| 1. |
- Andersson, Jonas, 1975-, et al.
(författare)
-
Artificial intelligence and the medical physics profession-A Swedish perspective
- 2021
-
Ingår i: Physica Medica-European Journal of Medical Physics. - : Elsevier BV. - 1120-1797 .- 1724-191X. ; 88, s. 218-225
-
Tidskriftsartikel (refereegranskat)abstract
- Background: There is a continuous and dynamic discussion on artificial intelligence (AI) in present-day society. AI is expected to impact on healthcare processes and could contribute to a more sustainable use of resources allocated to healthcare in the future. The aim for this work was to establish a foundation for a Swedish perspective on the potential effect of AI on the medical physics profession. Materials and methods: We designed a survey to gauge viewpoints regarding AI in the Swedish medical physics community. Based on the survey results and present-day situation in Sweden, a SWOT analysis was performed on the implications of AI for the medical physics profession. Results: Out of 411 survey recipients, 163 responded (40%). The Swedish medical physicists with a professional license believed (90%) that AI would change the practice of medical physics but did not foresee (81%) that AI would pose a risk to their practice and career. The respondents were largely positive to the inclusion of AI in educational programmes. According to self-assessment, the respondents' knowledge of and workplace preparedness for AI was generally low. Conclusions: From the survey and SWOT analysis we conclude that AI will change the medical physics profession and that there are opportunities for the profession associated with the adoption of AI in healthcare. To overcome the weakness of limited AI knowledge, potentially threatening the role of medical physicists, and build upon the strong position in Swedish healthcare, medical physics education and training should include learning objectives on AI.
|
|
| 2. |
- Nyholm, Tufve, et al.
(författare)
-
A national approach for automated collection of standardized and population-based radiation therapy data in Sweden
- 2016
-
Ingår i: Radiotherapy and Oncology. - : Elsevier BV. - 0167-8140 .- 1879-0887. ; 119:2, s. 344-350
-
Tidskriftsartikel (refereegranskat)abstract
- Purpose: To develop an infrastructure for structured and automated collection of interoperable radiation therapy (RT) data into a national clinical quality registry. Materials and methods: The present study was initiated in 2012 with the participation of seven of the 15 hospital departments delivering RT in Sweden. A national RT nomenclature and a database for structured unified storage of RT data at each site (Medical Information Quality Archive, MIQA) have been developed. Aggregated data from the MIQA databases are sent to a national RT registry located on the same IT platform (INCA) as the national clinical cancer registries. Results: The suggested naming convention has to date been integrated into the clinical workflow at 12 of 15 sites, and MIQA is installed at six of these. Involvement of the remaining 3/15 RT departments is ongoing, and they are expected to be part of the infrastructure by 2016. RT data collection from ARIA (R), Mosaiq (R), Eclipse (TM), and Oncentra (R) is supported. Manual curation of RT-structure information is needed for approximately 10% of target volumes, but rarely for normal tissue structures, demonstrating a good compliance to the RT nomenclature. Aggregated dose/volume descriptors are calculated based on the information in MIQA and sent to INCA using a dedicated service (MIQA2INCA). Correct linkage of data for each patient to the clinical cancer registries on the INCA platform is assured by the unique Swedish personal identity number. Conclusions: An infrastructure for structured and automated prospective collection of syntactically inter operable RT data into a national clinical quality registry for RT data is under implementation. Future developments include adapting MIQA to other treatment modalities (e.g. proton therapy and brachytherapy) and finding strategies to harmonize structure delineations. How the RT registry should comply with domain-specific ontologies such as the Radiation Oncology Ontology (ROO) is under discussion.
