Head-and-neck organs-at-risk auto-delineation using dual pyramid networks for CBCT-guided adaptive radiotherapy

Artificial intelligence for treatment delivery: image-guided radiotherapy

Radiation therapy (RT) is a highly digitized field relying heavily on computational methods and, as such, has a high affinity for the automation potential afforded by modern artificial intelligence (AI). This is particularly relevant where imaging is concerned and is especially so during image-guided RT (IGRT). With the advent of online adaptive RT (ART) workflows at magnetic resonance (MR) linear accelerators (linacs) and at cone-beam computed tomography (CBCT) linacs, the need for automation is further increased. AI as applied to modern IGRT is thus one area of RT where we can expect important developments in the near future. In this review article, after outlining modern IGRT and online ART workflows, we cover the role of AI in CBCT and MRI correction for dose calculation, auto-segmentation on IGRT imaging, motion management, and response assessment based on in-room imaging.

Clinical Experience With an Offline Adaptive Radiation Therapy Head and Neck Program: Dosimetric Benefits and Opportunities for Patient Selection

PURPOSE

The objective of this study was to develop a linear accelerator (LINAC)-based adaptive radiation therapy (ART) workflow for the head and neck that is informed by automated image tracking to identify major anatomic changes warranting adaptation. In this study, we report our initial clinical experience with the program and an investigation into potential trigger signals for ART.

METHODS AND MATERIALS

Offline ART was systematically performed on patients receiving radiation therapy for head and neck cancer on C-arm LINACs. Adaptations were performed at a single time point during treatment with resimulation approximately 3 weeks into treatment. Throughout treatment, all patients were tracked using an automated image tracking system called the Automated Watchdog for Adaptive Radiotherapy Environment (AWARE). AWARE measures volumetric changes in gross tumor volumes (GTVs) and selected normal tissues via cone beam computed tomography scans and deformable registration. The benefit of ART was determined by comparing adaptive plan dosimetry and normal tissue complication probabilities against the initial plans recalculated on resimulation computed tomography scans. Dosimetric differences were then correlated with AWARE-measured volume changes to identify patient-specific triggers for ART. Candidate trigger variables were evaluated using receiver operator characteristic analysis.

RESULTS

In total, 46 patients received ART in this study. Among these patients, we observed a significant decrease in dose to the submandibular glands (mean ± standard deviation: -219.2 ± 291.2 cGy, P < 10-5), parotids (-68.2 ± 197.7 cGy, P = .001), and oral cavity (-238.7 ± 206.7 cGy, P < 10-5) with the adaptive plan. Normal tissue complication probabilities for xerostomia computed from mean parotid doses also decreased significantly with the adaptive plans (P = .008). We also observed systematic intratreatment volume reductions (ΔV) for GTVs and normal tissues. Candidate triggers were identified that predicted significant improvement with ART, including parotid ΔV = 7%, neck ΔV = 2%, and nodal GTV ΔV = 29%.

CONCLUSIONS

Systematic offline head and neck ART was successfully deployed on conventional LINACs and reduced doses to critical salivary structures and the oral cavity. Automated cone beam computed tomography tracking provided information regarding anatomic changes that may aid patient-specific triggering for ART.

Parotid Gland Segmentation Using Purely Transformer-Based U-Shaped Network and Multimodal MRI

Parotid gland tumors account for approximately 2% to 10% of head and neck tumors. Segmentation of parotid glands and tumors on magnetic resonance images is essential in accurately diagnosing and selecting appropriate surgical plans. However, segmentation of parotid glands is particularly challenging due to their variable shape and low contrast with surrounding structures. Recently, deep learning has developed rapidly, and Transformer-based networks have performed well on many computer vision tasks. However, Transformer-based networks have yet to be well used in parotid gland segmentation tasks. We collected a multi-center multimodal parotid gland MRI dataset and implemented parotid gland segmentation using a purely Transformer-based U-shaped segmentation network. We used both absolute and relative positional encoding to improve parotid gland segmentation and achieved multimodal information fusion without increasing the network computation. In addition, our novel training approach reduces the clinician's labeling workload by nearly half. Our method achieved good segmentation of both parotid glands and tumors. On the test set, our model achieved a Dice-Similarity Coefficient of 86.99%, Pixel Accuracy of 99.19%, Mean Intersection over Union of 81.79%, and Hausdorff Distance of 3.87. The purely Transformer-based U-shaped segmentation network we used outperforms other convolutional neural networks. In addition, our method can effectively fuse the information from multi-center multimodal MRI dataset, thus improving the parotid gland segmentation.

Progressive auto-segmentation for cone-beam computed tomography-based online adaptive radiotherapy

Background and purpose

Accurate and automated segmentation of targets and organs-at-risk (OARs) is crucial for the successful clinical application of online adaptive radiotherapy (ART). Current methods for cone-beam computed tomography (CBCT) auto-segmentation face challenges, resulting in segmentations often failing to reach clinical acceptability. Current approaches for CBCT auto-segmentation overlook the wealth of information available from initial planning and prior adaptive fractions that could enhance segmentation precision.

