Radiomics analysis for prediction and classification of submucosal tumors based on gastrointestinal endoscopic ultrasonography.

Objectives: To identify and classify submucosal tumors by building and validating a radiomics model with gastrointestinal endoscopic ultrasonography (EUS) images. Methods: A total of 144 patients diagnosed with submucosal tumors through gastrointestinal EUS were collected between January 2019 and October 2020. There are 1952 radiomic features extracted from each patient's EUS images. The statistical test and the customized least absolute shrinkage and selection operator regression were used for feature selection. Subsequently, an extremely randomized trees algorithm was utilized to construct a robust radiomics classification model specifically tailored for gastrointestinal EUS images. The performance of the model was measured by evaluating the area under the receiver operating characteristic curve. Results: The radiomics model comprised 30 selected features that showed good discrimination performance in the validation cohorts. During validation, the area under the receiver operating characteristic curve was calculated as 0.9203 and the mean value after 10-fold cross-validation was 0.9260, indicating excellent stability and calibration. These results confirm the clinical utility of the model. Conclusions: Utilizing the dataset provided curated from gastrointestinal EUS examinations at our collaborating hospital, we have developed a well-performing radiomics model. It can be used for personalized and non-invasive prediction of the type of submucosal tumors, providing physicians with aid for early treatment and management of tumor progression.

Rising frequency of ozone-favorable synoptic weather patterns contributes to 2015-2022 ozone increase in Guangzhou.

Objective weather classification methods have been extensively applied to identify dominant ozone-favorable synoptic weather patterns (SWPs), however, the consistency of different classification methods is rarely examined. In this study, we apply two widely-used objective methods, the self-organizing map (SOM) and K-means clustering analysis, to derive ozone-favorable SWPs at four Chinese megacities in 2015-2022. We find that the two algorithms are largely consistent in recognizing dominant ozone-favorable SWPs for four Chinese megacities. In the case of classifying six SWPs, the derived circulation fields are highly similar with a spatial correlation of 0.99 between the two methods, and the difference in the mean frequency of each SWP is less than 7%. The six dominant ozone-favorable SWPs in Guangzhou are all characterized by anomaly higher radiation and temperature, lower cloud cover, relative humidity, and wind speed, and stronger subsidence compared to climatology mean. We find that during 2015-2022, the occurrence of ozone-favorable SWPs days increases significantly at a rate of 3.2 day/year, faster than the increases in the ozone exceedance days (3.0 day/year). The interannual variability between the occurrence of ozone-favorable SWPs and ozone exceedance days are generally consistent with a temporal correlation coefficient of 0.6. In particular, the significant increase in ozone-favorable SWPs in 2022, especially the Subtropical High type which typically occurs in September, is consistent with a long-lasting ozone pollution episode in Guangzhou during September 2022. Our results thus reveal that enhanced frequency of ozone-favorable SWPs plays an important role in the observed 2015-2022 ozone increase in Guangzhou.

One-class modelling applied to ATR-FTIR spectroscopy for determining document forgeries related to paper aging.

One of the great challenges of document analysis is determining document forgeries. The present work proposes a non-destructive approach to discriminate natural and artificially aged papers using infrared spectroscopy and soft independent modeling by class analogy (SIMCA) algorithms. This is of particular interest in cases of document falsifications made by artificial aging, for this study, SIMCA, and Data-Driven SIMCA (DD-SIMCA) classification models were built using naturally aged paper samples, taken from three time periods: 1st period from 1998 to 2003; 2nd period from 2004 to 2009; and 3rd period from 2010 to 2015. Artificially aged samples (exposed to high temperature or UV radiation) were used as test sets. Promising results in detecting document falsifications related to aging were obtained. Samples artificially aged at high temperature were correctly discriminated from the authentic samples (naturally aged) with 100% accuracy. In contrast, the samples under the photodegradation process showed a lower classification performance, with results above 90%.

Performance of the DASF compared to other combinations of OECD NAMs for eye hazard identification of surfactants.

