The semiotics of medical image Segmentation

Formal Methods for Establishing Simulation Interoperability for Military Health System Applications

INTRODUCTION

Advancements in information technology have facilitated information exchange practices within the Military Health System (MHS), enabling "systems of systems" approaches that broaden and coordinate the set of capabilities available to enhance patient outcomes. This is applicable for MHS modeling and simulation (M&S) applications as well. Learning from successful approaches applied in current interoperability solutions used in the military helps to ensure interoperability practices yield trusted compositions of simulations.

MATERIALS AND METHODS

The use of formal methods provides the rigor necessary to unambiguously communicate these approaches across the MHS community. Here, 3 formal methods are proposed to ensure the harmonization of models and alignment of M&S data needed for simulation interoperability for MHS applications.

RESULTS

To clarify considerations relevant for establishing simulation interoperability, the proposed formal methods are examined within a notional example of an injury sustained because of blast exposure. The first method applies the principles of semiotics, addressing the coding of information via syntax and semantics, to understand how to align and transform data across simulations within a composition. The second method applies the concepts of well-specified co-simulations, and the use of different techniques, tools, and algorithms to address the composition and synchronization of M&S components. The third method applies the mathematical branch of model theory to codify expert knowledge about concepts, assumptions, and constraints to ensure conceptual alignment within the simulation composition.

CONCLUSIONS

Biomedical research must contend with complexity inherent to computational human body modeling, enlisting expert knowledge from multiple domains supporting the development of cross-disciplinary research tools that resolve research foci and associated differences in underlying theories, methods, and applied tools. This is closely related to the broader context of digital engineering for military systems engineering.

Deep-learning-based image segmentation for image-based computational hemodynamic analysis of abdominal aortic aneurysms: a comparison study

Computational hemodynamics is increasingly being used to quantify hemodynamic characteristics in and around abdominal aortic aneurysms (AAA) in a patient-specific fashion. However, the time-consuming manual annotation hinders the clinical translation of computational hemodynamic analysis. Thus, we investigate the feasibility of using deep-learning-based image segmentation methods to reduce the time required for manual segmentation. Two of the latest deep-learning-based image segmentation methods, ARU-Net and CACU-Net, were used to test the feasibility of automated computer model creation for computational hemodynamic analysis. Morphological features and hemodynamic metrics of 30 computed tomography angiography (CTA) scans were compared between pre-dictions and manual models. The DICE score for both networks was 0.916, and the correlation value was above 0.95, indicating their ability to generate models comparable to human segmentation. The Bland-Altman analysis shows a good agreement between deep learning and manual segmentation results. Compared with manual (computational hemodynamics) model recreation, the time for automated computer model generation was significantly reduced (from ∼2 h to ∼10 min). Automated image segmentation can significantly reduce time expenses on the recreation of patient-specific AAA models. Moreover, our study showed that both CACU-Net and ARU-Net could accomplish AAA segmentation, and CACU-Net outperformed ARU-Net in terms of accuracy and time-saving.

An Ostensive Information Architecture to Enhance Semantic Interoperability for Healthcare Information Systems

Semantic interoperability establishes intercommunications and enables data sharing across disparate systems. In this study, we propose an ostensive information architecture for healthcare information systems to decrease ambiguity caused by using signs in different contexts for different purposes. The ostensive information architecture adopts a consensus-based approach initiated from the perspective of information systems re-design and can be applied to other domains where information exchange is required between heterogeneous systems. Driven by the issues in FHIR (Fast Health Interoperability Resources) implementation, an ostensive approach that supplements the current lexical approach in semantic exchange is proposed. A Semantic Engine with an FHIR knowledge graph as the core is constructed using Neo4j to provide semantic interpretation and examples. The MIMIC III (Medical Information Mart for Intensive Care) datasets and diabetes datasets have been employed to demonstrate the effectiveness of the proposed information architecture. We further discuss the benefits of the separation of semantic interpretation and data storage from the perspective of information system design, and the semantic reasoning towards patient-centric care underpinned by the Semantic Engine.

Combining natural and artificial intelligence for robust automatic anatomy segmentation: Application in neck and thorax auto-contouring

BACKGROUND

Automatic segmentation of 3D objects in computed tomography (CT) is challenging. Current methods, based mainly on artificial intelligence (AI) and end-to-end deep learning (DL) networks, are weak in garnering high-level anatomic information, which leads to compromised efficiency and robustness. This can be overcome by incorporating natural intelligence (NI) into AI methods via computational models of human anatomic knowledge.

PURPOSE

We formulate a hybrid intelligence (HI) approach that integrates the complementary strengths of NI and AI for organ segmentation in CT images and illustrate performance in the application of radiation therapy (RT) planning via multisite clinical evaluation.