Materials and methods

We introduce a novel framework that incorporates data from a patient's initial plan and previous adaptive fractions, harnessing this additional temporal context to significantly refine the segmentation accuracy for the current fraction's CBCT images. We present LSTM-UNet, an innovative architecture that integrates Long Short-Term Memory (LSTM) units into the skip connections of the traditional U-Net framework to retain information from previous fractions. The models underwent initial pre-training with simulated data followed by fine-tuning on a clinical dataset.

Results

Our proposed model's segmentation predictions yield an average Dice similarity coefficient of 79% from 8 Head & Neck organs and targets, compared to 52% from a baseline model without prior knowledge and 78% from a baseline model with prior knowledge but no memory.

Conclusions

Our proposed model excels beyond baseline segmentation frameworks by effectively utilizing information from prior fractions, thus reducing the effort of clinicians to revise the auto-segmentation results. Moreover, it works together with registration-based methods that offer better prior knowledge. Our model holds promise for integration into the online ART workflow, offering precise segmentation capabilities on synthetic CT images.

Evaluating AI-generated CBCT-based synthetic CT images for target delineation in palliative treatments of pelvic bone metastasis at conventional C-arm linacs

PURPOSE

One-table treatments with treatment imaging, preparation and delivery occurring at one treatment couch, could increase patients' comfort and throughput for palliative treatments. On regular C-arm linacs, however, cone-beam CT (CBCT) imaging quality is currently insufficient. Therefore, our goal was to assess the suitability of AI-generated CBCT based synthetic CT (sCT) images for target delineation and treatment planning for palliative radiotherapy.

MATERIALS AND METHODS

CBCTs and planning CT-scans of 22 female patients with pelvic bone metastasis were included. For each CBCT, a corresponding sCT image was generated by a deep learning model in ADMIRE 3.38.0. Radiation oncologists delineated 23 target volumes (TV) on the sCTs (TVsCT) and scored their delineation confidence. The delineations were transferred to planning CTs and manually adjusted if needed to yield gold standard target volumes (TVclin). TVsCT were geometrically compared to TVclin using Dice coefficient (DC) and Hausdorff Distance (HD). The dosimetric impact of TVsCT inaccuracies was evaluated for VMAT plans with different PTV margins.

RESULTS

Radiation oncologists scored the sCT quality as sufficient for 13/23 TVsCT (median: DC = 0.9, HD = 11 mm) and insufficient for 10/23 TVsCT (median: DC = 0.7, HD = 34 mm). For the sufficient category, remaining inaccuracies could be compensated by +1 to +4 mm additional margin to achieve coverage of V95% > 95% and V95% > 98%, respectively in 12/13 TVsCT.

CONCLUSION

The evaluated sCT quality allowed for accurate delineation for most targets. sCTs with insufficient quality could be identified accurately upfront. A moderate PTV margin expansion could address remaining delineation inaccuracies. Therefore, these findings support further exploration of CBCT based one-table treatments on C-arm linacs.

The Use of MR-Guided Radiation Therapy for Head and Neck Cancer and Recommended Reporting Guidance

Although magnetic resonance imaging (MRI) has become standard diagnostic workup for head and neck malignancies and is currently recommended by most radiological societies for pharyngeal and oral carcinomas, its utilization in radiotherapy has been heterogeneous during the last decades. However, few would argue that implementing MRI for annotation of target volumes and organs at risk provides several advantages, so that implementation of the modality for this purpose is widely accepted. Today, the term MR-guidance has received a much broader meaning, including MRI for adaptive treatments, MR-gating and tracking during radiotherapy application, MR-features as biomarkers and finally MR-only workflows. First studies on treatment of head and neck cancer on commercially available dedicated hybrid-platforms (MR-linacs), with distinct common features but also differences amongst them, have also been recently reported, as well as "biological adaptation" based on evaluation of early treatment response via functional MRI-sequences such as diffusion weighted ones. Yet, all of these approaches towards head and neck treatment remain at their infancy, especially when compared to other radiotherapy indications. Moreover, the lack of standardization for reporting MR-guided radiotherapy is a major obstacle both to further progress in the field and to conduct and compare clinical trials. Goals of this article is to present and explain all different aspects of MR-guidance for radiotherapy of head and neck cancer, summarize evidence, as well as possible advantages and challenges of the method and finally provide a comprehensive reporting guidance for use in clinical routine and trials.

Young oncologists benefit more than experts from deep learning-based organs-at-risk contouring modeling in nasopharyngeal carcinoma radiotherapy: A multi-institution clinical study exploring working experience and institute group style factor

Background

To comprehensively investigate the behaviors of oncologists with different working experiences and institute group styles in deep learning-based organs-at-risk (OAR) contouring.

