This document is the report of a task group AAPM and has been prepared primarily to advise medical physicists involved in external-beam radiation therapy patients with thoracic, abdominal, pelvic tumors affected by respiratory motion. describes magnitude motion, discusses radiotherapy specific problems caused explains techniques that explicitly manage motion during gives recommendations application these for patient care, including quality assurance (QA) guidelines devices their use...

Radiographic image guidance has emerged as the new paradigm for patient positioning, target localization, and external beam alignment in radiotherapy. Although widely varied modality method, all radiographic techniques have one thing common--they can give a significant radiation dose to patient. As with medical uses of ionizing radiation, general view is that this exposure should be carefully managed. The philosophy management adopted by diagnostic imaging community summarized acronym ALARA,...

There has been some concern that organ motion, especially intra-fraction motion due to breathing, can negate the potential merit of intensity-modulated radiotherapy (IMRT). We wanted find out whether this is justified. Specifically, we investigate IMRT delivery techniques with moving parts, e.g., a multileaf collimator (MLC), are particularly sensitive interplay between and leaf motion. also know if, by how much, fractionation treatment reduce effects.

High radiation dose in computed tomography (CT) scans increases the lifetime risk of cancer and has become a major clinical concern. Recently, iterative reconstruction algorithms with total variation (TV) regularization have been developed to reconstruct CT images from highly undersampled data acquired at low mAs levels order reduce imaging dose. Nonetheless, low-contrast structures tend be smoothed out by TV regularization, posing great challenge for method. To solve this problem, work we...

The treatment planning process for patients with head and neck (H&N) cancer is regarded as one of the most complicated due to large target volume, multiple prescription dose levels, many radiation-sensitive critical structures near target. Treatment this site requires a high level human expertise tremendous amount effort produce personalized quality plans, taking long week, which deteriorates chances tumor control patient survival. To solve problem, we propose investigate deep learning-based...

Abstract With the advancement of treatment modalities in radiation therapy for cancer patients, outcomes have improved, but at cost increased plan complexity and planning time. The accurate prediction dose distributions would alleviate this issue by guiding clinical optimization to save time maintain high quality plans. We modified a convolutional deep network model, U-net (originally designed segmentation purposes), predicting from patient image contours target volume (PTV) organs risk...

Objective The primary aim of this research was to address the limitations observed in medical knowledge prevalent large language models (LLMs) such as ChatGPT, by creating a specialized model with enhanced accuracy advice. Methods We achieved adapting and refining meta-AI (LLaMA) using dataset 100,000 patient-doctor dialogues sourced from widely used online consultation platform. These conversations were cleaned anonymized respect privacy concerns. In addition refinement, we incorporated...

The use of neural networks to directly predict three-dimensional dose distributions for automatic planning is becoming popular. However, the existing methods only patient anatomy as input and assume consistent beam configuration all patients in training database. purpose this work was develop a more general model that considers variable configurations addition achieve comprehensive with potentially easier clinical implementation, without need train specific models different settings.The...

Cone-beam computed tomography (CBCT) scanning is used daily or weekly (i.e., on-treatment CBCT) for accurate patient setup in image-guided radiotherapy. However, inaccuracy of CT numbers prevents CBCT from performing advanced tasks such as dose calculation and treatment planning. Motivated by the promising performance deep learning medical imaging, we propose a U-net-based approach that synthesizes CT-like images with planning CT, while keeping same anatomical structure CBCT.

Image guidance in radiotherapy and extracranial radiosurgery offers the potential for precise radiation dose delivery to a moving tumour. Recent work has demonstrated how locate track position of tumour real-time using diagnostic x-ray imaging find implanted radio-opaque markers. However, treatment plan through gating or beam tracking requires adequate consideration system latencies, including image acquisition, processing, communication delays, control inductance within motor, mechanical...

Respiration-induced tumour motion can potentially compromise the use of intensity-modulated radiotherapy (IMRT) as a dose escalation tool for lung treatment. We have experimentally investigated intra-fractional organ effects in IMRT treatments delivered by multi-leaf collimator (MLC). An in-house made motor-driven platform, which moves sinusoidally with an amplitude 1 cm and period 4 s, was used to mimic motion. Tumour simulated along cranial-caudal direction while MLC leaves moved across...

