Segmentation of organs-at-risk in cervical cancer CT images with a convolutional neural network

Automated segmentation in pelvic radiotherapy: A comprehensive evaluation of ATLAS-, machine learning-, and deep learning-based models

Artificial intelligence can standardize and automatize highly demanding procedures, such as manual segmentation, especially in an anatomical site as common as the pelvis. This study investigated four automated segmentation tools on computed tomography (CT) images in female and male pelvic radiotherapy (RT) starting from simpler and well-known atlas-based methods to the most recent neural networks-based algorithms. The evaluation included quantitative, qualitative and time efficiency assessments. A mono-institutional consecutive series of 40 cervical cancer and 40 prostate cancer structure sets were retrospectively selected. After a preparatory phase, the remaining 20 testing sets per each site were auto-segmented by the atlas-based model STAPLE, a Random Forest-based model, and two Deep Learning-based tools (DL), MVision and LimbusAI. Setting manual segmentation as the Ground Truth, 200 structure sets were compared in terms of Dice Similarity Coefficient (DSC), Hausdorff Distance (HD), and Distance-to-Agreement Portion (DAP). Automated segmentation and manual correction durations were recorded. Expert clinicians performed a qualitative evaluation. In cervical cancer CTs, DL outperformed the other tools with higher quantitative metrics, qualitative scores, and shorter correction times. On the other hand, in prostate cancer CTs, the performance across all the analyzed tools was comparable in terms of both quantitative and qualitative metrics. Such discrepancy in performance outcome could be explained by the wide range of anatomical variability in cervical cancer with respect to the strict bladder and rectum filling preparation in prostate Stereotactic Body Radiation Therapy (SBRT). Decreasing segmentation times can reduce the burden of pelvic radiation therapy routine in an automated workflow.

Generalizability of deep learning in organ-at-risk segmentation: A transfer learning study in cervical brachytherapy

PURPOSE

Deep learning can automate delineation in radiation therapy, reducing time and variability. Yet, its efficacy varies across different institutions, scanners, or settings, emphasizing the need for adaptable and robust models in clinical environments. Our study demonstrates the effectiveness of the transfer learning (TL) approach in enhancing the generalizability of deep learning models for auto-segmentation of organs-at-risk (OARs) in cervical brachytherapy.

METHODS

A pre-trained model was developed using 120 scans with ring and tandem applicator on a 3T magnetic resonance (MR) scanner (RT3). Four OARs were segmented and evaluated. Segmentation performance was evaluated by Volumetric Dice Similarity Coefficient (vDSC), 95 % Hausdorff Distance (HD95), surface DSC, and Added Path Length (APL). The model was fine-tuned on three out-of-distribution target groups. Pre- and post-TL outcomes, and influence of number of fine-tuning scans, were compared. A model trained with one group (Single) and a model trained with all four groups (Mixed) were evaluated on both seen and unseen data distributions.

RESULTS

TL enhanced segmentation accuracy across target groups, matching the pre-trained model's performance. The first five fine-tuning scans led to the most noticeable improvements, with performance plateauing with more data. TL outperformed training-from-scratch given the same training data. The Mixed model performed similarly to the Single model on RT3 scans but demonstrated superior performance on unseen data.

CONCLUSIONS

TL can improve a model's generalizability for OAR segmentation in MR-guided cervical brachytherapy, requiring less fine-tuning data and reduced training time. These results provide a foundation for developing adaptable models to accommodate clinical settings.

A deep learning-based 3D Prompt-nnUnet model for automatic segmentation in brachytherapy of postoperative endometrial carcinoma

PURPOSE

To create and evaluate a three-dimensional (3D) Prompt-nnUnet module that utilizes the prompts-based model combined with 3D nnUnet for producing the rapid and consistent autosegmentation of high-risk clinical target volume (HR CTV) and organ at risk (OAR) in high-dose-rate brachytherapy (HDR BT) for patients with postoperative endometrial carcinoma (EC).

METHODS AND MATERIALS

On two experimental batches, a total of 321 computed tomography (CT) scans were obtained for HR CTV segmentation from 321 patients with EC, and 125 CT scans for OARs segmentation from 125 patients. The numbers of training/validation/test were 257/32/32 and 87/13/25 for HR CTV and OARs respectively. A novel comparison of the deep learning neural network 3D Prompt-nnUnet and 3D nnUnet was applied for HR CTV and OARs segmentation. Three-fold cross validation and several quantitative metrics were employed, including Dice similarity coefficient (DSC), Hausdorff distance (HD), 95th percentile of Hausdorff distance (HD95%), and intersection over union (IoU).

RESULTS

The Prompt-nnUnet included two forms of parameters Predict-Prompt (PP) and Label-Prompt (LP), with the LP performing most similarly to the experienced radiation oncologist and outperforming the less experienced ones. During the testing phase, the mean DSC values for the LP were 0.96 ± 0.02, 0.91 ± 0.02, and 0.83 ± 0.07 for HR CTV, rectum and urethra, respectively. The mean HD values (mm) were 2.73 ± 0.95, 8.18 ± 4.84, and 2.11 ± 0.50, respectively. The mean HD95% values (mm) were 1.66 ± 1.11, 3.07 ± 0.94, and 1.35 ± 0.55, respectively. The mean IoUs were 0.92 ± 0.04, 0.84 ± 0.03, and 0.71 ± 0.09, respectively. A delineation time < 2.35 s per structure in the new model was observed, which was available to save clinician time.

CONCLUSION

The Prompt-nnUnet architecture, particularly the LP, was highly consistent with ground truth (GT) in HR CTV or OAR autosegmentation, reducing interobserver variability and shortening treatment time.

