Farah Deeba
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Farah Deeba has a total of 47 co-authors. Here are the top co-authors by number of shared publications:
Robert Rohling
Department of Electrical and Computer Engineering, University of British Columbia, Vancouver, BC, Canada
7 shared publicationsSeptimiu Salcudean
Department of Electrical and Computer Engineering, University of British Columbia, Vancouver, British Columbia, Canada
5 shared publicationsChantal Mayer
Department of Obstetrics and Gynecology, University of British Columbia, Vancouver, British Columbia, Canada
4 shared publicationsDenise Pugash
Department of Radiology, University of British Columbia, Vancouver, British Columbia, Canada
4 shared publicationsJefferson Terry
Department of Pathology and Laboratory Medicine, University of British Columbia, British Columbia, Canada
4 shared publicationsJennifer Hutcheon
Department of Obstetrics and Gynecology, University of British Columbia, Vancouver, British Columbia, Canada
3 shared publications
Latest Publications
- Open Access
- 25 June 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Deep transfer learning for detection of placenta-mediated diseases from ultrasound images
Placenta-mediated diseases, such as preeclampsia (PE) and small-for-gestational-age (SGA) neonates, are associated with structural and functional changes in the placenta. While ultrasound is routinely performed during pregnancy, its potential for detecting such diseases using deep learning remains underexplored. This study presents a deep transfer learning approach using Convolutional Neural Networks (CNNs) to detect placenta-mediated diseases from ultrasound B-mode images of the human placenta ex vivo. This study is a secondary analysis of data from a prospective case-control study, where placentas were collected from women who delivered at BC Women's Hospital, Vancouver, Canada, from April 2018 to April 2020. Ultrasound data obtained from ex vivo human placentas were used to perform transfer learning using three deep learning architectures: DenseNet-121, ResNet-50, and InceptionV3, each pretrained on one of two datasets: ImageNet or RadImageNet, to detect SGA and/or PE outcome. The dataset consisted of 46 placentas obtained from 40 participants, of which 25 placentas were complicated by SGA and/or PE (including 12 SGA-only placentas, 2 PE placentas, and 11 placentas affected by both SGA and PE). Experimental results demonstrate that DenseNet-121, when pretrained with ImageNet, achieved the most promising performance, with accuracy of 0.76 ± 0.12, F1-score of 0.78 ± 0.09, and area under the receiver operating characteristic curve (AUC) of 0.86 ± 0.10. Among the RadImageNet pretrained models, ResNet-50 yielded an accuracy 0.75 ± 0.10, F1-score 0.77 ± 0.07, and AUC of 0.84 ± 0.09. Our proof-of-concept results demonstrate that standard B-mode ultrasound images of the placenta ex vivo contain sufficient information to distinguish between normal pregnancies and pregnancies affected by SGA and PE.
- 25 June 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Open AccessDeep transfer learning for detection of placenta-mediated diseases from ultrasound images
Placenta-mediated diseases, such as preeclampsia (PE) and small-for-gestational-age (SGA) neonates, are associated with structural and functional changes in the placenta. While ultrasound is routinely performed during pregnancy, its potential for detecting such diseases using deep learning remains underexplored. This study presents a deep transfer learning approach using Convolutional Neural Networks (CNNs) to detect placenta-mediated diseases from ultrasound B-mode images of the human placenta ex vivo. This study is a secondary analysis of data from a prospective case-control study, where placentas were collected from women who delivered at BC Women's Hospital, Vancouver, Canada, from April 2018 to April 2020. Ultrasound data obtained from ex vivo human placentas were used to perform transfer learning using three deep learning architectures: DenseNet-121, ResNet-50, and InceptionV3, each pretrained on one of two datasets: ImageNet or RadImageNet, to detect SGA and/or PE outcome. The dataset consisted of 46 placentas obtained from 40 participants, of which 25 placentas were complicated by SGA and/or PE (including 12 SGA-only placentas, 2 PE placentas, and 11 placentas affected by both SGA and PE). Experimental results demonstrate that DenseNet-121, when pretrained with ImageNet, achieved the most promising performance, with accuracy of 0.76 ± 0.12, F1-score of 0.78 ± 0.09, and area under the receiver operating characteristic curve (AUC) of 0.86 ± 0.10. Among the RadImageNet pretrained models, ResNet-50 yielded an accuracy 0.75 ± 0.10, F1-score 0.77 ± 0.07, and AUC of 0.84 ± 0.09. Our proof-of-concept results demonstrate that standard B-mode ultrasound images of the placenta ex vivo contain sufficient information to distinguish between normal pregnancies and pregnancies affected by SGA and PE.
