RESUMEN

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.

RESUMEN

BACKGROUND: In the scientific literature on Malaria in Pregnancy (MiP), no studies have been conducted on lifestyles based on critical theory. The objective of this study was to analyse the lifestyles or singular processes of social determination of health in MiP in northwestern Colombia. METHODS: Mixed QUAN-QUAL convergent triangulation study. In the quantitative component, a psychometric evaluation and a cross-sectional design were conducted in 400 pregnant women to whom the Pender-Walker lifestyle scale and a survey on MiP prevention were applied. In the qualitative study, a critical ethnography was conducted with 46 pregnant women in whom their narratives and practices regarding lifestyles at home and healthcare were described. RESULTS: The frequency of MiP was 9%, and a higher occurrence of the disease was identified in those who did not control stagnant water (29%), did not use insecticide-treated net (16%) and went to the hospital (14%) or the microscopist (20%) when they had fever. This coincides with the presence of unhealthy lifestyles, little knowledge about malaria, and a low perception of the risk of getting sick, as well as meanings and experiences about MiP, maternity, and pregnancy that show a high clinical, cultural, and socioeconomic burden for the women studied. CONCLUSION: This epidemiological profile and the approach to lifestyles based on the postulates of critical theory in health evidence that pregnant women exposed to malaria suffer serious social, cultural and health injustices that are not possible to impact with the current health model of malaria control in Colombia guided by aetiopathogenic, biomedical, positivist and utilitarian theories.

Asunto(s)

RESUMEN

BACKGROUND: Pregnancy Associated Malaria (PAM) include malaria in pregnancy (MiP), placental malaria (PM), and congenital malaria (CM). The evidence available in Colombia on PAM focuses on one of the presentations (MiP, PM or CM), and no study longitudinally analyses the infection from the pregnant woman, passing through the placenta, until culminating in the newborn. This study determined the frequency of MiP, PM, and CM caused by Plasmodium vivax, Plasmodium falciparum, or mixed infections, according to Thick Blood Smear (TBS) and quantitative Polymerase Chain Reaction (qPCR). Identifying associated factors of PAM and clinical-epidemiological outcomes in northwestern Colombia. METHODS: Prospective study of 431 pregnant women, their placenta, and newborns registered in the data bank of the research Group "Salud y Comunidad César Uribe Piedrahíta" which collected information between 2014 and 2020 in endemic municipalities of the departments of Córdoba and Antioquia. The frequency of infection was determined with 95% confidence intervals. Comparisons were made with the Chi-square test, Student t-test, prevalence ratios, and control for confounding variables by log-binomial regression. RESULTS: The frequency of MiP was 22.3% (4.6% using TBS), PM 24.8% (1.4% using TBS), and CM 11.8% (0% using TBS). Using TBS predominated P. vivax. Using qPCR the proportions of P. vivax and P. falciparum were similar for MiP and PM, but P. falciparum predominated in CM. The frequency was higher in nulliparous, and women with previous malaria. The main clinical effects of PAM were anaemia, low birth weight, and abnormal APGAR score. CONCLUSIONS: The magnitude of infections was not detected with TBS because most cases were submicroscopic (TBS-negative, qPCR-positive). This confirmed the importance of improving the molecular detection of cases. PAM continue being underestimated in the country due to that in Colombia the control programme is based on TBS, despite its outcomes on maternal, and congenital health.

Asunto(s)

RESUMEN

Focused cardiac ultrasound (FoCUS) is a valuable point-of-care method for evaluating cardiovascular structures and function, but its scope is limited by equipment and operator's experience, resulting in primarily qualitative 2D exams. This study presents a novel framework to automatically estimate the 3D spatial relationship between standard FoCUS views. The proposed framework uses a multi-view U-Net-like fully convolutional neural network to regress line-based heatmaps representing the most likely areas of intersection between input images. The lines that best fit the regressed heatmaps are then extracted, and a system of nonlinear equations based on the intersection between view triplets is created and solved to determine the relative 3D pose between all input images. The feasibility and accuracy of the proposed pipeline were validated using a novel realistic in silico FoCUS dataset, demonstrating promising results. Interestingly, as shown in preliminary experiments, the estimation of the 2D images' relative poses enables the application of 3D image analysis methods and paves the way for 3D quantitative assessments in FoCUS examinations.

Asunto(s)

RESUMEN

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.

Asunto(s)

RESUMEN

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.

