Refine
Year of publication
Document Type
- Article (71) (remove)
Has Fulltext
- yes (71)
Is part of the Bibliography
- no (71)
Keywords
- Magnetic resonance imaging (6)
- CT (4)
- Hepatocellular carcinoma (4)
- MRI (4)
- Artificial intelligence (3)
- Cancer (3)
- microwave ablation (3)
- Algorithms (2)
- Bone density (2)
- DSM (2)
- Dynamic MRI (2)
- Machine learning (2)
- Microwave ablation (2)
- Multidetector computed tomography (2)
- Neoplasms (2)
- Osteoporosis (2)
- Prostate cancer (2)
- Radiomics (2)
- Spine (2)
- Tomography (x-ray computed) (2)
- Transarterial chemoembolization (2)
- breast cancer (2)
- computed tomography (2)
- hepatocellular carcinoma (2)
- liver (2)
- 16 segment AHA model (1)
- Ablation Techniques (1)
- Age determination by skeleton (1)
- Anemia (1)
- Angiography (1)
- Aromatase Inhibitors (1)
- Automated Tube Potential Selection (1)
- Awareness campaign (1)
- Berci needle (1)
- Biopsy (1)
- Blood (1)
- Bone diseases, Metabolic (1)
- Bone marrow (1)
- Breast tumors (1)
- COVID-19 (1)
- CT dual-energy computed tomography (1)
- CT pulmonary angiography (1)
- CT radiation exposure (1)
- CT-guidance (1)
- CT-guided interventions (1)
- Calcium (1)
- Cancer Staging (1)
- Cancer check up (1)
- Cancer staging (1)
- Carcinoma, Ductal, Breast (1)
- Cardiovascular diseases (1)
- Cardiovascular magnetic resonance (1)
- Cell binding (1)
- Cell staining (1)
- Chemoembolization (1)
- Children (1)
- Chondral Lesion (1)
- Cochlear implantation (1)
- Cohort studies (1)
- Colchicum (1)
- Computed tomography imaging (1)
- Computed tomography pulmonary angiography (CTPA) (1)
- Computed tomography, X-ray (1)
- Cone-beam computed tomography (1)
- Congenital (1)
- Contrast agent (1)
- Diagnostic differentiation (1)
- Diagnostic imaging (1)
- Diagnostic markers (1)
- Diffusion magnetic resonance imaging (1)
- Dual-Source CT (1)
- Dual-energy computed tomography (1)
- Dumon stents (1)
- Edema (1)
- Electric stimulation (1)
- Estrogen Receptor Modulators (1)
- Exudates and transudates (1)
- Facial nerve (1)
- Feasibility studies (1)
- Fetal heart (1)
- First experience with patients (1)
- Flow cytometry (1)
- Gadobutrol (1)
- Gadopentate dimeglumine (1)
- Goserelin (1)
- Groin pain (1)
- HCC (1)
- Heart defects (1)
- Herniated disk (1)
- Image processing (1)
- Image processing (computer-assisted) (1)
- In-TIPS thrombosis (1)
- Inguinal hernia (1)
- Inguinal pain (1)
- Intensive care units (1)
- Interventional oncological treatment (1)
- Intervertebral disc displacement (1)
- Kupffer cells (1)
- LNS (1)
- Laser interstitial thermal therapy (1)
- Laser navigation system (1)
- Lateral recess stenosis (1)
- Lipidol (1)
- Lipiodol (1)
- Liver (1)
- Local control (1)
- Low back pain (1)
- Lumbar spinal canal stenosis (1)
- Lumbar spine (1)
- Lung neoplasms (1)
- Lymphangioleiomyomatosis (1)
- MEDIC (1)
- Macrophages (1)
- Mastoiditis (1)
- Medical Oncology (1)
- Medical research (1)
- Metastasis (1)
- Mitomycin C (1)
- Mouse models (1)
- Multidetector Computed Tomography (1)
- Multiparametric MRI (1)
- Myocardial perfusion (1)
- Myocardial segmentation (1)
- Myocarditis (1)
- Necrotic area (1)
- Noninferiority (1)
- Nonpenetrating (1)
- Oncology (1)
- Osteoporotic fractures (1)
- Oswestry Disability Score (1)
- PSA screening (1)
- PSA-Screening (1)
- Patellofemoral Joint (1)
- Percutaneous (1)
- Phantom study (1)
- Phantoms (imaging) (1)
- Physics (1)
- Portal (1)
- Positron emission tomography (1)
- Preclinical research (1)
- Prediction (1)
- Predictive markers (1)
- Preventive medicine (1)
- Prognostic markers (1)
- Prostata-specific antigen (1)
- Prostataspezifisches Antigen (1)
- Prävention (1)
- Quantitative Imaging (1)
- Quantitative features (1)
- Radiology (1)
- Renal lesions (1)
- Response (1)
- Retrospective studies (1)
- Retrospective study (1)
- STIR (1)
- Shunt (1)
- Spinal fractures (1)
- Spinal injuries (1)
- Static MRI (1)
- Statistical analysis (1)
- Sub-segmentation (1)
- Survival (1)
- Survival data (1)
- TACE (1)
- TIPS (1)
- Temporomandibular joint (1)
- Temporomandibular joint dysfunction (1)
- Thrombosis (1)
- Tomography (1)
- Transjugular Intrahepatic Portosystemic Shunt (1)
- Translational research (1)
- Treatment outcome (1)
- Truncus arteriosus (1)
- Tumor volume (1)
- UWB diagnostics (1)
- Vaccination (1)
- Vasculitis (1)
- Vertebral body (1)
- Virtual noncalcium reconstructions (1)
- Vorsorgeuntersuchung (1)
- Wounds (1)
- X-ray computed (1)
