Publications

2024

1. 

   Analyis of 3D pathology samples using weakly supervised AI

   Andrew H Song, Mane Williams+, Drew FK Williamson+, Sarah SL Chow, Guillaume Jaume, Gan Gao, Andrew Zhang, and 12 more authors

   Cell, 2024

   Bib HTML Github Press Video Blog Poster

   @article{Song2024analysis,
     title = {{Analyis of 3D pathology samples using weakly supervised AI}},
     author = {Song, Andrew H and Williams+, Mane and Williamson+, Drew FK and Chow, Sarah SL and Jaume, Guillaume and Gao, Gan and Zhang, Andrew and Chen, Bowen and Baras, Alexander S and Serafin, Robert and Colling, Richard and Downes, Michelle R and Farre, Xavier and Humphrey, Peter and Verrill, Clare and True, Lawrence D and Parwani, Anil V and Liu, Jonathan TC and Mahmood, Faisal},
     journal = {Cell},
     volume = {187},
     number = {10},
     pages = {2502--2520},
     year = {2024},
     github = {https://github.com/mahmoodlab/TriPath},
     press = {https://www.massgeneralbrigham.org/en/about/newsroom/articles/ai-advancements-make-3d-pathology-possible},
   }

2. 

   Multimodal Prototyping for cancer survival prediction

   Andrew H Song, Richard J Chen, Guillaume Jaume, Anurag Jayant Vaidya, Alexander Baras, and Faisal Mahmood

   In International Conference on Machine Learning (ICML) , 2024

   HTML Github Poster

3. 

   Multistain Pretraining for Slide Representation Learning in Pathology

   Guillaume Jaume*, Anurag Vaidya*, Andrew Zhang+, Andrew H Song+, Richard J Chen, Sharifa Sahai, Dandan Mo, and 3 more authors

   In European Conference on Computer Vision (ECCV) , 2024

4. 

   Morphological Prototyping for Unsupervised Slide Representation Learning in Computational Pathology

   Andrew H Song*, Richard J Chen*, Tong Ding, Drew FK Williamson, Guillaume Jaume, and Faisal Mahmood

   In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , 2024

   arXiv Bib HTML Github Poster

   @inproceedings{song2024morphological,
     title = {Morphological Prototyping for Unsupervised Slide Representation Learning in Computational Pathology},
     author = {Song*, Andrew H and Chen*, Richard J and Ding, Tong and Williamson, Drew FK and Jaume, Guillaume and Mahmood, Faisal},
     booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
     year = {2024},
     github = {https://github.com/mahmoodlab/PANTHER},
   }

5. 

   Transcriptomics-guided Slide Representation Learning in Computational Pathology

   Guillaume Jaume*, Lukas Oldenburg*, Anurag Jayant Vaidya, Richard J. Chen, Drew FK Williamson, Thomas Peeters, Andrew H Song, and 1 more author

   In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , 2024

   arXiv Bib HTML Github

   @inproceedings{jaume2024transcriptomics,
     title = {Transcriptomics-guided Slide Representation Learning in Computational Pathology},
     author = {Jaume*, Guillaume and Oldenburg*, Lukas and Vaidya, Anurag Jayant and Chen, Richard J. and Williamson, Drew FK and Peeters, Thomas and Song, Andrew H and Mahmood, Faisal},
     booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
     year = {2024},
     github = {https://github.com/mahmoodlab/TANGLE}
   }

6. 

   Demographic bias in misdiagnosis by computational pathology models

   Anurag Vaidya*, Richard J Chen*, Drew FK Williamson*, Andrew H Song, Guillaume Jaume, Yuzhe Yang, Thomas Hartvigsen, and 6 more authors

   Nature Medicine, 2024

   Bib HTML PDF Github

   @article{vaidya2024demographic,
     title = {Demographic bias in misdiagnosis by computational pathology models},
     author = {Vaidya*, Anurag and Chen*, Richard J and Williamson*, Drew FK and Song, Andrew H and Jaume, Guillaume and Yang, Yuzhe and Hartvigsen, Thomas and Dyer, Emma C and Lu, Ming Y and Lipkova, Jana and Shaban, Muhammad and Chen, Tiffany Y and Mahmood, Faisal},
     journal = {Nature Medicine},
     volume = {30},
     number = {4},
     pages = {1174--1190},
     year = {2024},
     publisher = {Nature Publishing Group US New York},
     github = {https://github.com/mahmoodlab/CPATH_demographics},
   }

7. 

   Towards a general-purpose foundation model for computational pathology

   Richard J Chen*, Tong Ding*, Ming Y Lu*, Drew FK Williamson*, Guillaume Jaume, Andrew H Song, Bowen Chen, and 6 more authors

   Nature Medicine, 2024

   Bib HTML PDF Github

   @article{chen2024towards,
     title = {Towards a general-purpose foundation model for computational pathology},
     author = {Chen*, Richard J and Ding*, Tong and Lu*, Ming Y and Williamson*, Drew FK and Jaume, Guillaume and Song, Andrew H and Chen, Bowen and Zhang, Andrew and Shao, Daniel and Shaban, Muhammad and Williams, Mane and Oldenburg, Lukas and others},
     journal = {Nature Medicine},
     volume = {30},
     number = {3},
     pages = {850--862},
     year = {2024},
     publisher = {Nature Publishing Group},
     github = {https://github.com/mahmoodlab/uni},
   }

8. 

   Triage of 3D pathology data via 2.5D multiple-instance learning to guide pathologist assessments

   Gan Gao*, Andrew H Song*, Fiona Wang, David Brenes, Rui Wang, Sarah SL Chow, Kevin W Bishop, and 3 more authors

   In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshop on Computer Vision for Microscopy Image Analysis (CVMI) , 2024

   Bib HTML

   @inproceedings{gan2024triage,
     title = {{Triage of 3D pathology data via 2.5D multiple-instance learning to guide pathologist assessments}},
     author = {Gao*, Gan and Song*, Andrew H and Wang, Fiona and Brenes, David and Wang, Rui and Chow, Sarah SL and Bishop, Kevin W and True, Lawrence D and Mahmood, Faisal and Liu, Jonathan TC},
     booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshop on Computer Vision for Microscopy Image Analysis (CVMI)},
     year = {2024},
   }

9. Two-Phase Multitask Autoencoder-Based Deep Learning Framework for Subject-Independent EEG Motor Imagery Classification

   Changgyun Jin, Andrew H Song, and Seong-Eun Kim

   IEEE Access, 2024

   Bib HTML

   @article{Jin2024two,
     title = {Two-Phase Multitask Autoencoder-Based Deep Learning Framework for Subject-Independent EEG Motor Imagery Classification},
     author = {Jin, Changgyun and Song, Andrew H and Kim, Seong-Eun},
     journal = {IEEE Access},
     year = {2024},
     volume = {12},
     pages = {77356-77367},
   }

2023

1. 

   Artificial intelligence for digital and computational pathology

   Andrew H Song*, Guillaume Jaume*, Drew FK Williamson, Ming Y Lu, Anurag Vaidya, Tiffany R Miller, and Faisal Mahmood

   Nature Reviews Bioengineering, 2023

   Bib HTML PDF

   @article{song2023artificial,
     title = {Artificial intelligence for digital and computational pathology},
     author = {Song*, Andrew H and Jaume*, Guillaume and Williamson, Drew FK and Lu, Ming Y and Vaidya, Anurag and Miller, Tiffany R and Mahmood, Faisal},
     journal = {Nature Reviews Bioengineering},
     volume = {1},
     number = {12},
     pages = {930--949},
     year = {2023},
     publisher = {Nature Publishing Group UK London},
   }

2022

1. Integrating context for superior cancer prognosis

   Guillaume Jaume*, Andrew H Song*, and Faisal Mahmood

   Nature Biomedical Engineering, 2022

   Bib HTML

   @article{jaume2022integrating,
     title = {Integrating context for superior cancer prognosis},
     author = {Jaume*, Guillaume and Song*, Andrew H and Mahmood, Faisal},
     journal = {Nature Biomedical Engineering},
     volume = {6},
     number = {12},
     pages = {1323--1325},
     year = {2022},
     publisher = {Nature Publishing Group UK London},
   }

2. Incorporating intratumoral heterogeneity into weakly-supervised deep learning models via variance pooling

   Iain Carmichael*, Andrew H Song*, Richard J Chen, Drew FK Williamson, Tiffany Y Chen, and Faisal Mahmood

   In International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI) , 2022

   Bib PDF

   @inproceedings{carmichael2022incorporating,
     title = {Incorporating intratumoral heterogeneity into weakly-supervised deep learning models via variance pooling},
     author = {Carmichael*, Iain and Song*, Andrew H and Chen, Richard J and Williamson, Drew FK and Chen, Tiffany Y and Mahmood, Faisal},
     booktitle = {International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI)},
     pages = {387--397},
     year = {2022},
     organization = {Springer},
   }

3. Investigating morphologic correlates of driver gene mutation heterogeneity via deep learning

   Andrew H Song, Drew FK Williamson, and Faisal Mahmood

   Cancer Research, 2022

   Bib

   @article{song2022investigating,
     title = {Investigating morphologic correlates of driver gene mutation heterogeneity via deep learning},
     author = {Song, Andrew H and Williamson, Drew FK and Mahmood, Faisal},
     journal = {Cancer Research},
     volume = {82},
     number = {15},
     pages = {2672--2673},
     year = {2022},
     publisher = {AACR},
   }

