Semi-supervised learning for medical image classification using imbalanced training data

Advances of artificial intelligence in clinical application and scientific research of neuro-oncology: Current knowledge and future perspectives

Brain tumors refer to the abnormal growths that occur within the brain's tissue, comprising both primary neoplasms and metastatic lesions. Timely detection, precise staging, suitable treatment, and standardized management are of significant clinical importance for extending the survival rates of brain tumor patients. Artificial intelligence (AI), a discipline within computer science, is leveraging its robust capacity for information identification and combination to revolutionize traditional paradigms of oncology care, offering substantial potential for precision medicine. This article provides an overview of the current applications of AI in brain tumors, encompassing the primary AI technologies, their working mechanisms and working workflow, the contributions of AI to brain tumor diagnosis and treatment, as well as the role of AI in brain tumor scientific research, particularly in drug innovation and revealing tumor microenvironment. Finally, the paper addresses the existing challenges, potential solutions, and the future application prospects. This review aims to enhance our understanding of the application of AI in brain tumors and provide valuable insights for forthcoming clinical applications and scientific inquiries.

Automatic maxillary sinus segmentation and age estimation model for the northwestern Chinese Han population

BACKGROUND

Age estimation is vital in forensic science, with maxillary sinus development serving as a reliable indicator. This study developed an automatic segmentation model for maxillary sinus identification and parameter measurement, combined with regression and machine learning models for age estimation.

METHODS

Cone Beam Computed Tomography (CBCT) images from 292 Han individuals (ranging from 5 to 53 years) were used to train and validate the segmentation model. Measurements included sinus dimensions (length, width, height), inter-sinus distance, and volume. Age estimation models using multiple linear regression and random forest algorithms were built based on these variables.

RESULTS

The automatic segmentation model achieved high accuracy, which yielded a Dice similarity coefficient (DSC) of 0.873, an Intersection over Union (IoU) of 0.7753, a Hausdorff Distance 95% (HD95) of 9.8337, and an Average Surface Distance (ASD) of 2.4507. The regression model performed best, with mean absolute errors (MAE) of 1.45 years (under 18) and 3.51 years (aged 18 and above), providing relatively precise age predictions.

CONCLUSION

The maxillary sinus-based model is a promising tool for age estimation, particularly in adults, and could be enhanced by incorporating additional variables like dental dimensions.

Wide-field OCT volumetric segmentation using semi-supervised CNN and transformer integration

Wide-field optical coherence tomography (OCT) imaging can enable monitoring of peripheral changes in the retina, beyond the conventional fields of view used in current clinical OCT imaging systems. However, wide-field scans can present significant challenges for retinal layer segmentation. Deep Convolutional Neural Networks (CNNs) have shown strong performance in medical imaging segmentation but typically require large-scale, high-quality, pixel-level annotated datasets to be effectively developed. To address this challenge, we propose an advanced semi-supervised learning framework that combines the detailed capabilities of convolutional networks with the broader perspective of transformers. This method efficiently leverages labelled and unlabelled data to reduce dependence on extensive, manually annotated datasets. We evaluated the model performance on a dataset of 74 volumetric OCT scans, each performed using a prototype swept-source OCT system following a wide-field scan protocol with a 15 × 9 mm field of view, comprising 11,750 labelled and 29,016 unlabelled images. Wide-field retinal layer segmentation using the semi-supervised approach show significant improvements (P-value < 0.001) of up to 11% against a UNet baseline model. Comparisons with a clinical spectral-domain-OCT system revealed significant correlations of up to 0.91 (P-value < 0.001) in retinal layer thickness measurements. These findings highlight the effectiveness of semi-supervised learning with cross-teaching between CNNs and transformers for automated OCT layer segmentation.

A novel semi-supervised learning model based on pelvic radiographs for ankylosing spondylitis diagnosis reduces 90% of annotation cost

OBJECTIVE

Our study aims to develop a deep learning-based Ankylosing Spondylitis (AS) diagnostic model that achieves human expert-level performance using only a minimal amount of labeled samples for training, in regions with limited access to expert resources.

