Contextual associations represented both in neural networks and human behavior

Contextual associations facilitate object recognition in human vision. However, the role of context in artificial vision remains elusive as does the characteristics that humans use to define context. We investigated whether contextually related objects (bicycle-helmet) are represented more similarly in convolutional neural networks (CNNs) used for image understanding than unrelated objects (bicycle-fork). Stimuli were of objects against a white background and consisted of a diverse set of contexts (N=73). CNN representations of contextually related objects were more similar to one another than to unrelated objects across all CNN layers. Critically, the similarity found in CNNs correlated with human behavior across three experiments assessing contextual relatedness, emerging significant only in the later layers. The results demonstrate that context is inherently represented in CNNs as a result of object recognition training, and that the representation in the later layers of the network tap into the contextual regularities that predict human behavior.

Solitary skin-colored nodule on a child’s face

Sir, A healthy, six-year-old boy presented with a slowly grown dome-shaped nodule on the mandibular angle region present for two years. The patient’s past medical and family history were unremarkable. A physical examination revealed a solitary, 1.3 × 1 cm, firm, painless, flesh-colored tumor (Fig. 1). Dermoscopy showed branching, serpentine vessels on a pink background (Fig. 2a). These features disappeared when slight pressure was exerted on the dermoscope and the tumor exhibited a central, white, structureless area (Fig. 2b). An excisional biopsy was performed. A microscopic examination showed a well-circumscribed, paucicellular dermal tumor composed of eosinophilic collagen bundles separated by clefts and forming a storiform pattern. Scattered fibroblasts were found among the collagen bundles. The overlying epidermis was slightly flattened (Fig. 3). The diagnosis of solitary sclerotic fibroma was established. Sclerotic fibroma (SF), also known as storiform collagenoma, is a rare benign skin tumor. It usually manifests itself as an asymptomatic, slowly growing, white-to-skin-colored papule or nodule [1]. It was first described in patients with Cowden’s disease, yet may also occur sporadically [2]. There were no mucocutaneous features of Cowden’s disease (tricholemmomas, oral fibromas, acral keratoses, palmar pits, and gingival and palatal papules) in the patient and her family members. Dermatofibroma, the main differential diagnosis of SF, usually exhibits hyperplastic changes of the epidermis instead of atrophy, and the boundaries of the lesion are unclear [2]. Only two papers have been published describing the dermoscopic findings of SF, consisting of a white background with peripheral arborizing vessels [3]. A white background may be related to an increased dermal collagen density. It is also described in dermatofibroma, typically with a peripheral pigmentation network. Although dermoscopy may improve the clinical diagnosis of SF, histopathological analysis is required.

Plant leaf identification system using convolutional neural network

This paper proposes a leaf identification system using convolutional neural network (CNN). This proposed system can identify five types of local Malaysia leaf which were acacia, papaya, cherry, mango and rambutan. By using CNN from deep learning, the network is trained from the database that acquired from leaf images captured by mobile phone for image classification. ResNet-50 was the architecture has been used for neural networks image classification and training the network for leaf identification. The recognition of photographs leaves requested several numbers of steps, starting with image pre-processing, feature extraction, plant identification, matching and testing, and finally extracting the results achieved in MATLAB. Testing sets of the system consists of 3 types of images which were white background, and noise added and random background images. Finally, interfaces for the leaf identification system have developed as the end software product using MATLAB app designer. As a result, the accuracy achieved for each training sets on five leaf classes are recorded above 98%, thus recognition process was successfully implemented.