4. Covariance-free sparse Bayesian learning

   Alexander Lin, Andrew H Song, Berkin Bilgic, and Demba Ba

   IEEE Transactions on Signal Processing, 2022

   Bib HTML

   @article{lin2022covariance,
     title = {Covariance-free sparse Bayesian learning},
     author = {Lin, Alexander and Song, Andrew H and Bilgic, Berkin and Ba, Demba},
     journal = {IEEE Transactions on Signal Processing},
     volume = {70},
     pages = {3818--3831},
     year = {2022},
     publisher = {IEEE},
   }

5. High-dimensional sparse Bayesian learning without covariance matrices

   Alexander Lin, Andrew H Song, Berkin Bilgic, and Demba Ba

   In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) , 2022

   Bib

   @inproceedings{lin2022high,
     title = {High-dimensional sparse Bayesian learning without covariance matrices},
     author = {Lin, Alexander and Song, Andrew H and Bilgic, Berkin and Ba, Demba},
     booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
     pages = {1511--1515},
     year = {2022},
     organization = {IEEE},
   }

6. Mixture model auto-encoders: Deep clustering through dictionary learning

   Alexander Lin, Andrew H Song, and Demba Ba

   In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) , 2022

   Bib

   @inproceedings{lin2022mixture,
     title = {Mixture model auto-encoders: Deep clustering through dictionary learning},
     author = {Lin, Alexander and Song, Andrew H and Ba, Demba},
     booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
     pages = {3368--3372},
     year = {2022},
     organization = {IEEE},
   }

7. Adaptive state-space multitaper spectral estimation

   Andrew H Song*, Seong-Eun Kim*, and Emery N Brown

   IEEE Signal Processing Letters, 2022

   Bib

   @article{song2022adaptive,
     title = {Adaptive state-space multitaper spectral estimation},
     author = {Song*, Andrew H and Kim*, Seong-Eun and Brown, Emery N},
     journal = {IEEE Signal Processing Letters},
     volume = {29},
     pages = {523--527},
     year = {2022},
     publisher = {IEEE},
   }

2021

1. Gaussian process convolutional dictionary learning

   Andrew H Song, Bahareh Tolooshams, and Demba Ba

   IEEE Signal Processing Letters, 2021

   Bib

   @article{song2021gaussian,
     title = {Gaussian process convolutional dictionary learning},
     author = {Song, Andrew H and Tolooshams, Bahareh and Ba, Demba},
     journal = {IEEE Signal Processing Letters},
     volume = {29},
     pages = {95--99},
     year = {2021},
     publisher = {IEEE},
   }

2. PLSO: A generative framework for decomposing nonstationary time-series into piecewise stationary oscillatory components

   Andrew H Song, Demba Ba, and Emery N Brown

   In Uncertainty in Artificial Intelligence (UAI) , 2021

   Bib PDF

   @inproceedings{song2021plso,
     title = {PLSO: A generative framework for decomposing nonstationary time-series into piecewise stationary oscillatory components},
     author = {Song, Andrew H and Ba, Demba and Brown, Emery N},
     booktitle = {Uncertainty in Artificial Intelligence (UAI)},
     pages = {1371--1381},
     year = {2021},
     organization = {PMLR},
   }

2020

1. Convolutional dictionary learning based auto-encoders for natural exponential-family distributions

   Bahareh Tolooshams*, Andrew H Song*, Simona Temereanca, and Demba Ba

   In International Conference on Machine Learning (ICML) , 2020

   Bib PDF

   @inproceedings{tolooshams2020convolutional,
     title = {Convolutional dictionary learning based auto-encoders for natural exponential-family distributions},
     author = {Tolooshams*, Bahareh and Song*, Andrew H and Temereanca, Simona and Ba, Demba},
     booktitle = {International Conference on Machine Learning (ICML)},
     pages = {9493--9503},
     year = {2020},
     organization = {PMLR},
   }

2. Channel-attention dense u-net for multichannel speech enhancement

   Bahareh Tolooshams, Ritwik Giri, Andrew H Song, Umut Isik, and Arvindh Krishnaswamy

   In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) , 2020

   Bib

   @inproceedings{tolooshams2020channel,
     title = {Channel-attention dense u-net for multichannel speech enhancement},
     author = {Tolooshams, Bahareh and Giri, Ritwik and Song, Andrew H and Isik, Umut and Krishnaswamy, Arvindh},
     booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
     pages = {836--840},
     year = {2020},
     organization = {IEEE},
   }

3. Convolutional dictionary learning with grid refinement

   Andrew H Song, Francisco J Flores, and Demba Ba

   IEEE Transactions on Signal Processing, 2020

   Bib HTML Github

   @article{song2020convolutional,
     title = {Convolutional dictionary learning with grid refinement},
     author = {Song, Andrew H and Flores, Francisco J and Ba, Demba},
     journal = {IEEE Transactions on Signal Processing},
     volume = {68},
     pages = {2558--2573},
     year = {2020},
     publisher = {IEEE},
     github = {https://github.com/ds2p/srcdl}
   }

2019

1. Multitaper infinite hidden markov model for eeg

   Andrew H Song, Leon Chlon, Hugo Soulat, John Tauber, Sandya Subramanian, Demba Ba, and Michael J Prerau

   In International conference of the ieee engineering in medicine and biology society (EMBC) , 2019

   Bib

   @inproceedings{song2019multitaper,
     title = {Multitaper infinite hidden markov model for eeg},
     author = {Song, Andrew H and Chlon, Leon and Soulat, Hugo and Tauber, John and Subramanian, Sandya and Ba, Demba and Prerau, Michael J},
     booktitle = {International conference of the ieee engineering in medicine and biology society (EMBC)},
     pages = {5803--5807},
     year = {2019},
     organization = {IEEE},
   }

2018

1. A smoother state space multitaper spectrogram

   Andrew H Song, Sourish Chakravarty, and Emery N Brown

   In International conference of the ieee engineering in medicine and biology society (EMBC) , 2018

   Bib

   @inproceedings{song2018smoother,
     title = {A smoother state space multitaper spectrogram},
     author = {Song, Andrew H and Chakravarty, Sourish and Brown, Emery N},
     booktitle = {International conference of the ieee engineering in medicine and biology society (EMBC)},
     pages = {33--36},
     year = {2018},
     organization = {IEEE},
   }

2017

1. Pharmacological modulation of noradrenergic arousal circuitry disrupts functional connectivity of the locus ceruleus in humans

   Andrew H Song, Aaron Kucyi, Vitaly Napadow, Emery N Brown, Marco L Loggia, and Oluwaseun Akeju

   Journal of Neuroscience, 2017

   Bib

   @article{song2017pharmacological,
     title = {Pharmacological modulation of noradrenergic arousal circuitry disrupts functional connectivity of the locus ceruleus in humans},
     author = {Song, Andrew H and Kucyi, Aaron and Napadow, Vitaly and Brown, Emery N and Loggia, Marco L and Akeju, Oluwaseun},
     journal = {Journal of Neuroscience},
     volume = {37},
     number = {29},
     pages = {6938--6945},
     year = {2017},
     publisher = {Soc Neuroscience},
   }

2016

1. GABAA circuit mechanisms are associated with ether anesthesia-induced unconsciousness

   Oluwaseun Akeju, Allison E Hamilos, Andrew H Song, Kara J Pavone, Patrick L Purdon, and Emery N Brown

   Clinical Neurophysiology, 2016

   Bib

   @article{akeju2016gabaa,
     title = {GABAA circuit mechanisms are associated with ether anesthesia-induced unconsciousness},
     author = {Akeju, Oluwaseun and Hamilos, Allison E and Song, Andrew H and Pavone, Kara J and Purdon, Patrick L and Brown, Emery N},
     journal = {Clinical Neurophysiology},
     volume = {127},
     number = {6},
     pages = {2472--2481},
     year = {2016},
     publisher = {Elsevier},
   }

2. Electroencephalogram signatures of ketamine anesthesia-induced unconsciousness

   Oluwaseun Akeju, Andrew H Song, Allison E Hamilos, Kara J Pavone, Francisco J Flores, Emery N Brown, and Patrick L Purdon

   Clinical neurophysiology, 2016

   Bib

   @article{akeju2016electroencephalogram,
     title = {Electroencephalogram signatures of ketamine anesthesia-induced unconsciousness},
     author = {Akeju, Oluwaseun and Song, Andrew H and Hamilos, Allison E and Pavone, Kara J and Flores, Francisco J and Brown, Emery N and Purdon, Patrick L},
     journal = {Clinical neurophysiology},
     volume = {127},
     number = {6},
     pages = {2414--2422},
     year = {2016},
     publisher = {Elsevier},
   }

2015

1. Bring your own learner: A cloud-based, data-parallel commons for machine learning

   Ignacio Arnaldo, Kalyan Veeramachaneni, Andrew H Song, and Una-May O’Reilly

   IEEE Computational Intelligence Magazine, 2015

   Bib

   @article{arnaldo2015bring,
     title = {Bring your own learner: A cloud-based, data-parallel commons for machine learning},
     author = {Arnaldo, Ignacio and Veeramachaneni, Kalyan and Song, Andrew H and O'Reilly, Una-May},
     journal = {IEEE Computational Intelligence Magazine},
     volume = {10},
     number = {1},
     pages = {20--32},
     year = {2015},
     publisher = {IEEE},
   }