European Journal of Nuclear Medicine and Molecular Imaging最新文献

Purpose

360° CZT-cameras provide whole-body bone SPECT/CT recordings at delayed (DEL) and blood-pool (BP) phases with short recording times but long visual analysis times. This study aims to determine whether a standardized uptake value (SUV)-based detection of inflammatory arthritis (IA) could facilitate this analysis.

Methods

We included 72 patients with known or suspected IA who underwent two-phase whole-body bone SPECT/CT after 550–650 MBq [^99mTc]Tc-HDP injection. Forty-eight patients also had ultrasound (US) for peripheral IA, and 42 had MRI for axial IA. The skeleton was segmented into 26 joint areas and analyzed by trained observers using a visual consensus methodology and SUVmax measurements.

Results

A total of 1836 joint areas were analyzed, including 1126 peripheral ones (limb joints excluding hips and shoulders). SUVmax was predictive of visually abnormal SPECT joints with high areas under receiver-operating-characteristic (ROC) curves for non-peripheral (BP-SPECT: 0.941 ± 0.017, DEL-SPECT: 0.910 ± 0.014) and especially peripheral (BP-SPECT: 0.980 ± 0.005, DEL-SPECT: 0.939 ± 0.012) joints. An SUVmax threshold-based prediction of visual SPECT abnormalities had high negative predictive values (BP-SPECT: 99.2% (1479/1491), DEL-SPECT: 97.2% (1333/1372)) but low positive predictive values (BP-SPECT: 35.1% (121/345), DEL-SPECT: 51.2% (237/463)). MRI- and US-defined IA were best predicted by a visually abnormal BP-SPECT due to higher specificities than SUVmax thresholds (all p < 0.05).

Conclusion

On two-phase whole-body bone SPECT/CT, an SUVmax-based IA detection may not replace the conventional visual method. However, given the high negative predictive values provided by SUVmax thresholds, the time-consuming visual analysis of SPECT/CT slices could be confined to the small proportion of joints exceeding these thresholds.

Purpose

Accurate prediction of adverse pathology (AP) in prostate cancer (PCa) patients is crucial for formulating effective treatment strategies. This study aims to develop and evaluate a multimodal deep learning model based on [¹⁸F]PSMA-1007 PET/CT and multiparametric MRI (mpMRI) to predict the presence of AP, and investigate whether the model that integrates [¹⁸F]PSMA-1007 PET/CT and mpMRI outperforms the individual PET/CT or mpMRI models in predicting AP.

Methods

341 PCa patients who underwent radical prostatectomy (RP) with mpMRI and PET/CT scans were retrospectively analyzed. We generated deep learning signature from mpMRI and PET/CT with a multimodal deep learning model (MPC) based on convolutional neural networks and transformer, which was subsequently incorporated with clinical characteristics to construct an integrated model (MPCC). These models were compared with clinical models and single mpMRI or PET/CT models.

Results

The MPCC model showed the best performance in predicting AP (AUC, 0.955 [95% CI: 0.932–0.975]), which is higher than MPC model (AUC, 0.930 [95% CI: 0.901–0.955]). The performance of the MPC model is better than that of single PET/CT (AUC, 0.813 [95% CI: 0.780–0.845]) or mpMRI (AUC, 0.865 [95% CI: 0.829–0.901]). Additionally, MPCC model is also effective in predicting single adverse pathological features.

Conclusion

The deep learning model that integrates mpMRI and [¹⁸F]PSMA-1007 PET/CT enhances the predictive capabilities for the presence of AP in PCa patients. This improvement aids physicians in making informed preoperative decisions, ultimately enhancing patient prognosis.

Purpose

Center-specific effects in PET brain scans arise due to differences in technical and procedural aspects. This restricts the merging of data between centers and introduces source-specific bias.

Methods

We demonstrate the use of the recently proposed machine learning method Iterated Relevance Matrix Analysis (IRMA) for harmonization of center-specific effects in brain (^{18})F-Fluorodeoxyglucose ((^{18})F-FDG) PET scans. The center difference is learned by applying IRMA on PCA-based feature vectors of healthy controls (HC), resulting in a subspace (varvec{V}), representing information not comparable between centers, and the remaining subspace (varvec{U}), where no center differences are present. In this proof-of-concept study, we demonstrate the properties of the method using data from four centers. After center-harmonization, a Generalized Matrix Learning Vector Quantization (GMLVQ) model was trained to discriminate between Parkinson’s disease, Alzheimer’s disease and Dementia with Lewy Bodies.

