Shear wave (SW) imaging is an ultrasound elastogrpahy technique for estimating the elastic properties of biological tissues. Increasing the frequency would improve both the confinement of the radiation force generating the shear wave, and the imaging spatial resolution. The objectives of the study were to realize a simple high frequency (HF) system for the generation and detection of SW propagation and to implement this system to develop and characterize tissue-mimicking gelatin phantoms (TMGP) for HF SWI with elastic properties in the range of those encountered in biological tissue. A 5 MHz and 10 MHz focused transducer were used to induced SW’s in TMGP ranging from 4% to 12% gelatin with 3% silica for scattering and a 25 MHz single-element focused transducer recorded pulse-echo signals in order to capture the SW. The shear wave speeds in the TMGP were found to range linearly from 1.59-4.59 m/s in the 4% to 12% gelatin samples.

Elastography is an emerging functional imaging technique of current clinical research interest due to a direct relation between mechanical material parameters, especially the tissue stiffness, and tissue pathologies such as cancer. Digital Image Elasto-Tomography (DIET) is a new method that aims to develop elastographic techniques and create a simplified, improved breast cancer screening process. The elastic material information of breast tissue is reconstructed in the DIET concept from mechanically excited steady-state harmonic motion observed on the surface of the breast. While this inversion process has been traditionally approached using finite element methods, this surface-orientated problem is naturally suited to the use of Boundary Element Methods (BEMs) requiring the discretization only on the surface of the domain and on the interface of a potential inclusion. As only approximate information is available about breast tissue material parameters, this thesis presents the development of BEM based inverse problem algorithms suitable for the reconstruction of all material parameters in a proportionally damped isotropic linear elastic solid, where only the material density is known. The highly nonlinear identification process of a potential inclusion is treated through the combination of a systematic Grid-Search with gradient descent techniques. This algorithm is extended to a three-step algorithm that performs a background material parameter estimation before the subsequent identification of an inclusion and thus provides a confident indication for the differentiation between cancerous and healthy breast tissue. The development of these algorithms is illustrated by several simulation studies highlighting important reconstruction behaviors relevant to the elastographic inverse problem. A first experimental test on a silicon based breast phantom is presented.

Pathological phenomena often change the mechanical properties of the tissue. Therefore, estimation of tissue mechanical properties can be of clinical importance. Ultrasound elastography is a well-established strain estimation technique. Until recently, mainly 1D elastography algorithms have been developed. A few 2D algorithms have also been developed in the past. Both of these two types of technique ignore the tissue motion in the elevational direction, which could be a significant source of decorrelation in the RF data. In this thesis, a 3D elastography algorithm that estimates all the three components of tissue displacement is implemented and tested statistically. In this research, displacement fields of mechanical models are simulated. RF signals are then generated based on these displacement fields and used as the input of elastography algorithms. To evaluate the image quality of elastograms, absolute error, SNRe, CNRe and CNRasse are computed. The SNRe, CNRe and CNRasse values are investigated not only under different strain conditions, but also in different frame locations, which forms 3D strain filters. A statistical comparison between image qualities of the 3D technique and 2D technique is also provided. The results of this study show that the 3D elastography algorithm outperforms the 2D elastography algorithm in terms of image quality and robustness, especially under high strain conditions. This is because that the 3D algorithm estimates the elevational displacement, while the 2D technique only estimates the axial and lateral deformation. Since the elevational displacement could be an important source for the decorrelation in the RF data, the 3D technique is more effective and robust compared with the 2D technique.

