Anatomic attention regions via optimal anatomy modeling and recognition for DL-based image segmentation.

Organ segmentation is a crucial task in various medical imaging applications. Many deep learning models have been developed to do this, but they are slow and require a lot of computational resources. To solve this problem, attention mechanisms are used which can locate important objects of interest within medical images, allowing the model to segment them accurately even when there is noise or artifact. By paying attention to specific anatomical regions, the model becomes better at segmentation. Medical images have unique features in the form of anatomical information, which makes them different from natural images. Unfortunately, most deep learning methods either ignore this information or do not use it effectively and explicitly. Combined natural intelligence with artificial intelligence, known as hybrid intelligence, has shown promising results in medical image segmentation, making models more robust and able to perform well in challenging situations. In this paper, we propose several methods and models to find attention regions in medical images for deep learning-based segmentation via non-deep-learning methods. We developed these models and trained them using hybrid intelligence concepts. To evaluate their performance, we tested the models on unique test data and analyzed metrics including false negatives quotient and false positives quotient. Our findings demonstrate that object shape and layout variations can be explicitly learned to create computational models that are suitable for each anatomic object. This work opens new possibilities for advancements in medical image segmentation and analysis.

The effect of ankle ligament damage and surgical reconstructions on the mechanics of the ankle and subtalar joints revealed by three-dimensional stress MRI.

Common image-based diagnostic techniques used to detect ankle ligament injuries or the effects of those injuries (e.g., mechanical instability) include magnetic resonance imaging (MRI) and stress radiography. Each of these techniques has limitations. The interpretation of the results obtained through stress radiography, a two-dimensional technique, is highly controversial. MRI can facilitate visualization of soft tissue, but three-dimensional visualization of the full length of the ligaments or detecting partial ligament damage is difficult. This work is part of a long-term study aimed at improving the diagnostic ability of MRI by utilizing it not only to visualize the ligaments but also to detect the mechanical instability produced at the ankle and subtalar joints due to ligament damage. The goal of the present study was to evaluate the ability of a previously developed technique called 3D stress MRI (sMRI) to detect in vitro the effect of damage to the lateral collateral ligaments and the stabilizing effect produced by two common surgical reconstruction techniques. MRI data were collected from eight cadaver limbs in a MR compatible ankle-loading device in neutral, inversion, and anterior drawer. Each specimen was tested intact, after cutting the anterior talo-fibular ligament followed by the calcaneo-fibular ligament and after applying two reconstructions. Ligament injuries produced significant changes in the response of the ankle and subtalar joints to load as detected by the 3D stress MRI technique. Both surgical procedures restored mechanical stability to the joints but they differed in the amount and type of stabilization achieved. We concluded that 3D sMRI can extend the diagnostic power of MRI from the current practice of slice-by-slice visualization to the assessment of mechanical function, the compromise in this function due to injury, and the effects of surgery.

Mechanics of the ankle and subtalar joints revealed through a 3D quasi-static stress MRI technique.

A technique to study the three-dimensional (3D) mechanical characteristics of the ankle and of the subtalar joints in vivo and in vitro is described. The technique uses an MR scanner compatible 3D positioning and loading linkage to load the hindfoot with precise loads while the foot is being scanned. 3D image processing algorithms are used to derive from the acquired MR images bone morphology, hindfoot architecture, and joint kinematics. The technique was employed to study these properties both in vitro and in vivo. The ankle and subtler joint motion and the changes in architecture produced in response to an inversion load and an anterior drawer load were evaluated. The technique was shown to provide reliable measures of bone morphology. The left-to-right variations in bone morphology were less than 5%. The left-to-right variations in unloaded hindfoot architecture parameters were less than 10%, and these properties were only slightly affected by inversion and anterior drawer loads. Inversion and anterior drawer loads produced motion both at the ankle and at the subtalar joint. In addition, high degree of coupling, primarily of internal rotation with inversion, was observed both at the ankle and at the subtalar joint. The in vitro motion produced in response to inversion and anterior drawer load was greater than the in vivo motion. Finally, external motion, measured directly across the ankle complex, produced in response to load was much greater than the bone movements measured through the 3D stress MRI technique indicating the significant effect of soft tissue and skin interference.

Artery-vein separation via MRA--an image processing approach.

This paper presents a near-automatic process for separating vessels from background and other clutter as well as for separating arteries and veins in contrast-enhanced magnetic resonance angiographic (CE-MRA) image data, and an optimal method for three-dimensional visualization of vascular structures. The separation process utilizes fuzzy connected object delineation principles and algorithms. The first step of this separation process is the segmentation of the entire vessel structure from the background and other clutter via absolute fuzzy connectedness. The second step is to separate artery from vein within this entire vessel structure via iterative relative fuzzy connectedness. After seed voxels are specified inside artery and vein in the CE-MRA image, the small regions of the bigger aspects of artery and vein are separated in the initial iterations, and further detailed aspects of artery and vein are included in later iterations. At each iteration, the artery and vein compete among themselves to grab membership of each voxel in the vessel structure based on the relative strength of connectedness of the voxel in the artery and vein. This approach has been implemented in a software package for routine use in a clinical setting and tested on 133 CE-MRA studies of the pelvic region and two studies of the carotid system from six different hospitals. In all studies, unified parameter settings produced correct artery-vein separation. When compared with manual segmentation/separation, our algorithms were able to separate higher order branches, and therefore produced vastly more details in the segmented vascular structure. The total operator and computer time taken per study is on the average about 4.5 min. To date, this technique seems to be the only image processing approach that can be routinely applied for artery and vein separation.

