Sabah Afroze

Dr. Sabah Afroze

orcid

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
22 December 2025 in Journal of Imaging
Verified
Journal Article
Open access
PDF file
MDMou Deb
Mou Deb
MDMrinal Kanti Dhar
Mrinal Kanti Dhar
Poonguzhali ElangovanPoonguzhali Elangovan
Poonguzhali Elangovan
KGKeerthy Gopalakrishnan Gopalakrishnan
Keerthy Gopalakrishnan Gopalakrishnan
DSDIVYANSHI SOOD
DIVYANSHI SOOD
Shivaram P. ArunachalamShivaram P. Arunachalam
Shivaram P. Arunachalam
This study proposes a novel two-dimensional Empirical Mode Decomposition (2D EMD)-based deep learning framework to enhance model performance in multi-class image classification tasks and potential early detection of diseases in healthcare using medical imaging. To validate this approach, we apply it to gastrointestinal (GI) endoscopic image classification using the publicly available Kvasir dataset, which contains eight GI image classes with 1000 images each. The proposed 2D EMD-based design procedure decomposes images into a full set of intrinsic mode functions (IMFs) to enhance image features beneficial for AI model development. Integrating 2D EMD into a deep learning pipeline, we evaluate its impact on four popular models (ResNet152, VGG19bn, MobileNetV3L, and SwinTransformerV2S). The results demonstrate that subtracting IMFs from the original image consistently improves accuracy, F1-score, and AUC for all models. The study reveals a notable enhancement in model performance, with an approximately 9% increase in accuracy compared to counterparts without EMD integration for ResNet152. Similarly, there is an increase of around 18% for VGG19L, 3% for MobileNetV3L, and 8% for SwinTransformerV2. Additionally, explainable AI (XAI) techniques, such as Grad-CAM, illustrate that the model focuses on GI regions for predictions. This study highlights the efficacy of 2D EMD in enhancing deep learning model performance for GI image classification, with potential applications in other domains.

21 September 2023 in Research Square
Verified
Preprint
Open access
PDF file
VMVaidehi Mendpara
Vaidehi Mendpara
NGNarendranath Reddy Ganampet
Narendranath Reddy Ganampet
SASabah Afroze
Sabah Afroze
SGSulochana Gnanasekaran
Sulochana Gnanasekaran
SSSweta Sahu
Sweta Sahu
VVVishal Venugopal
Vishal Venugopal
Oligomenorrhea with different degrees of follicular and adrenal hyperandrogenism are the hallmarks of the condition of polycystic ovary syndrome (PCOS). For some of the women in their reproductive years, this endocrine illness is incredibly prevalent and comprises a variety of disorders. There are a set of symptoms, such as hirsutism, acne, and insulin resistance, for identifying the characteristics of PCOS. Various treatment modalities have been opted for over the years for the treatment and management of this condition, among which metformin and flutamide are the most prevalent, along with lifestyle modifications as prevalent recommendations to patients. Weight management for obese patients is the most challenging aspect of PCOS management. Still, similar findings are found in women with lean physiology or a normal BMI, indicating that PCOS symptoms prevail and occur irrespective of the BMI, but obese or overweight women face more problems. We determined the long-term effects of treatment modalities on PCOS symptoms and their improvement. Metformin was reported to primarily increase the blood levels of glucose as well as BMI. Blood pressure was also maintained among various researchers, and DHEAS levels were also altered along with serum sex hormone-binding globulin in the plasma of patients undergoing treatments specific for PCOS patients with a normal BMI or lean PCOS. Further studies with more extensive parameters being employed need to be conducted for the determination of the exact mechanism and cause of the disease to ease the treatment process.