arXiv subjects

David Fuentes

Publications and source records attributed to David Fuentes.

At least 19 recordsLinked to original sources

arXiv2026

Risk Prediction in Cancer Imaging Using Enriched Radiomics Features

Background: We aim to develop enriched radiomics features that integrate classical structural radiomics with novel functional radiomics derived from liver MRI for diagnosis and risk stratification in liver cancer. The proposed framework leverages enhancement pattern mapping (EPM) images to provide an automated and robust radiomics representation that captures intratumoral heterogeneity through pixel-level functional information. Methods: Pixel-wise EPM data reflecting blood perfusion were extracted from T1-weighted MRI scans. Classical structural radiomics features were extracted via existing software such as PyRadiomics. In addition, empirical quantiles of EPM values over all pixels within the image, and then smoothed using suitable basis. The smoothed quantiles, along with the classical structural quantiles, are used as functional radiomics features for diagnostic classification and tumor grade stratification, using L1-penalized logistic model that automatically downweights the contribution of the irrelevant features. Further, we conducted longitudinal analyses using Bayesian tensor response regression, which enables spatial smoothing and parsimonious modeling of temporally evolving imaging patterns. Results: The enriched radiomics features illustrate higher diagnostic classification performance (AUC=0.96, sensitivity> 0.8) and superior tumor grade stratification accuracy (AUC=0.87, sensitivity=0.8) compared to alternate radiomics features. Moreover, we find that the proportion of lesion pixels with significant reduction in EPM values over time is considerably higher (median = 0.12) in aggressive lesions versus stable or mildly aggressive lesions (median = 0.025). Conclusion: The enriched novel radiomics features can potentially replace classical radiomics analysis and be used for imaging biomarkers in cross-sectional and in longitudinal cancer imaging studies.

stat.AP↗

arXiv2025

Pre- and Post-Treatment Glioma Segmentation with the Medical Imaging Segmentation Toolkit

Medical image segmentation continues to advance rapidly, yet rigorous comparison between methods remains challenging due to a lack of standardized and customizable tooling. In this work, we present the current state of the Medical Imaging Segmentation Toolkit (MIST), with a particular focus on its flexible and modular postprocessing framework designed for the BraTS 2025 pre- and post-treatment glioma segmentation challenge. Since its debut in the 2024 BraTS adult glioma post-treatment segmentation challenge, MIST's postprocessing module has been significantly extended to support a wide range of transforms, including removal or replacement of small objects, extraction of the largest connected components, and morphological operations such as hole filling and closing. These transforms can be composed into user-defined strategies, enabling fine-grained control over the final segmentation output. We evaluate three such strategies - ranging from simple small-object removal to more complex, class-specific pipelines - and rank their performance using the BraTS ranking protocol. Our results highlight how MIST facilitates rapid experimentation and targeted refinement, ultimately producing high-quality segmentations for the BraTS 2025 challenge. MIST remains open source and extensible, supporting reproducible and scalable research in medical image segmentation.

cs.CV↗

arXiv2025

A Priori Generalizability Estimate for a CNN

We formulate truncated singular value decompositions of entire convolutional neural networks. We demonstrate the computed left and right singular vectors are useful in identifying which images the convolutional neural network is likely to perform poorly on. To create this diagnostic tool, we define two metrics: the Right Projection Ratio and the Left Projection Ratio. The Right (Left) Projection Ratio evaluates the fidelity of the projection of an image (label) onto the computed right (left) singular vectors. We observe that both ratios are able to identify the presence of class imbalance for an image classification problem. Additionally, the Right Projection Ratio, which only requires unlabeled data, is found to be correlated to the model's performance when applied to image segmentation. This suggests the Right Projection Ratio could be a useful metric to estimate how likely the model is to perform well on a sample.

cs.CV↗

arXiv2025

Learning Discontinuous Galerkin Solutions to Elliptic Problems via Small Linear Convolutional Neural Networks

In recent years, there has been an increasing interest in using deep learning and neural networks to tackle scientific problems, particularly in solving partial differential equations (PDEs). However, many neural network-based methods, such as physics-informed neural networks, depend on automatic differentiation and the sampling of collocation points, which can result in a lack of interpretability and lower accuracy compared to traditional numerical methods. To address this issue, we propose two approaches for learning discontinuous Galerkin solutions to PDEs using small linear convolutional neural networks. Our first approach is supervised and depends on labeled data, while our second approach is unsupervised and does not rely on any training data. In both cases, our methods use substantially fewer parameters than similar numerics-based neural networks while also demonstrating comparable accuracy to the true and DG solutions for elliptic problems.