|
|
| 3. |
- Vu, Minh Hoang, 1988-
(författare)
-
Resource efficient automatic segmentation of medical images
- 2023
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Cancer is one of the leading causes of death worldwide. In 2020, there were around 10 million cancer deaths and nearly 20 million new cancer cases in the world. Radiation therapy is essential in cancer treatments because half of the cancer patients receive radiation therapy at some point. During a radiotherapy treatment planning (RTP), an oncologist must manually outline two types of areas of the patient’s body: target, which will be treated, and organs-at-risks (OARs), which are essential to avoid. This step is called delineation. The purpose of the delineation is to generate a sufficient dose plan that can provide adequate radiation dose to a tumor and limit the radiation exposure to healthy tissue. Therefore, accurate delineations are essential to achieve this goal.Delineation is tedious and demanding for oncologists because it requires hours of concentrating work doing a repeated job. This is a RTP bottleneck which is often time- and resource-intensive. Current software, such as atlasbased techniques, can assist with this procedure by registering the patient’s anatomy to a predetermined anatomical map. However, the atlas-based methods are often slowed down and erroneous for patients with abnormal anatomies.In recent years, deep learning (DL) methods, particularly convolutional neural networks (CNNs), have led to breakthroughs in numerous medical imaging applications. The core benefits of CNNs are weight sharing and that they can automatically detect important visual features. A typical application of CNNs for medical images is to automatically segment tumors, organs, and structures, which is assumed to save radiation oncologists much time when delineating. This thesis contributes to resource efficient automatic segmentation and covers different aspects of resource efficiency.In Paper I, we proposed a novel end-to-end cascaded network for semantic segmentation in brain tumors in the multi-modal magnetic resonance imaging challenge in 2019. The proposed method used the hierarchical structure of the tumor sub-regions and was one of the top-ranking teams in the task of quantification of uncertainty in segmentation. A follow-up work to this paper was ranked second in the same task in the same challenge a year later.We systematically assessed the segmentation performance and computational costs of the technique called pseudo-3D as a function of the number of input slices in Paper II. We compared the results to typical two-dimensional (2D) and three-dimensional (3D) CNNs and a method called triplanar orthogonal 2D. The typical pseudo-3D approach considers adjacent slices to be several image input channels. We discovered that a substantial benefit from employing multiple input slices was apparent for a specific input size.We introduced a novel loss function in Paper III to address diverse issues, including imbalanced datasets, partially labeled data, and incremental learning. The proposed loss function adjusts to the given data to use all accessible data, even if some lack annotations. We show that the suggested loss function also performs well in an incremental learning context, where an existing model can be modified to incorporate the delineations of newly appearing organs semi-automatically.In Paper IV, we proposed a novel method for compressing high-dimensional activation maps, which are the primary source of memory use in modern systems. We examined three distinct compression methods for the activation maps to accomplishing this. We demonstrated that the proposed method induces a regularization effect that acts on the layer weight gradients. By employing the proposed technique, we reduced activation map memory usage by up to 95%.We investigated the use of generative adversarial networks (GANs) to enlarge a small dataset by generating synthetic images in Paper V. We use the real and generated data during training CNNs for the downstream segmentation tasks. Inspired by an existing GAN, we proposed a conditional version to generate high-dimensional and high-quality medical images of different modalities and their corresponding label maps. We evaluated the quality of the generated medical images and the effect of this augmentation on the performance of the segmentation task on six datasets.
|
|
| 4. |
- Nyholm, Tufve, et al.
(författare)
-
MR and CT data with multiobserver delineations of organs in the pelvic areaPart of the Gold Atlas project
- 2018
-
Ingår i: Med Phys. - : Wiley. - 0094-2405 .- 2473-4209. ; 45:3, s. 1295-1300
-
Tidskriftsartikel (refereegranskat)abstract
- PurposeWe describe a public dataset with MR and CT images of patients performed in the same position with both multiobserver and expert consensus delineations of relevant organs in the male pelvic region. The purpose was to provide means for training and validation of segmentation algorithms and methods to convert MR to CT like data, i.e., so called synthetic CT (sCT). Acquisition and validation methodsT1- and T2-weighted MR images as well as CT data were collected for 19 patients at three different departments. Five experts delineated nine organs for each patient based on the T2-weighted MR images. An automatic method was used to fuse the delineations. Starting from each fused delineation, a consensus delineation was agreed upon by the five experts for each organ and patient. Segmentation overlap between user delineations with respect to the consensus delineations was measured to describe the spread of the collected data. Finally, an open-source software was used to create deformation vector fields describing the relation between MR and CT images to further increase the usability of the dataset. Data format and usage notesThe dataset has been made publically available to be used for academic purposes, and can be accessed from . Potential applicationsThe dataset provides a useful source for training and validation of segmentation algorithms as well as methods to convert MR to CT-like data (sCT). To give some examples: The T2-weighted MR images with their consensus delineations can directly be used as a template in an existing atlas-based segmentation engine; the expert delineations are useful to validate the performance of a segmentation algorithm as they provide a way to measure variability among users which can be compared with the result of an automatic segmentation; and the pairwise deformably registered MR and CT images can be a source for an atlas-based sCT algorithm or for validation of sCT algorithm. (c) 2018 The Authors. Medical Physics published by Wiley Periodicals, Inc. on behalf of American Association of Physicists in Medicine.
|
|
| 5. |
- Ångström-Brännström, Charlotte, et al.
