Robin Dale
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Robin Dale has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
Hamid Dehghani
School of Computer Science Medical Imaging Lab University of Birmingham University Rd W B15 2TT Birmingham Birmingham UK
5 shared publications- Hamid Dehghani
University of Birmingham
3 shared publications Scott Howard
Department of Electrical Engineering and Bioengineering Program University of Notre Dame 275 Fitzpatrick Hall
3 shared publications- Scott Sheridan Howard
University of Notre Dame
3 shared publications - Thomas D. O'Sullivan
University of Notre Dame
3 shared publications - Felipe Orihuela-Espina
School of Computer Science, University of Birmingham, Birmingham, United Kingdom
2 shared publications
Latest Publications
- Open Access
- 26 March 2025
- Published by Optica Publishing Group in Biomedical Optics Express
- Vol. 16 (4) , 1582-1601
Towards real-time diffuse optical tomography with a handheld scanning probe
Diffuse optical tomography (DOT) performed using deep-learning allows high-speed reconstruction of tissue optical properties and could thereby enable image-guided scanning, e.g., to enhance clinical breast imaging. Previously published models are geometry-specific and, therefore, require extensive data generation and training for each use case, restricting the scanning protocol at the point of use. A transformer-based architecture is proposed to overcome these obstacles that encode spatially unstructured DOT measurements, enabling a single trained model to handle arbitrary scanning pathways and measurement density. The model is demonstrated with breast tissue-emulating simulated and phantom data, yielding - for 24 mm-deep absorptions (μ a ) and reduced scattering (μ s ′) images, respectively - average RMSEs of 0.0095±0.0023 cm−1 and 1.95±0.78 cm−1, Sørensen-Dice coefficients of 0.55±0.12 and 0.67±0.1, and anomaly contrast of 79±10% and 93.3±4.6% of the ground-truth contrast, with an effective imaging speed of 14 Hz. The average absolute μ a and μ s ′ values of homogeneous simulated examples were within 10% of the true values.
- 26 March 2025
- Published by Optica Publishing Group in Biomedical Optics Express
- Vol. 16 (4) , 1582-1601
Open AccessTowards real-time diffuse optical tomography with a handheld scanning probe
Diffuse optical tomography (DOT) performed using deep-learning allows high-speed reconstruction of tissue optical properties and could thereby enable image-guided scanning, e.g., to enhance clinical breast imaging. Previously published models are geometry-specific and, therefore, require extensive data generation and training for each use case, restricting the scanning protocol at the point of use. A transformer-based architecture is proposed to overcome these obstacles that encode spatially unstructured DOT measurements, enabling a single trained model to handle arbitrary scanning pathways and measurement density. The model is demonstrated with breast tissue-emulating simulated and phantom data, yielding - for 24 mm-deep absorptions (μ a ) and reduced scattering (μ s ′) images, respectively - average RMSEs of 0.0095±0.0023 cm−1 and 1.95±0.78 cm−1, Sørensen-Dice coefficients of 0.55±0.12 and 0.67±0.1, and anomaly contrast of 79±10% and 93.3±4.6% of the ground-truth contrast, with an effective imaging speed of 14 Hz. The average absolute μ a and μ s ′ values of homogeneous simulated examples were within 10% of the true values.
- Open Access
- 7 January 2025
- Published by Optica Publishing Group in Optica Open
Towards real-time diffuse optical tomography with a handheld scanning probe
Diffuse optical tomography (DOT) performed using deep-learning allows high-speed reconstruction of tissue optical properties, and could thereby enable image-guided scanning, e.g. to enhance clinical breast imaging. Previously published models are geometry specific, and therefore require extensive data generation and training for each use case, and restrict the scanning protocol at the point of use. To overcome these obstacles, a novel transformer-based architecture is proposed to encode spatially unstructured DOT measurements, enabling a single trained model to handle arbitrary scanning pathways and measurement density. The model is demonstrated with breast tissue-emulating simulated and phantom data, yielding - for 24 mm-deep absorption (μa) and reduced scattering (μs') images respectively - average RMSEs of 0.0095±0.0023 cm¯¹ and 1.95±0.78 cm¯¹, Sørensen-Dice coefficients of 0.55±0.12 and 0.67±0.1, and anomaly contrast of 79±10\% and 93.3±4.6% of the ground-truth contrast, with an effective imaging speed of 14 Hz. The average absolute μa and μs' values of homogeneous simulated examples were within 10% of the true values.
