Figure 1 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Source publication
The aim was to improve single-photon emission computed tomography (SPECT) quality for sparsely acquired 111In projections by adding deep learning generated synthetic intermediate projections (SIPs). Method: The recently constructed deep convolutional network for generating synthetic intermediate projections (CUSIP) was used for improving 20 sparsel...
Contexts in source publication
Context 1
... has a three-dimensional structure and consist of encoder and decoder units with skip connections between the corresponding layers ( Figure 1). The input matrix (image) consists of 30 normalized projections with a matrix size of 128 × 128, which is concatenated to a cubic matrix of (128 × 128 × 128). ...
Citations
... Hence, MC-based reconstruction is very promising. However, the noise level needs to be handled appropriately, and we aim to further investigate deep learning-generated synthetic intermediate projections (SIPs) in SPECT images, which have been demonstrated to more effectively reduce the noise level compared to post-filtering methods such as Gaussian filtering [32,33]. This might improve SNR in images reconstructed with MC-based OSEM reconstruction. ...
Background
Early cancer detection is crucial for patients’ survival. The image quality in ¹¹¹In-octreotide SPECT imaging could be improved by using Monte Carlo (MC)-based reconstruction. The aim of this observational study was to determine the detection rate of simulated liver lesions for MC-based ordered subset expectation maximization (OSEM) reconstruction compared to conventional attenuation-corrected OSEM reconstruction.
Methods
Thirty-seven SPECT/CT examinations with ¹¹¹In-octreotide were randomly selected. The inclusion criterion was no liver lesions at the time of examination and for the following 3 years. SPECT images of spheres representing lesions were simulated using MC. The raw data of the spheres were added to the raw data of the established healthy patients in 26 of the examinations, and the remaining 11 examinations were not modified. The images were reconstructed using conventional OSEM reconstruction with attenuation correction and post filtering (fAC OSEM) and MC-based OSEM reconstruction without and with post filtering (MC OSEM and fMC OSEM, respectively). The images were visually and blindly evaluated by a nuclear medicine specialist. The criteria evaluated were liver lesion yes or no, including coordinates if yes, with confidence level 1–3. The percentage of detected lesions and accuracy (percentage of correctly classified cases), as well as tumor-to-normal tissue concentration (TNC) ratios and signal-to-noise ratios (SNRs), were evaluated.
Results
The detection rates were 30.8% for fAC OSEM, 42.3% for fMC OSEM, and 50.0% for MC OSEM. The accuracies were 45.9% for fAC OSEM, 45.9% for fMC OSEM, and 54.1% for MC OSEM. The number of false positives was higher for fMC and MC OSEM. The observer’s confidence level was higher in filtered images than in unfiltered images. TNC ratios were significantly higher, statistically, with MC OSEM and fMC OSEM than with AC OSEM, but SNRs were similar due to higher noise with MC OSEM.
Conclusion
One in two lesions were found using MC OSEM versus one in three using conventional reconstruction. TNC ratios were significantly improved, statistically, using MC-based reconstruction, but the noise levels increased and consequently the confidence level of the observer decreased. For further improvements, image noise needs to be suppressed.
... Recent work has assessed the reduction in the number of acquired SPECT projections to reduce scan time without compromising quantitative accuracy or image quality. Rydén et al. [17] used a deep convolutional U-net-shaped neural network to generate intermediate 177 Lu SPECT projections (i.e. projections that were not acquired). ...
We highlight emerging uses of artificial intelligence (AI) in the field of theranostics, focusing on its significant potential to enable routine and reliable personalization of radiopharmaceutical therapies (RPTs). Personalized RPTs require patient-individual dosimetry calculations accompanying therapy. Image-based dosimetry needs: 1) quantitative imaging; 2) co-registration and organ/tumor identification on serial and multimodality images; 3) determination of the time-integrated activity; and 4) absorbed dose determination. AI models that facilitate these steps are reviewed. Additionally we discuss the potential to exploit biological information from diagnostic and therapeutic molecular images to derive biomarkers for absorbed dose and outcome prediction, towards personalization of therapies. We try to motivate the nuclear medicine community to expand and align efforts into making routine and reliable personalization of RPTs a reality.
