Non-Uniform Illumination Attack for Fooling Convolutional Neural Networks

Convolutional Neural Networks (CNNs) have made remarkable strides; however, they remain susceptible to vulnerabilities, particularly in the face of minor image perturbations that humans can easily recognize. This weakness, often termed as 'attacks', underscores the limited robustness of CNNs and the need for research into fortifying their resistance against such manipulations. This study introduces a novel Non-Uniform Illumination (NUI) attack technique, where images are subtly altered using varying NUI masks. Extensive experiments are conducted on widely-accepted datasets including CIFAR10, TinyImageNet, and CalTech256, focusing on image classification with 12 different NUI attack models. The resilience of VGG, ResNet, MobilenetV3-small and InceptionV3 models against NUI attacks are evaluated. Our results show a substantial decline in the CNN models' classification accuracy when subjected to NUI attacks, indicating their vulnerability under non-uniform illumination. To mitigate this, a defense strategy is proposed, including NUI-attacked images, generated through the new NUI transformation, into the training set. The results demonstrate a significant enhancement in CNN model performance when confronted with perturbed images affected by NUI attacks. This strategy seeks to bolster CNN models' resilience against NUI attacks.

Advances and Challenges in Meta-Learning: A Technical Review

Venue: IEEE Transactions on Pattern Analysis and Machine Intelligence ( Volume: 46, Issue: 7, July 2024)

Meta-learning empowers learning systems with the ability to acquire knowledge from multiple tasks, enabling faster adaptation and generalization to new tasks. This review provides a comprehensive technical overview of meta-learning, emphasizing its importance in real-world applications where data may be scarce or expensive to obtain. The article covers the state-of-the-art meta-learning approaches and explores the relationship between meta-learning and multi-task learning, transfer learning, domain adaptation and generalization, self-supervised learning, personalized federated learning, and continual learning. By highlighting the synergies between these topics and the field of meta-learning, the article demonstrates how advancements in one area can benefit the field as a whole, while avoiding unnecessary duplication of efforts. Additionally, the article delves into advanced meta-learning topics such as learning from complex multi-modal task distributions, unsupervised meta-learning, learning to efficiently adapt to data distribution shifts, and continual meta-learning. Lastly, the article highlights open problems and challenges for future research in the field. By synthesizing the latest research developments, this article provides a thorough understanding of meta-learning and its potential impact on various machine learning applications. We believe that this technical overview will contribute to the advancement of meta-learning and its practical implications in addressing real-world problems.

Advances in Deep Learning for Tuberculosis Screening using Chest X‑rays: The Last 5 Years Review

Venue: Journal of Medical Systems, Springer (2023)

There has been an explosive growth in research over the last decade exploring machine learning techniques for analyzing chest X-ray (CXR) images for screening cardiopulmonary abnormalities. In particular, we have observed a strong interest in screening for tuberculosis (TB). This interest has coincided with the spectacular advances in deep learning (DL) that is primarily based on convolutional neural networks (CNNs). These advances have resulted in signifcant research contributions in DL techniques for TB screening using CXR images. We review the research studies published over the last fve years (2016- 2021). We identify data collections, methodical contributions, and highlight promising methods and challenges. Further, we discuss and compare studies and identify those that ofer extension beyond binary decisions for TB, such as region-of-interest localization. In total, we systematically review 54 peer-reviewed research articles and perform meta-analysis.

Guest Editorial Multimodal Learning in Medical Imaging Informatics

Venue: IEEE Journal of Biomedical and Health Informatics ( Volume: 27, Issue: 3, March 2023)

The papers in this special section focus on multimodal learning in medical imaging informatics. Enormous amounts of health-related data are produced daily, such as those from personal devices, e.g., fitness trackers or mobile applications, ambient sensors, clinical data in electronic health records, pathology reports, lab results, medical images, voice recordings, etc. The practice of modern medicine increasingly relies on data from multiple sources to guide better care. Toward this goal, the papers in this section describe the tools and techniques that integrate multiple data types to describe a particular medical event/case toward developing higher confidence in their decision-making and guidance.

Cervical cancerous cell classifcation: opposition‑based harmony search for deep feature selection

Over 500 K (per year) cervical cancer cases are reported with a high mortality rate (6–9%). Automatically detecting cervical cancer using the Computer-Aided Diagnosis (CAD) tool at an early stage is important since it leads to successful treatment as pathologists. In this paper, we propose a tool that classifes cervical cancer cases from Pap smear cytology images using deep features. The proposed tool constitutes a Convolutional Neural Network (CNN) and a metaheuristic evolutionary algorithm called Opposition-based Harmony Search Algorithm (O-bHSA) for deep feature section. These features are classifed using standard classifers: SVM, MLP, and KNN. On two diferent publicly available datasets: Pap smear and liquid-based cytology, the proposed tool outperforms not only seven well-known optimization algorithms but also state-of-the-art methods. Codes are publicly available on GitHub.

SecureFed: federated learning empowered medical imaging technique to analyze lung abnormalities in chest X‑rays

Machine learning is an efective and accurate technique to diagnose COVID-19 infections using image data, and chest X-Ray (CXR) is no exception. Considering privacy issues, machine learning scientists end up receiving less medical imaging data. Federated Learning (FL) is a privacy-preserving distributed machine learning paradigm that generates an unbiased global model that follows local model (from clients) without exposing their personal data. In the case of heterogeneous data among clients, vanilla or default FL mechanism still introduces an insecure method for updating models. Therefore, we proposed SecureFed—a secure aggregation method—which ensures fairness and robustness. In our experiments, we employed COVID-19 CXR dataset (of size 2100 positive cases) and compared it with the existing FL frameworks such as FedAvg, FedMGDA+, and FedRAD. In our comparison, we primarily considered robustness (accuracy) and fairness (consistency). As the SecureFed produced consistently better results, it is generic enough to be considered for multimodal data.