The use of deep learning in interventional radiotherapy (brachytherapy): A review with a focus on open source and open data

Deep learning advanced to one of the most important technologies in almost all medical fields. Especially in areas, related to medical imaging it plays a big role. However, in interventional radiotherapy (brachytherapy) deep learning is still in an early phase. In this review, first, we investigated and scrutinised the role of deep learning in all processes of interventional radiotherapy and directly related fields. Additionally, we summarised the most recent developments. For better understanding, we provide explanations of key terms and approaches to solving common deep learning problems. To reproduce results of deep learning algorithms both source code and training data must be available. Therefore, a second focus of this work is on the analysis of the availability of open source, open data and open models. In our analysis, we were able to show that deep learning plays already a major role in some areas of interventional radiotherapy, but is still hardly present in others. Nevertheless, its impact is increasing with the years, partly self-propelled but also influenced by closely related fields. Open source, data and models are growing in number but are still scarce and unevenly distributed among different research groups. The reluctance in publishing code, data and models limits reproducibility and restricts evaluation to mono-institutional datasets. The conclusion of our analysis is that deep learning can positively change the workflow of interventional radiotherapy but there is still room for improvements when it comes to reproducible results and standardised evaluation methods.

Time-action and patient experience analyses of locally advanced cervical cancer brachytherapy

BACKGROUND AND PURPOSE

Although MRI-based image guided adaptive brachytherapy (IGABT) for locally advanced cervical cancer (LACC) has resulted in favorable outcomes, it can be logistically complex and time consuming compared to 2D image-based brachytherapy, and both physically and emotionally intensive for patients. This prospective study aims to perform time-action and patient experience analyses during IGABT to guide further improvements.

MATERIALS AND METHODS

LACC patients treated with IGABT were included for the time-action (56 patients) and patient experience (29 patients) analyses. Times per treatment step were reported on a standardized form. For the patient experience analysis, a baseline health status was established with the EQ-5D-5L questionnaire and the perceived pain, anxiety and duration for each treatment step were assessed with the NRS-11.

RESULTS

The median total procedure time from arrival until discharge was 530 (IQR: 480-565) minutes. Treatment planning (delineation, reconstruction, optimization) required the most time and took 175 (IQR: 145-195) minutes. Highest perceived pain was reported during applicator removal and treatment planning, anxiety during applicator removal, and duration during image acquisition and treatment planning. Perceived pain, anxiety and duration were correlated. Higher pre-treatment pain and anxiety scores were associated with higher perceived pain, anxiety and duration.

CONCLUSION

This study highlights the complexity, duration and impact on patient experience of the current IGABT workflow. Patient reported pre-treatment pain and anxiety can help identify patients that may benefit from additional support. Research and implementation of measures aiming at shortening the overall procedure duration, which may include logistical, staffing and technological aspects, should be prioritized.

Automatic segmentation of tumour and organs at risk in 3D MRI for cervical cancer radiation therapy with anatomical variations

Cervical cancer is a common cancer in women globally, with treatment usually involving radiation therapy (RT). Accurate segmentation for the tumour site and organ-at-risks (OARs) could assist in the reduction of treatment side effects and improve treatment planning efficiency. Cervical cancer Magnetic Resonance Imaging (MRI) segmentation is challenging due to a limited amount of training data available and large inter- and intra- patient shape variation for OARs. The proposed Masked-Net consists of a masked encoder within the 3D U-Net to account for the large shape variation within the dataset, with additional dilated layers added to improve segmentation performance. A new loss function was introduced to consider the bounding box loss during training with the proposed Masked-Net. Transfer learning from a male pelvis MRI data with a similar field of view was included. The approaches were compared to the 3D U-Net which was widely used in MRI image segmentation. The data used consisted of 52 volumes obtained from 23 patients with stage IB to IVB cervical cancer across a maximum of 7 weeks of RT with manually contoured labels including the bladder, cervix, gross tumour volume, uterus and rectum. The model was trained and tested with a 5-fold cross validation. Outcomes were evaluated based on the Dice Similarity Coefficients (DSC), the Hausdorff Distance (HD) and the Mean Surface Distance (MSD). The proposed method accounted for the small dataset, large variations in OAR shape and tumour sizes with an average DSC, HD and MSD for all anatomical structures of 0.790, 30.19mm and 3.15mm respectively.

Prospective Evaluation of Automated Contouring for CT-Based Brachytherapy for Gynecologic Malignancies

Purpose

The use of deep learning to auto-contour organs at risk (OARs) in gynecologic radiation treatment is well established. Yet, there is limited data investigating the prospective use of auto-contouring in clinical practice. In this study, we assess the accuracy and efficiency of auto-contouring OARs for computed tomography-based brachytherapy treatment planning of gynecologic malignancies.

Methods and Materials

An inhouse contouring tool automatically delineated 5 OARs in gynecologic radiation treatment planning: the bladder, small bowel, sigmoid, rectum, and urethra. Accuracy of each auto-contour was evaluated using a 5-point Likert scale: a score of 5 indicated the contour could be used without edits, while a score of 1 indicated the contour was unusable. During scoring, automated contours were edited and subsequently used for treatment planning. Dice similarity coefficient, mean surface distance, 95% Hausdorff distance, Hausdorff distance, and dosimetric changes between original and edited contours were calculated. Contour approval time and total planning time of a prospective auto-contoured (AC) cohort were compared with times from a retrospective manually contoured (MC) cohort.