Currently, the OECD has adopted three defined approaches (DAs) for eye hazard identification of non-surfactant liquids and solids (TG467) according to the three UN GHS categories (Cat.1, Cat.2, No Cat.). We are now expanding the applicability domain with a new DA for chemicals having surfactant (SF) properties (DASF). It is based on a combination of RhCE test methods (OECD TG492: EpiOcular™ EIT or SkinEthic™ HCE EIT) and a modification of the Short Time Exposure (STE, TG491) method. The aim of the current study was to compare the performance of the DASF with the performance of other NAMs currently included in the OECD TGs and with the classification based on the Draize eye test to identify potential additional DAs. The minimum performance criteria (75% Cat.1, 50% Cat.2, 70% No Cat.) used for the adoption of the DAs currently included in OECD TG467 were used for this purpose. The DASF identified 90.9% of Cat. 1 (N=23), 77.8% of Cat. 2 (N=9) and 76.0% of No Cat. (N=17) surfactants, meeting the minimum performance criteria. Some of the NAMs that are currently included in the OECD TGs seem promising methods to be part of a DA to identify Cat. 1 or No Cat. for eye hazard assessment of surfactants. However, the number of surfactants that have been tested to evaluate reliability and relevance was often too small. To date, the DASF is the only DA that has evaluated a sufficiently large number of surfactants and whose performance met the OECD acceptance criteria.

Three non-animal-based defined approaches (DAs) for eye hazard assessment of non-surfactant liquid and solid chemicals were adopted as full replacements as OECD Test Guideline (TG 467). We now extend the applicability domain to surfactants with a new DA (DASF), which combines OECD-adopted test systems based on human 3D eye models and rabbit 2D corneal cells. The DASF has been shown to provide reliable results in predicting the eye irritation potential of 50 surfactants. The aim of the current study was to compare the performance of the DASF with the performance of other OECD TG new approach methodologies and compare it with the classification based on historical animal test data. Based on this analysis no additional DAs could be derived. Until today, the DASF is the best predicting, human-relevant DA that covers the whole range of eye irritation responses across the different surfactant classes.

Corrigendum: Childhood cerebral visual impairment subtype classification based on an extensive versus a limited test battery.

[This corrects the article DOI: 10.3389/fnins.2023.1266201.].

Exploring Affective Representations in Emotional Narratives: An Exploratory Study Comparing ChatGPT and Human Responses.

While artificial Intelligence (AI) has made significant advancements, the seeming absence of its emotional ability has hindered effective communication with humans. This study explores how ChatGPT (ChatGPT-3.5 Mar 23, 2023 Version) represents affective responses to emotional narratives and compare these responses to human responses. Thirty-four participants read affect-eliciting short stories and rated their emotional responses and 10 recorded ChatGPT sessions generated responses to the stories. Classification analyses revealed the successful identification of affective categories of stories, valence, and arousal within and across sessions for ChatGPT. Classification analyses revealed the successful identification of affective categories of stories, valence, and arousal within and across sessions for ChatGPT. Classification accuracies predicting affective categories of stories, valence, and arousal of humans based on the affective ratings of ChatGPT and vice versa were not significant, indicating differences in the way the affective states were represented., indicating differences in the way the affective states were represented. These findings suggested that ChatGPT can distinguish emotional states and generate affective responses consistently, but there are differences in how the affective states are represented between ChatGPT and humans. Understanding these mechanisms is crucial for improving emotional interactions with AI.

Function-Genes and Disease-Genes Prediction Based on Network Embedding and One-Class Classification.

Using genes which have been experimentally-validated for diseases (functions) can develop machine learning methods to predict new disease/function-genes. However, the prediction of both function-genes and disease-genes faces the same problem: there are only certain positive examples, but no negative examples. To solve this problem, we proposed a function/disease-genes prediction algorithm based on network embedding (Variational Graph Auto-Encoders, VGAE) and one-class classification (Fast Minimum Covariance Determinant, Fast-MCD): VGAEMCD. Firstly, we constructed a protein-protein interaction (PPI) network centered on experimentally-validated genes; then VGAE was used to get the embeddings of nodes (genes) in the network; finally, the embeddings were input into the improved deep learning one-class classifier based on Fast-MCD to predict function/disease-genes. VGAEMCD can predict function-gene and disease-gene in a unified way, and only the experimentally-verified genes are needed to provide (no need for expression profile). VGAEMCD outperforms classical one-class classification algorithms in Recall, Precision, F-measure, Specificity, and Accuracy. Further experiments show that seven metrics of VGAEMCD are higher than those of state-of-art function/disease-genes prediction algorithms. The above results indicate that VGAEMCD can well learn the distribution characteristics of positive examples and accurately identify function/disease-genes.

GT-Net: global transformer network for multiclass brain tumor classification using MR images.

Multiclass classification of brain tumors from magnetic resonance (MR) images is challenging due to high inter-class similarities. To this end, convolution neural networks (CNN) have been widely adopted in recent studies. However, conventional CNN architectures fail to capture the small lesion patterns of brain tumors. To tackle this issue, in this paper, we propose a global transformer network dubbed GT-Net for multiclass brain tumor classification. The GT-Net mainly comprises a global transformer module (GTM), which is introduced on the top of a backbone network. A generalized self-attention block (GSB) is proposed to capture the feature inter-dependencies not only across spatial dimension but also channel dimension, thereby facilitating the extraction of the detailed tumor lesion information while ignoring less important information. Further, multiple GSB heads are used in GTM to leverage global feature dependencies. We evaluate our GT-Net on a benchmark dataset by adopting several backbone networks, and the results demonstrate the effectiveness of GTM. Further, comparison with state-of-the-art methods validates the superiority of our model.

Review on spiking neural network-based ECG classification methods for low-power environments.

This paper reviews arrhythmia classification studies using electrocardiogram (ECG) signals. Research on automatically diagnosing arrhythmia in daily life has been actively underway for early detection and treatment of heart disease. Development of automatic arrhythmia classification using ECG signal began based on handcrafted morphological feature extraction and machine learning-based classification methods. As deep neural networks (DNN) show excellent performance in the signal processing field, studies using various types of DNN are also being conducted in ECG classification. However, these DNN-based studies have extremely high computational complexity, making it challenging to perform real-time classification, and are unsuitable for low-power environments such as wearable devices due to high power consumption. Currently, research based on spiking neural network (SNN), which mimics the low-power operation of the human nervous system, is attracting attention as a method that can dramatically reduce complexity and power consumption. The classification accuracy of the SNN-based ECG classification studies is close to that of the DNN-based studies. When combined with neuromorphic hardware, it shows ultra-low-power performance, suggesting the possibility of use in lightweight devices. In this paper, the SNN-based ECG classification studies for low-power environments are mainly reviewed, and prior to this, conventional and DNN-based ECG classification studies are also reviewed. We hope that this review will be helpful to researchers and engineers interested in the field of ECG classification.

Automated echocardiography view classification and quality assessment with recognition of unknown views.

Purpose: Interpreting echocardiographic exams requires substantial manual interaction as videos lack scan-plane information and have inconsistent image quality, ranging from clinically relevant to unrecognizable. Thus, a manual prerequisite step for analysis is to select the appropriate views that showcase both the target anatomy and optimal image quality. To automate this selection process, we present a method for automatic classification of routine views, recognition of unknown views, and quality assessment of detected views. Approach: We train a neural network for view classification and employ the logit activations from the neural network for unknown view recognition. Subsequently, we train a linear regression algorithm that uses feature embeddings from the neural network to predict view quality scores. We evaluate the method on a clinical test set of 2466 echocardiography videos with expert-annotated view labels and a subset of 438 videos with expert-rated view quality scores. A second observer annotated a subset of 894 videos, including all quality-rated videos. Results: The proposed method achieved an accuracy of 84.9 % ± 0.67 for the joint objective of routine view classification and unknown view recognition, whereas a second observer reached an accuracy of 87.6%. For view quality assessment, the method achieved a Spearman's rank correlation coefficient of 0.71, whereas a second observer reached a correlation coefficient of 0.62. Conclusion: The proposed method approaches expert-level performance, enabling fully automatic selection of the most appropriate views for manual or automatic downstream analysis.

