RESUMEN
PURPOSE: In pediatric medicine, precise estimation of bone age is essential for skeletal maturity evaluation, growth disorder diagnosis, and therapeutic intervention planning. Conventional techniques for determining bone age depend on radiologists' subjective judgments, which may lead to non-negligible differences in the estimated bone age. This study proposes a deep learning-based model utilizing a fully connected convolutional neural network(CNN) to predict bone age from left-hand radiographs. METHODS: The data set used in this study, consisting of 473 patients, was retrospectively retrieved from the PACS (Picture Achieving and Communication System) of a single institution. We developed a fully connected CNN consisting of four convolutional blocks, three fully connected layers, and a single neuron as output. The model was trained and validated on 80% of the data using the mean-squared error as a cost function to minimize the difference between the predicted and reference bone age values through the Adam optimization algorithm. Data augmentation was applied to the training and validation sets yielded in doubling the data samples. The performance of the trained model was evaluated on a test data set (20%) using various metrics including, the mean absolute error (MAE), median absolute error (MedAE), root-mean-squared error (RMSE), and mean absolute percentage error (MAPE). The code of the developed model for predicting the bone age in this study is available publicly on GitHub at https://github.com/afiosman/deep-learning-based-bone-age-estimation . RESULTS: Experimental results demonstrate the sound capabilities of our model in predicting the bone age on the left-hand radiographs as in the majority of the cases, the predicted bone ages and reference bone ages are nearly close to each other with a calculated MAE of 2.3 [1.9, 2.7; 0.95 confidence level] years, MedAE of 2.1 years, RMAE of 3.0 [1.5, 4.5; 0.95 confidence level] years, and MAPE of 0.29 (29%) on the test data set. CONCLUSION: These findings highlight the usability of estimating the bone age from left-hand radiographs, helping radiologists to verify their own results considering the margin of error on the model. The performance of our proposed model could be improved with additional refining and validation.
Asunto(s)
Determinación de la Edad por el Esqueleto , Aprendizaje Profundo , Humanos , Estudios Retrospectivos , Determinación de la Edad por el Esqueleto/métodos , Niño , Femenino , Masculino , Arabia Saudita , Adolescente , Preescolar , Lactante , Redes Neurales de la Computación , Huesos de la Mano/diagnóstico por imagen , Huesos de la Mano/crecimiento & desarrolloRESUMEN
BACKGROUND: Direction Modulated Brachytherapy (DMBT) enables conformal dose distributions. However, clinicians may face challenges in creating viable treatment plans within a fast-paced clinical setting, especially for a novel technology like DMBT, where cumulative clinical experience is limited. Deep learning-based dose prediction methods have emerged as effective tools for enhancing efficiency. PURPOSE: To develop a voxel-wise dose prediction model using an attention-gating mechanism and a 3D UNET for cervical cancer high-dose-rate (HDR) brachytherapy treatment planning with DMBT six-groove tandems with ovoids or ring applicators. METHODS: A multi-institutional cohort of 122 retrospective clinical HDR brachytherapy plans treated to a prescription dose in the range of 4.8-7.0 Gy/fraction was used. A DMBT tandem model was constructed and incorporated onto a research version of BrachyVision Treatment Planning System (BV-TPS) as a 3D solid model applicator and retrospectively re-planned all cases by seasoned experts. Those plans were randomly divided into 64:16:20 as training, validating, and testing cohorts, respectively. Data augmentation was applied to the training and validation sets to increase the size by a factor of 4. An attention-gated 3D UNET architecture model was developed to predict full 3D dose distributions based on high-risk clinical target volume (CTVHR) and organs at risk (OARs) contour information. The model was trained using the mean absolute error loss function, Adam optimization algorithm, a learning rate of 0.001, 250 epochs, and a batch size of eight. In addition, a baseline UNET model was trained similarly for comparison. The model performance was evaluated on the testing dataset by analyzing the outcomes in terms of mean dose values and derived dose-volume-histogram indices from 3D dose distributions and comparing the generated dose distributions against the ground-truth dose distributions using dose statistics and clinically meaningful dosimetric indices. RESULTS: The proposed attention-gated 3D UNET model showed competitive