Limited Set Research Articles

Split-Level Evolutionary Neural Architecture Search With Elite Weight Inheritance.

Neural architecture search (NAS) has recently gained extensive interest in the deep learning community because of its great potential in automating the construction process of deep models. Among a variety of NAS approaches, evolutionary computation (EC) plays a pivotal role with its merit of gradient-free search ability. However, a massive number of the current EC-based NAS approaches evolve neural architectures in an absolutely discrete manner, which makes it tough to flexibly handle the number of filters for each layer, since they often reduce it to a limit set rather than searching for all possible values. Moreover, EC-based NAS methods are often criticized for their inefficiency in performance evaluation, which usually requires laborious full training for hundreds of candidate architectures generated. To address the inflexible search issue on the number of filters, this work proposes a split-level particle swarm optimization (PSO) approach. Each dimension of the particle is subdivided into an integer part and a fractional part, encoding the configurations of the corresponding layer, and the number of filters within a large range, respectively. In addition, the evaluation time is greatly saved by a novel elite weight inheritance method based on an online updating weight pool, and a customized fitness function considering multiple objectives is developed to well control the complexity of the searched candidate architectures. The proposed method, termed split-level evolutionary NAS (SLE-NAS), is computationally efficient, and outperforms many state-of-the-art peer competitors at much lower complexity across three popular image classification benchmark datasets.

GLOBALIZING SOCIETY AND THE COSMOPOLITAN PERSONALITY

The global changes in the 21st century regarding human populations speak of the changed position regarding the nation-state and the attempts of its institutions to control social, economic, and political life, as it has been done for centuries. In itself, this is a symptom of serious changes in the relationship between man and the world. The process of globalization, related to the crisis that the nation-state is going through, does not necessarily mean a finding of its decline. Rather, it expresses the fact that in the state of globality, the nation-state finds itself in a completely changed environment to which it must find ways to adapt to be able to define itself anew. The process of cosmopolitanism can be accepted as one of the options for this self-determination. Regionalism as a socio-structural phenomenon is limited at certain times by the social space and the individuals in it. Rationalism is a form of glocalization, while cosmopolitanism allows for this mobility, both of and in the social, and for the formation of a specific, cosmopolitan worldview on the part of the individual. Today, we as "mobile people" are characterized not only by our technological mobility (owning and carrying with us various technological gadgets) but also by our extremely flexible and (if we wish) full awareness of what is happening around us. us. Another question is, however, whether the setting of internal limitations by the person himself in front of himself, and of what he will undertake as an action, will be realized as an intention or will have the strength to set before himself as a goal to overcome and extinguishes the risky situations that await him in the future. Even if cosmopolitan in spirit, individual human subjectivity will always be the bearer of concrete facts such as origin, bioanthropological characteristics, value, and moral specifics, but they are not the leading ones. The individual specifics are the individual nuances in the rich originality that represents the cosmopolitan personality. Cosmopolitanism as the current and future social trajectory of humanity must be and lead to the absence of antagonistic, separating boundaries that are embedded in our human nature.

Globalizing Society and the Cosmopolitan Personality

The global changes in the 21st century regarding human populations speak of the changed position regarding the nation-state and the attempts of its institutions to control social, economic, and political life, as it has been done for centuries. In itself, this is a symptom of serious changes in the relationship between man and the world. The process of globalization, related to the crisis that the nation-state is going through, does not necessarily mean a finding of its decline. Rather, it expresses the fact that in the state of globality, the nation-state finds itself in a completely changed environment to which it must find ways to adapt to be able to define itself anew. The process of cosmopolitanism can be accepted as one of the options for this self-determination. Regionalism as a socio-structural phenomenon is limited at certain times by the social space and the individuals in it. Rationalism is a form of glocalization, while cosmopolitanism allows for this mobility, both of and in the social, and for the formation of a specific, cosmopolitan worldview on the part of the individual. Today, we as “mobile people” are characterized not only by our technological mobility (owning and carrying with us various technological gadgets) but also by our extremely flexible and (if we wish) full awareness of what is happening around us. Another question is, however, whether the setting of internal limitations by the person himself in front of himself, and of what he will undertake as an action, will be realized as an intention or will have the strength to set before himself as a goal to overcome and extinguishes the risky situations that await him in the future. Even if cosmopolitan in spirit, individual human subjectivity will always be the bearer of concrete facts such as origin, bioanthropological characteristics, value, and moral specifics, but they are not the leading ones. The individual specifics are the individual nuances in the rich originality that represents the cosmopolitan personality. Cosmopolitanism as the current and future social trajectory of humanity must be and lead to the absence of antagonistic, separating boundaries that are embedded in our human nature.

