# ASL to PET Translation by a Semi-supervised Residual-based Attention-guided Convolutional Neural Network

arXiv: https://arxiv.org/abs/2103.05116 · HTML: https://mlsanity.com/paper/2103.05116/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 37 references that are in the map.
- First posted on arXiv 8 Mar 2021.

## Builds on (most cited first, 14 of 14)

- [Deeply-Supervised Nets](https://mlsanity.com/paper/1409.5185/) (2014)
- [Not-so-supervised: a survey of semi-supervised, multi-instance, and transfer learning in medical image analysis](https://mlsanity.com/paper/1804.06353/) (2018)
- [MedGAN: Medical Image Translation using GANs](https://mlsanity.com/paper/1806.06397/) (2018)
- [Image Synthesis in Multi-Contrast MRI with Conditional Generative Adversarial Networks](https://mlsanity.com/paper/1802.01221/) (2018)
- [Multi-Task Attention-Based Semi-Supervised Learning for Medical Image Segmentation](https://mlsanity.com/paper/1907.12303/) (2019)
- [Unsupervised Medical Image Translation Using Cycle-MedGAN](https://mlsanity.com/paper/1903.03374/) (2019)
- [Deep CT to MR Synthesis using Paired and Unpaired Data](https://mlsanity.com/paper/1805.10790/) (2018)
- [Cross-Modality Synthesis from CT to PET using FCN and GAN Networks for Improved Automated Lesion Detection](https://mlsanity.com/paper/1802.07846/) (2018)
- [An Adaptive Intelligence Algorithm for Undersampled Knee MRI Reconstruction](https://mlsanity.com/paper/2004.07339/) (2020)
- [Semi-Supervised Multi-Task Learning With Chest X-Ray Images](https://mlsanity.com/paper/1908.03693/) (2019)
- [Semi-supervised multi-task learning for lung cancer diagnosis](https://mlsanity.com/paper/1802.06181/) (2018)
- [MRI to CT Translation with GANs](https://mlsanity.com/paper/1901.05259/) (2019)
- [Fast Dynamic Perfusion and Angiography Reconstruction using an end-to-end 3D Convolutional Neural Network](https://mlsanity.com/paper/1908.08947/) (2019)
- [Semi-supervised Learning Approach to Generate Neuroimaging Modalities with Adversarial Training](https://mlsanity.com/paper/1912.04391/) (2019)

## Built on by (most cited first, 2 of 2)

- [Brain MRI-to-PET Synthesis using 3D Convolutional Attention Networks](https://mlsanity.com/paper/2211.12082/) (2022)
- [Multi-task Deep Learning for Cerebrovascular Disease Classification and MRI-to-PET Translation](https://mlsanity.com/paper/2202.06142/) (2022)

## Abstract (arXiv)

Positron Emission Tomography (PET) is an imaging method that can assess physiological function rather than structural disturbances by measuring cerebral perfusion or glucose consumption. However, this imaging technique relies on injection of radioactive tracers and is expensive. On the contrary, Arterial Spin Labeling (ASL) MRI is a non-invasive, non-radioactive, and relatively cheap imaging technique for brain hemodynamic measurements, which allows quantification to some extent. In this paper we propose a convolutional neural network (CNN) based model for translating ASL to PET images, which could benefit patients as well as the healthcare system in terms of expenses and adverse side effects. However, acquiring a sufficient number of paired ASL-PET scans for training a CNN is prohibitive for many reasons. To tackle this problem, we present a new semi-supervised multitask CNN which is trained on both paired data, i.e. ASL and PET scans, and unpaired data, i.e. only ASL scans, which alleviates the problem of training a network on limited paired data. Moreover, we present a new residual-based-attention guided mechanism to improve the contextual features during the training process. Also, we show that incorporating T1-weighted scans as an input, due to its high resolution and availability of anatomical information, improves the results. We performed a two-stage evaluation based on quantitative image metrics by conducting a 7-fold cross validation followed by a double-blind observer study. The proposed network achieved structural similarity index measure (SSIM), mean squared error (MSE) and peak signal-to-noise ratio (PSNR) values of 0.85±0.08, 0.01±0.01, and 21.8±4.5 respectively, for translating from 2D ASL and T1-weighted images to PET data. The proposed model is publicly available via https://github.com/yousefis/ASL2PET.