
Pritam Mukherjee
Postdoctoral Research Fellow, Biomedical Informatics
Bio
I received my B. Tech(Hons) with a major in Electronics and Electrical Communication Engineering and a minor in Computer Science and Engineering from Indian Institute of Technology (IIT), Kharagpur in 2010. In 2016, I obtained a Ph.D in Electrical and Computer Engineering at the University of Maryland, College Park under the guidance of Prof. Sennur Ulukus. From January to December 2017, I was a postdoctoral researcher in the Electrical Engineering department at Stanford University with Prof. Tsachy Weissman and Prof. Ayfer Ozgur. From January 2018, I joined the Gevaertlab at BMIR in the Stanford School of Medicine where I am currently pursuing research into the application of machine learning and deep learning to uncover the interplay between biomedical imaging and genomics, as they relate to cancer research.
Professional Education
-
Doctor of Philosophy, University of Maryland College Park (2016)
-
Bachelor of Technology, Indian Institute of Technology, Kharagpur (2010)
All Publications
-
CT-based Radiomic Signatures for Predicting Histopathologic Features in Head and Neck Squamous Cell Carcinoma.
Radiology. Imaging cancer
2020; 2 (3): e190039
Abstract
Purpose: To determine the performance of CT-based radiomic features for noninvasive prediction of histopathologic features of tumor grade, extracapsular spread, perineural invasion, lymphovascular invasion, and human papillomavirus status in head and neck squamous cell carcinoma (HNSCC).Materials and Methods: In this retrospective study, which was approved by the local institutional ethics committee, CT images and clinical data from patients with pathologically proven HNSCC from The Cancer Genome Atlas (n = 113) and an institutional test cohort (n = 71) were analyzed. A machine learning model was trained with 2131 extracted radiomic features to predict tumor histopathologic characteristics. In the model, principal component analysis was used for dimensionality reduction, and regularized regression was used for classification.Results: The trained radiomic model demonstrated moderate capability of predicting HNSCC features. In the training cohort and the test cohort, the model achieved a mean area under the receiver operating characteristic curve (AUC) of 0.75 (95% confidence interval [CI]: 0.68, 0.81) and 0.66 (95% CI: 0.45, 0.84), respectively, for tumor grade; a mean AUC of 0.64 (95% CI: 0.55, 0.62) and 0.70 (95% CI: 0.47, 0.89), respectively, for perineural invasion; a mean AUC of 0.69 (95% CI: 0.56, 0.81) and 0.65 (95% CI: 0.38, 0.87), respectively, for lymphovascular invasion; a mean AUC of 0.77 (95% CI: 0.65, 0.88) and 0.67 (95% CI: 0.15, 0.80), respectively, for extracapsular spread; and a mean AUC of 0.71 (95% CI: 0.29, 1.0) and 0.80 (95% CI: 0.65, 0.92), respectively, for human papillomavirus status.Conclusion: Radiomic CT models have the potential to predict characteristics typically identified on pathologic assessment of HNSCC.Supplemental material is available for this article.© RSNA, 2020.
View details for DOI 10.1148/rycan.2020190039
View details for PubMedID 32550599
-
A shallow convolutional neural network predicts prognosis of lung cancer patients in multi-institutional computed tomography image datasets
Nature Machine Intelligence
2020; 2 (5): 274–282
View details for DOI 10.1038/s42256-020-0173-6
-
Predicting the tumor response to chemoradiotherapy for rectal cancer: Model development and external validation using MRI radiomics.
Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology
2019
Abstract
BACKGROUND: In well-responding patients to chemoradiotherapy for locally advanced rectal cancer (LARC), a watch-and-wait strategy can be considered. To implement organ-sparing strategies, accurate patient selection is needed. We investigate the use of MRI-based radiomics models to predict tumor response to improve patient selection.MATERIALS AND METHODS: Models were developed in a cohort of 70 patients and validated in an external cohort of 55 patients. Patients received chemoradiation followed by surgery and underwent T2-weighted and diffusion-weighted MRI (DW-MRI) before and after chemoradiation. The outcome measure was (near-)complete pathological tumor response (ypT0-1N0). Tumor segmentation was done on T2-images and transferred to b800-images and ADC maps, after which quantitative and four semantic features were extracted. We combined features using principal component analysis and built models using LASSO regression analysis. The best models based on precision and performance were selected for validation.RESULTS: 21/70 patients (30%) achieved ypT0-1N0 in the development cohort versus 13/55 patients (24%) in the validation cohort. Three models (t2_dwi_pre_post, semantic_dwi_adc_pre, semantic_dwi_post) were identified with an area-under-the-curve (AUC) of 0.83 (95% CI 0.70-0.95), 0.86 (95% CI 0.75-0.98) and 0.84 (95% CI 0.75-0.94) respectively. Two models (t2_dwi_pre_post, semantic_dwi_post) validated well in the external cohort with AUCs of 0.83 (95% CI 0.70-0.95) and 0.86 (95% CI 0.76-0.97). These models however did not outperform a previously established four-feature semantic model.CONCLUSION: Prediction models based on MRI radiomics non-invasively predict tumor response after chemoradiation for rectal cancer and can be used as an additional tool to identify patients eligible for an organ-preserving treatment.