Results

At the initial IRMA iteration, the system was able to determine the center origin of the four HC cohorts almost perfectly. The method required six iterations, corresponding to a six-dimensional subspace (varvec{V}), to determine the entire center difference. An uncorrected disease classification model was highly biased to center-specific effects, creating a falsely inflated performance when applying internal (cross-) validation. The cross-validation performance of the center-harmonized model remained high, while it generalized significantly better to unseen test cohorts. Furthermore, the framework is highly transparent, providing analytic reconstructions of the correction and visualizations of the data in voxel space.

Conclusion

IRMA can be used to learn and disregard center-specific information in features extracted from brain (^{18})F-FDG PET scans, while retaining disease-specific information.

Purpose

Quantitative analysis of PET images in brain PET/CT relies on MRI-derived regions of interest (ROIs). However, the pairs of PET/CT and MR images are not always available, and their alignment is challenging if their acquisition times differ considerably. To address these problems, this study proposes a deep learning framework for translating CT of PET/CT to synthetic MR images (MR_SYN) and performing automated quantitative regional analysis using MR_SYN-derived segmentation.

Methods

In this retrospective study, 139 subjects who underwent brain [¹⁸F]FBB PET/CT and T1-weighted MRI were included. A U-Net-like model was trained to translate CT images to MR_SYN; subsequently, a separate model was trained to segment MR_SYN into 95 regions. Regional and composite standardised uptake value ratio (SUVr) was calculated in [¹⁸F]FBB PET images using the acquired ROIs. For evaluation of MR_SYN, quantitative measurements including structural similarity index measure (SSIM) were employed, while for MR_SYN-based segmentation evaluation, Dice similarity coefficient (DSC) was calculated. Wilcoxon signed-rank test was performed for SUVrs computed using MR_SYN and ground-truth MR (MR_GT).

Results

Compared to MR_GT, the mean SSIM of MR_SYN was 0.974 ± 0.005. The MR_SYN-based segmentation achieved a mean DSC of 0.733 across 95 regions. No statistical significance (P > 0.05) was found for SUVr between the ROIs from MR_SYN and those from MR_GT, excluding the precuneus.

Conclusion

We demonstrated a deep learning framework for automated regional brain analysis in PET/CT with MR_SYN. Our proposed framework can benefit patients who have difficulties in performing an MRI scan.

Aim

To evaluate a deep learning-based time-of-flight (DLToF) model trained to enhance the image quality of non-ToF PET images for different tracers, reconstructed using BSREM algorithm, towards ToF images.

Methods

A 3D residual U-NET model was trained using 8 different tracers (FDG: 75% and non-FDG: 25%) from 11 sites from US, Europe and Asia. A total of 309 training and 33 validation datasets scanned on GE Discovery MI (DMI) ToF scanners were used for development of DLToF models of three strengths: low (L), medium (M) and high (H). The training and validation pairs consisted of target ToF and input non-ToF BSREM reconstructions using site-preferred regularisation parameters (beta values). The contrast and noise properties of each model were defined by adjusting the beta value of target ToF images. A total of 60 DMI datasets, consisting of a set of 4 tracers (¹⁸F-FDG, ¹⁸F-PSMA, ⁶⁸Ga-PSMA, ⁶⁸Ga-DOTATATE) and 15 exams each, were collected for testing and quantitative analysis of the models based on standardized uptake value (SUV) in regions of interest (ROI) placed in lesions, lungs and liver. Each dataset includes 5 image series: ToF and non-ToF BSREM and three DLToF images. The image series (300 in total) were blind scored on a 5-point Likert score by 4 readers based on lesion detectability, diagnostic confidence, and image noise/quality.

Results

In lesion SUV_max quantification with respect to ToF BSREM, DLToF-H achieved the best results among the three models by reducing the non-ToF BSREM errors from -39% to -6% for ¹⁸F-FDG (38 lesions); from -42% to -7% for ¹⁸F-PSMA (35 lesions); from -34% to -4% for ⁶⁸Ga-PSMA (23 lesions) and from -34% to -12% for ⁶⁸Ga-DOTATATE (32 lesions). Quantification results in liver and lung also showed ToF-like performance of DLToF models. Clinical reader resulted showed that DLToF-H results in an improved lesion detectability on average for all four radiotracers whereas DLToF-L achieved the highest scores for image quality (noise level). The results of DLToF-M however showed that this model results in the best trade-off between lesion detection and noise level and hence achieved the highest score for diagnostic confidence on average for all radiotracers.