- Open Access
- 17 March 2026
- Published by Elsevier in Biomedical Signal Processing and Control
- Vol. 120
Frequency-dependent ultrasound attenuation estimation with spatial regularization and monotonicity constraints
- 17 March 2026
- Published by Elsevier in Biomedical Signal Processing and Control
- Vol. 120
Open AccessFrequency-dependent ultrasound attenuation estimation with spatial regularization and monotonicity constraints
- 15 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Ultrasonics
- Vol. 73 (2) , 138-152
Automated Placental ROI Selection for Quantitative Ultrasound Analysis Using Boundary-Aware Thresholding
Quantitative ultrasound (QUS) analysis of placental tissue holds significant promise for evaluating pregnancy health and detecting placental pathologies. However, widespread clinical adoption of QUS is limited by the need for manual selection of a proper region of interest (ROI) for the calculation, which increases the analysis time and introduces operator variability. This study presents an automated ROI determination method that uses deep learning segmentation directly on minimally processed raw RF data (along with corresponding B-mode data for comparison) to replace manual ROI selection in placental QUS analysis while also taking advantage of the model’s internal confidence thresholds to reduce inclusion of non-placental tissue near ambiguous tissue boundaries. Using a diverse, multi-national data set of 1084 annotated ultrasound images, the proposed automated ROI model achieved a mean Dice similarity coefficient (DSC) above 0.8 for confidence thresholds between 50% to 75%. At thresholds above 75%, precision improved, but both DSC and recall performance declined, and the amount of placental tissue identified for an accurate QUS calculation fell below the minimum required ROI size. Bland-Altman analysis showed tight agreement between the QUS values derived from ground truth ROIs and automated ROIs up to a 75% confidence threshold, but reduced agreement at higher thresholds, consistent with inferior performance obtained for placental pixel area below the minimum. These findings demonstrate both the feasibility of automated ROI determination and the need for careful consideration of the confidence thresholds when assessing model performance.
- 15 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Ultrasonics
- Vol. 73 (2) , 138-152
Automated Placental ROI Selection for Quantitative Ultrasound Analysis Using Boundary-Aware Thresholding
Quantitative ultrasound (QUS) analysis of placental tissue holds significant promise for evaluating pregnancy health and detecting placental pathologies. However, widespread clinical adoption of QUS is limited by the need for manual selection of a proper region of interest (ROI) for the calculation, which increases the analysis time and introduces operator variability. This study presents an automated ROI determination method that uses deep learning segmentation directly on minimally processed raw RF data (along with corresponding B-mode data for comparison) to replace manual ROI selection in placental QUS analysis while also taking advantage of the model’s internal confidence thresholds to reduce inclusion of non-placental tissue near ambiguous tissue boundaries. Using a diverse, multi-national data set of 1084 annotated ultrasound images, the proposed automated ROI model achieved a mean Dice similarity coefficient (DSC) above 0.8 for confidence thresholds between 50% to 75%. At thresholds above 75%, precision improved, but both DSC and recall performance declined, and the amount of placental tissue identified for an accurate QUS calculation fell below the minimum required ROI size. Bland-Altman analysis showed tight agreement between the QUS values derived from ground truth ROIs and automated ROIs up to a 75% confidence threshold, but reduced agreement at higher thresholds, consistent with inferior performance obtained for placental pixel area below the minimum. These findings demonstrate both the feasibility of automated ROI determination and the need for careful consideration of the confidence thresholds when assessing model performance.