Methods

A deep learning-based contouring system (DLCS) was modeled from 188 CT datasets of patients with nasopharyngeal carcinoma (NPC) in institute A. Three institute oncology groups, A, B, and C, were included; each contained a beginner and an expert. For each of the 28 OARs, two trials were performed with manual contouring first and post-DLCS edition later, for ten test cases. Contouring performance and group consistency were quantified by volumetric and surface Dice coefficients. A volume-based and a surface-based oncologist satisfaction rate (VOSR and SOSR) were defined to evaluate the oncologists' acceptance of DLCS.

Results

Based on DLCS, experience inconsistency was eliminated. Intra-institute consistency was eliminated for group C but still existed for group A and group B. Group C benefits most from DLCS with the highest number of improved OARs (8 for volumetric Dice and 10 for surface Dice), followed by group B. Beginners obtained more numbers of improved OARs than experts (7 v.s. 4 in volumetric Dice and 5 v.s. 4 in surface Dice). VOSR and SOSR varied for institute groups, but the rates of beginners were all significantly higher than those of experts for OARs with experience group significance. A remarkable positive linear relationship was found between VOSR and post-DLCS edition volumetric Dice with a coefficient of 0.78.

Conclusions

The DLCS was effective for various institutes and the beginners benefited more than the experts.

CBCT-guided adaptive radiotherapy using self-supervised sequential domain adaptation with uncertainty estimation

Adaptive radiotherapy (ART) is an advanced technology in modern cancer treatment that incorporates progressive changes in patient anatomy into active plan/dose adaption during the fractionated treatment. However, the clinical application relies on the accurate segmentation of cancer tumors on low-quality on-board images, which has posed challenges for both manual delineation and deep learning-based models. In this paper, we propose a novel sequence transduction deep neural network with an attention mechanism to learn the shrinkage of the cancer tumor based on patients' weekly cone-beam computed tomography (CBCT). We design a self-supervised domain adaption (SDA) method to learn and adapt the rich textural and spatial features from pre-treatment high-quality computed tomography (CT) to CBCT modality in order to address the poor image quality and lack of labels. We also provide uncertainty estimation for sequential segmentation, which aids not only in the risk management of treatment planning but also in the calibration and reliability of the model. Our experimental results based on a clinical non-small cell lung cancer (NSCLC) dataset with sixteen patients and ninety-six longitudinal CBCTs show that our model correctly learns weekly deformation of the tumor over time with an average dice score of 0.92 on the immediate next step, and is able to predict multiple steps (up to 5 weeks) for future patient treatments with an average dice score reduction of 0.05. By incorporating the tumor shrinkage predictions into a weekly re-planning strategy, our proposed method demonstrates a significant decrease in the risk of radiation-induced pneumonitis up to 35% while maintaining the high tumor control probability.

Segmentation by test-time optimization for CBCT-based adaptive radiation therapy

PURPOSE

Online adaptive radiotherapy (ART) requires accurate and efficient auto-segmentation of target volumes and organs-at-risk (OARs) in mostly cone-beam computed tomography (CBCT) images, which often have severe artifacts and lack soft-tissue contrast, making direct segmentation very challenging. Propagating expert-drawn contours from the pretreatment planning CT through traditional or deep learning (DL)-based deformable image registration (DIR) can achieve improved results in many situations. Typical DL-based DIR models are population based, that is, trained with a dataset for a population of patients, and so they may be affected by the generalizability problem.

METHODS

In this paper, we propose a method called test-time optimization (TTO) to refine a pretrained DL-based DIR population model, first for each individual test patient, and then progressively for each fraction of online ART treatment. Our proposed method is less susceptible to the generalizability problem and thus can improve overall performance of different DL-based DIR models by improving model accuracy, especially for outliers. Our experiments used data from 239 patients with head-and-neck squamous cell carcinoma to test the proposed method. First, we trained a population model with 200 patients and then applied TTO to the remaining 39 test patients by refining the trained population model to obtain 39 individualized models. We compared each of the individualized models with the population model in terms of segmentation accuracy.

RESULTS

The average improvement of the Dice similarity coefficient (DSC) and 95% Hausdorff distance (HD95) of segmentation can be up to 0.04 (5%) and 0.98 mm (25%), respectively, with the individualized models compared to the population model over 17 selected OARs and a target of 39 patients. Although the average improvement may seem mild, we found that the improvement for outlier patients with structures of large anatomical changes is significant. The number of patients with at least 0.05 DSC improvement or 2 mm HD95 improvement by TTO averaged over the 17 selected structures for the state-of-the-art architecture VoxelMorph is 10 out of 39 test patients. By deriving the individualized model using TTO from the pretrained population model, TTO models can be ready in about 1 min. We also generated the adapted fractional models for each of the 39 test patients by progressively refining the individualized models using TTO to CBCT images acquired at later fractions of online ART treatment. When adapting the individualized model to a later fraction of the same patient, the model can be ready in less than a minute with slightly improved accuracy.

