Nahimiya Ibrahim

Dr. Nahimiya Ibrahim


Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
4 January 2023 in Diagnostics
Verified
Journal Article
Open access
PDF file
Gelan AyanaGelan Ayana
Gelan Ayana
kokeb Desekokeb Dese
kokeb Dese
YAYisak Dereje Asefa
Yisak Dereje Asefa
YKYonas Kebede
Yonas Kebede
Hika BarkiHika Barki
Hika Barki
Se-woon ChoeSe-woon Choe
Se-woon Choe
Breast mass identification is a crucial procedure during mammogram-based early breast cancer diagnosis. However, it is difficult to determine whether a breast lump is benign or cancerous at early stages. Convolutional neural networks (CNNs) have been used to solve this problem and have provided useful advancements. However, CNNs focus only on a certain portion of the mammogram while ignoring the remaining and present computational complexity because of multiple convolutions. Recently, vision transformers have been developed as a technique to overcome such limitations of CNNs, ensuring better or comparable performance in natural image classification. However, the utility of this technique has not been thoroughly investigated in the medical image domain. In this study, we developed a transfer learning technique based on vision transformers to classify breast mass mammograms. The area under the receiver operating curve of the new model was estimated as 1 ± 0, thus outperforming the CNN-based transfer-learning models and vision transformer models trained from scratch. The technique can, hence, be applied in a clinical setting, to improve the early diagnosis of breast cancer.

14 April 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
Leone MazzeoLeone Mazzeo
Leone Mazzeo
NINahimiya Ibrahim
Nahimiya Ibrahim
KPKatie S. Pickering
Katie S. Pickering
JOJacob Anthony Oyarzabal
Jacob Anthony Oyarzabal
EBErnest Bwogi
Ernest Bwogi
LPLeandro Pecchia
Leandro Pecchia
Oxygen concentrators (OCs) are essential medical devices providing oxygen in various settings, especially low-resource settings (LRSs). Despite their adaptability and cost-effectiveness, challenges arise in such environments due to factors like dust, temperature, and humidity, leading to premature OC failure. While efforts have been made to address these issues, understanding the primary contributing factor remains unclear. This study aims to shed light on this matter through the analysis of exhausted zeolite samples from Uganda, Ethiopia, and South Africa alongside a commercial virgin sample. The samples were comprehensively characterized through powder X-ray diffraction (PXRD) analysis, wavelength dispersive X-ray fluorescence (WDXRF) elemental analysis, Brunauer–Emmett–Teller (BET) surface analysis, and thermo-gravimetric analysis (TGA) coupled with mass spectrometry (MS). The characterization results confirmed a low silicon X-type framework (FAU-LSX) for all the samples. The maximum mass loss during TGA tests occurred at 130–160 °C, suggesting that water is the main component released from the zeolites. This was confirmed by MS analysis, which revealed the predominance of water in all the sample matrices. A correlation was found between OC efficiency and the amount of water adsorbed by the zeolites, proving that humidity has a key role in causing OC malfunctioning. No evidence for the presence of dust as a contaminant in the zeolites was found by the absence of the expected chemical elements in WDXRF. Since the outcomes of the study are independent of the geographical origin of the zeolites, its findings provide general guidance for engineers to modify OCs and prevent zeolite moisture poisoning.