Submitted by PAULO HENRIQUE DE SOUZA GARCIA null (paulousvet@gmail.com) on 2016-08-16T11:40:16Z No. of bitstreams: 1 Ultrassonografia convencional e Elastografia ARFI na aaliação renal e gatos adultos hígidos.pdf: 2204900 bytes, checksum: 6acbf410866645d13616b8dc7610bd26 (MD5) / Approved for entry into archive by Ana Paula Grisoto (grisotoana@reitoria.unesp.br) on 2016-08-16T14:18:14Z (GMT) No. of bitstreams: 1 garcia_phs_me_jabo.pdf: 2204900 bytes, checksum: 6acbf410866645d13616b8dc7610bd26 (MD5) / Made available in DSpace on 2016-08-16T14:18:14Z (GMT). No. of bitstreams: 1 garcia_phs_me_jabo.pdf: 2204900 bytes, checksum: 6acbf410866645d13616b8dc7610bd26 (MD5) Previous issue date: 2016-07-13 / O exame ultrassonográfico convencional tem baixa especificidade para detecção de alterações difusas, no entanto, o aumento da ecogenicidade renal é um dos achados mais comuns em cães e gatos com nefropatia. O objetivo deste estudo foi descrever a técnica de elastografia por irradiação da força de impulso acústico (ARFI) na avaliação dos rins de gatos adultos hígidos, e determinar os valores de referência. Foram incluídos neste trabalho dez gatos de pelo curto, adultos e saudáveis. Após sedação, foi realizada uma ampla tricotomia abdominal, para a realização do exame ultrassonográfico. O exame convencional, em Modo B foi realizado com um transdutor linear de 9,0 MHz usando equipamento de ultrassom ACUSON S2000 / SIEMENS (Siemens, Munique, Alemanha). A ecogenicidade, ecotextura, o tamanho e contornos renais foram avaliados. Com o mesmo transdutor, a elastografia foi realizada utilizando software para comparação das análises qualitativa e quantitativa do método. A elastografia qualitativa detectou a presença de deformidades e as velocidades de cisalhamento em diferentes locais (cranial, média e caudal) das regiões cortical e medular em ambos os rins. Os achados ultrassonográficos foram considerados normais em todos os gatos, sem alterações em arquitetura ou ecogenicidade renal. A elastografia qualitativa demonstrou que o córtex renal era deformável e apresentou áreas cinza escuro homogêneas; pelve renal tinha pouca rigidez (branca); e da medula mostrou um padrão de mosaico. Os resultados de velocidade de onda de cisalhamento foram diferentes em regiões cranial, média e caudal do córtex e medula: 2,46 m/s ± 0,45 m/s; 2,46m/s ± 0,48 m/s e 2, 37 m/s ± 0, 42 m/s (P = 0,795) no córtex e 1,61 m/s ± 0,69 m/s, 1,75 m/s ± 0,66 m/s e 2,00 m/s ± 0,55 m/s (P = 0,156) na medula, respectivamente. A ARFI quantitativa e qualitativa do rim em gatos adultos foi realizada facilmente e este estudo forneceu valores de referência para a caracterização da normalidade do parênquima renal em gatos hígidos. / Conventional ultrasonography has low specificity to detect diffuse changes, however, increased renal echogenicity is one of the most common findings in dogs and cats with nephropathy. The objective of this study was to describe elastography by acoustic radiation force impulse (ARFI) in the assessment of adult cats' kidneys and determine reference values. Ten healthy adults short hair cats were included. After sedation, abdominal hair was clipped in order to perform ultrasound exams. The conventional examination (B-mode) was performed with a 9.0 MHz linear array transducer ultrasound equipment using ACUSON S2000/Siemens (Siemens, Munich, Germany). Echogenicity, echotexture, size and contours of each kidney were evaluated. With the same transducer, elastography was performed using a software that compares qualitative and quantitative analysis. Qualitative elastography detected deformities and shear wave velocity rates in different portions (cortical and medulla' cranial, media and caudal regions). The sonographic findings were normal in all cats, with no changes in renal architecture or echogenicity. Qualitative elastography showed that renal cortex was softer with dark gray homogeneous areas; renal pelvis presented lower stiffness (white); and medulla showed a mosaic pattern. Shear wave velocities were obtained in cranial, medial, and caudal regions of the cortex and medulla: 2.46 m/s ± 0.45m/s; 2,46m/s ± 0.48 m/ s 2,37 m/s ± 0, 42 m/s (P = 0.795) in the cortex and 1.61 m/s ± 0.69 m/s 1.75 m/s ± 0.66 m/s and 2.00m/s ± 0.55m/s (P = 0.156) in medulla, respectively. Quantitative and qualitative ARFI kidney in adult cats was easily accomplished and this study was able to provide values for the characterization of the normal renal parenchyma in healthy cats.

