Domain-specific cues improve robustness of deep learning-based segmentation of CT volumes

Abstract

Machine learning has considerably improved medical image analysis in the past years. Although datadriven approaches are intrinsically adaptive and thus, generic, they often do not perform the same way on data from different imaging modalities. In particular computed tomography (CT) data poses many challenges to medical image segmentation based on convolutional neural networks (CNNs), mostly due to the broad dynamic range of intensities and the varying number of recorded slices of CT volumes. In this paper, we address these issues with a framework that adds domain-specific data preprocessing and augmentation to state-of-the-art CNN architectures. Our major focus is to stabilise the prediction performance over samples as a mandatory requirement for use in automated and semiautomated workflows in the clinical environment. To validate the architecture-independent effects of our approach we compare a neural architecture based on dilated convolutions for parallel multi-scale processing (a modified Mixed-Scale Dense Network: MS-D Net) to traditional scaling operations (a modified U-Net). Finally, we show that an ensemble model combines the strengths across different individual methods. Our framework is simple to implement into existing deep learning pipelines for CT analysis. It performs well on a range of tasks such as liver and kidney segmentation, without significant differences in prediction performance on strongly differing volume sizes and varying slice thickness. Thus our framework is an essential step towards performing robust segmentation of unknown real-world samples. The geometry of tumours, as described by, e.g. its size, shape or location, is a central clinical feature. Changes in these geometric characteristics are essential indicators of disease progression and can be used to measure treatment effects. An automated, quantitative assessment of these aspects and their changes from radiological images would yield an efficient and objective tool for radiologists to monitor the course of the disease. Thus, a reliable and accurate automated segmentation method is desirable to extract spatial tumour and organ characteristics from computed tomography (CT) volumes. In recent years, convolutional neural networks (CNNs) 1 became the state of the art method for image segmentation, as well as many other tasks in computer vision 2 , such as image classification, object detection and object tracking 3. The applications of CNNs are diverse, but the general data handling or preprocessing is often very similar in each case since the feature extraction is performed internally by the CNN itself. Improvements in the application of CNNs for medical image processing often address changes in the neural network architecture, the training algorithm or the use case 4,5. At the same time, most authors tend to ignore the data handling itself, treating medical images such as CT volumes the same way as grayscale or RGB images with additional dimensions. However, this approach neglects prior information about the specific physical proce...

Deep Learning: A Comprehensive Overview on Techniques, Taxonomy, Applications and Research Directions

“…For instance, a task-specific feature extractor considering domain knowledge in smart manufacturing for fault diagnosis can resolve the issues in traditional deep-learningbased methods [28]. Similarly, domain knowledge in medical image analysis [58], financial sentiment analysis [49], cybersecurity analytics [94,103] as well as conceptual data model in which semantic information, (i.e., meaningful for a system, rather than merely correlational) [45,121,131] is included, can play a vital role in the area. Transfer learning could be an effective way to get started on a new challenge with domain knowledge.…”

Segmentation of male pelvic organs on computed tomography with a deep neural network fine-tuned by a level-set method

“…There is also the presence of bone, which becomes overwhelmingly white, but this does not present a problem because it is not the focus in this study. This method reduces the range of intensity values in each sample, facilitating model convergence (18). Intensity normalization to zero mean and unit variance is also performed to improve neural network training.…”

Neural Network-derived perfusion maps: a Model-free approach to computed tomography perfusion in patients with acute ischemic stroke

“…Considering the apparently similar performance of CNNs and deconvolution-based algorithms, one might ask why the former approach might be preferable. Although machine learning algorithms have largely proven to overcome conventional image processing algorithms in practically every field, applications to CTP imaging are still limited (segmentation, [20][21][22] noise reduction, [22][23][24] novelty detection, [23,25] radiation dose reduction [23]). In particular, up until now generation of synthetic maps In this preliminary work, pre-processed images were used as input.…”