RESUMO
Pectus carinatum (PC) is a chest deformity caused by disproportionate growth of the costal cartilages compared with the bony thoracic skeleton, pulling the sternum forwards and leading to its protrusion. Currently, the most common non-invasive treatment is external compressive bracing, by means of an orthosis. While this treatment is widely adopted, the correct magnitude of applied compressive forces remains unknown, leading to suboptimal results. Moreover, the current orthoses are not suitable to monitor the treatment. The purpose of this study is to design a force measuring system that could be directly embedded into an existing PC orthosis without relevant modifications in its construction. For that, inspired by the currently commercially available products where a solid silicone pad is used, three concepts for silicone-based sensors, two capacitive and one magnetic type, are presented and compared. Additionally, a concept of a full pipeline to capture and store the sensor data was researched. Compression tests were conducted on a calibration machine, with forces ranging from 0 N to 300 N. Local evaluation of sensors' response in different regions was also performed. The three sensors were tested and then compared with the results of a solid silicon pad. One of the capacitive sensors presented an identical response to the solid silicon while the other two either presented poor repeatability or were too stiff, raising concerns for patient comfort. Overall, the proposed system demonstrated its potential to measure and monitor orthosis's applied forces, corroborating its potential for clinical practice.
Assuntos
Pectus Carinatum , Humanos , Pectus Carinatum/terapia , Silício , Esterno , Braquetes , Pressão , Resultado do TratamentoRESUMO
Breast cancer is the most prevalent cancer in the world and the fifth-leading cause of cancer-related death. Treatment is effective in the early stages. Thus, a need to screen considerable portions of the population is crucial. When the screening procedure uncovers a suspect lesion, a biopsy is performed to assess its potential for malignancy. This procedure is usually performed using real-time Ultrasound (US) imaging. This work proposes a visualization system for US breast biopsy. It consists of an application running on AR glasses that interact with a computer application. The AR glasses track the position of QR codes mounted on an US probe and a biopsy needle. US images are shown in the user's field of view with enhanced lesion visualization and needle trajectory. To validate the system, latency of the transmission of US images was evaluated. Usability assessment compared our proposed prototype with a traditional approach with different users. It showed that needle alignment was more precise, with 92.67 ± 2.32° in our prototype versus 89.99 ± 37.49° in a traditional system. The users also reached the lesion more accurately. Overall, the proposed solution presents promising results, and the use of AR glasses as a tracking and visualization device exhibited good performance.
Assuntos
Realidade Aumentada , Feminino , Humanos , Interface Usuário-Computador , Ultrassonografia Mamária , Ultrassonografia , BiópsiaRESUMO
Evaluation of the head shape of newborns is needed to detect cranial deformities, disturbances in head growth, and consequently, to predict short- and long-term neurodevelopment. Currently, there is a lack of automatic tools to provide a detailed evaluation of the head shape. Artificial intelligence (AI) methods, namely deep learning (DL), can be explored to develop fast and automatic approaches for shape evaluation. However, due to the clinical variability of patients' head anatomy, generalization of AI networks to the clinical needs is paramount and extremely challenging. In this work, a new framework is proposed to augment the 3D data used for training DL networks for shape evaluation. The proposed augmentation strategy deforms head surfaces towards different deformities. For that, a point-based 3D morphable model (p3DMM) is developed to generate a statistical model representative of head shapes of different cranial deformities. Afterward, a constrained transformation approach (3DHT) is applied to warp a head surface towards a target deformity by estimating a dense motion field from a sparse one resulted from the p3DMM. Qualitative evaluation showed that the proposed method generates realistic head shapes indistinguishable from the real ones. Moreover, quantitative experiments demonstrated that DL networks training with the proposed augmented surfaces improves their performance in terms of head shape analysis. Overall, the introduced augmentation allows to effectively transform a given head surface towards different deformity shapes, potentiating the development of DL approaches for head shape analysis.
Assuntos
Inteligência Artificial , Modelos Estatísticos , Humanos , Lactente , Recém-NascidoRESUMO
The increase of the aging population brings numerous challenges to health and aesthetic segments. Here, the use of laser therapy for dermatology is expected to increase since it allows for non-invasive and infection-free treatments. However, existing laser devices require doctors' manually handling and visually inspecting the skin. As such, the treatment outcome is dependent on the user's expertise, which frequently results in ineffective treatments and side effects. This study aims to determine the workspace and limits of operation of laser treatments for vascular lesions of the lower limbs. The results of this study can be used to develop a robotic-guided technology to help address the aforementioned problems. Specifically, workspace and limits of operation were studied in eight vascular laser treatments. For it, an electromagnetic tracking system was used to collect the real-time positioning of the laser during the treatments. The computed average workspace length, height, and width were 0.84 ± 0.15, 0.41 ± 0.06, and 0.78 ± 0.16 m, respectively. This corresponds to an average volume of treatment of 0.277 ± 0.093 m3. The average treatment time was 23.2 ± 10.2 min, with an average laser orientation of 40.6 ± 5.6 degrees. Additionally, the average velocities of 0.124 ± 0.103 m/s and 31.5 + 25.4 deg/s were measured. This knowledge characterizes the vascular laser treatment workspace and limits of operation, which may ease the understanding for future robotic system development.
Assuntos
Robótica , Extremidade Inferior/cirurgia , Robótica/métodos , Resultado do TratamentoRESUMO
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.
RESUMO
Breast cancer is a global public health concern. For women with suspicious breast lesions, the current diagnosis requires a biopsy, which is usually guided by ultrasound (US). However, this process is challenging due to the low quality of the US image and the complexity of dealing with the US probe and the surgical needle simultaneously, making it largely reliant on the surgeon's expertise. Some previous works employing collaborative robots emerged to improve the precision of biopsy interventions, providing an easier, safer, and more ergonomic procedure. However, for these equipment to be able to navigate around the breast autonomously, 3D breast reconstruction needs to be available. The accuracy of these systems still needs to improve, with the 3D reconstruction of the breast being one of the biggest focuses of errors. The main objective of this work is to develop a method to obtain a robust 3D reconstruction of the patient's breast, based on RGB monocular images, which later can be used to compute the robot's trajectories for the biopsy. To this end, depth estimation techniques will be developed, based on a deep learning architecture constituted by a CNN, LSTM, and MLP, to generate depth maps capable of being converted into point clouds. After merging several from multiple points of view, it is possible to generate a real-time reconstruction of the breast as a mesh. The development and validation of our method was performed using a previously described synthetic dataset. Hence, this procedure takes RGB images and the cameras' position and outputs the breasts' meshes. It has a mean error of 3.9 mm and a standard deviation of 1.2 mm. The final results attest to the ability of this methodology to predict the breast's shape and size using monocular images.Clinical Relevance- This work proposes a method based on artificial intelligence and monocular RGB images to obtain the breast's volume during robotic guided breast biopsies, improving their execution and safety.
Assuntos
Mamoplastia , Procedimentos Cirúrgicos Robóticos , Robótica , Humanos , Feminino , Inteligência Artificial , Mama/patologiaRESUMO
Breast cancer is the most prevalent type of cancer in women. Although mammography is used as the main imaging modality for the diagnosis, robust lesion detection in mammography images is a challenging task, due to the poor contrast of the lesion boundaries and the widely diverse sizes and shapes of the lesions. Deep Learning techniques have been explored to facilitate automatic diagnosis and have produced outstanding outcomes when used for different medical challenges. This study provides a benchmark for breast lesion detection in mammography images. Five state-of-art methods were evaluated on 1592 mammograms from a publicly available dataset (CBIS-DDSM) and compared considering the following seven metrics: i) mean Average Precision (mAP); ii) intersection over union; iii) precision; iv) recall; v) True Positive Rate (TPR); and vi) false positive per image. The CenterNet, YOLOv5, Faster-R-CNN, EfficientDet, and RetinaNet architectures were trained with a combination of the L1 localization loss and L2 localization loss. Despite all evaluated networks having mAP ratings greater than 60%, two managed to stand out among the evaluated networks. In general, the results demonstrate the efficiency of the model CenterNet with Hourglass-104 as its backbone and the model YOLOv5, achieving mAP scores of 70.71% and 69.36%, and TPR scores of 96.10% and 92.19%, respectively, outperforming the state-of-the-art models.Clinical Relevance - This study demonstrates the effectiveness of deep learning algorithms for breast lesion detection in mammography, potentially improving the accuracy and efficiency of breast cancer diagnosis.
Assuntos
Neoplasias da Mama , Aprendizado Profundo , Feminino , Humanos , Mamografia/métodos , Neoplasias da Mama/diagnóstico por imagem , Neoplasias da Mama/patologia , Detecção Precoce de Câncer , AlgoritmosRESUMO
Medical image segmentation is a paramount task for several clinical applications, namely for the diagnosis of pathologies, for treatment planning, and for aiding image-guided surgeries. With the development of deep learning, Convolutional Neural Networks (CNN) have become the state-of-the-art for medical image segmentation. However, issues are still raised concerning the precise object boundary delineation, since traditional CNNs can produce non-smooth segmentations with boundary discontinuities. In this work, a U-shaped CNN architecture is proposed to generate both pixel-wise segmentation and probabilistic contour maps of the object to segment, in order to generate reliable segmentations at the object's boundaries. Moreover, since the segmentation and contour maps must be inherently related to each other, a dual consistency loss that relates the two outputs of the network is proposed. Thus, the network is enforced to consistently learn the segmentation and contour delineation tasks during the training. The proposed method was applied and validated on a public dataset of cardiac 3D ultrasound images of the left ventricle. The results obtained showed the good performance of the method and its applicability for the cardiac dataset, showing its potential to be used in clinical practice for medical image segmentation.Clinical Relevance- The proposed network with dual consistency loss scheme can improve the performance of state-of-the-art CNNs for medical image segmentation, proving its value to be applied for computer-aided diagnosis.
Assuntos
Processamento de Imagem Assistida por Computador , Imageamento Tridimensional , Processamento de Imagem Assistida por Computador/métodos , Imageamento Tridimensional/métodos , Redes Neurais de Computação , Coração , Ventrículos do CoraçãoRESUMO
Chronic Venous Disorders (CVD) of the lower limbs are one of the most prevalent medical conditions, affecting 35% of adults in Europe and North America. Due to the exponential growth of the aging population and the worsening of CVD with age, it is expected that the healthcare costs and the resources needed for the treatment of CVD will increase in the coming years. The early diagnosis of CVD is fundamental in treatment planning, while the monitoring of its treatment is fundamental to assess a patient's condition and quantify the evolution of CVD. However, correct diagnosis relies on a qualitative approach through visual recognition of the various venous disorders, being time-consuming and highly dependent on the physician's expertise. In this paper, we propose a novel automatic strategy for the joint segmentation and classification of CVDs. The strategy relies on a multi-task deep learning network, denominated VENet, that simultaneously solves segmentation and classification tasks, exploiting the information of both tasks to increase learning efficiency, ultimately improving their performance. The proposed method was compared against state-of-the-art strategies in a dataset of 1376 CVD images. Experiments showed that the VENet achieved a classification performance of 96.4%, 96.4%, and 97.2% for accuracy, precision, and recall, respectively, and a segmentation performance of 75.4%, 76.7.0%, 76.7% for the Dice coefficient, precision, and recall, respectively. The joint formulation increased the robustness of both tasks when compared to the conventional classification or segmentation strategies, proving its added value, mainly for the segmentation of small lesions.
