RESUMEN
PURPOSE: Image artefacts continue to pose challenges in clinical molecular imaging, resulting in misdiagnoses, additional radiation doses to patients and financial costs. Mismatch and halo artefacts occur frequently in gallium-68 (68Ga)-labelled compounds whole-body PET/CT imaging. Correcting for these artefacts is not straightforward and requires algorithmic developments, given that conventional techniques have failed to address them adequately. In the current study, we employed differential privacy-preserving federated transfer learning (FTL) to manage clinical data sharing and tackle privacy issues for building centre-specific models that detect and correct artefacts present in PET images. METHODS: Altogether, 1413 patients with 68Ga prostate-specific membrane antigen (PSMA)/DOTA-TATE (TOC) PET/CT scans from 3 countries, including 8 different centres, were enrolled in this study. CT-based attenuation and scatter correction (CT-ASC) was used in all centres for quantitative PET reconstruction. Prior to model training, an experienced nuclear medicine physician reviewed all images to ensure the use of high-quality, artefact-free PET images (421 patients' images). A deep neural network (modified U2Net) was trained on 80% of the artefact-free PET images to utilize centre-based (CeBa), centralized (CeZe) and the proposed differential privacy FTL frameworks. Quantitative analysis was performed in 20% of the clean data (with no artefacts) in each centre. A panel of two nuclear medicine physicians conducted qualitative assessment of image quality, diagnostic confidence and image artefacts in 128 patients with artefacts (256 images for CT-ASC and FTL-ASC). RESULTS: The three approaches investigated in this study for 68Ga-PET imaging (CeBa, CeZe and FTL) resulted in a mean absolute error (MAE) of 0.42 ± 0.21 (CI 95%: 0.38 to 0.47), 0.32 ± 0.23 (CI 95%: 0.27 to 0.37) and 0.28 ± 0.15 (CI 95%: 0.25 to 0.31), respectively. Statistical analysis using the Wilcoxon test revealed significant differences between the three approaches, with FTL outperforming CeBa and CeZe (p-value < 0.05) in the clean test set. The qualitative assessment demonstrated that FTL-ASC significantly improved image quality and diagnostic confidence and decreased image artefacts, compared to CT-ASC in 68Ga-PET imaging. In addition, mismatch and halo artefacts were successfully detected and disentangled in the chest, abdomen and pelvic regions in 68Ga-PET imaging. CONCLUSION: The proposed approach benefits from using large datasets from multiple centres while preserving patient privacy. Qualitative assessment by nuclear medicine physicians showed that the proposed model correctly addressed two main challenging artefacts in 68Ga-PET imaging. This technique could be integrated in the clinic for 68Ga-PET imaging artefact detection and disentanglement using multicentric heterogeneous datasets.
Asunto(s)
Tomografía Computarizada por Tomografía de Emisión de Positrones , Neoplasias de la Próstata , Masculino , Humanos , Tomografía Computarizada por Tomografía de Emisión de Positrones/métodos , Artefactos , Radioisótopos de Galio , Privacidad , Tomografía de Emisión de Positrones/métodos , Aprendizaje Automático , Procesamiento de Imagen Asistido por Computador/métodosRESUMEN
This study aimed to assist doctors in detecting early-stage lung cancer. To achieve this, a hierarchical system that can detect nodules in the lungs using computed tomography (CT) images was developed. In the initial phase, a preexisting model (YOLOv5s) was used to detect lung nodules. A 0.3 confidence threshold was established for identifying nodules in this phase to enhance the model's sensitivity. The primary objective of the hierarchical model was to locate and categorize all lung nodules while minimizing the false-negative rate. Following the analysis of the results from the first phase, a novel 3D convolutional neural network (CNN) classifier was developed to examine and categorize the potential nodules detected by the YOLOv5s model. The objective was to create a detection framework characterized by an extremely low false positive rate and high accuracy. The Lung Nodule Analysis 2016 (LUNA 16) dataset was used to evaluate the effectiveness of this framework. This dataset comprises 888 CT scans that include the positions of 1186 nodules and 400,000 non-nodular regions in the lungs. The YOLOv5s technique yielded numerous incorrect detections owing to its low confidence level. Nevertheless, the addition of a 3D classification system significantly enhanced the precision of nodule identification. By integrating the outcomes of the YOLOv5s approach using a 30% confidence limit and the 3D CNN classification model, the overall system achieved 98.4% nodule detection accuracy and an area under the curve of 98.9%. Despite producing some false negatives and false positives, the suggested method for identifying lung nodules from CT scans is promising as a valuable aid in decision-making for nodule detection.