Medical negligence under pressure: obligations of clinicians and healthcare services in the setting of resource limitations.

Healthcare provision takes place in a variety of contexts, with variations of resources available to practitioners and their patients. Effects from the COVID-19 pandemic superimposed on existing system demands have driven increasing concern about resource limitations, particularly in rural and remote settings. This article explores the legal liability of medical practitioners and healthcare services with respect to actions in negligence arising from harm to patients suffered, either partly or wholly, as a result of resource limitations.

Galaxies in the zone of avoidance: Misclassifications using machine learning tools

Context. Automated methods for classifying extragalactic objects in large surveys offer significant advantages compared to manual approaches in terms of efficiency and consistency. However, the existence of the Galactic disk raises additional concerns. These regions are known for high levels of interstellar extinction, star crowding, and limited data sets and studies. Aims. In this study, we explore the identification and classification of galaxies in the zone of avoidance (ZoA). In particular, we compare our results in the near-infrared (NIR) with X-ray data. Methods. We analyzed the appearance of objects in the Galactic disk classified as galaxies using a published machine-learning (ML) algorithm and make a comparison with the visually confirmed galaxies from the VVV NIRGC catalog. Results. Our analysis, which includes the visual inspection of all sources cataloged as galaxies throughout the Galactic disk using ML techniques reveals significant differences. Only four galaxies were found in both the NIR and X-ray data sets. Several specific regions of interest within the ZoA exhibit a high probability of being galaxies in X-ray data but closely resemble extended Galactic objects. Our results indicate the difficulty in using ML methods for galaxy classification in the ZoA, which is mainly due to the scarcity of information on galaxies behind the Galactic plane in the training set. They also highlight the importance of considering specific factors that are present to improve the reliability and accuracy of future studies in this challenging region.

Noise sensitivity of the minimum spanning tree of the complete graph

Abstract We study the noise sensitivity of the minimum spanning tree (MST) of the $n$ -vertex complete graph when edges are assigned independent random weights. It is known that when the graph distance is rescaled by $n^{1/3}$ and vertices are given a uniform measure, the MST converges in distribution in the Gromov–Hausdorff–Prokhorov (GHP) topology. We prove that if the weight of each edge is resampled independently with probability $\varepsilon \gg n^{-1/3}$ , then the pair of rescaled minimum spanning trees – before and after the noise – converges in distribution to independent random spaces. Conversely, if $\varepsilon \ll n^{-1/3}$ , the GHP distance between the rescaled trees goes to $0$ in probability. This implies the noise sensitivity and stability for every property of the MST that corresponds to a continuity set of the random limit. The noise threshold of $n^{-1/3}$ coincides with the critical window of the Erdős-Rényi random graphs. In fact, these results follow from an analog theorem we prove regarding the minimum spanning forest of critical random graphs.

Brave the Wind and the Waves: Discovering Robust and Generalizable Graph Lottery Tickets.

