A deep learning-based framework for segmenting invisible clinical target volumes with estimated uncertainties for post-operative prostate cancer radiotherapy.

In post-operative radiotherapy for prostate cancer, precisely contouring the clinical target volume (CTV) to be irradiated is challenging, because the cancerous prostate gland has been surgically removed, so the CTV encompasses the microscopic spread of tumor cells, which cannot be visualized in clinical images like computed tomography or magnetic resonance imaging. In current clinical practice, physicians' segment CTVs manually based on their relationship with nearby organs and other clinical information, but this allows large inter-physician variability. Automating post-operative prostate CTV segmentation with traditional image segmentation methods has yielded suboptimal results. We propose using deep learning to accurately segment post-operative prostate CTVs. The model proposed is trained using labels that were clinically approved and used for patient treatment. To segment the CTV, we segment nearby organs first, then use their relationship with the CTV to assist CTV segmentation. To ease the encoding of distance-based features, which are important for learning both the CTV contours' overlap with the surrounding OARs and the distance from their borders, we add distance prediction as an auxiliary task to the CTV network. To make the DL model practical for clinical use, we use Monte Carlo dropout (MCDO) to estimate model uncertainty. Using MCDO, we estimate and visualize the 95% upper and lower confidence bounds for each prediction which informs the physicians of areas that might require correction. The model proposed achieves an average Dice similarity coefficient (DSC) of 0.87 on a holdout test dataset, much better than established methods, such as atlas-based methods (DSC<0.7). The predicted contours agree with physician contours better than medical resident contours do. A reader study showed that the clinical acceptability of the automatically segmented CTV contours is equal to that of approved clinical contours manually drawn by physicians. Our deep learning model can accurately segment CTVs with the help of surrounding organ masks. Because the DL framework can outperform residents, it can be implemented practically in a clinical workflow to generate initial CTV contours or to guide residents in generating these contours for physicians to review and revise. Providing physicians with the 95% confidence bounds could streamline the review process for an efficient clinical workflow as this would enable physicians to concentrate their inspecting and editing efforts on the large uncertain areas.

Synthesizing CT images from MR images with deep learning: model generalization for different datasets through transfer learning.

Background and purpose.Replacing CT imaging with MR imaging for MR-only radiotherapy has sparked the interest of many scientists and is being increasingly adopted in radiation oncology. Although many studies have focused on generating CT images from MR images, only models on data with the same dataset were tested. Therefore, how well the trained model will work for data from different hospitals and MR protocols is still unknown. In this study, we addressed the model generalization problem for the MR-to-CT conversion task.Materials and methods.Brain T2 MR and corresponding CT images were collected from SZSPH (source domain dataset), brain T1-FLAIR, T1-POST MR, and corresponding CT images were collected from The University of Texas Southwestern (UTSW) (target domain dataset). To investigate the model's generalizability ability, four potential solutions were proposed: source model, target model, combined model, and adapted model. All models were trained using the CycleGAN network. The source model was trained with a source domain dataset from scratch and tested with a target domain dataset. The target model was trained with a target domain dataset and tested with a target domain dataset. The combined model was trained with both source domain and target domain datasets, and tested with the target domain dataset. The adapted model used a transfer learning strategy to train a CycleGAN model with a source domain dataset and retrain the pre-trained model with a target domain dataset. MAE, RMSE, PSNR, and SSIM were used to quantitatively evaluate model performance on a target domain dataset.Results.The adapted model achieved best quantitative results of 74.56 ± 8.61, 193.18 ± 17.98, 28.30 ± 0.83, and 0.84 ± 0.01 for MAE, RMSE, PSNR, and SSIM using the T1-FLAIR dataset and 74.89 ± 15.64, 195.73 ± 31.29, 27.72 ± 1.43, and 0.83 ± 0.04 for MAE, RMSE, PSNR, and SSIM using the T1-POST dataset. The source model had the poorest performance.Conclusions.This work indicates high generalization ability to generate synthetic CT images from small training datasets of MR images using pre-trained CycleGAN. The quantitative results of the test data, including different scanning protocols and different acquisition centers, indicated the proof of this concept.

Author Correction: Cooperative nutrient accumulation sustains growth of mammalian cells.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

Multi-objective ensemble deep learning using electronic health records to predict outcomes after lung cancer radiotherapy.