Este trabalho apresenta uma análise sobre um novo método de formação de imagem, utilizando aparelhos de ultra-som a elastografia. Esta técnica baseia-se no fato de que quando um meio elástico, como o tecido, é deformado por uma tensão constante e uniaxial, todos os pontos no meio possuem um nível de deformação longitudinal cujo componente principal está ao longo do eixo de deformação. Se elementos do tecido possuem um módulo elástico diferente dos demais, a deformação nestes elementos será relativamente maior ou menor. Elementos mais rígidos geralmente deformam-se menos. Desta forma, pode-se mapear e identificar estruturas com diferentes níveis de dureza. A comparação entre os mapas de RF de pré e pós-deformação foi realizada pela técnica de block matching. Esta técnica consiste em comparar regiões, ou kernels, no mapa de pré-deformação com regiões de mesmo tamanho no mapa de pós-deformação. Esta comparação é feita pela minimização de uma função custo. Nesta técnica, o tamanho do kernel, é um dos principais parâmetros para melhorar a precisão das medidas de deslocamento. O principal objetivo neste trabalho é aperfeiçoar o algoritmo de block matching visando melhorar a precisão da determinação de deslocamento em técnicas de deformação dinâmica e estática, mantendo o custo computacional baixo. Para isto, foram utilizados phantoms com e sem inclusões mais duras que o meio. Os phantoms foram submetidos a deformações estáticas e dinâmicas. Foi possível determinar o comportamento destes phantoms sob estas formas de deformação, e as faixas de kernel e funções custo que forneceram os melhores resultados. Também foram gerados elastogramas do phantom com inclusão. Estas imagens permitiram avaliar a influência dos diferentes kernels sobre a resolução dos elastogramas e a capacidade em diferenciar a lesão do tecido circundante. Comparando os elastogramas obtidos sobre deformação dinâmica, utilizando os kernels que apresentaram o melhor desempenho, com as respectivas imagens em modo B, pôde-se observar que a inclusão estava clara e bem delimitada. / This work provides an analysis about a new method for image formation using ultrasound devices elastography. This technique is based on the fact that when an elastic medium, as the tissue, is deformed under a constant and directional stress, all the points in the medium have a deformation level whose main component is along the deformation axis. If tissues elements have different elastic modules, the deformation in these elements will be higher or lower. Normally harder elements have lower deformations. In this way, one can detect and identify structures with different elastic levels. The comparisons between the pre and post-deformation RF maps were done by the block matching technique. This technique is based on the comparison of regions, or kernels, in the pre-deformation maps with regions of the same size in the post-deformation map. This is done by the minimization of a cost function. In this technique, the kernel size is one of the most important parameters to obtain better resolution and precision in the displacement measurements. The goal of this work is to optimize the block matching algorithm to improve the displacement estimates precision in both dynamic and static deformations, while keeping a low computational cost. To obtain this, we used phantoms with and without inclusions harder than the medium. These phantoms were submitted to both static and dynamic deformations. It was possible to estimate the behavior of these phantoms under these deformations, and the kernel range and cost functions that provided the best results. Also, we generated the elastograms of the phantom with the inclusion. These images allowed us to evaluate the influence of the different kernel sizes under the elastograms resolution and their capability in differentiate the lesion from the embedding tissue. Comparing the elastograms obtained under dynamic deformation that had the best performance, with the B mode images, we could conclude that the inclusion was well delimited and clear.

