Multi-spectral In-Vivo FPGA-Based Surgical Imaging

Alsharari, Majed; Niemitz, Lorenzo; Sørensen, Simon Toft; Woods, Roger; Burke, Ray; Engels, Stefan Andersson; Reaño, Carlos; T., Son

doi:10.1007/978-3-031-19983-7_8

Cited by 2 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In earlier work Alsharari et al (2022), these approaches were combined with existing image processing algorithms leading to the creation of an initial model that demonstrated reasonable prediction accuracy, low complexity, and small number of parameters compared to the SOTA models. This provided the basis for the initial work and platform to be able to explore embedded machine learning applications on FPGA, the focus of this work.…”

Section: Machine Learning Approachesmentioning

confidence: 99%

“…Finally, the Hessian matrix is constructed to find the two eigenvalues that corresponds to each pixel of the image. We have implemented the same approach here and the reference Alsharari et al (2022) provides more details of the functionality of these blocks.…”

Section: Image Processing Blocksmentioning

confidence: 99%

“…The team at Queen's University Belfast is engaged on a joint project with the Tyndall National Institute (TNI), Cork, Ireland, clinicians and medical device companies in the creation of an intelligent surgical system (ISS) comprising a custom CMOS image sensor and embedded processing unit on a 1 mm x 1 mm fibre Alsharari et al (2022). The aim is to offer improved surgical operation capability by providing better clinical guidance and accurate diagnostic information, by converting detected signals at the edge into clinical significant medical images in real-time.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Efficient Implementation of AI Algorithms on an FPGA-based System for Enhancing Blood Vessel Segmentation

Alsharari,

Mai,

Garnier

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

Machine learning offers the potential to enhance real-time image analysis in surgical operations. This paper presents results from the implementation of machine learning algorithms targeted for an intelligent image processing system comprising a custom CMOS image sensor and field programmable gate array (FPGA). A novel method is presented for efficient image segmentation and minimises energy usage and requires low memory resources, which makes it suitable for implementation. Using two eigenvalues of the enhanced Hessian image, simplified traditional machine learning and deep learning methods are employed to learn the prediction of blood vessels. Quantitative comparisons are provided between different machine learning models based on accuracy, resource utilisation, throughput, and power usage. It is shown how a gradient boosting decision tree with 1000 times fewer parameters can achieve comparable state-of-the-art performance whilst only using a much smaller proportion of the resources and producing a 200 MHz design that operates at 1,779 frames per second at 3.85 W, making it highly suitable for the proposed system. A methodology for implementing the AI algorithms onto FPGA is presented and then used to provide additional results by extending the original work to a 512 × 512 image size along with more detailed analysis.

show abstract

Section: Machine Learning Approachesmentioning

confidence: 99%

Section: Image Processing Blocksmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation