A5040815655- Medical Imaging Techniques and Applications
- Radiomics and Machine Learning in Medical Imaging
- Prostate Cancer Treatment and Research
- Bone health and treatments
- Prostate Cancer Diagnosis and Treatment
- Advanced X-ray and CT Imaging
- AI in cancer detection
- Lung Cancer Diagnosis and Treatment
- Advanced Radiotherapy Techniques
- Cancer Diagnosis and Treatment
- Lymphoma Diagnosis and Treatment
- Medical Imaging and Analysis
- Biomedical Text Mining and Ontologies
- Cardiac Imaging and Diagnostics
- Digital Radiography and Breast Imaging
- Management of metastatic bone disease
- Radiopharmaceutical Chemistry and Applications
- Medical Image Segmentation Techniques
- Medical Imaging and Pathology Studies
- Cardiovascular Function and Risk Factors
- Cardiac Valve Diseases and Treatments
University of Gothenburg
2008-2023
Sahlgrenska University Hospital
2009-2023
Region Västra Götaland
2019
The purpose of this study was to develop a computer-assisted diagnosis (CAD) system based on image-processing techniques and artificial neural networks for the interpretation bone scans performed determine presence or absence metastases. <b>Methods:</b> A training group 810 consecutive patients who had undergone scintigraphy due suspected metastatic disease were included in study. Whole-body images, anterior posterior views, obtained after an injection <sup>99m</sup>Tc-methylene...
The aim of this multicenter study was to investigate whether a computer-assisted diagnosis (CAD) system could improve performance and reduce interobserver variation in bone-scan interpretations the presence or absence bone metastases. <b>Methods:</b> whole-body scans (anterior posterior views) 59 patients with breast prostate cancer who had undergone scintigraphy for suspected metastatic disease were studied. selected reflect spectrum pathology found everyday clinical work. Thirty-five...
A reproducible and quantitative imaging biomarker is needed to standardize the evaluation of changes in bone scans prostate cancer patients with skeletal metastasis. We performed a series analytic validation studies evaluate performance automated scan index (BSI) as an metastatic cancer. <b>Methods:</b> Three separate were accuracy, precision, reproducibility BSI. Simulation study: simulations predefined tumor burdens created assess accuracy precision. Fifty simulated burden ranging from low...
To validate a deep-learning (DL) algorithm for automated quantification of prostate cancer on positron emission tomography/computed tomography (PET/CT) and explore the potential PET/CT measurements as prognostic biomarkers.Training DL-algorithm regarding volume was performed manually segmented CT images in 100 patients. Validation carried out 45 patients with biopsy-proven hormone-naïve cancer. The were compared manual made independently by two observers. tumour burden based SUV abnormal...
Objective To develop a completely automated method, based on image processing techniques and artificial neural networks, for the interpretation of bone scans regarding presence or absence metastases. Methods A total 200 patients, all whom had diagnosis breast prostate cancer undergone scintigraphy, were studied retrospectively. Whole-body images, anterior posterior, obtained after injection 99mTc-methylene diphosphonate. The study material was randomly divided into training group test group,...
Sodium fluoride (NaF) positron emission tomography combined with computer (PET/CT) has shown to be more sensitive than the whole-body bone scan in detection of skeletal uptake due metastases prostate cancer. We aimed calculate a 3D index for NaF PET/CT and investigate its correlation (BSI) overall survival (OS) group patients cancer.NaF scans were studied 48 Automated segmentation thoracic lumbar spines, sacrum, pelvis, ribs, scapulae, clavicles, sternum made CT images. Hotspots PET images...
Summary Background 18F‐ FDG ‐ PET / CT has become a standard for assessing treatment response in patients with lymphoma. A subjective interpretation of the scan based on Deauville 5‐point scale been widely adopted. However, inter‐observer variability due to subjectivity is limitation. Our main goal develop an objective and automated method evaluating response. The first step validate artificial intelligence ( AI )‐based method, quantification reference levels liver mediastinal blood pool...
