Deep-learning-assisted algorithm for catheter reconstruction during MR-only gynecological interstitial brachytherapy

Artificial intelligence in interventional radiotherapy (brachytherapy): Enhancing patient-centered care and addressing patients' needs

This review explores the integration of artificial intelligence (AI) in interventional radiotherapy (IRT), emphasizing its potential to streamline workflows and enhance patient care. Through a systematic analysis of 78 relevant papers spanning from 2002 to 2024, we identified significant advancements in contouring, treatment planning, outcome prediction, and quality assurance. AI-driven approaches offer promise in reducing procedural times, personalizing treatments, and improving treatment outcomes for oncological patients. However, challenges such as clinical validation and quality assurance protocols persist. Nonetheless, AI presents a transformative opportunity to optimize IRT and meet evolving patient needs.

A Review of Artificial Intelligence in Brachytherapy

Artificial intelligence (AI) has the potential to revolutionize brachytherapy's clinical workflow. This review comprehensively examines the application of AI, focusing on machine learning and deep learning, in facilitating various aspects of brachytherapy. We analyze AI's role in making brachytherapy treatments more personalized, efficient, and effective. The applications are systematically categorized into seven categories: imaging, preplanning, treatment planning, applicator reconstruction, quality assurance, outcome prediction, and real-time monitoring. Each major category is further subdivided based on cancer type or specific tasks, with detailed summaries of models, data sizes, and results presented in corresponding tables. This review offers insights into the current advancements, challenges, and the impact of AI on treatment paradigms, encouraging further research to expand its clinical utility.

Rapid multi-catheter segmentation for magnetic resonance image-guided catheter-based interventions

BACKGROUND

Magnetic resonance imaging (MRI) is the gold standard for delineating cancerous lesions in soft tissue. Catheter-based interventions require the accurate placement of multiple long, flexible catheters at the target site. The manual segmentation of catheters in MR images is a challenging and time-consuming task. There is a need for automated catheter segmentation to improve the efficiency of MR-guided procedures.

PURPOSE

To develop and assess a machine learning algorithm for the detection of multiple catheters in magnetic resonance images used during catheter-based interventions.

METHODS

In this work, a 3D U-Net was trained to retrospectively segment catheters in scans acquired during clinical MR-guided high dose rate (HDR) prostate brachytherapy cases. To assess confidence in segmentation, multiple AI models were trained. On clinical test cases, average segmentation results were used to plan the brachytherapy delivery. Dosimetric parameters were compared to the original clinical plan. Data was obtained from 35 patients who underwent HDR prostate brachytherapy for focal disease with a total of 214 image volumes. 185 image volumes from 30 patients were used for training using a five-fold cross validation split to divide the data for training and validation. To generate confidence measures of segmentation accuracy, five trained models were generated. The remaining five patients (29 volumes) were used to test the performance of the trained model by comparison to manual segmentations of three independent observers and assessment of dosimetric impact on the final clinical brachytherapy plans.

RESULTS

The network successfully identified 95% of catheters in the test set at a rate of 0.89 s per volume. The multi-model method identified the small number of cases where AI segmentation of individual catheters was poor, flagging the need for user input. AI-based segmentation performed as well as segmentations by independent observers. Plan dosimetry using AI-segmented catheters was comparable to the original plan.

CONCLUSION

The vast majority of catheters were accurately identified by AI segmentation, with minimal impact on plan outcomes. The use of multiple AI models provided confidence in the segmentation accuracy and identified catheter segmentations that required further manual assessment. Real-time AI catheter segmentation can be used during MR-guided insertions to assess deflections and for rapid planning of prostate brachytherapy.

Accuracy of an electromagnetic tracking enabled afterloader based on the automated registration with CT phantom images

BACKGROUND

Electromagnetic tracking (EMT) has been researched for brachytherapy applications, showing a great potential for automating implant reconstruction, and overcoming image-based limitations such as contrast and spatial resolution. One of the challenges of this technology is that it does not intrinsically share the same reference frame as the patient's medical imaging.

PURPOSE

To present a novel phantom that can be used for a comprehensive quality assurance (QA) program of brachytherapy EMT systems and use this phantom to validate a novel applicator-based registration method of EMT and image reference frames for gynecological (GYN) interstitial brachytherapy.

MATERIALS AND METHODS

Eleven 6F-catheters (20 cm long), one 6F round tip catheter (29.4 cm long) and a tandem and ring gynecological applicator (Elekta, CT/MR 60°, 40 mm long tandem, 30 mm diameter ring) were placed in a rigid custom-made phantom (Elekta Brachytherapy, Veenendaal, The Netherlands) to reconstruct their geometry using a five-degree of freedom EMT sensor attached to an afterloader's check cable. All EMT reconstructions were done in three different environments: disturbance free (no metal nearby), computed tomography (CT)-on-rails brachytherapy suite and magnetic resonance imaging (MRI) brachytherapy suite. Implants were placed parallel to a magnetic field generatorand were reconstructed using two different acquisition methods: step-and-record and continuous motion. In all cases, the acquisition is performed at a rate of approximately 40 Hz. A CT scan of the phantom inside a water cube was obtained. In the treatment planning system (TPS), all catheters in the CT images were manually reconstructed and the applicator reconstruction was achieved by manually placing its solid 3D model, found in the applicator library of the TPS. The Iterative Closest Point and the Coherent Point Drift algorithms were used, initialized with four known points, to register both EMT and CT scan reference frames using corresponding points from the EMT and CT based reconstructions of the phantom, following three approaches: one gynecological applicator, four interstitial catheters inside four calibration plates having an S-shaped path, and four 5 mm diameter ceramic marbles found in each of the four calibration plates. Once registered, the registration error (perpendicular distance) was computed.

RESULTS

The absolute median deviation from the expected value for EMT measurements in the disturbance free environment, CT-on-rails brachytherapy suite, and MRI-brachytherapy suite are 0.41, 0.23, and 0.31 mm, respectively, while for the CT scan it is 0.18 mm. These values significantly lie below the sensor's expected accuracy of 0.70 mm (p < 0.001), suggesting that the environment did not have a significant impact on the measurements, given that care is taken in the immediate surroundings. In all three environments, the two acquisitions and three registration approaches have mean and median registration errors that lie at or below 1 mm, which is lower than the clinical acceptable threshold of 2 mm.

CONCLUSIONS

The novel phantom allowed to successfully evaluate the accuracy of EMT-based reconstructions of catheters and a GYN tandem and ring applicator in different clinical environments. A registration method based only on the applicator geometry, reconstructed withan EMT sensor and the TPS solid applicator library, was validated and shows clinically acceptable accuracy, comparable to CT-based reconstruction but within a few minutes. Since the applicator is also visible in MRI, this method could potentially be used in clinics in an EMT-MR interstitial GYN brachytherapy workflow.

Deep learning in MRI-guided radiation therapy: A systematic review

Recent advances in MRI-guided radiation therapy (MRgRT) and deep learning techniques encourage fully adaptive radiation therapy (ART), real-time MRI monitoring, and the MRI-only treatment planning workflow. Given the rapid growth and emergence of new state-of-the-art methods in these fields, we systematically review 197 studies written on or before December 31, 2022, and categorize the studies into the areas of image segmentation, image synthesis, radiomics, and real time MRI. Building from the underlying deep learning methods, we discuss their clinical importance and current challenges in facilitating small tumor segmentation, accurate x-ray attenuation information from MRI, tumor characterization and prognosis, and tumor motion tracking. In particular, we highlight the recent trends in deep learning such as the emergence of multi-modal, visual transformer, and diffusion models.

Attention-Gated Deep-Learning-Based Automatic Digitization of Interstitial Needles in High-Dose-Rate Brachytherapy for Cervical Cancer

Purpose

Deep learning can be used to automatically digitize interstitial needles in high-dose-rate (HDR) brachytherapy for patients with cervical cancer. The aim of this study was to design a novel attention-gated deep-learning model, which may further improve the accuracy of and better differentiate needles.

Methods and Materials

Seventeen patients with cervical cancer with 56 computed tomography-based interstitial HDR brachytherapy plans from the local hospital were retrospectively chosen with the local institutional review board's approval. Among them, 50 plans were randomly selected as the training set and the rest as the validation set. Spatial and channel attention gates (AGs) were added to 3-dimensional convolutional neural networks (CNNs) to highlight needle features and suppress irrelevant regions; this was supposed to facilitate convergence and improve accuracy of automatic needle digitization. Subsequently, the automatically digitized needles were exported to the Oncentra treatment planning system (Elekta Solutions AB, Stockholm, Sweden) for dose evaluation. The geometric and dosimetric accuracy of automatic needle digitization was compared among 3 methods: (1) clinically approved plans with manual needle digitization (ground truth); (2) the conventional deep-learning (CNN) method; and (3) the attention-added deep-learning (CNN + AG) method, in terms of the Dice similarity coefficient (DSC), tip and shaft positioning errors, dose distribution in the high-risk clinical target volume (HR-CTV), organs at risk, and so on.