... The deep neural network was designed and trained to generate 90 SIPs from an input of 30P. This network has previously been shown to perform well in reconstructions of 177 Lu-DOTATATE and Indium-111 ( 111 In)-octreotide images, showing high structural similarity between acquired projections and SIPs, and improved image quality in reconstructed images compared to reconstruction of 30P [16,17]. However, this study only evaluated images from one day post administration and did not evaluate any dosimetry. ...
... The use of SIPs seems to be a promising noise reduction technique, as it has previously yielded improved results compared to regular post filtering with Butterworth or Gaussian filters [16,17]. Future studies should be conducted with the aim of examining the detectability of small lesions in SPECT/CT imaging using SIPs instead of standard filtering. ...
Background
For dosimetry, the demand for whole-body SPECT/CT imaging, which require long acquisition durations with dual-head Anger cameras, is increasing. Here we evaluated sparsely acquired projections and assessed whether the addition of deep-learning-generated synthetic intermediate projections (SIPs) could improve the image quality while preserving dosimetric accuracy.
Methods
This study included 16 patients treated with ¹⁷⁷Lu-DOTATATE with SPECT/CT imaging (120 projections, 120P) at four time points. Deep neural networks (CUSIPs) were designed and trained to compile 90 SIPs from 30 acquired projections (30P). The 120P, 30P, and three different CUSIP sets (30P + 90 SIPs) were reconstructed using Monte Carlo-based OSEM reconstruction (yielding 120P_rec, 30P_rec, and CUSIP_recs). The noise levels were visually compared. Quantitative measures of normalised root mean square error, normalised mean absolute error, peak signal-to-noise ratio, and structural similarity were evaluated, and kidney and bone marrow absorbed doses were estimated for each reconstruction set.
Results
The use of SIPs visually improved noise levels. All quantitative measures demonstrated high similarity between CUSIP sets and 120P. Linear regression showed nearly perfect concordance of the kidney and bone marrow absorbed doses for all reconstruction sets, compared to the doses of 120P_rec (R² ≥ 0.97). Compared to 120P_rec, the mean relative difference in kidney absorbed dose, for all reconstruction sets, was within 3%. For bone marrow absorbed doses, there was a higher dissipation in relative differences, and CUSIP_recs outperformed 30P_rec in mean relative difference (within 4% compared to 9%). Kidney and bone marrow absorbed doses for 30P_rec were statistically significantly different from those of 120_rec, as opposed to the absorbed doses of the best performing CUSIP_rec, where no statistically significant difference was found.
Conclusion
When performing SPECT/CT reconstruction, the use of SIPs can substantially reduce acquisition durations in SPECT/CT imaging, enabling acquisition of multiple fields of view of high image quality with satisfactory dosimetric accuracy.
The expansion of tourism demand and the rapid growth of tourism industry objectively promote the tourism development and utilization of nature reserves. At present, there are various difficulties in the practical application of tourism environmental capacity assessment technology in nature reserves. This article attempts to carry out tourism monitoring and management in protected areas by combining 3D sensor image acquisition and environmental capacity assessment technology. First of all, this paper proposes a dynamic monitoring plan for the ecological environment of the reserve using 3D sensor image acquisition technology, and realizes the monitoring of tourists in the reserve and the collection of natural environment data. Secondly, this article proposes a new natural reserve tourism environment capacity assessment and pricing plan, and takes the Changtang National Park high-end tourism project as an example, and discusses its application in the form of a case study. This program provides a new solution for balancing the economic and environmental benefits of the reserve. Through simulation tests and questionnaire surveys, we found that the program can effectively improve the nature protection and tourism inspection work in the reserve.
