no code implementations • 12 Apr 2024 • Subhadarsi Nayak, Hrithwik Shalu, Joseph Stember
Tropospheric ozone, known as a concerning air pollutant, has been associated with health issues including asthma, bronchitis, and impaired lung function.
no code implementations • 26 Nov 2022 • Subhanik Purkayastha, Hrithwik Shalu, David Gutman, Shakeel Modak, Ellen Basu, Brian Kushner, Kim Kramer, Sofia Haque, Joseph Stember
As in prior DNE work, we used a small training set, consisting of 30 normal and 30 metastasis-containing post-contrast MRI brain scans, with 37% outside images.
no code implementations • 26 Nov 2022 • Joseph Stember, Mehrnaz Jenabi, Luca Pasquini, Kyung Peck, Andrei Holodny, Hrithwik Shalu
Whereas MRI produces anatomic information about the brain, functional MRI (fMRI) tells us about neural activity within the brain, including how various regions communicate with each other.
no code implementations • 17 Jun 2022 • Joseph Stember, Danielle Stember, Luca Pasquini, Jenabi Merhnaz, Andrei Holodny, Hrithwik Shalu
We hypothesized that a Deep Reinforcement Learning (DRL) classifier could learn effectively on a small fMRI training set.
no code implementations • 24 Mar 2022 • Joseph Stember, Robert Young, Hrithwik Shalu
We applied the CNNs to our training set, as well as a separate testing set with the same class balance of 25 progression and 25 regression images.
no code implementations • 17 Jun 2021 • Joseph Stember, Hrithwik Shalu
Part 2: Then, using these labels, whereas the supervised approach quickly overfit the training data and as expected performed poorly on the testing set (66% accuracy, just over random guessing), the reinforcement learning approach achieved an accuracy of 92%.
no code implementations • 16 Feb 2021 • Joseph Stember, Parvathy Jayan, Hrithwik Shalu
Purpose: We seek to use neural networks (NNs) to solve a well-known system of differential equations describing the balance between T cells and HIV viral burden.
no code implementations • 4 Feb 2021 • Joseph Stember, Hrithwik Shalu
We achieved perfect testing set accuracy with a training set of merely 30 images.
no code implementations • 24 Dec 2020 • Joseph Stember, Hrithwik Shalu
Materials and Methods: We initially clustered images using unsupervised deep learning clustering to generate candidate lesion masks for each MRI image.
no code implementations • 6 Aug 2020 • Joseph Stember, Hrithwik Shalu
Reinforcement learning predicted testing set lesion locations with 85% accuracy, compared to roughly 7% accuracy for the supervised deep network.
no code implementations • 26 Aug 2019 • Yucheng Liu, Naji Khosravan, Yulin Liu, Joseph Stember, Jonathan Shoag, Christopher E. Barbieri, Ulas Bagci, Sachin Jambawalikar
By using SynCT images (without segmentation labels) and MR images (with segmentation labels available), we have trained a deep segmentation network for precise delineation of prostate from real CT scans.