An artificial neural network (ANN)-based lung-tumor motion predictor for intrafractional MR tumor tracking

Yun, Jihyun; MacKenzie, M; Rathee, S; Robinson, Don; Fallone, B. G.

doi:10.1118/1.4730294

Cited by 32 publications

(39 citation statements)

References 27 publications

(72 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With an average RMSE of 0.67 ± 0.36 mm for a prediction horizon of 665 ms, our results are within the range of accuracies found elsewhere such as a RMSE of 1.2 ± 0.9 mm for a system latency of 600 ms, 0.97 mm for a latency of 400 ms and 0.9 mm for system latency of 520 ms . Our results are also within the range of accuracies when compared with the extensive list of prediction studies surveyed in Ref.…”

Section: Discussionsupporting

confidence: 88%

See 1 more Smart Citation

Feasibility of predicting tumor motion using online data acquired during treatment and a generalized neural network optimized with offline patient tumor trajectories

et al. 2018

View full text Add to dashboard Cite

show abstract

Section: Discussionsupporting

confidence: 88%

“…This value is in between the range of latencies (50 to 1400 ms) observed in some image‐guided adaptive radiotherapy systems . It is well‐known that prediction accuracy deteriorates as the prediction horizon increases …”

Section: Discussionmentioning

confidence: 71%

Feasibility of predicting tumor motion using online data acquired during treatment and a generalized neural network optimized with offline patient tumor trajectories

et al. 2018

View full text Add to dashboard Cite

show abstract

“…1). In addition, they can generalize correct responses that only broadly resemble the data in the learning phase [56], [65], [66].…”

Section: Methodsmentioning

confidence: 99%

BP-ANN for Fitting the Temperature-Germination Model and Its Application in Predicting Sowing Time and Region for Bermudagrass

Mantri

Ngai

et al. 2013

PLoS ONE

View full text Add to dashboard Cite

Temperature is one of the most significant environmental factors that affects germination of grass seeds. Reliable prediction of the optimal temperature for seed germination is crucial for determining the suitable regions and favorable sowing timing for turf grass cultivation. In this study, a back-propagation-artificial-neural-network-aided dual quintic equation (BP-ANN-QE) model was developed to improve the prediction of the optimal temperature for seed germination. This BP-ANN-QE model was used to determine optimal sowing times and suitable regions for three Cynodon dactylon cultivars (C. dactylon, ‘Savannah’ and ‘Princess VII’). Prediction of the optimal temperature for these seeds was based on comprehensive germination tests using 36 day/night (high/low) temperature regimes (both ranging from 5/5 to 40/40°C with 5°C increments). Seed germination data from these temperature regimes were used to construct temperature-germination correlation models for estimating germination percentage with confidence intervals. Our tests revealed that the optimal high/low temperature regimes required for all the three bermudagrass cultivars are 30/5, 30/10, 35/5, 35/10, 35/15, 35/20, 40/15 and 40/20°C; constant temperatures ranging from 5 to 40°C inhibited the germination of all three cultivars. While comparing different simulating methods, including DQEM, Bisquare ANN-QE, and BP-ANN-QE in establishing temperature based germination percentage rules, we found that the R2 values of germination prediction function could be significantly improved from about 0.6940–0.8177 (DQEM approach) to 0.9439–0.9813 (BP-ANN-QE). These results indicated that our BP-ANN-QE model has better performance than the rests of the compared models. Furthermore, data of the national temperature grids generated from monthly-average temperature for 25 years were fit into these functions and we were able to map the germination percentage of these C. dactylon cultivars in the national scale of China, and suggested the optimum sowing regions and times for them.

show abstract

“…These requirements include (1) characterization of multileaf collimator (MLC) motor operation in an external magnetic field, 18 (2) measurement of radio frequency (RF) noise from MLC and shielding technique, 19 (3) development of lung-tumor autocontouring 20 software compatible with MR images, and (4) development of lung-tumor motion prediction software for MR-based tracking. 21 We have focused on lung-tumor tracking due to the potential for a large range of motion during treatment delivery. Various studies have shown that lung-tumor may move up to 40 mm in superior-inferior (SI), 15 mm in anterior-posterior (AP), and 10 mm in left-right (LR) directions during normal breathing.…”

Section: Introductionmentioning

confidence: 99%

First demonstration of intrafractional tumor‐tracked irradiation using 2D phantom MR images on a prototype linac‐MR

et al. 2013

Self Cite

View full text Add to dashboard Cite

The authors report the first demonstration of intrafractional tumor tracking using 2D MR images. During 2 min of tracking, the authors delivered highly conformal dose to a moving target that simulates tumor motions. Compared to static target irradiation, the 50% beam width remains essentially the same (within 0.5 mm), with an increase in 80%-20% penumbra width of less than 1.7 mm in moving target irradiation. These results illustrate potential dosimetric advantages of intrafractional MR tumor tracking in treating mobile tumors as shown for the phantom case.

show abstract

An artificial neural network (ANN)-based lung-tumor motion predictor for intrafractional MR tumor tracking

Cited by 32 publications

References 27 publications

Feasibility of predicting tumor motion using online data acquired during treatment and a generalized neural network optimized with offline patient tumor trajectories

Feasibility of predicting tumor motion using online data acquired during treatment and a generalized neural network optimized with offline patient tumor trajectories

BP-ANN for Fitting the Temperature-Germination Model and Its Application in Predicting Sowing Time and Region for Bermudagrass

First demonstration of intrafractional tumor‐tracked irradiation using 2D phantom MR images on a prototype linac‐MR

Contact Info

Product

Resources

About