3D reconstruction of porous material based on 2D images using conditional generative adversarial neural networks (CGANs)

The School of Computing at the University of Leeds is offering a funded Ph.D. opportunity for students (international and UK-based) interested in the field of 3D image analysis and deep learning. The project aims to develop a framework for the 3D reconstruction of biological and geological porous materials, based on 2D images, using conditional generative adversarial neural networks (CGANs). Porous materials have unique properties, including porosity, permeability, surface area, and mechanical stiffness, that are related to their complex 3D structure. However, obtaining a full 3D representation of these materials can be challenging and time-consuming, making the use of computational methods like deep learning a more efficient and cost-effective approach.<br /> <br /> The Ph.D. project will focus on the use of CGANs to reconstruct 3D images of biological and geological porous materials from 2D images. The performance of the developed framework will be evaluated using metrics such as reconstruction accuracy, computational efficiency, image quality, and physical properties. <br /> <br /> The ideal candidate for this Ph.D. project should hold a Master&rsquo;s degree or equivalent in computer science, geoscience, mathematics, physics, biomedicine, or a related discipline. Familiarity with 3D image analysis, deep learning, and programming languages like Python or Matlab and packages such as TensorFlow or PyTorch is necessary. A motivation to learn about porous material physics or prior experience in this field is favourable.<br /> <br /> The successful completion of this Ph.D. project is expected to have a significant impact on the study of biological and geological porous materials. The CGAN-based framework developed in this project will reduce the need for extensive and expensive 3D imaging techniques, making it applicable in areas such as medical imaging, material science, biomedicine, environmental science, and geoscience. Furthermore, the findings of the project could be used to design variations of biological tissues that can serve specific purposes or exhibit certain behaviours which can be used as input for 3D printing artificial bone tissues.<br />

<p style="margin-bottom:11px"><strong>Full title</strong></p> <p>3D reconstruction of biological and geological porous material based on 2D images using conditional generative adversarial neural networks (CGANs)</p> <p><strong>Background</strong></p> <p>The study of biological and geological porous materials is of great importance in a variety of fields, including geology, biology, environmental science, and medicine. Porous materials have unique properties that are related to their complex 3D structure, including porosity, permeability, surface area, and mechanical stiffness. However, obtaining a full 3D representation of these materials can be challenging and time-consuming due to the need for extensive and expensive imaging techniques.</p> <p>The use of computational methods, such as deep learning, can provide a more efficient and cost-effective approach to the study of these materials. In particular, generative adversarial networks (GANs) have shown promising performance in 2D and 3D image generation tasks and can be used to reconstruct 3D images from 2D images.</p> <p><strong>Introduction</strong></p> <p>This Ph.D. project at the School of Computing, University of Leeds, aims to develop a framework for the 3D reconstruction of biological and geological porous materials based on 2D images using conditional generative adversarial neural networks (CGANs). CGANs are a variant of generative adversarial networks (GANs) where the generator and discriminator are conditioned on additional information, such as labels or images. CGANs have shown promising results in various image generation tasks, including image-to-image translation, super-resolution, and style transfer. CGANs allow for the generation of 3D images that are conditioned on the input 2D images and have certain properties of the porous material. This allows for the reconstruction of 3D images that are not only visually similar to the original 2D images but have tailored physical properties.</p> <p><strong>Research Methods and Techniques</strong></p> <p>The proposed Ph.D. project will use conditional generative adversarial networks (CGANs) to reconstruct 3D images of biological and geological porous materials from 2D images. In particular, meniscal and placental tissues will be studied as biological samples and organic-rich porous rocks will be investigated as geological samples. The student will design and train deep neural networks to generate 3D images that are visually similar to the input 2D images while having certain physical qualities. The student will also be expected to evaluate the performance of the CGAN-based framework using metrics such as reconstruction accuracy, computational efficiency, and image quality.</p> <p>The student will also be expected to compare the results of the CGAN-based framework to other state-of-the-art methods for 3D reconstruction and to conduct an in-depth analysis of the properties of the reconstructed images. This analysis may include a study of the influence of different training strategies and network architectures on the performance of the framework.</p> <p><strong>Eligibility</strong></p> <p>The ideal candidate for this Ph.D. project should hold a Master&rsquo;s degree or equivalent in computer science, geo-science, mathematics, physics, biomedicine, or a related discipline. The candidate should be familiar with 3D image analysis, deep learning, and programming languages like Python or Matlab, and packages such as TensorFlow or PyTorch is necessary. A motivation to learn about porous material physics or prior experience in this field is favorable.</p> <p><strong>Potential Impact</strong></p> <p>The successful completion of this Ph.D. project is expected to have a significant impact on the study of biological and geological porous materials. The CGAN-based framework developed in this project will reduce the need for extensive and expensive 3D imaging techniques. The framework is also suitable for designing variations of a biological tissue that may serve a specific purpose or shows certain behavior. This would be highly applicable for tasks such as 3D printing artificial bone tissues. In summary, the findings of this project are expected to have applications in other areas, such as medical imaging, material science, biomedicine, environmental science, and geoscience. &nbsp;</p> <p><strong>Research Group</strong></p> <p>The prospective student will initiate their work in Data Flow Lab at the University of Leeds (<a href="http://www.dataflowlab.org">www.dataflowlab.org</a>).&nbsp;Data Flow Lab is an interdisciplinary research group that tackles real-world problems of micro-scale fluid/solid interactions by harnessing the power of data science. We develop computationally-efficient image-based techniques to investigate the world of flow in micro-structures from subsurface water and energy resources to the amazing world of living cells and tissues.</p> <p>For more information and to express interest be in touch with Dr. Arash Rabbani at &lsquo;<a href="mailto:a.rabbani@leeds.ac.uk">a.rabbani@leeds.ac.uk&rsquo;</a> with the email subject starting with the word &lsquo;CGAN&rsquo;.&nbsp;&nbsp;</p>

