Downloads
Mobile android reconstruction in PACT:
1. Mobile reconstruction of circular PACT data
For the first time, PACT data was reconstructed on an android mobile phone. This opens up opportunities for portable photoacoustic imaging system development and data processing on a mobile device. Current reconstruction time is around ~2.5 seconds on a flagship android phone. Further improvements can be done in the future.
Reference Related to android recon work (Citation appreciated):
1. X. Hui, P. Rajendran, M. A. I. Zulkifli, T. Ling, and M. Pramanik, “Android mobile-platform-based image reconstruction for photoacoustic tomography,” Journal of Biomedical Optics 28(4), 046009 (2023).
Download:
The source code (python) of the android recon is available at Github code and the dataset used can be downloaded from Open Science Framework (OSF): data
Deep Learning in PAT:
1. Ultrasound-guided needle tracking with photoacoustic ground truth trained deep learning
A novel aproach to improve the ultrasound-guided needle tracking with deep learning trained with photoacoustic ground truth is proposed. The trained model (UIU-Net) is then applied on real clinical ultrasound images to visualize the needle with better precision and location tracking.
Reference Related to UIU-Net network (Citation appreciated):
1. X. Hui, P. Rajendran, T. Ling, X. Dai, L. Xing, and M. Pramanik, “Ultrasound-guided needle tracking with deep learning: A novel approach with photoacoustic ground truth,” Photoacoustics 34, 100575 (2023).
Download:
The source code (python) of the HD-UNet is available at Github code and the dataset used can be downloaded from Open Science Framework (OSF): data
2. Deep learning aided high frame rate (~3 Hz) circular PAT
A novel CNN-based deep learning architecture termed dense hybrid dense UNet (HD-UNet) has been applied to improve the frame rate by reconstructing high-quality PAT images from the data acquired at higher scanning speeds. The trained model is then applied on simulated and experimental data.
Reference Related to HD-UNet network (Citation appreciated):
1. P. Rajendran, and M. Pramanik, “High frame rate (~3 Hz) circular photoacoustic tomography using single-element ultrasound transducer aided with deep learning,” Journal of Biomedical Optics 27(6), 066005 (2022).
Download:
The source code (python) of the HD-UNet is available at Github code and the dataset used can be downloaded from Open Science Framework (OSF): data
3. Deep learning based multi-transducer PAT without radius calibration (RACOR-PAT)
A convolutional neural network (fully dense U-Net) aided with a convolutional long short-term memory (LSTM) block was for the reconstruction of PAT images. The trained model is then applied on simulated and experimental data.
Reference Related to TARES network (Citation appreciated):
1. P. Rajendran, and M. Pramanik, “Deep learning based multi-transducer photoacoustic tomography imaging without radius calibration,” Optics Letters 46(18), 4510-4513 (2022).
Download:
The source code (python) of the RACOR-PAT networked employed is available at Github code and the dataset used can be downloaded from Open Science Framework (OSF): data
4. Deep learning to improve the tangential resolution in PAT (TARES network)
A modified fully dense U-Net based architecture was trained on circular scan PAT images. The trained model is then applied on simulated and experimental data.
Reference Related to TARES network (Citation appreciated):
1. P. Rajendran, and M. Pramanik, “Deep learning approach to improve tangential resolution in photoacoustic tomography,” Biomedical Optics Express 11(12), 7311-7323 (2020).
Download:
The source code (python) of the TARES network employed is available at Github code and the datasets used can be downloaded from Open Science Framework (OSF): data
Deep Learning in ARPAM:
Convolution neural network for resolution enhancement and noise reduction in ARPAM
A modified fully dense U-Net based architecture was trained on simulated AR-PAM images. The trained model is then applied on simulated and experimental data.
Reference Related to resolution enhancement in ARPAM (Citation appreciated):
1. A. Sharma, and M. Pramanik, “Convolution neural network for resolution enhancement and noise reduction in acoustic resolution photoacoustic microscopy,” Biomedical Optics Express 11(12), 6826-6839 (2020).
Download:
The source code (python) of the network employed is available at Github code and the datasets used can be downloaded from Open Science Framework (OSF): data
MCEO_OCT:
Monte Carlo Simulation of optical coherence tomography in multilayered tissue with Embedded objects (MCEO_OCT)
We assume that the user is well versed with the original MCML, and MCML-EO code. If not, we recommend them to first go through the original MCML and MCML-EO codes and relevant support document to understand how the monte carlo modelling is done for light transport in multi-layered tissues with embedded objects. The MCML-EO code with support files are available on our website below (MCML-EO).
We have modified the MCML-EO code to incorporate the improved Importance Sampling method to simulate the light propagation for optical coherence tomography.
Reference Related to MCEO_OCT Simulation Package (Citation appreciated):
1. V. Periyasamy and M. Pramanik, "Importance sampling-based Monte Carlo simulation of time-domain optical coherence tomography with embedded objects," Applied Optics 55(11), 2921-2929 (2016).
2. V. Periyasamy and M. Pramanik, "Monte Carlo simulation of light transport in turbid medium with embedded object - spherical, cylindrical, ellipsoidal, or cuboidal object embedded within multilayered tissues," Journal of Biomedical Optics 19(4), 045003 (2014).
