The first Metatarsophalangeal (MTP) joint is essential for foot biomechanics and weight-bearing activities. Osteoarthritis in this joint can lead to pain, discomfort, and limited mobility. In order to treat this, Episurf Medical is working to produce individualized implants based on 3D segmentations of the joint. As manual segmentations are both time- and cost-consuming, and susceptible to human errors, automatic approaches are preferred. This thesis uses U-Net and DeepEdit as deep-learning based methods for segmentation of the MTP joint, with the latter being evaluated with and without user interactions. The dataset used in this study consisted of 38 CT images, where each model was trained on 30 images, and the remaining images were used as a test set. The final models were evaluated and compared with regards to the Dice Similarity Coefficient (DSC), precision, and recall. The U-Net model achieved DSC 0.944, precision 0.961, and recall 0.929. The automatic DeepEdit approach obtained DSC of 0.861, precision of 0.842, and recall of 0.891, while the interactive DeepEdit approach resulted in DSC of 0.918, precision of 0.912, and recall of 0.928. All pairwise comparisons in terms of precision and DSC showed significant differences (p<0.05), where U-Net had the highest performance, while the difference in recall was not found to be significant (p>0.05) for any comparison. The lower performances of DeepEdit compared to U-Net could be due to lower spatial resolution in the segmentations. Nevertheless, DeepEdit remains a promising method, and further investigations of unexplored areas could be addressed as future work. / Den första Metatarsalphalangeal(MTP) leden är viktig för fotens biomekanik och viktbärande aktiviteter. Artros i denna led kan leda till smärta, obehag och begränsad rörlighet. För att behandla detta arbetar Episurf Medical med att producera individanpassade implantat baserat på 3D segmenteringar av leden. Då manuella segmenteringar både är tids- och kostnadskrävande, samt känsliga för mänskliga fel, föredras automatiska metoder. Denna avhandling använder U-Net och DeepEdit som djupinlärningsbaserade metoder för segm- entering av MTP leden, varav det senare utvärderas med och utan användarint- eraktion. Datasetet som användes i denna studie bestod av 38 CT bilder, där varje modell tränades på 30 bilder och de återstående användes som testdata. De slutliga modellerna utvärderades och jämfördes med avseende på Dice Similarity Coefficient (DSC), precision och recall. U-Net modellen uppnådde DSC 0.944, precision 0.961 och recall 0.929. Den automatiska DeepEdit metoden erhöll DSC 0.861, precision 0.842 och recall 0.891, medan den interaktiva DeepEdit metoden resulterade i DSC 0.918, precision 0.912 och recall 0.928. Alla parvisa jämförelser avseende precision och DSC visade signifikanta skillnader (p<0.05), där U-Net hade den högsta prestandan, medan skillnaden i recall inte visade sig vara signifikant (p>0.05) för någon jämförelse. Den lägre prestandan för DeepEdit jämfört med U-Net kan bero på lägre spatiell upplösning i segmenteringarna. Dock är DeepEdit fortfarande en lovande metod, och ytterligare undersökningar av outforskade områden kan tas upp som framtida arbete.

Medical imaging technologies have allowed for in vivo evaluation of the human musculoskeletal system. With advances in both medical imaging and computing, patient-specific model development of anatomic structures is becoming a reality. Three-dimensional surface models are useful for patient-specific measurements and finite element studies. Orthopaedics is closely tied to engineering in the analysis of injury mechanisms, design of implantable medical devices, and potentially in the prediction of injury. However, a disconnection exists between medical imaging and orthopaedic analysis; whereby, the ability to generate three-dimensional models from an imaging dataset is difficult, which has restricted its application to large patient populations. We have compiled image processing, image segmentation, and surface generation tools in a single software package catered specifically to image-based orthopaedic analysis. We have also optimized an automated segmentation technique to allow for high-throughput bone segmentation and developed algorithms that help to automate the cumbersome process of mesh generation in finite element analysis. We apply these tools to evaluate graft placement in anterior cruciate ligament reconstruction in a multicenter study that aims to improve the patient outcomes of those that undergo this procedure.