CONCLUSIONS

The proposed TTO method is well suited for online ART and can boost segmentation accuracy for DL-based DIR models, especially for outlier patients where the pretrained models fail.

Deep learning based direct segmentation assisted by deformable image registration for cone-beam CT based auto-segmentation for adaptive radiotherapy

Cone-beam CT (CBCT)-based online adaptive radiotherapy calls for accurate auto-segmentation to reduce the time cost for physicians. However, deep learning (DL)-based direct segmentation of CBCT images is a challenging task, mainly due to the poor image quality and lack of well-labelled large training datasets. Deformable image registration (DIR) is often used to propagate the manual contours on the planning CT (pCT) of the same patient to CBCT. In this work, we undertake solving the problems mentioned above with the assistance of DIR. Our method consists of three main components. First, we use deformed pCT contours derived from multiple DIR methods between pCT and CBCT as pseudo labels for initial training of the DL-based direct segmentation model. Second, we use deformed pCT contours from another DIR algorithm as influencer volumes to define the region of interest for DL-based direct segmentation. Third, the initially trained DL model is further fine-tuned using a smaller set of true labels. Nine patients are used for model evaluation. We found that DL-based direct segmentation on CBCT without influencer volumes has much poorer performance compared to DIR-based segmentation. However, adding deformed pCT contours as influencer volumes in the direct segmentation network dramatically improves segmentation performance, reaching the accuracy level of DIR-based segmentation. The DL model with influencer volumes can be further improved through fine-tuning using a smaller set of true labels, achieving mean Dice similarity coefficient of 0.86, Hausdorff distance at the 95th percentile of 2.34 mm, and average surface distance of 0.56 mm. A DL-based direct CBCT segmentation model can be improved to outperform DIR-based segmentation models by using deformed pCT contours as pseudo labels and influencer volumes for initial training, and by using a smaller set of true labels for model fine tuning.

A Review of the Metrics Used to Assess Auto-Contouring Systems in Radiotherapy

Auto-contouring could revolutionise future planning of radiotherapy treatment. The lack of consensus on how to assess and validate auto-contouring systems currently limits clinical use. This review formally quantifies the assessment metrics used in studies published during one calendar year and assesses the need for standardised practice. A PubMed literature search was undertaken for papers evaluating radiotherapy auto-contouring published during 2021. Papers were assessed for types of metric and the methodology used to generate ground-truth comparators. Our PubMed search identified 212 studies, of which 117 met the criteria for clinical review. Geometric assessment metrics were used in 116 of 117 studies (99.1%). This includes the Dice Similarity Coefficient used in 113 (96.6%) studies. Clinically relevant metrics, such as qualitative, dosimetric and time-saving metrics, were less frequently used in 22 (18.8%), 27 (23.1%) and 18 (15.4%) of 117 studies, respectively. There was heterogeneity within each category of metric. Over 90 different names for geometric measures were used. Methods for qualitative assessment were different in all but two papers. Variation existed in the methods used to generate radiotherapy plans for dosimetric assessment. Consideration of editing time was only given in 11 (9.4%) papers. A single manual contour as a ground-truth comparator was used in 65 (55.6%) studies. Only 31 (26.5%) studies compared auto-contours to usual inter- and/or intra-observer variation. In conclusion, significant variation exists in how research papers currently assess the accuracy of automatically generated contours. Geometric measures are the most popular, however their clinical utility is unknown. There is heterogeneity in the methods used to perform clinical assessment. Considering the different stages of system implementation may provide a framework to decide the most appropriate metrics. This analysis supports the need for a consensus on the clinical implementation of auto-contouring.

Feasibility of a deep-learning based anatomical region labeling tool for Cone-Beam Computed Tomography scans in radiotherapy

Background and purpose

Currently, there is no robust indicator within the Cone-Beam Computed Tomography (CBCT) DICOM headers as to which anatomical region is present on the scan. This can be a predicament to CBCT-based algorithms trained on specific body regions, such as auto-segmentation and radiomics tools used in the radiotherapy workflow. We propose an anatomical region labeling (ARL) algorithm to classify CBCT scans into four distinct regions: head & neck, thoracic-abdominal, pelvis, and extremity.

Materials and methods

Algorithm training and testing was performed on 3,802 CBCT scans from 596 patients treated at our radiotherapy center. The ARL model, which consists of a convolutional neural network, makes use of a single CBCT coronal slice to output a probability of occurrence for each of the four classes. ARL was evaluated on the test dataset composed of 1,090 scans and compared to a support vector machine (SVM) model. ARL was also used to label CBCT treatment scans for 22 consecutive days as part of a proof-of-concept implementation. A validation study was performed on the first 100 unique patient scans to evaluate the functionality of the tool in the clinical setting.

Results

ARL achieved an overall accuracy of 99.2% on the test dataset, outperforming the SVM (91.5% accuracy). Our validation study has shown strong agreement between the human annotations and ARL predictions, with accuracies of 99.0% for all four regions.

