Multi-Atlas Segmentation of Anatomical Brain Structures Using Hierarchical Hypergraph Learning.

Semantic segmentation of anatomical structures in laparoscopic videos is a crucial task to enable the development of new computer-assisted systems that can assist surgeons during surgery. However, this is a difficult task due to artifacts and similar visual characteristics of anatomical structures on the laparoscopic videos. Recently, deep learning algorithms have been showed promising results on the segmentation of laparoscopic instruments. However, due to the lack of large public datasets for semantic segmentation of anatomical structures, there are only a few studies on this task. In this work, we evaluate the performance of five networks, namely U-Net, U-Net++, DynUNet, UNETR and DeepLabV3+, for segmentation of laparoscopic cholecystectomy images from the recently released CholecSeg8k dataset. To the best of our knowledge, this is the first benchmark performed on this dataset. Training was performed with dice loss. The networks were evaluated on segmentation of 8 anatomical structures and instruments, performance was quantified through the dice coefficient, intersection over union, recall, and precision. Apart from the U-Net, all networks obtained scores similar to each other, with the U-Net++ being the network with the best overall score with a mean Dice value of 0.62. Overall, the results show that there is still room for improvement in the segmentation of anatomical structures from laparoscopic videos. Clinical Relevance- The results of this study show the potential of deep neural networks for the segmentation of anatomical structures in laparoscopic images which can later be incorporated into computer-aided systems for surgeons.

In this paper, we developed a new deformable model, the charged fluid model (CFM), that uses the simulation of a charged fluid to segment anatomic structures in magnetic resonance (MR) images of the brain. Conceptually, the charged fluid behaves like a liquid such that it flows through and around different obstacles. The simulation evolves in two steps governed by Poisson's equation. The first step distributes the elements of the charged fluid within the propagating interface until an electrostatic equilibrium is achieved. The second step advances the propagating front of the charged fluid such that it deforms into a new shape in response to the image gradient. This approach required no prior knowledge of anatomic structures, required the use of only one parameter, and provided subpixel precision in the region of interest. We demonstrated the performance of this new algorithm in the segmentation of anatomic structures on simulated and real brain MR images of different subjects. The CFM was compared to the level-set-based methods [Caselles et al. (1993) and Malladi et al (1995)] in segmenting difficult objects in a variety of brain MR images. The experimental results in different types of MR images indicate that the CFM algorithm achieves good segmentation results and is of potential value in brain image processing applications.

Hierarchies of artificial neural networks(ANN's) were trained to segment regularly-shaped and constantly-located anatomical structures in x-ray computed tomography (CT) images. These neural networks learned to associate a point in an image with the anatomical structure containing the point using the image pixel intensity values located in a pattern around the point. The single layer ANN and the bilayer and multi-layer hierarchies of neural networks were developed and evaluated. The hierarchical Artificial Neural Networks(HANN's) consisted of a high-level ANN that identified large-scale anatomical structures (e.g., the head or chest), whose result was passed to a group of neural networks that identified smaller structures (e.g., the brain, sinus, soft tissue, skull, bone, or lung) within the large-scale structures. The ANN's were trained to segment and classify images based on different numbers of training images, numbers of sampling points per image, pixel intensity sampling patterns, hidden layer configuration. The experimental results indicate that multi-layer hierarchy of ANN's trained with data collected from multiple image series accurately classified anatomical structures in unknown chest and head CT images.

The visceral adipose tissue (VAT) volume is a predictive and/or prognostic factor for many cancers. The objective of our study was to develop an automatic measurement of the whole VAT volume using a multi-atlas segmentation (MAS) method from a computed tomography. A total of 31 sets of whole-body computed tomography volume data were used. The reference VAT volume was defined on the basis of manual segmentation (VATMANUAL). We developed an algorithm, which measured automatically the VAT volumes using a MAS based on a nonrigid volume registration algorithm coupled with a selective and iterative method for performance level estimation (SIMPLE), called VATMAS_SIMPLE. The results were evaluated using intraclass correlation coefficient and dice similarity coefficients. The intraclass correlation coefficient of VATMAS_SIMPLE was excellent, at 0.976 (confidence interval, 0.943-0.989) (P < 0.001). The dice similarity coefficient of VATMAS_SIMPLE was also good, at 0.905 (SD, 0.076). This newly developed algorithm based on a MAS can measure accurately the whole abdominopelvic VAT.