Results

The attention-gated CNN model was superior to CNN without AGs, with a greater DSC (approximately 94% for CNN + AG vs 89% for CNN). The needle tip and shaft errors of the CNN + AG method (1.1 mm and 1.8 mm, respectively) were also much smaller than those of the CNN method (2.0 mm and 3.3 mm, respectively). Finally, the dose difference for the HR-CTV D90 using the CNN + AG method was much more accurate than that using CNN (0.4% and 1.7%, respectively).

Conclusions

The attention-added deep-learning model was successfully implemented for automatic needle digitization in HDR brachytherapy, with clinically acceptable geometric and dosimetric accuracy. Compared with conventional deep-learning neural networks, attention-gated deep learning may have superior performance and great clinical potential.

Artificial intelligence applications in brachytherapy: A literature review

PURPOSE

Artificial intelligence (AI) has the potential to simplify and optimize various steps of the brachytherapy workflow, and this literature review aims to provide an overview of the work done in this field.

METHODS AND MATERIALS

We conducted a literature search in June 2022 on PubMed, Embase, and Cochrane for papers that proposed AI applications in brachytherapy.

RESULTS

A total of 80 papers satisfied inclusion/exclusion criteria. These papers were categorized as follows: segmentation (24), registration and image processing (6), preplanning (13), dose prediction and treatment planning (11), applicator/catheter/needle reconstruction (16), and quality assurance (10). AI techniques ranged from classical models such as support vector machines and decision tree-based learning to newer techniques such as U-Net and deep reinforcement learning, and were applied to facilitate small steps of a process (e.g., optimizing applicator selection) or even automate the entire step of the workflow (e.g., end-to-end preplanning). Many of these algorithms demonstrated human-level performance and offer significant improvements in speed.

CONCLUSIONS

AI has potential to augment, automate, and/or accelerate many steps of the brachytherapy workflow. We recommend that future studies adhere to standard reporting guidelines. We also stress the importance of using larger sample sizes and reporting results using clinically interpretable measures.

Automatic reconstruction of interstitial needles using CT images in post-operative cervical cancer brachytherapy based on deep learning

Purpose

The purpose of this study was to investigate the precision of deep learning (DL)-based auto-reconstruction in localizing interstitial needles in post-operative cervical cancer brachytherapy (BT) using three-dimensional (3D) computed tomography (CT) images.

Material and methods

A convolutional neural network (CNN) was developed and presented for automatic reconstruction of interstitial needles. Data of 70 post-operative cervical cancer patients who received CT-based BT were used to train and test this DL model. All patients were treated with three metallic needles. Dice similarity coefficient (DSC), 95% Hausdorff distance (95% HD), and Jaccard coefficient (JC) were applied to evaluate the geometric accuracy of auto-reconstruction for each needle. Dose-volume indexes (DVI) between manual and automatic methods were used to analyze the dosimetric difference. Correlation between geometric metrics and dosimetric difference was evaluated using Spearman correlation analysis.

Results

The mean DSC values of DL-based model were 0.88, 0.89, and 0.90 for three metallic needles. Wilcoxon signed-rank test indicated no significant dosimetric differences in all BT planning structures between manual and automatic reconstruction methods (p > 0.05). Spearman correlation analysis demonstrated weak link between geometric metrics and dosimetry differences.

Conclusions

DL-based reconstruction method can be used to precisely localize the interstitial needles in 3D-CT images. The proposed automatic approach could improve the consistency of treatment planning for post-operative cervical cancer brachytherapy.

Deep Learning in MRI-guided Radiation Therapy: A Systematic Review

MRI-guided radiation therapy (MRgRT) offers a precise and adaptive approach to treatment planning. Deep learning applications which augment the capabilities of MRgRT are systematically reviewed. MRI-guided radiation therapy offers a precise, adaptive approach to treatment planning. Deep learning applications which augment the capabilities of MRgRT are systematically reviewed with emphasis placed on underlying methods. Studies are further categorized into the areas of segmentation, synthesis, radiomics, and real time MRI. Finally, clinical implications, current challenges, and future directions are discussed.