- 7 January 2025
- Published by Optica Publishing Group in Optica Open
Open AccessTowards real-time diffuse optical tomography with a handheld scanning probe
Diffuse optical tomography (DOT) performed using deep-learning allows high-speed reconstruction of tissue optical properties, and could thereby enable image-guided scanning, e.g. to enhance clinical breast imaging. Previously published models are geometry specific, and therefore require extensive data generation and training for each use case, and restrict the scanning protocol at the point of use. To overcome these obstacles, a novel transformer-based architecture is proposed to encode spatially unstructured DOT measurements, enabling a single trained model to handle arbitrary scanning pathways and measurement density. The model is demonstrated with breast tissue-emulating simulated and phantom data, yielding - for 24 mm-deep absorption (μa) and reduced scattering (μs') images respectively - average RMSEs of 0.0095±0.0023 cm¯¹ and 1.95±0.78 cm¯¹, Sørensen-Dice coefficients of 0.55±0.12 and 0.67±0.1, and anomaly contrast of 79±10\% and 93.3±4.6% of the ground-truth contrast, with an effective imaging speed of 14 Hz. The average absolute μa and μs' values of homogeneous simulated examples were within 10% of the true values.
- Open Access
- 7 January 2025
- Published by Optica Publishing Group in Optica Open
Towards real-time diffuse optical tomography with a handheld scanning probe
Diffuse optical tomography (DOT) performed using deep-learning allows high-speed reconstruction of tissue optical properties, and could thereby enable image-guided scanning, e.g. to enhance clinical breast imaging. Previously published models are geometry specific, and therefore require extensive data generation and training for each use case, and restrict the scanning protocol at the point of use. To overcome these obstacles, a novel transformer-based architecture is proposed to encode spatially unstructured DOT measurements, enabling a single trained model to handle arbitrary scanning pathways and measurement density. The model is demonstrated with breast tissue-emulating simulated and phantom data, yielding - for 24 mm-deep absorption (μa) and reduced scattering (μs') images respectively - average RMSEs of 0.0095±0.0023 cm¯¹ and 1.95±0.78 cm¯¹, Sørensen-Dice coefficients of 0.55±0.12 and 0.67±0.1, and anomaly contrast of 79±10\% and 93.3±4.6% of the ground-truth contrast, with an effective imaging speed of 14 Hz. The average absolute μa and μs' values of homogeneous simulated examples were within 10% of the true values.
- 7 January 2025
- Published by Optica Publishing Group in Optica Open
Open AccessTowards real-time diffuse optical tomography with a handheld scanning probe
Diffuse optical tomography (DOT) performed using deep-learning allows high-speed reconstruction of tissue optical properties, and could thereby enable image-guided scanning, e.g. to enhance clinical breast imaging. Previously published models are geometry specific, and therefore require extensive data generation and training for each use case, and restrict the scanning protocol at the point of use. To overcome these obstacles, a novel transformer-based architecture is proposed to encode spatially unstructured DOT measurements, enabling a single trained model to handle arbitrary scanning pathways and measurement density. The model is demonstrated with breast tissue-emulating simulated and phantom data, yielding - for 24 mm-deep absorption (μa) and reduced scattering (μs') images respectively - average RMSEs of 0.0095±0.0023 cm¯¹ and 1.95±0.78 cm¯¹, Sørensen-Dice coefficients of 0.55±0.12 and 0.67±0.1, and anomaly contrast of 79±10\% and 93.3±4.6% of the ground-truth contrast, with an effective imaging speed of 14 Hz. The average absolute μa and μs' values of homogeneous simulated examples were within 10% of the true values.
- 1 January 2025
- Published by Optica Publishing Group
- p. W5B.4
Transformer-Encoder for Real-Time DOT Scanning
Deep-Learning based Diffuse Optical Tomography enables real-time clinical breast imaging, but current models are scanning-pathway-specific. Here, a transformer architecture is proposed to encode arbitrary scanning pathways, enabling flexible real-time imaging with a single trained model.
- 1 January 2025
- Published by Optica Publishing Group
- p. W5B.4
Transformer-Encoder for Real-Time DOT Scanning
Deep-Learning based Diffuse Optical Tomography enables real-time clinical breast imaging, but current models are scanning-pathway-specific. Here, a transformer architecture is proposed to encode arbitrary scanning pathways, enabling flexible real-time imaging with a single trained model.
- Open Access
- 1 July 2024
- Published by SPIE-Intl Soc Optical Eng in Journal of Biomedical Optics
- Vol. 29 (07) , 076004-21
Deep learning-enabled high-speed, multi-parameter diffuse optical tomography
Diffuse optical tomography (DOT) is a safe and non-invasive medical imaging technique in which near-infrared (NIR) light (600 to 1000 nm) is transmitted between an array of sources and detectors positioned on the surface of the body and the properties of the measured light are used to reconstruct images of the optical properties of the intervening tissue. DOT has been successfully applied in numerous research areas requiring characterization of tissue composition and metabolism, including neuroimaging1,2 and musculoskeletal3 imaging, and has been proposed as an alternative or complementary technique to X-ray mammography for clinical breast imaging.4 Specifically, as the spectral attenuation of NIR light is strongly dependent on tissue physiology, DOT-measured biomarkers can be used to detect tumors,5 distinguish malignant tumors from benign tumors,6,7 and predict individual responses to neoadjuvant chemotherapy,8 without exposing the patient to ionizing radiation.
