Data Science Lecturer
PhD, Biomedical Engineering, Mahidol University, 2022
MD, Ramathibodi Hospital, Mahidol University, 2018
The results suggested that dosiomic and CT radiomic features could improve RP prediction in thoracic radiotherapy. Dosiomic and radiomic feature knowledge might be transferrable from esophageal cancer to lung cancer.
Our approach offers a comprehensive tool for glaucoma management, facilitates the exploration of structure-function correlations in research, and underscores the importance of addressing artifacts in the clinical interpretation of OCT.
Some dosiomic features have low stability under interfractional error. The stability and values of the dosiomic features were affected by the total number of fractions. The effect of interfractional error on dosiomic features should be considered in further studies regarding dosiomics for reproducible results.
Recently, the rise of models based on deep neural networks (DNNs) has demonstrated enhanced effectiveness in survival analysis. However, deep learning dealing with survival analysis usually required specific architecture or strict discretization scheme limiting the temporal precision of input and output values. This research introduces the Implicit Continuous-Time Survival Function (ICTSurF), built on a continuous-time survival model, and constructs survival distribution through implicit representation. As a result, our method is capable of accepting inputs in continuous-time space and producing survival probabilities in continuous-time space, independent of neural network architecture. Comparative evaluations against existing methods underscore the remarkable competitiveness of our proposed approach. Furthermore, we highlight the advantages of a flexible discretization scheme, showing improved performance with a lower number of discretizations compared to a rigid scheme. Our model exhibits competitive performance compared to existing methods, enhancing the flexibility of input data.
The DLG correction factor strongly influences the accuracy of Mobius3D-calculated doses. Applying the optimal DLG correction factor can increase dose agreement and gamma passing rate between calculation and delivered doses of VMAT plans, which emphasizes the importance of optimizing this factor during the commissioning process.
This paper focuses on the assessment of respiratory mechanics, i.e., compliance (C) and resistance (R) on the analysis of respiratory signals. Inspired by the growing use and success of the transformer model in fields such as natural language processing, image recognition, and signal analysis, we have devised an innovative method that leverages automatic feature extraction via transformers to predict C and R. While the use of transformers in respiratory signals has not been widely studied yet, we demonstrate their efficacy for extracting relevant features from respiratory signals in this paper. As transformers require a lot of memory, we have developed a symbolic approach to process the signal, which significantly reduces the size of input data and results in a more compact model. Our experimental findings showed that the proposed algorithm achieved mean absolute errors of 6.91 mL/cmH2O and 3.01 cmH2O.s/L, as well as mean absolute percentage errors of 15% and 20.6% when determining respiratory C and R respectively. These results demonstrated the potential of the proposed method for developing a new generation of ventilation monitoring techniques that could enhance the care given to specific intensive care unit patients.
Survival analysis is a widely known method for predicting the likelihood of an event over time. The challenge of dealing with censored samples still remains. Traditional methods, such as the Cox Proportional Hazards (CPH) model, hinge on the limitations due to the strong assumptions of proportional hazards and the predetermined relationships between covariates. The rise of models based on deep neural networks (DNNs) has demonstrated enhanced effectiveness in survival analysis. This research introduces the Implicit Continuous-Time Survival Function (ICTSurF), built on a continuous-time survival model, and constructs survival distribution through implicit representation. As a result, our method is capable of accepting inputs in continuous-time space and producing survival probabilities in continuous-time space, independent of neural network architecture. Comparative assessments with existing methods underscore the high competitiveness of our proposed approach. Our implementation of ICTSurF is available at https://github.com/44REAM/ICTSurF.
SmartAdapt has adequate efficiency for image registration and contour propagation for adaptive purposes in various anatomical sites. However, there should be concern about its performance in regions with low contrast and small volumes.
<title>Abstract</title> Background This study evaluates StarGAN, a deep learning model designed to generate synthetic CT (sCT) images from MRI and CBCT data via a single model. The goal is to provide accurate Hounsfield Unit (HU) data for dose calculation and compare StarGAN's performance to CycleGAN. Methods StarGAN and CycleGAN were trained on a pelvic cancer dataset consisting of 23 training, 5 validation, and 5 testing cases. The evaluation involved qualitative and quantitative analyses, with a focus on synthetic image quality and dose distribution calculations. Results For sCT generated from CBCT, the StarGAN demonstrated superior anatomical preservation in qualitative evaluations. Quantitatively, CycleGAN exhibited lower mean absolute error (MAE) values for body (42.77 ± 4.28 HU), soft tissue (36.97 ± 3.87 HU), and bone (138.17 ± 20.29), whereas StarGAN presented higher MAE values (50.81 ± 5.16 HU, 44.57 ± 5.14 HU, 153.36 ± 27.67 HU, respectively). Dosimetric evaluations revealed a mean dose difference (DD) within 2% for planning the target volume (PTV) and body, with a gamma passing rate (GPR) > 90% under 2%/2 mm criteria. For sCT generated from MRI, qualitative evaluation also favored StarGAN's anatomical preservation. The CycleGAN resulted in lower MAEs (79.77 ± 13.96 HU, 70.14 ± 16.26 HU, and 253.62 ± 30.85 HU), whereas the StarGAN resulted in higher MAEs (94.65 ± 7.41 HU, 80.75 ± 9.60 HU, and 353.58 ± 34.85 HU). Both models achieved a mean DD within 2% in the PTV and body, and GPR > 90%. Conclusion While CycleGAN exhibited superior quantitative metrics, StarGAN was better in terms of anatomical preservation, highlighting its potential for sCT generation in radiotherapy.
Background: Radiation pneumonitis is a side effect of thoracic radiation therapy. Recently, machine learning models with radiomic features have improved radiation pneumonitis prediction by capturing spatial information. To further support clinical decision-making, this study explores the role of post hoc uncertainty quantification methods in enhancing model uncertainty estimate. Methods: We retrospectively analyzed a cohort of 101 esophageal cancer patients. This study evaluated four machine learning models: logistic regression, support vector machines, extreme gradient boosting, and random forest, using 15 dosimetric, 79 dosiomic, and 237 radiomic features to predict radiation pneumonitis. We applied uncertainty quantification methods, including Platt scaling, isotonic regression, Venn-ABERS predictor, and conformal prediction, to quantify uncertainty. Model performance was assessed through an area under the receiver operating characteristic curve (AUROC), area under the precision-recall curve (AUPRC), and adaptive calibration error using leave-one-out cross-validation. Results: Highest AUROC is achieved by the logistic regression model with the conformal prediction method (AUROC 0.75+-0.01, AUPRC 0.74+-0.01) at a certainty cut point of 0.8. Highest AUPRC of 0.82+-0.02 (with AUROC of 0.67+-0.04) achieved by The extreme gradient boosting model with conformal prediction at the 0.9 certainty threshold. Radiomic and dosiomic features improve both discriminative and calibration performance. Conclusions: Integrating uncertainty quantification into machine learning models with radiomic and dosiomic features may improve both predictive accuracy and calibration, supporting more reliable clinical decision-making. The findings emphasize the value of uncertainty quantification methods in enhancing applicability of predictive models for radiation pneumonitis in healthcare settings.
MobiusFX showed interchangeable gamma passing rates with measurement-based methods at the 3%/3 mm and 3%/2 mm criteria, supporting its use as an alternative for VMAT pretreatment verification. Machine- and system-specific factors should be considered for reliable clinical implementation.
