Joakim Jonsson

Bio: Joakim Jonsson is an academic researcher from Umeå University. The author has contributed to research in topics: Magnetic resonance imaging & Computer science. The author has an hindex of 15, co-authored 34 publications receiving 899 citations. Previous affiliations of Joakim Jonsson include Lund University.

Treatment planning using MRI data: an analysis of the dose calculation accuracy for different treatment regions.

Abstract: Because of superior soft tissue contrast, the use of magnetic resonance imaging (MRI) as a complement to computed tomography (CT) in the target definition procedure for radiotherapy is increasing. To keep the workflow simple and cost effective and to reduce patient dose, it is natural to strive for a treatment planning procedure based entirely on MRI. In the present study, we investigate the dose calculation accuracy for different treatment regions when using bulk density assignments on MRI data and compare it to treatment planning that uses CT data. MR and CT data were collected retrospectively for 40 patients with prostate, lung, head and neck, or brain cancers. Comparisons were made between calculations on CT data with and without inhomogeneity corrections and on MRI or CT data with bulk density assignments. The bulk densities were assigned using manual segmentation of tissue, bone, lung, and air cavities. The deviations between calculations on CT data with inhomogeneity correction and on bulk density assigned MR data were small. The maximum difference in the number of monitor units required to reach the prescribed dose was 1.6%. This result also includes effects of possible geometrical distortions. The dose calculation accuracy at the investigated treatment sites is not significantly compromised when using MRI data when adequate bulk density assignments are made. With respect to treatment planning, MRI can replace CT in all steps of the treatment workflow, reducing the radiation exposure to the patient, removing any systematic registration errors that may occur when combining MR and CT, and decreasing time and cost for the extra CT investigation.

Technical Note: MRI only prostate radiotherapy planning using the statistical decomposition algorithm

Abstract: Purpose: In order to enable a magnetic resonance imaging (MRI) only workflow in radiotherapy treatment planning, methods are required for generating Hounsfield unit (HU) maps (i.e., synthetic compu ...

Zero TE-based pseudo-CT image conversion in the head and its application in PET/MR attenuation correction and MR-guided radiation therapy planning.

Abstract: Purpose: To describe a method for converting Zero TE (ZTE) MR images into Xray attenuation information in the form of pseudo-CT images and demonstrate its performance for (1) attenuation correction ...

MR-OPERA : A Multicenter/Multivendor Validation of Magnetic Resonance Imaging-Only Prostate Treatment Planning Using Synthetic Computed Tomography Images

Abstract: Purpose: To validate the dosimetric accuracy and clinical robustness of a commercially available software for magnetic resonance (MR) to synthetic computed tomography (sCT) conversion, in an MR ima ...

Survey of Medical Image Registration

Abstract: Computerized Image Registration approaches can offer automatic and accurate image alignments without extensive user involvement and provide tools for visualizing combined images. The aim of this survey is to present a review of publications related to Medical Image Registration. This paper paints a comprehensive picture of image registration methods and their applications. This paper is an introduction for those new to the field, an overview for those working in the field and a reference for those searching for literature on a specific application. Methods are classified according to the different aspects of Medical Image Registration.

MR-based synthetic CT generation using a deep convolutional neural network method