The training and inference of Graph Neural Networks (GNNs) are costly when scaling up to large-scale graphs. Graph Lottery Ticket (GLT) has presented the first attempt to accelerate GNN inference on large-scale graphs by jointly pruning the graph structure and the model weights. Though promising, GLT encounters robustness and generalization issues when deployed in real-world scenarios, which are also long-standing and critical problems in deep learning ideology. In real-world scenarios, the distribution of unseen test data is typically diverse. We attribute the failures on out-of-distribution (OOD) data to the incapability of discerning causal patterns, which remain stable amidst distribution shifts. In traditional spase graph learning, the model performance deteriorates dramatically as the graph/network sparsity exceeds a certain high level. Worse still, the pruned GNNs are hard to generalize to unseen graph data due to limited training set at hand. To tackle these issues, we propose the Resilient Graph Lottery Ticket (RGLT) to find more robust and generalizable GLT in GNNs. Concretely, we reactivate a fraction of weights/edges by instantaneous gradient information at each pruning point. After sufficient pruning, we conduct environmental interventions to extrapolate potential test distribution. Finally, we perform last several rounds of model averages to further improve generalization. We provide multiple examples and theoretical analyses that underpin the universality and reliability of our proposal. Further, RGLT has been experimentally verified across various independent identically distributed (IID) and out-of-distribution (OOD) graph benchmarks.

Slitless spectrophotometry with forward modelling: Principles and application to measuring atmospheric transmission

Context. In the next decade, many optical surveys will aim to answer the question of the nature of dark energy by measuring its equation-of-state parameter at the per mill level. This requires trusting the photometric calibration of the survey with a precision never reached so far on many sources of systematic uncertainties. The measurement of the on-site atmospheric transmission for each exposure, or for each season or for the full survey on average, can help reach the per mill precision for the magnitudes. Aims. This work aims at proving the ability to use slitless spectroscopy for standard-star spectrophotometry and its use to monitor on-site atmospheric transmission as needed, for example, by the Vera C. Rubin Observatory Legacy Survey of Space and Time supernova cosmology program. We fully deal with the case of a disperser in the filter wheel, which is the configuration chosen in the Rubin Auxiliary Telescope. Methods. The theoretical basis of slitless spectrophotometry is at the heart of our forward-model approach to extract spectroscopic information from slitless data. We developed a publicly available software called Spectractor, which implements each ingredient of the model and finally performs a fit of a spectrogram model directly on image data to obtain the spectrum. Results. We show through simulations that our model allows us to understand the structure of spectrophotometric exposures. We also demonstrate its use on real data by solving specific issues and illustrating that our procedure allows the improvement of the model describing the data. Finally, we discuss how this approach can be used to directly extract atmospheric transmission parameters from the data and thus provide the base for on-site atmosphere monitoring. We show the efficiency of the procedure in simulations and test it on the limited available data set.

Negatives Make a Positive: An Embarrassingly Simple Approach to Semi-Supervised Few-Shot Learning.

Semi-Supervised Few-Shot Learning (SSFSL) aims to train a classifier that can adapt to new tasks using limited labeled data and a fixed amount of unlabeled data. Various sophisticated methods have been proposed to tackle the challenges associated with this problem. In this paper, we present a simple but quite effective approach to predict accurate negative pseudo-labels of unlabeled data from an indirect learning perspective. We leverage these pseudo-labels to augment the support set, which is typically limited in few-shot tasks, e.g., 1-shot classification. In such label-constrained scenarios, our approach can offer highly accurate negative pseudo-labels. By iteratively excluding negative pseudo-labels one by one, we ultimately derive a positive pseudo-label for each unlabeled sample in our approach. The integration of negative and positive pseudo-labels complements the limited support set, resulting in significant accuracy improvements for SSFSL. Our approach can be implemented in just few lines of code by only using off-the-shelf operations, yet it outperforms state-of-the-art methods on four benchmark datasets. Furthermore, our approach exhibits good adaptability and generalization capabilities when used as a plug-and-play counterpart alongside existing SSFSL methods and when extended to generalized linear models.