Conclusion

The high classification accuracy demonstrated by ARL suggests that it may be employed as a pre-processing step for site-specific, CBCT-based radiotherapy tools.

Accuracy and Feasibility of Synthetic CT for Lung Adaptive Radiotherapy: A Phantom Study

OBJECTIVES

The respiratory variations will lead to inconsistency between the actual delivery dose and the planning dose. How the minor interfractional amplitude changes affect the geometry and dose delivery accuracy remains to be investigated in the context of lung adaptive radiotherapy.

METHODS

Planning 4-dimensional-computed tomography and kV-cone beam computed tomography were scanned based on the Computerized Imaging Reference Systems phantom, which was employed to simulate the minor interfractional amplitude variations. The corresponding synthetic computed tomography for a particular motion pattern can be generated from Velocity program. Then a clinically meaningful synthetic computed tomography was analyzed through the geometrical and dosimetric assessment.

RESULTS

The image quality of synthetic computed tomography was improved obviously compared with cone beam computed tomography. Mean absolute error was minimized when no significant interfractional motion occurs and Velocity can be qualified for dealing with the regular breathing motion patterns. The mean percent hounsfield unit difference of the synthetic hounsfield unit values per organ relative to the planning 4-dimensional-computed tomography image was 22.3%. Under the same conditions, the mean percent hounsfield unit difference of the cone beam computed tomography hounsfield unit values per organ, relative to the planning 4-dimensional-computed tomography image was 83.9%. Overall, the accuracy of hounsfield unit in synthetic computed tomography was improved obviously and the variability of the synthetic image correlates with the planning 4-dimensional-computed tomography image variability. Meanwhile, the dose-volume histograms between planning 4-dimensional-computed tomography and synthetic computed tomography almost coincided each other, which indicates that Velocity program can qualify lung adaptive radiotherapy well when there were no interfractional respiratory variations. However, for cases with obvious interfractional amplitude change, the volume covered at least by 100% of the prescription dose was only 59.6% for that synthetic image.

CONCLUSION

The synthetic computed tomography images generated from Velocity were close to the real images in anatomy and dosimetry, which can make clinical lung adaptive radiotherapy possible based on the actual patient anatomy during treatment.

Automated lung tumor delineation on positron emission tomography/computed tomography via a hybrid regional network

BACKGROUND

Multimodality positron emission tomography/computed tomography (PET/CT) imaging combines the anatomical information of CT with the functional information of PET. In the diagnosis and treatment of many cancers, such as non-small cell lung cancer (NSCLC), PET/CT imaging allows more accurate delineation of tumor or involved lymph nodes for radiation planning.

PURPOSE

In this paper, we propose a hybrid regional network method of automatically segmenting lung tumors from PET/CT images.

METHODS

The hybrid regional network architecture synthesizes the functional and anatomical information from the two image modalities, whereas the mask regional convolutional neural network (R-CNN) and scoring fine-tune the regional location and quality of the output segmentation. This model consists of five major subnetworks, that is, a dual feature representation network (DFRN), a regional proposal network (RPN), a specific tumor-wise R-CNN, a mask-Net, and a score head. Given a PET/CT image as inputs, the DFRN extracts feature maps from the PET and CT images. Then, the RPN and R-CNN work together to localize lung tumors and reduce the image size and feature map size by removing irrelevant regions. The mask-Net is used to segment tumor within a volume-of-interest (VOI) with a score head evaluating the segmentation performed by the mask-Net. Finally, the segmented tumor within the VOI was mapped back to the volumetric coordinate system based on the location information derived via the RPN and R-CNN. We trained, validated, and tested the proposed neural network using 100 PET/CT images of patients with NSCLC. A fivefold cross-validation study was performed. The segmentation was evaluated with two indicators: (1) multiple metrics, including the Dice similarity coefficient, Jacard, 95th percentile Hausdorff distance, mean surface distance (MSD), residual mean square distance, and center-of-mass distance; (2) Bland-Altman analysis and volumetric Pearson correlation analysis.

RESULTS

In fivefold cross-validation, this method achieved Dice and MSD of 0.84 ± 0.15 and 1.38 ± 2.2 mm, respectively. A new PET/CT can be segmented in 1 s by this model. External validation on The Cancer Imaging Archive dataset (63 PET/CT images) indicates that the proposed model has superior performance compared to other methods.

CONCLUSION

The proposed method shows great promise to automatically delineate NSCLC tumors on PET/CT images, thereby allowing for a more streamlined clinical workflow that is faster and reduces physician effort.

Research on new treatment mode of radiotherapy based on pseudo-medical images

BACKGROUND AND OBJECTIVE

Multi-modal medical images with multiple feature information are beneficial for radiotherapy. A new radiotherapy treatment mode based on triangle generative adversarial network (TGAN) model was proposed to synthesize pseudo-medical images between multi-modal datasets.

