A5038260607- Radiomics and Machine Learning in Medical Imaging
- Lung Cancer Diagnosis and Treatment
- Dental Radiography and Imaging
- Medical Imaging and Analysis
- Head and Neck Cancer Studies
- Dental Implant Techniques and Outcomes
- Retinal Imaging and Analysis
- Advanced X-ray and CT Imaging
- Autoimmune Bullous Skin Diseases
- Medical Imaging Techniques and Applications
- Glaucoma and retinal disorders
- Remote Sensing and Land Use
- Systemic Lupus Erythematosus Research
- Smart Agriculture and AI
- Spectroscopy and Chemometric Analyses
- Optical Coherence Tomography Applications
- Cell Adhesion Molecules Research
- Currency Recognition and Detection
- Remote Sensing and LiDAR Applications
- Plant and Fungal Interactions Research
- Skin Diseases and Diabetes
- Plant Parasitism and Resistance
- Machine Learning in Healthcare
- Infectious Diseases and Mycology
- Advanced Neural Network Applications
University Medical Center Groningen
2018-2025
University of Groningen
2015-2025
Segmentation of mandibular bone in CT scans is crucial for 3D virtual surgical planning craniofacial tumor resection and free flap reconstruction the defect, order to obtain a detailed surface representation bones. A major drawback most existing segmentation methods that they require large amount expert knowledge manual or partially automatic segmentation. In fact, due lack experienced doctors experts, high quality hard achieve practice. Furthermore, mandibles influenced seriously by metal...
The aim of this study was to develop and evaluate a prediction model for 2-year overall survival (OS) in stage I-IIIA non-small cell lung cancer (NSCLC) patients who received definitive radiotherapy by considering clinical variables image features from pre-treatment CT-scans.NSCLC stereotactic were prospectively collected at the UMCG split into training hold out test set including 189 81 patients, respectively. External validation performed on 228 NSCLC treated with radiation or concurrent...
Lung cancer, chronic obstructive pulmonary disease (COPD), and coronary artery (CAD) are expected to cause most deaths by 2050. State-of-the-art computed tomography (CT) allows early detection of lung cancer simultaneous evaluation imaging biomarkers for the stages COPD, based on density bronchial wall thickness, CAD, calcium score (CACS), at low radiation dose. To determine cut-off values positive tests elevated risk presence is one major tasks before considering implementation CT screening...
Accurate pulmonary nodule detection is a crucial step in lung cancer screening.Computer-aided (CAD) systems are not routinely used by radiologists for clinical practice despite their potential benefits.Maximum intensity projection (MIP) images improve the of nodules radiological evaluation with computed tomography (CT) scans.Inspired methodology radiologists, we aim to explore feasibility applying MIP effectiveness automatic using convolutional neural networks (CNNs).We propose CNN-based...
Recently, deep learning (DL) algorithms showed to be promising in predicting outcomes such as distant metastasis-free survival (DMFS) and overall (OS) using pre-treatment imaging head neck cancer. Gross Tumor Volume of the primary tumor (GTVp) segmentation is used an additional channel input DL improve model performance. However, binary mask GTVp directs focus network defined region only uniformly. models trained for have also been generate predicted probability maps (TPM) where each pixel...
Glaucoma is a chronic progressive optic neuropathy that causes visual impairment or blindness if left untreated. It crucial to diagnose it at an early stage in order enable treatment. Fundus photography viable option for population-based screening. A fundus photograph enables the observation of excavation disk—the hallmark glaucoma. The quantified as vertical cup-to-disk ratio (VCDR). manual assessment retinal images is, however, time-consuming and costly. Thus, automated system necessary...
Purpose: Classic encoder–decoder-based convolutional neural network (EDCNN) approaches cannot accurately segment detailed anatomical structures of the mandible in computed tomography (CT), for instance, condyles and coronoids mandible, which are often affected by noise metal artifacts. The main reason is that EDCNN ignore connectivity organs. In this paper, we propose a novel CNN-based 3D segmentation approach has ability to structures. Methods: Different from classic EDCNNs need slice or...
Deep learning (DL) models can extract prognostic image features from pre-treatment PET/CT scans. The study objective was to explore the potential benefits of incorporating pathologic lymph node (PL) spatial information in addition that primary tumor (PT) DL-based for predicting local control (LC), regional (RC), distant-metastasis-free survival (DMFS), and overall (OS) oropharyngeal cancer (OPC) patients. included 409 OPC patients treated with definitive (chemo)radiotherapy between 2010...
In the HECKTOR 2022 challenge set [1], several state-of-the-art (SOTA, achieving best performance) deep learning models were introduced for predicting recurrence-free period (RFP) in head and neck cancer patients using PET CT images. This study investigates whether a conventional DenseNet architecture, with optimized numbers of layers image-fusion strategies, could achieve comparable performance as SOTA models. The dataset comprises 489 oropharyngeal (OPC) from seven distinct centers. It was...
Abstract Background Personalized treatment is increasingly required for oropharyngeal squamous cell carcinoma (OPSCC) patients due to emerging new cancer subtypes and options. Outcome prediction model can help identify low or high‐risk who may be suitable receive de‐escalation intensified approaches. Purpose To develop a deep learning (DL)‐based predicting multiple associated efficacy endpoints in OPSCC based on computed tomography (CT). Methods Two patient cohorts were used this study:...
Vibratory harvesting is the primary method used to harvest red jujubes. This study aimed improve efficiency of vibratory for jujubes and identify optimal parameters at different jujube tree diameters. A model forced vibration dynamics trees was established, a three-dimensional constructed diameter variations. kinematic simulation analysis then conducted determine inherent frequency modal patterns trees. Harmonic response performed displacement acceleration responses with diameters factors....
Accurate mandible segmentation is significant in the field of maxillofacial surgery to guide clinical diagnosis and treatment develop appropriate surgical plans. In particular, cone-beam computed tomography (CBCT) images with metal parts, such as those used oral (OMFS), often have susceptibilities when artifacts are present weak blurred boundaries caused by a high-attenuation material low radiation dose image acquisition. To overcome this problem, paper proposes novel deep learning-based...
Due to complex environmental factors such as illumination, shading between leaves and fruits, so on, it is a challenging task quickly identify red jujubes count in orchards. A counting method of jujube based on improved YOLOv5s was proposed, which realized the fast accurate detection reduced model scale estimation error. ShuffleNet V2 used backbone improve ability light weight. In addition, Stem, novel data loading module, proposed prevent loss information due change feature map size. PANet...
Accurate segmentation of the mandible from cone-beam computed tomography (CBCT) scans is an important step for building a personalized 3D digital model maxillofacial surgery and orthodontic treatment planning because low radiation dose short scanning duration. CBCT images, however, exhibit lower contrast higher levels noise artifacts due to extremely in comparison with conventional (CT), which makes automatic data challenging. In this work, we propose novel coarse-to-fine framework based on...
Our research focuses on winter jujube trees and is conducted in a greenhouse environment structured orchard to effectively control various growth conditions. The development of robotic system for harvesting crucial achieving mechanized harvesting. Harvesting jujubes efficiently requires accurate detection location. To address this issue, we proposed localization method based the MobileVit-Large selective kernel-GSConv-YOLO (MLG-YOLO) model. First, dataset constructed comprise scenarios...