- abdominal imaging (1)
- airway (1)
- amino acids (1)
- angiography (1)
- aortic stenosis (1)
- beads (1)
- biopsy (1)
- cardiac magnetic resonance (1)
- cardiac remodeling (1)
- chronic liver disease (CLD) (1)
- cisplatin (1)
- colorectal cancer (1)
- colorectal cancer (CRC) (1)
- colorectal cancer liver metastases (CRLM) (1)
- computer tomography (1)
- computer-assisted (1)
- cone-beam computed tomography (CBCT) (1)
- cone-beam computer tomography (1)
- conventional/traditional transarterial chemoembolization (cTACE) (1)
- critical care unit (1)
- critical ill patients (1)
- denervation (1)
- diagnostic imaging (1)
- drug-eluting beads TACE (DEB-TACE) (1)
- dual-energy (1)
- electromagnetic navigation bronchoscopy (EMN, ENB) (1)
- heart failure (1)
- hepatocellular carcinoma (HCC) (1)
- high-pitch (1)
- imaging (1)
- in vivo dosimetry (1)
- interventional radiology (1)
- intraarterial therapy (1)
- intratumoral (1)
- irinotecan-loaded drug-eluting beads TACE (DEBIRI-TACE) (1)
- laser-induced thermotherapy (1)
- lipiodol (1)
- liver metastases (1)
- livermetastases of colorectal cancer (1)
- locoregional chemotherapy (1)
- low-dose imaging (1)
- lung cancer (1)
- mantle cell lymphoma (1)
- microwave breast imaging (1)
- multidetector computed tomography (1)
- myocardial fibrosis (1)
- non‑Hodgkin's lymphoma (1)
- oval split ring resonator (1)
- overall survival (OS) (1)
- papilloma (1)
- patient study (1)
- percutaneous thermal ablation (1)
- peripheral blood stem cell transplant (1)
- portal vein (1)
- progression-free survival (PFS) (1)
- pulmonary hypertension (1)
- radiation (1)
- radiation dosage (1)
- radiation dosimetry (1)
- radiation protection (1)
- radiomics (1)
- rats (1)
- retuximab (1)
- scar (1)
- sepsis (1)
- sex‑determining region Y-box 11 (1)
- skin involvement (1)
- solitary pulmonary nodule (1)
- spine (1)
- stent (1)
- theranostics (1)
- thrombosis (1)
- tracheobronchomalacia (1)
- transarterial chemoembolization (TACE) (1)
- transbronchial biopsy (TBB) (1)
- tumor response (1)
- vertebroplasty (1)
- Öffentlichkeit (1)
Institute
- Medizin (71)
- Informatik und Mathematik (3)
- Informatik (1)
- Physik (1)
- Sonderforschungsbereiche / Forschungskollegs (1)
Background: Prostate cancer is a major health concern in aging men. Paralleling an aging society, prostate cancer prevalence increases emphasizing the need for efcient diagnostic algorithms.
Methods: Retrospectively, 106 prostate tissue samples from 48 patients (mean age,
66 ± 6.6 years) were included in the study. Patients sufered from prostate cancer (n = 38) or benign prostatic hyperplasia (n = 10) and were treated with radical prostatectomy or Holmium laser enucleation of the prostate, respectively. We constructed tissue microarrays (TMAs) comprising representative malignant (n = 38) and benign (n = 68) tissue cores. TMAs were processed to histological slides, stained, digitized and assessed for the applicability of machine learning strategies and open–source tools in diagnosis of prostate cancer. We applied the software QuPath to extract features for shape, stain intensity, and texture of TMA cores for three stainings, H&E, ERG, and PIN-4. Three machine learning algorithms, neural network (NN), support vector machines (SVM), and random forest (RF), were trained and cross-validated with 100 Monte Carlo random splits into 70% training set and 30% test set. We determined AUC values for single color channels, with and without optimization of hyperparameters by exhaustive grid search. We applied recursive feature elimination to feature sets of multiple color transforms.
Results: Mean AUC was above 0.80. PIN-4 stainings yielded higher AUC than H&E and
ERG. For PIN-4 with the color transform saturation, NN, RF, and SVM revealed AUC of 0.93 ± 0.04, 0.91 ± 0.06, and 0.92 ± 0.05, respectively. Optimization of hyperparameters improved the AUC only slightly by 0.01. For H&E, feature selection resulted in no increase of AUC but to an increase of 0.02–0.06 for ERG and PIN-4.
Conclusions: Automated pipelines may be able to discriminate with high accuracy between malignant and benign tissue. We found PIN-4 staining best suited for classifcation. Further bioinformatic analysis of larger data sets would be crucial to evaluate the reliability of automated classifcation methods for clinical practice and to evaluate potential discrimination of aggressiveness of cancer to pave the way to automatic precision medicine.