Domain Knowledge Driven 3D Dose Prediction Using Moment-Based Loss Function

• URL: http://arxiv.org/abs/2207.03414v1
• Date: Thu, 7 Jul 2022 16:35:06 GMT
• Title: Domain Knowledge Driven 3D Dose Prediction Using Moment-Based Loss Function
• Authors: Gourav Jhanwar, Navdeep Dahiya, Parmida Ghahremani, Masoud Zarepisheh, Saad Nadeem
• Abstract summary: Dose volume histogram (DVH) metrics are widely accepted evaluation criteria in the clinic. We propose a novel moment-based loss function for predicting 3D dose distribution.
• Score: 3.2653790770825686
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Dose volume histogram (DVH) metrics are widely accepted evaluation criteria in the clinic. However, incorporating these metrics into deep learning dose prediction models is challenging due to their non-convexity and non-differentiability. We propose a novel moment-based loss function for predicting 3D dose distribution for the challenging conventional lung intensity modulated radiation therapy (IMRT) plans. The moment-based loss function is convex and differentiable and can easily incorporate DVH metrics in any deep learning framework without computational overhead. The moments can also be customized to reflect the clinical priorities in 3D dose prediction. For instance, using high-order moments allows better prediction in high-dose areas for serial structures. We used a large dataset of 360 (240 for training, 50 for validation and 70 for testing) conventional lung patients with 2Gy $\times$ 30 fractions to train the deep learning (DL) model using clinically treated plans at our institution. We trained a UNet like CNN architecture using computed tomography (CT), planning target volume (PTV) and organ-at-risk contours (OAR) as input to infer corresponding voxel-wise 3D dose distribution. We evaluated three different loss functions: (1) The popular Mean Absolute Error (MAE) Loss, (2) the recently developed MAE + DVH Loss, and (3) the proposed MAE + Moments Loss. The quality of the predictions was compared using different DVH metrics as well as dose-score and DVH-score, recently introduced by the AAPM knowledge-based planning grand challenge. Model with (MAE + Moment) loss function outperformed the model with MAE loss by significantly improving the DVH-score (11%, p$<$0.01) while having similar computational cost. It also outperformed the model trained with (MAE+DVH) by significantly improving the computational cost (48%) and the DVH-score (8%, p$<$0.01).

