Dr. Bruno De Santi Profile

Dr. Bruno De Santi

SPIE Involvement:

Author

Area of Expertise:

image processing , image registration , photoacoustic imaging , deep learning

Websites:

Company Website | Personal Website

Bruno De Santi (Ph.D.) earned his master degree in Biomedical Engineering in the Polytechnic University of Turin, Turin, Italy. During his Ph.D. he developed interest in designing and implementing algorithms for multimodal image processing and image registration. His current research primarily focuses in developing deep learning-based solutions applied to breast photoacoustic imaging for image registration, motion compensation and image denoising, with the ultimate objective of clinically translating the Twente Photoacoustic Mammoscope 3 (PAM3).

Proceedings Article | 12 March 2024 Presentation + Paper

Using denoising diffusion probabilistic models to enhance quality of limited-view photoacoustic tomography

Bruno De Santi, Navchetan Awasthi, Srirang Manohar

Proceedings Volume 12842, 1284206 (2024) https://doi.org/10.1117/12.3001616

KEYWORDS: Data modeling, Diffusion, Image restoration, Image processing, Education and training, Denoising, Image quality, Acquisition tracking and pointing, Sensors, Photoacoustic tomography

Read Abstract +

SPIE Journal Paper | 13 January 2024 Open Access

Automated three-dimensional image registration for longitudinal photoacoustic imaging

Bruno De Santi, Lucia Kim, Rianne F. G. Bulthuis, Felix Lucka, Srirang Manohar

JBO, Vol. 29, Issue S1, S11515, (January 2024) https://doi.org/10.1117/12.10.1117/1.JBO.29.S1.S11515

KEYWORDS: Image registration, Breast, Acquisition tracking and pointing, 3D image processing, Deformation, Biological imaging, Neural networks, Education and training, Tunable filters, Imaging systems

Read Abstract +

SignificancePhotoacoustic tomography (PAT) has great potential in monitoring disease progression and treatment response in breast cancer. However, due to variations in breast repositioning, there is a chance of geometric misalignment between images. Further, poor repositioning can affect light fluence distribution and imaging field-of-view, making images different from one another. The net effect is that it becomes challenging to distinguish between image changes due to repositioning effects and those due to true biological variations.AimThe aim is to develop a three-dimensional image registration framework for geometrically aligning repeated PAT volumetric images, which are potentially affected by repositioning effects such as misalignment, changed radiant exposure conditions, and different fields-of-view.ApproachThe proposed framework involves the use of a coordinate-based neural network to represent the displacement field between pairs of PAT volumetric images. A loss function based on normalized cross correlation and Frangi vesselness feature extraction at multiple scales was implemented. We refer to our image registration framework as MUVINN-reg, which stands for multiscale vesselness-based image registration using neural networks. The approach was tested on a longitudinal dataset of healthy volunteer breast PAT images acquired with the hybrid photoacoustic-ultrasound Photoacoustic Mammoscope 3 imaging system. The registration performance was also tested under unfavorable repositioning conditions such as intentional mispositioning, and variation in breast-supporting cup size between measurements.ResultsA total of 13 pairs of repeated PAT scans were included in this study. MUVINN-reg showed excellent performance in co-registering each pair of images. The proposed framework was shown to be robust to image intensity shifts and field-of-view changes. Furthermore, MUVINN-reg could align vessels at imaging depths greater than 4 cm.ConclusionsThe proposed framework will enable the use of PAT for quantitative and reproducible monitoring of disease progression and treatment response.

DOWNLOAD PAPER

Proceedings Article | 27 March 2023 Poster

Improving quality of less-view breast photoacoustic tomography reconstruction using deep learning neural networks

Bruno De Santi, Fazael Ayatollahi, Felix Lucka, Navchetan Awasthi, Ben Cox, Srirang Manohar

Proceedings Volume PC12379, PC123793G (2023) https://doi.org/10.1117/12.2650604

KEYWORDS: Photoacoustic tomography, Neural networks, Breast, Ultrasonics, Transducers, Image quality, Data acquisition, Acquisition tracking and pointing, Photoacoustic spectroscopy, Image resolution

Read Abstract +

Proceedings Article | 27 March 2023 Poster

An automatic image registration algorithm to align serial photoacoustic images: a step toward repeatable longitudinal imaging

Bruno De Santi, Lucia Kim, Rianne Bulthuis, Felix Lucka, Ben Cox, Srirang Manohar

Proceedings Volume PC12379, PC1237938 (2023) https://doi.org/10.1117/12.2650407

KEYWORDS: Image registration, Photoacoustic spectroscopy, Breast, Tissue optics, Photoacoustic imaging, Oxygen, Multispectral imaging, Breast cancer, Tumors, Surgery

Read Abstract +

Keywords/Phrases

Search In:

Publication Years