GBERT: A hybrid deep learning model based on GPT-BERT for fake news detection.

The digital era has expanded social exposure with easy internet access for mobile users, allowing for global communication. Now, people can get to know what is going on around the globe with just a click; however, this has also resulted in the issue of fake news. Fake news is content that pretends to be true but is actually false and is disseminated to defraud. Fake news poses a threat to harmony, politics, the economy, and public opinion. As a result, bogus news detection has become an emerging research domain to identify a given piece of text as genuine or fraudulent. In this paper, a new framework called Generative Bidirectional Encoder Representations from Transformers (GBERT) is proposed that leverages a combination of Generative pre-trained transformer (GPT) and Bidirectional Encoder Representations from Transformers (BERT) and addresses the fake news classification problem. This framework combines the best features of both cutting-edge techniques-BERT's deep contextual understanding and the generative capabilities of GPT-to create a comprehensive representation of a given text. Both GPT and BERT are fine-tuned on two real-world benchmark corpora and have attained 95.30 % accuracy, 95.13 % precision, 97.35 % sensitivity, and a 96.23 % F1 score. The statistical test results indicate the effectiveness of the fine-tuned framework for fake news detection and suggest that it can be a promising approach for eradicating this global issue of fake news in the digital landscape.

Effect of thoracic manipulation on neck pain in the mobility group: A randomized controlled trial.

Background and aims: Thoracic spine manipulation (TSM) increases the thoracic spine's range of motion (ROM), effectively reducing pain intensity and disability in patients with mechanical neck pain. We aimed to determine the effect of TSM on neck pain intensity and functional impairment in patients classified under the "mobility" category in Childs' classification. Methods: In this randomized controlled trial, patients with mechanical neck pain who met the inclusion criteria were randomly assigned to either the TSM (n = 21) or sham manipulation (n = 20) group. The primary outcomes were pain during neck rotation and subjective improvement assessed using the Numerical Pain Rating Scale (NPRS) and Global Rating of Change (GROC), respectively. The secondary outcomes were NPRS at rest, disability (assessed using the Neck Disability Index [NDI]), and ROM of the cervical and thoracic spine rotation. Outcome measurements were performed at baseline, immediately after treatment, 1 week after treatment, and at the 4-week follow-up. Linear mixed models were used to analyze the NPRS, NDI, and ROM. The GROC was analyzed using a chi-square test for the percentage recording ≥+4; the means of each group were compared using an unpaired t-test. Results: The NPRS with neck rotation, neck and thoracic ROM, and NDI showed significant interactions between the groups. The NPRS with neck rotation was significantly lower in the TSM group than in the sham group at all time points after the treatment (p < 0.001). There was no difference between the groups in the proportion showing moderate (≥+4) improvement according to the GROC; however, there was a significant difference in the mean values (p = 0.013). Conclusion: Incorporating TSM into treatment protocols may improve clinical outcomes in patients with neck pain, potentially leading to better pain management and functional recovery. Therefore, physiotherapists should consider TSM as a viable and effective intervention to improve patient outcomes in neck pain rehabilitation.

Novel WFS1 variants are associated with different diabetes phenotypes.