The Achilles tendon is the largest tendon in the human body, which elastically stores and releases energy to facilitate walking and running. Tendons can suffer from a range of pathologies, most notably that of complete rupture, which affects athletes, physically active workers and the aged. There is a growing demand for in vivo methods of objectively measuring tendon health for aiding diagnosis, monitoring therapy and for assessment of new treatments. Knowledge of the changes in mechanical properties during the healing process is also limited and new methods to accurately and consistently estimate these could provide insights into the healing process and guide future research efforts. This thesis presents the development and use of 2D ultrasound elastography, a quantitative strain estimation imaging technique, as a tool to measure changes in the tensile mechanical properties of the Achilles tendon. This technique performs frame-to-frame block matching of image texture to track motion in an ultrasound signal sequence and create a strain estimation field from the spatial derivative of the motion. Elastography in the image-lateral direction of sagittal plane scans is of particular interest as this is in line with the longitudinal axis of the tendon, but presents extra accuracy issues from out of plane motion and lower image spatial resolution. Tendon rupture also presents unique problems to image acquisition and analysis- patient pain and safety are important considerations and disruption of the ultrasound texture can make 2D motion tracking more difficult. A new 2D elastography block matching algorithm, named `AutoQual', was developed to enable accurate tracking of motion in the image-lateral direction and reduce the impact of artefacts and errors common with damaged Achilles tendons image sequences. It was shown to outperform a multiscale block matching method when tested using ultrasound sequences from in vivo and gelatine phantom experiments. The input parameters of this algorithm were then optimised using the phantom data for benchmarking. The AutoQual algorithm was then used to analyse ultrasound sequences from a 24-week longitudinal study of 21 subjects with ruptured Achilles tendons to assess lateral, axial and principal strains during controlled passive motion of the foot or axial palpation of the ultrasound probe. Lateral and principal strains from controlled dorsiflexion were shown to be more repeatable and more sensitive to change than axial strains with manual palpation. This experience with lateral strain imaging from ruptured Achilles tendons gave an increased knowledge of the strain imaging artefacts and features that can occur. These are described in detail in order that they may be further mitigated in quantitative analysis by optimising acquisition protocols, further amendment of the block tracking algorithm, or exclusion of erroneous areas when selecting regions of interest. Regularisation is a potential solution to some common artefacts such as discontinuities from poor tracking in shadow regions. Regularisation of the lateral displacement fields is investigated using 2D bicubic smoothing splines. The regularisation parameters used are shown to have minimal effect on quantitative analysis and can aid visual clarity or reduce artefacts within certain settings. However, regularisation was also shown to cause large errors when parameters were set more aggressively. Finally, it is identified that cumulative lateral strain measurement of the Achilles and other tendons is feasible but that future work is needed to further improve the quality of force and cross sectional area measurements in order to infer mechanical properties accurately. Repeatable high force motion protocols also need to be developed to measure healthy tendons and to ensure comparable results between different patients and research groups.

L’élastographie est une modalité d'imagerie médicale émergente qui permet de mesurer les propriétés mécaniques des tissus moux humains. Ces mesures peuvent servir de biomarqueurs pour l'amélioration de la prise en charge des maladies, du diagnostic précoce et de l'évaluation de la sévérité, au suivi de la réponse au traitement. Parmi les différentes approches de l’élastographie, l'élastographie par Résonance Magnétique (ERM) et l’élastographie ultrasonore par ondes de cisaillement (Supersonic Shear Imaging (SSI)) suscitent des intérêts particuliers. Ces deux modalités ont été largement étudiées pour des applications cliniques multiples. Toutefois, chaque modalité repose sur des conditions d'acquisition et de reconstruction différentes et caractérisées par leur propres limites qui peuvent induire des biais de mesure intra-et inter-modalité et donc entraver l'interchangeabilité des deux modalités pour des applications cliniques. Dans un premier temps, ma thèse a porté sur l'identification des biais de mesure entre ERM et SSI. Grâce à une comparaison méthodologique approfondie des deux modalités, nous avons identifié les différentes caractéristiques de fréquence des ondes de cisaillement générées par les deux modalités et les contraintes spécifiques de reconstruction, en particulier en ERM, comme les principales sources de biais de mesure entre les deux modalités. Dans un deuxième temps, une étude de simulation a étéeffectuée afin de caractériser l'influence des conditions d'acquisition et de reconstruction sur l'exactitude et la précision des mesures d’ERM. Nous avons établi des abaci in silico pour identifier le nombre de voxels par longueur d'onde idéal (rapport λ/a) pour obtenir des mesures ERM exactes et précises. En outre, nous avons montré que le rééchantillonnage pouvait s’avérer efficace