This thesis presents a prototype beacon-based indoor positioning system using IR-based triangulation together with various inertial sensors mounted onto the receiver. By applying a Kalman filter, the mobile receivers can estimate their position by fusing the data received from the two independent measurement systems. Furthermore, the system is aimed to operate and conduct all calculations using microcontrollers. Multiple IR beacons and an AGV were constructed to determine the systems performance. Empirical and practical experiments show that the proposed localisation system is capable centimeter accuracy. However, because of hardware limitation the system has lacking update frequency and range. With the limitations in mind, it can be established that the final sensor-fused solution shows great promise but requires an extended component assessment and more advanced localisation estimations method such as an Extended Kalman Filter or particle filter to increase reliability.

Imbalanced training data is a common problem in machine learning applications. Thisproblem refers to datasets in which the foreground pixels are significantly fewer thanthe background pixels. By training a machine learning model with imbalanced data, theresult is typically a model that classifies all pixels as the background class. A result thatindicates no presence of a specific condition when it is actually present is particularlyundesired in medical imaging applications. This project proposes a sequential system oftwo fully convolutional neural networks to tackle the problem. Semantic segmentation oflung nodules in thoracic computed tomography images has been performed to evaluate theperformance of the system. The imbalanced data problem is present in the training datasetused in this project, where the average percentage of pixels belonging to the foregroundclass is 0.0038 %. The sequential system achieved a sensitivity of 83.1 % representing anincrease of 34 % compared to the single system. The system only missed 16.83% of thenodules but had a Dice score of 21.6 % due to the detection of multiple false positives. Thismethod shows considerable potential to be a solution to the imbalanced data problem withcontinued development.

Radiotherapy plays an increasingly important role in cancer treatment, and medical imaging plays an increasingly important role in radiotherapy. Magnetic resonance imaging (MRI) is poised to be a major component in the development towards more effective radiotherapy treatments with fewer side effects. This thesis attempts to contribute in realizing this potential. Radiotherapy planning requires simulation of radiation transport. The necessary physical properties are typically derived from CT images, but in some cases only MR images are available. In such a case, a crude but common approach is to approximate all tissue properties as equivalent to those of water. In this thesis we propose two methods to improve upon this approximation. The first uses a machine learning algorithm to automatically identify bone tissue in MR. The second, which we refer to as atlas-based regression, can be used to generate a realistic, patient-specific, pseudo-CT directly from anatomical MR images. Atlas-based regression uses deformable registration to estimate a pseudo-CT of a new patient based on a database of aligned MR and CT pairs. Cancerous tissue has a dierent structure from normal tissue. This affects molecular diusion, which can be measured using MRI. The prototypical diusion encoding sequence has recently been challenged with the introduction of more general  waveforms. To take full advantage of their capabilities it is, however, imperative to respect the constraints imposed by the hardware while at the same time maximizing the diffusion encoding strength. In this thesis we formulate this as a constrained optimization problem that is easily adaptable to various hardware constraints.

No description available.

No description available.

