Amirhossein Sanaat

Mr. Amirhossein Sanaat

Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, CH-1211 Geneva, Switzerland
orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 July 2020 in Applied Sciences
Verified
Journal Article
Open access
PDF file
Amirhossein SanaatAmirhossein Sanaat
Amirhossein Sanaat
Habib ZaidiHabib Zaidi
Habib Zaidi
The scintillation light distribution produced by photodetectors in positron emission tomography (PET) provides the depth of interaction (DOI) information required for high-resolution imaging. The goal of positioning techniques is to reverse the photodetector signal’s pattern map to the coordinates of the incident photon energy position. By considering the DOI information, monolithic crystals offer good spatial, energy, and timing resolution along with high sensitivity. In this work, a supervised deep neural network was used for the approximation of DOI and to assess through Monte Carlo (MC) simulations the performance on a small-animal PET scanner consisting of ten 50 × 50 × 10 mm3 continuous Lutetium-Yttrium Oxyorthosilicate doped with Cerium (LYSO: Ce) crystals and 12 × 12 silicon photomultiplier (SiPM) arrays. The scintillation position was predicted by a multilayer perceptron neural network with 256 units and 4 layers whose inputs were the number of fired pixels on the SiPM plane and the total deposited energy. A GEANT4 MC code was used to generate training and test datasets by altering the photons’ incident position, energy, and direction, as well as readout of the photodetector output. The calculated spatial resolutions in the X-Y plane and along the Z-axis were 0.96 and 1.02 mm, respectively. Our results demonstrated that using a multilayer perceptron (MLP)-based positioning algorithm in the detector modules, constituting the PET scanner, enhances the spatial resolution by approximately 18% while the absolute sensitivity remains constant. The proposed algorithm proved its ability to predict the DOI for depth under 7 mm with an error below 8.7%.

1 April 2025 in Radiology
Verified
Journal Article
Closed access
BJBin Jiang
Bin Jiang
NPNancy Pham
Nancy Pham
ESEric K. van Staalduinen
Eric K. van Staalduinen
YLYongkai Liu
Yongkai Liu
SNSanaz Nazari-Farsani
Sanaz Nazari-Farsani
GZGreg Zaharchuk
Greg Zaharchuk
Deep learning applications have permeated acute ischemic stroke imaging, particularly for stroke lesion segmentation; however, challenges remain, including the need for standardized protocols and test sets, larger public datasets, and performance validation in real-world settings.

8 February 2022 in Journal of Digital Imaging
Verified
Journal Article
Open access
PDF file
Amirhossein SanaatAmirhossein Sanaat
Amirhossein Sanaat
ISIsaac Shiri
Isaac Shiri
SFSohrab Ferdowsi
Sohrab Ferdowsi
HAHossein Arabi
Hossein Arabi
Habib ZaidiHabib Zaidi
Habib Zaidi
A small dataset commonly affects generalization, robustness, and overall performance of deep neural networks (DNNs) in medical imaging research. Since gathering large clinical databases is always difficult, we proposed an analytical method for producing a large realistic/diverse dataset. Clinical brain PET/CT/MR images including full-dose (FD), low-dose (LD) corresponding to only 5 % of events acquired in the FD scan, non-attenuated correction (NAC) and CT-based measured attenuation correction (MAC) PET images, CT images and T1 and T2 MR sequences of 35 patients were included. All images were registered to the Montreal Neurological Institute (MNI) template. Laplacian blending was used to make a natural presentation using information in the frequency domain of images from two separate patients, as well as the blending mask. This classical technique from the computer vision and image processing communities is still widely used and unlike modern DNNs, does not require the availability of training data. A modified ResNet DNN was implemented to evaluate four image-to-image translation tasks, including LD to FD, LD+MR to FD, NAC to MAC, and MRI to CT, with and without using the synthesized images. Quantitative analysis using established metrics, including the peak signal-to-noise ratio (PSNR), structural similarity index metric (SSIM), and joint histogram analysis was performed for quantitative evaluation. The quantitative comparison between the registered small dataset containing 35 patients and the large dataset containing 350 synthesized plus 35 real dataset demonstrated improvement of the RMSE and SSIM by 29% and 8% for LD to FD, 40% and 7% for LD+MRI to FD, 16% and 8% for NAC to MAC, and 24% and 11% for MRI to CT mapping task, respectively. The qualitative/quantitative analysis demonstrated that the proposed model improved the performance of all four DNN models through producing images of higher quality and lower quantitative bias and variance compared to reference images.

10 September 2022 in Human Brain Mapping
Verified
Journal Article
Open access
Amirhossein SanaatAmirhossein Sanaat
Amirhossein Sanaat
AAAzadeh Akhavanalaf
Azadeh Akhavanalaf
ISIsaac Shiri
Isaac Shiri
YSYazdan Salimi
Yazdan Salimi
HAHossein Arabi
Hossein Arabi
Habib ZaidiHabib Zaidi
Habib Zaidi
We aim to synthesize brain time‐of‐flight (TOF) PET images/sinograms from their corresponding non‐TOF information in the image space (IS) and sinogram space (SS) to increase the signal‐to‐noise ratio (SNR) and contrast of abnormalities, and decrease the bias in tracer uptake quantification. One hundred forty clinical brain 18F‐FDG PET/CT scans were collected to generate TOF and non‐TOF sinograms. The TOF sinograms were split into seven time bins (0, ±1, ±2, ±3). The predicted TOF sinogram was reconstructed and the performance of both models (IS and SS) compared with reference TOF and non‐TOF. Wide‐ranging quantitative and statistical analysis metrics, including structural similarity index metric (SSIM), root mean square error (RMSE), as well as 28 radiomic features for 83 brain regions were extracted to evaluate the performance of the CycleGAN model. SSIM and RMSE of 0.99 ± 0.03, 0.98 ± 0.02 and 0.12 ± 0.09, 0.16 ± 0.04 were achieved for the generated TOF‐PET images in IS and SS, respectively. They were 0.97 ± 0.03 and 0.22 ± 0.12, respectively, for non‐TOF‐PET images. The Bland & Altman analysis revealed that the lowest tracer uptake value bias (−0.02%) and minimum variance (95% CI: −0.17%, +0.21%) were achieved for TOF‐PET images generated in IS. For malignant lesions, the contrast in the test dataset was enhanced from 3.22 ± 2.51 for non‐TOF to 3.34 ± 0.41 and 3.65 ± 3.10 for TOF PET in SS and IS, respectively. The implemented CycleGAN is capable of generating TOF from non‐TOF PET images to achieve better image quality.

