5K+ CT Images on Fractured Limbs: A Dataset for Medical Imaging Research.

Imaging techniques widely use Computed Tomography (CT) scans for various purposes, such as screening, diagnosis, and decision-making. Of all, it holds true for bone injuries. To build fully automated Computer-Aided Detection (CADe) and Diagnosis (CADx) tools and techniques, it requires fairly large amount of data (with gold standard). Therefore, in this paper, since state-of-the-art works relied on small dataset, we introduced a CT image dataset on limbs that is designed to understand bone injuries. Our dataset is a collection of 24 patient-specific CT cases having fractures at upper and lower limbs. From upper limbs, 8 cases were collected from bones in/around the shoulder (left and right). Similarly, from lower limbs, 16 cases were collected from knees (left and right). Altogether, 5684 CT images (upper limbs: 2057 and lower limbs: 3627) were collected. Each patient-specific CT case is composed of maximum 257 scans/slices in average. Of all, clinically approved annotations were made on every 10th slices, resulting in 1787 images. Importantly, no fractured limbs were missed in our annotation. Besides, to avoid privacy and confidential issues, patient-related information were deleted. The proposed dataset could be a promising resource for the medical imaging research community, where imaging techniques are employed for various purposes. To the best of our knowledge, this is the first time 5K+ CT images on fractured limbs are provided for research and educational purposes.

Automated Fractured Bone Segmentation and Labeling from CT Images.

Within the scope of education and training, automatic and accurate segmentation of fractured bones from Computed Tomographic (CT) images is the fundamental step in several different applications, such as trauma analysis, visualization, diagnosis, surgical planning and simulation. It helps physicians analyze the severity of injury by taking into account the following fracture features, such as location of the fracture, number of pieces and deviation from the original location. Besides, it helps provide accurate 3D visualization and decide optimal recovery plans/processes. To accurately segment fracture bones from CT images, in the paper, we introduce a segmentation technique that makes labeling process easier. Based on the patient-specific anatomy, unique labels are assigned. Unlike conventional techniques, it also includes the removal of unwanted artifacts, such as flesh. In our experiments, we have demonstrated our concept with real-world data (with an accuracy of 95.45%) and have compared with state-of-the-art techniques. For validation, our tests followed expert-based decisions i.e., clinical ground-truth. With the results, our collection of 8000 CT images will be available upon the request.

A Systematic Review on Orthopedic Simulators for Psycho-Motor Skill and Surgical Procedure Training.

Precise simulators can replicate complete understanding of the models. In this survey, we focus on orthopedic simulators that are not only in replicating real-world models but also in educating with complete procedure: surgical, for instance. It covers 18 hip replacement, three-knee replacement, three facial surgeries, one spine surgery and six orthopedic psycho-motor skills training and assessment-based simulators. We also provide comparative studies and highlight current trends and possible challenges. We observed that orthopedic training methodologies have undergone a paradigm shift. This means that the simulators replace the use of sensitive hospital settings for training and skill acquisition. In brief, we address classified overview on existing orthopedic simulators: physical and Virtual Reality (VR)-based simulators. Key steps to develop computer-assisted, VR-based simulator are explored. Experts' opinion on the use of simulation technologies in the field of orthopedics is discussed.