Assuntos
Doenças Cardiovasculares , Redes Neurais de Computação , Veias , Idoso , Humanos , Europa (Continente) , Processamento de Imagem Assistida por Computador/métodos , América do Norte , Doença CrônicaRESUMO
Accurate lesion classification as benign or malignant in breast ultrasound (BUS) images is a critical task that requires experienced radiologists and has many challenges, such as poor image quality, artifacts, and high lesion variability. Thus, automatic lesion classification may aid professionals in breast cancer diagnosis. In this scope, computer-aided diagnosis systems have been proposed to assist in medical image interpretation, outperforming the intra and inter-observer variability. Recently, such systems using convolutional neural networks have demonstrated impressive results in medical image classification tasks. However, the lack of public benchmarks and a standardized evaluation method hampers the performance comparison of networks. This work is a benchmark for lesion classification in BUS images comparing six state-of-the-art networks: GoogLeNet, InceptionV3, ResNet, DenseNet, MobileNetV2, and EfficientNet. For each network, five input data variations that include segmentation information were tested to compare their impact on the final performance. The methods were trained on a multi-center BUS dataset (BUSI and UDIAT) and evaluated using the following metrics: precision, sensitivity, F1-score, accuracy, and area under the curve (AUC). Overall, the lesion with a thin border of background provides the best performance. For this input data, EfficientNet obtained the best results: an accuracy of 97.65% and an AUC of 96.30%.Clinical Relevance- This study showed the potential of deep neural networks to be used in clinical practice for breast lesion classification, also suggesting the best model choices.
Assuntos
Neoplasias da Mama , Aprendizado Profundo , Feminino , Humanos , Mama/diagnóstico por imagem , Neoplasias da Mama/diagnóstico por imagem , Redes Neurais de Computação , UltrassonografiaRESUMO
Left atrial appendage (LAA) is the major source of thromboembolism in patients with non-valvular atrial fibrillation. Currently, LAA occlusion can be offered as a treatment for these patients, obstructing the LAA through a percutaneously delivered device. Nevertheless, correct device sizing is a complex task, requiring manual analysis of medical images. This approach is sub-optimal, time-demanding, and highly variable between experts. Different solutions were proposed to improve intervention planning, but, no efficient solution is available to 2D ultrasound, which is the most used imaging modality for intervention planning and guidance. In this work, we studied the performance of recently proposed deep learning methods when applied for the LAA segmentation in 2D ultrasound. For that, it was created a 2D ultrasound database. Then, the performance of different deep learning methods, namely Unet, UnetR, AttUnet, TransAttUnet was assessed. All networks were compared using seven metrics: i) Dice coefficient; ii) Accuracy iii) Recall; iv) Specificity; v) Precision; vi) Hausdorff distance and vii) Average distance error. Overall, the results demonstrate the efficiency of AttUnet and TransAttUnet with dice scores of 88.62% and 89.28%, and accuracy of 88.25% and 86.30%, respectively. The current results demonstrate the feasibility of deep learning methods for LAA segmentation in 2D ultrasound.Clinical relevance- Our results proved the clinical potential of deep neural networks for the LAA anatomical analysis.
Assuntos
Apêndice Atrial , Aprendizado Profundo , Humanos , Apêndice Atrial/diagnóstico por imagem , Ecocardiografia Transesofagiana/métodos , Ultrassonografia , Bases de Dados FactuaisRESUMO
Ultrasound (US) imaging is a widely used medical imaging modality for the diagnosis, monitoring, and surgical planning for kidney conditions. Thus, accurate segmentation of the kidney and internal structures in US images is essential for the assessment of kidney function and the detection of pathological conditions, such as cysts, tumors, and kidney stones. Therefore, there is a need for automated methods that can accurately segment the kidney and internal structures in US images. Over the years, automatic strategies were proposed for such purpose, with deep learning methods achieving the current state-of-the-art results. However, these strategies typically ignore the segmentation of the internal structures of the kidney. Moreover, they were evaluated in different private datasets, hampering the direct comparison of results, and making it difficult to determination the optimal strategy for this task. In this study, we perform a comparative analysis of 7 deep learning networks for the segmentation of the kidney and internal structures (Capsule, Central Echogenic Complex (CEC), Cortex and Medulla) in 2D US images in an open access multi-class kidney US dataset. The dataset includes 514 images, acquired in multiple clinical centers using different US machines and protocols. The dataset contains the annotation of two experts, but 321 images with complete segmentation of all 4 classes were used. Overall, the results demonstrate that the DeepLabV3+ network outperformed the inter-rater variability with a Dice score of 78.0% compared to 75.6% for inter-rater variability. Specifically, DeepLabV3Plus achieved mean Dice scores of 94.2% for the Capsule, 85.8% for the CEC, 62.4% for the Cortex, and 69.6% for the Medulla. These findings suggest the potential of deep learning-based methods in improving the accuracy of kidney segmentation in US images.Clinical Relevance- This study shows the potential of DL for improving accuracy of kidney segmentation in US, leading to increased diagnostic efficiency, and enabling new applications such as computer-aided diagnosis and treatment, ultimately resulting in improved patient outcomes and reduced healthcare costs.1.