3. L.-H. Wang, S. L. Jacques, and L.-Q. Zheng, "MCML - Monte Carlo modeling of photon transport in multi-layered tissues," Computer Methods and Programs in Biomedicine 47, 131-146 (1995).
4. I. T. Lima, A. Kalra, H. E. Hernández-Figueroa, and S. S. Sherif, "Fast calculation of multipath diffusive reflectance in optical coherence tomography," Biomedical Optics Express 3(4), 692-700 (2012).
Download:
User Manual in PDF format
MCML-EO:
Monte Carlo Simulation for Light Transport in Multilayered Tissue with Embedded Objects (MCML-EO)
We assume that the user is well versed with the original MCML code. If not, we recommend them to first go through the original MCML code and relevant support document to understand how the monte carlo modelling is done for light transport in multi-layered tissues. The original MCML code with support files is available on Dr. Lihong Wang’s website (Original MCML).
We have modified the original MCML code to incorporate an embedded object (spherical, cylindrical, ellipsoidal, or cuboidal) in one of the layers. The reflection/transmission at the object and the surrounding tissue due to refractive index mismatch is also taken into consideration.
Reference Related to MCML-EO Simulation Package (Citation appreciated):
1. V. Periyasamy and M. Pramanik, "Monte Carlo simulation of light transport in turbid medium with embedded object - spherical, cylindrical, ellipsoidal, or cuboidal object embedded within multilayered tissues," Journal of Biomedical Optics 19(4), 045003 (2014).
2. V. Periyasamy and M. Pramanik, "Monte Carlo simulation of light transport in tissue for optimizing light delivery in photoacoustic imaging of the sentinel lymph node," Journal of Biomedical Optics 18(10), 106008 (2013).
3. L.-H. Wang, S. L. Jacques, and L.-Q. Zheng, "MCML - Monte Carlo modeling of photon transport in multi-layered tissues," Computer Methods and Programs in Biomedicine 47, 131-146 (1995).
Download:
User Manual in PDF format
RMCC:
Raman Monte Carlo of Cuboid (RMCC)
We assume that the user is well versed with the original MCML code. If not, we recommend them to first go through the original MCML code and relevant support document to understand how the monte carlo modelling is done for light transport in multi-layered tissues. The original MCML code with support files is available on Dr. Lihong Wang’s website (Original MCML).
We have modified the original MCML code to incorporate an embedded object (cuboidal) in one of the layers. Check our MCML-EO section on the top, if you need for information. Later, we modified the code to incorporate the Raman scattering.
Reference Related to RMCC Simulation Package (Citation appreciated):
1. V. Periyasamy, S. Sil, G. Dhal, F. Ariese, S. Umapathy, and M. Pramanik, "Experimentally validated Raman Monte Carlo simulation for a cuboid object to obtain Raman Spectroscopic signature for hiden material," Journal of Raman Spectroscopy 46(7), 669-676 (2015).
2. V. Periyasamy and M. Pramanik, "Monte Carlo simulation of light transport in turbid medium with embedded object - spherical, cylindrical, ellipsoidal, or cuboidal object embedded within multilayered tissues," Journal of Biomedical Optics 19(4), 045003 (2014).
3. L.-H. Wang, S. L. Jacques, and L.-Q. Zheng, "MCML - Monte Carlo modeling of photon transport in multi-layered tissues," Computer Methods and Programs in Biomedicine 47, 131-146 (1995).
Download:
User Manual in PDF format
RMEO:
Raman Monte Carlo with embedded object (RMEO)
We assume that the user is well versed with the original MCML code. If not, we recommend them to first go through the original MCML code and relevant support document to understand how the monte carlo modelling is done for light transport in multi-layered tissues. The original MCML code with support files is available on Dr. Lihong Wang’s website (Original MCML).
We have modified the original MCML code to incorporate an embedded objects (sphere, cube, cylinder) in one of the layers. Check our MCML-EO section on the top, if you need for information. Later, we modified the code to incorporate the Raman scattering.
Reference Related to RMCC Simulation Package (Citation appreciated):
1. V. Periyasamy, H. B. Jaafar, and M. Pramanik, “Raman Monte Carlo Simulation for light propagation for tissue with embedded objects,” Proc. SPIE 10492, 104920V (2018).
2. V. Periyasamy, S. Sil, G. Dhal, F. Ariese, S. Umapathy, and M. Pramanik, "Experimentally validated Raman Monte Carlo simulation for a cuboid object to obtain Raman Spectroscopic signature for hidden material," Journal of Raman Spectroscopy 46(7), 669-676 (2015).
3. V. Periyasamy and M. Pramanik, "Monte Carlo simulation of light transport in turbid medium with embedded object - spherical, cylindrical, ellipsoidal, or cuboidal object embedded within multilayered tissues," Journal of Biomedical Optics 19(4), 045003 (2014).
4. L.-H. Wang, S. L. Jacques, and L.-Q. Zheng, "MCML - Monte Carlo modeling of photon transport in multi-layered tissues," Computer Methods and Programs in Biomedicine 47, 131-146 (1995).
Download: