Small Data Challenges in Big Data Era: A Survey of Recent Progress on Unsupervised and Semi-Supervised Methods

Semi-supervised non-negative matrix factorization with structure preserving for image clustering

Semi-supervised learning methods have wide applications thanks to the reasonable utilization for a part of label information of data. In recent years, non-negative matrix factorization (NMF) has received considerable attention because of its interpretability and practicality. Based on the advantages of semi-supervised learning and NMF, many semi-supervised NMF methods have been presented. However, these existing semi-supervised NMF methods construct a label matrix only containing elements 1 and 0 to represent the labeled data and further construct a label regularization, which neglects an intrinsic structure of NMF. To address the deficiency, in this paper, we propose a novel semi-supervised NMF method with structure preserving. Specifically, we first construct a new label matrix with weights and further construct a label constraint regularizer to both utilize the label information and maintain the intrinsic structure of NMF. Then, based on the label constraint regularizer, the basis images of labeled data are extracted for monitoring and modifying the basis images learning of all data by establishing a basis regularizer. Finally, incorporating the label constraint regularizer and the basis regularizer into NMF, we propose a new semi-supervised NMF method. To solve the optimization problem, a multiplicative updating algorithm is developed. The proposed method is applied to image clustering to test its performance. Experimental results on eight data sets demonstrate the effectiveness of the proposed method in contrast with state-of-the-art unsupervised and semi-supervised algorithms.

Benefit from public unlabeled data: A Frangi filter-based pretraining network for 3D cerebrovascular segmentation

Precise cerebrovascular segmentation in Time-of-Flight Magnetic Resonance Angiography (TOF-MRA) data is crucial for computer-aided clinical diagnosis. The sparse distribution of cerebrovascular structures within TOF-MRA images often results in high costs for manual data labeling. Leveraging unlabeled TOF-MRA data can significantly enhance model performance. In this study, we have constructed the largest preprocessed unlabeled TOF-MRA dataset to date, comprising 1510 subjects. Additionally, we provide manually annotated segmentation masks for 113 subjects based on existing external image datasets to facilitate evaluation. We propose a simple yet effective pretraining strategy utilizing the Frangi filter, known for its capability to enhance vessel-like structures, to optimize the use of the unlabeled data for 3D cerebrovascular segmentation. This involves a Frangi filter-based preprocessing workflow tailored for large-scale unlabeled datasets and a multi-task pretraining strategy to efficiently utilize the preprocessed data. This approach ensures maximal extraction of useful knowledge from the unlabeled data. The efficacy of the pretrained model is assessed across four cerebrovascular segmentation datasets, where it demonstrates superior performance, improving the clDice metric by approximately 2%-3% compared to the latest semi- and self-supervised methods. Additionally, ablation studies validate the generalizability and effectiveness of our pretraining method across various backbone structures. The code and data have been open source at: https://github.com/shigen-StoneRoot/FFPN.

Enhancing Brain Age Prediction and Neurodegeneration Detection with Contrastive Learning on Regional Biomechanical Properties

The aging process affects brain structure and function, yet its biomechanical properties remain underexplored. Magnetic Resonance Elastography (MRE) provides a unique perspective by mapping brain tissue stiffness and damping ratio, observables that correlate with age and disease. Using a self-supervised contrastive regression framework, we demonstrate that MRE surpasses conventional structural magnetic resonance imaging (MRI) in sensitivity. Specifically, stiffness captures Alzheimer's disease (AD), while damping ratio detects subtle changes associated with mild cognitive impairment (MCI). Our regional analysis identifies deep brain structures, particularly the caudate and thalamus, as key biomarkers of aging. The greater age sensitivity of MRE translates to superior differentiation of AD and MCI from healthy individuals, pinpointing regions where significant biomechanical alterations occur, notably the thalamus in AD and hippocampus in MCI. Furthermore, our results reveal biomechanical alterations in cognitively healthy individuals whose aging profiles closely resemble patients with MCI and AD. These findings highlight MRE's potential as a biomarker for early neurodegenerative changes, aiding dementia risk detection and early intervention.

Hierarchical Graph Attention Network with Positive and Negative Attentions for Improved Interpretability: ISA-PN

With the advancement of deep learning (DL) methods in chemistry and materials science, the interpretability of DL models has become a critical issue in elucidating quantitative (molecular) structure-property relationships. Although attention mechanisms have been generally employed to explain the importance of molecular substructures that contribute to molecular properties, their interpretability remains limited. In this work, we introduce a versatile segmentation method and develop an interpretable subgraph attention (ISA) network with positive and negative streams (ISA-PN) to enhance the understanding of molecular structure-property relationships. The predictive performance of the ISA models was validated using data sets for aqueous solubility, lipophilicity, and melting temperature, with a particular focus on evaluating interpretability for the aqueous solubility data set. The ISA-PN model enables the quantification of the contributions of molecular substructures through positive and negative attention scores. Comparative analyses of the ISA, ISA-PN, and GC-Net (group contribution network) models demonstrate that the ISA-PN model significantly improves interpretability while maintaining similar accuracy levels. This study highlights the efficacy of the ISA-PN model in providing meaningful insights into the contributions of molecular substructures to molecular properties, thereby enhancing the interpretability of DL models in chemical applications.

Clinical validation and optimization of machine learning models for early prediction of sepsis

Introduction

Sepsis is a global health threat that has a high incidence and mortality rate. Early prediction of sepsis onset can drive effective interventions and improve patients' outcome.

Methods

Data were collected retrospectively from a cohort of 2,329 adult patients with positive bacteria cultures from a tertiary hospital in China between October 1, 2019 and September 30, 2020. Thirty six clinical features were selected as inputs for the models. We trained models in predicting sepsis by machine learning (ML) methods, including logistic regression, decision tree, random forest (RF), multi-layer perceptron, and light gradient boosting. We evaluated the performance of the five ML models and the evaluation metrics were: area under the ROC curve (AUC), accuracy, F1-score, sensitivity and specificity. The data of another cohort of 2,286 patients between October 1, 2020 and April 1, 2022 were used to validate the performance of the model performing best in the in the internal validation set. Shapley additive explanations (SHAP) method was applied to evaluate feature importance and explain the predictions of this model.

Results

Of the five machine learning models developed, the RF model demonstrated the best performance in terms of AUC (0.818), F1 value (0.38), and sensitivity (0.746). The RF model also has a comparable AUC (0.771) in the external validation set. The SHAP method identified procalcitonin, albumin, prothrombin time, and sex as the important variables contributing to the prediction of sepsis.

Discussion

The RF model we developed showed the greatest potential for early prediction of sepsis in admitted patients, which could aid clinicians in their decision-making process. Our findings also suggested that male patients with bacterial infections and high procalcitonin levels, lower albumin levels, or prolonged prothrombin times were more likely to develop sepsis.

Semisupervised Contrastive Learning for Bioactivity Prediction Using Cell Painting Image Data

Morphological profiling has recently demonstrated remarkable potential for identifying the biological activities of small molecules. Alongside the fully supervised and self-supervised machine learning methods recently proposed for bioactivity prediction from Cell Painting image data, we introduce here a semisupervised contrastive (SemiSupCon) learning approach. This approach combines the strengths of using biological annotations in supervised contrastive learning and leveraging large unannotated image data sets with self-supervised contrastive learning. SemiSupCon enhances downstream prediction performance of classifying MeSH pharmacological classifications from PubChem, as well as mode of action and biological target annotations from the Drug Repurposing Hub across two publicly available Cell Painting data sets. Notably, our approach has effectively predicted the biological activities of several unannotated compounds, and these findings were validated through literature searches. This demonstrates that our approach can potentially expedite the exploration of biological activity based on Cell Painting image data with minimal human intervention.

Dual-branch Transformer for semi-supervised medical image segmentation

PURPOSE

In recent years, the use of deep learning for medical image segmentation has become a popular trend, but its development also faces some challenges. Firstly, due to the specialized nature of medical data, precise annotation is time-consuming and labor-intensive. Training neural networks effectively with limited labeled data is a significant challenge in medical image analysis. Secondly, convolutional neural networks commonly used for medical image segmentation research often focus on local features in images. However, the recognition of complex anatomical structures or irregular lesions often requires the assistance of both local and global information, which has led to a bottleneck in its development. Addressing these two issues, in this paper, we propose a novel network architecture.

METHODS

We integrate a shift window mechanism to learn more comprehensive semantic information and employ a semi-supervised learning strategy by incorporating a flexible amount of unlabeled data. Specifically, a typical U-shaped encoder-decoder structure is applied to obtain rich feature maps. Each encoder is designed as a dual-branch structure, containing Swin modules equipped with windows of different size to capture features of multiple scales. To effectively utilize unlabeled data, a level set function is introduced to establish consistency between the function regression and pixel classification.

RESULTS

We conducted experiments on the COVID-19 CT dataset and DRIVE dataset and compared our approach with various semi-supervised and fully supervised learning models. On the COVID-19 CT dataset, we achieved a segmentation accuracy of up to 74.56%. Our segmentation accuracy on the DRIVE dataset was 79.79%.

CONCLUSIONS

The results demonstrate the outstanding performance of our method on several commonly used evaluation metrics. The high segmentation accuracy of our model demonstrates that utilizing Swin modules with different window sizes can enhance the feature extraction capability of the model, and the level set function can enable semi-supervised models to more effectively utilize unlabeled data. This provides meaningful insights for the application of deep learning in medical image segmentation. Our code will be released once the manuscript is accepted for publication.

Can Machine Learning Overcome the 95% Failure Rate and Reality that Only 30% of Approved Cancer Drugs Meaningfully Extend Patient Survival?

Despite implementing hundreds of strategies, cancer drug development suffers from a 95% failure rate over 30 years, with only 30% of approved cancer drugs extending patient survival beyond 2.5 months. Adding more criteria without eliminating nonessential ones is impractical and may fall into the "survivorship bias" trap. Machine learning (ML) models may enhance efficiency by saving time and cost. Yet, they may not improve success rate without identifying the root causes of failure. We propose a "STAR-guided ML system" (structure-tissue/cell selectivity-activity relationship) to enhance success rate and efficiency by addressing three overlooked interdependent factors: potency/specificity to the on/off-targets determining efficacy in tumors at clinical doses, on/off-target-driven tissue/cell selectivity influencing adverse effects in the normal organs at clinical doses, and optimal clinical doses balancing efficacy/safety as determined by potency/specificity and tissue/cell selectivity. STAR-guided ML models can directly predict clinical dose/efficacy/safety from five features to design/select the best drugs, enhancing success and efficiency of cancer drug development.

Semi-supervised recognition for artificial intelligence assisted pathology image diagnosis

The analysis and interpretation of cytopathological images are crucial in modern medical diagnostics. However, manually locating and identifying relevant cells from the vast amount of image data can be a daunting task. This challenge is particularly pronounced in developing countries where there may be a shortage of medical expertise to handle such tasks. The challenge of acquiring large amounts of high-quality labelled data remains, many researchers have begun to use semi-supervised learning methods to learn from unlabeled data. Although current semi-supervised learning models partially solve the issue of limited labelled data, they are inefficient in exploiting unlabeled samples. To address this, we introduce a new AI-assisted semi-supervised scheme, the Reliable-Unlabeled Semi-Supervised Segmentation (RU3S) model. This model integrates the ResUNet-SE-ASPP-Attention (RSAA) model, which includes the Squeeze-and-Excitation (SE) network, Atrous Spatial Pyramid Pooling (ASPP) structure, Attention module, and ResUNet architecture. Our model leverages unlabeled data effectively, improving accuracy significantly. A novel confidence filtering strategy is introduced to make better use of unlabeled samples, addressing the scarcity of labelled data. Experimental results show a 2.0% improvement in mIoU accuracy over the current state-of-the-art semi-supervised segmentation model ST, demonstrating our approach's effectiveness in solving this medical problem.