The thesis discusses the possibilities of using contour shape classification for detection of mis-segmented bones in computed tomography (CT) data. In the first part there are presented published methods and algorithms which deal with the segmentation of bone structures in CT data. Then segmentation of cortical bones is implemented by a simple thresholding with global threshold. The threshold is determined by the optimized fitting of a selected type probability distribution to the histogram. Subsequently, the thesis describes some important shape descriptors that can quantitatively describe the shapes of objects in the image. Further, the contour extraction is implemented and a suitable shape descriptor, cumulative angular function, is applied. Finally, the points which can potentially indicate mis-segmented bones are detected by using continuous wavelet transform. The proposed technique is tested on the real CT data.

Cone Beam Computed Tomography (CBCT) is a medical imaging technique routinely employed for diagnosis and treatment of patients with cranio-maxillo-facial defects. CBCT 3D reconstruction and segmentation of bones such as mandible or maxilla are essential procedures in orthodontic treatments. However, CBCT images present characteristics that are not desirable for processing, including low contrast, inhomogeneity, noise, and artifacts. Besides, values assigned to voxels are relative Hounsfield Units (HU), unlike traditional Computed Tomography (CT). Such drawbacks render CBCT segmentation a difficult and time-consuming task, usually performed manually with tools designed for medical image processing. We introduce two interactive two-stage methods for 3D segmentation of CBCT data: i) we first reduce the CBCT image resolution by grouping similar voxels into super-voxels defining a graph representation; ii) next, seeds placed by users guide graph clustering algorithms, splitting the bones into mandible and skull. We have evaluated our segmentation methods intensively by comparing the results against ground truth data of the mandible and the skull, in various scenarios. Results show that our methods produce accurate segmentation and are robust to changes in parameter settings. We also compared our approach with a similar segmentation strategy and we showed that it produces more accurate segmentation of the mandible and skull. In addition, we have evaluated our proposal with CT data of patients with deformed or missing bones. We obtained more accurate segmentation in all cases. As for the efficiency of our implementation, a segmentation of a typical CBCT image of the human head takes about five minutes. Finally, we carried out a usability test with orthodontists. Results have shown that our proposal not only produces accurate segmentation, as it also delivers an effortless and intuitive user interaction. / Tomografia Computadorizada de Feixe Cônico (TCFC) é uma modalidade para obtenção de imagens médicas 3D do crânio usada para diagnóstico e tratamento de pacientes com defeitos crânio-maxilo-faciais. A segmentação tridimensional de ossos como a mandíbula e a maxila são procedimentos essências em tratamentos ortodônticos. No entanto, a TCFC apresenta características não desejáveis para processamento digital como, por exemplo, baixo contraste, inomogeneidade, ruído e artefatos. Além disso, os valores atribuídos aos voxels são unidades de Hounsfield (HU) relativas, diferentemente da Tomografia Computadorizada (TC) tradicional. Esses inconvenientes tornam a segmentação de TCFC uma tarefa difícil e demorada, a qual é normalmente realizada por meio de ferramentas desenvolvidas para processamento digital de imagens médicas. Esta tese introduz dois métodos interativos para a segmentação 3D de TCFC, os quais são divididos em duas etapas: i) redução da resolução da TCFC por meio da agrupamento de voxels em super-voxels, seguida da criação de um grafo no qual os vértices são super-voxels; ii) posicionamento de sementes pelo usuário e segmentação por algoritmos de agrupamento em grafos, o que permite separar os ossos rotulados. Os métodos foram intensamente avaliados por meio da comparação dos resultados com padrão ouro da mandíbula e do crânio, considerando diversos cenários. Os resultados mostraram que os métodos não apenas produzem segmentações precisas, como também são robustos a mudanças nos parâmetros. Foi ainda realizada uma comparação com um trabalho relacionado, gerando melhores resultados tanto na segmentação da mandíbula quanto a do crânio. Além disso, foram avaliadas TCs de pacientes com ossos faltantes e quebrados. A segmentação de uma TCFC é realizada em cerca de 5 minutos. Por fim, foram realizados testes com usuarios ortodontistas. Os resultados mostraram que nossa proposta não apenas produz segmentações precisas, como também é de fácil interação.

