Phidakordor Sahshong
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Phidakordor Sahshong has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Manish Bhatt
Department of Electronics and Electrical Engineering, Indian Institute of Technology Guwahati, Assam, India
5 shared publications - Anusua Das
Department of Electronics and Electrical Engineering, Indian Institute of Technology Guwahati, Assam, India
3 shared publications - Akash Chandra
Department of Biological Sciences and Engineering, Indian Institute of Technology Gandhinagar, Gujarat, India
2 shared publications - Guy Cloutier
University of Montreal
2 shared publications - Karla Patricia Mercado- Shekhar
Department of Biological Sciences and Engineering, Indian Institute of Technology Gandhinagar, Gujarat, India
2 shared publications - Amit Nagora
Department of Electronics and Electrical Engineering, Indian Institute of Technology Guwahati, Assam, India
1 shared publication
Latest Publications
- 16 April 2026
- Published by AIP Publishing in Biophysics Reviews
- Vol. 7 (2)
Viscoelasticity image reconstruction in shear wave elastography: Methods, challenges, and current developments
Ultrasound shear wave elastography (SWE) is a noninvasive technique for characterizing the mechanical properties of soft tissues. Although early SWE methods assumed purely elastic behavior, most biological tissues are now recognized as viscoelastic, motivating the development of advanced reconstruction strategies. Existing approaches to viscoelastic imaging include physics-based modeling, inverse problem formulations, and numerical methods for estimating elasticity, viscosity, and frequency-dependent moduli. More recently, deep learning, particularly hybrid frameworks that incorporate biomechanical priors with data-driven models trained on synthetic and clinical data, has emerged as a promising direction for SWE reconstruction. Challenges remain in noise sensitivity, modeling assumptions, computational cost, and cross-platform standardization. Addressing these limitations is essential for translating viscoelastic biomarkers into routine clinical practice. These developments position SWE to evolve beyond stiffness mapping toward comprehensive viscoelastic biomarkers, with the potential to improve disease characterization, monitoring, and clinical decision-making.
- 16 April 2026
- Published by AIP Publishing in Biophysics Reviews
- Vol. 7 (2)
Viscoelasticity image reconstruction in shear wave elastography: Methods, challenges, and current developments
Ultrasound shear wave elastography (SWE) is a noninvasive technique for characterizing the mechanical properties of soft tissues. Although early SWE methods assumed purely elastic behavior, most biological tissues are now recognized as viscoelastic, motivating the development of advanced reconstruction strategies. Existing approaches to viscoelastic imaging include physics-based modeling, inverse problem formulations, and numerical methods for estimating elasticity, viscosity, and frequency-dependent moduli. More recently, deep learning, particularly hybrid frameworks that incorporate biomechanical priors with data-driven models trained on synthetic and clinical data, has emerged as a promising direction for SWE reconstruction. Challenges remain in noise sensitivity, modeling assumptions, computational cost, and cross-platform standardization. Addressing these limitations is essential for translating viscoelastic biomarkers into routine clinical practice. These developments position SWE to evolve beyond stiffness mapping toward comprehensive viscoelastic biomarkers, with the potential to improve disease characterization, monitoring, and clinical decision-making.
- 5 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Ultrasonics
- Vol. 73 (2) , 112-123
Multitask Learning Framework for Elasticity and Viscosity Image Reconstruction in Ultrasound Viscoelastography
Soft tissues are viscoelastic in nature, and shear wave viscoelastography has emerged as an effective tool for differentiating healthy and diseased tissues by assessing their viscoelastic properties. This study presents a noise-aware multitask deep learning framework that simultaneously reconstructs tissue elasticity and viscosity maps. The proposed unified model directly estimates viscoelastic parameters from noisy shear-wave data, eliminating the need for explicit shear wave attenuation measurements and improving robustness to noise. The framework was trained on 1,000 velocity field datasets generated from numerical simulations, and validated across numerical simulations, tissue-mimicking phantoms, and in vivo duck liver datasets. Results demonstrated high fidelity in reconstruction accuracy, with strong agreement with ground truth in simulations and phantoms. In simulated phantoms where ground truth was available, the root mean square error for viscosity across samples was 0.128 (95% CI: 0.105–0.150) and for elasticity was 2.363 (95% CI: 2.157–2.573), and the structural similarity index was more than 0.96. In four in vivo duck liver datasets, elasticity values ranged from 11.50 ± 6.32 to 25.50 ± 17.16 kPa and viscosity ranged from 0.85 ± 0.46 to 1.8 ± 0.37 Pa·s. The denoising module improved the signal-to-noise ratio up to threefold and enabled reliable performance even in low-SNR conditions. The framework enables rapid, noninvasive viscoelastic imaging and establishes a foundation for future diagnostic tools that go beyond stiffness-based assessments.