Small data methods in omics: the power of one

Over the last decade, biology has begun utilizing 'big data' approaches, resulting in large, comprehensive atlases in modalities ranging from transcriptomics to neural connectomics. However, these approaches must be complemented and integrated with 'small data' approaches to efficiently utilize data from individual labs. Integration of smaller datasets with major reference atlases is critical to provide context to individual experiments, and approaches toward integration of large and small data have been a major focus in many fields in recent years. Here we discuss progress in integration of small data with consortium-sized atlases across multiple modalities, and its potential applications. We then examine promising future directions for utilizing the power of small data to maximize the information garnered from small-scale experiments. We envision that, in the near future, international consortia comprising many laboratories will work together to collaboratively build reference atlases and foundation models using small data methods.

A machine learning-based approach for predicting renal function recovery in general ward patients with acute kidney injury

BACKGROUND

Acute kidney injury (AKI) is a significant challenge in healthcare. While there are considerable researches dedicated to AKI patients, a crucial factor in their renal function recovery, is often overlooked. Thus, our study aims to address this issue through the development of a machine learning model to predict restoration of kidney function in patients with AKI.

METHODS

Our study encompassed data from 350,345 cases, derived from three hospitals. AKI was classified in accordance with the Kidney Disease: Improving Global Outcomes. Criteria for recovery were established as either a 33% decrease in serum creatinine levels at AKI onset, which was initially employed for the diagnosis of AKI. We employed various machine learning models, selecting 43 pertinent features for analysis.

RESULTS

Our analysis contained 7,041 and 2,929 patients' data from internal cohort and external cohort respectively. The Categorical Boosting Model demonstrated significant predictive accuracy, as evidenced by an internal area under the receiver operating characteristic (AUROC) of 0.7860, and an external AUROC score of 0.7316, thereby confirming its robustness in predictive performance. SHapley Additive exPlanations (SHAP) values were employed to explain key factors impacting recovery of renal function in AKI patients.

CONCLUSION

This study presented a machine learning approach for predicting renal function recovery in patients with AKI. The model performance was assessed across distinct hospital settings, which revealed its efficacy. Although the model exhibited favorable outcomes, the necessity for further enhancements and the incorporation of more diverse datasets is imperative for its application in real- world.

SemiRS-COC: Semi-Supervised Classification for Complex Remote Sensing Scenes With Cross-Object Consistency

Semi-supervised learning (SSL), which aims to learn with limited labeled data and massive amounts of unlabeled data, offers a promising approach to exploit the massive amounts of satellite Earth observation images. The fundamental concept underlying most state-of-the-art SSL methods involves generating pseudo-labels for unlabeled data based on image-level predictions. However, complex remote sensing (RS) scene images frequently encounter challenges, such as interference from multiple background objects and significant intra-class differences, resulting in unreliable pseudo-labels. In this paper, we propose the SemiRS-COC, a novel semi-supervised classification method for complex RS scenes. Inspired by the idea that neighboring objects in feature space should share consistent semantic labels, SemiRS-COC utilizes the similarity between foreground objects in RS images to generate reliable object-level pseudo-labels, effectively addressing the issues of multiple background objects and significant intra-class differences in complex RS images. Specifically, we first design a Local Self-Learning Object Perception (LSLOP) mechanism, which transforms multiple background objects interference of RS images into usable annotation information, enhancing the model's object perception capability. Furthermore, we present a Cross-Object Consistency Pseudo-Labeling (COCPL) strategy, which generates reliable object-level pseudo-labels by comparing the similarity of foreground objects across different RS images, effectively handling significant intra-class differences. Extensive experiments demonstrate that our proposed method achieves excellent performance compared to state-of-the-art methods on three widely-adopted RS datasets.

Clustering analysis for classifying fake real estate listings

With the rapid growth of online property rental and sale platforms, the prevalence of fake real estate listings has become a significant concern. These deceptive listings waste time and effort for buyers and sellers and pose potential risks. Therefore, developing effective methods to distinguish genuine from fake listings is crucial. Accurately identifying fake real estate listings is a critical challenge, and clustering analysis can significantly improve this process. While clustering has been widely used to detect fraud in various fields, its application in the real estate domain has been somewhat limited, primarily focused on auctions and property appraisals. This study aims to fill this gap by using clustering to classify properties into fake and genuine listings based on datasets curated by industry experts. This study developed a K-means model to group properties into clusters, clearly distinguishing between fake and genuine listings. To assure the quality of the training data, data pre-processing procedures were performed on the raw dataset. Several techniques were used to determine the optimal value for each parameter of the K-means model. The clusters are determined using the Silhouette coefficient, the Calinski-Harabasz index, and the Davies-Bouldin index. It was found that the value of cluster 2 is the best and the Camberra technique is the best method when compared to overlapping similarity and Jaccard for distance. The clustering results are assessed using two machine learning algorithms: Random Forest and Decision Tree. The observational results have shown that the optimized K-means significantly improves the accuracy of the Random Forest classification model, boosting it by an impressive 96%. Furthermore, this research demonstrates that clustering helps create a balanced dataset containing fake and genuine clusters. This balanced dataset holds promise for future investigations, particularly for deep learning models that require balanced data to perform optimally. This study presents a practical and effective way to identify fake real estate listings by harnessing the power of clustering analysis, ultimately contributing to a more trustworthy and secure real estate market.

Automated Diagnosis of Major Depressive Disorder With Multi-Modal MRIs Based on Contrastive Learning: A Few-Shot Study

Depression ranks among the most prevalent mood-related psychiatric disorders. Existing clinical diagnostic approaches relying on scale interviews are susceptible to individual and environmental variations. In contrast, the integration of neuroimaging techniques and computer science has provided compelling evidence for the quantitative assessment of major depressive disorder (MDD). However, one of the major challenges in computer-aided diagnosis of MDD is to automatically and effectively mine the complementary cross-modal information from limited datasets. In this study, we proposed a few-shot learning framework that integrates multi-modal MRI data based on contrastive learning. In the upstream task, it is designed to extract knowledge from heterogeneous data. Subsequently, the downstream task is dedicated to transferring the acquired knowledge to the target dataset, where a hierarchical fusion paradigm is also designed to integrate features across inter- and intra-modalities. Lastly, the proposed model was evaluated on a set of multi-modal clinical data, achieving average scores of 73.52% and 73.09% for accuracy and AUC, respectively. Our findings also reveal that the brain regions within the default mode network and cerebellum play a crucial role in the diagnosis, which provides further direction in exploring reproducible biomarkers for MDD diagnosis.