afin de répondre aux critères de λ/a favorable lorsque le nombre de voxels par longueur d'onde initial était mal défini. Les résultats finaux, qui sont généralement calculés à partir des trois directions d'encodage, peuvent être améliorés grâce à des stratégies de pondération appropriées qui reposent sur le champ rotationnel du déplacement de l'onde de cisaillement. Pour la modalité SSI, nous avons utilisé le paramètre de qualité fourni par le fabricant afin d’éliminer raisonnablement des résultats peu fiables et améliorer encore la qualité des mesures. Ensuite nous avons intégré les stratégies d'optimisation proposées dans chaque modalité pour effectuer des études de comparaison expérimentales impartiales entre ces deux modalités. Des études in vitro ont été effectuées sur des fantômes commerciaux calibrés et aussi des fantômes à la base de l'alcool polyvinylique. Des résultats expérimentaux confirment bien ceux de la simulation. Des mesures SSI et ERM sont en bon accord quand des biais reliés à la théorie, l'expérimentation et la reconstruction sont minimisés. Des études in vivo ont été ensuite effectuées sur le foie de deux volontaires sains. On a constaté que lorsque le foie est quasi-élastique, des mesures SSI et ERM avec la qualité optimisée concordent bien les uns et les autres, ils sont donc interchangeables. Dans le cas du tissu hépatique viscoélastique, des mesures SSI et ERM dépendent de la fréquence. Dans ce contexte, des mesures ERM et SSI pour la même fréquence spécifique sont nécessaires pour réaliser une comparaison impartiale entre des deux modalités. / Elastography is an emerging medical imaging modality which permits to measure the mechanical properties of human soft tissue. The measured mechanical properties can serve as potential biomarkers for improving the management of diseases, from early diagnosis, to severity evaluation and therapy response monitoring. Among different approaches, Magnetic Resonance Elastography (MRE) and Supersonic Shear Imaging (SSI) have shown particular interests. The two modalities have been widely investigated for multiple clinical applications. However, each modality is challenged by specific acquisition and reconstruction conditions which may induce intra- and inter-modality measurement biases and hence impede the interchangeability of the two modalities. The first part of my thesis focused on identifying the measurement biases between MRE and SSI. Through a thorough methodological comparison study, we recognized different frequency characteristics of generated shear waves for the two modalities and modality specific reconstruction validity issues as the main sources for the measurement biases between the two modalities. Then through a dedicated simulation study, we established an in silico abaci to identify the favorable range of number of voxels per wavelength which leads to accurate and precise MRE. Moreover, resampling was proven effective to regulate poorly defined number of voxels per wavelength to the favorable range. The overall outcome, which is usually computed from the three acquired motionencoded directions, may further be improved by appropriate weighting strategies that are based on curl of shear displacement field. For SSI, we referred to the quality parameter provided by the manufacturer to reasonably eliminate unreliable results so as to further improve the measurement quality. After establishing the potential measurement biases between MRE and SSI, we incorporated the proposed quality optimization strategies into both modalities in order to perform unbiased experimental comparison studies between the two modalities. First, in vitro studies were carried out on commercial calibrated phantoms as well as home-made polyvinyl alcohol phantoms. Experimental results corroborate well the simulation findings. MRE and SSI measurements agree well witheach other when theory, experiment, and reconstruction biases are minimized. In vivo studies were then performed on the livers of two healthy volunteers. We found that when the liver is quasi-elastic, the quality-guided MRE and SSI measurements agree well with each other and hence are interchangeable. In case of viscoelastic liver tissue, both MRE and SSI measurements are frequency dependent. Thus frequency-specific measurements are essential for cross-validating the measurements of these two modalities.

Shear Wave Elastography (SWE) is an ultrasound based technique which is able to measure tissue stiffness through the speed of induced shear waves. Tissue stiffness is often related to pathological conditions and detecting mechanical changes can help the recognition of potential diseases. The clinical use of SWE is limited to isotropic tissue due to the difficulty in assessing a theoretical model for more complex tissue and this project therefore aimed to evaluate the possibility of obtaining a full mechanical characterization of a transversely isotropic (TI) phantom with dual-probe SWE. A TI hydrogel phantom was developed and mechanical tests were performed to verify its anisotropy and determine the elastic moduli in both the perpendicular and longitudinal directions. Shear moduli were estimated using conventional and dual-probe SWE comparing the results to theoretical pure-transverse (PT) and quasi-transverse (QT) wave propagation modes. Both mechanical and SWE tests showed that the phantoms were transversely isotropic ET/EL=0.81. Moreover, multiple wave propagation modes calculated with dual-probe SWE showed a good agreement with the theoretical curves and indicated the possibility of measuring all the elasticity constants needed to fully characterize an incompressible, TI tissue with dual-probe SWE.