Asunto(s)

RESUMEN

BACKGROUND: The meanings and experiences related to malaria in pregnancy (MiP) and its processes of social determination of health (PSDH) have not been reported in the world scientific literature. The objective was to understand the meanings and experiences of MiP, and to explain their PSDH in an endemic area from Colombia, 2022. METHODS: Critical ethnography with 46 pregnant women and 31 healthcare workers. In-depth and semi-structured interviews, focus group discussions, participant and non-participant observations, and field diaries were applied. A phenomenological-hermeneutic analysis, saturation and triangulation was carried out. The methodological rigor criteria were reflexivity, credibility, auditability, and transferability. RESULTS: At the singular level, participants indicated different problems in antenatal care and malaria control programmes, pregnant women were lacking knowledge about MiP, and malaria care was restricted to cases with high obstetric risk. Three additional levels that explain the PSDH of MiP were identified: (i) limitations of malaria control policies, and health-system, geographic, cultural and economic barriers by MiP diagnosis and treatment; (ii) problems of public health programmes and antenatal care; (iii) structural problems such as monetary poverty, scarcity of resources for public health and inefficiency in their use, lacking community commitment to preventive actions, and breach of institutional responsibilities of health promoter entity, municipalities and health services provider institutions. CONCLUSION: Initiatives for MiP control are concentrated at the singular level, PDSH identified in this research show the need to broaden the field of action, increase health resources, and improve public health programmes and antenatal care. It is also necessary to impact the reciprocal relationships of MiP with economic and cultural dimensions, although these aspects are increasingly diminished with the predominance and naturalization of neoliberal logic in health.

Asunto(s)

RESUMEN

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.

Asunto(s)

RESUMEN

In the context of Shared Autonomous Vehicles, the need to monitor the environment inside the car will be crucial. This article focuses on the application of deep learning algorithms to present a fusion monitoring solution which was three different algorithms: a violent action detection system, which recognizes violent behaviors between passengers, a violent object detection system, and a lost items detection system. Public datasets were used for object detection algorithms (COCO and TAO) to train state-of-the-art algorithms such as YOLOv5. For violent action detection, the MoLa InCar dataset was used to train on state-of-the-art algorithms such as I3D, R(2+1)D, SlowFast, TSN, and TSM. Finally, an embedded automotive solution was used to demonstrate that both methods are running in real-time.

Asunto(s)

RESUMEN

This study compared the clinical-parasitological profiles of gestational (GM), placental (PM), and congenital (CM) malaria in northwestern Colombia. A cross-sectional study with 829 pregnant women, 549 placentas, and 547 newborns was conducted. The frequency of GM was 35.8%, PM 20.9%, and CM 8.5%. P. vivax predominated in GM; in PM, the proportion of P. vivax and P. falciparum was similar; in CM, P. falciparum predominated. The main clinical findings were headache (49%), anemia (32%), fever (24%), and musculoskeletal pain (13%). The clinical manifestations were statistically higher in P. vivax infections. In submicroscopic GM (positive with qPCR and negative with thick blood smear), the frequency of anemia, sore throat, and a headache was statistically higher compared with pregnant women without malaria. GM, PM, and CM reduce birth weight and head circumference. In Colombia, this is the first research on the clinical characteristics of GM, PM, and CM; contrary to evidence from other countries, P. vivax and submicroscopic infections are associated with clinical outcomes.

RESUMEN

Mixed methods are essential in public health research and malaria control, because they allow grasping part of the complexity and diversity of the factors that determine health-disease. This study analyzes the mixed studies on malaria in Colombia, 1980-2022, through a systematic review in 15 databases and institutional repositories. The methodological quality was assessed with Mixed Methods Appraisal Tool (MMAT), STrengthening the Reporting of OBservational studies in Epidemiology (STROBE), and Standards for Reporting Qualitative Research (SRQR). The qualitative and quantitative findings were grouped into a four-level hierarchical matrix. The epidemiological profile of malaria morbidity, from traditional epidemiology, has been sustained by environmental problems, armed conflict, individual risk behaviors, and low adherence to recommendations from health institutions. However, the qualitative component reveals deeper causes that are less studied, of greater theoretical complexity, and that reflect challenges to design and implement health interventions, such as socioeconomic and political crises, poverty, and the neoliberal orientation in the malaria control policy; the latter reflected in the change in the role of the State, the fragmentation of control actions, the predominance of insurance over social assistance, the privatization of the provision of health services, the individualistic and economistic predominance of health, and low connection with popular tradition and community initiatives. The above confirms the importance of expanding mixed studies as a source of evidence to improve malaria research and control models in Colombia, and to identify the underlying causes of the epidemiological profile.