- Open Access
- 27 September 2022
- Published by Elsevier in Ultrasound in Medicine & Biology
- Vol. 48 (12) , 2486-2501
SWAVE 2.0 Imaging of Placental Elasticity and Viscosity: Potential Biomarkers for Placenta-Mediated Disease Detection
- 27 September 2022
- Published by Elsevier in Ultrasound in Medicine & Biology
- Vol. 48 (12) , 2486-2501
Open AccessSWAVE 2.0 Imaging of Placental Elasticity and Viscosity: Potential Biomarkers for Placenta-Mediated Disease Detection
- Open Access
Project SWAVE 2.0: An overview of the study design for multimodal placental image acquisition and alignment
- Open Access
- 1 December 2021
- Published by Elsevier in Medical Image Analysis
- Vol. 74, 102245
A multiparametric volumetric quantitative ultrasound imaging technique for soft tissue characterization
- 1 December 2021
- Published by Elsevier in Medical Image Analysis
- Vol. 74, 102245
Open AccessA multiparametric volumetric quantitative ultrasound imaging technique for soft tissue characterization
- 29 October 2020
- Published by Taylor & Francis in Fusion Science and Technology
- Vol. 76 (8) , 947-956
Temporal Profiling of Electron Temperatures Using the Hα–Hβ Line Emission and Triple Langmuir Probe Array in the Pre-Ionization Discharge of the MT-I Spherical Tokamak
Photodiodes masked with narrow-band filters have been used to obtain the temporal profiles of Hα and Hβ line emissions in the pre-ionization phase of hydrogen discharge in the MT-I Spherical Tokamak. The line ratio method relating the emission intensities of the above mentioned lines, having different excitation thresholds, provides the temporal profile of electron temperature. A triple Langmuir probe array having three individual sets of triple probes, arranged linearly, has also been used to measure the temporal profile of electron temperature at three different radial positions simultaneously. Additionally, a spectrometer HR4000+ is used to get the line-integrated emission intensity of H-Balmer lines. The objective of this experiment is to demonstrate the successful development of the optical and electric probe as a diagnostic tool for tokamak discharge.
- 29 October 2020
- Published by Taylor & Francis in Fusion Science and Technology
- Vol. 76 (8) , 947-956
Temporal Profiling of Electron Temperatures Using the Hα–Hβ Line Emission and Triple Langmuir Probe Array in the Pre-Ionization Discharge of the MT-I Spherical Tokamak
Photodiodes masked with narrow-band filters have been used to obtain the temporal profiles of Hα and Hβ line emissions in the pre-ionization phase of hydrogen discharge in the MT-I Spherical Tokamak. The line ratio method relating the emission intensities of the above mentioned lines, having different excitation thresholds, provides the temporal profile of electron temperature. A triple Langmuir probe array having three individual sets of triple probes, arranged linearly, has also been used to measure the temporal profile of electron temperature at three different radial positions simultaneously. Additionally, a spectrometer HR4000+ is used to get the line-integrated emission intensity of H-Balmer lines. The objective of this experiment is to demonstrate the successful development of the optical and electric probe as a diagnostic tool for tokamak discharge.
- 1 January 2020
- Published by Elsevier in Biomedical Signal Processing and Control
- Vol. 55, 101530
Computer-aided polyp detection based on image enhancement and saliency-based selection
- 1 January 2020
- Published by Elsevier in Biomedical Signal Processing and Control
- Vol. 55, 101530
Computer-aided polyp detection based on image enhancement and saliency-based selection
- 1 November 2019
- Published by Pleiades Publishing Ltd in High Temperature
- Vol. 57 (6) , 821-831
Optical Emission and Langmuir Probe Diagnostic Measurements in DC Electrode Pulse Discharge in Nitrogen
Optical emission of selected nitrogen bands is analyzed for different nitrogen fill pressure and input electrical power to find the changes in spectral intensities with changing discharge conditions....
- 1 November 2019
- Published by Pleiades Publishing Ltd in High Temperature
- Vol. 57 (6) , 821-831
Optical Emission and Langmuir Probe Diagnostic Measurements in DC Electrode Pulse Discharge in Nitrogen
Optical emission of selected nitrogen bands is analyzed for different nitrogen fill pressure and input electrical power to find the changes in spectral intensities with changing discharge conditions....