Adaobi Chiazor Emegoakor

Toufiq Musah, Chinasa Kalaiwo, Maimoona Akram et al.

Automated segmentation of BUS images is important for precise lesion delineation and tumor characterization, but is challenged by inherent artifacts and dataset inconsistencies. In this work, we evaluate the use of a modified Residual Encoder U-Net for breast ultrasound segmentation, with a focus on uncertainty quantification. We identify and correct for data duplication in the BUSI dataset, and use a deduplicated subset for more reliable estimates of generalization performance. Epistemic uncertainty is quantified using Monte Carlo dropout, deep ensembles, and their combination. Models are benchmarked on both in-distribution and out-of-distribution datasets to demonstrate how they generalize to unseen cross-domain data. Our approach achieves state-of-the-art segmentation accuracy on the Breast-Lesion-USG dataset with in-distribution validation, and provides calibrated uncertainty estimates that effectively signal regions of low model confidence. Performance declines and increased uncertainty observed in out-of-distribution evaluation highlight the persistent challenge of domain shift in medical imaging, and the importance of integrated uncertainty modeling for trustworthy clinical deployment. \footnote{Code available at: https://github.com/toufiqmusah/nn-uncertainty.git}

Chukwuemeka Arua Kalu, Adaobi Chiazor Emegoakor, Fortune Okafor et al.

Medical image segmentation is a critical achievement in modern medical science, developed over decades of research. It allows for the exact delineation of anatomical and pathological features in two- or three-dimensional pictures by utilizing notions like pixel intensity, texture, and anatomical context. With the advent of automated segmentation, physicians and radiologists may now concentrate on diagnosis and treatment planning while intelligent computers perform routine image processing tasks. This study used the BraTS Sub-Saharan Africa dataset, a selected subset of the BraTS dataset that included 60 multimodal MRI cases from patients with glioma. Surprisingly, the nnU Net model trained on the initial 60 instances performed better than the network trained on an offline-augmented dataset of 360 cases. Hypothetically, the offline augmentations introduced artificial anatomical variances or intensity distributions, reducing generalization. In contrast, the original dataset, when paired with nnU Net's robust online augmentation procedures, maintained realistic variability and produced better results. The study achieved a Dice score of 0.84 for whole tumor segmentation. These findings highlight the significance of data quality and proper augmentation approaches in constructing accurate, generalizable medical picture segmentation models, particularly for under-represented locations.