A5020018643- Lung Cancer Diagnosis and Treatment
- Radiomics and Machine Learning in Medical Imaging
- COVID-19 diagnosis using AI
- Lung Cancer Treatments and Mutations
- Chronic Obstructive Pulmonary Disease (COPD) Research
- Medical Imaging Techniques and Applications
- AI in cancer detection
- Advanced X-ray and CT Imaging
- Esophageal Cancer Research and Treatment
- Colorectal Cancer Screening and Detection
- Interstitial Lung Diseases and Idiopathic Pulmonary Fibrosis
- Artificial Intelligence in Healthcare and Education
- Advanced Neural Network Applications
- Medical Imaging and Pathology Studies
- Pleural and Pulmonary Diseases
- Atomic and Subatomic Physics Research
- Occupational and environmental lung diseases
- Cell Image Analysis Techniques
- Planetary Science and Exploration
- Obstructive Sleep Apnea Research
- Radiation Dose and Imaging
- Multiple Sclerosis Research Studies
- Space exploration and regulation
- Radiology practices and education
- Adrenal and Paraganglionic Tumors
Radboud University Nijmegen
2016-2025
Radboud University Medical Center
2016-2025
Analysis Group (United States)
2015-2024
University Medical Center
2015-2024
University Medical Center Groningen
2024
University of Groningen
2024
University Medical Center Utrecht
2024
Maastricht University
2024
Utrecht University
2024
Gentofte Hospital
2021-2023
We propose a novel Computer-Aided Detection (CAD) system for pulmonary nodules using multi-view convolutional networks (ConvNets), which discriminative features are automatically learnt from the training data. The network is fed with nodule candidates obtained by combining three candidate detectors specifically designed solid, subsolid, and large nodules. For each candidate, set of 2-D patches differently oriented planes extracted. proposed architecture comprises multiple streams ConvNets,...
In this work, we report the set-up and results of Liver Tumor Segmentation Benchmark (LiTS), which was organized in conjunction with IEEE International Symposium on Biomedical Imaging (ISBI) 2017 Conferences Medical Image Computing Computer-Assisted Intervention (MICCAI) 2018. The image dataset is diverse contains primary secondary tumors varied sizes appearances various lesion-to-background levels (hyper-/hypo-dense), created collaboration seven hospitals research institutions. Seventy-five...
The introduction of lung cancer screening programs will produce an unprecedented amount chest CT scans in the near future, which radiologists have to read order decide on a patient follow-up strategy. According current guidelines, workup screen-detected nodules strongly relies nodule size and type. In this paper, we present deep learning system based multi-stream multi-scale convolutional networks, automatically classifies all types relevant for workup. processes raw data containing without...
Convolutional neural networks (CNNs) have emerged as the most powerful technique for a range of different tasks in computer vision. Recent work suggested that CNN features are generic and can be used classification outside exact domain which were trained. In this we use from one such network, OverFeat, trained object detection natural images, nodule computed tomography scans. We 865 scans publicly available LIDC data set, read by four thoracic radiologists. Nodule candidates generated...
In this work, we report the set-up and results of Liver Tumor Segmentation Benchmark (LiTS), which was organized in conjunction with IEEE International Symposium on Biomedical Imaging (ISBI) 2017 Conferences Medical Image Computing Computer-Assisted Intervention (MICCAI) 2018. The image dataset is diverse contains primary secondary tumors varied sizes appearances various lesion-to-background levels (hyper-/hypo-dense), created collaboration seven hospitals research institutions. Seventy-five...
Background Accurate estimation of the malignancy risk pulmonary nodules at chest CT is crucial for optimizing management in lung cancer screening. Purpose To develop and validate a deep learning (DL) algorithm detected screening CT. Materials Methods In this retrospective study, DL was developed with 16 077 (1249 malignant) collected -between 2002 2004 from National Lung Screening Trial. External validation performed following three -cohorts -collected between 2010 Danish Cancer Trial: full...
To examine the factors that affect inter- and intraobserver agreement for pulmonary nodule type classification on low-radiation-dose computed tomographic (CT) images, their potential effect patient management.Nodules (n = 160) were randomly selected from Dutch-Belgian Lung Cancer Screening Trial cohort, with equal numbers of types similar sizes. Nodules scored by eight radiologists using morphologic categories proposed Fleischner Society guidelines management nodules as solid, part solid a...