cs.LG↗

arXiv2025

Adaptive Collocation Point Strategies For Physics Informed Neural Networks via the QR Discrete Empirical Interpolation Method

Physics-informed neural networks (PINNs) have gained significant attention for solving forward and inverse problems related to partial differential equations (PDEs). While advancements in loss functions and network architectures have improved PINN accuracy, the impact of collocation point sampling on their performance remains underexplored. Fixed sampling methods, such as uniform random sampling and equispaced grids, can fail to capture critical regions with high solution gradients, limiting their effectiveness for complex PDEs. Adaptive methods, inspired by adaptive mesh refinement from traditional numerical methods, address this by dynamically updating collocation points during training but may overlook residual dynamics between updates, potentially losing valuable information. To overcome this limitation, we propose two adaptive collocation point selection strategies utilizing the QR Discrete Empirical Interpolation Method (QR-DEIM), a reduced-order modeling technique for efficiently approximating nonlinear functions. Our results on benchmark PDEs demonstrate that our QR-DEIM-based approaches improve PINN accuracy compared to existing methods, offering a promising direction for adaptive collocation point strategies.

cs.LG↗

arXiv2024

Precision in the Face of Noise -- Lessons from Kahneman, Siboney, and Sunstein for Radiation Oncology

In this manuscript, we draw on the insights from Kahneman, Sibony, and Sunsteins influential nonfiction book Noise: A Flaw in Human Judgment to explore the concept of unwanted variability in judgment (i.e., noise). We introduce key terms and connect these insights to the field of radiation oncology by illustrating how noise contributes to errors in clinically relevant areas such as contouring. Additionally, we propose practical strategies to reduce noise in radiation oncology, such as through judgment aggregation and the use of artificial intelligence tools, building on the principles outlined in the book.

physics.med-ph↗

arXiv2024

Deep Learning-Based Automated Post-Operative Gross Tumor Volume Segmentation in Glioblastoma Patients

Precise automated delineation of post-operative gross tumor volume in glioblastoma cases is challenging and time-consuming owing to the presence of edema and the deformed brain tissue resulting from the surgical tumor resection. To develop a model for automated delineation of post-operative gross tumor volumes in glioblastoma, we proposed a novel 3D double pocket U-Net architecture that has two parallel pocket U-Nets. Both U-Nets were trained simultaneously with two different subsets of MRI sequences and the output from the models was combined to do the final prediction. We strategically combined the MRI input sequences (T1, T2, T1C, FL) for model training to achieve improved segmentation accuracy. The dataset comprised 82 post-operative studies collected from 23 glioblastoma patients who underwent maximal safe tumor resection. All had gross tumor volume (GTV) segmentations performed by human experts, and these were used as a reference standard. The results of 3D double pocket U-Net were compared with baseline 3D pocket U-Net models and the ensemble of 3D pocket U-Net models. All the models were evaluated with fivefold cross-validation in terms of the Dice similarity coefficient and Hausdorff distance. Our proposed double U-Net model trained with input sequences [T1, T1C, FL + T2, T1C] achieved a better mean Dice score of 0.8585 and Hausdorff distance of 4.1942 compared to all the baseline models and ensemble models trained. The presence of infiltrating tumors and vasogenic edema in the post-operative MRI scans tends to reduce segmentation accuracy when considering the MRI sequences T1, T2, T1C, and FL together for model training. The double U-Net approach of combining subsets of the MRI sequences as distinct inputs for model training improves segmentation accuracy by 7% when compared with the conventional method of model training with all four sequences.