METHODS

Our semi-supervised diagnostic model for AS was developed using 5389 pelvic radiographs (PXRs) from a single medical center, collected from March 2014 to April 2022. The dataset was split into a training set and a validation set with an 8:2 ratio, allocating 431 labeled images and the remaining 3880 unlabeled images for semi-supervised learning. The model's performance was evaluated on 982 PXRs from the same center, assessing metrics such as AUC, accuracy, precision, recall, and F1 scores. Interpretability analysis was performed using explainable algorithms to validate the model's clinical applicability.

RESULTS

Our semi-supervised learning model achieved accuracy, recall, and precision values of 0.891, 0.865, and 0.859, respectively, using only 10% of labeled data from the entire training set, surpassing human expert performance. Extensive interpretability analysis demonstrated the reliability of our model's predictions, making the deep neural network no longer a black box.

CONCLUSION

This study marks the first application of semi-supervised learning to diagnose AS using PXRs, achieving a 90% reduction in manual annotation costs. The model showcases robust generalization on an independent test set and delivers reliable diagnostic performance, supported by comprehensive interpretability analysis. This innovative approach paves the way for training high-performance diagnostic models on large datasets with minimal labeled data, heralding a cost-effective future for medical imaging research in big data analytics.

A review of deep learning-based reconstruction methods for accelerated MRI using spatiotemporal and multi-contrast redundancies

Accelerated magnetic resonance imaging (MRI) has played an essential role in reducing data acquisition time for MRI. Acceleration can be achieved by acquiring fewer data points in k-space, which results in various artifacts in the image domain. Conventional reconstruction methods have resolved the artifacts by utilizing multi-coil information, but with limited robustness. Recently, numerous deep learning-based reconstruction methods have been developed, enabling outstanding reconstruction performances with higher acceleration. Advances in hardware and developments of specialized network architectures have produced such achievements. Besides, MRI signals contain various redundant information including multi-coil redundancy, multi-contrast redundancy, and spatiotemporal redundancy. Utilization of the redundant information combined with deep learning approaches allow not only higher acceleration, but also well-preserved details in the reconstructed images. Consequently, this review paper introduces the basic concepts of deep learning and conventional accelerated MRI reconstruction methods, followed by review of recent deep learning-based reconstruction methods that exploit various redundancies. Lastly, the paper concludes by discussing the challenges, limitations, and potential directions of future developments.

Taming Overconfident Prediction on Unlabeled Data From Hindsight

Minimizing prediction uncertainty on unlabeled data is a key factor to achieve good performance in semi-supervised learning (SSL). The prediction uncertainty is typically expressed as the entropy computed by the transformed probabilities in output space. Most existing works distill low-entropy prediction by either accepting the determining class (with the largest probability) as the true label or suppressing subtle predictions (with the smaller probabilities). Unarguably, these distillation strategies are usually heuristic and less informative for model training. From this discernment, this article proposes a dual mechanism, named adaptive sharpening (ADS), which first applies a soft-threshold to adaptively mask out determinate and negligible predictions, and then seamlessly sharpens the informed predictions, distilling certain predictions with the informed ones only. More importantly, we theoretically analyze the traits of ADS by comparing it with various distillation strategies. Numerous experiments verify that ADS significantly improves state-of-the-art SSL methods by making it a plug-in. Our proposed ADS forges a cornerstone for future distillation-based SSL research.

Mpox-AISM: AI-mediated super monitoring for mpox and like-mpox

Swift and accurate diagnosis for earlier-stage monkeypox (mpox) patients is crucial to avoiding its spread. However, the similarities between common skin disorders and mpox and the need for professional diagnosis unavoidably impaired the diagnosis of earlier-stage mpox patients and contributed to mpox outbreak. To address the challenge, we proposed "Super Monitoring", a real-time visualization technique employing artificial intelligence (AI) and Internet technology to diagnose earlier-stage mpox cheaply, conveniently, and quickly. Concretely, AI-mediated "Super Monitoring" (mpox-AISM) integrates deep learning models, data augmentation, self-supervised learning, and cloud services. According to publicly accessible datasets, mpox-AISM's Precision, Recall, Specificity, and F1-score in diagnosing mpox reach 99.3%, 94.1%, 99.9%, and 96.6%, respectively, and it achieves 94.51% accuracy in diagnosing mpox, six like-mpox skin disorders, and normal skin. With the Internet and communication terminal, mpox-AISM has the potential to perform real-time and accurate diagnosis for earlier-stage mpox in real-world scenarios, thereby preventing mpox outbreak.