METHODS

The system employs five modules: (i) body region recognition, which automatically trims a given image to a precisely defined target body region; (ii) NI-based automatic anatomy recognition object recognition (AAR-R), which performs object recognition in the trimmed image without DL and outputs a localized fuzzy model for each object; (iii) DL-based recognition (DL-R), which refines the coarse recognition results of AAR-R and outputs a stack of 2D bounding boxes (BBs) for each object; (iv) model morphing (MM), which deforms the AAR-R fuzzy model of each object guided by the BBs output by DL-R; and (v) DL-based delineation (DL-D), which employs the object containment information provided by MM to delineate each object. NI from (ii), AI from (i), (iii), and (v), and their combination from (iv) facilitate the HI system.

RESULTS

The HI system was tested on 26 organs in neck and thorax body regions on CT images obtained prospectively from 464 patients in a study involving four RT centers. Data sets from one separate independent institution involving 125 patients were employed in training/model building for each of the two body regions, whereas 104 and 110 data sets from the 4 RT centers were utilized for testing on neck and thorax, respectively. In the testing data sets, 83% of the images had limitations such as streak artifacts, poor contrast, shape distortion, pathology, or implants. The contours output by the HI system were compared to contours drawn in clinical practice at the four RT centers by utilizing an independently established ground-truth set of contours as reference. Three sets of measures were employed: accuracy via Dice coefficient (DC) and Hausdorff boundary distance (HD), subjective clinical acceptability via a blinded reader study, and efficiency by measuring human time saved in contouring by the HI system. Overall, the HI system achieved a mean DC of 0.78 and 0.87 and a mean HD of 2.22 and 4.53 mm for neck and thorax, respectively. It significantly outperformed clinical contouring in accuracy and saved overall 70% of human time over clinical contouring time, whereas acceptability scores varied significantly from site to site for both auto-contours and clinically drawn contours.

CONCLUSIONS

The HI system is observed to behave like an expert human in robustness in the contouring task but vastly more efficiently. It seems to use NI help where image information alone will not suffice to decide, first for the correct localization of the object and then for the precise delineation of the boundary.

Combining simple interactivity and machine learning: a separable deep learning approach to subthalamic nucleus localization and segmentation in MRI for deep brain stimulation surgical planning

Purpose: Deep brain stimulation (DBS) is an interventional treatment for some neurological and neurodegenerative diseases. For example, in Parkinson's disease, DBS electrodes are positioned at particular locations within the basal ganglia to alleviate the patient's motor symptoms. These interventions depend greatly on a preoperative planning stage in which potential targets and electrode trajectories are identified in a preoperative MRI. Due to the small size and low contrast of targets such as the subthalamic nucleus (STN), their segmentation is a difficult task. Machine learning provides a potential avenue for development, but it has difficulty in segmenting such small structures in volumetric images due to additional problems such as segmentation class imbalance. Approach: We present a two-stage separable learning workflow for STN segmentation consisting of a localization step that detects the STN and crops the image to a small region and a segmentation step that delineates the structure within that region. The goal of this decoupling is to improve accuracy and efficiency and to provide an intermediate representation that can be easily corrected by a clinical user. This correction capability was then studied through a human-computer interaction experiment with seven novice participants and one expert neurosurgeon. Results: Our two-step segmentation significantly outperforms the comparative registration-based method currently used in clinic and approaches the fundamental limit on variability due to the image resolution. In addition, the human-computer interaction experiment shows that the additional interaction mechanism allowed by separating STN segmentation into two steps significantly improves the users' ability to correct errors and further improves performance. Conclusions: Our method shows that separable learning not only is feasible for fully automatic STN segmentation but also leads to improved interactivity that can ease its translation into clinical use.

Influence of segmentation accuracy in structural MR head scans on electric field computation for TMS and tES

In several diagnosis and therapy procedures based on electrostimulation effect, the internal physical quantity related to the stimulation is the induced electric field. To estimate the induced electric field in an individual human model, the segmentation of anatomical imaging, such as magnetic resonance image (MRI) scans, of the corresponding body parts into tissues is required. Then, electrical properties associated with different annotated tissues are assigned to the digital model to generate a volume conductor. However, the segmentation of different tissues is a tedious task with several associated challenges specially with tissues appear in limited regions and/or low-contrast in anatomical images. An open question is how segmentation accuracy of different tissues would influence the distribution of the induced electric field. In this study, we applied parametric segmentation of different tissues to exploit the segmentation of available MRI to generate different quality of head models using deep learning neural network architecture, named ForkNet. Then, the induced electric field are compared to assess the effect of model segmentation variations. Computational results indicate that the influence of segmentation error is tissue-dependent. In brain, sensitivity to segmentation accuracy is relatively high in cerebrospinal fluid (CSF), moderate in gray matter (GM) and low in white matter for transcranial magnetic stimulation (TMS) and transcranial electrical stimulation (tES). A CSF segmentation accuracy reduction of 10% in terms of Dice coefficient (DC) lead to decrease up to 4% in normalized induced electric field in both applications. However, a GM segmentation accuracy reduction of 5.6% DC leads to increase of normalized induced electric field up to 6%. Opposite trend of electric field variation was found between CSF and GM for both TMS and tES. The finding obtained here would be useful to quantify potential uncertainty of computational results.

