XD-LDL: Improving Generalization in Acne Severity Classification via Cross-Dataset Label Distribution Learning

Label Distribution Learning (LDL), as a more general learning setting than generic single-label and multi-label learning, has been commonly used in computer vision and many other applications. To date, existing LDL approaches are designed and applied to data without considering the interdependence between instances. In this paper, we propose a Graph Label Distribution Learning (GLDL) framework, which explicitly models three types of relationships: instance-instance, label-label, and instance-label, to learn the label distribution for networked data. A label-label network is learned to capture label-to-label correlation, through which GLDL can accurately learn label distributions for nodes. Dual graph convolution network (GCN) Co-training with heterogeneous message passing ensures two GCNs, one focusing on instance-instance relationship and the other one targeting label-label correlation, are jointly trained such that instance-instance relationship can help induce label-label correlation and vice versa. Our theoretical study derives the error bound of GLDL. For verification, four benchmark datasets with label distributions for nodes are created using common graph benchmarks. The experiments show that considering dependency helps learn better label distributions for networked data, compared to state-of-the-art LDL baseline. In addition, GLDL not only outperforms simple GCN and graph attention networks (GAT) using distribution loss but is also superior to its variant considering label-label relationship as a static network. GLDL and its benchmarks are the first research endeavors to address LDL for graphs. Code and benchmark data are released for public access.

- The Plant Disease Detection and Classification project is designed to help farmers identify crop diseases at an early stage using images of plant leaves. By applying advanced machine learning (ML) and deep learning (DL) techniques, this system aims to automatically detect and classify various plant diseases with high accuracy. Early identification of plant diseases plays a vital role in improving crop yield, reducing unnecessary pesticide usage, and encouraging sustainable farming practices. Once a disease is detected, the system not only identifies it but also provides a brief description and recommends appropriate prevention and treatment methods. To enhance performance, the project uses data augmentation and normalization techniques—helping the model handle variations in lighting, angles, and environmental conditions. The system is trained on a diverse dataset containing images of both healthy and diseased leaves from different plant species, categorized into 38 different classes. The project incorporates various machine learning algorithms such as Support Vector Machines (SVM), K-Nearest Neighbors (KNN), Decision Trees, and Random Forests, as well as a Convolutional Neural Network (CNN) for deep learning. Among these, CNNs have shown outstanding performance due to their ability to learn spatial features from images effectively. While existing research has shown promising results, real-world challenges such as varying image quality, lighting conditions, and background clutter still affect accuracy. This project aims to overcome these issues by training on large, diverse datasets and fine-tuning model parameters. Ultimately, this project hopes to empower farmers with an intelligent tool to monitor crop health, make informed decisions, and contribute to food security through precision agriculture. Keywords: Plant Disease Detection, Automated Disease Detection System, Machine Learning, Deep Learning, Data Augmentation, Data Normalization, Support Vector Machine, KNN Classifier, Convolutional Neural Network, Decision Trees, Random Forest

Label distribution learning (LDL) is a novel multi-label learning paradigm proposed in recent years for solving label ambiguity. Existing approaches typically exploit label correlations globally to improve the effectiveness of label distribution learning, by assuming that the label correlations are shared by all instances. However, different instances may share different label correlations, and few correlations are globally applicable in real-world applications. In this paper, we propose a new label distribution learning algorithm by exploiting sample correlations locally (LDL-SCL). To encode the influence of local samples, we design a local correlation vector for each instance based on the clustered local samples. Then we predict the label distribution for an unseen instance based on the original features and the local correlation vector simultaneously. Experimental results demonstrate that LDL-SCL can effectively deal with the label distribution problems and perform remarkably better than the state-of-the-art LDL methods.

Stream label distribution learning processing via broad learning system

The use of self-care methods, such as over-the-counter (OTC) products and complementary and alternative medicine (CAM), is common along the acne care pathway. This study aimed to explore self-care methods for acne and assess their associations with acne severity. This cross-sectional study was conducted among university students in health programs. Convenience sampling was used to invite participants to complete a survey containing sociodemographic, clinical, and self-care-related questions. Acne diagnosis and severity were evaluated by a physician via the Global Acne Grading System (GAGS). A multivariate regression model was used to analyze the associations between variables. The final sample comprised 190 participants, with 24.2% males and 70.8% females. Most participants had mild acne (77.4%) and reported positive family histories (82.1%). Approximately one-third used OTC products (31.1%), and nearly two-thirds used CAM (62.6%). The most frequently used OTC products were facial cleansers (48.2%), followed by creams and moisturizers (30.7%) and cleansing soap (21.1%). A lack of acne severity was the primary reason for the use of CAM. Social media (46.7%) and the internet (46.2%) were the most frequently reported sources of information. Acne severity was associated with OTC product use (p=0.009) and the duration of acne (p<0.001). Furthermore, OTC product use was associated with receiving a professional diagnosis (p<0.001). This study identified the most common OTC products and CAM used in acne and demonstrated an association between OTC product use and acne severity. Future studies should explore discussions on self-care methods in clinical consultations and the timing of using these methods throughout the care pathway. Integrating shared decision-making in clinical practice and tailoring educational interventions to patient preferences and communication channels may encourage the safe and effective use of self-care methods.