Assuntos
Aprendizado Profundo , Humanos , Diagnóstico por Computador/métodos , Rim/diagnóstico por imagem , Semântica , Conjuntos de Dados como AssuntoRESUMO
Formalizing surgical activities as triplets of the used instruments, actions performed, and target anatomies is becoming a gold standard approach for surgical activity modeling. The benefit is that this formalization helps to obtain a more detailed understanding of tool-tissue interaction which can be used to develop better Artificial Intelligence assistance for image-guided surgery. Earlier efforts and the CholecTriplet challenge introduced in 2021 have put together techniques aimed at recognizing these triplets from surgical footage. Estimating also the spatial locations of the triplets would offer a more precise intraoperative context-aware decision support for computer-assisted intervention. This paper presents the CholecTriplet2022 challenge, which extends surgical action triplet modeling from recognition to detection. It includes weakly-supervised bounding box localization of every visible surgical instrument (or tool), as the key actors, and the modeling of each tool-activity in the form of triplet. The paper describes a baseline method and 10 new deep learning algorithms presented at the challenge to solve the task. It also provides thorough methodological comparisons of the methods, an in-depth analysis of the obtained results across multiple metrics, visual and procedural challenges; their significance, and useful insights for future research directions and applications in surgery.
Assuntos
Inteligência Artificial , Cirurgia Assistida por Computador , Humanos , Endoscopia , Algoritmos , Cirurgia Assistida por Computador/métodos , Instrumentos CirúrgicosRESUMO
Context-aware decision support in the operating room can foster surgical safety and efficiency by leveraging real-time feedback from surgical workflow analysis. Most existing works recognize surgical activities at a coarse-grained level, such as phases, steps or events, leaving out fine-grained interaction details about the surgical activity; yet those are needed for more helpful AI assistance in the operating room. Recognizing surgical actions as triplets of combination delivers more comprehensive details about the activities taking place in surgical videos. This paper presents CholecTriplet2021: an endoscopic vision challenge organized at MICCAI 2021 for the recognition of surgical action triplets in laparoscopic videos. The challenge granted private access to the large-scale CholecT50 dataset, which is annotated with action triplet information. In this paper, we present the challenge setup and the assessment of the state-of-the-art deep learning methods proposed by the participants during the challenge. A total of 4 baseline methods from the challenge organizers and 19 new deep learning algorithms from the competing teams are presented to recognize surgical action triplets directly from surgical videos, achieving mean average precision (mAP) ranging from 4.2% to 38.1%. This study also analyzes the significance of the results obtained by the presented approaches, performs a thorough methodological comparison between them, in-depth result analysis, and proposes a novel ensemble method for enhanced recognition. Our analysis shows that surgical workflow analysis is not yet solved, and also highlights interesting directions for future research on fine-grained surgical activity recognition which is of utmost importance for the development of AI in surgery.
Assuntos
Benchmarking , Laparoscopia , Humanos , Algoritmos , Salas Cirúrgicas , Fluxo de Trabalho , Aprendizado ProfundoRESUMO
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.
Assuntos
Processamento de Imagem Assistida por Computador , Substância Branca , Gravidez , Feminino , Humanos , Processamento de Imagem Assistida por Computador/métodos , Encéfalo/diagnóstico por imagem , Cabeça , Feto/diagnóstico por imagem , Algoritmos , Imageamento por Ressonância Magnética/métodosRESUMO
Chronic Venous Disorders (CVD) of lower limbs are one of the most prevalent medical conditions, affecting 35% of adults in Europe and North America. The early diagnosis of CVD is critical, however, the diagnosis relies on a visual recognition of the various venous disorders which is time- consuming and dependent on the physician's expertise. Thus, automatic strategies for the classification of the CVD severity are claimed. This paper proposed an automatic ensemble-based strategy of Deep Convolutional Neural Networks (DCNN) for the classification of CVDs severity from medical images. First, a clinical dataset containing 1376 images of patients' legs with CVD of 5 different levels of severity was constructed. Then, the constructed dataset was randomly split into training, testing, and validation datasets. Subsequently, a set of DCNN were individually applied to the images for classification. Finally, instead of a traditional voting ensemble strategy, extracted feature vectors from each DCNN were concatenated and fed into a new ensemble optimization network. Experiments showed that the proposed strategy achieved a classification with 93.8%, 93.4%, 92.4% of accuracy, precision, and recall, respectively. Moreover, compared to the traditional ensemble strategy, improvement in the accuracy of ~2% was registered. The proposed strategy showed to be accurate and robust for the diagnosis of CVD severity from medical images. Nevertheless, further research using an extensive clinical database is required to validate the potential of this strategy. Clinical Relevance- An automatic classification of CVD to reduce the probability of underdiagnoses and promote the treatment of CVD in the early stages.
Assuntos
Doenças Cardiovasculares , Redes Neurais de Computação , Adulto , Bases de Dados Factuais , Europa (Continente) , HumanosRESUMO
BACKGROUND AND OBJECTIVE: Examination of head shape and brain during the fetal period is paramount to evaluate head growth, predict neurodevelopment, and to diagnose fetal abnormalities. Prenatal ultrasound is the most used imaging modality to perform this evaluation. However, manual interpretation of these images is challenging and thus, image processing methods to aid this task have been proposed in the literature. This article aims to present a review of these state-of-the-art methods. METHODS: In this work, it is intended to analyze and categorize the different image processing methods to evaluate fetal head and brain in ultrasound imaging. For that, a total of 109 articles published since 2010 were analyzed. Different applications are covered in this review, namely analysis of head shape and inner structures of the brain, standard clinical planes identification, fetal development analysis, and methods for image processing enhancement. RESULTS: For each application, the reviewed techniques are categorized according to their theoretical approach, and the more suitable image processing methods to accurately analyze the head and brain are identified. Furthermore, future research needs are discussed. Finally, topics whose research is lacking in the literature are outlined, along with new fields of applications. CONCLUSIONS: A multitude of image processing methods has been proposed for fetal head and brain analysis. Summarily, techniques from different categories showed their potential to improve clinical practice. Nevertheless, further research must be conducted to potentiate the current methods, especially for 3D imaging analysis and acquisition and for abnormality detection.
Assuntos
Cabeça , Ultrassonografia Pré-Natal , Encéfalo/diagnóstico por imagem , Feminino , Cabeça/diagnóstico por imagem , Humanos , Processamento de Imagem Assistida por Computador , Gravidez , UltrassonografiaRESUMO
Cephalometric analysis is an important and routine task in the medical field to assess craniofacial development and to diagnose cranial deformities and midline facial abnormalities. The advance of 3D digital techniques potentiated the development of 3D cephalometry, which includes the localization of cephalometric landmarks in the 3D models. However, manual labeling is still applied, being a tedious and time-consuming task, highly prone to intra/inter-observer variability. In this paper, a framework to automatically locate cephalometric landmarks in 3D facial models is presented. The landmark detector is divided into two stages: (i) creation of 2D maps representative of the 3D model; and (ii) landmarks' detection through a regression convolutional neural network (CNN). In the first step, the 3D facial model is transformed to 2D maps retrieved from 3D shape descriptors. In the second stage, a CNN is used to estimate a probability map for each landmark using the 2D representations as input. The detection method was evaluated in three different datasets of 3D facial models, namely the Texas 3DFR, the BU3DFE, and the Bosphorus databases. An average distance error of 2.3, 3.0, and 3.2 mm were obtained for the landmarks evaluated on each dataset. The obtained results demonstrated the accuracy of the method in different 3D facial datasets with a performance competitive to the state-of-the-art methods, allowing to prove its versability to different 3D models. Clinical Relevance- Overall, the performance of the landmark detector demonstrated its potential to be used for 3D cephalometric analysis.
Assuntos
Pontos de Referência Anatômicos , Imageamento Tridimensional , Pontos de Referência Anatômicos/diagnóstico por imagem , Cefalometria/métodos , Face/anatomia & histologia , Face/diagnóstico por imagem , Humanos , Imageamento Tridimensional/métodos , Reprodutibilidade dos TestesRESUMO
Ultrasound (US) imaging despite being safe, cost-effective, and radiation-free, presents poor quality and artifacts, requiring specific medical training in US probe handling and image evaluation. The use of simulators to train physicians has proven its effectiveness, but most of them require specific facilities and hardware. In the last few years, augmented reality has gained relevance to simulate real scenarios which can avoid large setups and broaden medical training to more physicians. This work proposes a new framework for the training of US images acquisition. It consists of a custom-made application that runs on AR glasses (Microsoft HoloLens 2) and interacts with a US simulator application. The AR glasses track the orientation of a QR code mounted on a US probe, communicating its orientation with the US simulator application. This allows the physician to interact with a US probe seeing in real-time the US image in the physician's field of view. The QR code tracking assessment of the AR glasses was conducted by measuring the orientation accuracy and precision when compared with the measures of an electromagnetic tracking device (i.e., NDI Aurora). The proposed solution presented a good performance, rendering the US image in AR glasses with real-time feedback. Moreover, it can track the QR code on the US probe with an accuracy of 0.755°, and a precision of 0.018°. Overall, the proposed framework presents promising results and the use of AR glasses as a tracking device reached a good performance. Clinical Relevance- Simulation is a relevant tool to train physicians, especially in US imaging. AR glasses can broaden the training to less trained physicians by reducing the need for complex setups. This technology allows the implementation of a more natural user interface, which can be relevant in scenarios where good coordination between the eyes and hands of the physician is necessary (i.e., Biopsies).
Assuntos
Realidade Aumentada , Simulação por Computador , UltrassonografiaRESUMO
Automatic lesion segmentation in mammography images assists in the diagnosis of breast cancer, which is the most common type of cancer especially among women. The robust segmentation of mammography images has been considered a backbreaking task due to: i) the low contrast of the lesion boundaries; ii) the extremely variable lesions' sizes and shapes; and iii) some extremely small lesions on the mammogram image. To overcome these drawbacks, Deep Learning methods have been implemented and have shown impressive results when applied to medical image segmentation. This work presents a benchmark for breast lesion segmentation in mammography images, where six state-of-the-art methods were evaluated on 1692 mammograms from a public dataset (CBIS-DDSM), and compared considering the following six metrics: i) Dice coefficient; ii) Jaccard index; iii) accuracy; iv) recall; v) specificity; and vi) precision. The base U-Net, UNETR, DynUNet, SegResNetVAE, RF-Net, MDA-Net architectures were trained with a combination of the cross-entropy and Dice loss functions. Although the networks presented Dice scores superior to 86%, two of them managed to distinguish themselves. In general, the results demonstrate the efficiency of the MDA-Net and DynUnet with Dice scores of 90.25% and 89.67%, and accuracy of 93.48% and 93.03%, respectively. Clinical Relevance--- The presented comparative study allowed to identify the current performance of deep learning strategies on the segmentation of breast lesions.