Search

Most children with autism spectrum disorder (ASD), in resource-limited settings (RLS), are diagnosed after the age of four. Our work confirmed and extended results of Pierce that eye tracking could discriminate between typically developing (TD) children and those with ASD. We demonstrated the initial 15 s was at least as discriminating as the entire video. We evaluated the GP-MCHAT-R, which combines the first 15 s of manually-coded gaze preference (GP) video with M-CHAT-R results on 73 TD children and 28 children with ASD, 36–99 months of age. The GP-MCHAT-R (AUC = 0.89 (95%CI: 0.82–0.95)), performed significantly better than the MCHAT-R (AUC = 0.78 (95%CI: 0.71–0.85)) and gaze preference (AUC = 0.76 (95%CI: 0.64–0.88)) alone. This tool may enable early screening for ASD in RLS. Supplementary Information The online version contains supplementary material available at 10.1007/s10803-021-04878-0.

Conventional methods to diagnose anemia require a blood draw. This generates a great problem in patients due to the fear of contracting a disease through syringes, or sensitivity to this element. The palpebral conjunctiva is an indicator of diseases such as the hordeolum, chalazion, marginal blepharitis, bacterial conjunctivitis, trachoma, and anemia. The palpebral conjunctiva pallor is an indicator of anemia and if we wanted to develop an automatic system, for the non-invasive diagnosis of anemia based on the analysis of photographs of the palpebral conjunctiva, we would need algorithms for the segmentation and analysis of this membrane. In this sense, this research proposes and develops a method for the automatic segmentation of the palpebral conjunctiva using an Android application and image processing techniques. As a result, the success of this segmentation method is 92.2%.

Pneumonia is one of the major causes of child mortality, yet with a timely diagnosis, it is usually curable with antibiotic therapy. In many developing regions, diagnosing pneumonia remains a challenge, due to shortages of medical resources. Lung ultrasound has proved to be a useful tool to detect lung consolidation as evidence of pneumonia. However, diagnosis of pneumonia by ultrasound has limitations: it is operator-dependent, and it needs to be carried out and interpreted by trained personnel. Pattern recognition and image analysis is a potential tool to enable automatic diagnosis of pneumonia consolidation without requiring an expert analyst. This paper presents a method for automatic classification of pneumonia using ultrasound imaging of the lungs and pattern recognition. The approach presented here is based on the analysis of brightness distribution patterns present in rectangular segments (here called "characteristic vectors") from the ultrasound digital images. In a first step we identified and eliminated the skin and subcutaneous tissue (fat and muscle) in lung ultrasound frames, and the "characteristic vectors"were analyzed using standard neural networks using artificial intelligence methods. We analyzed 60 lung ultrasound frames corresponding to 21 children under age 5 years (15 children with confirmed pneumonia by clinical examination and X-rays, and 6 children with no pulmonary disease) from a hospital based population in Lima, Peru. Lung ultrasound images were obtained using an Ultrasonix ultrasound device. A total of 1450 positive (pneumonia) and 1605 negative (normal lung) vectors were analyzed with standard neural networks, and used to create an algorithm to differentiate lung infiltrates from healthy lung. A neural network was trained using the algorithm and it was able to correctly identify pneumonia infiltrates, with 90.9% sensitivity and 100% specificity. This approach may be used to develop operator-independent computer algorithms for pneumonia diagnosis using ultrasound in young children.

Background Autism spectrum disorder (ASD) currently affects nearly 1 in 160 children worldwide. In over two-thirds of evaluations, no validated diagnostics are used and gold standard diagnostic tools are used in less than 5% of evaluations. Currently, the diagnosis of ASD requires lengthy and expensive tests, in addition to clinical confirmation. Therefore, fast, cheap, portable, and easy-to-administer screening instruments for ASD are required. Several studies have shown that children with ASD have a lower preference for social scenes compared with children without ASD. Based on this, eye-tracking and measurement of gaze preference for social scenes has been used as a screening tool for ASD. Currently available eye-tracking software requires intensive calibration, training, or holding of the head to prevent interference with gaze recognition limiting its use in children with ASD. Methods In this study, we designed a simple eye-tracking algorithm that does not require calibration or head holding, as a platform for future validation of a cost-effective ASD potential screening instrument. This system operates on a portable and inexpensive tablet to measure gaze preference of children for social compared to abstract scenes. A child watches a one-minute stimulus video composed of a social scene projected on the left side and an abstract scene projected on the right side of the tablet’s screen. We designed five stimulus videos by changing the social/abstract scenes. Every child observed all the five videos in random order. We developed an eye-tracking algorithm that calculates the child’s gaze preference for the social and abstract scenes, estimated as the percentage of the accumulated time that the child observes the left or right side of the screen, respectively. Twenty-three children without a prior history of ASD and 8 children with a clinical diagnosis of ASD were evaluated. The recorded video of the child´s eye movement was analyzed both manually by an observer and automatically by our algorithm. Results This study demonstrates that the algorithm correctly differentiates visual preference for either the left or right side of the screen (social or abstract scenes), identifies distractions, and maintains high accuracy compared to the manual classification. The error of the algorithm was 1.52%, when compared to the gold standard of manual observation. Discussion This tablet-based gaze preference/eye-tracking algorithm can estimate gaze preference in both children with ASD and without ASD to a high degree of accuracy, without the need for calibration, training, or restraint of the children. This system can be utilized in low-resource settings as a portable and cost-effective potential screening tool for ASD.

Pneumonia is one of the major causes of child mortality, but it is curable if one can achieves early diagnostics. Unfortunately, in developing countries there is a lack of infrastructure and medical experts in rural areas to provide the required diagnostics opportunely. Lung ultrasound echography has proved to be an important tool to detect lung consolidates as evidence of pneumonia. The use of ultrasound to detect pneumonia is limited by the image analysis for interpretation, which is carried by human experts. Pattern recognition and image analysis is a potential tool to facilitate recognition of pneumonia consolidates in absence of medical experts for automatic diagnostics. To perform an automatic analysis of lung ultrasound images for pneumonia detection, the noise introduced by the image portion of the skin, notably complicates the processing and interpretation. This paper presents a methodology to recognize and eliminate the portion of the skin in lung ultrasound images.

International audience; Pneumonia is one of the major causes of child mortality. Unfortunately, in developing countries there is a lack of infrastructure and medical experts in rural areas to provide the required diagnostics opportunely. Lung ultrasound echography has proved to be an important tool to detect lung consolidates as evidence of pneumonia. This paper presents a method for automatic diagnostics of pneumonia using ultrasound imaging of the lungs. The approach presented here is based on the analysis of patterns present in rectangular segments from the ultrasound digital images. Specific features from the characteristic vectors were obtained and classified with standard neural networks. A training and testing set of positive and negative vectors were compiled. Vectors obtained from a single patient were included only in the testing or in the training set, but never in both. Our approach was able to correctly classify vectors with evidence of pneumonia, with 91.5% sensitivity and 100% specificity.