Cone Beam Computed Tomography (CBCT) is a medical imaging technique routinely employed for diagnosis and treatment of patients with cranio-maxillo-facial defects. CBCT 3D reconstruction and segmentation of bones such as mandible or maxilla are essential procedures in orthodontic treatments. However, CBCT images present characteristics that are not desirable for processing, including low contrast, inhomogeneity, noise, and artifacts. Besides, values assigned to voxels are relative Hounsfield Units (HU), unlike traditional Computed Tomography (CT). Such drawbacks render CBCT segmentation a difficult and time-consuming task, usually performed manually with tools designed for medical image processing. We introduce two interactive two-stage methods for 3D segmentation of CBCT data: i) we first reduce the CBCT image resolution by grouping similar voxels into super-voxels defining a graph representation; ii) next, seeds placed by users guide graph clustering algorithms, splitting the bones into mandible and skull. We have evaluated our segmentation methods intensively by comparing the results against ground truth data of the mandible and the skull, in various scenarios. Results show that our methods produce accurate segmentation and are robust to changes in parameter settings. We also compared our approach with a similar segmentation strategy and we showed that it produces more accurate segmentation of the mandible and skull. In addition, we have evaluated our proposal with CT data of patients with deformed or missing bones. We obtained more accurate segmentation in all cases. As for the efficiency of our implementation, a segmentation of a typical CBCT image of the human head takes about five minutes. Finally, we carried out a usability test with orthodontists. Results have shown that our proposal not only produces accurate segmentation, as it also delivers an effortless and intuitive user interaction. / Tomografia Computadorizada de Feixe Cônico (TCFC) é uma modalidade para obtenção de imagens médicas 3D do crânio usada para diagnóstico e tratamento de pacientes com defeitos crânio-maxilo-faciais. A segmentação tridimensional de ossos como a mandíbula e a maxila são procedimentos essências em tratamentos ortodônticos. No entanto, a TCFC apresenta características não desejáveis para processamento digital como, por exemplo, baixo contraste, inomogeneidade, ruído e artefatos. Além disso, os valores atribuídos aos voxels são unidades de Hounsfield (HU) relativas, diferentemente da Tomografia Computadorizada (TC) tradicional. Esses inconvenientes tornam a segmentação de TCFC uma tarefa difícil e demorada, a qual é normalmente realizada por meio de ferramentas desenvolvidas para processamento digital de imagens médicas. Esta tese introduz dois métodos interativos para a segmentação 3D de TCFC, os quais são divididos em duas etapas: i) redução da resolução da TCFC por meio da agrupamento de voxels em super-voxels, seguida da criação de um grafo no qual os vértices são super-voxels; ii) posicionamento de sementes pelo usuário e segmentação por algoritmos de agrupamento em grafos, o que permite separar os ossos rotulados. Os métodos foram intensamente avaliados por meio da comparação dos resultados com padrão ouro da mandíbula e do crânio, considerando diversos cenários. Os resultados mostraram que os métodos não apenas produzem segmentações precisas, como também são robustos a mudanças nos parâmetros. Foi ainda realizada uma comparação com um trabalho relacionado, gerando melhores resultados tanto na segmentação da mandíbula quanto a do crânio. Além disso, foram avaliadas TCs de pacientes com ossos faltantes e quebrados. A segmentação de uma TCFC é realizada em cerca de 5 minutos. Por fim, foram realizados testes com usuarios ortodontistas. Os resultados mostraram que nossa proposta não apenas produz segmentações precisas, como também é de fácil interação.

