes for the advanced analysis of whole slide images. However, currently, best‐performing AI algorithms image are deemed black boxes since it remains – even their developers often unclear why algorithm delivered a particular result. Especially in medicine, better understanding algorithmic decisions is essential avoid mistakes and adverse effects on patients. This review article aims provide medical experts with insights issue explainability pathology. A short introduction relevant underlying core concepts machine learning shall nurture reader's specific this field. Addressing explainability, rapidly evolving research field explainable (XAI) has developed many techniques methods make black‐box machine‐learning systems more transparent. These XAI first step making understandable by humans. we argue that an explanation interface must complement these models results useful human stakeholders achieve high level causability, i.e. causal user. especially causability play crucial role also compliance regulatory requirements. We conclude promoting need novel user interfaces applications pathology, which enable contextual allow expert ask interactive ‘what‐if’‐questions. In such will not only be important causability. They keeping human‐in‐the‐loop bringing experts' experience conceptual knowledge processes.

Language: Английский

Citations

45
Extracting structured information from unstructured histopathology reports using generative pre‐trained transformer 4 (GPT‐4) DOI Creative Commons
Daniel Truhn,

Chiara ML Loeffler,

Gustav Müller‐Franzes

et al.

The Journal of Pathology, Journal Year: 2023, Volume and Issue: 262(3), P. 310 - 319

Published: Dec. 14, 2023

Abstract Deep learning applied to whole‐slide histopathology images (WSIs) has the potential enhance precision oncology and alleviate workload of experts. However, developing these models necessitates large amounts data with ground truth labels, which can be both time‐consuming expensive obtain. Pathology reports are typically unstructured or poorly structured texts, efforts implement reporting templates have been unsuccessful, as lead perceived extra workload. In this study, we hypothesised that language (LLMs), such generative pre‐trained transformer 4 (GPT‐4), extract from plain using a zero‐shot approach without requiring any re‐training. We tested hypothesis by utilising GPT‐4 information histopathological reports, focusing on two extensive sets pathology for colorectal cancer glioblastoma. found high concordance between LLM‐generated human‐generated data. Consequently, LLMs could potentially employed routinely machine in future. © 2023 The Authors. Journal published John Wiley & Sons Ltd behalf Pathological Society Great Britain Ireland.

Language: Английский

Citations

43
Regression-based Deep-Learning predicts molecular biomarkers from pathology slides DOI Creative Commons
Omar S.M. El Nahhas, Chiara Maria Lavinia Loeffler, Zunamys I. Carrero

et al.

Nature Communications, Journal Year: 2024, Volume and Issue: 15(1)

Published: Feb. 10, 2024

Deep Learning (DL) can predict biomarkers from cancer histopathology. Several clinically approved applications use this technology. Most approaches, however, categorical labels, whereas are often continuous measurements. We hypothesize that regression-based DL outperforms classification-based DL. Therefore, we develop and evaluate a self-supervised attention-based weakly supervised regression method predicts directly 11,671 images of patients across nine types. test our for multiple biologically relevant biomarkers: homologous recombination deficiency score, used pan-cancer biomarker, as well markers key biological processes in the tumor microenvironment. Using significantly enhances accuracy biomarker prediction, while also improving predictions' correspondence to regions known clinical relevance over classification. In large cohort colorectal patients, prediction scores provide higher prognostic value than scores. Our open-source approach offers promising alternative analysis computational pathology.

Language: Английский

Citations

34
Computational Pathology: A Survey Review and The Way Forward DOI Creative Commons
Mahdi S. Hosseini, Babak Ehteshami Bejnordi, Vincent Quoc‐Huy Trinh

et al.

Journal of Pathology Informatics, Journal Year: 2024, Volume and Issue: unknown, P. 100357 - 100357

Published: Jan. 1, 2024

Computational Pathology (CPath) is an interdisciplinary science that augments developments of computational approaches to analyze and model medical histopathology images. The main objective for CPath develop infrastructure workflows digital diagnostics as assistive CAD system clinical pathology, facilitating transformational changes in the diagnosis treatment cancer are mainly address by tools. With evergrowing deep learning computer vision algorithms, ease data flow from currently witnessing a paradigm shift. Despite sheer volume engineering scientific works being introduced image analysis, there still considerable gap adopting integrating these algorithms practice. This raises significant question regarding direction trends undertaken CPath. In this article we provide comprehensive review more than 800 papers challenges faced problem design all-the-way application implementation viewpoints. We have catalogued each paper into model-card examining key layout current landscape hope helps community locate relevant facilitate understanding field's future directions. nutshell, oversee cycle stages which required be cohesively linked together associated with such multidisciplinary science. overview different perspectives data-centric, model-centric, application-centric problems. finally sketch remaining directions technical integration For updated information on survey accessing original cards repository, please refer GitHub. Updated version draft can also found arXiv.

Language: Английский

Citations

33
Deep learning in cancer genomics and histopathology DOI Creative Commons
Michaela Unger, Jakob Nikolas Kather

Genome Medicine, Journal Year: 2024, Volume and Issue: 16(1)

Published: March 27, 2024

Abstract Histopathology and genomic profiling are cornerstones of precision oncology routinely obtained for patients with cancer. Traditionally, histopathology slides manually reviewed by highly trained pathologists. Genomic data, on the other hand, is evaluated engineered computational pipelines. In both applications, advent modern artificial intelligence methods, specifically machine learning (ML) deep (DL), have opened up a fundamentally new way extracting actionable insights from raw which could augment potentially replace some aspects traditional evaluation workflows. this review, we summarize current emerging applications DL in genomics, including basic diagnostic as well advanced prognostic tasks. Based growing body evidence, suggest that be groundwork kind workflow cancer research. However, also point out models can biases flaws users healthcare research need to know about, propose ways address them.

Language: Английский

Citations

24