MolFeSCue: enhancing molecular property prediction in data-limited and imbalanced contexts using few-shot and contrastive learning

MOTIVATION

Predicting molecular properties is a pivotal task in various scientific domains, including drug discovery, material science, and computational chemistry. This problem is often hindered by the lack of annotated data and imbalanced class distributions, which pose significant challenges in developing accurate and robust predictive models.

RESULTS

This study tackles these issues by employing pretrained molecular models within a few-shot learning framework. A novel dynamic contrastive loss function is utilized to further improve model performance in the situation of class imbalance. The proposed MolFeSCue framework not only facilitates rapid generalization from minimal samples, but also employs a contrastive loss function to extract meaningful molecular representations from imbalanced datasets. Extensive evaluations and comparisons of MolFeSCue and state-of-the-art algorithms have been conducted on multiple benchmark datasets, and the experimental data demonstrate our algorithm's effectiveness in molecular representations and its broad applicability across various pretrained models. Our findings underscore MolFeSCues potential to accelerate advancements in drug discovery.

AVAILABILITY AND IMPLEMENTATION

We have made all the source code utilized in this study publicly accessible via GitHub at http://www.healthinformaticslab.org/supp/ or https://github.com/zhangruochi/MolFeSCue. The code (MolFeSCue-v1-00) is also available as the supplementary file of this paper.

RAgE: Robust Age Estimation Through Subject Anchoring With Consistency Regularisation

Modern facial age estimation systems can achieve high accuracy when training and test datasets are identically distributed and captured under similar conditions. However, domain shifts in data, encountered in practice, lead to a sharp drop in accuracy of most existing age estimation algorithms. In this article, we propose a novel method, namely RAgE, to improve the robustness and reduce the uncertainty of age estimates by leveraging unlabelled data through a subject anchoring strategy and a novel consistency regularisation term. First, we propose an similarity-preserving pseudo-labelling algorithm by which the model generates pseudo-labels for a cohort of unlabelled images belonging to the same subject, while taking into account the similarity among age labels. In order to improve the robustness of the system, a consistency regularisation term is then used to simultaneously encourage the model to produce invariant outputs for the images in the cohort with respect to an anchor image. We propose a novel consistency regularisation term the noise-tolerant property of which effectively mitigates the so-called confirmation bias caused by incorrect pseudo-labels. Experiments on multiple benchmark ageing datasets demonstrate substantial improvements over the state-of-the-art methods and robustness to confounding external factors, including subject's head pose, illumination variation and appearance of expression in the face image.

Semi-Supervised and Unsupervised Deep Visual Learning: A Survey

State-of-the-art deep learning models are often trained with a large amount of costly labeled training data. However, requiring exhaustive manual annotations may degrade the model's generalizability in the limited-label regime.Semi-supervised learning and unsupervised learning offer promising paradigms to learn from an abundance of unlabeled visual data. Recent progress in these paradigms has indicated the strong benefits of leveraging unlabeled data to improve model generalization and provide better model initialization. In this survey, we review the recent advanced deep learning algorithms on semi-supervised learning (SSL) and unsupervised learning (UL) for visual recognition from a unified perspective. To offer a holistic understanding of the state-of-the-art in these areas, we propose a unified taxonomy. We categorize existing representative SSL and UL with comprehensive and insightful analysis to highlight their design rationales in different learning scenarios and applications in different computer vision tasks. Lastly, we discuss the emerging trends and open challenges in SSL and UL to shed light on future critical research directions.

Machine learning hypothesis-generation for patient stratification and target discovery in rare disease: our experience with Open Science in ALS

Introduction

Advances in machine learning (ML) methodologies, combined with multidisciplinary collaborations across biological and physical sciences, has the potential to propel drug discovery and development. Open Science fosters this collaboration by releasing datasets and methods into the public space; however, further education and widespread acceptance and adoption of Open Science approaches are necessary to tackle the plethora of known disease states.

Motivation

In addition to providing much needed insights into potential therapeutic protein targets, we also aim to demonstrate that small patient datasets have the potential to provide insights that usually require many samples (>5,000). There are many such datasets available and novel advancements in ML can provide valuable insights from these patient datasets.

Problem statement

Using a public dataset made available by patient advocacy group AnswerALS and a multidisciplinary Open Science approach with a systems biology augmented ML technology, we aim to validate previously reported drug targets in ALS and provide novel insights about ALS subpopulations and potential drug targets using a unique combination of ML methods and graph theory.

Methodology

We use NetraAI to generate hypotheses about specific patient subpopulations, which were then refined and validated through a combination of ML techniques, systems biology methods, and expert input.

Results

We extracted 8 target classes, each comprising of several genes that shed light into ALS pathophysiology and represent new avenues for treatment. These target classes are broadly categorized as inflammation, epigenetic, heat shock, neuromuscular junction, autophagy, apoptosis, axonal transport, and excitotoxicity. These findings are not mutually exclusive, and instead represent a systematic view of ALS pathophysiology. Based on these findings, we suggest that simultaneous targeting of ALS has the potential to mitigate ALS progression, with the plausibility of maintaining and sustaining an improved quality of life (QoL) for ALS patients. Even further, we identified subpopulations based on disease onset.

Conclusion

In the spirit of Open Science, this work aims to bridge the knowledge gap in ALS pathophysiology to aid in diagnostic, prognostic, and therapeutic strategies and pave the way for the development of personalized treatments tailored to the individual's needs.