<p>Formal applications for research degree study should be made online through the&nbsp;<a href="https://www.leeds.ac.uk/research-applying/doc/applying-research-degrees">University&#39;s website</a>. Please state clearly in the Planned Course of Study Section that you are applying for&nbsp;<em><strong>PHD Computing FT&nbsp;</strong></em>and in the research information section&nbsp;that the research degree you wish to be considered for is <em><strong>3D reconstruction of porous material based on 2D images using conditional generative adversarial neural networks (CGANs)</strong></em>&nbsp;as well as&nbsp;<a href="https://eps.leeds.ac.uk/computing/staff/11422/dr-arash-rabbani">Dr Arash Rabbani</a> as your proposed supervisor.</p> <p>If English is not your first language, you must provide evidence that you meet the University&#39;s minimum English language requirements (below).</p> <p><em>As an international research-intensive university, we welcome students from all walks of life and from across the world. We foster an inclusive environment where all can flourish and prosper, and we are proud of our strong commitment to student education. Across all Faculties we are dedicated to diversifying our community and we welcome the unique contributions that individuals can bring, and particularly encourage applications from, but not limited to Black, Asian, people who belong to a minority ethnic community, people who identify as LGBT+ and people with disabilities. Applicants will always be selected based on merit and ability.</em></p> <p class="MsoNoSpacing">Applications will be considered on an ongoing basis. &nbsp;Potential applicants are strongly encouraged to contact the supervisors for an informal discussion before making a formal application. &nbsp;We also advise that you apply at the earliest opportunity as the application and selection process may close early, should we receive a sufficient number of applications or that a suitable candidate is appointed.</p> <p>Please note that you must provide the following documents in support of your application by the closing date of 25 May 2023:</p> <ul> <li>Full Transcripts of all degree study or if in final year of study, full transcripts to date</li> <li>Personal Statement outlining your interest in the project</li> <li>CV</li> <li>Funding information:&nbsp; School of Computing</li> </ul>

Applicants to research degree programmes should normally have at least a first class or an upper second class British Bachelors Honours degree (or equivalent) in an appropriate discipline. The criteria for entry for some research degrees may be higher, for example, several faculties, also require a Masters degree. Applicants are advised to check with the relevant School prior to making an application. Applicants who are uncertain about the requirements for a particular research degree are advised to contact the School or Graduate School prior to making an application.

The minimum English language entry requirement for research postgraduate research study is an IELTS of 6.0 overall with at least 5.5 in each component (reading, writing, listening and speaking) or equivalent. The test must be dated within two years of the start date of the course in order to be valid. Some schools and faculties have a higher requirement.

<p class="MsoNoSpacing">A highly competitive School of Computing Studentship consisting of the award of fees at the UK fee rate of &pound;4,596 or Non-UK fee rate of &pound;25,500 (currently for 2022/23 academic session) with a maintenance grant (currently &pound;17,668 for session 2022/23) for 3.5 years.</p> <p>This opportunity is open to all applicants. All candidates will be placed into the School of Computing Studentship Competition and selection is based on academic merit.<br /> <br /> <strong>Important:&nbsp;</strong> Any costs associated with your arrival at the University of Leeds to start your PhD including flights, immigration health surcharge/medical insurance and Visa costs are <strong>not</strong> covered under this studentship.</p> <p>Please refer to the&nbsp;<a href="https://www.ukcisa.org.uk/">UKCISA</a>&nbsp;website for&nbsp;information regarding Fee Status for Non-UK Nationals.</p>

<p>For further information regarding your application, please contact Doctoral College Admissions:<br /> e:&nbsp;<a href="mailto:phd@engineering.leeds.ac.uk">phd@engineering.leeds.ac.uk</a>, t: +44 (0)113 343 5057.</p> <p>For further information regarding the project, please contact:<br /> Dr Arash Rabbani, e:&nbsp;<a href="mailto:h.e.wang@leeds.ac.uk">a.rabbani@leeds.ac.uk</a></p>