Results

Thirty AC cases from January 2022 to July 2022 and 31 MC cases from July 2021 to January 2022 were included. The mean (±SD) Likert score for each OAR was the following: bladder 4.77 (±0.58), small bowel 3.96 (±0.91), sigmoid colon 3.92 (±0.81), rectum 4.6 (±0.71), and urethra 4.27 (±0.78). No ACs required major edits. All OARs had a mean Dice similarity coefficient > 0.86, mean surface distance < 0.48 mm, 95% Hausdorff distance < 3.2 mm, and Hausdorff distance < 10.32 mm between original and edited contours. There was no significant difference in dose-volume histogram metrics (D2.0 cc/D0.1 cc) between original and edited contours (P values > .05). The average time to plan approval in the AC cohort was 19% less than the MC cohort. (AC vs MC, 117.0 + 18.0 minutes vs 144.9 ± 64.5 minutes, P = .045).

Conclusions

Automated contouring is useful and accurate in clinical practice. Auto-contouring OARs streamlines radiation treatment workflows and decreases time required to design and approve gynecologic brachytherapy plans.

Segmentation of 71 Anatomical Structures Necessary for the Evaluation of Guideline-Conforming Clinical Target Volumes in Head and Neck Cancers

The delineation of the clinical target volumes (CTVs) for radiation therapy is time-consuming, requires intensive training and shows high inter-observer variability. Supervised deep-learning methods depend heavily on consistent training data; thus, State-of-the-Art research focuses on making CTV labels more homogeneous and strictly bounding them to current standards. International consensus expert guidelines standardize CTV delineation by conditioning the extension of the clinical target volume on the surrounding anatomical structures. Training strategies that directly follow the construction rules given in the expert guidelines or the possibility of quantifying the conformance of manually drawn contours to the guidelines are still missing. Seventy-one anatomical structures that are relevant to CTV delineation in head- and neck-cancer patients, according to the expert guidelines, were segmented on 104 computed tomography scans, to assess the possibility of automating their segmentation by State-of-the-Art deep learning methods. All 71 anatomical structures were subdivided into three subsets of non-overlapping structures, and a 3D nnU-Net model with five-fold cross-validation was trained for each subset, to automatically segment the structures on planning computed tomography scans. We report the DICE, Hausdorff distance and surface DICE for 71 + 5 anatomical structures, for most of which no previous segmentation accuracies have been reported. For those structures for which prediction values have been reported, our segmentation accuracy matched or exceeded the reported values. The predictions from our models were always better than those predicted by the TotalSegmentator. The sDICE with 2 mm margin was larger than 80% for almost all the structures. Individual structures with decreased segmentation accuracy are analyzed and discussed with respect to their impact on the CTV delineation following the expert guidelines. No deviation is expected to affect the rule-based automation of the CTV delineation.

Delineation of clinical target volume and organs at risk in cervical cancer radiotherapy by deep learning networks

PURPOSE

Delineation of the clinical target volume (CTV) and organs-at-risk (OARs) is important in cervical cancer radiotherapy. But it is generally labor-intensive, time-consuming, and subjective. This paper proposes a parallel-path attention fusion network (PPAF-net) to overcome these disadvantages in the delineation task.

METHODS

The PPAF-net utilizes both the texture and structure information of CTV and OARs by employing a U-Net network to capture the high-level texture information, and an up-sampling and down-sampling (USDS) network to capture the low-level structure information to accentuate the boundaries of CTV and OARs. Multi-level features extracted from both networks are then fused together through an attention module to generate the delineation result.

RESULTS

The dataset contains 276 computed tomography (CT) scans of patients with cervical cancer of staging IB-IIA. The images are provided by the West China Hospital of Sichuan University. Simulation results demonstrate that PPAF-net performs favorably on the delineation of the CTV and OARs (e.g., rectum, bladder and etc.) and achieves the state-of-the-art delineation accuracy, respectively, for the CTV and OARs. In terms of the Dice Similarity Coefficient (DSC) and the Hausdorff Distance (HD), 88.61% and 2.25 cm for the CTV, 92.27% and 0.73 cm for the rectum, 96.74% and 0.68 cm for the bladder, 96.38% and 0.65 cm for the left kidney, 96.79% and 0.63 cm for the right kidney, 93.42% and 0.52 cm for the left femoral head, 93.69% and 0.51 cm for the right femoral head, 87.53% and 1.07 cm for the small intestine, and 91.50% and 0.84 cm for the spinal cord.

CONCLUSIONS

The proposed automatic delineation network PPAF-net performs well on CTV and OARs segmentation tasks, which has great potential for reducing the burden of radiation oncologists and increasing the accuracy of delineation. In future, radiation oncologists from the West China Hospital of Sichuan University will further evaluate the results of network delineation, making this method helpful in clinical practice.

Assessing Interobserver Variability in the Delineation of Structures in Radiation Oncology: A Systematic Review

PURPOSE

The delineation of target volumes and organs at risk is the main source of uncertainty in radiation therapy. Numerous interobserver variability (IOV) studies have been conducted, often with unclear methodology and nonstandardized reporting. We aimed to identify the parameters chosen in conducting delineation IOV studies and assess their performances and limits.

METHODS AND MATERIALS

We conducted a systematic literature review to highlight major points of heterogeneity and missing data in IOV studies published between 2018 and 2021. For the main used metrics, we did in silico analyses to assess their limits in specific clinical situations.

RESULTS

All disease sites were represented in the 66 studies examined. Organs at risk were studied independently of tumor site in 29% of reviewed IOV studies. In 65% of studies, statistical analyses were performed. No gold standard (GS; ie, reference) was defined in 36% of studies. A single expert was considered as the GS in 21% of studies, without testing intraobserver variability. All studies reported both absolute and relative indices, including the Dice similarity coefficient (DSC) in 68% and the Hausdorff distance (HD) in 42%. Limitations were shown in silico for small structures when using the DSC and dependence on irregular shapes when using the HD. Variations in DSC values were large between studies, and their thresholds were inconsistent. Most studies (51%) included 1 to 10 cases. The median number of observers or experts was 7 (range, 2-35). The intraclass correlation coefficient was reported in only 9% of cases. Investigating the feasibility of studying IOV in delineation, a minimum of 8 observers with 3 cases, or 11 observers with 2 cases, was required to demonstrate moderate reproducibility.