accuracy in predicting 3D dose distributions that closely resemble the ground-truth dose distributions. The average values of the mean absolute errors were 1.82 ± 29.09 Gy (vs. 6.41 ± 20.16 Gy for a baseline UNET) in CTVHR, 0.89 ± 1.25 Gy (vs. 0.94 ± 3.96 Gy for a baseline UNET) in the bladder, 0.33 ± 0.67 Gy (vs. 0.53 ± 1.66 Gy for a baseline UNET) in the rectum, and 0.55 ± 1.57 Gy (vs. 0.76 ± 2.89 Gy for a baseline UNET) in the sigmoid. The results showed that the mean absolute error (MAE) for the bladder, rectum, and sigmoid were 0.22 ± 1.22 Gy (3.62%) (p = 0.015), 0.21 ± 1.06 Gy (2.20%) (p = 0.172), and -0.03 ± 0.54 Gy (1.13%) (p = 0.774), respectively. The MAE for D90, V100%, and V150% of the CTVHR were 0.46 ± 2.44 Gy (8.14%) (p = 0.018), 0.57 ± 11.25% (5.23%) (p = 0.283), and -0.43 ± 19.36% (4.62%) (p = 0.190), respectively. The proposed model needs less than 5 s to predict a full 3D dose distribution of 64 × 64 × 64 voxels for any new patient plan, thus making it sufficient for near real-time applications and aiding with decision-making in the clinic. CONCLUSIONS: Attention gated 3D-UNET model demonstrated a capability in predicting voxel-wise dose prediction, in comparison to 3D UNET, for DMBT intracavitary brachytherapy planning. The proposed model could be used to obtain dose distributions for near real-time decision-making before DMBT planning and quality assurance. This will guide future automated planning, making the workflow more efficient and clinically viable.
Asunto(s)
Braquiterapia , Dosificación Radioterapéutica , Planificación de la Radioterapia Asistida por Computador , Neoplasias del Cuello Uterino , Humanos , Braquiterapia/métodos , Braquiterapia/instrumentación , Neoplasias del Cuello Uterino/radioterapia , Neoplasias del Cuello Uterino/diagnóstico por imagen , Femenino , Planificación de la Radioterapia Asistida por Computador/métodos , Estudios Retrospectivos , Dosis de Radiación , Aprendizaje ProfundoRESUMEN
PURPOSE: Accurate deformable registration of magnetic resonance imaging (MRI) scans containing pathologies is challenging due to changes in tissue appearance. In this paper, we developed a novel automated three-dimensional (3D) convolutional U-Net based deformable image registration (ConvUNet-DIR) method using unsupervised learning to establish correspondence between baseline pre-operative and follow-up MRI scans of patients with brain glioma. METHODS: This study involved multi-parametric brain MRI scans (T1, T1-contrast enhanced, T2, FLAIR) acquired at pre-operative and follow-up time for 160 patients diagnosed with glioma, representing the BraTS-Reg 2022 challenge dataset. ConvUNet-DIR, a deep learning-based deformable registration workflow using 3D U-Net style architecture as a core, was developed to establish correspondence between the MRI scans. The workflow consists of three components: (1) the U-Net learns features from pairs of MRI scans and estimates a mapping between them, (2) the grid generator computes the sampling grid based on the derived transformation parameters, and (3) the spatial transformation layer generates a warped image by applying the sampling operation using interpolation. A similarity measure was used as a loss function for the network with a regularization parameter limiting the deformation. The model was trained via unsupervised learning using pairs of MRI scans on a training data set (n = 102) and validated on a validation data set (n = 26) to assess its generalizability. Its performance was evaluated on a test set (n = 32) by computing the Dice score and structural similarity index (SSIM) quantitative metrics. The model's performance also was compared with the baseline state-of-the-art VoxelMorph (VM1 and VM2) learning-based algorithms. RESULTS: The ConvUNet-DIR model showed promising competency in performing accurate 3D deformable registration. It achieved a mean Dice score of 0.975 ± 0.003 and SSIM of 0.908 ± 0.011 on the test set (n = 32). Experimental results also demonstrated that ConvUNet-DIR outperformed the VoxelMorph algorithms concerning Dice (VM1: 0.969 ± 0.006 and VM2: 0.957 ± 0.008) and SSIM (VM1: 0.893 ± 0.012 and VM2: 0.857 ± 0.017) metrics. The time required to perform a registration for a pair of MRI scans is about 1 s on the CPU. CONCLUSIONS: The developed deep learning-based model can perform an end-to-end deformable registration of a pair of 3D MRI scans for glioma patients without human intervention. The model could provide accurate, efficient, and robust deformable registration without needing pre-alignment and labeling. It outperformed the state-of-the-art VoxelMorph learning-based deformable registration algorithms and other supervised/unsupervised deep learning-based methods reported in the literature.
