A5079579470- AI in cancer detection
- Radiomics and Machine Learning in Medical Imaging
- Breast Cancer Treatment Studies
- Digital Imaging for Blood Diseases
- Cutaneous Melanoma Detection and Management
- Cell Image Analysis Techniques
- Medical Imaging and Analysis
- Artificial Intelligence in Healthcare and Education
- Cancer Genomics and Diagnostics
- Cervical Cancer and HPV Research
- Global Cancer Incidence and Screening
- Cancer Immunotherapy and Biomarkers
- Breast Lesions and Carcinomas
- Geological and Geophysical Studies
- Cancer Cells and Metastasis
- Colorectal Cancer Screening and Detection
- Biomedical Text Mining and Ontologies
- Distributed and Parallel Computing Systems
- Epigenetics and DNA Methylation
- Cardiomyopathy and Myosin Studies
- Nuclear Receptors and Signaling
- Brain Tumor Detection and Classification
- Melanoma and MAPK Pathways
- Domain Adaptation and Few-Shot Learning
- Optical Imaging and Spectroscopy Techniques
University Medical Center Utrecht
2014-2025
Utrecht University
2017-2024
Heidelberg University
2018-2020
University Hospital Heidelberg
2018-2020
The Netherlands Cancer Institute
2017
Radboud University Medical Center
2017
Radboud University Nijmegen
2017
Isala
2017
Canisius-Wilhelmina Ziekenhuis
2017
Erasmus MC Cancer Institute
2017
<h3>Importance</h3> Application of deep learning algorithms to whole-slide pathology images can potentially improve diagnostic accuracy and efficiency. <h3>Objective</h3> Assess the performance automated at detecting metastases in hematoxylin eosin–stained tissue sections lymph nodes women with breast cancer compare it pathologists' diagnoses a setting. <h3>Design, Setting, Participants</h3> Researcher challenge competition (CAMELYON16) develop solutions for node (November 2015-November...
Abstract Background The presence of lymph node metastases is one the most important factors in breast cancer prognosis. common way to assess regional status sentinel procedure. likely contain metastasized cells and excised, histopathologically processed, examined by a pathologist. This tedious examination process time-consuming can lead small being missed. However, recent advances whole-slide imaging machine learning have opened an avenue for analysis digitized sections with computer...
Triple-negative breast cancer (TNBC) is considered aggressive, and therefore, virtually all young patients with TNBC receive (neo)adjuvant chemotherapy. Increased stromal tumor-infiltrating lymphocytes (sTILs) have been associated a favorable prognosis in TNBC. However, whether this association holds for who are node-negative (N0), (< 40 years), chemotherapy-naïve, thus can be used chemotherapy de-escalation strategies, unknown.We selected N0 diagnosed between 1989 2000 from Dutch...
During the last years, whole slide imaging has become more affordable and widely accepted in pathology labs. Digital slides are increasingly being used for digital archiving of routinely produced clinical slides, remote consultation tumor boards, quantitative image analysis research purposes education. However, implementation a fully Pathology Department requires an depth look into suitability routine use (the quality factors that affect it) required infrastructure to support such storage...
Abstract Breast cancer tumor grade is strongly associated with patient survival. In current clinical practice, pathologists assign after visual analysis of tissue specimens. However, different studies show significant inter-observer variation in breast grading. Computer-based grading methods have been proposed but only work on specifically selected areas and/or require labor-intensive annotations to be applied new datasets. this study, we trained and evaluated a deep learning-based model...
The rapid introduction of digital pathology has greatly facilitated development artificial intelligence (AI) models in that have shown great promise assisting morphological diagnostics and quantitation therapeutic targets. We are now at a tipping point where companies started to bring algorithms the market, questions arise whether community is ready implement AI routine workflow. However, concerns also about use pathology. This article reviews pros cons introducing diagnostic
Recognition of mitotic figures in histologic tumor specimens is highly relevant to patient outcome assessment. This task challenging for algorithms and human experts alike, with deterioration algorithmic performance under shifts image representations. Considerable covariate occur when assessment performed on different types, images are acquired using digitization devices, or produced laboratories. observation motivated the inception 2022 challenge MItosis Domain Generalization (MIDOG 2022)....