- 5 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Ultrasonics
- Vol. 73 (2) , 112-123
Multitask Learning Framework for Elasticity and Viscosity Image Reconstruction in Ultrasound Viscoelastography
Soft tissues are viscoelastic in nature, and shear wave viscoelastography has emerged as an effective tool for differentiating healthy and diseased tissues by assessing their viscoelastic properties. This study presents a noise-aware multitask deep learning framework that simultaneously reconstructs tissue elasticity and viscosity maps. The proposed unified model directly estimates viscoelastic parameters from noisy shear-wave data, eliminating the need for explicit shear wave attenuation measurements and improving robustness to noise. The framework was trained on 1,000 velocity field datasets generated from numerical simulations, and validated across numerical simulations, tissue-mimicking phantoms, and in vivo duck liver datasets. Results demonstrated high fidelity in reconstruction accuracy, with strong agreement with ground truth in simulations and phantoms. In simulated phantoms where ground truth was available, the root mean square error for viscosity across samples was 0.128 (95% CI: 0.105–0.150) and for elasticity was 2.363 (95% CI: 2.157–2.573), and the structural similarity index was more than 0.96. In four in vivo duck liver datasets, elasticity values ranged from 11.50 ± 6.32 to 25.50 ± 17.16 kPa and viscosity ranged from 0.85 ± 0.46 to 1.8 ± 0.37 Pa·s. The denoising module improved the signal-to-noise ratio up to threefold and enabled reliable performance even in low-SNR conditions. The framework enables rapid, noninvasive viscoelastic imaging and establishes a foundation for future diagnostic tools that go beyond stiffness-based assessments.
- Open Access
- 29 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. PP, 1
Deep Parenchymal Steatosis Assessment and Quantification in Histopathology
Manual annotation of liver biopsies is time-consuming, prone to human error, and suffers from high inter-observer variability. Automated algorithms for classifying metabolic dysfunction-associated steatohepatitis (MASH) in liver transplants can improve accuracy, speed, and consistency in diagnosing hepatic steatosis. This study presents a hybrid approach that combines image processing, machine learning, and deep learning for steatosis classification, leveraging state-of-the-art segmentation models. The first step involves deep learning based segmentation models to obtain histological tissue detection. Next, Gabor kernels are applied, followed by an adaptive color deconvolution to separate hematoxylin and eosin channels, along with the Macenko method for extended steatosis detection. Then, the macrosteatosis quantification is done using various segmentation models. Microsteatosis cleaning is performed to reject false positives in microsteatosis with techniques such as logistic regression, one-class SVM, and Isolation Forest. The algorithm is developed and tested on 385 H&E-stained liver images obtained from 77 donors. It demonstrated improved performance in both tissue and steatosis detection, showing an overall accuracy of 0.54% higher and a remarkable 5.03% increase in F1 score as compared to the state-of-the-art HEPASS algorithm. The performance of the proposed model on another public dataset shows an improvement of over 3% in accuracy across all the sets.
