Evaluating cross-modality domain adaptation for medical imaging

AI Quick Summary

Improving medical diagnosis by evaluating cross-modality domain adaptation in medical imaging. Initial situation and problem definition:Medical imaging provides different tools and procedures for imaging the interior of the human body. Examples of these modalities include CTs or MRIs, to cite some. Analyzing the human body by using different modalities helps to make better health diagnosis. However, the image appearance adaption might be challenging due to the limited amount of data, which might also exhibit larger variability.Aim of the work and expected results:The aim of this work is to study and to develop an image appearance adaption method to translate between two different medical imaging modalities. We aim at obtaining realistic-looking appearance with semantic consistency for paired data. This work has three main outcomes. First, we focus on studying existing approaches and reproducing their results. Second, we target the development of novel image translation architectures/modules by using domain-specific knowledge. Desired methods and procedure:The first stage of the project involves the selection of the proper cross-domain datasets. Next, we focus on reproducing existing approaches from available github repositories. The goal is to understand the limitations of existing methods. The second stage will involve tackling the weaknesses of existing approaches by exploring different blocks/modules and also by using knowledge from the medical literature. Every week, there will be a meeting, where the student will provide insights of the achievements via presentations, jupyter notebooks, etc. Discussions about next steps and guidance will be provided by the mentor. The source code will be developed in python/pytorch and will be privately stored in github. The. code can be built from scratch or from existing repositories. The bachelor work will be written in parallel as the experiments are being conducted.Creativity, variants, innovation: As domain-adaptation for digital health tasks is gaining more attention, there is the possibility to be pioneer in a field which has a direct impact on the health system. Besides the technical aspects, it gives the chance to the student to learn more about the digital health domain.

Project Idea Metadata

• Project Idea Name: Evaluating cross-modality domain adaptation for medical imaging
• Date: 11/25/2022 9:33:38 PM
• Administrators:

Project Idea Description

Initial situation and problem definition:

Medical imaging provides different tools and procedures for imaging the interior of the human body. Examples of these modalities include CTs or MRIs, to cite some. Analyzing the human body by using different modalities helps to make better health diagnosis. However, the image appearance adaption might be challenging due to the limited amount of data, which might also exhibit larger variability.

Aim of the work and expected results:

The aim of this work is to study and to develop an image appearance adaption method to translate between two different medical imaging modalities. We aim at obtaining realistic-looking appearance with semantic consistency for paired data. This work has three main outcomes. First, we focus on studying existing approaches and reproducing their results. Second, we target the development of novel image translation architectures/modules by using domain-specific knowledge.

Desired methods and procedure:

The first stage of the project involves the selection of the proper cross-domain datasets. Next, we focus on reproducing existing approaches from available github repositories. The goal is to understand the limitations of existing methods. The second stage will involve tackling the weaknesses of existing approaches by exploring different blocks/modules and also by using knowledge from the medical literature. Every week, there will be a meeting, where the student will provide insights of the achievements via presentations, jupyter notebooks, etc. Discussions about next steps and guidance will be provided by the mentor. The source code will be developed in python/pytorch and will be privately stored in github. The. code can be built from scratch or from existing repositories. The bachelor work will be written in parallel as the experiments are being conducted.

Creativity, variants, innovation:

As domain-adaptation for digital health tasks is gaining more attention, there is the possibility to be pioneer in a field which has a direct impact on the health system. Besides the technical aspects, it gives the chance to the student to learn more about the digital health domain.

Improving medical diagnosis by evaluating cross-modality domain adaptation in medical imaging.