CONCLUSIONS

Implementation of future IOV studies would benefit from a more standardized methodology: clear definitions of the gold standard and metrics and a justification of the tradeoffs made in the choice of the number of observers and number of delineated cases should be provided.

The role of Artificial intelligence in the assessment of the spine and spinal cord

Artificial intelligence (AI) application development is underway in all areas of radiology where many promising tools are focused on the spine and spinal cord. In the past decade, multiple spine AI algorithms have been created based on radiographs, computed tomography, and magnetic resonance imaging. These algorithms have wide-ranging purposes including automatic labeling of vertebral levels, automated description of disc degenerative changes, detection and classification of spine trauma, identification of osseous lesions, and the assessment of cord pathology. The overarching goals for these algorithms include improved patient throughput, reducing radiologist workload burden, and improving diagnostic accuracy. There are several pre-requisite tasks required in order to achieve these goals, such as automatic image segmentation, facilitating image acquisition and postprocessing. In this narrative review, we discuss some of the important imaging AI solutions that have been developed for the assessment of the spine and spinal cord. We focus on their practical applications and briefly discuss some key requirements for the successful integration of these tools into practice. The potential impact of AI in the imaging assessment of the spine and cord is vast and promises to provide broad reaching improvements for clinicians, radiologists, and patients alike.

Systematic Review of Tumor Segmentation Strategies for Bone Metastases

Purpose: To investigate the segmentation approaches for bone metastases in differentiating benign from malignant bone lesions and characterizing malignant bone lesions. Method: The literature search was conducted in Scopus, PubMed, IEEE and MedLine, and Web of Science electronic databases following the guidelines of Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA). A total of 77 original articles, 24 review articles, and 1 comparison paper published between January 2010 and March 2022 were included in the review. Results: The results showed that most studies used neural network-based approaches (58.44%) and CT-based imaging (50.65%) out of 77 original articles. However, the review highlights the lack of a gold standard for tumor boundaries and the need for manual correction of the segmentation output, which largely explains the absence of clinical translation studies. Moreover, only 19 studies (24.67%) specifically mentioned the feasibility of their proposed methods for use in clinical practice. Conclusion: Development of tumor segmentation techniques that combine anatomical information and metabolic activities is encouraging despite not having an optimal tumor segmentation method for all applications or can compensate for all the difficulties built into data limitations.

MAD-Net: Multi-attention dense network for functional bone marrow segmentation

Radiotherapy is the main treatment modality for various pelvic malignancies. However, high intensity radiation can damage the functional bone marrow (FBM), resulting in hematological toxicity (HT). Accurate identification and protection of the FBM during radiotherapy planning can reduce pelvic HT. The traditional manual method for contouring the FBM is time-consuming and laborious. Therefore, development of an efficient and accurate automatic segmentation mode can provide a distinct leverage in clinical settings. In this paper, we propose the first network for performing the FBM segmentation task, which is referred to as the multi-attention dense network (named MAD-Net). Primarily, we introduce the dense convolution block to promote the gradient flow in the network as well as incite feature reuse. Next, a novel slide-window attention module is proposed to emphasize long-range dependencies and exploit interdependencies between features. Finally, we design a residual-dual attention module as the bottleneck layer, which further aggregates useful spatial details and explores intra-class responsiveness of high-level features. In this work, we conduct extensive experiments on our dataset of 3838 two-dimensional pelvic slices. Experimental results demonstrate that the proposed MAD-Net transcends previous state-of-the-art models in various metrics. In addition, the contributions of the proposed components are verified by ablation analysis, and we conduct experiments on three other datasets to manifest the generalizability of MAD-Net.

Synergy between artificial intelligence and precision medicine for computer-assisted oral and maxillofacial surgical planning

OBJECTIVES

The aim of this review was to investigate the application of artificial intelligence (AI) in maxillofacial computer-assisted surgical planning (CASP) workflows with the discussion of limitations and possible future directions.

MATERIALS AND METHODS

An in-depth search of the literature was undertaken to review articles concerned with the application of AI for segmentation, multimodal image registration, virtual surgical planning (VSP), and three-dimensional (3D) printing steps of the maxillofacial CASP workflows.

RESULTS

The existing AI models were trained to address individual steps of CASP, and no single intelligent workflow was found encompassing all steps of the planning process. Segmentation of dentomaxillofacial tissue from computed tomography (CT)/cone-beam CT imaging was the most commonly explored area which could be applicable in a clinical setting. Nevertheless, a lack of generalizability was the main issue, as the majority of models were trained with the data derived from a single device and imaging protocol which might not offer similar performance when considering other devices. In relation to registration, VSP and 3D printing, the presence of inadequate heterogeneous data limits the automatization of these tasks.

CONCLUSION

The synergy between AI and CASP workflows has the potential to improve the planning precision and efficacy. However, there is a need for future studies with big data before the emergent technology finds application in a real clinical setting.

CLINICAL RELEVANCE

The implementation of AI models in maxillofacial CASP workflows could minimize a surgeon's workload and increase efficiency and consistency of the planning process, meanwhile enhancing the patient-specific predictability.

Patient-specific three-dimensional dose distribution prediction via deep learning for prostate cancer therapy: Improvement with the structure loss

PURPOSE

Deep learning (DL)-based dose distribution prediction can potentially reduce the cost of inverse planning process. We developed and introduced a structure-focused loss (L_struct) for 3D dose prediction to improve prediction accuracy. This study investigated the influence of L_struct on DL-based dose prediction for patients with prostate cancer. The proposed L_struct, which is similar in concept to dose-volume histogram (DVH)-based optimization in clinical practice, has the potential to provide more interpretable and accurate DL-based optimization.