Dynamic Weighting Translation Transfer Learning for Imbalanced Medical Image Classification

Medical image diagnosis using deep learning has shown significant promise in clinical medicine. However, it often encounters two major difficulties in real-world applications: (1) domain shift, which invalidates the trained model on new datasets, and (2) class imbalance problems leading to model biases towards majority classes. To address these challenges, this paper proposes a transfer learning solution, named Dynamic Weighting Translation Transfer Learning (DTTL), for imbalanced medical image classification. The approach is grounded in information and entropy theory and comprises three modules: Cross-domain Discriminability Adaptation (CDA), Dynamic Domain Translation (DDT), and Balanced Target Learning (BTL). CDA connects discriminative feature learning between source and target domains using a synthetic discriminability loss and a domain-invariant feature learning loss. The DDT unit develops a dynamic translation process for imbalanced classes between two domains, utilizing a confidence-based selection approach to select the most useful synthesized images to create a pseudo-labeled balanced target domain. Finally, the BTL unit performs supervised learning on the reassembled target set to obtain the final diagnostic model. This paper delves into maximizing the entropy of class distributions, while simultaneously minimizing the cross-entropy between the source and target domains to reduce domain discrepancies. By incorporating entropy concepts into our framework, our method not only significantly enhances medical image classification in practical settings but also innovates the application of entropy and information theory within deep learning and medical image processing realms. Extensive experiments demonstrate that DTTL achieves the best performance compared to existing state-of-the-art methods for imbalanced medical image classification tasks.

A Critical Analysis of Deep Semi-Supervised Learning Approaches for Enhanced Medical Image Classification

Deep semi-supervised learning (DSSL) is a machine learning paradigm that blends supervised and unsupervised learning techniques to improve the performance of various models in computer vision tasks. Medical image classification plays a crucial role in disease diagnosis, treatment planning, and patient care. However, obtaining labeled medical image data is often expensive and time-consuming for medical practitioners, leading to limited labeled datasets. DSSL techniques aim to address this challenge, particularly in various medical image tasks, to improve model generalization and performance. DSSL models leverage both the labeled information, which provides explicit supervision, and the unlabeled data, which can provide additional information about the underlying data distribution. That offers a practical solution to resource-intensive demands of data annotation, and enhances the model’s ability to generalize across diverse and previously unseen data landscapes. The present study provides a critical review of various DSSL approaches and their effectiveness and challenges in enhancing medical image classification tasks. The study categorized DSSL techniques into six classes: consistency regularization method, deep adversarial method, pseudo-learning method, graph-based method, multi-label method, and hybrid method. Further, a comparative analysis of performance for six considered methods is conducted using existing studies. The referenced studies have employed metrics such as accuracy, sensitivity, specificity, AUC-ROC, and F1 score to evaluate the performance of DSSL methods on different medical image datasets. Additionally, challenges of the datasets, such as heterogeneity, limited labeled data, and model interpretability, were discussed and highlighted in the context of DSSL for medical image classification. The current review provides future directions and considerations to researchers to further address the challenges and take full advantage of these methods in clinical practices.

Medical long-tailed learning for imbalanced data: Bibliometric analysis

BACKGROUND

In the last decade, long-tail learning has become a popular research focus in deep learning applications in medicine. However, no scientometric reports have provided a systematic overview of this scientific field. We utilized bibliometric techniques to identify and analyze the literature on long-tailed learning in deep learning applications in medicine and investigate research trends, core authors, and core journals. We expanded our understanding of the primary components and principal methodologies of long-tail learning research in the medical field.

METHODS

Web of Science was utilized to collect all articles on long-tailed learning in medicine published until December 2023. The suitability of all retrieved titles and abstracts was evaluated. For bibliometric analysis, all numerical data were extracted. CiteSpace was used to create clustered and visual knowledge graphs based on keywords.