Gatekeeper model for ion selective membranes

A two-parameter model describes the resistance of a membrane challenged with different salt concentrations on either side of the membrane. This model treats the membrane as a circuit consisting of a resistor located between two switches. One switch is on the diluate side of the membrane. The second switch is on the concentrated side. The probability of the diluate side switch being active (loaded with a counter-ion) is β (dimensionless) and the probability of the switch being active (loaded with a counter-ion) on the concentrated side is γ (dimensionless). The probability of the circuit being active is the product of the probabilities βγ in which case the circuit is actively transporting a counter-ion across the membrane. The probability functions are calculated from the conductivity of the diluate λD (mS/cm), the concentrate λC (mS/cm) and a fitted parameter {Ksat} (mS/cm). The functions are β = λD/(λD +{Ksat}) and γ = λD/(λD + {Ksat}). These functions derived from enzyme kinetics where {Ksat} is analogous to the Michaelis-Menton saturation coefficient. The second fitted parameter is the minimum resistance rmin (Ωˑcm2) representing the case where the product βγ approaches unity (λD and λC ≫ {Ksat}). The product of the minimum resistance rmin and the applied voltage is analogous to the reciprocal of the maximum rate of an enzyme reaction. The resistance of the membrane rmem (Ωˑcm2) is rmem = rmin/(βγ). Measurements made with equal salt solutions on both sides of the membrane are used to calculate the resistance under any salt conditions. The probability functions β and γ represent the relative activity of the counter-ions on the surfaces of the membrane. This suggests that the Nernst potential across the membrane vmem (Volts) is expressed as vmem= (ɌT/Ƒ)ˑln (γ/β) where Ɍ (8.314 J/°K⋅mol) is the gas law constant, T (°K) is the temperature, and Ƒ (96,485 C/mol) is the Faraday constant. The current density (A/cm2) generated across the membrane under reverse electrodialysis conditions is i = vmem/rmem and the power density P (W/cm2) is P = i2rmem. It is, therefore, possible to estimate the performance of a membrane from a limited data set of resistance data such as may be found in the literature.

HyperFast: Instant Classification for Tabular Data

Training deep learning models and performing hyperparameter tuning can be computationally demanding and time-consuming. Meanwhile, traditional machine learning methods like gradient-boosting algorithms remain the preferred choice for most tabular data applications, while neural network alternatives require extensive hyperparameter tuning or work only in toy datasets under limited settings. In this paper, we introduce HyperFast, a meta-trained hypernetwork designed for instant classification of tabular data in a single forward pass. HyperFast generates a task-specific neural network tailored to an unseen dataset that can be directly used for classification inference, removing the need for training a model. We report extensive experiments with OpenML and genomic data, comparing HyperFast to competing tabular data neural networks, traditional ML methods, AutoML systems, and boosting machines. HyperFast shows highly competitive results, while being significantly faster. Additionally, our approach demonstrates robust adaptability across a variety of classification tasks with little to no fine-tuning, positioning HyperFast as a strong solution for numerous applications and rapid model deployment. HyperFast introduces a promising paradigm for fast classification, with the potential to substantially decrease the computational burden of deep learning. Our code, which offers a scikit-learn-like interface, along with the trained HyperFast model, can be found at https://github.com/AI-sandbox/HyperFast.

Near-infrared spectroscopy combined with deep convolutional generative adversarial network for prediction of component content in melt-cast explosive

Rapid and nondestructive prediction of component content is the key to improve industrial production efficiency. However, limited data sets also result in low generalization capabilities of the model, and it is time-consuming to obtain a large amount of content reference values and costly. Here, near infrared (NIR) spectroscopy technique combined with deep convolutional generated countermeasure network (DCGAN) was used to predict the trinitrotoluene (TNT) content of the melt-cast explosive. DCGAN was used to simultaneously extend its spectral data and content data. After several iterations, fake data were produced, which was very similar to the experimental data. The partial least squares (PLS) regression model was established and the performance was compared before and after data enhancement. The results showed that this method not only improved the performance of regression model, but also solved the problem of requiring large number of training data.