Self-Supervised Contrastive Representation Learning for Semi-Supervised Time-Series Classification

Learning time-series representations when only unlabeled data or few labeled samples are available can be a challenging task. Recently, contrastive self-supervised learning has shown great improvement in extracting useful representations from unlabeled data via contrasting different augmented views of data. In this work, we propose a novel Time-Series representation learning framework via Temporal and Contextual Contrasting (TS-TCC) that learns representations from unlabeled data with contrastive learning. Specifically, we propose time-series-specific weak and strong augmentations and use their views to learn robust temporal relations in the proposed temporal contrasting module, besides learning discriminative representations by our proposed contextual contrasting module. Additionally, we conduct a systematic study of time-series data augmentation selection, which is a key part of contrastive learning. We also extend TS-TCC to the semi-supervised learning settings and propose a Class-Aware TS-TCC (CA-TCC) that benefits from the available few labeled data to further improve representations learned by TS-TCC. Specifically, we leverage the robust pseudo labels produced by TS-TCC to realize a class-aware contrastive loss. Extensive experiments show that the linear evaluation of the features learned by our proposed framework performs comparably with the fully supervised training. Additionally, our framework shows high efficiency in few labeled data and transfer learning scenarios.

Source Free Semi-Supervised Transfer Learning for Diagnosis of Mental Disorders on fMRI Scans

The high prevalence of mental disorders gradually poses a huge pressure on the public healthcare services. Deep learning-based computer-aided diagnosis (CAD) has emerged to relieve the tension in healthcare institutions by detecting abnormal neuroimaging-derived phenotypes. However, training deep learning models relies on sufficient annotated datasets, which can be costly and laborious. Semi-supervised learning (SSL) and transfer learning (TL) can mitigate this challenge by leveraging unlabeled data within the same institution and advantageous information from source domain, respectively. This work is the first attempt to propose an effective semi-supervised transfer learning (SSTL) framework dubbed S3TL for CAD of mental disorders on fMRI data. Within S3TL, a secure cross-domain feature alignment method is developed to generate target-related source model in SSL. Subsequently, we propose an enhanced dual-stage pseudo-labeling approach to assign pseudo-labels for unlabeled samples in target domain. Finally, an advantageous knowledge transfer method is conducted to improve the generalization capability of the target model. Comprehensive experimental results demonstrate that S3TL achieves competitive accuracies of 69.14%, 69.65%, and 72.62% on ABIDE-I, ABIDE-II, and ADHD-200 datasets, respectively. Furthermore, the simulation experiments also demonstrate the application potential of S3TL through model interpretation analysis and federated learning extension.

Artificial intelligence in diabetes management: Advancements, opportunities, and challenges

The increasing prevalence of diabetes, high avoidable morbidity and mortality due to diabetes and diabetic complications, and related substantial economic burden make diabetes a significant health challenge worldwide. A shortage of diabetes specialists, uneven distribution of medical resources, low adherence to medications, and improper self-management contribute to poor glycemic control in patients with diabetes. Recent advancements in digital health technologies, especially artificial intelligence (AI), provide a significant opportunity to achieve better efficiency in diabetes care, which may diminish the increase in diabetes-related health-care expenditures. Here, we review the recent progress in the application of AI in the management of diabetes and then discuss the opportunities and challenges of AI application in clinical practice. Furthermore, we explore the possibility of combining and expanding upon existing digital health technologies to develop an AI-assisted digital health-care ecosystem that includes the prevention and management of diabetes.

Mu-Net a Light Architecture for Small Dataset Segmentation of Brain Organoid Bright-Field Images

To characterize the growth of brain organoids (BOs), cultures that replicate some early physiological or pathological developments of the human brain are usually manually extracted. Due to their novelty, only small datasets of these images are available, but segmenting the organoid shape automatically with deep learning (DL) tools requires a larger number of images. Light U-Net segmentation architectures, which reduce the training time while increasing the sensitivity under small input datasets, have recently emerged. We further reduce the U-Net architecture and compare the proposed architecture (MU-Net) with U-Net and UNet-Mini on bright-field images of BOs using several data augmentation strategies. In each case, we perform leave-one-out cross-validation on 40 original and 40 synthesized images with an optimized adversarial autoencoder (AAE) or on 40 transformed images. The best results are achieved with U-Net segmentation trained on optimized augmentation. However, our novel method, MU-Net, is more robust: it achieves nearly as accurate segmentation results regardless of the dataset used for training (various AAEs or a transformation augmentation). In this study, we confirm that small datasets of BOs can be segmented with a light U-Net method almost as accurately as with the original method.

Federated Learning in Computational Toxicology: An Industrial Perspective on the Effiris Hackathon

In silico approaches have acquired a towering role in pharmaceutical research and development, allowing laboratories all around the world to design, create, and optimize novel molecular entities with unprecedented efficiency. From a toxicological perspective, computational methods have guided the choices of medicinal chemists toward compounds displaying improved safety profiles. Even if the recent advances in the field are significant, many challenges remain active in the on-target and off-target prediction fields. Machine learning methods have shown their ability to identify molecules with safety concerns. However, they strongly depend on the abundance and diversity of data used for their training. Sharing such information among pharmaceutical companies remains extremely limited due to confidentiality reasons, but in this scenario, a recent concept named "federated learning" can help overcome such concerns. Within this framework, it is possible for companies to contribute to the training of common machine learning algorithms, using, but not sharing, their proprietary data. Very recently, Lhasa Limited organized a hackathon involving several industrial partners in order to assess the performance of their federated learning platform, called "Effiris". In this paper, we share our experience as Roche in participating in such an event, evaluating the performance of the federated algorithms and comparing them with those coming from our in-house-only machine learning models. Our aim is to highlight the advantages of federated learning and its intrinsic limitations and also suggest some points for potential improvements in the method.

Multi-Scale Dynamic Graph Learning for Brain Disorder Detection With Functional MRI

Resting-state functional magnetic resonance imaging (rs-fMRI) has been widely used in the detection of brain disorders such as autism spectrum disorder based on various machine/deep learning techniques. Learning-based methods typically rely on functional connectivity networks (FCNs) derived from blood-oxygen-level-dependent time series of rs-fMRI data to capture interactions between brain regions-of-interest (ROIs). Graph neural networks have been recently used to extract fMRI features from graph-structured FCNs, but cannot effectively characterize spatiotemporal dynamics of FCNs, e.g., the functional connectivity of brain ROIs is dynamically changing in a short period of time. Also, many studies usually focus on single-scale topology of FCN, thereby ignoring the potential complementary topological information of FCN at different spatial resolutions. To this end, in this paper, we propose a multi-scale dynamic graph learning (MDGL) framework to capture multi-scale spatiotemporal dynamic representations of rs-fMRI data for automated brain disorder diagnosis. The MDGL framework consists of three major components: 1) multi-scale dynamic FCN construction using multiple brain atlases to model multi-scale topological information, 2) multi-scale dynamic graph representation learning to capture spatiotemporal information conveyed in fMRI data, and 3) multi-scale feature fusion and classification. Experimental results on two datasets show that MDGL outperforms several state-of-the-art methods.