Background: The WFS1 gene encodes the protein wolframin, which is crucial for maintaining endoplasmic reticulum homeostasis. Variants in this gene are predominantly associated with Wolfram syndrome and have been implicated in other disorders such as diabetes mellitus and psychiatric diseases, which increases the rate of clinical misdiagnosis. Methods: Patients were diagnosed with early-onset unclassified diabetes according to their clinical and laboratory data. We performed whole-exome sequencing (WES) in 165 patients, interpreting variants according to the American College of Medical Genetics/Association for Molecular Pathology (ACMG/AMP) 2015 guidelines. Variant verification was done by Sanger sequencing. In vitro experiments were conducted to evaluate the effects of WFS1 compound heterozygous variants. Results: We identified WFS1 compound heterozygous variants (p.A214fs*74/p.F329I and p.I427S/p.I304T) in two patients with Wolfram Syndrome-Like disorders (WSLD). Both WFS1 compound heterozygous variants were associated with increased ER stress, reduced cell viability, and decreased SERCA2b mRNA levels. Additionally, pathogenic or likely pathogenic WFS1 heterozygous variants were identified in the other three patients. Conclusion: Our results underscore the importance of early genetic testing for diagnosing young-onset diabetes and highlight the clinical relevance of WFS1 variants in increasing ER stress and reducing cell viability. Incorporating these genetic insights into clinical practice can reduce misdiagnoses and improve treatment strategies for related disorders.

Enhancing Outcomes in Prosthetic Joint Infections: The Significance of the Periprosthetic Joint Infection Tumor, Node, and Metastasis (PJI-TNM) Classification and Biodegradable Antibiotic Beads.

BACKGROUND AND OBJECTIVES: Periprosthetic joint infections (PJIs) that occur after hip and knee arthroplasty have a major influence on patient outcomes and healthcare expenses. This study assesses the effectiveness of the PJI tumor, node, and metastasis (PJI-TNM) categorization system and the latest developments in local antibiotic delivery methods for the treatment of PJIs. MATERIALS AND METHODS: The study involved a retrospective analysis of 23 patients who received treatment for septic hip or knee prostheses at the SUUB Orthopedics and Traumatology Clinic between January 1, 2022, and February 10, 2024. Approval was gained following ethical considerations. Patients were categorized using the PJI-TNM system, and their therapy was customized based on the severity of the infection. The surgical procedures involved either one-stage or two-stage revisions, utilizing vancomycin and gentamicin antibiotic-loaded calcium sulfate beads to administer antibiotics locally. Data pertaining to demographics, clinical characteristics, and microbiology were gathered and examined. RESULTS: The study comprised 14 male and 9 female patients, with an average age of 68 years. The presence of chronic infections was mostly seen, indicating the development of mature biofilm. Prevalent coexisting medical conditions included diabetes, obesity, and heart failure. The duration of infection control measures was, on average, six months, and 65% of patients reported experiencing enhanced mobility. Acute infections with positive antibiotic responses underwent one-stage modifications. For the majority of patients, a treatment approach involving two-stage modifications, which includes the use of antibiotic-loaded spacers followed by the installation of a prosthesis, proved to be beneficial. CONCLUSIONS: The PJI-TNM classification system improves the management of PJI by offering a systematic method for customized therapy. Calcium sulfate beads, which are biodegradable carriers for antibiotics, provide notable advantages, especially for individuals with severe comorbidities. Continuous progress in diagnostic techniques and localized administration of antibiotics is essential for enhancing the therapy of PJI and improving patient outcomes.

Painless Nodular Cheek Skin Swelling: A Clinical Challenge.

Basaloid neoplasms of the head and neck region pose a specific challenge both for clinicians and pathologists. It is a diverse group of neoplasms that include benign as well as malignant entities. These neoplasms can arise from various head and neck subsites such as skin, salivary gland, and sinonasal tract. Cytological diagnosis of these tumors is extremely difficult due to morphological overlap with other biphasic tumors and within the basaloid group itself. Here, we are presenting a case of basaloid neoplasm which turned out to be a basal cell adenocarcinoma of the left parotid gland on postoperative histopathological examination.

Compost incorporation and wildflowers introduction for stormwater infiltration and erosion-control vegetation cover establishment in post-construction landscapes.

