Evaluation of Semiautomatic and Deep Learning-Based Fully Automatic Segmentation Methods on [18F]FDG PET/CT Images from Patients with Lymphoma: Influence on Tumor Characterization.

The objective is to assess the performance of seven semiautomatic and two fully automatic segmentation methods on [18F]FDG PET/CT lymphoma images and evaluate their influence on tumor quantification. All lymphoma lesions identified in 65 whole-body [18F]FDG PET/CT staging images were segmented by two experienced observers using manual and semiautomatic methods. Semiautomatic segmentation using absolute and relative thresholds, k-means and Bayesian clustering, and a self-adaptive configuration (SAC) of k-means and Bayesian was applied. Three state-of-the-art deep learning-based segmentations methods using a 3D U-Net architecture were also applied. One was semiautomatic and two were fully automatic, of which one is publicly available. Dice coefficient (DC) measured segmentation overlap, considering manual segmentation the ground truth. Lymphoma lesions were characterized by 31 features. Intraclass correlation coefficient (ICC) assessed features agreement between different segmentation methods. Nine hundred twenty [18F]FDG-avid lesions were identified. The SAC Bayesian method achieved the highest median intra-observer DC (0.87). Inter-observers' DC was higher for SAC Bayesian than manual segmentation (0.94 vs 0.84, p < 0.001). Semiautomatic deep learning-based median DC was promising (0.83 (Obs1), 0.79 (Obs2)). Threshold-based methods and publicly available 3D U-Net gave poorer results (0.56 ≤ DC ≤ 0.68). Maximum, mean, and peak standardized uptake values, metabolic tumor volume, and total lesion glycolysis showed excellent agreement (ICC ≥ 0.92) between manual and SAC Bayesian segmentation methods. The SAC Bayesian classifier is more reproducible and produces similar lesion features compared to manual segmentation, giving the best concordant results of all other methods. Deep learning-based segmentation can achieve overall good segmentation results but failed in few patients impacting patients' clinical evaluation.

Are lesion features reproducible between 18F-FDG PET/CT images when acquired on analog or digital PET/CT scanners?

OBJECTIVES: To compare lesion features extracted from 18F-FDG PET/CT images acquired on analog and digital scanners, on consecutive imaging data from the same subjects. METHODS: Whole-body 18F-FDG PET/CT images from 55 oncological patients were acquired twice after a single 18F-FDG injection, with a digital and an analog PET/CT scanner, alternately. Twenty-nine subjects were examined first on the digital, and 26 first on the analog equipment. Image reconstruction was performed using manufacturer standard clinical protocols and protocols that fulfilled EARL1 specifications. Twenty-five features based on lesion standardized uptake value (SUV) and geometry were assessed. To compare these features, intraclass correlation coefficient (ICC), relative difference (RD), absolute value of RD (|RD|), and repeatability coefficient (RC) were used. RESULTS: In total, 323 18F-FDG avid lesions were identified. High agreement (ICC > 0.75) was obtained for most of the lesion features pulled out from both scanners' imaging data, especially when reconstruction protocols fulfilled EARL1 specifications. For EARL1 reconstruction images, the features frequently used in clinics, SUVmax, SUVpeak, SUVmean, metabolic tumor volume, and total lesion glycolysis, reached an ICC of 0.92, 0.95, 0.87, 0.98, and 0.98, and a median RD (digital-analog) of 3%, 5%, 4%, - 3% and 1%, respectively. Using standard reconstruction protocols, the ICC were 0.84, 0.93, 0.80, 0.98, and 0.98, and the RD were 20%, 11%, 13%, - 7%, and 7%, respectively. CONCLUSION: Under controlled acquisition and reconstruction parameters, most of the features studied can be used for research and clinical work. This is especially important for multicenter studies and patient follow-ups. KEY POINTS: • Using manufacturer standard clinical reconstruction protocols, lesions SUV was significantly higher when using the digital scanner, especially the SUVmax that was approximately 20% higher. • High agreement was obtained for the majority of the lesion features when using reconstruction protocols that fulfilled EARL1 specifications. • Longitudinal patient studies can be performed interchangeably between digital and analog scanners when both fulfill EARL1 specifications.

Coupling sparse Cox models with clustering of longitudinal transcriptomics data for trauma prognosis.

BACKGROUND: Longitudinal gene expression analysis and survival modeling have been proved to add valuable biological and clinical knowledge. This study proposes a novel framework to discover gene signatures and patterns in a high-dimensional time series transcriptomics data and to assess their association with hospital length of stay. METHODS: We investigated a longitudinal and high-dimensional gene expression dataset from 168 blunt-force trauma patients followed during the first 28 days after injury. To model the length of stay, an initial dimensionality reduction step was performed by applying Cox regression with elastic net regularization using gene expression data from the first hospitalization days. Also, a novel methodology to impute missing values to the genes selected previously was proposed. We then applied multivariate time series (MTS) clustering to analyse gene expression over time and to stratify patients with similar trajectories. The validation of the patients' partitions obtained by MTS clustering was performed using Kaplan-Meier curves and log-rank tests. RESULTS: We were able to unravel 22 genes strongly associated with hospital's discharge. Their expression values in the first days after trauma showed to be good predictors of the length of stay. The proposed mixed imputation method allowed to achieve a complete dataset of short time series with a minimum loss of information for the 28 days of follow-up. MTS clustering enabled to group patients with similar genes trajectories and, notably, with similar discharge days from the hospital. Patients within each cluster have comparable genes' trajectories and may have an analogous response to injury. CONCLUSION: The proposed framework was able to tackle the joint analysis of time-to-event information with longitudinal multivariate high-dimensional data. The application to length of stay and transcriptomics data revealed a strong relationship between gene expression trajectory and patients' recovery, which may improve trauma patient's management by healthcare systems. The proposed methodology can be easily adapted to other medical data, towards more effective clinical decision support systems for health applications.