Fundus Image-Label Pairs Synthesis and Retinopathy Screening via GANs With Class-Imbalanced Semi-Supervised Learning

Retinopathy is the primary cause of irreversible yet preventable blindness. Numerous deep-learning algorithms have been developed for automatic retinal fundus image analysis. However, existing methods are usually data-driven, which rarely consider the costs associated with fundus image collection and annotation, along with the class-imbalanced distribution that arises from the relative scarcity of disease-positive individuals in the population. Semi-supervised learning on class-imbalanced data, despite a realistic problem, has been relatively little studied. To fill the existing research gap, we explore generative adversarial networks (GANs) as a potential answer to that problem. Specifically, we present a novel framework, named CISSL-GANs, for class-imbalanced semi-supervised learning (CISSL) by leveraging a dynamic class-rebalancing (DCR) sampler, which exploits the property that the classifier trained on class-imbalanced data produces high-precision pseudo-labels on minority classes to leverage the bias inherent in pseudo-labels. Also, given the well-known difficulty of training GANs on complex data, we investigate three practical techniques to improve the training dynamics without altering the global equilibrium. Experimental results demonstrate that our CISSL-GANs are capable of simultaneously improving fundus image class-conditional generation and classification performance under a typical label insufficient and imbalanced scenario. Our code is available at: https://github.com/Xyporz/CISSL-GANs.

Semi-Supervised 3D Medical Image Segmentation Based on Dual-Task Consistent Joint Learning and Task-Level Regularization

Semi-supervised learning has attracted wide attention from many researchers since its ability to utilize a few data with labels and relatively more data without labels to learn information. Some existing semi-supervised methods for medical image segmentation enforce the regularization of training by implicitly perturbing data or networks to perform the consistency. Most consistency regularization methods focus on data level or network structure level, and rarely of them focus on the task level. It may not directly lead to an improvement in task accuracy. To overcome the problem, this work proposes a semi-supervised dual-task consistent joint learning framework with task-level regularization for 3D medical image segmentation. Two branches are utilized to simultaneously predict the segmented and signed distance maps, and they can learn useful information from each other by constructing a consistency loss function between the two tasks. The segmentation branch learns rich information from both labeled and unlabeled data to strengthen the constraints on the geometric structure of the target. Experimental results on two benchmark datasets show that the proposed method can achieve better performance compared with other state-of-the-art works. It illustrates our method improves segmentation performance by utilizing unlabeled data and consistent regularization.

Bi-DCNet: Bilateral Network with Dilated Convolutions for Left Ventricle Segmentation

Left ventricular segmentation is a vital and necessary procedure for assessing cardiac systolic and diastolic function, while echocardiography is an indispensable diagnostic technique that enables cardiac functionality assessment. However, manually labeling the left ventricular region on echocardiography images is time consuming and leads to observer bias. Recent research has demonstrated that deep learning has the capability to employ the segmentation process automatically. However, on the downside, it still ignores the contribution of all semantic information through the segmentation process. This study proposes a deep neural network architecture based on BiSeNet, named Bi-DCNet. This model comprises a spatial path and a context path, with the former responsible for spatial feature (low-level) acquisition and the latter responsible for contextual semantic feature (high-level) exploitation. Moreover, it incorporates feature extraction through the integration of dilated convolutions to achieve a larger receptive field to capture multi-scale information. The EchoNet-Dynamic dataset was utilized to assess the proposed model, and this is the first bilateral-structured network implemented on this large clinical video dataset for accomplishing the segmentation of the left ventricle. As demonstrated by the experimental outcomes, our method obtained 0.9228 and 0.8576 in DSC and IoU, respectively, proving the structure's effectiveness.

Automatic Classification of Histopathology Images across Multiple Cancers Based on Heterogeneous Transfer Learning

Background: Current artificial intelligence (AI) in histopathology typically specializes on a single task, resulting in a heavy workload of collecting and labeling a sufficient number of images for each type of cancer. Heterogeneous transfer learning (HTL) is expected to alleviate the data bottlenecks and establish models with performance comparable to supervised learning (SL). Methods: An accurate source domain model was trained using 28,634 colorectal patches. Additionally, 1000 sentinel lymph node patches and 1008 breast patches were used to train two target domain models. The feature distribution difference between sentinel lymph node metastasis or breast cancer and CRC was reduced by heterogeneous domain adaptation, and the maximum mean difference between subdomains was used for knowledge transfer to achieve accurate classification across multiple cancers. Result: HTL on 1000 sentinel lymph node patches (L-HTL-1000) outperforms SL on 1000 sentinel lymph node patches (L-SL-1-1000) (average area under the curve (AUC) and standard deviation of L-HTL-1000 vs. L-SL-1-1000: 0.949 ± 0.004 vs. 0.931 ± 0.008, p value = 0.008). There is no significant difference between L-HTL-1000 and SL on 7104 patches (L-SL-2-7104) (0.949 ± 0.004 vs. 0.948 ± 0.008, p value = 0.742). Similar results are observed for breast cancer. B-HTL-1008 vs. B-SL-1-1008: 0.962 ± 0.017 vs. 0.943 ± 0.018, p value = 0.008; B-HTL-1008 vs. B-SL-2-5232: 0.962 ± 0.017 vs. 0.951 ± 0.023, p value = 0.148. Conclusions: HTL is capable of building accurate AI models for similar cancers using a small amount of data based on a large dataset for a certain type of cancer. HTL holds great promise for accelerating the development of AI in histopathology.