Magnetic resonance elastography (MRE) Is capable of non-invasively quantifying the mechanical properties of skeletal muscles in vivo. This information can be clinically useful to understand the effects of pathologies on the mechanical properties of muscle and to quantify the effects of treatment. Advances in inversion algorithms quantify muscle anisotropy in two-dimensional (2D) and three-dimensional (3D) imaging. Databases of the shear stiffness of skeletal muscle have been presented in the relaxed and contracted states in the upper extremity (biceps brachii, flexor digitorum profundus, and upper trapezius), distal leg muscles (tibialis anterior, medial gastrocnemius, lateral gastrocnemius, and trapezius), and proximal leg muscles (vastus lateralis, vastus medialis, and sartorius). MRE measurements have successfully validated a mathematical model of skeletal muscle behavior in the biceps brachii, correlated to electromyographic data in the distal leg muscles and quantified the effects of pathologies on the distal and proximal leg muscles. Future research efforts should be directed toward improving one-dimensional (1D) and 3D MRE data acquisition and image processing, tracking the effects of treatment on pathologic muscle and correlating the shear stiffness with clinical measurements.

Background: Before making any treatment decisions for patients with non-small cell lung cancer (NSCLC), it is crucial to determine whether the cancer has spread to the mediastinal lymph nodes (LNs). The preferred method for mediastinal staging is Endobronchial Ultrasound Transbronchial Needle Aspiration (EBUS-TBNA). However, EBUS-TBNA has been reported to generate inconclusive results as much as 40% of the time. Since this jeopardizes good patient care, there is near-universal consensus on the need to develop and study a novel method for LN staging. Recent research has shown that AI and deep learning are used to accurately interpret images with comparisons to clinicians in radiology, pathology, and cardiology. Additionally, EBUS-Elastography is a novel modality which could be used as an adjunct to EBUS-TBNA for LN staging. This technology uses impedance ultrasonography to measure tissue stiffness. Methods: There are three parts to this thesis. The first part involved the training, validating, and testing NeuralSeg, a deep neural network, to predict LN malignancy based on B-mode EBUS-TBNA images. The second part of this thesis involves EBUS-Elastography, defining the blue colour threshold and the optimal SAR cut-off value based on the blue threshold that most accurately distinguished benign and malignant LN. Finally, this thesis's third part involves validating part II's findings. Results: Part I resulted in an overall accuracy of 80.63% (76.93% to 83.97%), a sensitivity of 43.23% (35.30% to 51.41%), a specificity of 96.91% (94.54% to 98.45%), a positive predictive value of 85.90% (76.81% to 91.80%), a negative predictive value of 79.68% (77.34% to 81.83%), and an AUC of 0.701 (0.646 to 0.755). Part II Level 60 was chosen as the blue threshold with an AUC of 0.89 (95% CI: 0.77-1.00), and the optimal SAR cut off was found to be 0.4959 with a sensitivity of 92.30% (95% CI: 62.10% to 99.60%) and a specificity of 76.50% (95% CI: 49.80% to 92.20%). Using the blue threshold and SAR cut-off, the results of part III resulted in an overall accuracy of 70.59% (95% (CI) 63.50% to 77.01%), the sensitivity of 43.04% (CI: 31.94% to 54.67%), and a specificity of 90.74% (CI: 83.63% to 95.47%). Conclusion: It was observed that both AI and AI-powered EBUS-Elastography achieved high specificities on larger sample sizes, indicative that these methods may be helpful in identifying LN malignancy. However, due to the novelty of these technologies, more extensive multi-centre studies must be conducted before these processes can be standardized. / Thesis / Master of Health Sciences (MSc) / Non-Small Cell Lung Cancer (NSCLC) treatment decisions are made using vital information by performing biopsies to collect tissue from the lymph nodes near the lungs. The current method is called Endobronchial Ultrasound Transbronchial Needle Aspiration (EBUS-TBNA), which involves a scope with a fine needle attached to it. This scope is led down the airway and guided by ultrasound to obtain the tissue needed to determine whether the lymph nodes have cancerous tissue. If the lymph nodes contain cancerous tissue, the patient may need chemotherapy; however, lung surgery may be the best treatment option if they do not. Many factors impact how successfully these tissue samples can be obtained, such as the skill and experience of the surgeon. These factors often lead to inconclusive results, making it difficult to make correct treatment decisions. Novel technologies such as Artificial Intelligence and Elastography are being used to diagnose lung cancer by interpreting images and providing information on tissue stiffness. We trained an Artificial Intelligence program to predict malignancy based on EBUS-TBNA images. Additionally, we trained the AI program to analyze Elastography images to aid us in understanding the relationship between the colour pattern of the elastography images and cancerous tissue. This thesis assesses how these novel technologies contribute to lung cancer diagnosis.