A5084461663- AI in cancer detection
- Radiomics and Machine Learning in Medical Imaging
- Colorectal Cancer Screening and Detection
- Generative Adversarial Networks and Image Synthesis
- Breast Cancer Treatment Studies
- Medical Image Segmentation Techniques
- Artificial Intelligence in Healthcare and Education
- Cancer Immunotherapy and Biomarkers
- Breast Lesions and Carcinomas
- COVID-19 diagnosis using AI
- Global Cancer Incidence and Screening
- Prostate Cancer Diagnosis and Treatment
- Aluminum toxicity and tolerance in plants and animals
- Liver Disease Diagnosis and Treatment
- Renal and related cancers
- Spectroscopy Techniques in Biomedical and Chemical Research
- MRI in cancer diagnosis
- Renal Diseases and Glomerulopathies
- Systemic Sclerosis and Related Diseases
- Cardiovascular Health and Risk Factors
- Immunotherapy and Immune Responses
- Health, Environment, Cognitive Aging
- Cancer Cells and Metastasis
- Cancer Risks and Factors
- Retinal Imaging and Analysis
Radboud University Nijmegen
2017-2024
Radboud University Medical Center
2018-2024
University Medical Center
2022
Significance Statement Histopathologic assessment of kidney tissue currently relies on manual scoring or traditional image-processing techniques to quantify and classify features, time-consuming approaches that have limited reproducibility. The authors present an alternative approach, featuring a convolutional neural network for multiclass segmentation in sections stained by periodic acid–Schiff. Their findings demonstrate applicability networks from multiple centers, biopsies nephrectomy...
Variation between stains in histopathology is commonplace across different medical centers. This can have a significant effect on the reliability of machine learning algorithms. In this paper, we propose to reduce performance variability by using -consistent generative adversarial (CycleGAN) networks remove staining variation. We improve upon regular CycleGAN incorporating residual learning. comprehensively evaluate our stain transformation method and compare its usefulness addition...
Algorithms can improve the objectivity and efficiency of histopathologic slide analysis. In this paper, we investigated impact scanning systems (scanners) cycle-GAN-based normalization on algorithm performance, by comparing different deep learning models to automatically detect prostate cancer in whole-slide images. Specifically, compare U-Net, DenseNet EfficientNet. Models were developed a multi-center cohort with 582 WSIs subsequently evaluated two independent test sets including 85 50...
Diagnoses in kidney disease often depend on quantification and presence of specific structures the tissue. The progress field whole-slide imaging deep learning has opened up new possibilities for automatic analysis histopathological slides. An initial step renal tissue assessment is differentiation segmentation relevant specimens. We propose a method using convolutional neural networks. Nine found (pathological) are included task: glomeruli, proximal tubuli, distal arterioles, capillaries,...
The tumour microenvironment has been shown to be a valuable source of prognostic information for different cancer types. This holds in particular triple negative breast (TNBC), subtype which currently no biomarkers are established. Although methods assess infiltrating lymphocytes (TILs) have published, it remains unclear method (marker, region) yields the most optimal information. In addition, date, objective TILs assessment available. For this proof concept study, subset our previously...
Computational algorithms for the interpretation of laboratory test results can support physicians and specialists in medicine. The aim this study was to develop, implement evaluate a machine learning algorithm that automatically assesses risk low body iron storage, reflected by ferritin plasma levels, anemic primary care patients using minimal set basic tests, namely complete blood count C-reactive protein (CRP).Laboratory measurements were used develop validate algorithm. performance...
(1) Background: Histopathological assessment of Wilms tumors (WT) is crucial for risk group classification to guide postoperative stratification in chemotherapy pre-treated WT cases. However, due the heterogeneous nature tumor, significant interobserver variation between pathologists diagnosis has been observed, potentially leading misclassification and suboptimal treatment. We investigated whether artificial intelligence (AI) can contribute accurate reproducible histopathological through...
Convolutional neural networks (CNNs) offer the potential to generate comprehensive quantitative analysis of histologic features. Diagnostic reporting benign breast disease (BBD) biopsies is usually limited subjective assessment most severe lesion in a sample, while ignoring vast majority tissue features, including involution background terminal duct lobular units (TDLUs), structures from which cancers arise. Studies indicate that increased levels age-related TDLU BBD predict lower cancer...
Hypomagnesemia (blood Mg2+ concentration <0.7 mM) is a common electrolyte disorder in patients with type 2 diabetes (T2D), but the etiology remains largely unknown. In T2D, reduced blood levels are associated an increased decline renal function, independent of glycemic control and hypertension. To study underlying mechanism this phenomenon, we investigated effects hypomagnesemia high-fat-diet (HFD)-fed mice. mice fed low dietary Mg2+, HFD resulted severe within 4 wk. Renal or intestinal...
Abstract Background Breast terminal duct lobular units (TDLUs), the source of most breast cancer (BC) precursors, are shaped by age-related involution, a gradual process, and postpartum involution (PPI), dramatic inflammatory process that restores baseline microanatomy after weaning. Dysregulated PPI is implicated in pathogenesis BCs. We propose assessment TDLUs period may have value risk estimation, but characteristics these tissues relation to epidemiological factors incompletely...
Abstract Introduction: We used micro-computed tomography (microCT), a high-resolution imaging option, to detect and characterize microcalcifications (MCs) in three dimensions within pathology blocks of benign malignant breast tissues. Methods: A set 44 formalin-fixed, paraffin-embedded tissue were assessed from n=22 women at two time points: biopsy subsequent DCIS or with invasive disease cancer. Blocks scanned using the Bruker Skyscan 1276 microCT resolution 10 µm. SkyScan analysis CTAn...
Abstract Background: Biopsy diagnosis of benign breast disease (BBD) based on the most severe lesion in a sample predicts future cancer risk and has implications for screening management. Lobules are functional unit structures from which BBD arises. We developed preliminarily validated an automated computational pathology algorithm to discriminate normal lobules as step toward comprehensive characterization biopsies. Methods: 152 biopsies (27 training, 125 validation) Mayo Clinic were...