Due to respiration, many tumours in the thorax and abdomen may move as much 3 cm peak-to-peak during radiation treatment. To mitigate motion-induced irradiation of normal lung tissue, clinics have employed external markers gate treatment beam. This technique assumes that correlation between surface internal tumour position remains constant inter-fractionally intra-fractionally. In this work, a study has been performed assess validity assumption for based gated radiotherapy, by measuring...

Online adaptive radiation therapy (ART) promises the ability to deliver an optimal treatment in response daily patient anatomic variation. A major technical barrier for clinical implementation of online ART is requirement rapid image segmentation. Deformable registration (DIR) has been used as automated segmentation method transfer tumor/organ contours from planning images. However, current computational time DIR insufficient ART. In this work, issue addressed by using computer graphics...

The Monte Carlo code PENELOPE has been used to simulate electron beams from a Siemens Mevatron KDS linac with nominal energies of 6, 12 and 18 MeV. Owing its accuracy, which stems that the underlying physical interaction models, is suitable for simulating problems interest medical physics community. It includes geometry package allows definition complex quadric geometries, such as those irradiation instruments, in straightforward manner. Dose distributions water simulated agree well...

Synchronized moving aperture radiation therapy (SMART) is a new technique for treating mobile tumours under development at Massachusetts General Hospital (MGH). The basic idea of SMART to synchronize the beam formed by dynamic multileaf collimator (DMLC) with tumour motion induced respiration. based on concept average trajectory (ATT) exhibited during During treatment simulation stage, measured and ATT derived. Then, original IMRT MLC leaf sequence modified using compensate motion....

In gated radiation therapy procedures, the lung tumor position is used directly (by implanted radiopaque markers) or indirectly external surrogate methods) to decrease volume of irradiated healthy tissue. Due a risk pneumothorax, many clinics do not implant fiducials, and treatment primarily based on respiratory induced signal. The method relies upon assumption that internal motion well correlated with motion, this correlation constant in time. Using set data contains synchronous traces, we...

A Monte Carlo user code, MCDOSE, has been developed for radiotherapy treatment planning (RTP) dose calculations. MCDOSE is designed as a calculation module suitable adaptation to host RTP systems. can be used both conventional photon/electron beam and intensity modulated (IMRT) planning. uses multiple-source model reconstruct the phase space. Based on simulated or measured data acquired during commissioning, source-model parameters are adjusted through an automated procedure. Beam modifiers...

Monte Carlo (MC) simulation is commonly considered to be the most accurate dose calculation method in radiotherapy. However, its efficiency still requires improvement for many routine clinical applications. In this paper, we present our recent progress toward development of a graphics processing unit (GPU)-based MC package, gDPM v2.0. It utilizes parallel computation ability GPU achieve high efficiency, while maintaining same particle transport physics as original planning (DPM) code and...

Accurate radiation dose calculation is essential for successful proton radiotherapy. Monte Carlo (MC) simulation considered to be the most accurate method. However, long computation time limits it from routine clinical applications. Recently, graphics processing units (GPUs) have been widely used accelerate computationally intensive tasks in We developed a fast MC package, gPMC, on GPU. In transport modeled by class II condensed history scheme with continuous slowing down approximation....

X-ray imaging dose from serial cone-beam CT (CBCT) scans raises a clinical concern in most image guided radiation therapy procedures. It is the goal of this paper to develop fast GPU-based algorithm reconstruct high quality CBCT images undersampled and noisy projection data so as lower dose. For purpose, we have developed an iterative tight frame (TF) based reconstruction algorithm. A condition that real has sparse representation under TF basis imposed iteration process regularization...

Accurate and automatic brain metastases target delineation is a key step for efficient effective stereotactic radiosurgery (SRS) treatment planning. In this work, we developed deep learning convolutional neural network (CNN) algorithm segmenting on contrast-enhanced T1-weighted magnetic resonance imaging (MRI) datasets. We integrated the CNN-based into an segmentation workflow validated both Multimodal Brain Tumor Image Segmentation challenge (BRATS) data clinical patients' data. Validation...