Accurately predicting treatment outcome is crucial for creating personalized treatment plans and follow-up schedules. Electronic health records (EHRs) contain valuable patient-specific information that can be leveraged to improve outcome prediction. We propose a reliable multi-objective ensemble deep learning (MoEDL) method that uses features extracted from EHRs to predict high risk of treatment failure after radiotherapy in patients with lung cancer. The dataset used in this study contains EHRs of 814 patients who had not achieved disease-free status and 193 patients who were disease-free with at least one year follow-up time after lung cancer radiation therapy. The proposed MoEDL consists of three phases: (1) training with dynamic ensemble deep learning; (2) model selection with adaptive multi-objective optimization; and (3) testing with evidential reasoning (ER) fusion. Specifically, in the training phase, we employ deep perceptron networks as base learners to handle various issues with EHR data. The architecture and key hyper-parameters of each base learner are dynamically adjusted to increase the diversity of learners while reducing the time spent tuning hyper-parameters. Furthermore, we integrate the snapshot ensembles (SE) restarting strategy, multi-objective optimization, and ER fusion to improve the prediction robustness and accuracy of individual networks. The SE restarting strategy can yield multiple candidate models at no additional training cost in the training stage. The multi-objective model simultaneously considers sensitivity, specificity, and AUC as objective functions, overcoming the limitations of single-objective-based model selection. For the testing stage, we utilized an analytic ER rule to fuse the output scores from each optimal model to obtain reliable and robust predictive results. Our experimental results demonstrate that MoEDL can perform better than other conventional methods.

Cooperative nutrient accumulation sustains growth of mammalian cells.

The coordination of metabolic processes to allow increased nutrient uptake and utilization for macromolecular synthesis is central for cell growth. Although studies of bulk cell populations have revealed important metabolic and signaling requirements that impact cell growth on long time scales, whether the same regulation influences short-term cell growth remains an open question. Here we investigate cell growth by monitoring mass accumulation of mammalian cells while rapidly depleting particular nutrients. Within minutes following the depletion of glucose or glutamine, we observe a growth reduction that is larger than the mass accumulation rate of the nutrient. This indicates that if one particular nutrient is depleted, the cell rapidly adjusts the amount that other nutrients are accumulated, which is consistent with cooperative nutrient accumulation. Population measurements of nutrient sensing pathways involving mTOR, AKT, ERK, PKA, MST1, or AMPK, or pro-survival pathways involving autophagy suggest that they do not mediate this growth reduction. Furthermore, the protein synthesis rate does not change proportionally to the mass accumulation rate over these time scales, suggesting that intracellular metabolic pools buffer the growth response. Our findings demonstrate that cell growth can be regulated over much shorter time scales than previously appreciated.

Direct observation of mammalian cell growth and size regulation.

We introduce a microfluidic system for simultaneously measuring single-cell mass and cell cycle progression over multiple generations. We use this system to obtain over 1,000 h of growth data from mouse lymphoblast and pro-B-cell lymphoid cell lines. Cell lineage analysis revealed a decrease in the growth rate variability at the G1-S phase transition, which suggests the presence of a growth rate threshold for maintaining size homeostasis.

Mass sensors with mechanical traps for weighing single cells in different fluids.

We present two methods by which single cells can be mechanically trapped and continuously monitored within the suspended microchannel resonator (SMR) mass sensor. Since the fluid surrounding the trapped cell can be quickly and completely replaced on demand, our methods are well suited for measuring changes in cell size and growth in response to drugs or other chemical stimuli. We validate our methods by measuring the density of single polystyrene beads and Saccharomyces cerevisiae yeast cells with a precision of approximately 10(-3) g cm(-3), and by monitoring the growth of single mouse lymphoblast cells before and after drug treatment.

Refining motifs by improving information content scores using neighborhood profile search.

The main goal of the motif finding problem is to detect novel, over-represented unknown signals in a set of sequences (e.g. transcription factor binding sites in a genome). The most widely used algorithms for finding motifs obtain a generative probabilistic representation of these over-represented signals and try to discover profiles that maximize the information content score. Although these profiles form a very powerful representation of the signals, the major difficulty arises from the fact that the best motif corresponds to the global maximum of a non-convex continuous function. Popular algorithms like Expectation Maximization (EM) and Gibbs sampling tend to be very sensitive to the initial guesses and are known to converge to the nearest local maximum very quickly. In order to improve the quality of the results, EM is used with multiple random starts or any other powerful stochastic global methods that might yield promising initial guesses (like projection algorithms). Global methods do not necessarily give initial guesses in the convergence region of the best local maximum but rather suggest that a promising solution is in the neighborhood region. In this paper, we introduce a novel optimization framework that searches the neighborhood regions of the initial alignment in a systematic manner to explore the multiple local optimal solutions. This effective search is achieved by transforming the original optimization problem into its corresponding dynamical system and estimating the practical stability boundary of the local maximum. Our results show that the popularly used EM algorithm often converges to sub-optimal solutions which can be significantly improved by the proposed neighborhood profile search. Based on experiments using both synthetic and real datasets, our method demonstrates significant improvements in the information content scores of the probabilistic models. The proposed method also gives the flexibility in using different local solvers and global methods depending on their suitability for some specific datasets.