RESULTS

A total of 579 articles met the evaluation criteria. Over the last decade, the annual number of publications and citation frequency both showed significant growth, following a power-law and exponential trend, respectively. Noteworthy contributors to this field include Husanbir Singh Pannu, Fadi Thabtah, and Talha Mahboob Alam, while leading journals such as IEEE ACCESS, COMPUTERS IN BIOLOGY AND MEDICINE, IEEE TRANSACTIONS ON MEDICAL IMAGING, and COMPUTERIZED MEDICAL IMAGING AND GRAPHICS have emerged as pivotal platforms for disseminating research in this area. The core of long-tailed learning research within the medical domain is encapsulated in six principal themes: deep learning for imbalanced data, model optimization, neural networks in image analysis, data imbalance in health records, CNN in diagnostics and risk assessment, and genetic information in disease mechanisms.

CONCLUSION

This study summarizes recent advancements in applying long-tail learning to deep learning in medicine through bibliometric analysis and visual knowledge graphs. It explains new trends, sources, core authors, journals, and research hotspots. Although this field has shown great promise in medical deep learning research, our findings will provide pertinent and valuable insights for future research and clinical practice.

CosSIF: Cosine similarity-based image filtering to overcome low inter-class variation in synthetic medical image datasets

Crafting effective deep learning models for medical image analysis is a complex task, particularly in cases where the medical image dataset lacks significant inter-class variation. This challenge is further aggravated when employing such datasets to generate synthetic images using generative adversarial networks (GANs), as the output of GANs heavily relies on the input data. In this research, we propose a novel filtering algorithm called Cosine Similarity-based Image Filtering (CosSIF). We leverage CosSIF to develop two distinct filtering methods: Filtering Before GAN Training (FBGT) and Filtering After GAN Training (FAGT). FBGT involves the removal of real images that exhibit similarities to images of other classes before utilizing them as the training dataset for a GAN. On the other hand, FAGT focuses on eliminating synthetic images with less discriminative features compared to real images used for training the GAN. The experimental results reveal that the utilization of either the FAGT or FBGT method reduces low inter-class variation in clinical image classification datasets and enables GANs to generate synthetic images with greater discriminative features. Moreover, modern transformer and convolutional-based models, trained with datasets that utilize these filtering methods, lead to less bias toward the majority class, more accurate predictions of samples in the minority class, and overall better generalization capabilities. Code and implementation details are available at: https://github.com/mominul-ssv/cossif.

TNCB: Tri-Net With Cross-Balanced Pseudo Supervision for Class Imbalanced Medical Image Classification

In clinical settings, the implementation of deep neural networks is impeded by the prevalent problems of label scarcity and class imbalance in medical images. To mitigate the need for labeled data, semi-supervised learning (SSL) has gained traction. However, existing SSL schemes exhibit certain limitations. 1) They commonly fail to address the class imbalance problem. Training with imbalanced data makes the model's prediction biased towards majority classes, consequently introducing prediction bias. 2) They usually suffer from training bias arising from unreasonable training strategies, such as strong coupling between the generation and utilization of pseudo labels. To address these problems, we propose a novel SSL framework called Tri-Net with Cross-Balanced pseudo supervision (TNCB). Specifically, two student networks focusing on different learning tasks and a teacher network equipped with an adaptive balancer are designed. This design enables the teacher model to pay more focus on minority classes, thereby reducing prediction bias. Additionally, we propose a virtual optimization strategy to further enhance the teacher model's resistance to class imbalance. Finally, to fully exploit valuable knowledge from unlabeled images, we employ cross-balanced pseudo supervision, where an adaptive cross loss function is introduced to reduce training bias. Extensive evaluation on four datasets with different diseases, image modalities, and imbalance ratios consistently demonstrate the superior performance of TNCB over state-of-the-art SSL methods. These results indicate the effectiveness and robustness of TNCB in addressing imbalanced medical image classification challenges.

Data pyramid structure for optimizing EUS-based GISTs diagnosis in multi-center analysis with missing label

This study introduces the Data Pyramid Structure (DPS) to address data sparsity and missing labels in medical image analysis. The DPS optimizes multi-task learning and enables sustainable expansion of multi-center data analysis. Specifically, It facilitates attribute prediction and malignant tumor diagnosis tasks by implementing a segmentation and aggregation strategy on data with absent attribute labels. To leverage multi-center data, we propose the Unified Ensemble Learning Framework (UELF) and the Unified Federated Learning Framework (UFLF), which incorporate strategies for data transfer and incremental learning in scenarios with missing labels. The proposed method was evaluated on a challenging EUS patient dataset from five centers, achieving promising diagnostic performance. The average accuracy was 0.984 with an AUC of 0.927 for multi-center analysis, surpassing state-of-the-art approaches. The interpretability of the predictions further highlights the potential clinical relevance of our method.