Quoted text in the mental healthcare electronic record: an analysis of the distribution and content of single-word quotations

ObjectiveTo investigate the distribution and content of quoted text within the electronic health records (EHRs) using a previously developed natural language processing tool to generate a database of quotations.Designχ2 and logistic regression were used to assess the profile of patients receiving mental healthcare for whom quotations exist. K-means clustering using pre-trained word embeddings developed on general discharge summaries and psychosis specific mental health records were used to group one-word quotations into semantically similar groups and labelled by human subjective judgement.SettingEHRs from a large mental healthcare provider serving a geographic catchment area of 1.3 million residents in South London.ParticipantsFor analysis of distribution, 33 499 individuals receiving mental healthcare on 30 June 2019 in South London and Maudsley. For analysis of content, 1587 unique lemmatised words, appearing a minimum of 20 times on the database of quotations created on 16 January 2020.ResultsThe strongest individual indicator of quoted text is inpatient care in the preceding 12 months (OR 9.79, 95% CI 7.84 to 12.23). Next highest indicator is ethnicity with those with a black background more likely to have quoted text in comparison to white background (OR 2.20, 95% CI 2.08 to 2.33). Both are attenuated slightly in the adjusted model. Early psychosis intervention word embeddings subjectively produced categories pertaining to: mental illness, verbs, negative sentiment, people/relationships, mixed sentiment, aggression/violence and negative connotation.ConclusionsThe findings that inpatients and those from a black ethnic background more commonly have quoted text raise important questions around where clinical attention is focused and whether this may point to any systematic bias. Our study also shows that word embeddings trained on early psychosis intervention records are useful in categorising even small subsets of the clinical records represented by one-word quotations.

Light Penetration Properties of Visible and NIR Radiation in Tomatoes Applied to Non-Destructive Quality Assessment

Tomato is an important food product for which the development of non-destructive quality assessment methods is of great interest. Using visible and near-infrared (NIR) spectroscopy, the sugar content, acidity and even taste can be estimated through the use of chemometric methods (e.g., partial least squares regression). In the case of reflection spectra, which are the common modality for imaging spectroscopy, the question arises regarding how much of the interior of the tomato contributes to the measured spectra. An experiment was performed with tomatoes of four different types: beef tomato, classic round tomato, cocktail tomato, and snack tomato. The tomatoes were sliced at different thicknesses and imaged on a 98% reflective white background and a 4% reflective black background. Spectral images were acquired with VNIR (400–1000 nm) and NIR (900–1700 nm) imaging spectrographs. The difference between the spectra with a white and black background was used to determine the relationship between the wavelength and the light penetration depth. The results show that at wavelengths between 600 and 1100 nm, light penetrates the tomatoes up to a distance of 20 mm. The relation more or less follows the law of Lambert–Beer. This relation was the same for all four types of tomatoes. These results help the interpretation of chemometric models based on reflection (imaging) spectroscopy.

COVID-19 vaccination and menstrual cycle changes: A United Kingdom (UK) retrospective case-control study

Objectives. Our objectives were (1) to evaluate the prevalence of menstrual changes following vaccination against COVID-19, (2) to test potential risk factors for any such changes, and (3) to identify patterns of symptoms in participants' written accounts. Design. A secondary analysis of a retrospective online survey titled The Covid-19 Pandemic and Women's Reproductive Health , conducted in March 2021 in the UK before widespread media attention regarding potential impacts of SARS-CoV-2 vaccination on menstruation. Setting. Participants were recruited via a Facebook ad campaign in the UK. Participants. Eligibility criteria for survey completion were age greater than 18 years, having ever menstruated and currently living in the UK. In total, 26,710 people gave consent and completed the survey. For this analysis we selected 4,989 participants who were pre-menopausal and vaccinated. These participants were aged 28 to 43, predominantly from England (81%), of white background (95%) and not using hormonal contraception (58%). Main outcome measure. Reports of any menstrual changes (yes/no) following COVID-19 vaccination and words used to describe menstrual changes. Results. Among pre-menopausal vaccinated individuals (n=4,989), 80% did not report any menstrual cycle changes up to 4 months after their first COVID-19 vaccine injection. Current use of combined oral contraceptives was associated with lower odds of reporting any changes by 48% (OR = 0.52, 95CI = [0.34 to 0.78], P<0.001). Odds of reporting any menstrual changes were increased by 44% for current smokers (OR = 1.16, 95CI = [1.06 to 1.26], P<0.01) and by more than 50% for individuals with a positive COVID status [Long Covid (OR = 1.61, 95CI = [1.28 to 2.02], P<0.001), acute COVID (OR = 1.54, 95CI = [1.27 to 1.86], P<0.001)]. The effects remain after adjusting for self-reported magnitude of menstrual cycle changes over the year preceding the survey. Written accounts report diverse symptoms; the most common words include 'cramps', 'late', 'early', 'spotting', 'heavy' and 'irregular', with a low level of clustering among them. Conclusions. Following vaccination for COVID-19, menstrual disturbance occurred in 20% of individuals in a UK sample. Out of 33 variables investigated, smoking and a previous history of SARS-CoV-2 infection are found to be risk factors while using oestradiol-containing contraceptives was found to be a protective factor. Diverse experiences were reported, from menstrual bleeding cessation to heavy menstrual bleeding.