Asunto(s)
Neoplasias Encefálicas , Aprendizaje Profundo , Glioma , Imagen por Resonancia Magnética , Aprendizaje Automático no Supervisado , Humanos , Imagen por Resonancia Magnética/métodos , Neoplasias Encefálicas/diagnóstico por imagen , Neoplasias Encefálicas/radioterapia , Glioma/diagnóstico por imagen , Glioma/radioterapia , Glioma/patología , Oncología por Radiación/métodos , Procesamiento de Imagen Asistido por Computador/métodos , Imagenología Tridimensional/métodosRESUMEN
Recent studies have raised broad safety and health concerns about using of gadolinium contrast agents during magnetic resonance imaging (MRI) to enhance identification of active tumors. In this paper, we developed a deep learning-based method for three-dimensional (3D) contrast-enhanced T1-weighted (T1) image synthesis from contrast-free image(s). The MR images of 1251 patients with glioma from the RSNA-ASNR-MICCAI BraTS Challenge 2021 dataset were used in this study. A 3D dense-dilated residual U-Net (DD-Res U-Net) was developed for contrast-enhanced T1 image synthesis from contrast-free image(s). The model was trained on a randomly split training set (n = 800) using a customized loss function and validated on a validation set (n = 200) to improve its generalizability. The generated images were quantitatively assessed against the ground-truth on a test set (n = 251) using the mean absolute error (MAE), mean-squared error (MSE), peak signal-to-noise ratio (PSNR), structural similarity (SSIM), normalized mutual information (NMI), and Hausdorff distance (HDD) metrics. We also performed a qualitative visual similarity assessment between the synthetic and ground-truth images. The effectiveness of the proposed model was compared with a 3D U-Net baseline model and existing deep learning-based methods in the literature. Our proposed DD-Res U-Net model achieved promising performance for contrast-enhanced T1 synthesis in both quantitative metrics and perceptual evaluation on the test set (n = 251). Analysis of results on the whole brain region showed a PSNR (in dB) of 29.882 ± 5.924, a SSIM of 0.901 ± 0.071, a MAE of 0.018 ± 0.013, a MSE of 0.002 ± 0.002, a HDD of 2.329 ± 9.623, and a NMI of 1.352 ± 0.091 when using only T1 as input; and a PSNR (in dB) of 30.284 ± 4.934, a SSIM of 0.915 ± 0.063, a MAE of 0.017 ± 0.013, a MSE of 0.001 ± 0.002, a HDD of 1.323 ± 3.551, and a NMI of 1.364 ± 0.089 when combining T1 with other MRI sequences. Compared to the U-Net baseline model, our model revealed superior performance. Our model demonstrated excellent capability in generating synthetic contrast-enhanced T1 images from contrast-free MR image(s) of the whole brain region when using multiple contrast-free images as input. Without incorporating tumor mask information during network training, its performance was inferior in the tumor regions compared to the whole brain which requires further improvements to replace the gadolinium administration in neuro-oncology.
