TIminer: NGS data mining pipeline for cancer immunology and immunotherapy.

SUMMARY: Recently, a number of powerful computational tools for dissecting tumor-immune cell interactions from next-generation sequencing data have been developed. However, the assembly of analytical pipelines and execution of multi-step workflows are laborious and involve a large number of intermediate steps with many dependencies and parameter settings. Here we present TIminer, an easy-to-use computational pipeline for mining tumor-immune cell interactions from next-generation sequencing data. TIminer enables integrative immunogenomic analyses, including: human leukocyte antigens typing, neoantigen prediction, characterization of immune infiltrates and quantification of tumor immunogenicity. AVAILABILITY AND IMPLEMENTATION: TIminer is freely available at http://icbi.i-med.ac.at/software/timiner/timiner.shtml. CONTACT: zlatko.trajanoski@i-med.ac.at. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

HaN-Seg: The head and neck organ-at-risk CT and MR segmentation challenge.

BACKGROUND AND PURPOSE: To promote the development of auto-segmentation methods for head and neck (HaN) radiation treatment (RT) planning that exploit the information of computed tomography (CT) and magnetic resonance (MR) imaging modalities, we organized HaN-Seg: The Head and Neck Organ-at-Risk CT and MR Segmentation Challenge. MATERIALS AND METHODS: The challenge task was to automatically segment 30 organs-at-risk (OARs) of the HaN region in 14 withheld test cases given the availability of 42 publicly available training cases. Each case consisted of one contrast-enhanced CT and one T1-weighted MR image of the HaN region of the same patient, with up to 30 corresponding reference OAR delineation masks. The performance was evaluated in terms of the Dice similarity coefficient (DSC) and 95-percentile Hausdorff distance (HD95), and statistical ranking was applied for each metric by pairwise comparison of the submitted methods using the Wilcoxon signed-rank test. RESULTS: While 23 teams registered for the challenge, only seven submitted their methods for the final phase. The top-performing team achieved a DSC of 76.9 % and a HD95 of 3.5 mm. All participating teams utilized architectures based on U-Net, with the winning team leveraging rigid MR to CT registration combined with network entry-level concatenation of both modalities. CONCLUSION: This challenge simulated a real-world clinical scenario by providing non-registered MR and CT images with varying fields-of-view and voxel sizes. Remarkably, the top-performing teams achieved segmentation performance surpassing the inter-observer agreement on the same dataset. These results set a benchmark for future research on this publicly available dataset and on paired multi-modal image segmentation in general.

Tackling the class imbalance problem of deep learning-based head and neck organ segmentation.

PURPOSE: The segmentation of organs at risk (OAR) is a required precondition for the cancer treatment with image- guided radiation therapy. The automation of the segmentation task is therefore of high clinical relevance. Deep learning (DL)-based medical image segmentation is currently the most successful approach, but suffers from the over-presence of the background class and the anatomically given organ size difference, which is most severe in the head and neck (HAN) area. METHODS: To tackle the HAN area-specific class imbalance problem, we first optimize the patch size of the currently best performing general-purpose segmentation framework, the nnU-Net, based on the introduced class imbalance measurement, and second introduce the class adaptive Dice loss to further compensate for the highly imbalanced setting. RESULTS: Both the patch size and the loss function are parameters with direct influence on the class imbalance, and their optimization leads to a 3% increase in the Dice score and 22% reduction in the 95% Hausdorff distance compared to the baseline, finally reaching [Formula: see text] and [Formula: see text] mm for the segmentation of seven HAN organs using a single and simple neural network. CONCLUSION: The patch size optimization and the class adaptive Dice loss are both simply integrable in current DL-based segmentation approaches and allow to increase the performance for class imbalance segmentation tasks.

Heart rate estimation from ballistocardiographic signals using deep learning.

