{rfName}
Ex

Indexed in

License and Use

Icono OpenAccess

Citations

3

Altmetrics

Analysis of institutional authors

Viar-Hernandez, DavidCorresponding AuthorManuel Molina-Maza, JuanAuthorRodriguez-Vila, BorjaAuthorMalpica, NorbertoAuthorTorrado-Carvajal, AngelAuthor

Share

October 29, 2024
Publications
>
Article
Sí

Exploring dual energy CT synthesis in CBCT-based adaptive radiotherapy and proton therapy: application of denoising diffusion probabilistic models

Publicated to: PHYSICS IN MEDICINE AND BIOLOGY. 69 (21): 215011- - 2024-11-07 69(21), DOI: 10.1088/1361-6560/ad8547

Authors:

Viar-Hernandez, D; Molina-Maza, JM; Pan, SY; Salari, E; Chang, CW; Eidex, Z; Zhou, J; Vera-Sanchez, JA; Rodriguez-Vila, B; Malpica, N; Torrado-Carvajal, A; Yang, XF
[+]

Affiliations

Ctr Protonterapia Quironsalud, Dept Fis Med, Madrid, Spain - Author
Emory Univ, Dept Radiat Oncol, Atlanta, GA 30322 USA - Author
Univ Rey Juan Carlos, Med Image Anal & Biometry Lab, Madrid, Spain - Author
See more

Abstract

Background. Adaptive radiotherapy (ART) requires precise tissue characterization to optimize treatment plans and enhance the efficacy of radiation delivery while minimizing exposure to organs at risk. Traditional imaging techniques such as cone beam computed tomography (CBCT) used in ART settings often lack the resolution and detail necessary for accurate dosimetry, especially in proton therapy. Purpose. This study aims to enhance ART by introducing an innovative approach that synthesizes dual-energy computed tomography (DECT) images from CBCT scans using a novel 3D conditional denoising diffusion probabilistic model (DDPM) multi-decoder. This method seeks to improve dose calculations in ART planning, enhancing tissue characterization. Methods. We utilized a paired CBCT-DECT dataset from 54 head and neck cancer patients to train and validate our DDPM model. The model employs a multi-decoder Swin-UNET architecture that synthesizes high-resolution DECT images by progressively reducing noise and artifacts in CBCT scans through a controlled diffusion process. Results. The proposed method demonstrated superior performance in synthesizing DECT images (High DECT MAE 39.582 +/- 0.855 and Low DECT MAE 48.540 +/- 1.833) with significantly enhanced signal-to-noise ratio and reduced artifacts compared to traditional GAN-based methods. It showed marked improvements in tissue characterization and anatomical structure similarity, critical for precise proton and radiation therapy planning. Conclusions. This research has opened a new avenue in CBCT-CT synthesis for ART/APT by generating DECT images using an enhanced DDPM approach. The demonstrated similarity between the synthesized DECT images and ground truth images suggests that these synthetic volumes can be used for accurate dose calculations, leading to better adaptation in treatment planning.
[+]

Keywords

AccuracyAdaptive proton therapyCone-beam computed tomographyCone-beam ctDect synthesiDect synthesisDiffusionDiffusion modelHeadHead and neck neoplasmsHumansImage processing, computer-assistedLunModels, statisticalNeckNetworkProton therapyRadiation-therapyRadiotherapy planning, computer-assistedRadiotherapy, image-guidedRange uncertaintiesSignal-to-noise ratio

Quality index

Bibliometric impact. Analysis of the contribution and dissemination channel

The work has been published in the journal PHYSICS IN MEDICINE AND BIOLOGY due to its progression and the good impact it has achieved in recent years, according to the agency WoS (JCR), it has become a reference in its field. In the year of publication of the work, 2024 there are still no calculated indicators, but in 2023, it was in position 44/213, thus managing to position itself as a Q1 (Primer Cuartil), in the category Radiology, Nuclear Medicine & Medical Imaging.

Independientemente del impacto esperado determinado por el canal de difusión, es importante destacar el impacto real observado de la propia aportación.

Según las diferentes agencias de indexación, el número de citas acumuladas por esta publicación hasta la fecha 2026-04-06:

  • WoS: 2
[+]

Impact and social visibility

From the perspective of influence or social adoption, and based on metrics associated with mentions and interactions provided by agencies specializing in calculating the so-called "Alternative or Social Metrics," we can highlight as of 2026-04-06:

  • The use of this contribution in bookmarks, code forks, additions to favorite lists for recurrent reading, as well as general views, indicates that someone is using the publication as a basis for their current work. This may be a notable indicator of future more formal and academic citations. This claim is supported by the result of the "Capture" indicator, which yields a total of: 4 (PlumX).

It is essential to present evidence supporting full alignment with institutional principles and guidelines on Open Science and the Conservation and Dissemination of Intellectual Heritage. A clear example of this is:

  • The work has been submitted to a journal whose editorial policy allows open Open Access publication.
[+]

Leadership analysis of institutional authors

This work has been carried out with international collaboration, specifically with researchers from: United States of America.

There is a significant leadership presence as some of the institution’s authors appear as the first or last signer, detailed as follows: First Author (Viar Hernández, David) .

the author responsible for correspondence tasks has been Viar Hernández, David.

[+]

Project objectives

Los objetivos perseguidos en esta aportación se centran en mejorar la radioterapia adaptativa (ART) mediante la síntesis de imágenes de tomografía computarizada de doble energía (DECT) a partir de escaneos de tomografía computarizada de haz cónico (CBCT). Se pretende desarrollar un modelo probabilístico de difusión condicional tridimensional (DDPM) con arquitectura multi-decodificador Swin-UNET para reducir el ruido y los artefactos en las imágenes CBCT. Además, se busca evaluar la precisión de la síntesis de imágenes DECT en términos de error medio absoluto (MAE) y la relación señal-ruido. Otro objetivo es mejorar la caracterización tisular y la similitud estructural anatómica para optimizar la planificación de dosis en ART y terapia con protones. Finalmente, se aspira a validar la aplicabilidad clínica de las imágenes sintetizadas para cálculos dosimétricos precisos.
[+]

Most relevant results

Los resultados más relevantes del estudio evidencian avances significativos en la síntesis de imágenes DECT a partir de CBCT para radioterapia adaptativa. En primer lugar, el modelo DDPM multi-decoder logró un error medio absoluto (MAE) de 39.582 ± 0.855 para DECT alta energía y 48.540 ± 1.833 para DECT baja energía. En segundo lugar, se observó una mejora sustancial en la relación señal-ruido y una reducción notable de artefactos en comparación con métodos basados en GAN. Además, se alcanzaron avances importantes en la caracterización tisular y la similitud estructural anatómica, aspectos cruciales para la planificación precisa en terapias de protones y radiación. Estos resultados respaldan la utilidad clínica del enfoque propuesto.
[+]

Awards linked to the item

This research is part of Project PID2020-116769RB-I00, Adaptive Proton Therapy Using Artificial Intelligence (ADAPT-AI), (PIs: Norberto Malpica and Angel Torrado-Carvajal) funded by Ministerio de Ciencia e Investigacion (MCIN)/Agencia Estatal de Investigacion (AEI).
[+]