METHODS

CBCT, MRI and CT images of 80 patients with nasopharyngeal carcinoma were selected. The TGAN model based on multi-scale discriminant network was used for data training between different image domains. The generator of the TGAN model refers to cGAN and CycleGAN, and only one generation network can establish the non-linear mapping relationship between multiple image domains. The discriminator used multi-scale discrimination network to guide the generator to synthesize pseudo-medical images that are similar to real images from both shallow and deep aspects. The accuracy of pseudo-medical images was verified in anatomy and dosimetry.

RESULTS

In the three synthetic directions, namely, CBCT → CT, CBCT → MRI, and MRI → CT, significant differences (p < 0.05) in the three-fold-cross validation results on PSNR and SSIM metrics between the pseudo-medical images obtained based on TGAN and the real images. In the testing stage, for TGAN, the MAE metric results in the three synthesis directions (CBCT → CT, CBCT → MRI, and MRI → CT) were presented as mean (standard deviation), which were 68.67 (5.83), 83.14 (8.48), and 79.96 (7.59), and the NMI metric results were 0.8643 (0.0253), 0.8051 (0.0268), and 0.8146 (0.0267) respectively. In terms of dose verification, the differences in dose distribution between the pseudo-CT obtained by TGAN and the real CT were minimal. The H values of the measurement results of dose uncertainty in PGTV, PGTVnd, PTV1, and PTV2 were 42.510, 43.121, 17.054, and 7.795, respectively (P < 0.05). The differences were statistically significant. The gamma pass rate (2%/2 mm) of pseudo-CT obtained by the new model was 94.94% (0.73%), and the numerical results were better than those of the three other comparison models.

CONCLUSIONS

The pseudo-medical images acquired based on TGAN were close to the real images in anatomy and dosimetry. The pseudo-medical images synthesized by the TGAN model have good application prospects in clinical adaptive radiotherapy.

Registration-guided deep learning image segmentation for cone beam CT-based online adaptive radiotherapy

PURPOSE

Adaptive radiotherapy (ART), especially online ART, effectively accounts for positioning errors and anatomical changes. One key component of online ART process is accurately and efficiently delineating organs at risk (OARs) and targets on online images, such as Cone Beam Computed Tomography (CBCT). Direct application of deep learning (DL)-based segmentation to CBCT images suffered from issues such as low image quality and limited available contour labels for training. To overcome these obstacles to online CBCT segmentation, we propose a registration-guided DL (RgDL) segmentation framework that integrates image registration algorithms and DL segmentation models.

METHODS

The RgDL framework is composed of two components: image registration and registration-guided DL segmentation. The image registration algorithm transforms / deforms planning contours, which were subsequently used as guidance by the DL model to obtain accurate final segmentations. We had two implementations of the proposed framework-Rig-RgDL (Rig for rigid body) and Def-RgDL (Def for deformable)-with rigid body (RB) registration or deformable image registration (DIR) as the registration algorithm, respectively, and U-Net as the DL model architecture. The two implementations of RgDL framework were trained and evaluated on seven OARs in an institutional clinical Head and Neck (HN) dataset.

RESULTS

Compared to the baseline approaches using the registration or the DL alone, RgDLs achieved more accurate segmentation, as measured by higher mean Dice similarity coefficients (DSC) and other distance-based metrics. Rig-RgDL achieved a DSC of 84.5% on seven OARs on average, higher than RB or DL alone by 4.5% and 4.7%. The average DSC of Def-RgDL was 86.5%, higher than DIR or DL alone by 2.4% and 6.7%. The inference time required by the DL model component to generate final segmentations of seven OARs was less than one second in RgDL. By examining the contours from RgDLs and DL case by case, we found that RgDL was less susceptible to image artifacts. We also studied how the performances of RgDL and DL vary with the size of the training dataset. The DSC of DL dropped by 12.1% as the number of training data decreased from 22 to 5, while RgDL only dropped by 3.4%.

CONCLUSION

By incorporating the patient-specific registration guidance to a population-based DL segmentation model, RgDL framework overcame the obstacles associated with online CBCT segmentation, including low image quality and insufficient training data, and achieved better segmentation accuracy than baseline methods. The resulting segmentation accuracy and efficiency show promise for applying this RgDL framework for online ART. This article is protected by copyright. All rights reserved.

