A review of image processing and analysis of computed tomography images using deep learning methods

Area of Science:

• Artificial Intelligence
• Medical Imaging
• Radiotherapy

Background:

• Deep learning (DL) methods, especially artificial neural networks, have advanced significantly, excelling in complex data analysis.
• Healthcare increasingly utilizes DL for image processing due to the field's reliance on imaging data.
• Radiotherapy heavily depends on anatomical and functional images, such as Computed Tomography (CT).

Purpose of the Study:

• To review deep learning methodologies and neural network structures.
• To connect these DL concepts to medical CT image processing in radiotherapy.
• To focus on image enhancement and analysis stages within radiotherapy.

Main Methods:

• Review of deep learning methodologies, including neural network types and architectures.
• Application of DL concepts to medical CT image processing for radiotherapy.
• Examination of specific image enhancement and analysis techniques.

Main Results:

• Deep learning excels at extracting patterns from large, complex datasets like medical images.
• DL techniques are applicable to various radiotherapy CT image processing tasks.
• Specific applications include image denoising, super-resolution, generation, registration, and segmentation.

Conclusions:

• Deep learning offers powerful tools for advancing medical CT image processing in radiotherapy.
• Understanding DL methodologies is crucial for optimizing radiotherapy workflows.
• Further research and application of DL in radiotherapy imaging are warranted.