2019
DOI: 10.1002/mp.13765
|View full text |Cite
|
Sign up to set email alerts
|

Toward predicting the evolution of lung tumors during radiotherapy observed on a longitudinal MR imaging study via a deep learning algorithm

Abstract: Purpose To predict the spatial and temporal trajectories of lung tumor during radiotherapy monitored under a longitudinal magnetic resonance imaging (MRI) study via a deep learning algorithm for facilitating adaptive radiotherapy (ART). Methods We monitored 10 lung cancer patients by acquiring weekly MRI‐T2w scans over a course of radiotherapy. Under an ART workflow, we developed a predictive neural network (P‐net) to predict the spatial distributions of tumors in the coming weeks utilizing images acquired ear… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

1
35
0

Year Published

2020
2020
2024
2024

Publication Types

Select...
6

Relationship

1
5

Authors

Journals

citations
Cited by 38 publications
(36 citation statements)
references
References 31 publications
1
35
0
Order By: Relevance
“…An alternative method, investigated by Wang et al, would be to treat each patient as a time series, with the goal of predicting the future state of the change tumor volume. 32 We elected to generate daily predictions to provide a simplified mode that did not rely on the possible uncertainty of the future state, allowing physicians to make real time decisions based the changes that have already occurred.…”
Section: Discussionmentioning
confidence: 99%
See 1 more Smart Citation
“…An alternative method, investigated by Wang et al, would be to treat each patient as a time series, with the goal of predicting the future state of the change tumor volume. 32 We elected to generate daily predictions to provide a simplified mode that did not rely on the possible uncertainty of the future state, allowing physicians to make real time decisions based the changes that have already occurred.…”
Section: Discussionmentioning
confidence: 99%
“…In cases in which the reviewer does not support the need for ART, the probability threshold can be increased mid‐treatment, only providing subsequent alerts in cases with continued corresponding increase in the magnitude of tumor regression. An alternative method, investigated by Wang et al, would be to treat each patient as a time series, with the goal of predicting the future state of the change tumor volume 32 . We elected to generate daily predictions to provide a simplified mode that did not rely on the possible uncertainty of the future state, allowing physicians to make real time decisions based the changes that have already occurred.…”
Section: Discussionmentioning
confidence: 99%
“…Recurrent and/or recursive neural networks (RNNs) are among the supervised deep learning algorithms, which in contrast to CNN models, have the ability to access/send/process information over time steps. RNNs take sequences of input vectors to model them one at a time enabling both parallel and sequential processing appropriate for data analysis in time series, such as dynamic or longitudinal studies (Wang et al 2019a ).
Fig.
…”
Section: Principles Of Machine Learning and Deep Learningmentioning
confidence: 99%
“…Recurrent neural networks (RNN) are specialized in processing time series images . Such networks have been combined with CNN to track two‐dimensional motions of markers implanted in liver using ultrasound images, and recently to track lung tumor changes in response to radiotherapy at our institution . In this paper, we present a similar algorithm, a convolutional recurrence neural network (CRNN), for real‐time three‐dimensional (3D) localization of mobile lung tumors from CBCT projections.…”
Section: Introductionmentioning
confidence: 99%
“…23 Such networks have been combined with CNN to track two-dimensional motions of markers implanted in liver using ultrasound images, 24 and recently to track lung tumor changes in response to radiotherapy at our institution. 25 In this paper, we present a similar algorithm, a convolutional recurrence neural network (CRNN), for real-time three-dimensional (3D) localization of mobile lung tumors from CBCT projections. The CRNN is designed to process both static features embedded in a particular kV projection, as well as the temporal evolution of such features in a stream of projections.…”
Section: Introductionmentioning
confidence: 99%