Asunto(s)
Gadolinio , Neoplasias , Humanos , Procesamiento de Imagen Asistido por Computador/métodos , Imagen por Resonancia Magnética/métodos , EncéfaloRESUMEN
PURPOSE: In this paper, we compare four novel knowledge-based planning (KBP) algorithms using deep learning to predict three-dimensional (3D) dose distributions of head and neck plans using the same patients' dataset and quantitative assessment metrics. METHODS: A dataset of 340 oropharyngeal cancer patients treated with intensity-modulated radiation therapy was used in this study, which represents the AAPM OpenKBP - 2020 Grand Challenge dataset. Four 3D convolutional neural network architectures were built. The models were trained on 64% of the data set and validated on 16% for voxel-wise dose predictions: U-Net, attention U-Net, residual U-Net (Res U-Net), and attention Res U-Net. The trained models were then evaluated for their performance on a test data set (20% of the data) by comparing the predicted dose distributions against the ground-truth using dose statistics and dose-volume indices. RESULTS: The four KBP dose prediction models exhibited promising performance with an averaged mean absolute dose error within the body contour <3 Gy on 68 plans in the test set. The average difference in predicting the D99 index for all targets was 0.92 Gy (p = 0.51) for attention Res U-Net, 0.94 Gy (p = 0.40) for Res U-Net, 2.94 Gy (p = 0.09) for attention U-Net, and 3.51 Gy (p = 0.08) for U-Net. For the OARs, the values for the D m a x ${D_{max}}$ and D m e a n ${D_{mean}}$ indices were 2.72 Gy (p < 0.01) for attention Res U-Net, 2.94 Gy (p < 0.01) for Res U-Net, 1.10 Gy (p < 0.01) for attention U-Net, 0.84 Gy (p < 0.29) for U-Net. CONCLUSION: All models demonstrated almost comparable performance for voxel-wise dose prediction. KBP models that employ 3D U-Net architecture as a base could be deployed for clinical use to improve cancer patient treatment by creating plans with consistent quality and making the radiotherapy workflow more efficient.
Asunto(s)
Aprendizaje Profundo , Radioterapia de Intensidad Modulada , Humanos , Dosificación Radioterapéutica , Planificación de la Radioterapia Asistida por Computador/métodos , Cuello , Cabeza , Radioterapia de Intensidad Modulada/métodos , Órganos en RiesgoRESUMEN
Objective.To establish an open framework for developing plan optimization models for knowledge-based planning (KBP).Approach.Our framework includes radiotherapy treatment data (i.e. reference plans) for 100 patients with head-and-neck cancer who were treated with intensity-modulated radiotherapy. That data also includes high-quality dose predictions from 19 KBP models that were developed by different research groups using out-of-sample data during the OpenKBP Grand Challenge. The dose predictions were input to four fluence-based dose mimicking models to form 76 unique KBP pipelines that generated 7600 plans (76 pipelines × 100 patients). The predictions and KBP-generated plans were compared to the reference plans via: the dose score, which is the average mean absolute voxel-by-voxel difference in dose; the deviation in dose-volume histogram (DVH) points; and the frequency of clinical planning criteria satisfaction. We also performed a theoretical investigation to justify our dose mimicking models.Main results.The range in rank order correlation of the dose score between predictions and their KBP pipelines was 0.50-0.62, which indicates that the quality of the predictions was generally positively correlated with the quality of the plans. Additionally, compared to the input predictions, the KBP-generated plans performed significantly better (P< 0.05; one-sided Wilcoxon test) on 18 of 23 DVH points. Similarly, each optimization model generated plans that satisfied a higher percentage of criteria than the reference plans, which satisfied 3.5% more criteria than the set of all dose predictions. Lastly, our theoretical investigation demonstrated that the dose mimicking models generated plans that are also optimal for an inverse planning model.Significance.This was the largest international effort to date for evaluating the combination of KBP prediction and optimization models. We found that the best performing models significantly outperformed the reference dose and dose predictions. In the interest of reproducibility, our data and code is freely available.