- 1 July 2024
- Published by SPIE-Intl Soc Optical Eng in Journal of Biomedical Optics
- Vol. 29 (07) , 076004-21
Open AccessDeep learning-enabled high-speed, multi-parameter diffuse optical tomography
Diffuse optical tomography (DOT) is a safe and non-invasive medical imaging technique in which near-infrared (NIR) light (600 to 1000 nm) is transmitted between an array of sources and detectors positioned on the surface of the body and the properties of the measured light are used to reconstruct images of the optical properties of the intervening tissue. DOT has been successfully applied in numerous research areas requiring characterization of tissue composition and metabolism, including neuroimaging1,2 and musculoskeletal3 imaging, and has been proposed as an alternative or complementary technique to X-ray mammography for clinical breast imaging.4 Specifically, as the spectral attenuation of NIR light is strongly dependent on tissue physiology, DOT-measured biomarkers can be used to detect tumors,5 distinguish malignant tumors from benign tumors,6,7 and predict individual responses to neoadjuvant chemotherapy,8 without exposing the patient to ionizing radiation.
- 1 January 2024
- Published by Optica Publishing Group
- p. OS3D.6
Experimental validation of multi-parameter diffuse optical tomography using deep-learning
This study presents experimental validation of a deep-learning (DL) model for simultaneous 3D reconstruction of absolute absorption and reduced scattering. The model improved structural similarity and contrast, but increased cross-talk compared to an analytical algorithm.
- 1 January 2024
- Published by Optica Publishing Group
- p. OS3D.6
Experimental validation of multi-parameter diffuse optical tomography using deep-learning
This study presents experimental validation of a deep-learning (DL) model for simultaneous 3D reconstruction of absolute absorption and reduced scattering. The model improved structural similarity and contrast, but increased cross-talk compared to an analytical algorithm.
- 1 January 2024
- Published by Optica Publishing Group
- p. JM4A.28
FREEnet: a dynamic deep-learning model for freehand diffuse optical tomography
A deep-learning (DL) model for handheld diffuse optical tomography is presented. The fully convolutional network can reconstruct 3D absorption and scattering from arbitrarily undersampled scan data at a rate of 18.5Hz, enabling real-time imaging.
- 1 January 2024
- Published by Optica Publishing Group
- p. JM4A.28
FREEnet: a dynamic deep-learning model for freehand diffuse optical tomography
A deep-learning (DL) model for handheld diffuse optical tomography is presented. The fully convolutional network can reconstruct 3D absorption and scattering from arbitrarily undersampled scan data at a rate of 18.5Hz, enabling real-time imaging.
- Open Access
- 16 March 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of Engineering in Medicine and Biology
- Vol. 4, 85-95
System Derived Spatial-Temporal CNN for High-Density fNIRS BCI
An intuitive and generalisable approach to spatial-temporal feature extraction for high-density (HD) functional Near-Infrared Spectroscopy (fNIRS) brain-computer interface (BCI) is proposed, demonstrated here using Frequency-Domain (FD) fNIRS for motor-task classification. Enabled by the HD probe design, layered topographical maps of Oxy/deOxy Haemoglobin changes are used to train a 3D convolutional neural network (CNN), enabling simultaneous extraction of spatial and temporal features. The proposed spatial-temporal CNN is shown to effectively exploit the spatial relationships in HD fNIRS measurements to improve the classification of the functional haemodynamic response, achieving an average F1 score of 0.69 across seven subjects in a mixed subjects training scheme, and improving subject-independent classification as compared to a standard temporal CNN.
- 16 March 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of Engineering in Medicine and Biology
- Vol. 4, 85-95
Open AccessSystem Derived Spatial-Temporal CNN for High-Density fNIRS BCI
An intuitive and generalisable approach to spatial-temporal feature extraction for high-density (HD) functional Near-Infrared Spectroscopy (fNIRS) brain-computer interface (BCI) is proposed, demonstrated here using Frequency-Domain (FD) fNIRS for motor-task classification. Enabled by the HD probe design, layered topographical maps of Oxy/deOxy Haemoglobin changes are used to train a 3D convolutional neural network (CNN), enabling simultaneous extraction of spatial and temporal features. The proposed spatial-temporal CNN is shown to effectively exploit the spatial relationships in HD fNIRS measurements to improve the classification of the functional haemodynamic response, achieving an average F1 score of 0.69 across seven subjects in a mixed subjects training scheme, and improving subject-independent classification as compared to a standard temporal CNN.