Time-correlated single photon counting (TCSPC) systems are used for range profiling. The systems offer cm precision at kilometer ranges. This opens up for long range imaging with high resolution, for example by reflective tomography. With range profiles from various aspect angles around a target reflective tomography can be used to create an image. The tomographic image is a reconstruction of the boundary of the cross-section of the target. Images can be used for various purposes, e.g. identification of satellites. The quality of the tomographic reconstruction depends on the accuracy of the TCSPC system. Range profiles with a cm precision allows studies and reconstruction of complex objects. With this work we investigated the current limitations when reconstructing complex targets with reflective tomography and present possible solutions to existing problems. The limitations were investigated by studying parameters such as the intensity of the laser beam, SNR, center of rotation, angular resolution, and the angular sector. We also present methods that can improve the tomographic image. A new pre-processing method that adjusts range profiles after estimating responses with RJMCMC was introduced. We also studied different types of filters in the reconstruction process. Lastly we introduced two new post-processing methods. One that removes artifacts by considering the convex hull and one that sharpens edges in the tomographic image. The performance study showed that reflective tomography using a TCSPC system is robust in a controlled environment. Details in the low cm-range of an object can be reconstructed with high precision. However, for some target types issues appear. Of the tested performance parameters a high angle resolution was deemed to be the most important. When considering moving targets the importance of the center of rotation and integration time will also increase. The study of improvement methods showed that choosing the generalized ramp filter in the FBP more then doubled the SNR. Adjusting the range profiles, considering the convex hull, and sharpening edges are methods that work well for specific signal types. We showed that many issues that arise when measuring on complex objects can be solved with signal processing. Therefore we believe that reflective tomography can be used in various applications in the future. / Tidskorrelerad räkning av fotoner (time-correlated single photon counting, TCSPC) är en teknik som används för att skapa avståndsprofiler med cm-precision på upp emot flera kilometers håll. Tekniken kan användas till att skapa avbildningar av föremål på långa avstånd, till exempel med reflektiv tomografi. Reflektiv tomografi kan användas när man har avståndsprofiler runt om ett föremål. Den tomografiska återskapningen beskriver de yttre kanterna av ett föremåls tvärsnitt. Bildernas kvalité är starkt beroende av noggrannheten i TCSPC-systemet. En cm-precision möjliggör studier och återskapningar av föremål med små detaljer. Detta arbete går ut på att undersöka begränsningarna med återskapandet av detaljerade föremål och framlägga metoder som förbättrar återskapningarna. Begränsningarna undersöktes genom att studera olika parametrar, såsom intensiteten i lasern, SNR, rotationscentrum, vinkelupplösning och vinkelsektorer. Vi presenterade också nya metoder som förbättrar återskapningarna. Vi tittade bland annat på en metod som korrigerar avståndsprofilerna med hjälp av anpassningar med RJMCMC. Sedan undersöktes olika filter i återskapningen. Avslutningsvis introducerades två nya metoder i efterbehandlingen. En som tar hänsyn till konvexa höljet och en annan som gör kanter i bilderna skarpare. Prestandaundersökningen visade att reflektiv tomografi baserad på ett TCSPC-system är robust i en kontrollerad miljö. Centimeterstora detaljer kan återskapas med hög upplösning. För vissa förem\aa l uppstår dock problem. Av de testade prestandaparametrarna var en hög vinkelupplösning den viktigaste. Valet av rotationscentrum och integrationstiden kommer spela en större roll med föremål i rörelse. Studien av förbättringsmetoder visade att bilders SNR mer än dubblas om det generella rampfiltret används i FBP. Att korrigera avståndsprofilerna med RJMCMC, ta hänsyn till komplexa höljet och att göra kanter skarpare är metoder som fungerar bra med vissa signaltyper. Mer arbete finns att göra men vi visade att många problem i reflektiv tomografi går att lösa med signalbehandling. Vi tror därför att reflektiv tomografi går en ljus framtid till mötes.

Studien behandlar pressfotografers inställning till bildbehandling, hur de motiverar de åtgärder de säger sig vidta under bildbehandling och hur tänker de sig att bildbehandling inverkar på bilders trovärdighet. Studien syftar också till att identifiera några av de premisser som potentiellt kan ligga till grund för pressfotografens vägval under bildbehandling, samt att visa hur dessa premisser tillsammans skapar stringens som påverkar pressfotografens syn på bildbehandling. Studiens resultat, som bygger på djupintervjuer med fem pressfotografer, redovisar bildbehandling som ett personligt förfarande så till vida att varje fotograf på individuell basis bedömer hur en bild bör justeras. Bildens syfte, genre, kvalitet och budskap samt medielogiska aspekter, med betoning på fotografens arbetssituation, är också aspekter sompåverkar potentiellt påverkar handlingsvalen. Bland intervjupersonerna framträder även två huvudlinjer i synen på bildbehandling: den ena vilken ger uttryck för en tekniktilltro – kamerans begränsningar respekteras och ses i viss mån också som en garant för bildens äkthet. Den andra linjen manifesterar en mer dynamisk syn på bildbehandling som utgår från fotografens subjektiva upplevelse av fototillfället. Det centrala är här inte vad kameran lyckas återge utan ansvaret läggs istället över på fotografen i egenskap av reporter. Principen att aldrig vilseleda läsaren, att varje åtgärd i bildbehandlingen alltid vidtas i syfte att förstärka bildens budskap samt för att underlätta för läsaren vid tolkning av bildinnehållet, verkar hela tiden vägledande och kan sägas utgöra en okränkbar maxim när pressfotografer resonerar kring etiska överväganden.

