# Improving the Timing Resolution of Positron Emission Tomography Detectors Using Boosted Learning -- A Residual Physics Approach

arXiv: https://arxiv.org/abs/2302.01681 · HTML: https://mlsanity.com/paper/2302.01681/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 91 references that are in the map.
- First posted on arXiv 3 Feb 2023.

## Builds on (most cited first, 19 of 19)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI](https://mlsanity.com/paper/1910.10045/) (2019)
- [Tabular Data: Deep Learning is Not All You Need](https://mlsanity.com/paper/2106.03253/) (2021)
- [Deep Convolutional Neural Network for Inverse Problems in Imaging](https://mlsanity.com/paper/1611.03679/) (2016)
- [A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAI](https://mlsanity.com/paper/1907.07374/) (2019)
- [A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects](https://mlsanity.com/paper/2004.02806/) (2020)
- [Consistent Individualized Feature Attribution for Tree Ensembles](https://mlsanity.com/paper/1802.03888/) (2018)
- [Residual Reinforcement Learning for Robot Control](https://mlsanity.com/paper/1812.03201/) (2018)
- [Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models](https://mlsanity.com/paper/1708.08296/) (2017)
- [Residual Policy Learning](https://mlsanity.com/paper/1812.06298/) (2018)
- [TossingBot: Learning to Throw Arbitrary Objects with Residual Physics](https://mlsanity.com/paper/1903.11239/) (2019)
- [Towards Explainable Artificial Intelligence](https://mlsanity.com/paper/1909.12072/) (2019)
- [Medical image denoising using convolutional denoising autoencoders](https://mlsanity.com/paper/1608.04667/) (2016)
- [Applications of Deep Learning and Reinforcement Learning to Biological Data](https://mlsanity.com/paper/1711.03985/) (2017)
- [GBDT-MO: Gradient Boosted Decision Trees for Multiple Outputs](https://mlsanity.com/paper/1909.04373/) (2019)
- [Federated Multi-Agent Deep Reinforcement Learning Approach via Physics-Informed Reward for Multi-Microgrid Energy Management](https://mlsanity.com/paper/2301.00641/) (2022)
- [Combining Learned and Analytical Models for Predicting Action Effects from Sensory Data](https://mlsanity.com/paper/1710.04102/) (2017)

## Built on by (most cited first, 2 of 2)

- [Rethinking Timing Residuals: Advancing PET Detectors with Explicit TOF Corrections](https://mlsanity.com/paper/2502.07630/) (2025)
- [Machine learning enables experimental access to photon-by-photon arrival times in scintillation detectors](https://mlsanity.com/paper/2605.27937/) (2026)

## Abstract (arXiv)

Artificial intelligence (AI) is entering medical imaging, mainly enhancing image reconstruction. Nevertheless, improvements throughout the entire processing, from signal detection to computation, potentially offer significant benefits. This work presents a novel and versatile approach to detector optimization using machine learning (ML) and residual physics. We apply the concept to positron emission tomography (PET), intending to improve the coincidence time resolution (CTR). PET visualizes metabolic processes in the body by detecting photons with scintillation detectors. Improved CTR performance offers the advantage of reducing radioactive dose exposure for patients. Modern PET detectors with sophisticated concepts and read-out topologies represent complex physical and electronic systems requiring dedicated calibration techniques. Traditional methods primarily depend on analytical formulations successfully describing the main detector characteristics. However, when accounting for higher-order effects, additional complexities arise matching theoretical models to experimental reality. Our work addresses this challenge by combining traditional calibration with AI and residual physics, presenting a highly promising approach. We present a residual physics-based strategy using gradient tree boosting and physics-guided data generation. The explainable AI framework SHapley Additive exPlanations (SHAP) was used to identify known physical effects with learned patterns. In addition, the models were tested against basic physical laws. We were able to improve the CTR significantly (more than 20%) for clinically relevant detectors of 19 mm height, reaching CTRs of 185 ps (450-550 keV).