Urban and suburban development frequently disturbs and compacts soils, reducing infiltration rates and fertility, posing challenges for post-development vegetation establishment, and contributing to soil erosion. This study investigated the effectiveness of compost incorporation in enhancing stormwater infiltration and vegetation establishment in urban landscapes. Experimental treatments comprised a split-split plot design of vegetation mix (grass, wildflowers, and grass-wildflowers) as main plot, ground cover (hydro-mulch and excelsior) as subplot, and compost (30% Compost and No-Compost) as sub-subplot factors. Wildflower inclusion was motivated by their recognized ecological benefits, including aesthetics, pollinator habitat, and deep root systems. Vegetation cover was assessed using RGB (Red-Green-Blue) imagery and ArcGIS-based supervised image classification. Over a 24-month period, bulk density, infiltration rate, soil penetration resistance, vegetation cover, and root mass density were assessed. Results highlighted that Compost treatments consistently reduced bulk density by 19-24%, lowered soil penetration resistance to under 2 MPa at both field-capacity and water-stressed conditions, and increased infiltration rate by 2-3 times compared to No-Compost treatments. Vegetation cover assessment revealed rapid establishment with 30% compost and 60:40 grass-wildflower mix, persisting for an initial 12 months. Subsequently, all treatments exhibited similar vegetation coverage from 13 to 24 months, reaching 95-100% cover. Compost treatments had significantly higher root mass density within the top 15 cm than No-Compost, but compost addition did not alter the root profile beyond the 15 cm depth incorporation depth. The findings suggest that incorporating 30% compost and including a wildflower or grass-wildflower mix appears to be effective in enhancing stormwater infiltration and provides rapid erosion control vegetation cover establishment in post-construction landscapes.

Understanding the implications of hand impairments in light of the International Classification of Function model.

BACKGROUND: Incorporating an occupation-based assessment along with or in place of an assessment of body functions and structures is not performed routinely in hand therapy practice. PURPOSE: (a) Explore correlations between body functions, activities and participation (A&P), and quality of life (QOL); (b) assess the extent to which personal factors and body functions contribute to variations in A&P and QOL; (c) compare the QOL of individuals with and without hand impairment (HI). STUDY DESIGN: Cross-sectional. METHODS: Seventy-seven patients (Mean age=43.70 SD=17.56; 47 males and 30 females) with chronic and acute hand impairment were recruited from two hand clinics and matched with healthy participants. Assessments were administered to participants in their first visit to the hand clinic. QOL was measured with the World Health Organization QOL questionnaire; A&P with the Disabilities of the Arm Shoulder and Hand (DASH) questionnaire; pain with the Patient-Rated Wrist/Hand Evaluation; hand function with The Functional Dexterity Test, Jamar Dynamometer and Pinch Gauge. RESULTS: Significant correlations were found between QOL and A&P, dexterity, and pain, as well as between A&P and hand strength and pain. Personal factors, hand function, and pain collectively explained 28.9% of QOL variance and 61.4% of A&P variance. Pain emerged as the sole significant contributor to QOL variance, while both hand function and pain significantly influenced A&P variance. Comparisons between the study group and controls highlighted significant differences in QOL domains, with the HI group reporting lower perceived QOL in physical, social, and environmental domains. CONCLUSION: The significance of adopting a comprehensive approach in HI intervention was highlighted. A complex interplay of factors across different levels of the International Classification of Functioning, Disability and Health (ICF) framework imply that clinicians should avoid fixating exclusively on isolated factors or specific domains.

Machine learning based stellar classification with highly sparse photometry data.

Background: Identifying stars belonging to different classes is vital in order to build up statistical samples of different phases and pathways of stellar evolution. In the era of surveys covering billions of stars, an automated method of identifying these classes becomes necessary. Methods: Many classes of stars are identified based on their emitted spectra. In this paper, we use a combination of the multi-class multi-label Machine Learning (ML) method XGBoost and the PySSED spectral-energy-distribution fitting algorithm to classify stars into nine different classes, based on their photometric data. The classifier is trained on subsets of the SIMBAD database. Particular challenges are the very high sparsity (large fraction of missing values) of the underlying data as well as the high class imbalance. We discuss the different variables available, such as photometric measurements on the one hand, and indirect predictors such as Galactic position on the other hand. Results: We show the difference in performance when excluding certain variables, and discuss in which contexts which of the variables should be used. Finally, we show that increasing the number of samples of a particular type of star significantly increases the performance of the model for that particular type, while having little to no impact on other types. The accuracy of the main classifier is ∼0.7 with a macro F1 score of 0.61. Conclusions: While the current accuracy of the classifier is not high enough to be reliably used in stellar classification, this work is an initial proof of feasibility for using ML to classify stars based on photometry.