- 29 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. PP, 1
Open AccessDeep Parenchymal Steatosis Assessment and Quantification in Histopathology
Manual annotation of liver biopsies is time-consuming, prone to human error, and suffers from high inter-observer variability. Automated algorithms for classifying metabolic dysfunction-associated steatohepatitis (MASH) in liver transplants can improve accuracy, speed, and consistency in diagnosing hepatic steatosis. This study presents a hybrid approach that combines image processing, machine learning, and deep learning for steatosis classification, leveraging state-of-the-art segmentation models. The first step involves deep learning based segmentation models to obtain histological tissue detection. Next, Gabor kernels are applied, followed by an adaptive color deconvolution to separate hematoxylin and eosin channels, along with the Macenko method for extended steatosis detection. Then, the macrosteatosis quantification is done using various segmentation models. Microsteatosis cleaning is performed to reject false positives in microsteatosis with techniques such as logistic regression, one-class SVM, and Isolation Forest. The algorithm is developed and tested on 385 H&E-stained liver images obtained from 77 donors. It demonstrated improved performance in both tissue and steatosis detection, showing an overall accuracy of 0.54% higher and a remarkable 5.03% increase in F1 score as compared to the state-of-the-art HEPASS algorithm. The performance of the proposed model on another public dataset shows an improvement of over 3% in accuracy across all the sets.
- 4 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-10
Modified Power Law Dispersion Model for Shear Waves in Soft Tissues
Biological tissues display frequency-dependent non-linear dispersion in shear wave dispersion imaging. The dispersive behavior is due to the viscosity of soft tissues and may be correlated with tissue pathology. This study presents an empirically modified power law dispersion model that incorporates tissue nonlinearity and improves the dispersion modeling in shear wave elastography across an extended frequency bandwidth. The model was validated using numerically simulated phantoms, synthetic phantoms, and ex vivo goat muscle and liver tissues. The results demonstrate a higher goodness of fit compared to conventional models, including the Kelvin–Voigt, linear, and power-law dispersion models. Shear wave phase velocity, dispersion, and concavity maps are reconstructed in phantoms and ex vivo tissue samples. Quantitative values of dispersion are obtained as 1.55 ± 0.67 m/s/100 Hz and 1.68 ± 0.38 m/s/100 Hz in CIRS and PVA phantoms, respectively, and 3.16 ± 0.89 m/s/100 Hz and 1.44 ± 0.58 m/s/100 Hz in ex vivo goat muscle and liver tissues, respectively. The corresponding values of concavity are 4.12±2.11 m/s/kHz and 4.11±0.92 m/s/kHz in CIRS and PVA phantoms, respectively, and 6.52±2.71 m/s/kHz and 3.53±1.72 m/s/kHz in ex vivo goat muscle and liver tissues, respectively.
- 4 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-10
Modified Power Law Dispersion Model for Shear Waves in Soft Tissues
Biological tissues display frequency-dependent non-linear dispersion in shear wave dispersion imaging. The dispersive behavior is due to the viscosity of soft tissues and may be correlated with tissue pathology. This study presents an empirically modified power law dispersion model that incorporates tissue nonlinearity and improves the dispersion modeling in shear wave elastography across an extended frequency bandwidth. The model was validated using numerically simulated phantoms, synthetic phantoms, and ex vivo goat muscle and liver tissues. The results demonstrate a higher goodness of fit compared to conventional models, including the Kelvin–Voigt, linear, and power-law dispersion models. Shear wave phase velocity, dispersion, and concavity maps are reconstructed in phantoms and ex vivo tissue samples. Quantitative values of dispersion are obtained as 1.55 ± 0.67 m/s/100 Hz and 1.68 ± 0.38 m/s/100 Hz in CIRS and PVA phantoms, respectively, and 3.16 ± 0.89 m/s/100 Hz and 1.44 ± 0.58 m/s/100 Hz in ex vivo goat muscle and liver tissues, respectively. The corresponding values of concavity are 4.12±2.11 m/s/kHz and 4.11±0.92 m/s/kHz in CIRS and PVA phantoms, respectively, and 6.52±2.71 m/s/kHz and 3.53±1.72 m/s/kHz in ex vivo goat muscle and liver tissues, respectively.