Trabecular bone structure as well as bone mineral density (BMD) have impact on the biomechanical competence of bone. In osteoporosis-related fractures, there have been shown to exist disconnections in the trabecular network as well as low bone mineral density. Imaging of bone parameters is therefore of importance in detecting osteoporosis. One available imaging device is cone-beam computed tomography (CBCT). This device is often used in pre-operative imaging of dental implants, for which the trabecular network also has great importance. Fourteen or 15 trabecular bone specimens from the radius were imaged for conducting this in vitro project. The imaging data from one dual-energy X-ray absorptiometry (DXA), two multi-slice computed tomography (MSCT), one high-resolution peripheral quantitative computed tomography (HR-pQCT) and four CBCT devices were segmented using an in-house developed code based on homogeneity thresholding. Seven trabecular microarchitecture parameters, as well as two trabecular bone stiffness parameters, were computed from the segmented data. Measurements from micro-computed tomography (micro-CT) data of the same bone specimens were regarded as gold standard. Correlations between MSCT and micro-CT data showed great variations, depending on device, imaging parameters and between the bone parameters. Only the bone-volume fraction (BV/TV) parameter was stable with strong correlations. Regarding both HR-pQCT and CBCT, the correlations to micro-CT were strong for bone structure parameters as well as bone stiffness parameters. The CBCT device 3D Accuitomo showed the strongest correlations, but overestimated BV/TV more than three times compared to micro-CT. The imaging protocol most often used in clinical imaging practice at our clinic demonstrated strong correlations as well as low radiation dose. CBCT data of trabecular bone can be used for analysing trabecular bone properties, like bone microstructure and bone biomechanics, showing strong correlations to the reference method of micro-CT. The results depend on choice of CBCT device as well as segmentation method used. The in-house developed code based on homogeneity thresholding is appropriate for CBCT data. The overestimations of BV/TV must be considered when estimating bone properties in future clinical dental implant and osteoporosis research.

Deep learning methods for medical image segmentation are hindered by the lack of training data. This thesis aims to develop a method that overcomes this problem. Basic U-net trained on XCAT phantom data was tested first. The segmentation results were unsatisfactory even when artificial quantum noise was added. As a workaround, CycleGAN was used to add tissue textures to the XCAT phantom images by analyzing patient CT images. The generated images were used totrain the network. The textures introduced by CycleGAN improved the segmentation, but some errors remained. Basic U-net was replaced with Attention U-net, which further improved the segmentation. More work is needed to fine-tune and thoroughly evaluate the method. The results obtained so far demonstrate the potential of this method for the segmentation of medical images. The proposed algorithms may be used in iterative image reconstruction algorithms in multi-energy computed tomography.

When radiologists examine X-rays, it is crucial that they are aware of the laterality of the examined body part. The laterality refers to which side of the body that is considered, e.g. Left and Right. The consequences of a mistake based on information regarding the incorrect laterality could be disastrous. This thesis aims to address this problem by providing a deep neural network model that classifies X-rays based on their laterality. X-ray images contain markers that are used to indicate the laterality of the image. In this thesis, both a classification model and a detection model have been trained to detect these markers and to identify the laterality. The models have been trained and evaluated on four body parts: knees, feet, hands and shoulders. The images can be divided into three laterality classes: Bilateral, Left and Right. The model proposed in this thesis is a combination of two classification models: one for distinguishing between Bilateral and Unilateral images, and one for classifying Unilateral images as Left or Right. The latter utilizes the confidence of the predictions to categorize some of them as less accurate (Uncertain), which includes images where the marker is not visible or very hard to identify. The model was able to correctly distinguish Bilateral from Unilateral with an accuracy of 100.0 %. For the Unilateral images, 5.00 % were categorized as Uncertain and for the remaining images, 99.99 % of those were classified correctly as Left or Right.