Digital breast tomosynthesis (DBT) is becoming an important part of breast cancer screening and diagnosis. Compared to two-dimensional mammography, tomosynthesis introduces limited three-dimensional (3D) resolution, but maintains high in-plane resolution, low dose, and allows for similar clinical protocols. The scanning motion and oblique projections of tomosynthesis acquisitions introduce shift-variance to the image quality, in addition to effects such as source blurring and geometric magnification. Shift-variant detector response caused by oblique incidence has been extensively studied previously and is most easily mitigated by letting the source and detector move in sync. In addition, conical reconstruction grids, that is, a grid aligned with the central tomosynthesis projection, have been proposed to compensate for magnification effects. This paper introduces a shift-variant cascaded systems model for tomosynthesis and validates it against measurements. As an example, the model was used to investigate the shift-variance of a tomosynthesis system. The shift-variant cascaded systems model was validated on a slit-scanning photon-counting DBT system, with synchronous source-detector movement, using simple back-projection in a conical reconstruction volume. The modulation transfer function (MTF), normalized noise-power spectrum (NNPS), and detective quantum efficiency (DQE) were used as figures of merit. Simulations were performed for single points while measurements were done over a finite volume, assuming local shift invariance. To investigate the full extent of shift-variance, 80 locations across the volume were simulated, and the MTF and DQE at 2.5lp/mm were calculated as a function of position. The simulated metrics generally agreed well with their corresponding measurements. The frequency at 50% MTF along the scan direction showed a relatively small variation, ranging from 2.1 to 2.4lp/mm for the different locations. The frequency at 50% MTF along the chest-mammilla direction showed a larger variation, ranging from 2.9 to 3.8lp/mm. All points exhibited a similarly shaped NNPS but the noise magnitude varied with slice height. The zero-frequency DQE in reconstructed slices was lower than that of the projections, an effect likely caused by noise-aliasing increasing the zero-frequency noise. A shift-variant cascaded systems model has been developed for slit-scanning tomosynthesis using simple back-projection. The model was successfully validated against measurements. Even though the study was performed on a slit-scanning system, several parts of the framework can be applied and extended to other tomosynthesis geometries. The conical reconstruction grid has low variation in image quality in the scan direction where the 3D information is acquired, but source and geometric magnification still dominate in the slit direction, causing a larger variation in image quality. We conclude that image quality is close to shift-invariant in the scan direction, but not in the height and chest-mammilla directions, and we recommend that small measurement volumes are used when measuring image quality in these directions to minimize the effects of shift variance.

Background: Acne is a common chronic inflammatory disease of the skin. Vitamin-D is fat soluble vitamin with immunomodulatory function, its deficiency has been noticed in various skin diseases. Objectives: assess frequency of serum vitamin-D deficiency among acne vulgaris patients and the effect of vitamin-D supplementation on acne grading. Method: the study was conducted on two phases, phase I was a cross-sectional study included measuring serum vitamin D level for 80 acne patients attending dermatology clinic at Menoufia University Hospital. Phase II was case control study where studied acne patients with vitamin-D deficiency (66 patients) were randomly divided into two groups; one group (33 patients) were treated with free Oral vitamin-D 2000IU/ tablet for 2 months in addition to regular acne treatment. The other group (33 patients) received traditional treatment for acne without vitamin-D supplementation and both groups were followed up clinically for two months. Results: frequency of vitamin-D deficiency among studied patients was 82.5%, there was statistically significant relationship between vitamin-D deficiency and severity of acne. Vitamin-D deficiency is significantly prevalent among female patients (98.4%). There was significant improvement in acne grading after vitamin-D supplementation Conclusion and recommendation: There’s significant relation between vitamin-D deficiency and severity of acne vulgaris and vitamin -D has a good role in management of acne. So. It is recommended to evaluate the serum level of vitamin D in acne patients and provide vitamin D supplementation to vitamin D deficient patients beside topical treatments for acne.

