3D-MedTranCSGAN: 3D Medical Image Transformation using CSGAN

• Published in: Computers in biology and medicine 2023-02, Vol.153, p.106541-106541, Article 106541
• Main Authors: Poonkodi, S., Kanchana, M.
• Format: Article
• Language: English
• Subjects: 3D UNet; 3DCascadeNet; Automation; Computed tomography; Computer vision; Computer vison; CSGAN; Datasets; Deep learning; Encoding-Decoding; Generative adversarial networks; Image enhancement; Image processing; Image Processing, Computer-Assisted - methods; Image reconstruction; Imaging, Three-Dimensional; Medical image transformation; Medical imaging; Movement; Neural networks; PatchGAN; Positron emission; Signal-To-Noise Ratio; Synthesis; Three dimensional imaging; Three dimensional models; Transformations
• ISSN: 0010-4825; 1879-0534
• DOI: 10.1016/j.compbiomed.2023.106541

Computer vision techniques are a rapidly growing area of transforming medical images for various specific medical applications. In an end-to-end application, this paper proposes a 3D Medical Image Transformation Using a CSGAN model named a 3D-MedTranCSGAN. The 3D-MedTranCSGAN model is an integration of non-adversarial loss components and the Cyclic Synthesized Generative Adversarial Networks. The proposed model utilizes PatchGAN's discriminator network, to penalize the difference between the synthesized image and the original image. The model also computes the non-adversary loss functions such as content, perception, and style transfer losses. 3DCascadeNet is a new generator architecture introduced in the paper, which is used to enhance the perceptiveness of the transformed medical image by encoding-decoding pairs. We use the 3D-MedTranCSGAN model to do various tasks without modifying specific applications: PET to CT image transformation; reconstruction of CT to PET; modification of movement artefacts in MR images; and removing noise in PET images. We found that 3D-MedTranCSGAN outperformed other transformation methods in our experiments. For the first task, the proposed model yields SSIM is 0.914, PSNR is 26.12, MSE is 255.5, VIF is 0.4862, UQI is 0.9067 and LPIPs is 0.2284. For the second task, the model yields 0.9197, 25.7, 257.56, 0.4962, 0.9027, 0.2262. For the third task, the model yields 0.8862, 24.94, 0.4071, 0.6410, 0.2196. For the final task, the model yields 0.9521, 33.67, 33.57, 0.6091, 0.9255, 0.0244. Based on the result analysis, the proposed model outperforms the other techniques. •3D-MedTranCSGAN model transforms the PET to CT images to enhance medical images in datasets.•CSGAN is Cyclic Synthesized GAN, first time this model is utilised for medical image transformation.•Proposed model performs reconstruction of CT to PET, correction and removing noise in medical images.•For Generator and Discriminator network utilised 3D-CascadeNet and PatchGAN respectively.•Comparative study is done between proposed and other GAN models.