eess.IV↗

arXiv2024

Two Stage Segmentation of Cervical Tumors using PocketNet

Cervical cancer remains the fourth most common malignancy amongst women worldwide.1 Concurrent chemoradiotherapy (CRT) serves as the mainstay definitive treatment regimen for locally advanced cervical cancers and includes external beam radiation followed by brachytherapy.2 Integral to radiotherapy treatment planning is the routine contouring of both the target tumor at the level of the cervix, associated gynecologic anatomy and the adjacent organs at risk (OARs). However, manual contouring of these structures is both time and labor intensive and associated with known interobserver variability that can impact treatment outcomes. While multiple tools have been developed to automatically segment OARs and the high-risk clinical tumor volume (HR-CTV) using computed tomography (CT) images,3,4,5,6 the development of deep learning-based tumor segmentation tools using routine T2-weighted (T2w) magnetic resonance imaging (MRI) addresses an unmet clinical need to improve the routine contouring of both anatomical structures and cervical cancers, thereby increasing quality and consistency of radiotherapy planning. This work applied a novel deep-learning model (PocketNet) to segment the cervix, vagina, uterus, and tumor(s) on T2w MRI. The performance of the PocketNet architecture was evaluated, when trained on data via five-fold cross validation. PocketNet achieved a mean Dice-Sorensen similarity coefficient (DSC) exceeding 70% for tumor segmentation and 80% for organ segmentation. Validation on a publicly available dataset from The Cancer Imaging Archive (TCIA) demonstrated the models robustness, achieving DSC scores of 67.3% for tumor segmentation and 80.8% for organ segmentation. These results suggest that PocketNet is robust to variations in contrast protocols, providing reliable segmentation of the regions of interest.

cs.CV↗

arXiv2024

1D Thermoembolization Model Using CT Imaging Data for Porcine Liver

Objective: Innovative therapies such as thermoembolization are expected to play an important role in improvising care for patients with diseases such as hepatocellular carcinoma. Thermoembolization is a minimally invasive strategy that combines thermal ablation and embolization in a single procedure. This approach exploits an exothermic chemical reaction that occurs when an acid chloride is delivered via an endovascular route. However, comprehension of the complexities of the biophysics of thermoembolization is challenging. Mathematical models can aid in understanding such complex processes and assisting clinicians in making informed decisions. In this study, we used a Hagen Poiseuille 1D blood flow model to predict the mass transport and possible embolization locations in a porcine hepatic artery. Method: The 1D flow model was used on in vivo embolization imaging data of three pigs. The hydrolysis time constant of acid chloride chemical reaction was optimized for each pig, and LOOCV method was used to test the model's predictive ability. Conclusion: This basic model provided a balanced accuracy rate of 66.8% for identifying the possible locations of embolization in the hepatic artery. Use of the model provides an initial understanding of the vascular transport phenomena that are predicted to occur as a result of thermoembolization.

physics.med-ph↗

arXiv2024

MIST: A Simple and Scalable End-To-End 3D Medical Imaging Segmentation Framework

Medical imaging segmentation is a highly active area of research, with deep learning-based methods achieving state-of-the-art results in several benchmarks. However, the lack of standardized tools for training, testing, and evaluating new methods makes the comparison of methods difficult. To address this, we introduce the Medical Imaging Segmentation Toolkit (MIST), a simple, modular, and end-to-end medical imaging segmentation framework designed to facilitate consistent training, testing, and evaluation of deep learning-based medical imaging segmentation methods. MIST standardizes data analysis, preprocessing, and evaluation pipelines, accommodating multiple architectures and loss functions. This standardization ensures reproducible and fair comparisons across different methods. We detail MIST's data format requirements, pipelines, and auxiliary features and demonstrate its efficacy using the BraTS Adult Glioma Post-Treatment Challenge dataset. Our results highlight MIST's ability to produce accurate segmentation masks and its scalability across multiple GPUs, showcasing its potential as a powerful tool for future medical imaging research and development.

eess.IV↗

arXiv2023

Solutions to Elliptic and Parabolic Problems via Finite Difference Based Unsupervised Small Linear Convolutional Neural Networks

In recent years, there has been a growing interest in leveraging deep learning and neural networks to address scientific problems, particularly in solving partial differential equations (PDEs). However, many neural network-based methods like PINNs rely on auto differentiation and sampling collocation points, leading to a lack of interpretability and lower accuracy than traditional numerical methods. As a result, we propose a fully unsupervised approach, requiring no training data, to estimate finite difference solutions for PDEs directly via small linear convolutional neural networks. Our proposed approach uses substantially fewer parameters than similar finite difference-based approaches while also demonstrating comparable accuracy to the true solution for several selected elliptic and parabolic problems compared to the finite difference method.

cs.LG↗

arXiv2023

Evolving Horizons in Radiotherapy Auto-Contouring: Distilling Insights, Embracing Data-Centric Frameworks, and Moving Beyond Geometric Quantification