1 March 2024 in Quantitative Imaging in Medicine and Surgery
Verified
Journal Article
Open access
PDF file
MAMohammad-Saber Azimi
Mohammad-Saber Azimi
AKAlireza Kamali-Asl
Alireza Kamali-Asl
MAMohammad-Reza Ay
Mohammad-Reza Ay
NZNavid Zeraatkar
Navid Zeraatkar
MHMahboubeh-Sadat Hosseini
Mahboubeh-Sadat Hosseini
HAHossein Arabi
Hossein Arabi
Background: Positron emission tomography (PET) imaging encounters the obstacle of partial volume effects, arising from its limited intrinsic resolution, giving rise to (I) considerable bias, particularly for structures comparable in size to the point spread function (PSF) of the system; and (II) blurred image edges and blending of textures along the borders. We set out to build a deep learning-based framework for predicting partial volume corrected full-dose (FD + PVC) images from either standard or low-dose (LD) PET images without requiring any anatomical data in order to provide a joint solution for partial volume correction and de-noise LD PET images. Methods: We trained a modified encoder-decoder U-Net network with standard of care or LD PET images as the input and FD + PVC images by six different PVC methods as the target. These six PVC approaches include geometric transfer matrix (GTM), multi-target correction (MTC), region-based voxel-wise correction (RBV), iterative Yang (IY), reblurred Van-Cittert (RVC), and Richardson-Lucy (RL). The proposed models were evaluated using standard criteria, such as peak signal-to-noise ratio (PSNR), root mean squared error (RMSE), structural similarity index (SSIM), relative bias, and absolute relative bias. Results: Different levels of error were observed for these partial volume correction methods, which were relatively smaller for GTM with a SSIM of 0.63 for LD and 0.29 for FD, IY with an SSIM of 0.63 for LD and 0.67 for FD, RBV with an SSIM of 0.57 for LD and 0.65 for FD, and RVC with an SSIM of 0.89 for LD and 0.94 for FD PVC approaches. However, large quantitative errors were observed for multi-target MTC with an RMSE of 2.71 for LD and 2.45 for FD and RL with an RMSE of 5 for LD and 3.27 for FD PVC approaches. Conclusions: We found that the proposed framework could effectively perform joint de-noising and partial volume correction for PET images with LD and FD input PET data (LD vs. FD). When no magnetic resonance imaging (MRI) images are available, the developed deep learning models could be used for partial volume correction on LD or standard PET-computed tomography (PET-CT) scans as an image quality enhancement technique.

1 February 2020 in Physics in Medicine & Biology
Verified
Journal Article
Open access
PDF file
Amirhossein SanaatAmirhossein Sanaat
Amirhossein Sanaat
HAHossein Arabi
Hossein Arabi
MAMohammad Reza Ay
Mohammad Reza Ay
Habib ZaidiHabib Zaidi
Habib Zaidi
We propose a small-animal PET scanner design combining two sets of monolithic crystals with two different thicknesses. The detectors with thinner crystals serve for high resolution imaging while the thicker crystals retain the detection efficiency. Two small-animal PET models based on 10 and 12 detector blocks made of monolithic LYSO crystals were implemented in the GEANT4 Monte Carlo toolkit. In each of these models, half of the detector blocks consisted of a crystal thickness of 10 mm whereas the second half had a crystal thickness of 2 mm. The scintillator crystals were coupled to SiPM arrays. For the first model, the detector blocks were arranged in a full-ring polygonal geometry in such a way that detector blocks with the same thickness were sitting opposite to each other. For the second model, detector blocks with different crystal thicknesses were facing each other. The performance of the proposed PET models was assessed using standard parameters, including spatial resolution, sensitivity and noise equivalent count rate. Comparison was made with conventional PET models with crystal thicknesses of 2 mm, 6 mm and 10 mm. PET models with a crystal thickness of 2 mm led to the highest spatial resolution (up to 0.6 mm FWHM) at the cost of poor absolute sensitivity (2.5%). On the other hand, PET models with a crystal thickness of 10 mm led to good detection efficiency (4.4%), yet with substantial degradation of spatial resolution (1.2 mm FWHM). The proposed PET models with thick and thin crystals exhibited an optimal trade-off between spatial resolution and sensitivity outperforming the PET model with fixed 6 mm crystal by achieving a spatial resolution of 0.7 mm and absolute sensitivity of 3.7%. The novel proposed PET design concept achieved an optimal trade-off between the sensitivity and spatial resolution by combining two sets of monolithic crystals.