Asunto(s)
Planificación de la Radioterapia Asistida por Computador , Radioterapia de Intensidad Modulada , Humanos , Bases del Conocimiento , Dosificación Radioterapéutica , Planificación de la Radioterapia Asistida por Computador/métodos , Radioterapia de Intensidad Modulada/métodos , Reproducibilidad de los ResultadosRESUMEN
PURPOSE: Deep learning-based knowledge-based planning (KBP) methods have been introduced for radiotherapy dose distribution prediction to reduce the planning time and maintain consistent high-quality plans. This paper presents a novel KBP model using an attention-gating mechanism and a three-dimensional (3D) U-Net for intensity-modulated radiation therapy (IMRT) 3D dose distribution prediction in head-and-neck cancer. METHODS: A total of 340 head-and-neck cancer plans, representing the OpenKBP-2020 AAPM Grand Challenge data set, were used in this study. All patients were treated with the IMRT technique and a dose prescription of 70 Gy. The data set was randomly divided into 64%/16%/20% as training/validation/testing cohorts. An attention-gated 3D U-Net architecture model was developed to predict full 3D dose distribution. The developed model was trained using the mean-squared error loss function, Adam optimization algorithm, a learning rate of 0.001, 120 epochs, and batch size of 4. In addition, a baseline U-Net model was also similarly trained for comparison. The model performance was evaluated on the testing data set by comparing the generated dose distributions against the ground-truth dose distributions using dose statistics and clinical dosimetric indices. Its performance was also compared to the baseline model and the reported results of other deep learning-based dose prediction models. RESULTS: The proposed attention-gated 3D U-Net model showed high capability in accurately predicting 3D dose distributions that closely replicated the ground-truth dose distributions of 68 plans in the test set. The average value of the mean absolute dose error was 2.972 ± 1.220 Gy (vs. 2.920 ± 1.476 Gy for a baseline U-Net) in the brainstem, 4.243 ± 1.791 Gy (vs. 4.530 ± 2.295 Gy for a baseline U-Net) in the left parotid, 4.622 ± 1.975 Gy (vs. 4.223 ± 1.816 Gy for a baseline U-Net) in the right parotid, 3.346 ± 1.198 Gy (vs. 2.958 ± 0.888 Gy for a baseline U-Net) in the spinal cord, 6.582 ± 3.748 Gy (vs. 5.114 ± 2.098 Gy for a baseline U-Net) in the esophagus, 4.756 ± 1.560 Gy (vs. 4.992 ± 2.030 Gy for a baseline U-Net) in the mandible, 4.501 ± 1.784 Gy (vs. 4.925 ± 2.347 Gy for a baseline U-Net) in the larynx, 2.494 ± 0.953 Gy (vs. 2.648 ± 1.247 Gy for a baseline U-Net) in the PTV_70, and 2.432 ± 2.272 Gy (vs. 2.811 ± 2.896 Gy for a baseline U-Net) in the body contour. The average difference in predicting the D99 value for the targets (PTV_70, PTV_63, and PTV_56) was 2.50 ± 1.77 Gy. For the organs at risk, the average difference in predicting the D m a x ${D_{max}}$ (brainstem, spinal cord, and mandible) and D m e a n ${D_{mean}}$ (left parotid, right parotid, esophagus, and larynx) values was 1.43 ± 1.01 and 2.44 ± 1.73 Gy, respectively. The average value of the homogeneity index was 7.99 ± 1.45 for the predicted plans versus 5.74 ± 2.95 for the ground-truth plans, whereas the average value of the conformity index was 0.63 ± 0.17 for the predicted plans versus 0.89 ± 0.19 for the ground-truth plans. The proposed model needs less than 5 s to predict a full 3D dose distribution of 64 × 64 × 64 voxels for a new patient that is sufficient for real-time applications. CONCLUSIONS: The attention-gated 3D U-Net model demonstrated a capability in predicting accurate 3D dose distributions for head-and-neck IMRT plans with consistent quality. The prediction performance of the proposed model was overall superior to a baseline standard U-Net model, and it was also competitive to the performance of the best state-of-the-art dose prediction method reported in the literature. The proposed model could be used to obtain dose distributions for decision-making before planning, quality assurance of planning, and guiding-automated planning for improved plan consistency, quality, and planning efficiency.
