Multi-label Classification System Research Articles

A multi-class fundus disease classification system based on an adaptive scale discriminator and hybrid loss

Fundus images are crucial in the observation and detection of ophthalmic diseases. However, detecting multiple ophthalmic diseases from fundus images using deep learning techniques is a complex and challenging task One challenge is the complexity of fundus disease structures, which leads to low detection accuracy. Another challenge is the class imbalance problem common in multi-label image classification, which increases the difficulty of algorithm training and evaluation. To address these issues, this study leverages deep learning to propose an ophthalmic disease classification system. We first employ ResNet50 as the backbone network to extract image features, and then use our designed multi-dimensional attention module and adaptive scale discriminator to enhance the network's ability to detect disease features. During training, we innovatively propose a hybrid loss function method to improve the detection capability on imbalanced data. Finally, we conducted experiments on the ODRI-5K dataset with the proposed classification system. In the test set, our method achieved an AUC of 98.53 and an F1-score of 89.73. This result fully demonstrates the excellent disease classification capability of our method. In summary, the multi-label fundus image disease classification system we proposed exhibits outstanding recognition capability, providing an effective solution for the diagnosis of multi-label fundus image diseases.

Gender Tapestry: gender classification as color assignation

AbstractGender Tapestry is a multi-stage interactive AI art project, challenging traditional gender classification systems. This project diverges from binary approaches by recognizing the individuality of the gender experience and expression. This paper draws parallels to the ways color perception differs amongst people and how gender is also experienced in different ways due to lived experiences. Gender Tapestry uses a multi-label classification system, with predictions extending across six gender categories, with a custom RGB color generated based on the outcomes. Participants receive binary images of their face in their personalized colors and styles, while their uploaded photos contribute to a live Generative Adversarial Network training process. This work was created in response to the very binary representations of gender in AI and the lack of representation for genders outside of the binary. The culmination is an evolving mosaic artwork, incorporating all users' custom colors, illustrating gender as a fluid construct. The mosaic gains in complexity as more images are added and more colors enter the mix, creating a community artwork on gender as a 3D color spectrum. This work contributes to the discourse on diversity and inclusion in AI, emphasizing the fluidity of gender and fostering unconventional artistic representations.

RNA-RBP interactions recognition using multi-label learning and feature attention allocation

In this study, we present a sophisticated multi-label deep learning framework for the prediction of RNA-RBP (RNA-binding protein) interactions, a critical aspect in understanding RNA functionality modulation and its implications in disease pathogenesis. Our approach leverages machine learning to develop a rapid and cost-efficient predictive model for these interactions. The proposed model captures the complex characteristics of RNA and recognizes corresponding RBPs through its dual-module architecture. The first module employs convolutional neural networks (CNNs) for intricate feature extraction from RNA sequences, enabling the model to discern nuanced patterns and attributes. The second module is a multi-view multi-label classification system incorporating a feature attention mechanism. The second module is a multi-view multi-label classification system that utilizes a feature attention mechanism. This mechanism is designed to intricately analyze and distinguish between common and unique deep features derived from the diverse RNA characteristics. To evaluate the model's efficacy, extensive experiments were conducted on a comprehensive RNA-RBP interaction dataset. The results emphasize substantial improvements in the model's ability to predict RNA-RBP interactions compared to existing methodologies. This advancement emphasizes the model's potential in contributing to the understanding of RNA-mediated biological processes and disease etiology.

An uncertainty-aware self-training framework with consistency regularization for the multilabel classification of common computed tomography signs in lung nodules.

Computed tomography (CT) signs of lung nodules play an important role in indicating lung nodules' malignancy, and accurate automatic classification of these signs can help doctors improve their diagnostic efficiency. However, few relevant studies targeting multilabel classification (MLC) of nodule signs have been conducted. Moreover, difficulty in obtaining labeled data also restricts this avenue of research to a large extent. To address these problems, a multilabel automatic classification system for nodule signs is proposed, which consists of a 3-dimensional (3D) convolutional neural network (CNN) and an efficient new semi-supervised learning (SSL) framework. Two datasets were used in our experiments: Lung Nodule Analysis 16 (LUNA16), a public dataset for lung nodule classification, and a private dataset of nodule signs. The private dataset contains 641 nodules, 454 of which were annotated with 6 important signs by radiologists. Our classification system consists of 2 main parts: a 3D CNN model and an SSL method called uncertainty-aware self-training framework with consistency regularization (USC). In the system, supervised training is performed with labeled data, and simultaneously, an uncertainty-and-confidence-based strategy is used to select pseudo-labeled samples for unsupervised training, thus jointly realizing the optimization of the model. For the MLC of nodule signs, our proposed 3D CNN achieved satisfactory results with a mean average precision (mAP) of 0.870 and a mean area under the curve (AUC) of 0.782. In semi-supervised experiments, compared with supervised learning, our proposed SSL method could increase the mAP by 7.6% (from 0.730 to 0.806) and the mean AUC by 8.1% (from 0.631 to 0.712); it thus efficiently utilized the unlabeled data and achieved superior performance improvement compared to the recently advanced methods. We realized the optimal MLC of lung nodule signs with our proposed 3D CNN. Our proposed SSL method can also offer an efficient solution for the insufficiency of labeled data that may exist in the MLC tasks of 3D medical images.

From Scores to Predictions in Multi-Label Classification: Neural Thresholding Strategies

In this paper, we propose a novel approach for obtaining predictions from per-class scores to improve the accuracy of multi-label classification systems. In a multi-label classification task, the expected output is a set of predicted labels per each testing sample. Typically, these predictions are calculated by implicit or explicit thresholding of per-class real-valued scores: classes with scores exceeding a given threshold value are added to a prediction set. In our work, we propose a neural network-based thresholding phase for multi-label classification systems and examine its influence on the overall classification performance measured by micro- and macro-averaged F1 scores on synthetic and real datasets. In contrast to classic thresholding methods, our approach has the unique property of being able to recover from scoring errors, because each decision about a given label prediction depends on the corresponding class score, as well as on all the other class scores for a given sample at once. The method can be used in combination with any classification system that outputs real-valued class scores. The proposed thresholding methods are trained offline, after the completion of the scoring phase. As such, it can be considered a universal fine-tuning step that can be employed in any multi-label classification system that seeks to find the best multi-label predictions based on class scores. In our experiments on real datasets, the input class scores were obtained from two third-party baseline classification systems. We show that our approach outperforms the traditional thresholding methods, which results in the improved performance of all tested multi-label classification tasks. In terms of relative improvement, on real datasets, the micro-F1 score is higher by up to 40.6%, the macro-F1 score is higher by up to 3.6%, and the averaged micro–macro-F1 score is higher by up to 30.1%, considering single models only. We show that ensembles and hybrid models give even better results. We show examples of successful extreme recoveries, where the system, equipped with our method, was able to correctly predict labels, which were highly underscored after the scoring phase.

Multi-label Retinal Disease Classification Using Transformers.

Early detection of retinal diseases is one of the most important means of preventing partial or permanent blindness in patients. In this research, a novel multi-label classification system is proposed for the detection of multiple retinal diseases, using fundus images collected from a variety of sources. First, a new multi-label retinal disease dataset, the MuReD dataset, is constructed, using a number of publicly available datasets for fundus disease classification. Next, a sequence of post-processing steps is applied to ensure the quality of the image data and the range of diseases, present in the dataset. For the first time in fundus multi-label disease classification, a transformer-based model optimized through extensive experimentation is used for image analysis and decision making. Numerous experiments are performed to optimize the configuration of the proposed system. It is shown that the approach performs better than state-of-the-art works on the same task by 7.9% and 8.1% in terms of AUC score for disease detection and disease classification, respectively. The obtained results further support the potential applications of transformer-based architectures in the medical imaging field.

A multi-label classification system for anomaly classification in electrocardiogram.

Automatic classification of ECG signals has become a research hotspot, and most of the research work in this field is currently aimed at single-label classification. However, a segment of ECG signal may contain more than two cardiac diseases, and single-label classification cannot accurately judge all possibilities. Besides, single-label classification performs classification in units of segmented beats, which destroys the contextual relevance of signal data. Therefore, studying the multi-label classification of ECG signals becomes more critical. This study proposes a method based on the multi-label question transformation method-binary correlation and classifies ECG signals by constructing a deep sequence model. Binary correlation simplifies the learning difficulty of deep learning models and converts multi-label problems into multiple binary classification problems. The experimental results are as follows: F1 score is 0.767, Hamming Loss is 0.073, Coverage is 3.4, and Ranking Loss is 0.262. It performs better than existing work.

VacPred: Sequence-based prediction of plant vacuole proteins using machine-learning techniques

Subcellular localization prediction of the proteome is one of major goals of large-scale genome or proteome sequencing projects to define the gene functions that could be possible with the help of computational modeling techniques. Previously, different methods have been developed for this purpose using multi-label classification system and achieved a high level of accuracy. However, during the validation of our blind dataset of plant vacuole proteins, we observed that they have poor performance with accuracy value range from ~1.3% to 48.5%. The results showed that the previously developed methods are not very accurate for the plant vacuole protein prediction and thus emphasize the need to develop a more accurate and reliable algorithm. In this study, we have developed various compositions as well as PSSM-based models and achieved a high accuracy than previously developed methods. We have shown that our best model achieved ~63% accuracy on blind dataset, which is far better than currently available tools. Furthermore, we have implemented our best models in the form of GUI-based free software called 'VacPred' which is compatible with both Linux and Window platform. This software is freely available for download at www.deepaklab.com/vacpred.

A Multi-label Classification System to Distinguish among Fake, Satirical, Objective and Legitimate News in Brazilian Portuguese

Currently, there has been a significant increase in the diffusion of fake news worldwide, especially the political class, where the possible misinformation that can be propagated, appearing at the elections debates around the world. However, news with a recreational purpose, such as satirical news, is often confused with objective fake news. In this work, we decided to address the differences between objectivity and legitimacy of news documents, where each article is treated as belonging to two conceptual classes: objective/satirical and legitimate/fake. Therefore, we propose a DSS (Decision Support System) based on a Text Mining (TM) pipeline with a set of novel textual features using multi-label methods for classifying news articles on these two domains. For this, a set of multi-label methods was evaluated with a combination of different base classifiers and then compared with a multi-class approach. Also, a set of real-life news data was collected from several Brazilian news portals for these experiments. Results obtained reported our DSS as adequate (0.80 f1-score) when addressing the scenario of misleading news, challenging the multi-label perspective, where the multi-class methods (0.01 f1-score) overcome by the proposed method. Moreover, it was analyzed how each stylometric features group used in the experiments influences the result aiming to discover if a particular group is more relevant than others. As a result, it was noted that the complexity group of features could be more relevant than others.

Developing a FHIR-based EHR phenotyping framework: A case study for identification of patients with obesity and multiple comorbidities from discharge summaries.

Standards-based clinical data normalization has become a key component of effective data integration and accurate phenotyping for secondary use of electronic healthcare records (EHR) data. HL7 Fast Healthcare Interoperability Resources (FHIR) is an emerging clinical data standard for exchanging electronic healthcare data and has been used in modeling and integrating both structured and unstructured EHR data for a variety of clinical research applications. The overall objective of this study is to develop and evaluate a FHIR-based EHR phenotyping framework for identification of patients with obesity and its multiple comorbidities from semi-structured discharge summaries leveraging a FHIR-based clinical data normalization pipeline (known as NLP2FHIR). We implemented a multi-class and multi-label classification system based on the i2b2 Obesity Challenge task to evaluate the FHIR-based EHR phenotyping framework. Two core parts of the framework are: (a) the conversion of discharge summaries into corresponding FHIR resources - Composition, Condition, MedicationStatement, Procedure and FamilyMemberHistory using the NLP2FHIR pipeline, and (b) the implementation of four machine learning algorithms (logistic regression, support vector machine, decision tree, and random forest) to train classifiers to predict disease state of obesity and 15 comorbidities using features extracted from standard FHIR resources and terminology expansions. We used the macro- and micro-averaged precision (P), recall (R), and F1 score (F1) measures to evaluate the classifier performance. We validated the framework using a second obesity dataset extracted from the MIMIC-III database. Using the NLP2FHIR pipeline, 1237 clinical discharge summaries from the 2008 i2b2 obesity challenge dataset were represented as the instances of the FHIR Composition resource consisting of 5677 records with 16 unique section types. After the NLP processing and FHIR modeling, a set of 244,438 FHIR clinical resource instances were generated. As the results of the four machine learning classifiers, the random forest algorithm performed the best with F1-micro(0.9466)/F1-macro(0.7887) and F1-micro(0.9536)/F1-macro(0.6524) for intuitive classification (reflecting medical professionals' judgments) and textual classification (reflecting the judgments based on explicitly reported information of diseases), respectively. The MIMIC-III obesity dataset was successfully integrated for prediction with minimal configuration of the NLP2FHIR pipeline and machine learning models. The study demonstrated that the FHIR-based EHR phenotyping approach could effectively identify the state of obesity and multiple comorbidities using semi-structured discharge summaries. Our FHIR-based phenotyping approach is a first concrete step towards improving the data aspect of phenotyping portability across EHR systems and enhancing interpretability of the machine learning-based phenotyping algorithms.