Design of New Dispersants Using Machine Learning and Visual Analytics

Artificial intelligence (AI) is an emerging technology that is revolutionizing the discovery of new materials. One key application of AI is virtual screening of chemical libraries, which enables the accelerated discovery of materials with desired properties. In this study, we developed computational models to predict the dispersancy efficiency of oil and lubricant additives, a critical property in their design that can be estimated through a quantity named blotter spot. We propose a comprehensive approach that combines machine learning techniques with visual analytics strategies in an interactive tool that supports domain experts' decision-making. We evaluated the proposed models quantitatively and illustrated their benefits through a case study. Specifically, we analyzed a series of virtual polyisobutylene succinimide (PIBSI) molecules derived from a known reference substrate. Our best-performing probabilistic model was Bayesian Additive Regression Trees (BART), which achieved a mean absolute error of 5.50±0.34 and a root mean square error of 7.56±0.47, as estimated through 5-fold cross-validation. To facilitate future research, we have made the dataset, including the potential dispersants used for modeling, publicly available. Our approach can help accelerate the discovery of new oil and lubricant additives, and our interactive tool can aid domain experts in making informed decisions based on blotter spot and other key properties.

Masked Contrastive Representation Learning for Reinforcement Learning

In pixel-based reinforcement learning (RL), the states are raw video frames, which are mapped into hidden representation before feeding to a policy network. To improve sample efficiency of state representation learning, recently, the most prominent work is based on contrastive unsupervised representation. Witnessing that consecutive video frames in a game are highly correlated, to further improve data efficiency, we propose a new algorithm, i.e., masked contrastive representation learning for RL (M-CURL), which takes the correlation among consecutive inputs into consideration. In our architecture, besides a CNN encoder for hidden presentation of input state and a policy network for action selection, we introduce an auxiliary Transformer encoder module to leverage the correlations among video frames. During training, we randomly mask the features of several frames, and use the CNN encoder and Transformer to reconstruct them based on context frames. The CNN encoder and Transformer are jointly trained via contrastive learning where the reconstructed features should be similar to the ground-truth ones while dissimilar to others. During policy evaluation, the CNN encoder and the policy network are used to take actions, and the Transformer module is discarded. Our method achieves consistent improvements over CURL on 14 out of 16 environments from DMControl suite and 23 out of 26 environments from Atari 2600 Games. The code is available at https://github.com/teslacool/m-curl.

Robust and accurate performance anomaly detection and prediction for cloud applications: a novel ensemble learning-based framework

Effectively detecting run-time performance anomalies is crucial for clouds to identify abnormal performance behavior and forestall future incidents. To be used for real-world applications, an effective anomaly detection framework should meet three main challenging requirements: high accuracy for identifying anomalies, good robustness when application patterns change, and prediction ability for upcoming anomalies. Unfortunately, existing research about performance anomaly detection usually focuses on improving detection accuracy, while little research tackles the three challenges simultaneously. We conduct experiments for existing detection methods on multiple application monitoring data, and results show that existing detection methods usually focus on different features in data, which will lead to their diverse performance on different data patterns. Therefore, existing anomaly detection methods have difficulty improving detection accuracy and robustness and predicting anomalies. To address the three requirements, we propose an Ensemble Learning-Based Detection (ELBD) framework which integrates existing well-selected detection methods. The framework includes three classic linear ensemble methods (maximum, average, and weighted average) and a novel deep ensemble method. Our experiments show that the ELBD framework realizes better detection accuracy and robustness, where the deep ensemble method can achieve the most accurate and robust detection for cloud applications. In addition, it can predict anomalies in the next four minutes with an F1 score higher than 0.8. The paper also proposes a new indicator $$ARP\_score$$ A R P _ s c o r e to measure detection accuracy, robustness, and multi-step prediction ability. The $$ARP\_score$$ A R P _ s c o r e of the deep ensemble method is 5.1821, which is much higher than other detection methods.

Scarce Data in Intelligent Technical Systems: Causes, Characteristics, and Implications

Technical systems generate an increasing amount of data as integrated sensors become more available. Even so, data are still often scarce because of technical limitations of sensors, an expensive labelling process, or rare concepts, such as machine faults, which are hard to capture. Data scarcity leads to incomplete information about a concept of interest. This contribution details causes and effects of scarce data in technical systems. To this end, a typology is introduced which defines different types of incompleteness. Based on this, machine learning and information fusion methods are presented and discussed that are specifically designed to deal with scarce data. The paper closes with a motivation and a call for further research efforts into a combination of machine learning and information fusion.

K-Shot Contrastive Learning of Visual Features With Multiple Instance Augmentations

In this paper, we propose the K-Shot Contrastive Learning (KSCL) of visual features by applying multiple augmentations to investigate the sample variations within individual instances. It aims to combine the advantages of inter-instance discrimination by learning discriminative features to distinguish between different instances, as well as intra-instance variations by matching queries against the variants of augmented samples over instances. Particularly, for each instance, it constructs an instance subspace to model the configuration of how the significant factors of variations in K-shot augmentations can be combined to form the variants of augmentations. Given a query, the most relevant variant of instances is then retrieved by projecting the query onto their subspaces to predict the positive instance class. This generalizes the existing contrastive learning that can be viewed as a special one-shot case. An eigenvalue decomposition is performed to configure instance subspaces, and the embedding network can be trained end-to-end through the differentiable subspace configuration. Experiment results demonstrate the proposed K-shot contrastive learning achieves superior performances to the state-of-the-art unsupervised methods.

Trends of Microwave Devices Design Based on Artificial Neural Networks: A Review

The usage of techniques of the artificial neural networks (ANNs) in the field of microwave devices has recently increased. The advantages of ANNs in comparison with traditional full-wave methods are that the prediction speed when the traditional time-consuming iterative calculations are not required and also the complex mathematical model of the microwave device is no longer needed. Therefore, the design of microwave device could be repeated many times in real time. However, methods of artificial neural networks still lag behind traditional full-wave methods in terms of accuracy. The prediction accuracy depends on the structure of the selected neural network and also on the obtained dataset for the training of the network. Therefore, the paper presents a systematic review of the implementation of ANNs in the field of the design and analysis of microwave devices. The guidelines for the systematic literature review and the systematic mapping research procedure, as well as the Preferred Report Items for Systematic Reviews and Meta-Analysis statements (PRISMA) are used to conduct literature search and report the results. The goal of the paper is to summarize the application areas of usage of ANNs in the field of microwave devices, the type and structure of the used artificial neural networks, the type and size of the dataset, the interpolation and the augmentation of the training dataset, the training algorithm and training errors and also to discuss the future perspectives of the usage of ANNs in the field of microwave devices.