The objective of this study was to determine the prevalence of facial acne and its impact on the quality of life among adolescents attending secondary schools in Muar, Malaysia. A cross-sectional study was conducted where 409 samples were selected using stratified cluster random sampling from two secondary schools in Muar, involving Form 1 to Form 5 students. Students were diagnosed clinically and the severity of facial acne was assessed using Global Acne Grading System. A self-reported Cardiff Acne Disability Index was used to assess the quality of life among adolescents who had acne. The prevalence of facial acne among the adolescents was 67.5% (n = 276). Facial acne increased with increasing age (p = 0.001). It was more common among males (71.1%) than females (64.6%), p = 0.165. The males also had a higher prevalence of severe acne (p = 0.001). The quality of life was affected by the severity of acne. Students with severe acne had higher levels of Cardiff Acne Disability Index (rho = 0.521). Facial acne is a common disorder and appears to have a considerable impact on quality of life among adolescents. The above findings should alert health care professionals and the school authorities to actively identify, manage and educate adolescents with facial acne.

Joint segmentation and registration of images is a focused area of research nowadays. Jointly segmenting and registering noisy images and images having weak boundaries/intensity inhomogeneity is a challenging task. In medical image processing, joint segmentation and registration are essential methods that aid in distinguishing structures and aligning images for precise diagnosis and therapy. However, these methods encounter challenges, such as computational complexity and sensitivity to variations in image quality, which may reduce their effectiveness in real-world applications. Another major issue is still attaining effective joint segmentation and registration in the presence of artifacts or anatomical deformations. In this paper, a new nonparametric joint model is proposed for the segmentation and registration of multi-modality images having weak boundaries/noise. For segmentation purposes, the model will be utilizing local binary fitting data term and for registration, it is utilizing conditional mutual information. For regularization of the model, we are using linear curvature. The new proposed model is more efficient to segmenting and registering multi-modality images having intensity inhomogeneity, noise and/or weak boundaries. The proposed model is also tested on the images obtained from the freely available CHOAS dataset and compare the results of the proposed model with the other existing models using statistical measures such as the Jaccard similarity index, relative reduction, Dice similarity coefficient and Hausdorff distance. It can be seen that the proposed model outperforms the other existing models in terms of quantitatively and qualitatively.

Clinical assessment of motor symptoms in Parkinson’s disease (PD) relies on rater-dependent scoring, which is subjective and may lead to substantial inter-rater variability. Conventional machine learning typically uses single-label targets and thus fails to capture the distributional nature of clinical ratings or the inherent ambiguity and continuity of disease progression. To address this issue, we propose PD-LDL, a multi-task label distribution learning (LDL) framework that jointly predicts MDS-UPDRS Part III scores and Hoehn & Yahr (H&Y) stages. PD-LDL employs a TabNet backbone for tabular feature selection and representation learning, and assigns Gaussian label distributions to model uncertainty in scoring and staging. However, directly learning large label distributions can increase output dimensionality and hamper optimization if label dependencies are ignored. To mitigate this, we introduce an adaptive label graph module inspired by UMAP, which constructs a fuzzy label affinity graph on the label distribution manifold and uses a graph-consistency loss to regularize model outputs according to learned structural correlations among labels. Experiments on the PPMI database demonstrate that PD-LDL consistently outperforms strong classical, deep tabular, and LDL baselines on both score prediction and staging tasks. The proposed framework not only improves predictive performance, but also more faithfully captures the continuity and ambiguity of PD-related labels, providing a interpretable tool for joint motor symptom scoring and staging in clinical practice.

The original JPEG compression standard is efficient at low to medium levels of compression with relatively low levels of loss in visual image quality and has found widespread use in the imaging industry. Excessive compression using JPEG however, results in well-known artifacts such as blocking and ringing, and the variation in image quality as a result of differing scene content is well documented. JPEG 2000 has been developed to improve on JPEG in terms of functionality and image quality at lower bit rates. One of the more fundamental changes is the use of a discrete wavelet transform instead of a discrete cosine transform, which provides several advantages both in terms of the way in which the image is encoded and overall image quality. This study involves a comparison of subjective image quality between JPEG and JPEG 2000 to establish whether JPEG 2000 does indeed demonstrate significant improvements in visual quality. A particular focus of this work is the inherent scene dependency of the two algorithms and their influence on subjective image quality results. Further work on the characterization of scene content is carried out in a connected study [S. Triantaphillidou, E. Allen, and R. E. Jacobson, Image quality comparison between JPEG and JPEG2000. II. Scene dependency, scene analysis, and classification

The reported prevalence of acne in adolescence is variable; improved treatment may have modified its prevalence and severity; acne has been related to psychiatric morbidity for many years. Two thousand six hundred and fifty-seven high school students were examined, and adolescents with acne were interviewed about the subject of acne vulgaris. The severity of acne was graded using the Global Acne Grading System (GAGS). The Hospital Anxiety and Depression (HAD) scale was evaluated for one of every two subjects with acne (n = 308) and for the same number of sex-matched control subjects (n = 308) to determine the prevalence of depression and anxiety. Six hundred and fifteen of the subjects (23. 1%) were determined to have acne. Acne prevalence in girls and boys was 16.1% and 29.2%, respectively (P < 0.001). Two hundred and twenty-five (15.8%) of 1424 boys and only 109 (8.8%) of 1233 girls had moderate or severe/very severe acne (P < 0.001), but the GAGS scores in the groups of boys and girls with acne were not significantly different. The acne and control groups showed no significant differences in the HAD anxiety and depression subscale scores. The HAD anxiety subscale scores of girls were significantly higher than those of boys in the acne group. The severity of acne was not correlated with the HAD anxiety or depression subscale scores. Acne results in higher anxiety in adolescent girls. Although acne and moderate/severe acne are more common in adolescent boys, the severity of acne was found to be similar in boys and girls with acne. Adolescent girls are more vulnerable than boys to the negative psychological effects of acne.