(författare)
-
Children Undergoing Radiotherapy : Swedish Parents' Experiences and Suggestions for Improvement
- 2015
-
Ingår i: PLOS ONE. - : Public library science. - 1932-6203. ; 10:10
-
Tidskriftsartikel (refereegranskat)abstract
- Approximately 300 children, from 0 to 18 years old, are diagnosed with cancer in Sweden every year. Of these children, 80-90 of them undergo radiotherapy treatment for their cancer. Although radiotherapy is an encounter with advanced technology, few studies have investigated the child's and the parent's view of the procedure. As part of an ongoing multi-center study aimed to improve patient preparation and the care environment in pediatric radiotherapy, this article reports the findings from interviews with parents at baseline. The aim of the present study was twofold: to describe parents' experience when their child undergoes radiotherapy treatment, and to report parents' suggestions for improvements during radiotherapy for their children. Sixteen mothers and sixteen fathers of children between 2-16 years old with various cancer diagnoses were interviewed. Data were analyzed using content analysis. The findings showed that cancer and treatment turns people's lives upside down, affecting the entire family. Further, the parents experience the child's suffering and must cope with intense feelings. Radiotherapy treatment includes preparation by skilled and empathetic staff. The parents gradually find that they can deal with the process; and lastly, parents have suggestions for improvements during the radiotherapy treatment. An overarching theme emerged: that despair gradually turns to a sense of security, with a sustained focus on and close interaction with the child. In conclusion, an extreme burden was experienced around the start of radiotherapy, though parents gradually coped with the process.
|
|
| 6. |
- Adjeiwaah, Mary, 1980-
(författare)
-
Quality assurance for magnetic resonance imaging (MRI) in radiotherapy
- 2017
-
Licentiatavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Magnetic resonance imaging (MRI) utilizes the magnetic properties of tissues to generate image-forming signals. MRI has exquisite soft-tissue contrast and since tumors are mainly soft-tissues, it offers improved delineation of the target volume and nearby organs at risk. The proposed Magnetic Resonance-only Radiotherapy (MR-only RT) work flow allows for the use of MRI as the sole imaging modality in the radiotherapy (RT) treatment planning of cancer. There are, however, issues with geometric distortions inherent with MR image acquisition processes. These distortions result from imperfections in the main magnetic field, nonlinear gradients, as well as field disturbances introduced by the imaged object. In this thesis, we quantified the effect of system related and patient-induced susceptibility geometric distortions on dose distributions for prostate as well as head and neck cancers. Methods to mitigate these distortions were also studied.In Study I, mean worst system related residual distortions of 3.19, 2.52 and 2.08 mm at bandwidths (BW) of 122, 244 and 488 Hz/pixel up to a radial distance of 25 cm from a 3T PET/MR scanner was measured with a large field of view (FoV) phantom. Subsequently, we estimated maximum shifts of 5.8, 2.9 and 1.5 mm due to patient-induced susceptibility distortions. VMAT-optimized treatment plans initially performed on distorted CT (dCT) images and recalculated on real CT datasets resulted in a dose difference of less than 0.5%. The magnetic susceptibility differences at tissue-metallic,-air and -bone interfaces result in local B0 magnetic field inhomogeneities. The distortion shifts caused by these field inhomogeneities can be reduced by shimming. Study II aimed to investigate the use of shimming to improve the homogeneity of local B0 magnetic field which will be beneficial for radiotherapy applications. A shimming simulation based on spherical harmonics modeling was developed. The spinal cord, an organ at risk is surrounded by bone and in close proximity to the lungs may have high susceptibility differences. In this region, mean pixel shifts caused by local B0 field inhomogeneities were reduced from 3.47±1.22 mm to 1.35±0.44 mm and 0.99±0.30 mm using first and second order shimming respectively. This was for a bandwidth of 122 Hz/pixel and an in-plane voxel size of 1×1 mm2. Also examined in Study II as in Study I was the dosimetric effect of geometric distortions on 21 Head and Neck cancer treatment plans. The dose difference in D50 at the PTV between distorted CT and real CT plans was less than 1.0%.In conclusion, the effect of MR geometric distortions on dose plans was small. Generally, we found patient-induced susceptibility distortions were larger compared with residual system distortions at all delineated structures except the external contour. This information will be relevant when setting margins for treatment volumes and organs at risk. The current practice of characterizing MR geometric distortions utilizing spatial accuracy phantoms alone may not be enough for an MR-only radiotherapy workflow. Therefore, measures to mitigate patient-induced susceptibility effects in clinical practice such as patient-specific correction algorithms are needed to complement existing distortion reduction methods such as high acquisition bandwidth and shimming.