METHODS

This study involved 104 patients who underwent prostate radiotherapy. We used 3D U-Net-based architecture to predict dose distributions from computed tomography and contours of the planning target volume and organs-at-risk. We trained two models using different loss functions: L2 loss and L_struct. Predicted doses were compared in terms of dose-volume parameters and the Dice similarity coefficient of isodose volume.

RESULTS

DVH analysis showed that the L_struct model had smaller errors from the ground truth than the L2 model. The L_struct model achieved more consistent dose distributions than the L2 model, with errors close to zero. The isodose Dice score of the L_struct model was greater than that of the L2 model by >20% of the prescribed dose.

CONCLUSIONS

We developed L_struct using labels of inputted contours for DL-based dose prediction for prostate radiotherapy. L_struct can be generalized to any DL architecture, thereby enhancing the dose prediction accuracy.

Evaluation of auto-segmentation for brachytherapy of postoperative cervical cancer using deep learning-based workflow

Objective. The purpose of this study was to evaluate the accuracy of brachytherapy (BT) planning structures derived from Deep learning (DL) based auto-segmentation compared with standard manual delineation for postoperative cervical cancer.Approach. We introduced a convolutional neural networks (CNN) which was developed and presented for auto-segmentation in cervical cancer radiotherapy. The dataset of 60 patients received BT of postoperative cervical cancer was used to train and test this model for delineation of high-risk clinical target volume (HRCTV) and organs at risk (OARs). Dice similarity coefficient (DSC), 95% Hausdorff distance (95%HD), Jaccard coefficient (JC) and dose-volume index (DVI) were used to evaluate the accuracy. The correlation between geometric metrics and dosimetric difference was performed by Spearman's correlation analysis. The radiation oncologists scored the auto-segmented contours by rating the lever of satisfaction (no edits, minor edits, major edits).Main results. The mean DSC values of DL based model were 0.87, 0.94, 0.86, 0.79 and 0.92 for HRCTV, bladder, rectum, sigmoid and small intestine, respectively. The Bland-Altman test obtained dose agreement for HRCTV_D_90%, HRCTV_D_mean, bladder_D_2cc, sigmoid_D_2ccand small intestine_D_2cc. Wilcoxon's signed-rank test indicated significant dosimetric differences in bladder_D_0.1cc, rectum_D_0.1ccand rectum_D_2cc(P< 0.05). A strong correlation between HRCTV_D_90%with its DSC (R= -0.842,P= 0.002) and JC (R= -0.818,P= 0.004) were found in Spearman's correlation analysis. From the physician review, 80% of HRCTVs and 72.5% of OARs in the test dataset were shown satisfaction (no edits).Significance. The proposed DL based model achieved a satisfied agreement between the auto-segmented and manually defined contours of HRCTV and OARs, although the clinical acceptance of small volume dose of OARs around the target was a concern. DL based auto-segmentation was an essential component in cervical cancer workflow which would generate the accurate contouring.

Evaluation of generalization ability for deep learning-based auto-segmentation accuracy in limited field of view CBCT of male pelvic region

PURPOSE

The aim of this study was to evaluate generalization ability of segmentation accuracy for limited FOV CBCT in the male pelvic region using a full-image CNN. Auto-segmentation accuracy was evaluated using various datasets with different intensity distributions and FOV sizes.

METHODS

A total of 171 CBCT datasets from patients with prostate cancer were enrolled. There were 151, 10, and 10 CBCT datasets acquired from Vero4DRT, TrueBeam STx, and Clinac-iX, respectively. The FOV for Vero4DRT, TrueBeam STx, and Clinac-iX was 20, 26, and 25 cm, respectively. The ROIs, including the bladder, prostate, rectum, and seminal vesicles, were manually delineated. The U² -Net CNN network architecture was used to train the segmentation model. A total of 131 limited FOV CBCT datasets from Vero4DRT were used for training (104 datasets) and validation (27 datasets); thereafter the rest were for testing. The training routine was set to save the best weight values when the DSC in the validation set was maximized. Segmentation accuracy was qualitatively and quantitatively evaluated between the ground truth and predicted ROIs in the different testing datasets.

RESULTS

The mean scores ± standard deviation of visual evaluation for bladder, prostate, rectum, and seminal vesicle in all treatment machines were 1.0 ± 0.7, 1.5 ± 0.6, 1.4 ± 0.6, and 2.1 ± 0.8 points, respectively. The median DSC values for all imaging devices were ≥0.94 for the bladder, 0.84-0.87 for the prostate and rectum, and 0.48-0.69 for the seminal vesicles. Although the DSC values for the bladder and seminal vesicles were significantly different among the three imaging devices, the DSC value of the bladder changed by less than 1% point. The median MSD values for all imaging devices were ≤1.2 mm for the bladder and 1.4-2.2 mm for the prostate, rectum, and seminal vesicles. The MSD values for the seminal vesicles were significantly different between the three imaging devices.

CONCLUSION

The proposed method is effective for testing datasets with different intensity distributions and FOV from training datasets.

