YOLO as a Region Proposal Network for Diagnosing Breast Cancer

Bal, Ananya; Das, Meenakshi; Satapathy, Shashank Mouli

doi:10.1109/ghci50508.2021.9513988

Cited by 3 publications

(1 citation statement)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The study involved comprehensive benchmarking, training, and testing of these algorithms on diverse datasets to assess their performance. Among the evaluated algorithms, YOLOv2 and RetinaNet emerged as the best performers, showcasing superior results compared to YOLOv3 across multiple datasets [29]. The authors found YOLOv2 to be a best option for accurate and fast cell detection, even in challenging data scenarios.…”

Section: Autonomous Microscopes Through Object Detection Networkmentioning

confidence: 97%

Reviewing AI-enabled microscopes for diagnostic purposes

Afzal,

Noureen,

Mahmood

et al. 2024

Computational Optics 2024

View full text Add to dashboard Cite

Microscopes are an essential optical instrument for diagnostic purposes. Now, AI is included in these diagnostic processes with microscopes which has revolutionized this area of field. Diagnostic processes have become more accurate, efficient and less time consuming for pathologists and patients as well. This paper provides a detailed review of artificial intelligence (AI) enabled microscopy for diagnostic applications. Latest advancements in AI enabled microscopes are discussed, focusing on their applications in medical diagnostics. The review come up with a range of microscopy techniques and how AI algorithms help in real-time image analysis, recognition of abnormalities, and disease prediction. Moreover, challenges and opportunities associated with these smart microscopes are also determined. The purpose of this paper is to serve as a valuable resource for researchers, clinicians, and technologists who are working on AI-enabled microscope designs for diagnostic applications.

show abstract

Section: Autonomous Microscopes Through Object Detection Networkmentioning

confidence: 97%