Asunto(s)

RESUMEN

Multi-human detection and tracking in indoor surveillance is a challenging task due to various factors such as occlusions, illumination changes, and complex human-human and human-object interactions. In this study, we address these challenges by exploring the benefits of a low-level sensor fusion approach that combines grayscale and neuromorphic vision sensor (NVS) data. We first generate a custom dataset using an NVS camera in an indoor environment. We then conduct a comprehensive study by experimenting with different image features and deep learning networks, followed by a multi-input fusion strategy to optimize our experiments with respect to overfitting. Our primary goal is to determine the best input feature types for multi-human motion detection using statistical analysis. We find that there is a significant difference between the input features of optimized backbones, with the best strategy depending on the amount of available data. Specifically, under a low-data regime, event-based frames seem to be the preferred input feature type, while higher data availability benefits the combined use of grayscale and optical flow features. Our results demonstrate the potential of sensor fusion and deep learning techniques for multi-human tracking in indoor surveillance, although it is acknowledged that further studies are needed to confirm our findings.

Asunto(s)

RESUMEN

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.

Asunto(s)

RESUMEN

This study aimed to evaluate the accuracy of the thick blood smear (TBS) versus quantitative polymerase chain reaction (qPCR) for the diagnosis of malaria associated with pregnancy (MAP) caused by P. falciparum or P. vivax in Colombia in its gestational malaria (GM), placental malaria (PM), and congenital malaria (CM) forms as well as to compare its accuracy in different subgroups of pregnant women according to the presence of fever, anemia and a history of malaria. This was a diagnostic evaluation of 829 pregnant women, 579 placentas, 381 umbilical cord samples, and 221 neonatal peripheral blood samples. Accuracy was evaluated based on the parameters of sensitivity, specificity, predictive values, likelihood ratios, and validity index, with their 95% confidence intervals. The frequency of GM was 36% (n = 297/829), PM 27% (n = 159/579), and CM 16.5% (n = 63/381) in umbilical cord samples and 2% (n = 5/221) in neonatal peripheral blood samples. For GM, the sensitivity was 55%, with higher rates in those infected with P. vivax (68%), with a history of malaria (69%), and with fever (96%). These three subgroups presented the best results in terms of the negative likelihood ratio and validity index. For PM, sensitivity was 8%; in subgroup analyses in terms of species, symptomatology (anemia and fever), and history of malaria, it was 1-18%, and the negative likelihood ratio was >0.80 in all subgroups. No false positives were recorded in any of the subgroups. The TBS did not detect any cases of CM. This study found the TBS yielded satisfactory results in terms of diagnosing GM for P. vivax, pregnant women with previous malaria and febrile. It also showed that the TBS is not useful for diagnosing PM and CM. It is necessary to conduct surveillance of MAP with molecular methods in in groups where TBS is deficient (asymptomatic GM, P. falciparum, and pregnant women without history of malaria) to optimize the timely treatment of PM and CM, avoid the deleterious effects of MAP and achieve the malaria elimination goals in Colombia.

RESUMEN

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.

Asunto(s)

RESUMEN

OBJECTIVE.: To evaluate the accuracy of thick smear (TS) versus quantitative polymerase chain reaction (PCR) for pregnancy-associated malaria (PAM). MATERIALS AND METHODS.: We carried out a systematic review of diagnostic tests in nine databases. Methodological quality was evaluated with QUADAS. Sensitivity, specificity, positive likelihood ratio (PLR), negative likelihood ratio (NLR), diagnostic odds ratio (DOR) and area under the ROC curve were estimated. Heterogeneity was determined with the Der Simonian-Laird Q method and uncertainty with the weighted percentage of each study on the overall result. RESULTS.: We included 10 studies with 5691 pregnant women, 1415 placentas and 84 neonates. In the studies with nested PCR (nPCR) and quantitative PCR (qPCR) as the standard, the diagnostic accuracy results were statistically similar, with very low sensitivity (50 and 54%, respectively), high specificity (99% in both cases), high PLR and poor NLR. When nPCR was used, the DOR was 162 (95%CI=66-401) and the area under the ROC curve was 95%, while with qPCR it was 231 (95%CI=27-1951) and 78%, respectively. CONCLUSIONS.: We demonstrated that research on the diagnostic accuracy of TS in PAM is limited. Microscopy showed poor performance in the diagnosis of asymptomatic or low parasitemia infections, which reinforces the importance of implementing other types of techniques for the follow-up and control of malaria infections in pregnant women, in order to achieve the control and possible elimination of PAM.