Automatic segmentation for plan-of-the-day selection in CBCT-guided adaptive radiation therapy of cervical cancer

Objective.Plan-of-the-day (PoD) adaptive radiation therapy (ART) is based on a library of treatment plans, among which, at each treatment fraction, the PoD is selected using daily images. However, this strategy is limited by PoD selection uncertainties. This work aimed to propose and evaluate a workflow to automatically and quantitatively identify the PoD for cervix cancer ART based on daily CBCT images.Approach.The quantification was based on the segmentation of the main structures of interest in the CBCT images (clinical target volume [CTV], rectum, bladder, and bowel bag) using a deep learning model. Then, the PoD was selected from the treatment plan library according to the geometrical coverage of the CTV. For the evaluation, the resulting PoD was compared to the one obtained considering reference CBCT delineations.Main results.In experiments on a database of 23 patients with 272 CBCT images, the proposed method obtained an agreement between the reference PoD and the automatically identified PoD for 91.5% of treatment fractions (99.6% when considering a 5% margin on CTV coverage).Significance.The proposed automatic workflow automatically selected PoD for ART using deep-learning methods. The results showed the ability of the proposed process to identify the optimal PoD in a treatment plan library.

The future of MRI in radiation therapy: Challenges and opportunities for the MR community

Radiation therapy is a major component of cancer treatment pathways worldwide. The main aim of this treatment is to achieve tumor control through the delivery of ionizing radiation while preserving healthy tissues for minimal radiation toxicity. Because radiation therapy relies on accurate localization of the target and surrounding tissues, imaging plays a crucial role throughout the treatment chain. In the treatment planning phase, radiological images are essential for defining target volumes and organs-at-risk, as well as providing elemental composition (e.g., electron density) information for radiation dose calculations. At treatment, onboard imaging informs patient setup and could be used to guide radiation dose placement for sites affected by motion. Imaging is also an important tool for treatment response assessment and treatment plan adaptation. MRI, with its excellent soft tissue contrast and capacity to probe functional tissue properties, holds great untapped potential for transforming treatment paradigms in radiation therapy. The MR in Radiation Therapy ISMRM Study Group was established to provide a forum within the MR community to discuss the unmet needs and fuel opportunities for further advancement of MRI for radiation therapy applications. During the summer of 2021, the study group organized its first virtual workshop, attended by a diverse international group of clinicians, scientists, and clinical physicists, to explore our predictions for the future of MRI in radiation therapy for the next 25 years. This article reviews the main findings from the event and considers the opportunities and challenges of reaching our vision for the future in this expanding field.

Deep learning in CT image segmentation of cervical cancer: a systematic review and meta-analysis

Background

This paper attempts to conduct a systematic review and meta-analysis of deep learning (DLs) models for cervical cancer CT image segmentation.

Methods

Relevant studies were systematically searched in PubMed, Embase, The Cochrane Library, and Web of science. The literature on DLs for cervical cancer CT image segmentation were included, a meta-analysis was performed on the dice similarity coefficient (DSC) of the segmentation results of the included DLs models. We also did subgroup analyses according to the size of the sample, type of segmentation (i.e., two dimensions and three dimensions), and three organs at risk (i.e., bladder, rectum, and femur). This study was registered in PROSPERO prior to initiation (CRD42022307071).

Results

A total of 1893 articles were retrieved and 14 articles were included in the meta-analysis. The pooled effect of DSC score of clinical target volume (CTV), bladder, rectum, femoral head were 0.86(95%CI 0.84 to 0.87), 0.91(95%CI 0.89 to 0.93), 0.83(95%CI 0.79 to 0.88), and 0.92(95%CI 0.91to 0.94), respectively. For the performance of segmented CTV by two dimensions (2D) and three dimensions (3D) model, the DSC score value for 2D model was 0.87 (95%CI 0.85 to 0.90), while the DSC score for 3D model was 0.85 (95%CI 0.82 to 0.87). As for the effect of the capacity of sample on segmentation performance, no matter whether the sample size is divided into two groups: greater than 100 and less than 100, or greater than 150 and less than 150, the results show no difference (P > 0.05). Four papers reported the time for segmentation from 15 s to 2 min.

Conclusion

DLs have good accuracy in automatic segmentation of CT images of cervical cancer with a less time consuming and have good prospects for future radiotherapy applications, but still need public high-quality databases and large-scale research verification.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13014-022-02148-6.

Automatic segmentation of colon, small intestine, and duodenum based on scale attention network

PURPOSE

Automatic segmentation of colon, small intestine, and duodenum is a challenging task because of the great variability in the scale of the target organs. Multi-scale features are the key to alleviating this problem. Previous works focused on extracting discriminative multi-scale features through a hierarchical structure. Instead, the purpose of this work is to exploit these powerful multi-scale features more efficiently.

METHODS

A Scale Attention Module (SAM) was proposed to recalibrate multi-scale features by explicitly modeling their importance score adaptively. The SAM was introduced into the segmentation model to construct the Scale Attention Network (SANet). The multi-scale features extracted from the encoder were first re-extracted to obtain more specific multi-scale features. Then the SAM was applied to recalibrate the features. Specifically, for the feature of each scale, a summation of Global Average Pooling and Global Max Pooling was used to create scale-wise feature representations. According to the representations, a lightweight network was used to generate the importance score of each scale. The features were recalibrated based on the scores, and a simple pixel-by-pixel summation was used to fuse the multi-scale features. The fused multi-scale feature was fed into a segmentation head to complete the task.

RESULTS

The models were evaluated using fivefold cross-validation on 70 upper abdominal computed tomography scans of patients in a volume manner. The results showed that SANet could effectively alleviate the scale-variability problem and achieve better performance compared with UNet, Attention UNet, UNet++, Deeplabv3p, and CascadedUNet. The Dice similarity coefficients (DSCs) of colon, small intestine, and duodenum were (84.06 ± 3.66)%, (76.79 ± 5.12)%, and (61.68 ± 4.32)%, respectively. The HD95 were (7.51 ± 2.45) mm, (11.08 ± 2.45) mm, and (12.21 ± 1.95) mm, respectively. The values of relative volume difference were (3.4 ± 0.8)%, (11.6 ± 11.81)%, and (6.2 ± 3.71)%, respectively. The values of center-of-mass distance were 7.85 ± 2.82, 9.89 ± 2.70, and 9.94 ± 1.58, respectively. Compared with other attention modules and multi-scale feature exploitation approaches, SAM could obtain a 0.83-2.71 points improvement in terms of DSC with a comparable or even less number of parameters. The extensive experiments confirmed the effectiveness of SAM.

