Influence of High-Performance Image-to-Image Translation Networks on Clinical Visual Assessment and Outcome Prediction: Utilizing Ultrasound to MRI Translation in Prostate Cancer

TL;DR

This study evaluates various image-to-image translation networks for converting ultrasound to MRI in prostate cancer, highlighting the strengths of 2D-Pix2Pix in feature detection and classification accuracy, with implications for clinical practice.

Contribution

The paper introduces a comprehensive analysis of I2I networks in clinical settings, identifying 2D-Pix2Pix as superior in low-level feature detection and demonstrating improved classification using synthetic MRI data.

Findings

2D-Pix2Pix achieved the highest SSIM (~0.855) among tested networks.

Synthetic MRI-based classification outperformed ultrasound-based methods with ~0.93 accuracy and AUC.

Half of the radiomic features were lost during translation, indicating room for improvement.

Abstract

Purpose: This study examines the core traits of image-to-image translation (I2I) networks, focusing on their effectiveness and adaptability in everyday clinical settings. Methods: We have analyzed data from 794 patients diagnosed with prostate cancer (PCa), using ten prominent 2D/3D I2I networks to convert ultrasound (US) images into MRI scans. We also introduced a new analysis of Radiomic features (RF) via the Spearman correlation coefficient to explore whether networks with high performance (SSIM>85%) could detect subtle RFs. Our study further examined synthetic images by 7 invited physicians. As a final evaluation study, we have investigated the improvement that are achieved using the synthetic MRI data on two traditional machine learning and one deep learning method. Results: In quantitative assessment, 2D-Pix2Pix network substantially outperformed the other 7 networks, with an average SSIM~0.855. The RF analysis revealed that 76 out of 186 RFs were identified using the 2D-Pix2Pix algorithm alone, although half of the RFs were lost during the translation process. A detailed qualitative review by 7 medical doctors noted a deficiency in low-level feature recognition in I2I tasks. Furthermore, the study found that synthesized image-based classification outperformed US image-based classification with an average accuracy and AUC~0.93. Conclusion: This study showed that while 2D-Pix2Pix outperformed cutting-edge networks in low-level feature discovery and overall error and similarity metrics, it still requires improvement in low-level feature performance, as highlighted by Group 3. Further, the study found using synthetic image-based classification outperformed original US image-based methods.