Noha S. Tawfik

Breast cancer is the second leading cause of cancer-related mortality among women. Early detection enables timely treatment, improving survival outcomes. This paper presents a comparative evaluation of federated learning (FL) frameworks for multiclass breast cancer classification using ultrasound images drawn from three datasets: BUSI, BUS-UCLM, and BCMID, which include 600, 38, and 323 patients, respectively. Five state-of-the-art networks were tested, with MobileNet, ResNet and InceptionNet identified as the most effective for FL deployment. Two aggregation strategies, FedAvg and FedProx, were assessed under varying levels of data heterogeneity in two and three client settings. Results from experiments indicate that the FL models outperformed local and centralized training, bypassing the adverse impacts of data isolation and domain shift. In the two-client federations, FL achieving up to 8% higher accuracy and almost 6% higher macro-F1 scores on average that local and centralized training. FedProx on MobileNet maintained a stable performance in the three-client federation with best average accuracy of 73.31%, and macro-F1 of 67.3% despite stronger heterogeneity. Consequently, these results suggest that the proposed multiclass model has the potential to support clinical workflows by assisting in automated risk stratification. If deployed, such a system could allow radiologists to prioritize high-risk patients more effectively. The findings emphasize the potential of federated learning as a scalable, privacy-preserving infrastructure for collaborative medical imaging and breast cancer diagnosis.

Social networks have become deeply integrated into our daily lives, leading to an increase in image sharing across different platforms. Simultaneously, the existence of robust and user-friendly media editors not only facilitates artistic innovation, but also raises concerns regarding the ease of creating misleading media. This highlights the need for developing new advanced techniques for the image copy detection task, which involves evaluating whether photos or videos originate from the same source. This research introduces a novel application of the Vision Transformer (ViT) model to the image copy detection task on the DISC21 dataset. Our approach involves innovative strategic sampling of the extensive DISC21 training set using K-means clustering to achieve a representative subset. Additionally, we employ complex augmentation pipelines applied while training with varying intensities. Our methodology follows the instance discrimination concept, where the Vision Transformer model is used as a classifier to map different augmentations of the same image to the same class. Next, the trained ViT model extracts descriptors of original and manipulated images that subsequently underwent post-processing to reduce dimensionality. Our best-achieving model, tested on a refined query set of 10K augmented images from the DISC21 dataset, attained a state-of-the-art micro-average precision of 0.79, demonstrating the effectiveness and innovation of our approach.

Crying is a newborn’s main way of communicating. Despite their apparent similarity, newborn cries are physically generated and have distinct characteristics. Experienced medical professionals, nurses, and parents are able to recognize these variations based on their prior interactions. Nonetheless, interpreting a baby’s cries can be challenging for carers, first-time parents, and inexperienced paediatricians. This paper uses advanced deep learning techniques to propose a novel approach for baby cry classification. This study aims to accurately classify different cry types associated with everyday infant needs, including hunger, discomfort, pain, tiredness, and the need for burping. The proposed model achieves an accuracy of 98.33%, surpassing the performance of existing studies in the field. IoT-enabled sensors are utilized to capture cry signals in real time, ensuring continuous and reliable monitoring of the infant’s acoustic environment. This integration of IoT technology with deep learning enhances the system’s responsiveness and accuracy. Our study highlights the significance of accurate cry classification in understanding and meeting the needs of infants and its potential impact on improving infant care practices. The methodology, including the dataset, preprocessing techniques, and architecture of the deep learning model, is described. The results demonstrate the performance of the proposed model, and the discussion analyzes the factors contributing to its high accuracy.

The rapid advancement of technology has created new opportunities to improve the accuracy and efficiency of medical diagnoses, treatments, and overall patient care in several medical domains, including mental health. One promising novel approach is federated learning, a machine learning approach that allows multiple devices to train a shared model without exchanging raw data. Instead of centralizing the data in one location, each device or machine holds a portion of the data and collaborates with other devices to update the shared model. In this way, federated learning enables training on more extensive and diverse datasets than would be possible with centralized training while preserving the privacy and security of individual data. In the mental health domain, federated learning has the potential to improve mental disorders’ detection, diagnosis, and treatment. By pooling data from multiple sources while maintaining patient privacy by keeping data secure and ensuring that they are not used for unauthorized purposes. This literature survey reviews recent studies that have exploited federated learning in the psychiatric domain, covering multiple data resources and different machine-learning techniques. Furthermore, we formulate the gap in the current methodologies and propose new research directions.

Ahmed El-Sayed, Omar Nasr, Noha Tawfik. Proceedings of The 9th Social Media Mining for Health Research and Applications (SMM4H 2024) Workshop and Shared Tasks. 2024.

It is becoming more challenging for health professionals to keep up to date with current research. To save time, many experts perform evidence syntheses on systematic reviews instead of primary studies. Subsequently, there is a need to update reviews to include new evidence, which requires a significant amount of effort and delays the update process. These efforts can be significantly reduced by applying computer-assisted techniques to identify relevant studies. In this study, we followed a “human-in-the-loop” approach by engaging medical experts through a controlled user experiment to update systematic reviews. The primary outcome of interest was to compare the performance levels achieved when judging full abstracts versus single sentences accompanied by Natural Language Inference labels. The experiment included post-task questionnaires to collect participants’ feedback on the usability of the computer-assisted suggestions. The findings lead us to the conclusion that employing sentence-level, for relevance assessment, achieves higher recall.