no code implementations • 19 Mar 2024 • Aneesh Rangnekar, Nishant Nadkarni, Jue Jiang, Harini Veeraraghavan
We assessed the trustworthiness of two self-supervision pretrained transformer models, Swin UNETR and SMIT, for fine-tuned lung (LC) tumor segmentation using 670 CT and MRI scans.
no code implementations • 2 Oct 2023 • Jue Jiang, Harini Veeraraghavan
However, more accurate and efficient attention guided MIM approaches are difficult to implement with Swin due to it's lack of an explicit global attention.
no code implementations • 6 Mar 2023 • Josiah Simeth, Jue Jiang, Anton Nosov, Andreas Wibmer, Michael Zelefsky, Neelam Tyagi, Harini Veeraraghavan
MRRN-DS significantly outperformed ResUnet in Dataset2 (DSC of 0. 54 vs. 0. 44, p<0. 001) and the Unet++ in Dataset3 (DSC of 0. 45 vs. p=0. 04).
no code implementations • 25 Oct 2022 • Jue Jiang, Jun Hong, Kathryn Tringale, Marsha Reyngold, Christopher Crane, Neelam Tyagi, Harini Veeraraghavan
ProRSeg based dose accumulation accounting for intra-fraction (pre-treatment to post-treatment MRI scan) and inter-fraction motion showed that the organ dose constraints were violated in 4 patients for stomach-duodenum and for 3 patients for small bowel.
1 code implementation • 20 May 2022 • Jue Jiang, Neelam Tyagi, Kathryn Tringale, Christopher Crane, Harini Veeraraghavan
Self-supervised learning (SSL) has demonstrated success in medical image segmentation using convolutional networks.
no code implementations • 11 May 2022 • Jiening Zhu, Harini Veeraraghavan, Larry Norton, Joseph O. Deasy, Allen Tannenbaum
We approach the directionality problem from a novel perspective by the use of the optimal transport map of a local image patch to a uni-color patch of its mean.
no code implementations • 26 Jan 2022 • Jue Jiang, Harini Veeraraghavan
The registration network was trained in an unsupervised manner using pairs of planning CT (pCT) and CBCT images and produced a progressively deformed sequence of images.
no code implementations • 16 Jul 2021 • Jue Jiang, Andreas Rimner, Joseph O. Deasy, Harini Veeraraghavan
Network design, methods to combine MRI with CT information, distillation learning under informative (MRI to CT), weak (CT to MRI) and equal teacher (MRI to MRI), and ablation tests were performed.
no code implementations • 26 Feb 2021 • Harini Veeraraghavan, Jue Jiang, Sharif Elguindi, Sean L. Berry, Ifeanyirochukwu Onochie, Aditya Apte, Laura Cervino, Joseph O. Deasy
NBSA's segmentations were less variable than multiple 3D methods, including for small organs with low soft-tissue contrast such as the submandibular glands (surface Dice of 0. 90).
no code implementations • 17 Feb 2021 • Jue Jiang, Sadegh Riyahi Alam, Ishita Chen, Perry Zhang, Andreas Rimner, Joseph O. Deasy, Harini Veeraraghavan
Validation was done on 20 weekly CBCTs from patients not used in training.
no code implementations • 19 Jul 2020 • Jue Jiang, Harini Veeraraghavan
Our contribution is a unified cross-modality feature disentagling approach for multi-domain image translation and multiple organ segmentation.
1 code implementation • 18 Jul 2020 • Jue Jiang, Yu Chi Hu, Neelam Tyagi, Andreas Rimner, Nancy Lee, Joseph O. Deasy, Sean Berry, Harini Veeraraghavan
Our method achieved an overall average DSC of 0. 87 on T1w and 0. 90 on T2w for the abdominal organs, 0. 82 on T2wFS for the parotid glands, and 0. 77 on T2w MRI for lung tumors.
no code implementations • MIDL 2019 • Hyemin Um, Jue Jiang, Maria Thor, Andreas Rimner, Leo Luo, Joseph O. Deasy, Harini Veeraraghavan
Our approach simultaneously combines feature streams computed at multiple image resolutions and feature levels through residual connections.
no code implementations • 11 Sep 2019 • Jue Jiang, Elguindi Sharif, Hyemin Um, Sean Berry, Harini Veeraraghavan
We developed our approach using U-net and compared it against multiple state-of-the-art self attention methods.
no code implementations • 10 Sep 2019 • Jue Jiang, Jason Hu, Neelam Tyagi, Andreas Rimner, Sean L. Berry, Joseph O. Deasy, Harini Veeraraghavan
Our approach, called cross-modality educed deep learning segmentation (CMEDL) combines CT and pseudo MR produced from CT by aligning their features to obtain segmentation on CT.
no code implementations • 1 Feb 2019 • Peter Klages, Ilyes Benslimane, Sadegh Riyahi, Jue Jiang, Margie Hunt, Joe Deasy, Harini Veeraraghavan, Neelam Tyagi
A total of twenty paired CT and MR images were used in this study to investigate two conditional generative adversarial networks, Pix2Pix, and Cycle GAN, for generating synthetic CT images for Headand Neck cancer cases.
no code implementations • 31 Jan 2019 • Jue Jiang, Yu-Chi Hu, Neelam Tyagi, Pengpeng Zhang, Andreas Rimner, Joseph O. Deasy, Harini Veeraraghavan
This method produced the highest segmentation accuracy with a DSC of 0. 75 and the lowest Hausdroff distance on the test dataset.