An in vivo analysis of the motion of the peri-talar joint complex based on MR imaging.

The purpose of this work is to characterize the three-dimensional (3-D) motion of the peritalar joint complex in vivo using magnetic resonance imaging (MRI). Each image data set utilized in this study is made of 60 longitudinal MR slices of the foot in each of eight positions from extreme pronation to extreme supination. We acquired and analyzed ten such data sets from normal subjects, seven data sets from pathological joints and two postoperative data sets. We segmented and formed the surfaces of the calcaneus, talus, cuboid and navicular from all data sets. About 30 geometrical parameters are computed for each joint in each position. The results present features of normal motion and show how normal and abnormal motion can be distinguished. They also show the consequences of surgery on the motion. This non- invasive method offers a unique tool to characterize and quantify the 3-D motion of the rearfoot in vivo from MR images.

A characterization of the geometric architecture of the peritalar joint complex via MRI: an aid to the classification of foot type.

The purpose of this work is to study the architecture of the rearfoot using in vivo MR image data. Each data set used in this study is made of sixty sagittal slices of the foot acquired in a 1.5-T commercial GE MR system. We use the live-wire method to delineate boundaries and form the surfaces of the bones. In the first part of this work, we describe a new method to characterize the three-dimensional (3-D) relationships of four bones of the peritalar complex and apply this description technique to data sets from ten normal subjects and from seven pathological cases. In the second part, we propose a procedure to classify feet, based on the values of these new architectural parameters. We conclude that this noninvasive method offers a unique tool to characterize the 3-D architecture of the feet in live patients, based on a set of new architectural parameters. This can be integrated into a set of tools to improve diagnosis and treatment of foot malformations.

3D MR image analysis of the morphology of the rear foot: application to classification of bones.

The purpose of this work is to characterize the three-dimensional (3D) morphology of the bones of the rear foot using MR image data. It has two sub-aims: (i) to study the variability of the various computed architectural measures caused by the subjectivity and variations in the various processing operations; (ii) to study the morphology of the bones included in the peritalar complex. Each image data set utilized in this study consists of sixty sagittal slices of the foot acquired on a 1.5 T commercial GE MR system. The description of the rear foot morphology is based mainly on the principal axes, which represent the inertia axes of the bones, and on the bone surfaces. We use the live-wire method [Falcao AX, Udupa JK, Samarasekera S, Shoba S, Hirsch BE, Lotufo RA. User-steered image segmentation paradigms: live wire and live lane. Proceedings of the Society of Photo-optical Instrumentation Engineers 1996;2710:278-288] for segmenting and forming the surfaces of the bones. In the first part of this work, we focus on the analysis of the dependence of the principal axes system on segmentation and on scan orientation. In the second part, we describe the normal morphology of the rear foot considering the four bones namely calcaneus, cuboid, navicular, and talus, and compare this to a population from the upper Pleistocene. We conclude that this non-invasive method offers a unique tool to characterize the bone morphology in live patients towards the goal of understanding the architecture and kinematics of normal and pathological joints in vivo.

Multidimensional data format specification: a generalization of the American College of Radiology-National Electric Manufacturers Association standards.

Multidimensional image data are becoming increasingly common in biomedical imaging. Three-dimensional visualization and analysis techniques based on three-dimensional image data have become an established discipline in biomedicine. Some imaging problems generate image data of even higher dimensions. It often becomes necessary, rather than just convenient, to consider the higher-dimensional data as a whole to adequately answer the underlying imaging questions. Despite this established need for convenient exchange of image and image-derived information, no exchange protocols are available that adequately meet the needs of multidimensional imaging systems. This paper describes an exchange protocol that has been designed after careful consideration of the common requirements of methodologies for visualization and analysis of multidimensional data. It is based on and is a generalization of the widely accepted American College of Radiology-National Electrical Manufacturers Association (ACR-NEMA) standards specified for two-dimensional images. It is implemented and actively being used in a data-, application-, and machine-independent software environment, being developed in the authors' department, for the visualization and analysis of multidimensional images.

Performance evaluation of an iterative image reconstruction algorithm for positron emission tomography.

An image reconstruction method motivated by positron emission tomography (PET) is discussed. The measurements tend to be noisy and so the reconstruction method should incorporate the statistical nature of the noise. The authors set up a discrete model to represent the physical situation and arrive at a nonlinear maximum a posteriori probability (MAP) formulation of the problem. An iterative approach which requires the solution of simple quadratic equations is proposed. The authors also present a methodology which allows them to experimentally optimize an image reconstruction method for a specific medical task and to evaluate the relative efficacy of two reconstruction methods for a particular task in a manner which meets the high standards set by the methodology of statistical hypothesis testing. The new MAP algorithm is compared to a method which maximizes likelihood and with two variants of the filtered backprojection method.