Innovative Research Award

Fizza Ghulam Nabi — University of the Punjab, Pakistan

Fizza Ghulam Nabi
Affiliation	University of the Punjab
Country	Pakistan
Scopus ID	57193326172
Documents	36
Citations	173
h-index	6
Subject Area	Computer Vision
Event	Technology Scientists Awards
ORCID	0000-0003-4784-3059

Fizza Ghulam Nabi is a researcher affiliated with the University of the Punjab whose scholarly work includes computer vision and medical image segmentation. Her publication record includes recent contributions addressing feature aggregation, selective downsampling, and model-guided segmentation, demonstrating engagement with contemporary deep-learning approaches for image analysis and computational biomedical applications.[1] [2]

Abstract

Fizza Ghulam Nabi is a computer vision researcher affiliated with the University of the Punjab, Pakistan, whose scholarly record includes 36 documents, 173 citations, and an h-index of 6. Her recent publications address medical image segmentation through feature aggregation, selective downsampling, and guided feature interaction. Her co-authored research on U-shaped segmentation models examines feature selection and aggregation through MLFA and DGIA modules, while SDNAL-Seg investigates multi-scale downsampling and non-adjacent layer guidance. These studies demonstrate sustained engagement with deep learning, image analysis, segmentation architecture, and computational methods relevant to contemporary computer vision research and biomedical image processing applications.[1] [2]

Keywords

Computer Vision; Medical Image Segmentation; Deep Learning; U-Shaped Networks; Feature Aggregation; Selective Downsampling; Neural Networks; Biomedical Image Analysis; Image Processing; Artificial Intelligence.[1] [2]

Introduction

Medical image segmentation is an important computer vision problem supporting the extraction of anatomical structures and clinically relevant regions from imaging data. Contemporary research increasingly combines U-shaped architectures with feature aggregation, attention, and multi-scale processing to improve segmentation quality. Nabi’s recent work contributes to this broader methodological direction through collaborative studies of segmentation architecture.[1] [2]

Research Profile

Nabi’s reported scholarly profile comprises 36 documents, 173 citations, and an h-index of 6, with Computer Vision identified as her principal subject area. Her recent publications show particular involvement in deep-learning-based medical image segmentation, including architectural optimization of U-shaped networks and multi-scale feature processing. Her institutional affiliation is the University of the Punjab.[1] [2]

Research Contributions

Her recent collaborative contributions focus on improving how neural networks preserve and combine visual information during segmentation. The MDI-Net study investigates multilayer feature aggregation and decoder-guided interaction, while SDNAL-Seg introduces selective downsampling and non-adjacent layer guidance. Together, these works address representation quality, contextual fusion, and segmentation efficiency in medical imaging.[1] [2]

Publications

Nabi’s recent publication record includes research on medical image segmentation and computational modeling. In particular, she co-authored studies on feature aggregation in U-shaped segmentation models and SDNAL-Seg, a framework using multi-scale selective downsampling and non-adjacent layer guidance. She also co-authored research on nonlinear musculoskeletal modeling of human arm impedance.[1] [2] [3]

• Revisiting feature aggregation in U-shaped models for medical image segmentation — Computer Vision and Image Understanding, 272, 104924 (2026). DOI: 10.1016/j.cviu.2026.104924.[1]
• SDNAL-Seg: multi-scale selective downsampling and non-adjacent layers guidance for medical image segmentation — Signal, Image and Video Processing, 20, 408 (2026). DOI: 10.1007/s11760-026-05376-5.[2]
• Estimation of human arm impedance using a nonlinear musculoskeletal model for posture and movement control — Journal of Engineering Research, 14(2), 2529–2548 (2026). DOI: 10.1016/j.jer.2026.02.024.[3]

Research Impact

The available scholarly metrics indicate an established research presence, with 173 citations and an h-index of 6 across 36 reported documents. Her recent work addresses practical challenges in medical image segmentation, including feature distortion during downsampling and effective information exchange between network stages. Such methodological developments are relevant to automated biomedical image analysis.[1] [2]

Award Suitability

For the Innovative Research Award, Nabi’s profile presents relevant evidence through sustained publication activity, citation performance, and recent contributions to computer vision and medical image segmentation. Her collaborative research examines concrete architectural problems and proposes technically defined solutions, providing a scholarly basis for recognition within an award category emphasizing innovative computational research and emerging imaging methodologies.[1] [2]

Conclusion

Fizza Ghulam Nabi’s documented research activity reflects a developing profile in computer vision, particularly medical image segmentation and deep-learning architectures. Her recent co-authored publications address feature aggregation, selective downsampling, contextual guidance, and computational modeling. Combined with her reported bibliometric indicators, these contributions provide a reasonable scholarly foundation for consideration under the Innovative Research Award.[1] [2] [3]

External Links

• Orcid Profile
• Scopus Author Profile
• DOI — Human Arm Impedance Study
• Technology Scientists Awards

References

1. Shen, H., Li, S., Nabi, F. G., Davydov, M., Abbas, N., Wang, D., & Yang, G. (2026). Revisiting feature aggregation in U-shaped models for medical image segmentation. Computer Vision and Image Understanding, 272, 104924.
   https://doi.org/10.1016/j.cviu.2026.104924
2. Lin, Q., Li, G., Pan, X., Lin, Y., Nabi, F. G., Li, S., Yang, G., & Wu, Z. (2026). SDNAL-Seg: Multi-scale selective downsampling and non-adjacent layers guidance for medical image segmentation. Signal, Image and Video Processing, 20, 408.
   https://doi.org/10.1007/s11760-026-05376-5
3. Hafeez, M. A., Ghaffar, A., Nabi, F. G., Virk, U. S., Tahir, A., Sundaraj, K., & Yang, G. (2026). Estimation of human arm impedance using a nonlinear musculoskeletal model for posture and movement control. Journal of Engineering Research, 14(2), 2529–2548.
   https://doi.org/10.1016/j.jer.2026.02.024
4. Elsevier. (n.d.). Scopus author details: Fizza Ghulam Nabi, Author ID 57193326172. Scopus.
   https://www.scopus.com/authid/detail.uri?authorId=57193326172