Shape information plays an important role in biomedical image analysis because of the strong shape characteristics of biological structures. It is often used as a prior to constrain or refine the intermediate shape information derived from low-level image features. In this paper, we give an overview of the sparse shape composition based prior modeling method and its various applications of biomedical image analysis. Instead of learning a generative shape model, it incorporates shape priors on-the-fly through the sparse shape composition. Particularly, a shape instance derived from low level image features is refined by a sparse linear combination of a sparse set of shapes in the repository. We also design three strategies to improve run-time efficiency. 1) When the shape repository contains a large number of instances, K-SVD can be used to learn a more compact but still informative shape dictionary. 2) If the derived shape instance has a large number of vertices, which often appears in 3D problems, affinity propagation method can be used to partition the surface into small subregions. 3) When there are multiple structures, hierarchical scheme is employed to model them simultaneously. These strategies decrease the scale of the sparse optimization problem and thus speed up the algorithm. Our method is applied on different biomedical image analysis problems, including localization, tracking and segmentation of anatomical structures. In all of these applications, this method achieves promising results.

Rapid advances in imaging modalities have increased the importance of image segmentation techniques. These techniques automatically extract data for the anatomical structure of interest and facilitate their quantitative analysis. Here we present a framework for a semi-automatic segmentation method that incorporates a local classifier derived from a neighboring image. Using the local classifier we were able to consider otherwise challenging cases of segmentation merely as two-class classification without any complicated parameters. Our method is simple to implement and easy to operate. We successfully tested our method on computed tomography images.

BackgroundThis study investigates the variation in segmentation of several pelvic anatomical structures on computed tomography (CT) between multiple observers and a commercial automatic segmentation method, in the context of quality assurance and evaluation during a multicentre clinical trial.MethodsCT scans of two prostate cancer patients (‘benchmarking cases’), one high risk (HR) and one intermediate risk (IR), were sent to multiple radiotherapy centres for segmentation of prostate, rectum and bladder structures according to the TROG 03.04 “RADAR” trial protocol definitions. The same structures were automatically segmented using iPlan software for the same two patients, allowing structures defined by automatic segmentation to be quantitatively compared with those defined by multiple observers. A sample of twenty trial patient datasets were also used to automatically generate anatomical structures for quantitative comparison with structures defined by individual observers for the same datasets.ResultsThere was considerable agreement amongst all observers and automatic segmentation of the benchmarking cases for bladder (mean spatial variations < 0.4 cm across the majority of image slices). Although there was some variation in interpretation of the superior-inferior (cranio-caudal) extent of rectum, human-observer contours were typically within a mean 0.6 cm of automatically-defined contours. Prostate structures were more consistent for the HR case than the IR case with all human observers segmenting a prostate with considerably more volume (mean +113.3%) than that automatically segmented. Similar results were seen across the twenty sample datasets, with disagreement between iPlan and observers dominant at the prostatic apex and superior part of the rectum, which is consistent with observations made during quality assurance reviews during the trial.ConclusionsThis study has demonstrated quantitative analysis for comparison of multi-observer segmentation studies. For automatic segmentation algorithms based on image-registration as in iPlan, it is apparent that agreement between observer and automatic segmentation will be a function of patient-specific image characteristics, particularly for anatomy with poor contrast definition. For this reason, it is suggested that automatic registration based on transformation of a single reference dataset adds a significant systematic bias to the resulting volumes and their use in the context of a multicentre trial should be carefully considered.