CONCLUSIONS

The SANet can efficiently exploit multi-scale features to alleviate the scale-variability problem and improve the segmentation performance on colon, small intestine, and duodenum of the upper abdomen.

A deep learning-based self-adapting ensemble method for segmentation in gynecological brachytherapy

Purpose

Fast and accurate outlining of the organs at risk (OARs) and high-risk clinical tumor volume (HRCTV) is especially important in high-dose-rate brachytherapy due to the highly time-intensive online treatment planning process and the high dose gradient around the HRCTV. This study aims to apply a self-configured ensemble method for fast and reproducible auto-segmentation of OARs and HRCTVs in gynecological cancer.

Materials and methods

We applied nnU-Net (no new U-Net), an automatically adapted deep convolutional neural network based on U-Net, to segment the bladder, rectum and HRCTV on CT images in gynecological cancer. In nnU-Net, three architectures, including 2D U-Net, 3D U-Net and 3D-Cascade U-Net, were trained and finally ensembled. 207 cases were randomly chosen for training, and 30 for testing. Quantitative evaluation used well-established image segmentation metrics, including dice similarity coefficient (DSC), 95% Hausdorff distance (HD95%), and average surface distance (ASD). Qualitative analysis of automated segmentation results was performed visually by two radiation oncologists. The dosimetric evaluation was performed by comparing the dose-volume parameters of both predicted segmentation and human contouring.

Results

nnU-Net obtained high qualitative and quantitative segmentation accuracy on the test dataset and performed better than previously reported methods in bladder and rectum segmentation. In quantitative evaluation, 3D-Cascade achieved the best performance in the bladder (DSC: 0.936 ± 0.051, HD95%: 3.503 ± 1.956, ASD: 0.944 ± 0.503), rectum (DSC: 0.831 ± 0.074, HD95%: 7.579 ± 5.857, ASD: 3.6 ± 3.485), and HRCTV (DSC: 0.836 ± 0.07, HD95%: 7.42 ± 5.023, ASD: 2.094 ± 1.311). According to the qualitative evaluation, over 76% of the test data set had no or minor visually detectable errors in segmentation.

Conclusion

This work showed nnU-Net’s superiority in segmenting OARs and HRCTV in gynecological brachytherapy cases in our center, among which 3D-Cascade shows the highest accuracy in segmentation across different applicators and patient anatomy.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13014-022-02121-3.

Evaluation of auto-segmentation for EBRT planning structures using deep learning-based workflow on cervical cancer

Deep learning (DL) based approach aims to construct a full workflow solution for cervical cancer with external beam radiation therapy (EBRT) and brachytherapy (BT). The purpose of this study was to evaluate the accuracy of EBRT planning structures derived from DL based auto-segmentation compared with standard manual delineation. Auto-segmentation model based on convolutional neural networks (CNN) was developed to delineate clinical target volumes (CTVs) and organs at risk (OARs) in cervical cancer radiotherapy. A total of 300 retrospective patients from multiple cancer centers were used to train and validate the model, and 75 independent cases were selected as testing data. The accuracy of auto-segmented contours were evaluated using geometric and dosimetric metrics including dice similarity coefficient (DSC), 95% hausdorff distance (95%HD), jaccard coefficient (JC) and dose-volume index (DVI). The correlation between geometric metrics and dosimetric difference was performed by Spearman’s correlation analysis. The right and left kidney, bladder, right and left femoral head showed superior geometric accuracy (DSC: 0.88–0.93; 95%HD: 1.03 mm–2.96 mm; JC: 0.78–0.88), and the Bland–Altman test obtained dose agreement for these contours (P > 0.05) between manual and DL based methods. Wilcoxon’s signed-rank test indicated significant dosimetric differences in CTV, spinal cord and pelvic bone (P < 0.001). A strong correlation between the mean dose of pelvic bone and its 95%HD (R = 0.843, P < 0.001) was found in Spearman’s correlation analysis, and the remaining structures showed weak link between dosimetric difference and all of geometric metrics. Our auto-segmentation achieved a satisfied agreement for most EBRT planning structures, although the clinical acceptance of CTV was a concern. DL based auto-segmentation was an essential component in cervical cancer workflow which would generate the accurate contouring.

The clinical evaluation of atlas-based auto-segmentation for automatic contouring during cervical cancer radiotherapy

Purpose

Our purpose was to investigate the influence of atlas library size and CT cross-slice number on the accuracy and efficiency of the atlas-based auto-segmentation (ABAS) method for the automatic contouring of clinical treatment volume (CTV) and organs at risk (OARs) during cervical cancer radiotherapy.

Methods

Of 140 cervical cancer patients, contours from 20, 40, 60, 80, 100, and 120 patients were selected incrementally to create six atlas library groups in ABAS. Another 20 tested patients were automatically contoured with the ABAS method and manually contoured by the same professional oncologist. Contours included CTV, bladder, rectum, femoral head-L, femoral head-R, and spinal cord. The CT cross-slice numbers of the 20 tested patients included 61, 65, 72, 75, 81, and 84. The index of dice similarity coefficients (DSCs) and Hausdorff distance (HD) were used to assess the consistency between ABAS automatic contouring and manual contouring. The randomized block analysis of variance and paired t-test were used for statistical analysis.