Deep learning has significantly advanced the potential for automated contouring in radiotherapy planning. In this manuscript, guided by contemporary literature, we underscore three key insights: (1) High-quality training data is essential for auto-contouring algorithms; (2) Auto-contouring models demonstrate commendable performance even with limited medical image data; (3) The quantitative performance of auto-contouring is reaching a plateau. Given these insights, we emphasize the need for the radiotherapy research community to embrace data-centric approaches to further foster clinical adoption of auto-contouring technologies.

physics.med-ph↗

arXiv2023

Distributed Conditional GAN (discGAN) For Synthetic Healthcare Data Generation

In this paper, we propose a distributed Generative Adversarial Networks (discGANs) to generate synthetic tabular data specific to the healthcare domain. While using GANs to generate images has been well studied, little to no attention has been given to generation of tabular data. Modeling distributions of discrete and continuous tabular data is a non-trivial task with high utility. We applied discGAN to model non-Gaussian multi-modal healthcare data. We generated 249,000 synthetic records from original 2,027 eICU dataset. We evaluated the performance of the model using machine learning efficacy, the Kolmogorov-Smirnov (KS) test for continuous variables and chi-squared test for discrete variables. Our results show that discGAN was able to generate data with distributions similar to the real data.

cs.LG↗

arXiv2023

FMG-Net and W-Net: Multigrid Inspired Deep Learning Architectures For Medical Imaging Segmentation

Accurate medical imaging segmentation is critical for precise and effective medical interventions. However, despite the success of convolutional neural networks (CNNs) in medical image segmentation, they still face challenges in handling fine-scale features and variations in image scales. These challenges are particularly evident in complex and challenging segmentation tasks, such as the BraTS multi-label brain tumor segmentation challenge. In this task, accurately segmenting the various tumor sub-components, which vary significantly in size and shape, remains a significant challenge, with even state-of-the-art methods producing substantial errors. Therefore, we propose two architectures, FMG-Net and W-Net, that incorporate the principles of geometric multigrid methods for solving linear systems of equations into CNNs to address these challenges. Our experiments on the BraTS 2020 dataset demonstrate that both FMG-Net and W-Net outperform the widely used U-Net architecture regarding tumor subcomponent segmentation accuracy and training efficiency. These findings highlight the potential of incorporating the principles of multigrid methods into CNNs to improve the accuracy and efficiency of medical imaging segmentation.

eess.IV↗

arXiv2023

A Generalized Surface Loss for Reducing the Hausdorff Distance in Medical Imaging Segmentation

Within medical imaging segmentation, the Dice coefficient and Hausdorff-based metrics are standard measures of success for deep learning models. However, modern loss functions for medical image segmentation often only consider the Dice coefficient or similar region-based metrics during training. As a result, segmentation architectures trained over such loss functions run the risk of achieving high accuracy for the Dice coefficient but low accuracy for Hausdorff-based metrics. Low accuracy on Hausdorff-based metrics can be problematic for applications such as tumor segmentation, where such benchmarks are crucial. For example, high Dice scores accompanied by significant Hausdorff errors could indicate that the predictions fail to detect small tumors. We propose the Generalized Surface Loss function, a novel loss function to minimize Hausdorff-based metrics with more desirable numerical properties than current methods and with weighting terms for class imbalance. Our loss function outperforms other losses when tested on the LiTS and BraTS datasets using the state-of-the-art nnUNet architecture. These results suggest we can improve medical imaging segmentation accuracy with our novel loss function.

eess.IV↗

arXiv2022

Resection cavity auto-contouring for patients with pediatric medulloblastoma using only CT information

Purpose: Target delineation for radiation therapy is a time-consuming and complex task. Autocontouring gross tumor volumes (GTVs) has been shown to increase efficiency. However, there is limited literature on post-operative target delineation, particularly for CT-based studies. To this end, we trained a CT-based autocontouring model to contour the post-operative GTV of pediatric patients with medulloblastoma. Methods: 104 retrospective pediatric CT scans were used to train a GTV auto-contouring model. 80 patients were then preselected for contour visibility, continuity, and location to train an additional model. Each GTV was manually annotated with a visibility score based on the number of slices with a visible GTV (1 = <25%, 2 = 25%-50%, 3 = >50%-75%, and 4 = >75%-100%). Contrast and the contrast-to-noise ratio (CNR) were calculated for the GTV contour with respect to a cropped background image. Both models were tested on the original and pre-selected testing sets. The resulting surface and overlap metrics were calculated comparing the clinical and autocontoured GTVs and the corresponding clinical target volumes (CTVs). Results: 80 patients were pre-selected to have a continuous GTV within the posterior fossa. Of these, 7, 41, 21, and 11 were visibly scored as 4, 3, 2, and 1, respectively. The contrast and CNR removed an additional 11 and 20 patients from the dataset, respectively. The Dice similarity coefficients (DSC) were 0.61 +/- 0.29 and 0.67 +/- 0.22 on the models without pre-selected training data and 0.55 +/- 13.01 and 0.83 +/- 0.17 on the models with pre-selected data, respectively. The DSC on the CTV expansions were 0.90 +/- 0.13. Conclusion: We automatically contoured continuous GTVs within the posterior fossa on scans that had contrast >=10 HU. CT-Based auto-contouring algorithms have potential to positively impact centers with limited MRI access.