Semiotic Aggregation in Deep Learning

Convolutional neural networks utilize a hierarchy of neural network layers. The statistical aspects of information concentration in successive layers can bring an insight into the feature abstraction process. We analyze the saliency maps of these layers from the perspective of semiotics, also known as the study of signs and sign-using behavior. In computational semiotics, this aggregation operation (known as superization) is accompanied by a decrease of spatial entropy: signs are aggregated into supersign. Using spatial entropy, we compute the information content of the saliency maps and study the superization processes which take place between successive layers of the network. In our experiments, we visualize the superization process and show how the obtained knowledge can be used to explain the neural decision model. In addition, we attempt to optimize the architecture of the neural model employing a semiotic greedy technique. To the extent of our knowledge, this is the first application of computational semiotics in the analysis and interpretation of deep neural networks.

Modified Selfish Herd Optimizer for Function Optimization

Selfish herd optimizer (SHO) is a new optimization algorithm. However, its optimization performance is not satisfactory. The main reason for this phenomenon is the weak global search ability of SHO. In this paper, in order to increase the global search ability of SHO, we add Levy-flight distribution strategy. To verify the performance of the proposed algorithm, we use 10 benchmark functions as test cases. Experiment results show that our algorithm is more competitive.

LinSEM: Linearizing segmentation evaluation metrics for medical images

Numerous algorithms are available for segmenting medical images. Empirical discrepancy metrics are commonly used in measuring the similarity or difference between segmentations by algorithms and "true" segmentations. However, one issue with the commonly used metrics is that the same metric value often represents different levels of "clinical acceptability" for different objects depending on their size, shape, and complexity of form. An ideal segmentation evaluation metric should be able to reflect degrees of acceptability directly from metric values and be able to show the same acceptability meaning by the same metric value for objects of different shape, size, and form. Intuitively, metrics which have a linear relationship with degree of acceptability will satisfy these conditions of the ideal metric. This issue has not been addressed in the medical image segmentation literature. In this paper, we propose a method called LinSEM for linearizing commonly used segmentation evaluation metrics based on corresponding degrees of acceptability evaluated by an expert in a reader study. LinSEM consists of two main parts: (a) estimating the relationship between metric values and degrees of acceptability separately for each considered metric and object, and (b) linearizing any given metric value corresponding to a given segmentation of an object based on the estimated relationship. Since algorithmic segmentations do not usually cover the full range of variability of acceptability, we create a set (SS) of simulated segmentations for each object that guarantee such coverage by using image transformations applied to a set (ST) of true segmentations of the object. We then conduct a reader study wherein the reader assigns an acceptability score (AS) for each sample in SS, expressing the acceptability of the sample on a 1 to 5 scale. Then the metric-AS relationship is constructed for the object by using an estimation method. With the idea that the ideal metric should be linear with respect to acceptability, we can then linearize the metric value of any segmentation sample of the object from a set (SA) of actual segmentations to its linearized value by using the constructed metric-acceptability relationship curve. Experiments are conducted involving three metrics - Dice coefficient (DC), Jaccard index (JI), and Hausdorff Distance (HD) - on five objects: skin outer boundary of the head and neck (cervico-thoracic) body region superior to the shoulders, right parotid gland, mandible, cervical esophagus, and heart. Actual segmentations (SA) of these objects are generated via our Automatic Anatomy Recognition (AAR) method. Our results indicate that, generally, JI has a more linear relationship with acceptability before linearization than other metrics. LinSEM achieves significantly improved uniformity of meaning post-linearization across all tested objects and metrics, except in a few cases where the departure from linearity was insignificant. This improvement is generally the largest for DC and HD reaching 8-25% for many tested cases. Although some objects (such as right parotid gland and esophagus for DC and JI) are close in their meaning between themselves before linearization, they are distant in this meaning from other objects but are brought close to other objects after linearization. This suggests the importance of performing linearization considering all objects in a body region and body-wide.

A novel technique for analysing histogram equalized medical images using superpixels

We present a novel technique to distinguish between an original image and its histogram equalized version. Histogram equalization and superpixel segmentation such as SLIC (simple linear iterative clustering) are very popular image processing tools. Based on these two concepts, we introduce a method for finding whether an image (grayscale) is histogram equalized or not. Because sometimes we see images that look visually similar but they are actually processed or changed by some image enhancement process such as histogram equalization. We can merely infer whether the image is dark, bright or has a small dynamic range. Moreover, we also compare the result of SLIC superpixels with three other superpixel segmentation algorithms namely, quick shift, watersheds, and Felzenszwalb's segmentation algorithm.