Asunto(s)
Neoplasias de Cabeza y Cuello , Radioterapia de Intensidad Modulada , Atención , Neoplasias de Cabeza y Cuello/radioterapia , Humanos , Redes Neurales de la Computación , Órganos en Riesgo , Dosificación Radioterapéutica , Planificación de la Radioterapia Asistida por Computador/métodos , Radioterapia de Intensidad Modulada/métodosRESUMEN
PURPOSE: The existence of multicontrast magnetic resonance (MR) images increases the level of clinical information available for the diagnosis and treatment of brain cancer patients. However, acquiring the complete set of multicontrast MR images is not always practically feasible. In this study, we developed a state-of-the-art deep learning convolutional neural network (CNN) for image-to-image translation across three standards MRI contrasts for the brain. METHODS: BRATS'2018 MRI dataset of 477 patients clinically diagnosed with glioma brain cancer was used in this study, with each patient having T1-weighted (T1), T2-weighted (T2), and FLAIR contrasts. It was randomly split into 64%, 16%, and 20% as training, validation, and test set, respectively. We developed a U-Net model to learn the nonlinear mapping of a source image contrast to a target image contrast across three MRI contrasts. The model was trained and validated with 2D paired MR images using a mean-squared error (MSE) cost function, Adam optimizer with 0.001 learning rate, and 120 epochs with a batch size of 32. The generated synthetic-MR images were evaluated against the ground-truth images by computing the MSE, mean absolute error (MAE), peak signal-to-noise ratio (PSNR), and structural similarity index (SSIM). RESULTS: The generated synthetic-MR images with our model were nearly indistinguishable from the real images on the testing dataset for all translations, except synthetic FLAIR images had slightly lower quality and exhibited loss of details. The range of average PSNR, MSE, MAE, and SSIM values over the six translations were 29.44-33.25 dB, 0.0005-0.0012, 0.0086-0.0149, and 0.932-0.946, respectively. Our results were as good as the best-reported results by other deep learning models on BRATS datasets. CONCLUSIONS: Our U-Net model exhibited that it can accurately perform image-to-image translation across brain MRI contrasts. It could hold great promise for clinical use for improved clinical decision-making and better diagnosis of brain cancer patients due to the availability of multicontrast MRIs. This approach may be clinically relevant and setting a significant step to efficiently fill a gap of absent MR sequences without additional scanning.
Asunto(s)
Neoplasias Encefálicas , Aprendizaje Profundo , Encéfalo/diagnóstico por imagen , Neoplasias Encefálicas/diagnóstico por imagen , Humanos , Procesamiento de Imagen Asistido por Computador/métodos , Imagen por Resonancia Magnética/métodos , Redes Neurales de la ComputaciónRESUMEN
In order to deliver accurate and safe treatment to cancer patients in radiation therapy using advanced techniques such as intensity modulated radiation therapy (IMRT) and volumetric-arc radiation therapy (VMAT), patient specific quality assurance (QA) should be performed before treatment. IMRT/VMAT dose measurements in a phantom using various devices have been clinically adopted as standard method for QA. This approach allows the verification of the accuracy of the dose calculation, data transfer, and the delivery system. However, patient-specific QA procedures are expensive and require significant time and effort by the physicists. Over the past 5 years, machine learning (ML) and deep learning (DL) algorithms for predictions of IMRT/VMAT QA outcome have been investigated. Various ML and DL models have shown promising prediction accuracy and a high potential as time-efficient virtual QA tool. In this paper, we review the ML and DL based models that were developed for patient specific IMRT and VMAT QA outcome predictions from algorithmic and clinical applicability perspectives. We focus on comparing the algorithms, the dataset sizes, the input parameters and features, the QA outcome prediction approaches, the validation, the performance, the clinical applicability, and the potential clinical impact. In addition, we discuss the present challenges as well as the future directions in the implementation of these models. To the best of our knowledge, this is the first review on the application of ML and DL based models in IMRT/VMAT QA predictions.