Catheter reconstruction and dosimetric verification of MRI-only treatment planning (MRTP) for interstitial HDR brachytherapy using PETRA sequence

Objective. The feasibility of MRI-only treatment planning (MRTP) for interstitial high-dose rate (HDR) brachytherapy (BT) was investigated for patients diagnosed with gynecologic cancer.Approach. A clinical MRTP workflow utilizing a 'pointwise encoding time reduction with radial acquisition (PETRA)' sequence was proposed. This is a clinically available MRI sequence optimized to improve interstitial catheter-tissue contrast. Interstitial needles outside the obturator region were reconstructed using MR images only. For catheters penetrating through the obturator, a library-based reconstruction was proposed. In this work, dwell coordinates from the clinical CT-based reconstruction were used as the surrogate for the library-based approach. For MR-only plan, dwell times were activated and assigned as in the clinical plans. The catheter reconstruction was assessed by comparing dwell position coordinates. The dosimetric comparisons between a clinical plan and MR-only plan were assessed for physical and EQD2 dose and volume parameters forD₉₀,D₅₀andD₉₈for clinical target volume (CTV) andD_2cc,D_0.1ccandD_5ccfor OARs.Main results. Catheter reconstruction was possible using the optimized PETRA sequence on MR images. An overall reconstruction difference of 1.7 ± 0.5 mm, attributed to registration-based errors, was found compared to the CT-based reconstruction. The MRTP workflow has the potential to generate a treatment plan with an equivalent dosimetric quality compared to the conventional CT/MRI-based approach. For CTVD₉₀, physical and EQD2 dose and volume parameter differences were 1.5 ± 1.9% and 0.7 ± 1.0 Gy, respectively. ForD_2ccOARs, DVH (EQD2) differences were -0.4 ± 1.1% (-0.2 ± 0.5 Gy), 0.5 ± 2.8% (0.2 ± 1.3 Gy) and -0.5 ± 1.4% (-0.2 ± 0.5 Gy) for rectum, bladder, and sigmoid, respectively.Significance. With the proposed MRTP approach, CT imaging may no longer be needed in HDR BT for interstitial gynecologic treatment. A proof-of-concept study was conducted to demonstrated that MRTP using PETRA is feasible, with comparable dosimetric results to the conventional CT/MRI-based approach.

Automating implant reconstruction in interstitial brachytherapy of the breast: A hybrid approach combining electromagnetic tracking and image segmentation

BACKGROUND AND PURPOSE

To develop a method for automatic reconstruction of catheter implants in interstitial brachytherapy (iBT) of the breast by means of electromagnetic tracking (EMT) with the goal of making treatment planning as time-effective and accurate as possible.

MATERIALS AND METHODS

The implant geometry of 64 patients was recorded using an afterloader prototype with EMT functionality immediately after the planning CT. EMT data were transferred to the CT image space by rigidly registering the catheter fixation buttons as landmarks. To further improve reconstruction accuracy, the EMT reconstruction points were used as starting points to define small regions of interest (ROI) in the CT image. Within these ROIs, the catheter track was segmented in the CT using image processing operations such as thresholding and blob detection, thus refining the reconstruction. The perpendicular distance between the refined EMT implant reconstruction points and the manually reconstructed catheters by an experienced treatment planner was calculated as a measure of their geometric agreement.

RESULTS

Geometrically, the refined EMT based implant reconstruction shows excellent agreement with the manual reconstruction. The median distance across all patients is 0.25 mm and the 95th percentile is 1 mm. Refinement takes approximately 0.5 s per reconstruction point and typically does not exceed 3 min per implant at no user interaction.

CONCLUSION

The refined EMT based implant reconstruction proved to be extremely accurate and fast compared to manual reconstruction. The presented procedure can in principle be easily transferred to clinical routine and therefore has enormous potential to provide significant time savings in iBT treatment planning whilst improving reconstruction accuracy.

Review on Treatment Planning Systems for Cervix Brachytherapy (Interventional Radiotherapy): Some Desirable and Convenient Practical Aspects to Be Implemented from Radiation Oncologist and Medical Physics Perspectives

Intracavitary brachytherapy (BT, Interventional Radiotherapy, IRT), plays an essential role in the curative intent of locally advanced cervical cancer, for which the conventional approach involves external beam radiotherapy with concurrent chemotherapy followed by BT. This work aims to review the different methodologies used by commercially available treatment planning systems (TPSs) in exclusive magnetic resonance imaging-based (MRI) cervix BT with interstitial component treatments. Practical aspects and improvements to be implemented into the TPSs are discussed. This review is based on the clinical expertise of a group of radiation oncologists and medical physicists and on interactive demos provided by the software manufacturers. The TPS versions considered include all the new tools currently in development for future commercial releases. The specialists from the supplier companies were asked to propose solutions to some of the challenges often encountered in a clinical environment through a questionnaire. The results include not only such answers but also comments by the authors that, in their opinion, could help solve the challenges covered in these questions. This study summarizes the possibilities offered nowadays by commercial TPSs, highlighting the absence of some useful tools that would notably improve the planning of MR-based interstitial component cervix brachytherapy.