physics.med-ph↗

arXiv2022

Deep Learning-Based Dose Prediction for Automated, Individualized Quality Assurance of Head and Neck Radiation Therapy Plans

Purpose: This study aimed to use deep learning-based dose prediction to assess head and neck (HN) plan quality and identify suboptimal plans. Methods: A total of 245 VMAT HN plans were created using RapidPlan knowledge-based planning (KBP). A subset of 112 high-quality plans was selected under the supervision of an HN radiation oncologist. We trained a 3D Dense Dilated U-Net architecture to predict 3-dimensional dose distributions using 3-fold cross-validation on 90 plans. Model inputs included CT images, target prescriptions, and contours for targets and organs at risk (OARs). The model's performance was assessed on the remaining 22 test plans. We then tested the application of the dose prediction model for automated review of plan quality. Dose distributions were predicted on 14 clinical plans. The predicted versus clinical OAR dose metrics were compared to flag OARs with suboptimal normal tissue sparing using a 2 Gy dose difference or 3% dose-volume threshold. OAR flags were compared to manual flags by 3 HN radiation oncologists. Results: The predicted dose distributions were of comparable quality to the KBP plans. The differences between the predicted and KBP-planned D1%, D95%, and D99% across the targets were within -2.53%(SD=1.34%), -0.42%(SD=1.27%), and -0.12%(SD=1.97%), respectively, and the OAR mean and maximum doses were within -0.33Gy(SD=1.40Gy) and -0.96Gy(SD=2.08Gy). For the plan quality assessment study, radiation oncologists flagged 47 OARs for possible plan improvement. There was high interphysician variability; 83% of physician-flagged OARs were flagged by only one of 3 physicians. The comparative dose prediction model flagged 63 OARs, including 30 of 47 physician-flagged OARs. Conclusion: Deep learning can predict high-quality dose distributions, which can be used as comparative dose distributions for automated, individualized assessment of HN plan quality.

physics.med-ph↗

arXiv2022

Automation of Radiation Treatment Planning for Rectal Cancer

To develop an automated workflow for rectal cancer three-dimensional conformal radiotherapy treatment planning that combines deep-learning(DL) aperture predictions and forward-planning algorithms. We designed an algorithm to automate the clinical workflow for planning with field-in-field. DL models were trained, validated, and tested on 555 patients to automatically generate aperture shapes for primary and boost fields. Network inputs were digitally reconstructed radiography, gross tumor volume(GTV), and nodal GTV. A physician scored each aperture for 20 patients on a 5-point scale(>3 acceptable). A planning algorithm was then developed to create a homogeneous dose using a combination of wedges and subfields. The algorithm iteratively identifies a hotspot volume, creates a subfield, and optimizes beam weight all without user intervention. The algorithm was tested on 20 patients using clinical apertures with different settings, and the resulting plans(4 plans/patient) were scored by a physician. The end-to-end workflow was tested and scored by a physician on 39 patients using DL-generated apertures and planning algorithms. The predicted apertures had Dice scores of 0.95, 0.94, and 0.90 for posterior-anterior, laterals, and boost fields, respectively. 100%, 95%, and 87.5% of the posterior-anterior, laterals, and boost apertures were scored as clinically acceptable, respectively. Wedged and non-wedged plans were clinically acceptable for 85% and 50% of patients, respectively. The final plans hotspot dose percentage was reduced from 121%($\pm$ 14%) to 109%($\pm$ 5%) of prescription dose. The integrated end-to-end workflow of automatically generated apertures and optimized field-in-field planning gave clinically acceptable plans for 38/39(97%) of patients. We have successfully automated the clinical workflow for generating radiotherapy plans for rectal cancer for our institution.

physics.med-ph↗