Combination of clinical, radiomic, and "delta" radiomic features in survival prediction of metastatic gastroesophageal adenocarcinoma.

Objectives: To identify combined clinical, radiomic, and delta-radiomic features in metastatic gastroesophageal adenocarcinomas (GEAs) that may predict survival outcomes. Methods: A total of 166 patients with metastatic GEAs on palliative chemotherapy with baseline and treatment/follow-up (8-12 weeks) contrast-enhanced CT were retrospectively identified. Demographic and clinical data were collected. Three-dimensional whole-lesional radiomic analysis was performed on the treatment/follow-up scans. "Delta" radiomic features were calculated based on the change in radiomic parameters compared to the baseline. The univariable analysis (UVA) Cox proportional hazards model was used to select clinical variables predictive of overall survival (OS) and progression-free survival (PFS) (p-value <0.05). The radiomic and "delta" features were then assessed in a multivariable analysis (MVA) Cox model in combination with clinical features identified on UVA. Features with a p-value <0.01 in the MVA models were selected to assess their pairwise correlation. Only non-highly correlated features (Pearson's correlation coefficient <0.7) were included in the final model. Leave-one-out cross-validation method was used, and the 1-year area under the receiver operating characteristic curve (AUC) was calculated for PFS and OS. Results: Of the 166 patients (median age of 59.8 years), 114 (69%) were male, 139 (84%) were non-Asian, and 147 (89%) had an Eastern Cooperative Oncology Group (ECOG) performance status of 0-1. The median PFS and OS on treatment were 3.6 months (95% CI 2.86, 4.63) and 9 months (95% CI 7.49, 11.04), respectively. On UVA, the number of chemotherapy cycles and number of lesions at the end of treatment were associated with both PFS and OS (p < 0.001). ECOG status was associated with OS (p = 0.0063), but not PFS (p = 0.054). Of the delta-radiomic features, delta conventional HUmin, delta gray-level zone length matrix (GLZLM) GLNU, and delta GLZLM LGZE were incorporated into the model for PFS, and delta shape compacity was incorporated in the model for OS. Of the treatment/follow-up radiomic features, shape compacity and neighborhood gray-level dependence matrix (NGLDM) contrast were used in both models. The combined 1-year AUC (Kaplan-Meier estimator) was 0.82 and 0.81 for PFS and OS, respectively. Conclusions: A combination of clinical, radiomics, and delta-radiomic features may predict PFS and OS in GEAs with reasonable accuracy.

Convolutional neural networks for improving image quality with noisy PET data.

GOAL: PET is a relatively noisy process compared to other imaging modalities, and sparsity of acquisition data leads to noise in the images. Recent work has focused on machine learning techniques to improve PET images, and this study investigates a deep learning approach to improve the quality of reconstructed image volumes through denoising by a 3D convolution neural network. Potential improvements were evaluated within a clinical context by physician performance in a reading task. METHODS: A wide range of controlled noise levels was emulated from a set of chest PET data in patients with lung cancer, and a convolutional neural network was trained to denoise the reconstructed images using the full-count reconstructions as the ground truth. The benefits, over conventional Gaussian smoothing, were quantified across all noise levels by observer performance in an image ranking and lesion detection task. RESULTS: The CNN-denoised images were generally ranked by the physicians equal to or better than the Gaussian-smoothed images for all count levels, with the largest effects observed in the lowest-count image sets. For the CNN-denoised images, overall lesion contrast recovery was 60% and 90% at the 1 and 20 million count levels, respectively. Notwithstanding the reduced lesion contrast recovery in noisy data, the CNN-denoised images also yielded better lesion detectability in low count levels. For example, at 1 million true counts, the average true positive detection rate was around 40% for the CNN-denoised images and 30% for the smoothed images. CONCLUSION: Significant improvements were found for CNN-denoising for very noisy images, and to some degree for all noise levels. The technique presented here offered however limited benefit for detection performance for images at the count levels routinely encountered in the clinic.

Perforations associated with peripherally inserted central catheters in a neonatal population.

BACKGROUND: Peripherally inserted central catheters (PICCs) are increasingly used in neonates but perforations can result in devastating complications such as pericardial and pleural effusions. Identifying risk factors may guide surveillance and reduce morbidity and mortality. OBJECTIVE: To determine the risk factors for PICC perforation in neonates. MATERIALS AND METHODS: Retrospective case:control (1:2) study of neonates admitted between 2004-2014. Charts and imaging were reviewed for clinical and therapeutic risk factors. RESULTS: Among 3,454 PICCs, 15 cases of perforation (incidence 0.4%, 5 pericardial effusions, 10 pleural effusions) were matched to 30 controls, based on gestation and insertion date. Timing of perforations post-insertion was median 4 days for pericardial effusions and 21.5 days for pleural effusions. A risk factor for pericardial effusion was lower weight at PICC insertion compared with controls. There were no statistically significant differences between cases and controls in catheter material, insertion site, PICC size and lumen number. Among upper limb PICCs, pericardial effusions were associated with tip positions more proximal to the heart at insertion (P=0.005) and at perforation (P=0.008), compared with controls. Pleural effusions were associated with tip positions more distal from the heart at perforation (P=0.008). Within 48 h before perforation, high/medium risk infusions included total parenteral nutrition (100% cases vs. 56.7% controls, P=0.002) and vancomycin (60% cases vs. 23.3% controls, P=0.02). CONCLUSION: PICC-associated pericardial effusions and pleural effusions are rare but inherent risks and can occur at any time after insertion. Risk factors and etiologies are multifactorial, but PICC tip position may be a modifiable risk factor. To mitigate this risk, we have developed and disseminated guidelines for target PICC positions and routinely do radiographs to monitor PICCs for migration and malposition in our NICU. The increased knowledge of risk profiles from this study has helped focus surveillance efforts and facilitate early recognition and treatment.