View details for DOI 10.1016/j.radonc.2019.07.033
View details for PubMedID 31431368
-
Secure Degrees of Freedom of the Multiple Access Wiretap Channel With Multiple Antennas
IEEE TRANSACTIONS ON INFORMATION THEORY
2018; 64 (3): 2093–2103
View details for DOI 10.1109/TIT.2018.2793848
View details for Web of Science ID 000425665200039
-
Distributed Statistical Estimation of High-Dimensional and Nonparametric Distributions
IEEE. 2018: 506–10
View details for Web of Science ID 000448139300102
-
Secrecy in MIMO Networks With No Eavesdropper CSIT
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC. 2017: 4382–91
View details for DOI 10.1109/TCOMM.2017.2705054
View details for Web of Science ID 000413137400023
-
Secure Degrees of Freedom Region of the Two-User MISO Broadcast Channel With Alternating CSIT
IEEE TRANSACTIONS ON INFORMATION THEORY
2017; 63 (6): 3823–53
View details for DOI 10.1109/TIT.2017.2663427
View details for Web of Science ID 000402058900030
-
Secure Degrees of Freedom of One-Hop Wireless Networks With No Eavesdropper CSIT
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC. 2017: 1898–1922
View details for DOI 10.1109/TIT.2016.2618725
View details for Web of Science ID 000395822500033
-
Covert Bits Through Queues
IEEE. 2016: 626–30
View details for Web of Science ID 000402623000097
-
Real Interference Alignment for the MIMO Multiple Access Wiretap Channel
IEEE. 2016
View details for Web of Science ID 000390993202038
-
Real Interference Alignment for Vector Channels
IEEE. 2016: 1476–80
View details for Web of Science ID 000390098701108
-
MIMO One Hop Networks with No Eve CSIT
IEEE. 2016: 894–901
View details for Web of Science ID 000400601400127
-
Secure Degrees of Freedom of MIMO Rayleigh Block Fading Wiretap Channels With No CSI Anywhere
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS
2015; 14 (5): 2655–69
View details for DOI 10.1109/TWC.2015.2390234
View details for Web of Science ID 000354468600024
-
Secure Degrees of Freedom of the Interference Channel with No Eavesdropper CSI
IEEE. 2015: 317–21
View details for Web of Science ID 000380406900066
-
Secrecy for MISO Broadcast Channels via Alternating CSIT
IEEE. 2015: 4157–62
View details for Web of Science ID 000371708104062
-
Secrecy for MISO Broadcast Channels with Heterogeneous CSIT
IEEE. 2015: 1966–70
View details for Web of Science ID 000380904702004
-
Secure Degrees of Freedom of the Multiple Access Wiretap Channel with No Eavesdropper CSI
IEEE. 2015: 2311–15
View details for Web of Science ID 000380904702073
-
MISO Broadcast Channels with Confidential Messages and Alternating CSIT
IEEE. 2014: 216–20
View details for Web of Science ID 000346496100043
-
Secure DoF of MIMO Rayleigh Block Fading Wiretap Channels with No CSI Anywhere
IEEE. 2014: 1959–64
View details for Web of Science ID 000366666802018
-
Even Symmetric Parallel Linear Deterministic Interference Channels are Inseparable
IEEE. 2013: 1106–13
View details for Web of Science ID 000350802400152
-
Fading Wiretap Channel with No CSI Anywhere
IEEE. 2013: 1347–51
View details for Web of Science ID 000348913401096
-
A SPT Treatment to the Realization of the Sign-LMS Based Adaptive Filters
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS
2012; 59 (9): 2025–33
View details for DOI 10.1109/TCSI.2012.2185300
View details for Web of Science ID 000308109600018
-
A SPT treatment to the Bit Serial Realization of the Sign-LMS based Adaptive Filter
IEEE. 2010: 2678–81
View details for Web of Science ID 000287216002224