Asunto(s)
Aprendizaje Profundo , Radioterapia de Intensidad Modulada , Humanos , Aprendizaje Automático , Fantasmas de Imagen , Garantía de la Calidad de Atención de Salud , Dosificación Radioterapéutica , Planificación de la Radioterapia Asistida por ComputadorRESUMEN
To obtain dose distributions more physically representative to the patient anatomy in brachytherapy, calculation algorithms that can account for heterogeneity are required. The current standard AAPM Task Group No 43 (TG-43) dose calculation formalism has some clinically relevant dosimetric limitations. Lack of tissue heterogeneity and scattered dose corrections are the major weaknesses of the TG-43 formalism and could lead to systematic dose errors in target volumes and organs at risk. Over the last decade, model-based dose calculation algorithms (MBDCAs) have been clinically offered as complementary algorithms beyond the TG43 formalism for high dose rate (HDR) brachytherapy treatment planning. These algorithms provide enhanced dose calculation accuracy by using the information in the patient's computed tomography images, which allows modeling the patient's geometry, material compositions, and the treatment applicator. Several researchers have investigated the implementation of MBDCAs in HDR brachytherapy for dose optimization, but moving toward using them as primary algorithms for dose calculations is still lagging. Therefore, an overview of up-to-date research is needed to familiarize clinicians with the current status of the MBDCAs for different cancers in HDR brachytherapy. In this paper, we review the MBDCAs for HDR brachytherapy from a dosimetric perspective. Treatment sites covered include breast, gynecological, lung, head and neck, esophagus, liver, prostate, and skin cancers. Moreover, we discuss the current status of implementation of MBDCAs and the challenges.
Asunto(s)
Braquiterapia , Algoritmos , Humanos , Método de Montecarlo , Dosis de Radiación , Dosificación Radioterapéutica , Planificación de la Radioterapia Asistida por ComputadorRESUMEN
PURPOSES: Multileaf collimator (MLC) positional accuracy during dynamic intensity modulation radiotherapy (IMRT) delivery is crucial for safe and accurate patient treatment. The deviations of individual leaf positions from its intended positions can lead to errors in the dose delivered to the patient and hence may adversely affect the treatment outcome. In this study, we propose a state-of-the-art machine learning (ML) method based on an artificial neural network (ANN) for accurately predicting the MLC leaf positional deviations during the dynamic IMRT treatment delivery priori using log file data. METHODS: Data of ten patients treated with sliding window dynamic IMRT delivery were retrospectively retrieved from a single-institution database. The patients' plans were redelivered with no patient on the couch using a Varian linear accelerator equipped with a Millennium 120 HD MLC system. Then the machine recorded log files data, a total of over 400 files containing 360 800 control points, were collected. A total of 14 parameters were extracted from the planning data in the log files such as leaf planned positions, dose fraction, leaf velocity, leaf moving status, leaf gap, and others. Next, we developed a feed-forward ANN architecture mapping the input parameters with the output to predict the MLC leaf positional deviations during the delivery priori. The proposed model was trained on 70% of the total data using the delivered leaf positional data as a target response. The trained model was then validated and tested on 30% of the available data. The model accuracy was evaluated using the mean squared error (MSE), regression plot, and error histogram. RESULTS: The deviations between the individual MLC planned and delivered positions can reach up to a few millimeters, with a maximum deviation of 1.2 mm. The predicted leaf positions at control points closely matched the delivered positions for all MLC leaves during the treatment delivery. The ANN model achieved a maximum MSE of 0.0001 mm2 (root MSE of 0.0097 mm) in predicting the leaf positions at control points of test data for each leaf. The correlation coefficient, that measures the goodness of fit, was perfect (R = 0.999) in all plots indicating an excellent agreement between the predicted and delivered MLC positions for the training, validation, and test data. CONCLUSIONS: We successfully demonstrated a proposed ANN-based method capable of accurately predicting the individual MLC leaf positional deviations during the dynamic IMRT delivery priori. Our ML model based on ANN outperformed the reported accuracy in the literature of various ML models. The results of this study could be extended to actual application in the dose calculation/optimization, hence enhancing the gamma passing rate for patient-specific IMRT quality assurance.
