| 1. |
|
|
| 2. |
|
|
| 3. |
- Gålne, Anni, et al.
(författare)
-
AI-based quantification of whole-body tumour burden on somatostatin receptor PET/CT
- 2023
-
Ingår i: European Journal of Hybrid Imaging. - 2510-3636. ; 7:1
-
Tidskriftsartikel (refereegranskat)abstract
- Background: Segmenting the whole-body somatostatin receptor-expressing tumour volume (SRETVwb) on positron emission tomography/computed tomography (PET/CT) images is highly time-consuming but has shown value as an independent prognostic factor for survival. An automatic method to measure SRETVwb could improve disease status assessment and provide a tool for prognostication. This study aimed to develop an artificial intelligence (AI)-based method to detect and quantify SRETVwb and total lesion somatostatin receptor expression (TLSREwb) from [68Ga]Ga-DOTA-TOC/TATE PET/CT images. Methods: A UNet3D convolutional neural network (CNN) was used to train an AI model with [68Ga]Ga-DOTA-TOC/TATE PET/CT images, where all tumours were manually segmented with a semi-automatic method. The training set consisted of 148 patients, of which 108 had PET-positive tumours. The test group consisted of 30 patients, of which 25 had PET-positive tumours. Two physicians segmented tumours in the test group for comparison with the AI model. Results: There were good correlations between the segmented SRETVwb and TLSREwb by the AI model and the physicians, with Spearman rank correlation coefficients of r = 0.78 and r = 0.73, respectively, for SRETVwb and r = 0.83 and r = 0.81, respectively, for TLSREwb. The sensitivity on a lesion detection level was 80% and 79%, and the positive predictive value was 83% and 84% when comparing the AI model with the two physicians. Conclusion: It was possible to develop an AI model to segment SRETVwb and TLSREwb with high performance. A fully automated method makes quantification of tumour burden achievable and has the potential to be more widely used when assessing PET/CT images.
|
|
| 4. |
- Minarik, David, et al.
(författare)
-
Denoising of Scintillation Camera Images Using a Deep Convolutional Neural Network: A Monte Carlo Simulation Approach
- 2020
-
Ingår i: Journal of Nuclear Medicine. - : Society of Nuclear Medicine. - 0161-5505 .- 2159-662X. ; 61:2, s. 298-303
-
Tidskriftsartikel (refereegranskat)abstract
- Scintillation camera images contain a large amount of Poisson noise. We have investigated whether noise can be removed in whole-body bone scans using convolutional neural networks (CNNs) trained with sets of noisy and noiseless images obtained by Monte Carlo simulation. Methods: Three CNNs were generated using 3 different sets of training images: simulated bone scan images, images of a cylindric phantom with hot and cold spots, and a mix of the first two. Each training set consisted of 40,000 noiseless and noisy image pairs. The CNNs were evaluated with simulated images of a cylindric phantom and simulated bone scan images. The mean squared error between filtered and true images was used as difference metric, and the coefficient of variation was used to estimate noise reduction. The CNNs were compared with gaussian and median filters. A clinical evaluation was performed in which the ability to detect metastases for CNN- and gaussian-filtered bone scans with half the number of counts was compared with standard bone scans. Results: The best CNN reduced the coefficient of variation by, on average, 92%, and the best standard filter reduced the coefficient of variation by 88%. The best CNN gave a mean squared error that was on average 68% and 20% better than the best standard filters, for the cylindric and bone scan images, respectively. The best CNNs for the cylindric phantom and bone scans were the dedicated CNNs. No significant differences in the ability to detect metastases were found between standard, CNN-, and gaussian-filtered bone scans. Conclusion: Noise can be removed efficiently regardless of noise level with little or no resolution loss. The CNN filter enables reducing the scanning time by half and still obtaining good accuracy for bone metastasis assessment.
|
|
| 5. |
- Oddstig, Jenny, et al.
(författare)
-
Comparison of conventional and Si-photomultiplier-based PET systems for image quality and diagnostic performance
- 2019
-
Ingår i: BMC Medical Imaging. - : Springer Science and Business Media LLC. - 1471-2342. ; 19:1
-
Tidskriftsartikel (refereegranskat)abstract
- BACKGROUND: A new generation of positron emission tomography with computed tomography (PET-CT) was recently introduced using silicon (Si) photomultiplier (PM)-based technology. Our aim was to compare the image quality and diagnostic performance of a SiPM-based PET-CT (Discovery MI; GE Healthcare, Milwaukee, WI, USA) with a time-of-flight PET-CT scanner with a conventional PM detector (Gemini TF; Philips Healthcare, Cleveland, OH, USA), including reconstruction algorithms per vendor's recommendations. METHODS: Imaging of the National Electrical Manufacturers Association IEC body phantom and 16 patients was carried out using 1.5 min/bed for the Discovery MI PET-CT and 2 min/bed for the Gemini TF PET-CT. Images were analysed for recovery coefficients for the phantom, signal-to-noise ratio in the liver, standardized uptake values (SUV) in lesions, number of lesions and metabolic TNM classifications in patients. RESULTS: In phantom, the correct (> 90%) activity level was measured for spheres ≥17 mm for Discovery MI, whereas the Gemini TF reached a correct measured activity level for the 37-mm sphere. In patient studies, metabolic TNM classification was worse using images obtained from the Discovery MI compared those obtained from the Gemini TF in 4 of 15 patients. A trend toward more malignant, inflammatory and unclear lesions was found using images acquired with the Discovery MI compared with the Gemini TF, but this was not statistically significant. Lesion-to-blood-pool SUV ratios were significantly higher in images from the Discovery MI compared with the Gemini TF for lesions smaller than 1 cm (p < 0.001), but this was not the case for larger lesions (p = 0.053). The signal-to-noise ratio in the liver was similar between platforms (p = 0.52). Also, shorter acquisition times were possible using the Discovery MI, with preserved signal-to-noise ratio in the liver. CONCLUSIONS: Image quality was better with Discovery MI compared to conventional Gemini TF. Although no gold standard was available, the results indicate that the new PET-CT generation will provide potentially better diagnostic performance.
|
|
| 6. |
- Trägårdh, Elin, et al.
(författare)
-
RECOMIA-a cloud-based platform for artificial intelligence research in nuclear medicine and radiology
- 2020
-
Ingår i: Ejnmmi Physics. - : Springer Science and Business Media LLC. - 2197-7364. ; 7:1
-
Tidskriftsartikel (refereegranskat)abstract
- Background: Artificial intelligence (AI) is about to transform medical imaging. The Research Consortium for Medical Image Analysis (RECOMIA), a not-for-profit organisation, has developed an online platform to facilitate collaboration between medical researchers and AI researchers. The aim is to minimise the time and effort researchers need to spend on technical aspects, such as transfer, display, and annotation of images, as well as legal aspects, such as de-identification. The purpose of this article is to present the RECOMIA platform and its AI-based tools for organ segmentation in computed tomography (CT), which can be used for extraction of standardised uptake values from the corresponding positron emission tomography (PET) image. Results: The RECOMIA platform includes modules for (1) local de-identification of medical images, (2) secure transfer of images to the cloud-based platform, (3) display functions available using a standard web browser, (4) tools for manual annotation of organs or pathology in the images, (5) deep learning-based tools for organ segmentation or other customised analyses, (6) tools for quantification of segmented volumes, and (7) an export function for the quantitative results. The AI-based tool for organ segmentation in CT currently handles 100 organs (77 bones and 23 soft tissue organs). The segmentation is based on two convolutional neural networks (CNNs): one network to handle organs with multiple similar instances, such as vertebrae and ribs, and one network for all other organs. The CNNs have been trained using CT studies from 339 patients. Experienced radiologists annotated organs in the CT studies. The performance of the segmentation tool, measured as mean Dice index on a manually annotated test set, with 10 representative organs, was 0.93 for all foreground voxels, and the mean Dice index over the organs were 0.86 (0.82 for the soft tissue organs and 0.90 for the bones). Conclusion: The paper presents a platform that provides deep learning-based tools that can perform basic organ segmentations in CT, which can then be used to automatically obtain the different measurement in the corresponding PET image. The RECOMIA platform is available on request atfor research purposes.
|
|