CRS-CONT: A Well-Trained General Encoder for Facial Expression Analysis

Existing facial expression recognition (FER) methods train encoders with different large-scale training data for specific FER applications. In this paper, we propose a new task in this field. This task aims to pre-train a general encoder to extract any facial expression representations without fine-tuning. To tackle this task, we extend the self-supervised contrastive learning to pre-train a general encoder for facial expression analysis. To be specific, given a batch of facial expressions, some positive and negative pairs are firstly constructed based on coarse-grained labels and a FER-specified data augmentation strategy. Secondly, we propose the coarse-contrastive (CRS-CONT) learning, where the features of positive pairs are pulled together, while pushed away from the features of negative pairs. Moreover, one key event is that the excessive constraint on the coarse-grained feature distribution will affect fine-grained FER applications. To address this, a weight vector is designed to control the optimization of the CRS-CONT learning. As a result, a well-trained general encoder with frozen weights could preferably adapt to different facial expressions and realize the linear evaluation on any target datasets. Extensive experiments on both in- the-wild and in- the-lab FER datasets show that our method provides superior or comparable performance against state-of-the-art FER methods, especially on unseen facial expressions and cross-dataset evaluation. We hope that this work will help to reduce the training burden and develop a new solution against the fully-supervised feature learning with fine-grained labels. Code and the general encoder will be publicly available at https://github.com/hangyu94/CRS-CONT.

eSPA+: Scalable Entropy-Optimal Machine Learning Classification for Small Data Problems

Classification problems in the small data regime (with small data statistic T and relatively large feature space dimension D) impose challenges for the common machine learning (ML) and deep learning (DL) tools. The standard learning methods from these areas tend to show a lack of robustness when applied to data sets with significantly fewer data points than dimensions and quickly reach the overfitting bound, thus leading to poor performance beyond the training set. To tackle this issue, we propose eSPA+, a significant extension of the recently formulated entropy-optimal scalable probabilistic approximation algorithm (eSPA). Specifically, we propose to change the order of the optimization steps and replace the most computationally expensive subproblem of eSPA with its closed-form solution. We prove that with these two enhancements, eSPA+ moves from the polynomial to the linear class of complexity scaling algorithms. On several small data learning benchmarks, we show that the eSPA+ algorithm achieves a many-fold speed-up with respect to eSPA and even better performance results when compared to a wide array of ML and DL tools. In particular, we benchmark eSPA+ against the standard eSPA and the main classes of common learning algorithms in the small data regime: various forms of support vector machines, random forests, and long short-term memory algorithms. In all the considered applications, the common learning methods and eSPA are markedly outperformed by eSPA+, which achieves significantly higher prediction accuracy with an orders-of-magnitude lower computational cost.

Deep semi-supervised learning via dynamic anchor graph embedding in latent space

Recently, deep semi-supervised graph embedding learning has drawn much attention for its appealing performance on the data with a pre-specified graph structure, which could be predefined or empirically constructed based on given data samples. However, the pre-specified graphs often contain considerable noisy/inaccurate connections and have a huge size for large datasets. Most existing embedding algorithms just take the graph off the shelf during the whole training stage and thus are easy to be misled by the inaccurate graph edges, as well as may result in large model size. In this paper, we attempt to address these issues by proposing a novel deep semi-supervised algorithm for simultaneous graph embedding and node classification, utilizing dynamic graph learning in neural network hidden layer space. Particularly, we construct an anchor graph to summarize the whole dataset using the hidden layer features of a consistency-constrained network. The anchor graph is used for sampling node neighborhood context, which is then presented together with node labels as contextual information to train an embedding network. The outputs of the consistency network and the embedding networks are finally concatenated together to pass a softmax function to perform node classification. The two networks are optimized jointly using both labeled and unlabeled data to minimize a single semi-supervised objective function, including a cross-entropy loss, a consistency loss and an embedding loss. Extensive experimental results on popular image and text datasets have shown that the proposed method is able to improve the performance of existing graph embedding and node classification methods, and outperform many state-of-the-art approaches on both types of datasets.

Improving Nonlinear Interpolation of K-Space Data Using Semi-Supervised Learning and Autoregressive Model

Parallel magnetic resonance imaging (pMRI) accelerates data acquisition by undersampling k-space through an array of receiver coils. Finding accurate relationships between acquired and missing k-space data determines the interpolation performance and reconstruction quality. Autocalibration signals (ACS) are generally used to learn the interpolation coefficients for reconstructing the missing k-space data. Based on the estimation-approximation error analysis in machine learning, increasing training data size can reduce estimation error and therefore enhance generalization ability of the interpolator, but scanning time will be longer if more ACS data are acquired. We propose to augment training data using unacquired and acquired data outside of ACS region through semi-supervised learning idea and autoregressive model. Local neighbor unacquired k-space data can be used for training tasks and reducing the generalization error. Experimental results show that the proposed method outperforms the conventional methods by suppressing noise and aliasing artifacts.

Severity Prediction for Bug Reports Using Multi-Aspect Features: A Deep Learning Approach

The severity of software bug reports plays an important role in maintaining software quality. Many approaches have been proposed to predict the severity of bug reports using textual information. In this research, we propose a deep learning framework called MASP that uses convolutional neural networks (CNN) and the content-aspect, sentiment-aspect, quality-aspect, and reporter-aspect features of bug reports to improve prediction performance. We have performed experiments on datasets collected from Eclipse and Mozilla. The results show that the MASP model outperforms the state-of-the-art CNN model in terms of average Accuracy, Precision, Recall, F1-measure, and the Matthews Correlation Coefficient (MCC) by 1.83%, 0.46%, 3.23%, 1.72%, and 6.61%, respectively.