Abstract The prognostic value of mitotic figures in tumor tissue is well-established for many types and automating this task high research interest. However, especially deep learning-based methods face performance deterioration the presence domain shifts, which may arise from different types, slide preparation digitization devices. We introduce MIDOG++ dataset, an extension MIDOG 2021 2022 challenge datasets. provide region interest images 503 histological specimens seven with variable...
Abstract Pathologists’ assessment of sentinel lymph nodes (SNs) for breast cancer (BC) metastases is a treatment-guiding yet labor-intensive and costly task because the performance immunohistochemistry (IHC) in morphologically negative cases. This non-randomized, single-center clinical trial (International Standard Randomized Controlled Trial Number:14323711) assessed efficacy an artificial intelligence (AI)-assisted workflow detecting BC SNs while maintaining diagnostic safety standards....
Breast cancer (BC) prognosis is largely influenced by histopathological grade, assessed according to the Nottingham modification of Bloom-Richardson (BR). Mitotic count (MC) a component grading but prone subjectivity. This study investigated whether mitoses counting in BC using digital whole slide images (WSI) compares better light microscopy (LM) when assisted artificial intelligence (AI), and which extent differences MC (AI or not) result BR grade variations.Fifty patients with paired core...
Ductal carcinoma in situ (DCIS) is a non-invasive breast cancer that can progress into invasive ductal (IDC). Studies suggest DCIS often overtreated since considerable part of lesions may never IDC. Lower grade have lower progression speed and risk, possibly allowing treatment de-escalation. However, studies show significant inter-observer variation grading. Automated image analysis provide an objective solution to address high subjectivity grading by pathologists. In this study, we...
Quality control of immunohistochemistry (IHC) slides is crucial to ascertain accurate patient management. Visual assessment the most commonly used method assess quality IHC from samples in daily pathology routines. Control tissues for are typically obtained prior cases containing normal or specific antigen-expressing disease samples, especially tumors. Since such eventually run out, and tumors may be heterogeneous, constant expression levels one sample next cannot guaranteed. With increasing...
193 Background: Guidelines recommend molecular diagnostics for homologous and mismatch repair (MMR) defects in men with metastatic castration-resistant prostate cancer. However, clinical practice, routine testing is hindered because it costly, time-consuming not available all laboratories. Moreover, many patients need to be tested identify the few these genetic aberrations. To address challenges, image-based artificial intelligence (AI) algorithms have been developed predict alterations from...
Pathologists diagnose prostate cancer (PCa) on hematoxylin and eosin (HE)-stained sections of needle biopsies (PBx). Some laboratories use costly immunohistochemistry (IHC) for all cases to optimize workflow, often exceeding reimbursement the full specimen. Despite rise in digital pathology artificial intelligence (AI) algorithms, clinical implementation studies are scarce. This prospective trial evaluated whether an AI-assisted workflow detecting PCa PBx reduces IHC while maintaining...
•Oncologists treat most eTNBC patients with chemotherapy due to a lack of implemented prognostic and predictive biomarkers.•We studied cohort systemic treatment-naïve young women node-negative 20 years median follow-up.•LVI (HR 2.35), fibrotic focus 1.61) sTILs 0.75 per 10% increment) had independent value for BCSS.•The presence LVI <30% identified an ultra-high risk recurrence or death.•De-escalation trials should consider the exclusion when is present. BackgroundIn absence biomarkers,...
Myocardial fibrosis can lead to heart failure and act as a substrate for cardiac arrhythmias. In dilated cardiomyopathy diffuse interstitial reactive be observed, whereas arrhythmogenic is characterized by fibrofatty replacement in predominantly the right ventricle. The p.Arg14del mutation phospholamban (PLN) gene has been associated with recently also cardiomyopathy. Aim of present study determine exact pattern fatty PLN positive patients, novel method high resolution systematic digital...