TY  - JOUR
AU  - Diwakar, Manoj
PY  - 2026
DA  - 2026/02/02
TI  - Saliency Object Detection-Based Medical Image Fusion: Future Directions for Smart Healthcare Systems
JO  - Biomedical Informatics and Smart Healthcare
T2  - Biomedical Informatics and Smart Healthcare
JF  - Biomedical Informatics and Smart Healthcare
VL  - 2
IS  - 1
SP  - 1
EP  - 4
DO  - 10.62762/BISH.2025.918243
UR  - https://www.icck.org/article/abs/BISH.2025.918243
KW  - medical image fusion
KW  - object detection
KW  - total variation
KW  - saliency features
AB  - Saliency Object Detection-Based Medical Image Fusion concentrates on the most prominent anatomical parts that naturally attract attention. The process begins with a two-step pipeline. First, it identifies the salient regions those structures most critical to a diagnostic decision. These highlighted areas are then fed into a guided-filtering framework. This work blends them with complementary information from a second imaging modality, such as CT and MRI. The method uses total variation regularization to suppress noise while preserving edges. A saliency-based weighting scheme ensures that every key detail is retained. The result is a single, high-quality image that carries the full diagnostic power of both inputs, providing physicians with a clearer, more informative view without sacrificing clinically relevant information.
SN  - 3068-5524
PB  - Institute of Central Computation and Knowledge
LA  - English
ER  - 

@article{Diwakar2026Saliency,
  author = {Manoj Diwakar},
  title = {Saliency Object Detection-Based Medical Image Fusion: Future Directions for Smart Healthcare Systems},
  journal = {Biomedical Informatics and Smart Healthcare},
  year = {2026},
  volume = {2},
  number = {1},
  pages = {1-4},
  doi = {10.62762/BISH.2025.918243},
  url = {https://www.icck.org/article/abs/BISH.2025.918243},
  abstract = {Saliency Object Detection-Based Medical Image Fusion concentrates on the most prominent anatomical parts that naturally attract attention. The process begins with a two-step pipeline. First, it identifies the salient regions those structures most critical to a diagnostic decision. These highlighted areas are then fed into a guided-filtering framework. This work blends them with complementary information from a second imaging modality, such as CT and MRI. The method uses total variation regularization to suppress noise while preserving edges. A saliency-based weighting scheme ensures that every key detail is retained. The result is a single, high-quality image that carries the full diagnostic power of both inputs, providing physicians with a clearer, more informative view without sacrificing clinically relevant information.},
  keywords = {medical image fusion, object detection, total variation, saliency features},
  issn = {3068-5524},
  publisher = {Institute of Central Computation and Knowledge}
}