PurposeOur purpose was to perform an in vivo validation of ultrasound imaging for intrafraction motion estimation using the Elekta Clarity Autoscan system during prostate radiation therapy. The study was conducted as part of the Clarity-Pro trial (NCT02388308).Methods and MaterialsInitial locations of intraprostatic fiducial markers were identified from cone beam computed tomography scans. Marker positions were translated according to Clarity intrafraction 3-dimensional prostate motion estimates. The updated locations were projected onto the 2-dimensional electronic portal imager plane. These Clarity-based estimates were compared with the actual portal-imaged 2-dimensional marker positions. Images from 16 patients encompassing 80 fractions were analyzed. To investigate the influence of intraprostatic markers and image quality on ultrasound motion estimation, 3 observers rated image quality, and the marker visibility on ultrasound images was assessed.ResultsThe median difference between Clarity-defined intrafraction marker locations and portal-imaged marker locations was 0.6 mm (with 95% limit of agreement at 2.5 mm). Markers were identified on ultrasound in only 3 of a possible 240 instances. No linear relationship between image quality and Clarity motion estimation confidence was identified. The difference between Clarity-based motion estimates and electronic portal–imaged marker location was also independent of image quality. Clarity estimation confidence was degraded in a single fraction owing to poor probe placement.ConclusionsThe accuracy of Clarity intrafraction prostate motion estimation is comparable with that of other motion-monitoring systems in radiation therapy. The effect of fiducial markers in the study was deemed negligible as they were rarely visible on ultrasound images compared with intrinsic anatomic features. Clarity motion estimation confidence was robust to variations in image quality and the number of ultrasound-imaged anatomic features; however, it was degraded as a result of poor probe placement.

Label distribution learning (LDL) is the state-of-the-art approach to dealing with a number of real-world applications, such as chronological age estimation from a face image, where there is an inherent similarity among adjacent age labels. LDL takes into account the semantic similarity by assigning a label distribution to each instance. The well-known Kullback-Leibler (KL) divergence is the widely used loss function for the LDL framework. However, the KL divergence does not fully and effectively capture the semantic similarity among age labels, thus leading to suboptimal performance. In this article, we propose a novel loss function based on the optimal transport theory for the LDL-based age estimation. A ground metric function plays an important role in the optimal transport formulation. It should be carefully determined based on the underlying geometric structure of the label space of the application in-hand. The label space in the age estimation problem has a specific geometric structure, that is, closer ages have more inherent semantic relationships. Inspired by this, we devise a novel ground metric function, which enables the loss function to increase the influence of highly correlated ages; thus exploiting the semantic similarity among ages more effectively than the existing loss functions. We then use the proposed loss function, namely, γ -Wasserstein loss, for training a deep neural network (DNN). This leads to a notoriously computationally expensive and nonconvex optimization problem. Following the standard methodology, we formulate the optimization function as a convex problem and then use an efficient iterative algorithm to update the parameters of the DNN. Extensive experiments in age estimation on different benchmark datasets validate the effectiveness of the proposed method, which consistently outperforms state-of-the-art approaches.

Poor sleep quality is extremely prevalent, with about one third of adults in the USA obtaining less than the recommended amount of sleep. In addition, poor sleep quality has been linked to an increased risk of many conditions, including diabetes, hypertension, psychiatric conditions, and overall all-cause mortality. Research has shown that sleep disturbance does impact skin disease, although many details of this relationship are still unclear. The goal of this study is to determine if there is a relationship between acne severity and sleep quality in adults. Forty subjects with acne were recruited from dermatology clinics in Cleveland, OH, to participate in this study. Acne severity was assessed using the Global Acne Grading Scale (GAGS). To assess sleep quality, subjects completed the Pittsburgh Sleep Quality Index (PSQI) and completed a seven-day sleep journal. Subjects also completed the Dermatology Life Quality Index (DLQI), the Patient Health Questionnaire-2 (PHQ-2), and provided information about current and past acne treatments as well as their opinion regarding their own acne severity and exacerbating factors. Our findings support the hypothesis that there is a potential relationship between sleep quality and acne.