Artificial Intelligence Applied to Non-Invasive Imaging Modalities in Identification of Nonmelanoma Skin Cancer: A Systematic Review

BACKGROUND

The objective of this study is to systematically analyze the current state of the literature regarding novel artificial intelligence (AI) machine learning models utilized in non-invasive imaging for the early detection of nonmelanoma skin cancers. Furthermore, we aimed to assess their potential clinical relevance by evaluating the accuracy, sensitivity, and specificity of each algorithm and assessing for the risk of bias.

METHODS

Two reviewers screened the MEDLINE, Cochrane, PubMed, and Embase databases for peer-reviewed studies that focused on AI-based skin cancer classification involving nonmelanoma skin cancers and were published between 2018 and 2023. The search terms included skin neoplasms, nonmelanoma, basal-cell carcinoma, squamous-cell carcinoma, diagnostic techniques and procedures, artificial intelligence, algorithms, computer systems, dermoscopy, reflectance confocal microscopy, and optical coherence tomography. Based on the search results, only studies that directly answered the review objectives were included and the efficacy measures for each were recorded. A QUADAS-2 risk assessment for bias in included studies was then conducted.

RESULTS

A total of 44 studies were included in our review; 40 utilizing dermoscopy, 3 using reflectance confocal microscopy (RCM), and 1 for hyperspectral epidermal imaging (HEI). The average accuracy of AI algorithms applied to all imaging modalities combined was 86.80%, with the same average for dermoscopy. Only one of the three studies applying AI to RCM measured accuracy, with a result of 87%. Accuracy was not measured in regard to AI based HEI interpretation.

CONCLUSION

AI algorithms exhibited an overall favorable performance in the diagnosis of nonmelanoma skin cancer via noninvasive imaging techniques. Ultimately, further research is needed to isolate pooled diagnostic accuracy for nonmelanoma skin cancers as many testing datasets also include melanoma and other pigmented lesions.

The efficacy of supervised learning and semi-supervised learning in diagnosis of impacted third molar on panoramic radiographs through artificial intelligence model

OBJECTIVES

The aim of the study was to evaluate the efficacy of traditional supervised learning (SL) and semi-supervised learning (SSL) in the classification of mandibular third molars (Mn3s) on panoramic images. The simplicity of preprocessing step and the outcome of the performance of SL and SSL were analyzed.

METHODS

Total 1625 Mn3s cropped images from 1000 panoramic images were labeled for classifications of the depth of impaction (D class), spatial relation with adjacent second molar (S class), and relationship with inferior alveolar nerve canal (N class). For the SL model, WideResNet (WRN) was applicated and for the SSL model, LaplaceNet (LN) was utilized.

RESULTS

In the WRN model, 300 labeled images for D and S classes, and 360 labeled images for N class were used for training and validation. In the LN model, only 40 labeled images for D, S, and N classes were used for learning. The F1 score were 0.87, 0.87, and 0.83 in WRN model, 0.84, 0.94, and 0.80 for D class, S class, and N class in the LN model, respectively.

CONCLUSIONS

These results confirmed that the LN model applied as SSL, even utilizing a small number of labeled images, demonstrated the satisfactory of the prediction accuracy similar to that of the WRN model as SL.

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.

An Insight of Deep Learning Based Demand Forecasting in Smart Grids

Smart grids are able to forecast customers' consumption patterns, i.e., their energy demand, and consequently electricity can be transmitted after taking into account the expected demand. To face today's demand forecasting challenges, where the data generated by smart grids is huge, modern data-driven techniques need to be used. In this scenario, Deep Learning models are a good alternative to learn patterns from customer data and then forecast demand for different forecasting horizons. Among the commonly used Artificial Neural Networks, Long Short-Term Memory networks-based on Recurrent Neural Networks-are playing a prominent role. This paper provides an insight into the importance of the demand forecasting issue, and other related factors, in the context of smart grids, and collects some experiences of the use of Deep Learning techniques, for demand forecasting purposes. To have an efficient power system, a balance between supply and demand is necessary. Therefore, industry stakeholders and researchers should make a special effort in load forecasting, especially in the short term, which is critical for demand response.