The visualization of medical images with advanced techniques, such as augmented reality and virtual reality, represent a breakthrough for medical professionals. In contrast to more traditional visualization tools lacking 3D capabilities, these systems use the three available dimensions. To visualize medical images in 3D, the anatomical areas of interest must be segmented. Currently, manual segmentation, which is the most commonly used technique, and semi-automatic approaches can be time consuming because a doctor is required, making segmentation for each individual case unfeasible. Using new technologies, such as computer vision and artificial intelligence for segmentation algorithms and augmented and virtual reality for visualization techniques implementation, we designed a complete platform to solve this problem and allow medical professionals to work more frequently with anatomical 3D models obtained from medical imaging. As a result, the Nextmed project, due to the different implemented software applications, permits the importation of digital imaging and communication on medicine (dicom) images on a secure cloud platform and the automatic segmentation of certain anatomical structures with new algorithms that improve upon the current research results. A 3D mesh of the segmented structure is then automatically generated that can be printed in 3D or visualized using both augmented and virtual reality, with the designed software systems. The Nextmed project is unique, as it covers the whole process from uploading dicom images to automatic segmentation, 3D reconstruction, 3D visualization, and manipulation using augmented and virtual reality. There are many researches about application of augmented and virtual reality for medical image 3D visualization; however, they are not automated platforms. Although some other anatomical structures can be studied, we focused on one case: a lung study. Analyzing the application of the platform to more than 1000 dicom images and studying the results with medical specialists, we concluded that the installation of this system in hospitals would provide a considerable improvement as a tool for medical image visualization.

Pinta is a system for segmentation and visualization of anatomical structures obtained from serial sections reconstructed from magnetic resonance imaging. The system approaches the segmentation problem by assigning each volumetric region to an anatomical structure. This is accomplished by satisfying constraints at the pixel level, slice level, and volumetric level. Each slice is represented by an attributed graph, where nodes correspond to regions and links correspond to the relations between regions. These regions are obtained by grouping pixels based on similarity and proximity. The slice level attributed graphs are then coerced to form a volumetric attributed graph, where volumetric consistency can be verified. The volumetric graph is used to ensure consistency from symbolic representations obtained from individual slices. The system allows errors to be made at the slice level, yet removes them when the volumetric consistency cannot be verified. Once the segmentation is complete, the 3D surfaces of the brain can be constructed and visualized. >

Objective:Precise segmentation of human organs and anatomic structures (especially organs at risk, OARs) is the basis and prerequisite for the treatment planning of radiation therapy. In order to ensure rapid and accurate design of radiotherapy treatment planning, an automatic organ segmentation technique was investigated based on deep learning convolutional neural network.MethodA deep learning convolutional neural network (CNN) algorithm called BCDU-Net has been modified and developed further by us. Twenty two thousand CT images and the corresponding organ contours of 17 types delineated manually by experienced physicians from 329 patients were used to train and validate the algorithm. The CT images randomly selected were employed to test the modified BCDU-Net algorithm. The weight parameters of the algorithm model were acquired from the training of the convolutional neural network.ResultThe average Dice similarity coefficient (DSC) of the automatic segmentation and manual segmentation of the human organs of 17 types reached 0.8376, and the best coefficient reached up to 0.9676. It took 1.5–2 s and about 1 h to automatically segment the contours of an organ in an image of the CT dataset for a patient and the 17 organs for the CT dataset with the method developed by us, respectively.ConclusionThe modified deep neural network algorithm could be used to automatically segment human organs of 17 types quickly and accurately. The accuracy and speed of the method meet the requirements of its application in radiotherapy.

Accurate segmentation and classification of different anatomical structures of teeth from medical images plays an essential role in many clinical applications. Usually, the anatomical structures of teeth are manually labelled by experienced clinical doctors, which is time consuming. However, automatic segmentation and classification is a challenging task because the anatomical structures and surroundings of the tooth in medical images are rather complex. Therefore, in this paper, we propose an effective framework which is designed to segment the tooth with a Selective Binary and Gaussian Filtering Regularized Level Set (GFRLS) method improved by fully utilizing three dimensional (3D) information, and classify the tooth by employing unsupervised learning Pulse Coupled Neural Networks (PCNN) model. In order to evaluate the proposed method, the experiments are conducted on the different datasets of mandibular molars and the experimental results show that our method can achieve better accuracy and robustness compared to other four state of the art clustering methods.