Background The coronavirus disease 2019 (COVID-19) pandemic has spread across the globe with alarming speed, morbidity, and mortality. Immediate triage of patients chest infections suspected to be caused by COVID-19 using CT may assistance when results from definitive viral testing are delayed. Purpose To develop validate an artificial intelligence (AI) system score likelihood extent pulmonary on scans Reporting Data System (CO-RADS) severity scoring systems. Materials Methods CO-RADS AI...
Purpose: Current computer‐aided detection (CAD) systems for pulmonary nodules in computed tomography (CT) scans have a good performance relatively small nodules, but often fail to detect the much rarer larger which are more likely be cancerous. We present novel CAD system specifically designed solid than 10 mm. Methods: The proposed pipeline is initiated by three‐dimensional lung segmentation algorithm optimized include large attached pleural wall via morphological processing. An additional...
Pulmonary subsolid nodules (SSNs) have a high likelihood of malignancy, but are often indolent. A conservative treatment approach may therefore be suitable. The aim the current study was to evaluate whether close follow-up SSNs with computed tomography safe approach. population consisted participants Dutch-Belgian lung cancer screening trial (Nederlands Leuvens Longkanker Screenings Onderzoek; NELSON). All detected during were included in this analysis. Retrospectively, all persistent and...
To benchmark the performance of state-of-the-art computer-aided detection (CAD) pulmonary nodules using largest publicly available annotated CT database (LIDC/IDRI), and to show that CAD finds lesions not identified by LIDC’s four-fold double reading process. The LIDC/IDRI contains 888 thoracic scans with a section thickness 2.5 mm or lower. We report two commercial one academic system. influence presence contrast, thickness, reconstruction kernel on was assessed. Four radiologists...
Pulmonary lobe segmentation in computed tomography scans is essential for regional assessment of pulmonary diseases. Recent works based on convolution neural networks have achieved good performance this task. However, they are still limited capturing structured relationships due to the nature convolution. The shape lobes affect each other and their borders relate appearance structures, such as vessels, airways, pleural wall. We argue that structural play a critical role accurate delineation...
Abstract We propose iW-Net, a deep learning model that allows for both automatic and interactive segmentation of lung nodules in computed tomography images. iW-Net is composed two blocks: the first one provides an second to correct it by analyzing 2 points introduced user nodule’s boundary. For this purpose, physics inspired weight map takes input into account proposed, which used as feature system’s loss function. Our approach extensively evaluated on public LIDC-IDRI dataset, where we...
To study trends in the incidence of reported pulmonary nodules and stage I lung cancer chest CT.We analyzed detected CT scans period between 2008 2019. Imaging metadata radiology reports from all studies were collected two large Dutch hospitals. A natural language processing algorithm was developed to identify with any nodule.Between 2019, a total 74,803 patients underwent 166,688 examinations at both hospitals combined. During this period, annual number increased 9955 6845 20,476 13,286 The...
The malignancy of lung nodules is most often detected by analyzing changes the nodule diameter in follow-up scans. A recent study showed that comparing volume or mass a over time much more significant than diameter. Since survival rate higher when disease still an early stage it important to detect growth as soon possible. However manual segmentation time-consuming. Whereas there are several well evaluated methods for solid nodules, less work done on subsolid which actually show nodules. In...
Abstract Background Outside a screening program, early-stage lung cancer is generally diagnosed after the detection of incidental nodules in clinically ordered chest CT scans. Despite advances artificial intelligence (AI) systems for detection, clinical validation these lacking non-screening setting. Method We developed deep learning-based AI system and assessed its performance actionable benign (requiring follow-up), small cancers, pulmonary metastases scans acquired two Dutch hospitals...
Purpose To evaluate the added value of Lung CT Screening Reporting and Data System (Lung-RADS) assessment category 4X over categories 3, 4A, 4B for differentiating between benign malignant subsolid nodules (SSNs). Materials Methods SSNs on all baseline computed tomographic (CT) scans from National Cancer Trial that would have been classified as Lung-RADS 3 or higher were identified, resulting in 374 analysis. An experienced screening radiologist volumetrically segmented solid cores located...
Lung-RADS represents a categorical system published by the American College of Radiology to standardise management in lung cancer screening. The purpose study was quantify how well readers agree assigning categories screening CTs; secondary goals were assess causes disagreement and evaluate its impact on patient management.For observer study, 80 baseline follow-up scans randomly selected from NLST trial covering all an equal distribution. Agreement seven observers analysed using Cohen's...