|
|
| 7. |
- Björeland, Ulrika, 1974-
(författare)
-
MRI in prostate cancer : implications for target volume
- 2023
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Prostate cancer (PCa) is the most common cancer among men, with 10 000 new cases per year in Sweden [1]. To diagnose PCa, magnetic resonance imaging (MRI) is used to identify and classify the disease. The patient’s treatment strategy depends on PCa classification and clinical data, which are weighted together into a risk group classification from 1–5. For patients with higher risk classes (>3), radiotherapy together with hormone therapy is a common treatment option [2].In radiotherapy (RT), individual treatment plans are created based on the patient’s anatomy. These plans are based on computed tomography (CT), often supplemented with MRI images. MRI and CT complement each other, as MRI has better soft tissue contrast and CT has better bone contrast. Based on the images, the volumes to be treated (target) and the volumes to be avoided (risk organs) are defined. Prostate RT is complex, and there are uncertainties regarding the patient's internal movements and how the patient is positioned before each treatment. To account for these uncertainties, the radiation field is expanded (extended margins to target) to ensure that the treatment volume receives its radiotherapy. RT is most often given in fractions. Fractionation, dose, and treatment volume depend on the patient’s risk category. The treatment area can be, for example, only prostate, prostate with extra radiation dose (boost) to an intraprostatic tumour, or prostate with lymph node (LN) irradiation. LN irradiation is most often given for preventive purposes for PCa with a risk classification >4, which means no cancer has been identified, but any microscopic spread to the LNs is being treated profylactically.In RT, target identification is essential both in the treatment planning images (CT/MRI) and at treatment. Studies have shown that PCa often re-occurs in or near the volume of the dominant (often largest) intraprostatic tumour [3, 4], and this volume is relevant for boosting. For patients treated with hormone therapy before radiotherapy, tumour identification is complicated. Hormones change the tumour characteristics, affecting the image contrast and making the tumour difficult to identify. To study this, we investigated whether texture analysis could identify the tumour volume after hormone therapy (paper II). However, even with texture analysis, the tumour was difficult to identify. A follow-up study examined whether the image information in MRI images taken before hormone therapy could indicate how the treatment fell out (paper IV). However, no correlation was seen between image features and the progression of PCa.Identifying the target and correctly positioning the patient for each treatment fraction is the most important procedure in radiotherapy. The prostate is a mobile organ; therefore, intraprostatic fiducial markers are inserted before treatment planning to reduce positioning uncertainties. Each radiotherapy session begins with an X-ray image where the markers are visible, and the radiation can be delivered based on the markers' position. The markers are also used as guidance for large target volumes, such as for prostate with LN irradiation. With better knowledge of the prostate and LN movements, the margins can potentially be reduced, followed by reduced radiation dose to healthy tissue and therefore reduced side effects for patients. Movements in the radiotherapy volume were the focus of paper I. Using MRI images, the movements of the prostate and LNs were measured during the course of radiotherapy, and we found that LN movement is independent of the movement of the prostate and that the movement varies in the target volume.In addition to the recurrence of PCa in the tumour area, there is an increased risk of recurrence in the prostate periphery close to the rectum. Since the rectum and prostate are in contact for some patients, RT must be adapted to make rectum side effects tolerable. One way to increase the distance between the prostate and the rectum is to inject a gel between the two organs. The distance makes it easier to achieve a better dose distribution to the PCa. This idea resulted in paper III, where patients were given a gel between the prostate and rectum. MRI was used to check the stability of the gel during the course of RT and was evaluated together with long-term follow-up of the patient’s well-being and acceptance of the gel. We found that the radiation dose to the rectum was lower with a spacer, although the spacer was not completely stable during treatment.
|
|
| 8. |
- Gustafsson, Christian, et al.