Conclusion

This study demonstrated that the DLToF models are suitable for both FDG and non-FDG tracers and could be utilized for digital BGO PET/CT scanners to provide an image quality and lesion detectability comparable and close to ToF.

Purpose

The aim of this study was to investigate the radiological and pathological characteristics of false-positive lesions on [⁶⁸Ga]Ga-PSMA-11 PET/CT during the primary staging of prostate cancer.

Methods

This study retrospectively analyzed 216 prostate cancer patients who had [⁶⁸Ga]Ga-PSMA-11 PET/CT before radical prostatectomy. False-positive lesion was defined as suspicious lesion with PRIMARY score ≥ 3 on PET/CT but benign on whole-mount pathology. To analyze the radiological and pathological features of false-positive lesions, no-uptake areas on PSMA PET/CT with benign pathology on the whole-mount specimen were randomly delineated and defined as true-negative lesions. The pathological features of false-positive and true-negative lesions were compared using Fisher’s exact test. The differences of SUVmax and SUVmean between false-positive and true-positive lesions were determined and compared using the Wilcoxon matched-pairs signed-ranks test. In addition, PSMA expression in false-positive lesions was assessed by immunohistochemistry.

Results

A total of 36 false-positive lesions were identified on [⁶⁸Ga]Ga-PSMA-11 PET/CT: 25 (69.44%) were simple atrophy with cyst formation, 7 (19.44%) were prostatic nodular hyperplasia, 3 (8.33%) were inflammation and 1 (2.78%) was normal glands. A comparable number of 36 true-negative lesions were delineated: 21 (58.33%) were normal glands, 8 (22.22%) were simple atrophy with cyst formation, 6 (16.67%) were prostatic nodular hyperplasia, and 1 (2.78%) were inflammation. The Fisher’s exact test revealed a statistically significant difference in the prevalence of simple atrophy with cyst formation between false-positive and true-negative lesions (69.44% vs. 22.22%; P < 0.001). Differences in SUVmax and SUVmean between false-positive and true-positive lesions were also statistically significant (both P < 0.001). PSMA expression in false-positive lesions was confirmed via immunohistochemistry.

Conclusion

This study determined that simple atrophy with cyst formation is a distinctive pathological feature of false-positive lesions on [⁶⁸Ga]Ga-PSMA-11 PET/CT. This observation is likely attributable to the elevated PSMA expression in simple atrophy with cyst formation, as confirmed by histological analysis. Additionally, false-positive lesions were found to have significantly lower SUV compared to true-positive lesions.

Purpose: While many studies have explored the link between biomarkers and cognitive decline in Parkinson's disease (PD), a more comprehensive approach is needed, combining striatal dopamine depletion, cerebral glucose metabolism, and cognitive assessments. In this study, we investigated the relationships between striatal dopamine transporter (DAT) uptake, cerebral glucose hypometabolism, and cognition, as well as the potential progression pattern of these changes in PD.

Methods: We enrolled 62 patients with PD and 33 healthy controls. The subjects underwent N-(3-[¹⁸F]fluoropropyl)-2β-carbomethoxy-3β-(4-iodophenyl)nortropane (FP-CIT) PET/CT, [¹⁸F] fluorodeoxyglucose (FDG) PET/CT, and detailed neuropsychological testing. The mean standard uptake value ratio (SUVR) value of the regions showing significantly lower metabolism in PD patients was defined as SUVR_[hypo]. The relationship between striatal DAT uptake and SUVR_[hypo] was assessed using general linear models, while their impact on cognitive function was evaluated with multivariate linear regression. Additionally, the pattern of their changes was assessed using an event-based model.

Results: Compared to the control group, PD patients exhibited glucose hypometabolism in specific cortical regions. DAT uptake in the anterior and posterior putamen was positively correlated with SUVR_[hypo]. Decreased DAT uptake in the anterior putamen and caudate nucleus was associated with lower z-score in visuospatial function. Decreased DAT uptake in the posterior and anterior putamen occurred first, followed by PD-related cerebral hypometabolism, and visuospatial function.

Conclusion: This study highlights the interconnectedness of dopaminergic depletion, cerebral glucose hypometabolism, and visuospatial dysfunction, proposing that striatal DAT uptake may serve as an early biomarker for cerebral hypometabolism and cognitive impairment in PD.