The aim of this study was to examine the relation between pain and bone metastases in a group patients with prostate or breast cancer that had been referred for scintigraphy. Whole-body scans, anterior posterior views obtained dual detector gamma camera were studied from 101 consecutive who undergone scintigraphy (600 MBq Tc-99m MDP) because suspected metastatic disease. At time examination, all asked whether they felt any recently trauma. This information correlated classifications...
Abstract To develop an artificial intelligence (AI)-based method for the detection of focal skeleton/bone marrow uptake (BMU) in patients with Hodgkin’s lymphoma (HL) undergoing staging FDG-PET/CT. The results AI a separate test group were compared to interpretations independent physicians. skeleton and bone segmented using convolutional neural network. training was based on 153 un-treated patients. Bone significantly higher than mean BMU marked as abnormal, index, total squared abnormal...
A bone scan is a common method for monitoring metastases in patients with advanced prostate cancer. The Bone Scan Index (BSI) measures the tumor burden on skeleton, expressed as percentage of total skeletal mass. Previous studies have shown that BSI associated survival cancer patients. objective this study was to investigate what extent regional measurements, obtained by an automated method, can improve analysis analyzing images computed values twelve regions, population consisting 1013...
Abstract Aim To compare total metabolic tumour volume (tMTV), calculated using two artificial intelligence (AI)‐based tools, with manual segmentation by specialists as the reference. Methods Forty‐eight consecutive Hodgkin lymphoma (HL) patients staged [18F] fluorodeoxyglucose positron emission tomography/computed tomography were included. The median age was 35 years (range: 7–75), 46% female. tMTV automatically measured AI‐based tools assisted reporting system (PARS) (from Siemens) and...
A quantitative analysis of metastatic bone involvement can be an important prognostic indicator survival or a tool in monitoring treatment response patients with cancer. The purpose this study was to develop completely automated decision support system for whole-body scans using image and artificial neural networks. population consisted 795 scans. first detects classifies individual hotspots as being not. second prediction model then the scan regarding disease on patient level. test set...
Classification of focal skeleton/bone marrow uptake (BMU) can be challenging. The aim is to investigate whether an artificial intelligence-based method (AI), which highlights suspicious BMU, increases interobserver agreement among a group physicians from different hospitals classifying Hodgkin's lymphoma (HL) patients staged with [18F]FDG PET/CT.Forty-eight PET/CT at Sahlgenska University Hospital between 2017 and 2018 were reviewed twice, 6 months apart, regarding BMU. During the second...
Summary Bone Scan Index ( BSI ) is a validated imaging biomarker to objectively assess tumour burden in bone patients with prostate cancer, and can be used monitor treatment response. It not known if significantly altered when images are acquired at time difference of 1 h. The aim this study was investigate automatic calculation affected hour apart, after approximately 3 4 We prospectively studied cancer who were referred for scintigraphy according clinical routine. performed whole‐body scan...
The Bone Scan Index (BSI) is used to quantitatively assess the total tumour burden in bone scans of patients with metastatic prostate cancer. clinical utility BSI has recently been validated as a prognostic imaging biomarker. However, on-treatment change dependent on reproducibility scans. objective this prospective study evaluate intra-patient two scan procedures performed at one-week interval. We prospectively studied cancer who were referred for scintigraphy our centres according routine....
Background Echocardiography combining Doppler and two-dimensional data is recommended for quantitative assessments of valvular regurgitation. We applied a new method to calculate the mitral annulus (MA) area in combination with multiple sample sites. Individuals without regurgitation whom left ventricular stroke volumes (SV) should be identical were investigated order evaluate feasibility Methods results Twenty subjects included. Flow velocity was registered pulsed different positions...
Abstract Purpose: To develop an artificial intelligence (AI)-based method for the detection of focal skeleton/bone marrow uptake (BMU) in patients with Hodgkin´s lymphoma (HL) undergoing staging FDG-PET/CT. The results AI a separate test group were compared to interpretations independent physicians. Methods: skeleton and bone segmented using convolutional neural network. training was based on 153 un-treated patients. Bone significantly higher than mean BMU marked as abnormal, index, total...