Dans cette thèse, nous présentons une méthode de segmentation d’images radiographiques des membres inférieurs en régions d’intérêt (ROIs), une méthode de recalage rigide tridimensionnel (3D) / bidimensionnel (2D) des prothèses du genou sur les deux images biplanaires radiographiques calibrées et une méthode de reconstruction 3D des membres inférieurs à partir de deux images biplanaires radiographiques calibrées. Le premier article présente une méthode de segmentation de rotule, astragale et bassin des images radiographiques en régions d’intérêt basée sur la fusion de multi-atlas et superpixels. Cette méthode utilise l’apprentissage d’une base de données d’images radiographiques de ces os segmentées manuellement et recalées entre elles pour estimer un ensemble de superpixels permettant de tenir compte de toute la variabilité locale et non linéaire existante dans la base, puis la propagation d’étiquettes basée sur le concept d’entropie pour raffiner la carte de segmentations en régions internes afin d’obtenir le résultat final. Le deuxième article présente une méthode de recalage rigide 3D / 2D des composants tibiaux et fémoraux de prothèse du genou sur deux images biplanaires radiographiques calibrées. Cette méthode utilise une mesure de similarité hybride basée sur les notions de contours et régions puis un algorithme d’optimisation stochastique pour estimer la position des composants. La similarité basée sur les régions est stable et robuste contre les bruits. Cependant, cette mesure n’est pas précise car le nombre de pixels aux contours est inférieur au celui à l’intérieur de la région. Au contraire, la similarité basée sur les contours est précise mais plus sensible au bruit ou à d’autres artefacts existant dans les images. C’est pourquoi la combinaison de ces deux similarités fournit une méthode de recalage robuste et précise. Le troisième article représente une méthode statistique biplanaire de reconstruction 3D de rotule, astragale et bassin. Cette méthode utilise un algorithme de réduction de dimensionnalité pour définir un modèle déformable paramétrique qui contient toutes les déformations statistiques admissibles apprises à partir d’une base de données des structures osseuses. Puis un algorithme d’optimisation stochastique est utilisé pour minimiser la différence entre la projection des contours / régions des modèles surfaciques osseux avec ceux segmentés sur les deux images radiographiques. / In this thesis, we present a segmentation method of lower limbs of X-ray images into regions of interest (ROIs), a three-dimensional (3D) / two-dimensional (2D) rigid registration method of knee implant components to biplanar X-ray images, and a 3D reconstruction method of the lower limbs using biplanar X-ray images. The first paper presents a superpixel and multi-atlas-based segmentation method of the patella, talus, and pelvis into regions of interest. This method uses a training dataset of pre-segmented and co-registered X-ray images of these bones to estimate a collection of superpixels allowing to take into account all the nonlinear and local variability existing in the dataset, then a propagation of label based on the entropy concept for refining the segmentation map into internal regions to the final result. The second paper presents a 3D / 2D rigid registration method of tibial and femoral components of knee implants to calibrated biplanar X-ray images. This method uses a hybrid edge- and region-based similarity measure then a stochastic optimization algorithm to estimate the component position. The region-based similarity is stable and robust to noise. However, this measure is not precise because the number of pixels in the border is fewer than the number of pixels inside the region. On the contrary, the edge-based similarity is accurate but more sensitive to noise or other artifacts existing in the images. That’s why the combination of these two similarity types provides a robust and accurate registration method. The third paper presents a statistical biplanar 3D reconstruction method of the patella, talus, and pelvis. This method uses a dimensionality reduction algorithm to define a deformable parametric model which contains all admissible statistical deformations learned from the bone structure dataset. Then a stochastic optimization algorithm is used to minimize the difference between the contour / region projection of bone models and the contours / regions in two segmented X-ray images.