(författare)
-
Registration free automatic identification of gold fiducial markers in MRI target delineation images for prostate radiotherapy
- 2017
-
Ingår i: Medical physics (Lancaster). - : Wiley. - 0094-2405. ; 44:11, s. 5563-5574
-
Tidskriftsartikel (refereegranskat)abstract
- Purpose: The superior soft tissue contrast of magnetic resonance imaging (MRI) compared to computed tomography (CT) has urged the integration of MRI and elimination of CT in radiotherapy treatment (RT) for prostate. An intraprostatic gold fiducial marker (GFM) appears hyperintense on CT. On T2-weighted (T2w) MRI target delineation images, the GFM appear as a small signal void similar to calcifications and post biopsy fibrosis. It can therefore be difficult to identify the markers without CT. Detectability of GFMs can be improved using additional MR images, which are manually registered to target delineation images. This task requires manual labor, and is associated with interoperator differences and image registration errors. The aim of this work was to develop and evaluate an automatic method for identification of GFMs directly in the target delineation images without the need for image registration.Methods: T2w images, intended for target delineation, and multiecho gradient echo (MEGRE) images intended for GFM identification, were acquired for prostate cancer patients. Signal voids in the target delineation images were identified as GFM candidates. The GFM appeared as round, symmetric, signal void with increasing area for increasing echo time in the MEGRE images. These image features were exploited for automatic identification of GFMs in a MATLAB model using a patient training dataset (n = 20). The model was validated on an independent patient dataset (n = 40). The distances between the identified GFM in the target delineation images and the GFM in CT images were measured. A human observatory study was conducted to validate the use of MEGRE images.Results: The sensitivity, specificity, and accuracy of the automatic method and the observatory study was 84%, 74%, 81% and 98%, 94%, 97%, respectively. The mean absolute difference in the GFM distances for the automatic method and observatory study was 1.28 1.25 mm and 1.14 +/- 1.06 mm, respectively.Conclusions: Multiecho gradient echo images were shown to be a feasible and reliable way to perform GFM identification. For clinical practice, visual inspection of the results from the automatic method is needed at the current stage.
|
|
| 9. |
- Jonsson, Joakim, 1984-, et al.
(författare)
-
Treatment planning of intracranial targets on MRI derived substitute CT data
- 2013
-
Ingår i: Radiotherapy and Oncology. - : Elsevier BV. - 0167-8140 .- 1879-0887. ; 108:1, s. 118-122
-
Tidskriftsartikel (refereegranskat)abstract
- BACKGROUND: The use of magnetic resonance imaging (MRI) as a complement to computed tomography (CT) in the target definition procedure for radiotherapy is increasing. To eliminate systematic uncertainties due to image registration, a workflow based entirely on MRI may be preferable. In the present pilot study, we investigate dose calculation accuracy for automatically generated substitute CT (s-CT) images of the head based on MRI. We also produce digitally reconstructed radiographs (DRRs) from s-CT data to evaluate the feasibility of patient positioning based on MR images. METHODS AND MATERIALS: Five patients were included in the study. The dose calculation was performed on CT, s-CT, s-CT data without inhomogeneity correction and bulk density assigned MRI images. Evaluation of the results was performed using point dose and dose volume histogram (DVH) comparisons, and gamma index evaluation. RESULTS: The results demonstrate that the s-CT images improves the dose calculation accuracy compared to the method of non-inhomogeneity corrected dose calculations (mean improvement 2.0 percentage points) and that it performs almost identically to the method of bulk density assignment. The s-CT based DRRs appear to be adequate for patient positioning of intra-cranial targets, although further investigation is needed on this subject. CONCLUSIONS: The s-CT method is very fast and yields data that can be used for treatment planning without sacrificing accuracy.
|
|
| 10. |
- Simkó, Attila, et al.
(författare)
-
MRI bias field correction with an implicitly trained CNN
- 2022
-
Ingår i: Proceedings of the 5th international conference on medical imaging with deep learning. - : ML Research Press. ; , s. 1125-1138
-
Konferensbidrag (refereegranskat)abstract
- In magnetic resonance imaging (MRI), bias fields are difficult to correct since they are inherently unknown. They cause intra-volume intensity inhomogeneities which limit the performance of subsequent automatic medical imaging tasks, \eg, tissue-based segmentation. Since the ground truth is unavailable, training a supervised machine learning solution requires approximating the bias fields, which limits the resulting method. We introduce implicit training which sidesteps the inherent lack of data and allows the training of machine learning solutions without ground truth. We describe how training a model implicitly for bias field correction allows using non-medical data for training, achieving a highly generalized model. The implicit approach was compared to a more traditional training based on medical data. Both models were compared to an optimized N4ITK method, with evaluations on six datasets. The implicitly trained model improved the homogeneity of all encountered medical data, and it generalized better for a range of anatomies, than the model trained traditionally. The model achieves a significant speed-up over an optimized N4ITK method—by a factor of 100, and after training, it also requires no parameters to tune. For tasks such as bias field correction - where ground truth is generally not available, but the characteristics of the corruption are known - implicit training promises to be a fruitful alternative for highly generalized solutions.
|
|