Asunto(s)
Neoplasias Pulmonares , Nódulo Pulmonar Solitario , Humanos , Neoplasias Pulmonares/diagnóstico por imagen , Nódulo Pulmonar Solitario/diagnóstico por imagen , Tomografía Computarizada por Rayos X/métodos , Pulmón/diagnóstico por imagen , Redes Neurales de la Computación , Interpretación de Imagen Radiográfica Asistida por Computador/métodosRESUMEN
PURPOSE: We aimed to investigate whether a clinically feasible dual time-point (DTP) approach can accurately estimate the metabolic uptake rate constant (Ki) and to explore reliable acquisition times through simulations and clinical assessment considering patient comfort and quantification accuracy. METHODS: We simulated uptake kinetics in different tumors for four sets of DTP PET images within the routine clinical static acquisition at 60-min post-injection (p.i.). We determined Ki for a total of 81 lesions. Ki quantification from full dynamic PET data (Patlak-Ki) and Ki from DTP (DTP-Ki) were compared. In addition, we scaled a population-based input function (PBIFscl) with the image-derived blood pool activity sampled at different time points to assess the best scaling time-point for Ki quantifications in the simulation data. RESULTS: In the simulation study, Ki estimated using DTP via (30,60-min), (30,90-min), (60,90-min), and (60,120-min) samples showed strong correlations (r ≥ 0.944, P < 0.0001) with the true value of Ki. The DTP results with the PBIFscl at 60-min time-point in (30,60-min), (60,90-min), and (60,120-min) were linearly related to the true Ki with a slope of 1.037, 1.008, 1.013 and intercept of -6 × 10-4, 2 × 10-5, 5 × 10-5, respectively. In a clinical study, strong correlations (r ≥ 0.833, P < 0.0001) were observed between Patlak-Ki and DTP-Ki. The Patlak-derived mean values of Ki, tumor-to-background-ratio, signal-to-noise-ratio, and contrast-to-noise-ratio were linearly correlated with the DTP method. CONCLUSIONS: Besides calculating the retention index as a commonly used quantification parameter inDTP imaging,our DTP method can accurately estimate Ki.
Asunto(s)
Estudios de Factibilidad , Fluorodesoxiglucosa F18 , Tomografía de Emisión de Positrones , Humanos , Fluorodesoxiglucosa F18/metabolismo , Tomografía de Emisión de Positrones/métodos , Factores de Tiempo , Procesamiento de Imagen Asistido por Computador/métodos , Cinética , Neoplasias/diagnóstico por imagen , Neoplasias/metabolismo , Transporte Biológico , Masculino , Femenino , Persona de Mediana Edad , Anciano , Simulación por ComputadorRESUMEN
BACKGROUND: To investigate the use of dynamic radiomics features derived from dual-time-point (DTP-feature) [18F]FDG PET metabolic uptake rate Ki parametric maps to develop a predictive model for response to chemotherapy in lymphoma patients. METHODS: We analyzed 126 lesions from 45 lymphoma patients (responding n = 75 and non-responding n = 51) treated with chemotherapy from two different centers. Static and DTP radiomics features were extracted from baseline static PET images and DTP Ki parametric maps. Spearman's rank correlations were calculated between static and DTP features to identify features with potential additional information. We first employed univariate analysis to determine correlations between individual features, and subsequently utilized multivariate analysis to derive predictive models utilizing DTP and static radiomics features before and after ComBat harmonization. For multivariate modeling, we utilized both the minimum redundancy maximum relevance feature selection technique and the XGBoost classifier. To evaluate our model, we partitioned the patient datasets into training/validation and testing sets using an 80/20% split. Different metrics for classification including area under the curve (AUC), sensitivity (SEN), specificity (SPE), and accuracy (ACC) were reported in test sets. RESULTS: Via Spearman's rank correlations, there was negligible to moderate correlation between 32 out of 65 DTP features and some static features (ρ < 0.7); all the other 33 features showed high correlations (ρ ≥ 0.7). In univariate modeling, no significant difference between AUC of DTP and static features was observed. GLRLM_RLNU from static features demonstrated a strong correlation (AUC = 0.75, p value = 0.0001, q value = 0.0007) with therapy response. The most predictive DTP features were GLCM_Energy, GLCM_Entropy, and Uniformity, each with AUC = 0.73, p value = 0.0001, and q value < 0.0005. In multivariate analysis, the mean ranges of AUCs increased following harmonization. Use of harmonization plus combining DTP and static features was shown to provide significantly improved predictions (AUC = 0.97 ± 0.02, accuracy = 0.89 ± 0.05, sensitivity = 0.92 ± 0.09, and specificity = 0.88 ± 0.05). All models depicted significant performance in terms of AUC, ACC, SEN, and SPE (p < 0.05, Mann-Whitney test). CONCLUSIONS: Our results demonstrate significant value in harmonization of radiomics features as well as combining DTP and static radiomics models for predicting response to chemotherapy in lymphoma patients.