Multi-organ auto-delineation in head-and-neck MRI for radiation therapy using regional convolutional neural network

Magnetic resonance imaging (MRI) allows accurate and reliable organ delineation for many disease sites in radiation therapy because MRI is able to offer superb soft-tissue contrast. Manual organ-at-risk delineation is labor-intensive and time-consuming. This study aims to develop a deep-learning-based automated multi-organ segmentation method to release the labor and accelerate the treatment planning process for head-and-neck (HN) cancer radiotherapy. A novel regional convolutional neural network (R-CNN) architecture, namely, mask scoring R-CNN, has been developed in this study. In the proposed model, a deep attention feature pyramid network is used as a backbone to extract the coarse features given by MRI, followed by feature refinement using R-CNN. The final segmentation is obtained through mask and mask scoring networks taking those refined feature maps as input. With the mask scoring mechanism incorporated into conventional mask supervision, the classification error can be highly minimized in conventional mask R-CNN architecture. A cohort of 60 HN cancer patients receiving external beam radiation therapy was used for experimental validation. Five-fold cross-validation was performed for the assessment of our proposed method. The Dice similarity coefficients of brain stem, left/right cochlea, left/right eye, larynx, left/right lens, mandible, optic chiasm, left/right optic nerve, oral cavity, left/right parotid, pharynx, and spinal cord were 0.89 ± 0.06, 0.68 ± 0.14/0.68 ± 0.18, 0.89 ± 0.07/0.89 ± 0.05, 0.90 ± 0.07, 0.67 ± 0.18/0.67 ± 0.10, 0.82 ± 0.10, 0.61 ± 0.14, 0.67 ± 0.11/0.68 ± 0.11, 0.92 ± 0.07, 0.85 ± 0.06/0.86 ± 0.05, 0.80 ± 0.13, and 0.77 ± 0.15, respectively. After the model training, all OARs can be segmented within 1 min.

Generative adversarial networks in medical image segmentation: A review

PURPOSE

Since Generative Adversarial Network (GAN) was introduced into the field of deep learning in 2014, it has received extensive attention from academia and industry, and a lot of high-quality papers have been published. GAN effectively improves the accuracy of medical image segmentation because of its good generating ability and capability to capture data distribution. This paper introduces the origin, working principle, and extended variant of GAN, and it reviews the latest development of GAN-based medical image segmentation methods.

METHOD

To find the papers, we searched on Google Scholar and PubMed with the keywords like "segmentation", "medical image", and "GAN (or generative adversarial network)". Also, additional searches were performed on Semantic Scholar, Springer, arXiv, and the top conferences in computer science with the above keywords related to GAN.

RESULTS

We reviewed more than 120 GAN-based architectures for medical image segmentation that were published before September 2021. We categorized and summarized these papers according to the segmentation regions, imaging modality, and classification methods. Besides, we discussed the advantages, challenges, and future research directions of GAN in medical image segmentation.

CONCLUSIONS

We discussed in detail the recent papers on medical image segmentation using GAN. The application of GAN and its extended variants has effectively improved the accuracy of medical image segmentation. Obtaining the recognition of clinicians and patients and overcoming the instability, low repeatability, and uninterpretability of GAN will be an important research direction in the future.

Geometric and Dosimetric Evaluation of Deep Learning-Based Automatic Delineation on CBCT-Synthesized CT and Planning CT for Breast Cancer Adaptive Radiotherapy: A Multi-Institutional Study

Purpose

We developed a deep learning model to achieve automatic multitarget delineation on planning CT (pCT) and synthetic CT (sCT) images generated from cone-beam CT (CBCT) images. The geometric and dosimetric impact of the model was evaluated for breast cancer adaptive radiation therapy.

Methods

We retrospectively analyzed 1,127 patients treated with radiotherapy after breast-conserving surgery from two medical institutions. The CBCT images for patient setup acquired utilizing breath-hold guided by optical surface monitoring system were used to generate sCT with a generative adversarial network. Organs at risk (OARs), clinical target volume (CTV), and tumor bed (TB) were delineated automatically with a 3D U-Net model on pCT and sCT images. The geometric accuracy of the model was evaluated with metrics, including Dice similarity coefficient (DSC) and 95% Hausdorff distance (HD95). Dosimetric evaluation was performed by quick dose recalculation on sCT images relying on gamma analysis and dose-volume histogram (DVH) parameters. The relationship between ΔD95, ΔV95 and DSC-CTV was assessed to quantify the clinical impact of the geometric changes of CTV.

Results

The ranges of DSC and HD95 were 0.73–0.97 and 2.22–9.36 mm for pCT, 0.63–0.95 and 2.30–19.57 mm for sCT from institution A, 0.70–0.97 and 2.10–11.43 mm for pCT from institution B, respectively. The quality of sCT was excellent with an average mean absolute error (MAE) of 71.58 ± 8.78 HU. The mean gamma pass rate (3%/3 mm criterion) was 91.46 ± 4.63%. DSC-CTV down to 0.65 accounted for a variation of more than 6% of V95 and 3 Gy of D95. DSC-CTV up to 0.80 accounted for a variation of less than 4% of V95 and 2 Gy of D95. The mean ΔD90/ΔD95 of CTV and TB were less than 2Gy/4Gy, 4Gy/5Gy for all the patients. The cardiac dose difference in left breast cancer cases was larger than that in right breast cancer cases.

Conclusions

The accurate multitarget delineation is achievable on pCT and sCT via deep learning. The results show that dose distribution needs to be considered to evaluate the clinical impact of geometric variations during breast cancer radiotherapy.