Time Conserving Multi-Label Classification System by Incorporating Pyramid Data Structure

Data classification is one of the evergreen research areas of data analysis. Numerous data classification approaches exist in the literature and most of the classification systems are based on binary and multi-class classification. Multi-label classification system attempts to suggest multiple labels for a single entity. However, it is complex to attain a better multi-label classification system. Taking this as a challenge, this work proposes a multi-label classification system, which extracts the features of both entities and labels. The relationship between them are organised in the pyramid data structure. As the features are organized effectively, the interrelated labels are present in the same tier. This feature makes it simple for suggesting multiple labels for a single entity. The performance of this work is analysed over three different datasets and compared against existing approaches in terms of precision, recall, accuracy and time consumption.

Hierarchical classification of diatom images using ensembles of predictive clustering trees

This paper presents a hierarchical multi-label classification (HMC) system for diatom image classification. HMC is a variant of classification where an instance may belong to multiple classes at the same time and these classes/labels are organized in a hierarchy. Our approach to HMC exploits the classification hierarchy by building a single predictive clustering tree (PCT) that can simultaneously predict all different levels in the hierarchy of taxonomic ranks: genus, species, variety, and form. Hence, PCTs are very efficient: a single classifier is valid for the hierarchical classification scheme as a whole. To improve the predictive performance of the PCTs, we construct ensembles of PCTs. We evaluate our system on the ADIAC database of diatom images. We apply several feature extraction techniques that can be used in the context of diatom images. Moreover, we investigate whether the combination of these techniques increases predictive performance. The results show that ensembles of PCTs have better predictive performance and are more efficient than SVMs. Furthermore, the proposed system outperforms the most widely used approaches for image annotation. Finally, we demonstrate how the system can be used by taxonomists to annotate new diatom images.

Hierarchical annotation of medical images

We present a hierarchical multi-label classification (HMC) system for medical image annotation. HMC is a variant of classification where an instance may belong to multiple classes at the same time and these classes/labels are organized in a hierarchy. Our approach to HMC exploits the annotation hierarchy by building a single predictive clustering tree (PCT) that can simultaneously predict all annotations of an image. Hence, PCTs are very efficient: a single classifier is valid for the hierarchical semantics as a whole, as compared to other approaches that produce many classifiers, each valid just for one given class. To improve performance, we construct ensembles of PCTs. We evaluate our system on the IRMA database that consists of X-ray images. We investigate its performance under a variety of conditions. To begin with, we consider two ensemble approaches, bagging and random forests. Next, we use several state-of-the-art feature extraction approaches and combinations thereof. Finally, we employ two types of feature fusion, i.e., low and high level fusion. The experiments show that our system outperforms the best-performing approach from the literature (a collection of SVMs, each predicting one label at the lowest level of the hierarchy), both in terms of error and efficiency. This holds across a range of descriptors and descriptor combinations, regardless of the type of feature fusion used. To stress the generality of the proposed approach, we have also applied it for automatic annotation of a large number of consumer photos with multiple annotations organized in semantic hierarchy. The obtained results show that this approach is general and easily applicable in different domains, offering state-of-the-art performance.