Objective.Ballistocardiography (BCG) is an unobtrusive approach for cost-effective and patient-friendly health monitoring. In this work, deep learning methods are used for heart rate estimation from BCG signals and are compared against five digital signal processing methods found in literature.Approach.The models are evaluated on a dataset featuring BCG recordings from 42 patients, acquired with a pneumatic system. Several different deep learning architectures, including convolutional, recurrent and a combination of both are investigated. Besides model performance, we are also concerned about model size and specifically investigate less complex and smaller networks.Main results.Deep learning models outperform traditional methods by a large margin. Across 14 patients in a held-out testing set, an architecture with stacked convolutional and recurrent layers achieves an average mean absolute error (MAE) of 2.07 beat min-1, whereas the best-performing traditional method reaches 4.24 beat min-1. Besides smaller errors, deep learning models show more consistent performance across different patients, indicating the ability to better deal with inter-patient variability, a prevalent issue in BCG analysis. In addition, we develop a smaller version of the best-performing architecture, that only features 8283 parameters, yet still achieves an average MAE of 2.32 beat min-1on the testing set.Significance.This is the first study that applies and compares different deep learning architectures to heart rate estimation from bed-based BCG signals. Compared to signal processing algorithms, deep learning models show dramatically smaller errors and more consistent results across different individuals. The results show that using smaller models instead of excessively large ones can lead to sufficient performance for specific biosignal processing applications. Additionally, we investigate the use of fully convolutional networks for 1D signal processing, which is rarely applied in literature.

Training of head and neck segmentation networks with shape prior on small datasets.

PURPOSE: Cancer in the head and neck area is commonly treated with radiotherapy. A key step for low-risk treatment is the accurate delineation of organs at risk in the planning imagery. The success of deep learning in image segmentation led to automated algorithms achieving human expert performance on certain datasets. However, such algorithms require large datasets for training and fail to segment previously unseen pathologies, where human experts still succeed. As pathologies are rare and large datasets costly to generate, we investigate the effect of: reduced training data, batch sizes and incorporation of prior knowledge. METHODS: The small data problem is studied by training a full-volume segmentation network with the reduced amount of data from the MICCAI 2015 head and neck segmentation challenge. To improve the segmentation, we evaluate the batch size as a hyper-parameter and first study and then incorporate a stacked autoencoder as shape prior into the training process. RESULTS: We found that using half of the training data (12 images of 25) results in an accuracy drop of only 3% for the segmentation of organs at risk. Also, the batch size turns out to be relevant for the quality of the segmentation when trained with less than half of the data. By applying PCA on the autoencoder's latent space we achieve a compact and accurate shape model, which is used as a regularizer and significantly improves the segmentation results. CONCLUSION: Small training data of up to 12 training images is enough to train accurate head and neck segmentation models. By using a shape prior for regularization, the performance of the segmentation can be improved significantly on the full dataset. When training on fewer than 12 images, the batch size is relevant and models have to be trained much longer until convergence.

Multi-organ segmentation of the head and neck area: an efficient hierarchical neural networks approach.

PURPOSE: In radiation therapy, a key step for a successful cancer treatment is image-based treatment planning. One objective of the planning phase is the fast and accurate segmentation of organs at risk and target structures from medical images. However, manual delineation of organs, which is still the gold standard in many clinical environments, is time-consuming and prone to inter-observer variations. Consequently, many automated segmentation methods have been developed. METHODS: In this work, we train two hierarchical 3D neural networks to segment multiple organs at risk in the head and neck area. First, we train a coarse network on size-reduced medical images to locate the organs of interest. Second, a subsequent fine network on full-resolution images is trained for a final accurate segmentation. The proposed method is purely deep learning based; accordingly, no pre-registration or post-processing is required. RESULTS: The approach has been applied on a publicly available computed tomography dataset, created for the MICCAI 2015 Auto-Segmentation challenge. In an extensive evaluation process, the best configurations for the trained networks have been determined. Compared to the existing methods, the presented approach shows state-of-the-art performance for the segmentation of seven different structures in the head and neck area. CONCLUSION: We conclude that 3D neural networks outperform the most existing model- and atlas-based methods for the segmentation of organs at risk in the head and neck area. The ease of use, high accuracy and the test time efficiency of the method make it promising for image-based treatment planning in clinical practice.