Artificial intelligence in image-guided radiotherapy: a review of treatment target localization

Modern conformal beam delivery techniques require image-guidance to ensure the prescribed dose to be delivered as planned. Recent advances in artificial intelligence (AI) have greatly augmented our ability to accurately localize the treatment target while sparing the normal tissues. In this paper, we review the applications of AI-based algorithms in image-guided radiotherapy (IGRT), and discuss the indications of these applications to the future of clinical practice of radiotherapy. The benefits, limitations and some important trends in research and development of the AI-based IGRT techniques are also discussed. AI-based IGRT techniques have the potential to monitor tumor motion, reduce treatment uncertainty and improve treatment precision. Particularly, these techniques also allow more healthy tissue to be spared while keeping tumor coverage the same or even better.

Synthetic CT-aided multiorgan segmentation for CBCT-guided adaptive pancreatic radiotherapy

PURPOSE

The delineation of organs at risk (OARs) is fundamental to cone-beam CT (CBCT)-based adaptive radiotherapy treatment planning, but is time consuming, labor intensive, and subject to interoperator variability. We investigated a deep learning-based rapid multiorgan delineation method for use in CBCT-guided adaptive pancreatic radiotherapy.

METHODS

To improve the accuracy of OAR delineation, two innovative solutions have been proposed in this study. First, instead of directly segmenting organs on CBCT images, a pretrained cycle-consistent generative adversarial network (cycleGAN) was applied to generating synthetic CT images given CBCT images. Second, an advanced deep learning model called mask-scoring regional convolutional neural network (MS R-CNN) was applied on those synthetic CT to detect the positions and shapes of multiple organs simultaneously for final segmentation. The OAR contours delineated by the proposed method were validated and compared with expert-drawn contours for geometric agreement using the Dice similarity coefficient (DSC), 95th percentile Hausdorff distance (HD95), mean surface distance (MSD), and residual mean square distance (RMS).

RESULTS

Across eight abdominal OARs including duodenum, large bowel, small bowel, left and right kidneys, liver, spinal cord, and stomach, the geometric comparisons between automated and expert contours are as follows: 0.92 (0.89-0.97) mean DSC, 2.90 mm (1.63-4.19 mm) mean HD95, 0.89 mm (0.61-1.36 mm) mean MSD, and 1.43 mm (0.90-2.10 mm) mean RMS. Compared to the competing methods, our proposed method had significant improvements (p < 0.05) in all the metrics for all the eight organs. Once the model was trained, the contours of eight OARs can be obtained on the order of seconds.

CONCLUSIONS

We demonstrated the feasibility of a synthetic CT-aided deep learning framework for automated delineation of multiple OARs on CBCT. The proposed method could be implemented in the setting of pancreatic adaptive radiotherapy to rapidly contour OARs with high accuracy.

Automated delineation of head and neck organs at risk using synthetic MRI-aided mask scoring regional convolutional neural network

PURPOSE

Auto-segmentation algorithms offer a potential solution to eliminate the labor-intensive, time-consuming, and observer-dependent manual delineation of organs-at-risk (OARs) in radiotherapy treatment planning. This study aimed to develop a deep learning-based automated OAR delineation method to tackle the current challenges remaining in achieving reliable expert performance with the state-of-the-art auto-delineation algorithms.

METHODS

The accuracy of OAR delineation is expected to be improved by utilizing the complementary contrasts provided by computed tomography (CT) (bony-structure contrast) and magnetic resonance imaging (MRI) (soft-tissue contrast). Given CT images, synthetic MR images were firstly generated by a pre-trained cycle-consistent generative adversarial network. The features of CT and synthetic MRI were then extracted and combined for the final delineation of organs using mask scoring regional convolutional neural network. Both in-house and public datasets containing CT scans from head-and-neck (HN) cancer patients were adopted to quantitatively evaluate the performance of the proposed method against current state-of-the-art algorithms in metrics including Dice similarity coefficient (DSC), 95th percentile Hausdorff distance (HD95), mean surface distance (MSD), and residual mean square distance (RMS).

RESULTS

Across all of 18 OARs in our in-house dataset, the proposed method achieved an average DSC, HD95, MSD, and RMS of 0.77 (0.58-0.90), 2.90 mm (1.32-7.63 mm), 0.89 mm (0.42-1.85 mm), and 1.44 mm (0.71-3.15 mm), respectively, outperforming the current state-of-the-art algorithms by 6%, 16%, 25%, and 36%, respectively. On public datasets, for all nine OARs, an average DSC of 0.86 (0.73-0.97) were achieved, 6% better than the competing methods.

CONCLUSION

We demonstrated the feasibility of a synthetic MRI-aided deep learning framework for automated delineation of OARs in HN radiotherapy treatment planning. The proposed method could be adopted into routine HN cancer radiotherapy treatment planning to rapidly contour OARs with high accuracy.