Abstract 6258: Inference of gene expression using fragmentation patterns from targeted high-depth sequencing of cell-free DNA

Abstract Cell-free DNA (cfDNA) circulating in blood plasma arises primarily from cellular chromatin fragmentation and release due to cell death. Studies have demonstrated that the assessment of fragmentomic features of cfDNA enables gene expression inference and tissue-of-origin classification with potential applications for noninvasive cancer detection. However, due to low depth of coverage of sites of interest, current whole genome sequencing (WGS) methods have not been able to infer expression of individual genes or limited gene sets. Therefore, we developed a targeted sequencing approach that enables individual gene expression inference from cfDNA fragmentation patterns based on transcriptional start-site gene activation probability (TSS-GAP). To assess the sensitivity of this method for cfDNA-inferred gene expression profiling, we applied TSS-GAP to blends of micrococcal nuclease (MNase)-digested DNA from a cancer cell line (LS180) and sorted peripheral blood mononuclear cells (PBMC), with LS180 DNA at varying concentrations (0.1-10%). This enabled the determination of the limit of detection (LoD), relative to healthy donor background levels, on the basis of the genes’ activation probabilities (TSS-GAP scores). We found 936 genes with high inferred expression in the LS180 cancer cell line and low inferred expression in non-cancer samples (i.e. CD4, CD14, and plasma cfDNA from 4 healthy donors) and used those for healthy donor background and LoD assessment. Using these gene-level background values as cutoffs, blends were assessed to determine the lowest blend level at which expression of the gene was able to be differentiated from background. Out of the 936 genes, 326 (34.8%) were detectable at a blend level of 0.1%, 59 (6.3%) at 0.3%, 31 (3.3%) at 1%, 19 (2.0%) at 3%, and 39 (4.2%) at 10%. In total, 416 genes could be detected by TSS-GAP at levels 1% of or lower above background, highlighting the potential of our method for detecting expression of certain genes even from a small fraction of cells contributing cfDNA to liquid biopsy samples. Further expansion of this work could consider the utility of such a method for circulating tumor DNA (ctDNA) detection, cfDNA tissue-of-origin classification, and deconvolution of cell types contributing to cfDNA found in blood. Citation Format: Emily Leff, Alexander Tseng, Victoria Cheung, Ehsan Tabari, Kimberly Walter, Alex Lovejoy, Cheng-Ho J. Lin. Inference of gene expression using fragmentation patterns from targeted high-depth sequencing of cell-free DNA [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 6258.

Demystifying the likelihood of reidentification in neuroimaging data: A technical and regulatory analysis

Abstract Sharing research data has been widely promoted in the field of neuroimaging and has enhanced the rigor and reproducibility of neuroimaging studies. Yet the emergence of novel software tools and algorithms, such as face recognition, has raised concerns due to their potential to reidentify defaced neuroimaging data that are thought to have been deidentified. Despite the surge of privacy concerns, however, the risk of reidentification via these tools and algorithms has not yet been examined outside the limited settings for demonstration purposes. There is also a pressing need to carefully analyze regulatory implications of this new reidentification attack because concerns about the anonymity of data are the main reason that researchers think they are legally constrained from sharing their data. This study aims to tackle these gaps through rigorous technical and regulatory analyses. Using a simulation analysis, we first tested the generalizability of the matching accuracies in defaced neuroimaging data reported in a recent face recognition study (Schwarz et al., 2021). The results showed that the real-world likelihood of reidentification in defaced neuroimaging data via face recognition would be substantially lower than that reported in the previous studies. Next, by taking a US jurisdiction as a case study, we analyzed whether the novel reidentification threat posed by face recognition would place defaced neuroimaging data out of compliance under the current regulatory regime. Our analysis suggests that defaced neuroimaging data using existing tools would still meet the regulatory requirements for data deidentification. A brief comparison with the EU’s General Data Protection Regulation (GDPR) was also provided. Then, we examined the implication of NIH’s new Data Management and Sharing Policy on the current practice of neuroimaging data sharing based on the results of our simulation and regulatory analyses. Finally, we discussed future directions of open data sharing in neuroimaging.

