Abstract Magnetic resonance (MR) imaging is widely used for assessing infant head and brain development and for diagnosing pathologies. The main goal of this work is the development of a segmentation framework to create patient-specific head and brain anatomical models from MR images for clinical evaluation. The proposed strategy consists of a fusion-based Deep Learning (DL) approach that combines the information of different image sequences within the MR acquisition protocol, including the axial T1w, sagittal T1w, and coronal T1w after contrast. These image sequences are used as input for different fusion encoder–decoder network architectures based on the well-established U-Net framework. Specifically, three different fusion strategies are proposed and evaluated, namely early, intermediate, and late fusion. In the early fusion approach, the images are integrated at the beginning of the encoder–decoder architecture. In the intermediate fusion strategy, each image sequence is processed by an independent encoder, and the resulting feature maps are then jointly processed by a single decoder. In the late fusion method, each image is individually processed by an encoder–decoder, and the resulting feature maps are then combined to generate the final segmentations. A clinical in-house dataset consisting of 19 MR scans was used and divided into training, validation, and testing sets, with 3 MR scans defined as a fixed validation set. For the remaining 16 MR scans, a cross-validation approach was adopted to assess the performance of the methods. The training and testing processes were carried out with a split ratio of 75% for the training set and 25% for the testing set. The results show that the early and intermediate fusion methodologies presented the better performance (Dice coefficient of 97.6 ± 1.5% and 97.3 ± 1.8% for the head and Dice of 94.5 ± 1.7% and 94.8 ± 1.8% for the brain, respectively), whereas the late fusion method generated slightly worst results (Dice of 95.5 ± 4.4% and 93.8 ± 3.1% for the head and brain, respectively). Nevertheless, the volumetric analysis showed that no statistically significant differences were found between the volumes of the models generated by all the segmentation strategies and the ground truths. Overall, the proposed frameworks demonstrate accurate segmentation results and prove to be feasible for anatomical model analysis in clinical practice.

Objective - Medical image segmentation is essential for several clinical tasks, including diagnosis, surgical and treatment planning, and image-guided interventions. Deep Learning (DL) methods have become the state-of-the-art for several image segmentation scenarios. However, a large and well-annotated dataset is required to effectively train a DL model, which is usually difficult to obtain in clinical practice, especially for 3D images. Methods - In this paper, we proposed Deep-DM, a learning-guided deformable model framework for 3D medical imaging segmentation using limited training data. In the proposed method, an energy function is learned by a Convolutional Neural Network (CNN) and integrated into an explicit deformable model to drive the evolution of an initial surface towards the object to segment. Specifically, the learning-based energy function is iteratively retrieved from localized anatomical representations of the image containing the image information around the evolving surface at each iteration. By focusing on localized regions of interest, this representation excludes irrelevant image information, facilitating the learning process. Results and conclusion - The performance of the proposed method is demonstrated for the tasks of left ventricle and fetal head segmentation in ultrasound, left atrium segmentation in Magnetic Resonance, and bladder segmentation in Computed Tomography, using different numbers of training volumes in each study. The results obtained showed the feasibility of the proposed method to segment different anatomical structures in different imaging modalities. Moreover, the results also showed that the proposed approach is less dependent on the size of the training dataset in comparison with state-of-the-art DL-based segmentation methods, outperforming them for all tasks when a low number of samples is available. Significance - Overall, by offering a more robust and less data-intensive approach to accurately segmenting anatomical structures, the proposed method has the potential to enhance clinical tasks that require image segmentation strategies.

Ultrasound (US) phantoms are models that aim to simulate human tissues with the same or similar acoustic properties. They are used for training clinical procedures, diagnostic techniques and testing and calibration of new systems. Some models for these purposes can be found in the literature, but their reproducibility in terms of lesion placement is restricted. This work aims to construct a breast phantom to plan and train breast biopsy. We propose a strategy to construct a synthetic breast phantom compatible with US using a pour-in-mold approach. The presented study focuses on the design and production of the breast phantom with lesion. This technique focuses on the correct representation of a base model and positioning reproducibility of the lesion. Based on the literature, an ideal 3D breast model was created in SolidWorks. This model is used as a reference for molds creation and after 3D printed. These molds were filled with a Ballistic Gel based mixture. Two experiments were set to validate the proposed methodology, with these experiments were presenting the minimum and the maximum error relative to the breast and lesion volume, also giving the error relative to the method used for lesion positioning. The described methodology allows the construction of a phantom with an error of 1.47 +/- 0.78mm in the breast surface, compared to the ideal model (i.e. CAD version). Concerning the lesion's centroid, an error of 0.52 +/- 0.23mm was detected. The described strategy proved to be an accurate, fast production and low-cost model to be used in the training of breast biopsies procedures.

Deformational Plagiocephaly (DP) is a common medical condition in children. The deformity can be corrected using good practices recommended by the medical staff, however, in more severe cases, physical therapy is required. In this sense, cranial orthoses are mostly used to correct the deformity. However, the standard solutions do not quantify the treatment and are mostly produced through manually-based fabrication processes. Our research teams explored the potential of flexible materials, namely thermoplastic polyurethane (TPU), for the construction of complex shapes. However, the current systems do not have any strategy to quantify the applied force and pressure. In this study, a new strategy to quantify the pressure in a TPU structure is proposed and evaluated. The strategy consisted in placing the TPU material between a magnetic sensor (bottom part) and a magnetic (top part). After the material was placed on these components, we applied known forces and displacements on the bottom part and recorded the magnetic field (as the magnet was moving towards the sensor) to create a calibration curve that allowed us to classify the variation of the magnetic field according to the displacement exerted. Compression experiments were performed with the TPU material. Our results demonstrated that for the same displacement, the applied force varied proportinally with the internal thickness

International benchmarking competitions have become fundamental for the comparative performance assessment of image analysis methods. However, little attention has been given to investigating what can be learnt from these competitions. Do they really generate scientific progress? What are common and successful participation strategies? What makes a solution superior to a competing method? To address this gap in the literature, we performed a multicenter study with all 80 competitions that were conducted in the scope of IEEE ISBI 2021 and MICCAI 2021. Statistical analyses performed based on comprehensive descriptions of the submitted algorithms linked to their rank as well as the underlying participation strategies revealed common characteristics of winning solutions. These typically include the use of multi-task learning (63%) and/or multi-stage pipelines (61%), and a focus on augmentation (100%), image preprocessing (97%), data curation (79%), and post-processing (66%). The “typical” lead of a winning team is a computer scientist with a doctoral degree, five years of experience in biomedical image analysis, and four years of experience in deep learning. Two core general development strategies stood out for highly-ranked teams: the reflection of the metrics in the method design and the focus on analyzing and handling failure cases. According to the organizers, 43% of the winning algorithms exceeded the state of the art but only 11% completely solved the respective domain problem. The insights of our study could help researchers (1) improve algorithm development strategies when approaching new problems, and (2) focus on open research questions revealed by this work.

In-utero fetal MRI is emerging as an important tool in the diagnosis and analysis of the developing human brain. Automatic segmentation of the developing fetal brain is a vital step in the quantitative analysis of prenatal neurodevelopment both in the research and clinical context. However, manual segmentation of cerebral structures is time-consuming and prone to error and inter-observer variability. Therefore, we organized the Fetal Tissue Annotation (FeTA) Challenge in 2021 in order to encourage the development of automatic segmentation algorithms on an international level. The challenge utilized FeTA Dataset, an open dataset of fetal brain MRI reconstructions segmented into seven different tissues (external cerebrospinal fluid, gray matter, white matter, ventricles, cerebellum, brainstem, deep gray matter). 20 international teams participated in this challenge, submitting a total of 21 algorithms for evaluation. In this paper, we provide a detailed analysis of the results from both a technical and clinical perspective. All participants relied on deep learning methods, mainly U-Nets, with some variability present in the network architecture, optimization, and image pre- and post-processing. The majority of teams used existing medical imaging deep learning frameworks. The main differences between the submissions were the fine tuning done during training, and the specific pre- and post-processing steps performed. The challenge results showed that almost all submissions performed similarly. Four of the top five teams used ensemble learning methods. However, one team's algorithm performed significantly superior to the other submissions, and consisted of an asymmetrical U-Net network architecture. This paper provides a first of its kind benchmark for future automatic multi-tissue segmentation algorithms for the developing human brain in utero.

The use of radio frequency identification technology (RFID) has grown significantly in recent years. Since some chips have now memory capability, it is possible to read and write them, easing the tracing of different parts/components. In addition, and in opposition to standard technology for identification, e.g. barcode, a RFID reader can detect multiple chips simultaneously.Our team is recently exploring the potential of passive RFID tags to be used for package tracing. However, since these chips use energy from electromagnetic waves for communication and to power themselves, the communication range is very low, which could be an obstacle for some applications.In this article, we present a proof-of-concept of a motorized system to increase the read volume of the traditional RFID readers. The system resembles a robot with a tool specifically designed to support the reader. It will have four degrees of freedom controlled by different servomotors that will allow the reader to move to different zones. The new concept was compared with the traditional static RFID reader. While the static reader showed a reduced detection volume, 8400mm 3 , our approach proved, in our preliminary study, to guarantee an higher detection volume, 2.89×10 7 mm 3 , corroborating its potential to read RFID tags inserted into standard packages.Overall, the preliminary results show that our system has the potential to increase the detection range of RFID tags and to facilitate future package tracking systems.

The Radio Frequency Identification (RFID) technology has been used mainly to manage products and have stock control in real time. This technology is commonly used in the form of tags that are positioned outside of the object. However, the RFID insertion strategies are still sub-optimal, thus, there has been attempted to create methods to insert labels during the plastic injection process. However, must of the available insertion strategies do not satisfy the needs of large companies, since they are not standard. So, the objective of this study is to present a proof of concept of a new RFID tags insertion strategy adapted to plastic parts. The system uses a robot to pick up an RFID chip and insert it into a cavity of a mold. Then it will take some of the same material and with an ultrasound welder the plastic material will be melted to close the structure.For this project, we started by carrying out some experiments to understand the limitations of the available RFID chips, such as: maximum distance that can be detected, maximum temperature without damage when subjected to a welding process. With these experiments we will validate our proof of concept. Through these experiments we conclude that chips are detected at greater distances if they are centered with the reader’s antenna. Moreover, it was possible to confirm that they supported high temperatures.Overall, the current results corroborate the potential of this technique for the insertion of RFID in standard processes of the plastic industry.

Landmark labeling in 3D head surfaces is an important and routine task in clinical practice to evaluate head shape, namely to analyze cranial deformities or growth evolution. However, manual labeling is still applied, being a tedious and time-consuming task, highly prone to intra-/inter-observer variability, and can mislead the diagnose. Thus, automatic methods for anthropometric landmark detection in 3D models have a high interest in clinical practice. In this paper, a novel framework is proposed to accurately detect landmarks in 3D infant's head surfaces. The proposed method is divided into two stages: (i) 2D representation of the 3D head surface; and (ii) landmark detection through a deep learning strategy. Moreover, a 3D data augmentation method to create shape models based on the expected head variability is proposed. The proposed framework was evaluated in synthetic and real datasets, achieving accurate detection results. Furthermore, the data augmentation strategy proved its added value, increasing the method's performance. Overall, the obtained results demonstrated the robustness of the proposed method and its potential to be used in clinical practice for head shape analysis.