Related papers

• The effect of data augmentation and 3D-CNN depth on Alzheimer's Disease detection [51.697248252191265]
  This work summarizes and strictly observes best practices regarding data handling, experimental design, and model evaluation. We focus on Alzheimer's Disease (AD) detection, which serves as a paradigmatic example of challenging problem in healthcare. Within this framework, we train predictive 15 models, considering three different data augmentation strategies and five distinct 3D CNN architectures.
  arXiv  Detail & Related papers  (2023-09-13T10:40:41Z)
• Weakly supervised segmentation of intracranial aneurysms using a novel 3D focal modulation UNet [0.5106162890866905]
  We propose FocalSegNet, a novel 3D focal modulation UNet, to detect an aneurysm and offer an initial, coarse segmentation of it from time-of-flight MRA image patches. We trained and evaluated our model on a public dataset, and in terms of UIA detection, our model showed a low false-positive rate of 0.21 and a high sensitivity of 0.80.
  arXiv  Detail & Related papers  (2023-08-06T03:28:08Z)
• Predicting Ejection Fraction from Chest X-rays Using Computer Vision for Diagnosing Heart Failure [8.955986135184375]
  Ejection fraction (EF) is a key metric for the diagnosis and management of heart failure. While chest x-rays (CXR) are quick, inexpensive, and require less expertise, they do not provide sufficient information to the human eye to estimate EF. This work explores the efficacy of computer vision techniques to predict reduced EF solely from CXRs.
  arXiv  Detail & Related papers  (2022-12-19T21:18:27Z)
• Clinical Deterioration Prediction in Brazilian Hospitals Based on Artificial Neural Networks and Tree Decision Models [56.93322937189087]
  An extremely boosted neural network (XBNet) is used to predict clinical deterioration (CD) The XGBoost model obtained the best results in predicting CD among Brazilian hospitals' data.
  arXiv  Detail & Related papers  (2022-12-17T23:29:14Z)
• Ischemic Stroke Lesion Prediction using imbalanced Temporal Deep Gaussian Process (iTDGP) [2.649401887836554]
  Acute Ischemic Stroke (AIS) occurs when the blood supply to the brain is suddenly interrupted because of a blocked artery. Current standard AIS assessment method, which thresholds the 3D measurement maps extracted from Computed Tomography Perfusion (CTP) images, is not accurate enough. We propose imbalanced Temporal Deep Process (iTDGP), a probabilistic model that can improve AIS prediction by using baseline Gaussian time series.
  arXiv  Detail & Related papers  (2022-11-16T17:32:29Z)
• Density-Aware Personalized Training for Risk Prediction in Imbalanced Medical Data [89.79617468457393]
  Training models with imbalance rate (class density discrepancy) may lead to suboptimal prediction. We propose a framework for training models for this imbalance issue. We demonstrate our model's improved performance in real-world medical datasets.
  arXiv  Detail & Related papers  (2022-07-23T00:39:53Z)
• SurvLatent ODE : A Neural ODE based time-to-event model with competing risks for longitudinal data improves cancer-associated Deep Vein Thrombosis (DVT) prediction [68.8204255655161]
  We propose a generative time-to-event model, SurvLatent ODE, which parameterizes a latent representation under irregularly sampled data. Our model then utilizes the latent representation to flexibly estimate survival times for multiple competing events without specifying shapes of event-specific hazard function. SurvLatent ODE outperforms the current clinical standard Khorana Risk scores for stratifying DVT risk groups.
  arXiv  Detail & Related papers  (2022-04-20T17:28:08Z)
• Unsupervised Pre-Training on Patient Population Graphs for Patient-Level Predictions [48.02011627390706]
  Pre-training has shown success in different areas of machine learning, such as Computer Vision (CV), Natural Language Processing (NLP) and medical imaging. In this paper, we apply unsupervised pre-training to heterogeneous, multi-modal EHR data for patient outcome prediction. We find that our proposed graph based pre-training method helps in modeling the data at a population level.
  arXiv  Detail & Related papers  (2022-03-23T17:59:45Z)
• Deep Learning 3D Dose Prediction for Conventional Lung IMRT Using Consistent/Unbiased Automated Plans [3.4742750855568767]
  In this work, we use consistent plans generated by our in-house automated planning system (named ECHO'') to train the DL model. ECHO generates consistent/unbiased plans by solving large-scale constrained optimization problems sequentially. The quality of the predictions was compared using different DVH metrics as well as dose-score and DVH-score, recently introduced by the AAPM knowledge-based planning grand challenge.
  arXiv  Detail & Related papers  (2021-06-07T15:15:05Z)
• A comparison of Monte Carlo dropout and bootstrap aggregation on the performance and uncertainty estimation in radiation therapy dose prediction with deep learning neural networks [0.46180371154032895]
  We propose to use Monte Carlo dropout (MCDO) and the bootstrap aggregation (bagging) technique on deep learning models to produce uncertainty estimations for radiation therapy dose prediction. Performance-wise, bagging provides statistically significant reduced loss value and errors in most of the metrics investigated.
  arXiv  Detail & Related papers  (2020-11-01T00:24:43Z)
• Probabilistic 3D surface reconstruction from sparse MRI information [58.14653650521129]
  We present a novel probabilistic deep learning approach for concurrent 3D surface reconstruction from sparse 2D MR image data and aleatoric uncertainty prediction. Our method is capable of reconstructing large surface meshes from three quasi-orthogonal MR imaging slices from limited training sets.
  arXiv  Detail & Related papers  (2020-10-05T14:18:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.