OBJETIVOS.: Evaluar la exactitud de gota gruesa (GG) frente a la reacción en cadena de la polimerasa (PCR) cuantitativa para la malaria asociada al embarazo (MAE). MATERIALES Y MÉTODOS.: Se realizó una revisión sistemática de pruebas diagnósticas en nueve bases de datos. Se evaluó la calidad metodológica con QUADAS. Se estimó sensibilidad, especificidad, cociente de probabilidad positivo (CPP) y negativo (CPN), razón de odds diagnóstica (ORD) y área bajo la curva ROC. Se determinó la heterogeneidad con el estadístico Q de Der Simonian-Laird y la incertidumbre con el porcentaje de peso de cada estudio sobre el resultado global. RESULTADOS.: Se incluyeron diez estudios con 5691 gestantes, 1415 placentas y 84 neonatos. En los estudios con nPCR (PCR anidada) y qPCR (PCR cuantitativa) como estándar, los resultados de exactitud diagnóstica fueron estadísticamente similares, con sensibilidad muy baja (50 y 54%, respectivamente), alta especificidad (99% en ambos casos), alto CPP y deficiente CPN. Usando nPCR la OR diagnóstica fue 162 (IC95%=66-401) y el área bajo la curva ROC fue 95%, mientras que con qPCR fueron 231 (IC95%=27-1951) y 78%, respectivamente. CONCLUSIONES.: Mediante un protocolo exhaustivo se demostró el bajo desarrollo de investigaciones sobre la exactitud diagnóstica de la GG en MAE. Se demostró que la microscopía tiene un desempeño deficiente para el diagnóstico de infecciones asintomáticas o de baja parasitemia, lo que afianza la importancia de implementar otro tipo de técnicas en el seguimiento y control de las infecciones por malaria en las gestantes, con el fin de lograr el control y posible eliminación de la MAE.

Asunto(s)

RESUMEN

Abstract We present the first case in Colombia of tricuspid endovascular valve in valve for failed bioprosthesis in a 40 years old patient with very high operative risk with great results, proposing kissing balloon annulus cracking technique as a practical solution for the colombian specialists.

Resumen Se presenta el primer caso en Colombia de un reemplazo percutáneo tipo válvula en válvula por falla de bioprótesis tricúspide en un paciente de 40 años con un muy alto riesgo quirúrgico, con excelentes resultados, proponiendo la técnica kissing balloon de fractura anular como una solución práctica para los especialistas colombianos.

RESUMEN

Passive immunity acquired through transplacental IgG transport is essential to protect infants against pathogens as childhood vaccination programs begins. Diarrhea caused by rotavirus and neonatal tetanus are common and potentially fatal childhood infections that can be prevented by transplacental IgG. However, it is not known whether maternal infections in pregnancy can reduce the transfer of these antibodies to the fetus. This study evaluated the effect of submicroscopic Plasmodium infection during pregnancy on the transfer of maternal IgG antibodies against rotavirus (anti-RV) and tetanus toxoid (anti-TT) to newborns of pregnant women residing in Puerto Libertador and Tierralta, Colombia. Expression of different immune mediators and levels of IgG against rotavirus and tetanus toxoid were quantified in pregnant women with and without Plasmodium infection during pregnancy. Submicroscopic infection at the time of delivery was associated with a cord-to-maternal ratio (CMR) > 1 for anti-RV and < 1 for anti-TT IgG, as well as with an increase in the expression of immune mediators of inflammation (IFN-γ), anti-inflammation (IL-10, TGF-ß), and regulation (FoxP3, CTLA-4). When compared by species, these findings (CMR > 1 for anti-RV and < 1 for anti-TT IgG) were conserved in submicroscopic Plasmodium vivax infections at delivery. The impact of Plasmodium infections on neonatal susceptibility to other infections warrants further exploration.

Asunto(s)

RESUMEN

With the evolution of technology associated with mobility and autonomy, Shared Autonomous Vehicles will be a reality. To ensure passenger safety, there is a need to create a monitoring system inside the vehicle capable of recognizing human actions. We introduce two datasets to train human action recognition inside the vehicle, focusing on violence detection. The InCar dataset tackles violent actions for in-car background which give us more realistic data. The InVicon dataset although doesn't have the realistic background as the InCar dataset can provide skeleton (3D body joints) data. This datasets were recorded with RGB, Depth, Thermal, Event-based, and Skeleton data. The resulting dataset contains 6 400 video samples and more than 3 million frames, collected from sixteen distinct subjects. The dataset contains 58 action classes, including violent and neutral (i.e., non-violent) activities.