The eight papers in this special section focus on serious game computer applications for the health care field. During this period, we witnessed the creation of several conferences, providing a forum to discuss and share knowledge, experiences, and scientific and technical results, related to state-of-the-art solutions and technologies on serious games and applications for health and healthcare. The growth of computational capacity, development of new forms of interaction with the user (patient), and theoretical foundations produced by the scientific community over the past few years have now made it possible and viable to develop solutions, based on serious games, to face real problems. The possibility to create scenarios for medical training and simulation, the use of video games in rehabilitation procedures in an extra hospital environment, and the engagement provided by forms of teaching based on video games are just some examples of how this technology can be used. This special issue aims to highlight some of the high-quality research produced in the field of serious games applied to health.

An automatic algorithm to identify Standard Denavit-Hartenberg parameters of serial manipulators is proposed. The method is based on geometric operations and dual vector algebra to process and determine the relative transformation matrices, from which it is computed the Standard Denavit-Hartenberg (DH) parameters (ai, ai, di, θi). The algorithm was tested in several serial robotic manipulators with varying kinematic structures and joint types: the KUKA LBR iiwa R800, the Rethink Robotics Sawyer, the ABB IRB 140, the Universal Robots UR3, the KINOVA MICO, and the Omron Cobra 650. For all these robotic manipulators, the proposed algorithm was capable of correctly identifying a set of DH parameters. The algorithm source code as well as the test scenarios are publicly available.

Over the years, medical image tracking has gained considerable attention from both medical and research communities due to its widespread utility in a multitude of clinical applications, from functional assessment during diagnosis and therapy planning to structure tracking or image fusion during image-guided interventions. Despite the ever-increasing number of image tracking methods available, most still consist of independent implementations with specific target applications, lacking the versatility to deal with distinct end-goals without the need for methodological tailoring and/or exhaustive tuning of numerous parameters. With this in mind, we have developed the medical image tracking toolbox (MITT)-a software package designed to ease customization of image tracking solutions in the medical field. While its workflow principles make it suitable to work with 2-D or 3-D image sequences, its modules offer versatility to set up computationally efficient tracking solutions, even for users with limited programming skills. MITT is implemented in both C/C++ and MATLAB, including several variants of an object-based image tracking algorithm and allowing to track multiple types of objects (i.e., contours, multi-contours, surfaces, and multi-surfaces) with several customization features. In this paper, the toolbox is presented, its features discussed, and illustrative examples of its usage in the cardiology field provided, demonstrating its versatility, simplicity, and time efficiency.

A novel semi-automatic algorithm for aortic valve (AV) wall segmentation is presented for 3D transesophageal echocardiography (TEE) datasets. The proposed methodology uses a 3D cylindrical formulation of the B-spline Explicit Active Surfaces (BEAS) framework in a dual-stage energy evolution process, comprising a threshold-based and a localized region-based stage. Hereto, intensity and shape-based features are combined to accurately delineate the AV wall from the ascending aorta (AA) to the left ventricular outflow tract (LVOT). Shape-prior information is included using a profile-based statistical shape model (SSM), and embedded in BEAS through two novel regularization terms: one confining the segmented AV profiles to shapes seen in the SSM (hard regularization) and another penalizing according to the profile's degree of likelihood (soft regularization). The proposed energy functional takes thus advantage of the intensity data in regions with strong image content, while complementing it with shape knowledge in regions with nearly absent image data. The proposed algorithm has been validated in 20 3D-TEE datasets with both stenotic and non-stenotic valves. It was shown to be accurate, robust and computationally efficient, taking less than 1 second to segment the AV wall from the AA to the LVOT with an average accuracy of 0.78 mm. Semi-automatically extracted measurements at four relevant anatomical levels (LVOT, aortic annulus, sinuses of Valsalva and sinotubular junction) showed an excellent agreement with experts' ones, with a higher reproducibility than manually-extracted measures.