Abstract: Purpose Interests have been rapidly growing in the field of radiotherapy to replace CT with magnetic resonance imaging (MRI), due to superior soft tissue contrast offered by MRI and the desire to reduce unnecessary radiation dose. MR-only radiotherapy also simplifies clinical workflow and avoids uncertainties in aligning MR with CT. Methods, however, are needed to derive CT-equivalent representations, often known as synthetic CT (sCT), from patient MR images for dose calculation and DRR-based patient positioning. Synthetic CT estimation is also important for PET attenuation correction in hybrid PET-MR systems. We propose in this work a novel deep convolutional neural network (DCNN) method for sCT generation and evaluate its performance on a set of brain tumor patient images. Methods The proposed method builds upon recent developments of deep learning and convolutional neural networks in the computer vision literature. The proposed DCNN model has 27 convolutional layers interleaved with pooling and unpooling layers and 35 million free parameters, which can be trained to learn a direct end-to-end mapping from MR images to their corresponding CTs. Training such a large model on our limited data is made possible through the principle of transfer learning and by initializing model weights from a pretrained model. Eighteen brain tumor patients with both CT and T1-weighted MR images are used as experimental data and a sixfold cross-validation study is performed. Each sCT generated is compared against the real CT image of the same patient on a voxel-by-voxel basis. Comparison is also made with respect to an atlas-based approach that involves deformable atlas registration and patch-based atlas fusion. Results The proposed DCNN method produced a mean absolute error (MAE) below 85 HU for 13 of the 18 test subjects. The overall average MAE was 84.8 ± 17.3 HU for all subjects, which was found to be significantly better than the average MAE of 94.5 ± 17.8 HU for the atlas-based method. The DCNN method also provided significantly better accuracy when being evaluated using two other metrics: the mean squared error (188.6 ± 33.7 versus 198.3 ± 33.0) and the Pearson correlation coefficient(0.906 ± 0.03 versus 0.896 ± 0.03). Although training a DCNN model can be slow, training only need be done once. Applying a trained model to generate a complete sCT volume for each new patient MR image only took 9 s, which was much faster than the atlas-based approach. Conclusions A DCNN model method was developed, and shown to be able to produce highly accurate sCT estimations from conventional, single-sequence MR images in near real time. Quantitative results also showed that the proposed method competed favorably with an atlas-based method, in terms of both accuracy and computation speed at test time. Further validation on dose computation accuracy and on a larger patient cohort is warranted. Extensions of the method are also possible to further improve accuracy or to handle multi-sequence MR images.

In vivo bidirectional color Doppler flow imaging of picoliter blood volumes using optical coherence tomography

Abstract: We describe a novel optical system for bidirectional color Doppler imaging of flow in biological tissues with micrometer-scale resolution and demonstrate its use for in vivo imaging of blood flow in an animal model. Our technique, color Doppler optical coherence tomography (CDOCT), performs spatially localized optical Doppler velocimetry by use of scanning low-coherence interferometry. CDOCT is an extension of optical coherence tomography (OCT), employing coherent signal-acquisition electronics and joint time-frequency analysis algorithms to perform flow imaging simultaneous with conventional OCT imaging. Cross-sectional maps of blood flow velocity with <50-μm spatial resolution and <0.6-mm/s velocity precision were obtained through intact skin in living hamster subdermal tissue. This technology has several potential medical applications.

Automatic Liver Lesion Segmentation Using A Deep Convolutional Neural Network Method

Abstract: Liver lesion segmentation is an important step for liver cancer diagnosis, treatment planning and treatment evaluation. LiTS (Liver Tumor Segmentation Challenge) provides a common testbed for comparing different automatic liver lesion segmentation methods. We participate in this challenge by developing a deep convolutional neural network (DCNN) method. The particular DCNN model works in 2.5D in that it takes a stack of adjacent slices as input and produces the segmentation map corresponding to the center slice. The model has 32 layers in total and makes use of both long range concatenation connections of U-Net [1] and short-range residual connections from ResNet [2]. The model was trained using the 130 LiTS training datasets and achieved an average Dice score of 0.67 when evaluated on the 70 test CT scans, which ranked first for the LiTS challenge at the time of the ISBI 2017 conference.

Guidelines for Imaging and Staging of Neuroblastic Tumors: Consensus Report from the International Neuroblastoma Risk Group Project

Abstract: Neuroblastoma is an enigmatic disease entity; some tumors disappear spontaneously without any therapy, while others progress with a fatal outcome despite the implementation of maximal modern therapy. However, strong prognostic factors can accurately predict whether children have "good" or "bad" disease at diagnosis, and the clinical stage is currently the most significant and clinically relevant prognostic factor. Therefore, for an individual patient, proper staging is of paramount importance for risk assessment and selection of optimal treatment. In 2009, the International Neuroblastoma Risk Group (INRG) Project proposed a new staging system designed for tumor staging before any treatment, including surgery. Compared with the focus of the International Neuroblastoma Staging System, which is currently the most used, the focus has now shifted from surgicopathologic findings to imaging findings. The new INRG Staging System includes two stages of localized disease, which are dependent on whether image-defined risk factors (IDRFs) are or are not present. IDRFs are features detected with imaging at the time of diagnosis. The present consensus report was written by the INRG Imaging Committee to optimize imaging and staging and reduce interobserver variability. The rationales for using imaging methods (ultrasonography, magnetic resonance imaging, computed tomography, and scintigraphy), as well as technical guidelines, are described. Definitions of the terms recommended for assessing IDRFs are provided with examples. It is anticipated that the use of standardized nomenclature will contribute substantially to more uniform staging and thereby facilitate comparisons of clinical trials conducted in different parts of the world.