고등학교 영어 교과서 속 칭찬과 칭찬응답

Objectives The purpose of the paper was to analyze two speech acts (compliment and compliment response) in high school English textbooks and to find whether they were presented authentically and accurately according to L2 pragmatic norms.
 Methods Compliments in 8 differing textbooks were analyzed in terms of three aspects of compliment (syntactic structures, lexicals and topics), and compliment responses in textbooks were categorized according to four types of response (acceptance, amendment, rejection and non-acknowledgement). Then the analyzed compliments and compliment responses were compared with those acts made by English native speakers.
 Results Compliments in textbooks heavily relied on specific syntactic structures, used a variety of adjectives rather than a limited set of adjectives, and focused more on personality than physical appearance as compliment topics, which showed clear differences from what English native speakers do in their performance of compliments. Also unlike native speakers who prefer acceptance by responding positively to compliments, compliment responses in textbooks over-used non-acceptance strategies through refusal or non-acknowledgement.
 Conclusions Given these results, English textbooks should be developed based only on pragmatic norms of target language speakers, not intuitions or L1 knowledge of textbook developers.

Modelling of beer sensory staleness based on flavour instability parameters

Why was the work done: The deterioration of the flavour of fresh beer is challenging for the brewing industry. Despite extensive research on flavour instability, the focus has centred on a limited set of parameters, rather than taking a broader approach.
 How was the work done: in this study, the intent was to produce a flavour stable beer. Using a low kilning temperature, malt of low staling potential was used in combination with best brewing practice to produce three batches of unpasteurised top fermented pale beers at a pilot scale. Forty-three markers were analysed in the fresh and aged beers (30°C for 15, 30, 60 and 90 days). Staleness was evaluated by a trained sensory panel and multivariate data analysis was used to explore how the markers contribute to staleness.
 What are the main findings: Repeatability was achieved between replicate brews and, subsequently, staling. Polyphenols, haze, total reactive antioxidant potential (TRAP), iso-α-acids, colour, furfural, 2-methylpropanal and 2-methylbutanal showed a strong correlation with staleness. Staleness doubled after 60 days of storage at 30°C, despite volatile aldehydes remaining below their sensory thresholds, implying a synergistic effect of carbonyls contributing to staleness. A Partial Least Square (PLS) model was established, modelling the sensory staleness from 2-methylpropanal, furfural, TRAP and the trans-/cis-iso-α-acids ratio.
 Why is the work important: The staling phenomena could be reproduced in beers from parallel brewing trials with only minor variations. The four parameters in PLS modelling indicate that beer staling involves a combination of oxidative and non-oxidative pathways.

Validation of ToucHb, a non-invasive haemoglobin estimation: Effective for normal ranges, needs improvement for anaemia detection.

Non-invasive methods for haemoglobin estimation hold enormous potential for early detection and treatment of anaemia, especially in limited resource settings. We sought to validate the diagnostic accuracy of ToucHb, a non-invasive haemoglobin estimation device available in the Indian market. We prospectively evaluated the diagnostic performance of the ToucHb device using the Automated complete blood count (CBC) method as the gold standard. Persons referred for haemoglobin estimation to the central laboratory of the government medical college hospital in Mysore, southern India were included in the study. Out Of 140 people approached, 127 gave consent; 65% (n = 82) were female with median age of 37 (IQR 28-45). ToucHB reported median haemoglobin value of 14 g/dL compared to 13.3 g/dL for CBC. Within 1 g/dL and 2 g/dL of CBC, 55.2% (70/127) and 74% (94/127) of ToucHb haemoglobin observations fell, respectively. The Bland-Altman plot showed a mean difference of 3 g/dL in haemoglobin between ToucHb and CBC among those with anaemia. The ToucHb device showed 22.2% sensitivity and 94.5% specificity for anaemia detection. In rural resource-limited settings, point of care non-invasive devices such as ToucHb can improve access and acceptance for anaemia screening. However, ToucHb has showed low sensitivity for anaemia detection and low accuracy at lower haemoglobin values. The utility of the instrument is especially limited in detecting anaemia, while it can estimate haemoglobin accurately among those with haemoglobin is in the normal range. Based on these findings, ToucHb and devices that work on the core technology deployed in ToucHb may be better suited to monitor known haemoglobin level rather than in anaemia screening or detection in primary/ secondary care and community settings.