Asunto(s)
Redes Neurales de la Computación , Planificación de la Radioterapia Asistida por Computador/métodos , Radioterapia de Intensidad ModuladaRESUMEN
Purpose: Predicting patients' survival outcomes is recognized of key importance to clinicians in oncology toward determining an ideal course of treatment and patient management. This study applies radiomics analysis on pre-operative multi-parametric MRI of patients with glioblastoma from multiple institutions to identify a signature and a practical machine learning model for stratifying patients into groups based on overall survival. Methods: This study included 163 patients' data with glioblastoma, collected by BRATS 2018 Challenge from multiple institutions. In this proposed method, a set of 147 radiomics image features were extracted locally from three tumor sub-regions on standardized pre-operative multi-parametric MR images. LASSO regression was applied for identifying an informative subset of chosen features whereas a Cox model used to obtain the coefficients of those selected features. Then, a radiomics signature model of 9 features was constructed on the discovery set and it performance was evaluated for patients stratification into short- (<10 months), medium- (10-15 months), and long-survivors (>15 months) groups. Eight ML classification models, trained and then cross-validated, were tested to assess a range of survival prediction performance as a function of the choice of features. Results: The proposed mpMRI radiomics signature model had a statistically significant association with survival (P < 0.001) in the training set, but was not confirmed (P = 0.110) in the validation cohort. Its performance in the validation set had a sensitivity of 0.476 (short-), 0.231 (medium-), and 0.600 (long-survivors), and specificity of 0.667 (short-), 0.732 (medium-), and 0.794 (long-survivors). Among the tested ML classifiers, the ensemble learning model's results showed superior performance in predicting the survival classes, with an overall accuracy of 57.8% and AUC of 0.81 for short-, 0.47 for medium-, and 0.72 for long-survivors using the LASSO selected features combined with clinical factors. Conclusion: A derived GLCM feature, representing intra-tumoral inhomogeneity, was found to have a high association with survival. Clinical factors, when added to the radiomics image features, boosted the performance of the ML classification model in predicting individual glioblastoma patient's survival prognosis, which can improve prognostic quality a further step toward precision oncology.
RESUMEN
The accurate measurement of field output factors at small field sizes typically encountered in SRS and IMRT is challenging. In this study we measured detector output ratios for small fields using a range of detectors and orientations, we then calculated correction factors for each detector using film dosimetry as reference to obtain field output factors. The calculated correction factors were compared to the ones from TRS 483. Detectors used were: EBT3 Gafchromic film, PTW semiflex 31010 chamber, PTW pinpoint 31016 chamber, PTW diamond (used in two different orientations) and PTW SRS 60018 diode. Photon beam energies were 6 MV flat and 7 MV FFF with square field sizes from 0.5 to 10.0 cm side. Semiflex and pinpoint chambers agreed well with film down to 2.0 cm field size but under-responded by up to 40% at 0.5 cm field size. At 0.5 cm field size, diamond with stem parallel to beam axis under-estimated field output factors by up to 6.2%; diamond with stem perpendicular to beam axis over-estimated field output factors by up to 1.5% and diode over-estimated field output factors by up to 6.5%. Calculated correction factors, in general, agreed with and confirmed those given in TRS 483 film is an acceptable alternative to Monte Carlo simulation for deriving correction factors for solid state detectors. For field sizes smaller than 1.0 cm, diamond detector with stem perpendicular to beam axis was the most adequate for field output factor measurement, although not recommended in TRS 483.
RESUMEN
We studied the effects of the presence of an air cavity and scatter due to patient size on dose distribution near an Iriduim-192 brachytherapy source (Ir-192). The source was modeled using Monte Carlo (MC) code MCNP5. The Radial dose, gL(r), and the anisotropy function, F(r,θ) specified by the AAPM TG-43 have been determined and compared with the consensus data (AAPM report No. 229). We compared our MC results to the measured dose distribution using an EBT3 Gafchromic® film measurement. The dose was determined in the presence of an air cavity of 3, 5, and 7mm diameters located at 2mm distance from Ir-192. The dose was also determined for Ir-192 centered in 30×30×30cm3 and 80×80×80cm3 water phantoms. The MC results of gL(r) and F(r,θ) agreed with the consensus data to within 2% and 3%, respectively. The MC and the measured dose distributions agreed well with a maximum difference of 8.2% at the periphery of the film. The dose at 10cm from the Ir-192 source with a full scattering medium (80×80×80cm3) was 7% higher compared to the dose in (30×30×30cm3) water phantom. The dose to water in the presence of a 3, 5, and 7mm diameter air cavity increased by an average of 3%, 6%, and 9%, respectively, compared to the dose with no air cavity. Ignoring scatter effects and the heterogeneity correction in the presence of an air cavity can lead to significant errors in dose delivered to patients.