Real-Time Deformation Measurements Using Single Image Photogrammetry

Most photogrammetric measurements are currently based on image acquisition in the field and subsequent processing in office environment with certain temporal delay. However, in some cases it is necessary to process the data real-time, or at least in-situ. Bridge load testing is an example of measurement processing directly at the place of imaging, where almost immediate information about the current state or change of the object is required. An algorithm is developed for these purposes, including a camera controlling software and a MATLAB code that identifies and quantifies the shifts of the observed points in the image plane. The observed points are in the shape of black disks on a white background. Using a horizontal camera position individual epochs are captured. Each image is immediately transferred to a computer via Wi-Fi. The MATLAB code then loads the image and binarizes it. Binarization of the image is performed by the Canny edge detector. Using normalized 2-D cross-correlation, the algorithm determines the approximate coordinates based on a target template. A function performs least squares ellipse fitting and determines the center of the target in sub-pixel accuracy, the semi-major axis, the semi-minor axis and the rotation angle of the ellipse. The target detection is executed in a while cycle loop, which compares the point coordinates from each epoch to the initial state, thus quantifying the deformations in pixels. If the next image is not yet available, the loop restarts. The deformations are calculated based on the known scale of each target. This paper presents a detailed description of the development of the algorithm, the results achieved and the proposed improvements going forward.

The Effect of Changing Colours on Central Crowding Reading

Background: Crowding can be defined as the impaired recognition of closely spaced objects. Changing colour and lighting enhance visual comfort and perceptual troubles that influence impaired vision reading. Objective: The current study was aimed to investigate the impact of changing the flanker distance and unflanked targets with colours on central crowding reading for subjects with their distant best correction (BCVA) equal to or greater than 6/6. Methodology: Six native English speakers (age: 18–38) who participated in a cross-section intervention study were asked to identify the orientation of the letter E (flanked or unflanked) in different directions around the central target in different colours (red, green, blue and black) on a white background. Results: Different colours affect central crowding (p<0.05). However, the central crowding reading of red was not affected by changing flankers (P > 0.05). Conclusion: Central reading crowding is visual crowding. Different colours affect central crowding. However, the central crowding reading in red was not affected by changes in flankers.

Automated optimum visualization system for construction drawing reading

The task of reading drawings on construction sites has significant efficiency and cost problems. Recent products utilising laser projectors attempt to address the issue of drawing comprehension by projecting full scale versions of the drawings onto 3D surfaces, giving an in-place representation of the steps required to complete a task. However, they only allow projection in red or green at a single brightness level due to the inherent constraints of using a laser-based system, which could cause problems depending on the surface to be projected on and the ambient conditions. Thus, there is a need for a solution that is able to adjust the visualisation parameters of the displayed information based on the surface being projected onto. This study presents a system that automatically changes the visualisation parameters based on the colour and texture of the current surface to make drawings visible under any planar-like surfaces. The proposed system consists of software and hardware, and the software algorithm contains of two parts 1) the optimisation run that computes and updates the visualisation parameters and 2) the detection loop which runs continually and checks if the optimisation run needs to be triggered or not. In order to verify the proposed system, tests on 8 subjects with 4 background surfaces commonly found on site were performed. The test subjects were timed to find 10 bolt holes projected onto the surface using the optimisation system, which was then compared to a control case of black lines projected onto a white background. The system allowed users to complete the task on the real-world backgrounds in the same time as the control case, with the system resulting in up to a 600% decrease in recognition time on some backgrounds.