Medical image analysis is critical yet challenged by the need of jointly segmenting organs or tissues, and numerous instances for anatomical structures and tumor microenvironment analysis. Existing studies typically formulated different segmentation tasks in isolation, which overlooks the fundamental interdependencies between these tasks, leading to suboptimal segmentation performance and insufficient medical image understanding. To address this issue, we propose a Co-Seg++ framework for versatile medical segmentation. Specifically, we introduce a novel co-segmentation paradigm, allowing semantic and instance segmentation tasks to mutually enhance each other. We first devise a spatio-sequential prompt encoder (SSP-Encoder) to capture long-range spatial and sequential relationships between segmentation regions and image embeddings as prior spatial constraints. Moreover, we devise a multi-task collaborative decoder (MTC-Decoder) that leverages cross-guidance to strengthen the contextual consistency of both tasks, jointly computing semantic and instance segmentation masks. Extensive experiments on diverse CT and histopathology datasets demonstrate that the proposed Co-Seg++ outperforms state-of-the-arts in the semantic, instance, and panoptic segmentation of dental anatomical structures, histopathology tissues, and nuclei instances. The source code is available at https://github.com/xq141839/Co-Seg-Plus.

Artificial intelligence, represented by deep learning, has received increasing attention in the field of oral and maxillofacial medical imaging, which has been widely studied in image analysis and image quality improvement. This narrative review provides an insight into the following applications of deep learning in oral and maxillofacial imaging: detection, recognition and segmentation of teeth and other anatomical structures, detection and diagnosis of oral and maxillofacial diseases, and forensic personal identification. In addition, the limitations of the studies and the directions for future development are summarized.

Accurate segmentation of key anatomical structures in pediatric echocardiography is essential for the diagnosis and treatment of congenital heart disease. However, most of the existing segmentation methods for echocardiography have the problem of loss of detailed information, which has a certain impact on the accuracy of segmentation. Based on this, we propose a multi-directional attention (MDA) network for echocardiographic segmentation. This method uses U-Net as the backbone network to extract the initial features of different layers, and then sends the initial features to our proposed MDA module for feature enhancement. Among them, MDA includes two parts: First, considering the different contribution rates of spatial information in different directions to features, we construct a multi-directional spatial attention (MDSA) module to extract spatial information in different directions. Then to avoid the loss of channel information, we construct a channel weight constraint module (CWC) to constrain the weight of the spatial features extracted by MDSA. Finally, the group fusion feature output by MDA is used as the input of the decoder, and the final segmentation prediction result is obtained by setting the layered feature fusion (LFF) module. We conduct an extensive evaluation of 4,485 two-dimensional (2D) pediatric echocardiograms from 127 echocardiographic videos. Experiments show that the proposed algorithm can achieve the results of pediatric echocardiographic anatomical structures (left ventricle (LV), left atrium (LA)) with the average dice, precision, and recall were 0.9346, 0.9370, and 0.9406.

Bioluminescence tomography is known as a highly ill-posed inverse problem. To improve the reconstruction performance by introducing anatomical structures as a priori knowledge, an automatic segmentation framework has been proposed in this paper to extract the mouse whole-body organs and tissues, which enables to build up a heterogeneous mouse model for reconstruction of bioluminescence tomography. Finally, an in vivo mouse experiment has been conducted to evaluate this framework by using an X-ray computed tomography system and a multi-view bioluminescence imaging system. The findings suggest that the proposed method can realize fast automatic segmentation of mouse anatomical structures, ultimately enhancing the reconstruction performance of bioluminescence tomography. DOI: http://dx.doi.org/10.11591/telkomnika.v11i9.3241