RESUMEN
Introduction: This study was conducted to evaluate the predictive values of volumetric parameters and radiomic features (RFs) extracted from pretreatment 68Ga-PSMA PET and baseline clinical parameters in response to 177Lu-PSMA therapy. Materials and methods: In this retrospective multicenter study, mCRPC patients undergoing 177Lu-PSMA therapy were enrolled. According to the outcome of therapy, the patients were classified into two groups including positive biochemical response (BCR) (≥ 50% reduction in the serum PSA value) and negative BCR (< 50%). Sixty-five RFs, eight volumetric parameters, and also seventeen clinical parameters were evaluated for the prediction of BCR. In addition, the impact of such parameters on overall survival (OS) was evaluated. Results: 33 prostate cancer patients with a median age of 69 years (range: 49-89) were enrolled. BCR was observed in 22 cases (66%), and 16 cases (48.5%) died during the follow-up time. The results of Spearman correlation test indicated a significant relationship between BCR and treatment cycle, administered dose, HISTO energy, GLCM entropy, and GLZLM LZLGE (p<0.05). In addition, according to the Mann-Whitney U test, age, cycle, dose, GLCM entropy, and GLZLM LZLGE were significantly different between BCR and non BCR patients (p<0.05). According to the ROC curve analysis for feature selection for prediction of BCR, GLCM entropy, age, treatment cycle, and administered dose showed acceptable results (p<0.05). According to SVM for assessing the best model for prediction of response to therapy, GLCM entropy alone showed the highest predictive performance in treatment planning. For the entire cohort, the Kaplan-Meier test revealed a median OS of 21 months (95% CI: 12.12-29.88). The median OS was estimated at 26 months (95% CI: 17.43-34.56) for BCR patients and 13 months (95% CI: 9.18-16.81) for non BCR patients. Among all variables included in the Kaplan Meier, the only response to therapy was statistically significant (p=0.01). Conclusion: This exploratory study showed that the heterogeneity parameter of pretreatment 68Ga-PSMA PET images might be a potential predictive value for response to 177Lu-PSMA therapy in mCRPC; however, further prospective studies need to be carried out to verify these findings.
RESUMEN
PURPOSE: We aimed to investigate whether short dynamic PET imaging started at injection, complemented with routine clinical acquisition at 60-min post-injection (static), can achieve reliable kinetic analysis. METHODS: Dynamic and static 18F-2-fluoro-2-deoxy-D-glucose (FDG) PET data were generated using realistic simulations to assess uncertainties due to statistical noise as well as bias. Following image reconstructions, kinetic parameters obtained from a 2-tissue-compartmental model (2TCM) were estimated, making use of the static image, and the time duration of dynamic PET data were incrementally shortened. We also investigated, in the first 2-min, different frame sampling rates, towards optimized dynamic PET imaging. Kinetic parameters from shortened dynamic datasets were additionally estimated for 9 patients (15 scans) with liver metastases of colorectal cancer, and were compared with those derived from full dynamic imaging using correlation and Passing-Bablok regression analyses. RESULTS: The results showed that by reduction of dynamic scan times from 60-min to as short as 5-min, while using static data at 60-min post-injection, bias and variability stayed comparable in estimated kinetic parameters. Early frame samplings of 5, 24 and 30 s yielded highest biases compared to other schemes. An early frame sampling of 10 s generally kept both bias and variability to a minimum. In clinical studies, strong correlation (r ≥ 0.97, P < 0.0001) existed between all kinetic parameters in full vs. shortened scan protocols. CONCLUSIONS: Shortened 5-min dynamic scan, sampled as 12 × 10 + 6 × 30 s, followed by 3-min static image at 60-min post-injection, enables accurate and robust estimation of 2TCM parameters, while enabling generation of SUV estimates.