Astronomy is at the forefront of the 'Big Data' regime, with telescopes collecting increasingly large volumes of data. The tools astronomers use to analyse and draw conclusions from these data need to be able to keep up, with machine learning providing many of the solutions. Being able to classify different astronomical objects by type helps to disentangle the astrophysics making them unique, offering new insights into how the Universe works. Here, we present how machine learning can be used to classify different kinds of stars, in order to augment large databases of the sky. This will allow astronomers to more easily extract the data they need to perform their scientific analyses.

Reconstruction residual network with a fused spatial-channel attention mechanism for automatically classifying diabetic foot ulcer.

Diabetic foot ulcer (DFU) is a common chronic complication of diabetes. This complication is characterized by the formation of ulcers that are difficult to heal on the skin of the foot. Ulcers can negatively affect patients' quality of life, and improperly treated lesions can result in amputation and even death. Traditionally, the severity and type of foot ulcers are determined by doctors through visual observations and on the basis of their clinical experience; however, this subjective evaluation can lead to misjudgments. In addition, quantitative methods have been developed for classifying and scoring are therefore time-consuming and labor-intensive. In this paper, we propose a reconstruction residual network with a fused spatial-channel attention mechanism (FARRNet) for automatically classifying DFUs. The use of pseudo-labeling and Data augmentation as a pre-processing technique can overcome problems caused by data imbalance and small sample size. The developed model's attention was enhanced using a spatial channel attention (SPCA) module that incorporates spatial and channel attention mechanisms. A reconstruction mechanism was incorporated into the developed residual network to improve its feature extraction ability for achieving better classification. The performance of the proposed model was compared with that of state-of-the-art models and those in the DFUC Grand Challenge. When applied to the DFUC Grand Challenge, the proposed method outperforms other state-of-the-art schemes in terms of accuracy, as evaluated using 5-fold cross-validation and the following metrics: macro-average F1-score, AUC, Recall, and Precision. FARRNet achieved the F1-score of 60.81%, AUC of 87.37%, Recall of 61.04%, and Precision of 61.56%. Therefore, the proposed model is more suitable for use in medical diagnosis environments with embedded devices and limited computing resources. The proposed model can assist patients in initial identifications of ulcer wounds, thereby helping them to obtain timely treatment.

Comparison of disease and risk classifications of AML before and after incorporation of NGS analysis of bone marrow samples.

Mutation profiling by next-generation sequencing (NGS) has facilitated understanding of the molecular pathogenesis of acute myeloid leukemia (AML), and has been incorporated into the new disease classification (International Consensus Classification; ICC) and risk classification (European LeukemiaNet [ELN] 2022; ELN2022). We compared disease subtypes between the previous disease classification (4th edition of the WHO classification; WHO-4) and the ICC in 91 patients with AML diagnosed at our institution. We also compared disease risk classifications using the previous risk classification (ELN2017) and the ELN2022. Targeted sequencing of bone marrow samples was conducted at Kyoto University. We found that entities under AML with recurrent genetic abnormalities were well-established, with almost no change from the WHO-4 to the ICC. In contrast, 16.7% of cases of AML, not otherwise specified in the WHO-4 were reclassified into AML with mutated TP53, and 36.7% were reclassified into AML with myelodysplasia-related gene mutations or cytogenetic abnormalities per the ICC. Meanwhile, the ELN2017 and ELN2022 showed no difference in concordance indexes in multivariate Cox regression analysis for progression-free and overall survival. The superiority of the ELN2022 over the ELN2017 could not be confirmed in our single-center retrospective study, and further investigation including multicenter prospective studies is needed.