Comparison of Efficacy and Safety Profile of Conservative Versus Surgical Management of Meniscal Injuries

Background: Surgical management of meniscal tear carries financial implications in resource limited settings like ours. Conservative management could address this issue, if its safety and efficacy profile is better understood. Objectives: The objective of this study was to compare the efficacy and safety of conservative and surgical management of patients with meniscal tear with conservative management.Material and Methods: Descriptive comparative study of 80 patients with meniscal tear, recruited through non-probability convenient sampling technique, was carried out at Orthopedic unit MMC MTI Mardan, during 1st August 2022 and 31st July 2023. Patients were assigned to surgical and conservative group. International Knee Documentation Committee (IKDC) score at baseline and 3 months after treatment were compared for efficacy. Treatment related complications were noted.Results: A total of 80 patients were enrolled with 40 patients in each group (surgical versus conservative). The mean baseline and IKDC score at week 12 in surgical versus conservative group were 45.069±13.301 versus 51.873±17.90 and 79.52±7.40 versus 73.92±11.67 respectively. Surgical group showed treatment response in 37 patients (92.5%) versus 31 (77.5%) in conservative approach (p value 0.060). Surgical site infection was observed in 5 patients (12.5%) in surgical group. Medication related adverse effects were observed in 3 patients (7.5%) in conservative group.Conclusion: No appreciable differences in the clinical results, such as pain reduction or better knee function, between patients who received meniscal surgery and those who underwent conservative treatment for meniscal tears.Keywords: Conservative Approach, Meniscal Injury, Surgical Approach, Treatment Outcomes

Evaluation of Effectiveness of Self-Supervised Learning in Chest X-Ray Imaging to Reduce Annotated Images.

A significant challenge in machine learning-based medical image analysis is the scarcity of medical images. Obtaining a large number of labeled medical images is difficult because annotating medical images is a time-consuming process that requires specialized knowledge. In addition, inappropriate annotation processes can increase model bias. Self-supervised learning (SSL) is a type of unsupervised learning method that extracts image representations. Thus, SSL can be an effective method to reduce the number of labeled images. In this study, we investigated the feasibility of reducing the number of labeled images in a limited set of unlabeled medical images. The unlabeled chest X-ray (CXR) images were pretrained using the SimCLR framework, and then the representations were fine-tuned as supervised learning for the target task. A total of 2000 task-specific CXR images were used to perform binary classification of coronavirus disease 2019 (COVID-19) and normal cases. The results demonstrate that the performance of pretraining on task-specific unlabeled CXR images can be maintained when the number of labeled CXR images is reduced by approximately 40%. In addition, the performance was significantly better than that obtained without pretraining. In contrast, a large number of pretrained unlabeled images are required to maintain performance regardless of task specificity among a small number of labeled CXR images. In summary, to reduce the number of labeled images using SimCLR, we must consider both the number of images and the task-specific characteristics of the target images.

Dorsolateral prefrontal activity supports a cognitive space organization of cognitive control.

Cognitive control resolves conflicts between task-relevant and -irrelevant information to enable goal-directed behavior. As conflicts can arise from different sources (e.g., sensory input, internal representations), how a limited set of cognitive control processes can effectively address diverse conflicts remains a major challenge. Based on the cognitive space theory, different conflicts can be parameterized and represented as distinct points in a (low-dimensional) cognitive space, which can then be resolved by a limited set of cognitive control processes working along the dimensions. It leads to a hypothesis that conflicts similar in their sources are also represented similarly in the cognitive space. We designed a task with five types of conflicts that could be conceptually parameterized. Both human performance and fMRI activity patterns in the right dorsolateral prefrontal cortex support that different types of conflicts are organized based on their similarity, thus suggesting cognitive space as a principle for representing conflicts.