Results

The mean DSC values of “CTV, bladder, femoral head, and spinal cord” were all larger than 0.8. The femoral head and spinal cord showed a high degree of agreement between ABAS automatic contouring and manual contouring, with a mean DC >0.80 and HD <1 cm in all atlas library groups. A post-hoc least significant difference comparison indicated that no significant difference had been found between different atlas library sizes with DSC and HD values. For ABAS efficiency, the atlas library size had no effect on the time of ABAS automatic contouring. The time of automatic contouring increased slightly with the increase in CT cross-slice numbers, which were 99.9, 106.8, 114.0, 120.6, 127.9, and 134.8 s with CT cross-slices of 61, 65, 72, 75, 81, and 84, respectively.

Conclusion

A total of 20 atlas library sizes and a minimum CT cross-slice number including CTV and OARs are enough for ensuring the accuracy and efficiency of ABAS automatic contouring during cervical cancer radiotherapy.

Fully automated segmentation of clinical target volume in cervical cancer from magnetic resonance imaging with convolutional neural network

PURPOSE

Contouring clinical target volume (CTV) from medical images is an essential step for radiotherapy (RT) planning. Magnetic resonance imaging (MRI) is used as a standard imaging modality for CTV segmentation in cervical cancer due to its superior soft-tissue contrast. However, the delineation of CTV is challenging as CTV contains microscopic extensions that are not clearly visible even in MR images, resulting in significant contour variability among radiation oncologists depending on their knowledge and experience. In this study, we propose a fully automated deep learning-based method to segment CTV from MR images.

METHODS

Our method begins with the bladder segmentation, from which the CTV position is estimated in the axial view. The superior-inferior CTV span is then detected using an Attention U-Net. A CTV-specific region of interest (ROI) is determined, and three-dimensional (3-D) blocks are extracted from the ROI volume. Finally, a CTV segmentation map is computed using a 3-D U-Net from the extracted 3-D blocks.

RESULTS

We developed and evaluated our method using 213 MRI scans obtained from 125 patients (183 for training, 30 for test). Our method achieved (mean ± SD) Dice similarity coefficient of 0.85 ± 0.03 and the 95th percentile Hausdorff distance of 3.70 ± 0.35 mm on test cases, outperforming other state-of-the-art methods significantly (p-value < 0.05). Our method also produces an uncertainty map along with the CTV segmentation by employing the Monte Carlo dropout technique to draw physician's attention to the regions with high uncertainty, where careful review and manual correction may be needed.

CONCLUSIONS

Experimental results show that the developed method is accurate, fast, and reproducible for contouring CTV from MRI, demonstrating its potential to assist radiation oncologists in alleviating the burden of tedious contouring for RT planning in cervical cancer.

Pelvic U-Net: multi-label semantic segmentation of pelvic organs at risk for radiation therapy anal cancer patients using a deeply supervised shuffle attention convolutional neural network

BACKGROUND

Delineation of organs at risk (OAR) for anal cancer radiation therapy treatment planning is a manual and time-consuming process. Deep learning-based methods can accelerate and partially automate this task. The aim of this study was to develop and evaluate a deep learning model for automated and improved segmentations of OAR in the pelvic region.

METHODS

A 3D, deeply supervised U-Net architecture with shuffle attention, referred to as Pelvic U-Net, was trained on 143 computed tomography (CT) volumes, to segment OAR in the pelvic region, such as total bone marrow, rectum, bladder, and bowel structures. Model predictions were evaluated on an independent test dataset (n = 15) using the Dice similarity coefficient (DSC), the 95th percentile of the Hausdorff distance (HD₉₅), and the mean surface distance (MSD). In addition, three experienced radiation oncologists rated model predictions on a scale between 1-4 (excellent, good, acceptable, not acceptable). Model performance was also evaluated with respect to segmentation time, by comparing complete manual delineation time against model prediction time without and with manual correction of the predictions. Furthermore, dosimetric implications to treatment plans were evaluated using different dose-volume histogram (DVH) indices.

RESULTS

Without any manual corrections, mean DSC values of 97%, 87% and 94% were found for total bone marrow, rectum, and bladder. Mean DSC values for bowel cavity, all bowel, small bowel, and large bowel were 95%, 91%, 87% and 81%, respectively. Total bone marrow, bladder, and bowel cavity segmentations derived from our model were rated excellent (89%, 93%, 42%), good (9%, 5%, 42%), or acceptable (2%, 2%, 16%) on average. For almost all the evaluated DVH indices, no significant difference between model predictions and manual delineations was found. Delineation time per patient could be reduced from 40 to 12 min, including manual corrections of model predictions, and to 4 min without corrections.

CONCLUSIONS

Our Pelvic U-Net led to credible and clinically applicable OAR segmentations and showed improved performance compared to previous studies. Even though manual adjustments were needed for some predicted structures, segmentation time could be reduced by 70% on average. This allows for an accelerated radiation therapy treatment planning workflow for anal cancer patients.

A Data-Adaptive Loss Function for Incomplete Data and Incremental Learning in Semantic Image Segmentation

In the last years, deep learning has dramatically improved the performances in a variety of medical image analysis applications. Among different types of deep learning models, convolutional neural networks have been among the most successful and they have been used in many applications in medical imaging. Training deep convolutional neural networks often requires large amounts of image data to generalize well to new unseen images. It is often time-consuming and expensive to collect large amounts of data in the medical image domain due to expensive imaging systems, and the need for experts to manually make ground truth annotations. A potential problem arises if new structures are added when a decision support system is already deployed and in use. Since the field of radiation therapy is constantly developing, the new structures would also have to be covered by the decision support system. In the present work, we propose a novel loss function to solve multiple problems: imbalanced datasets, partially-labeled data, and incremental learning. The proposed loss function adapts to the available data in order to utilize all available data, even when some have missing annotations. We demonstrate that the proposed loss function also works well in an incremental learning setting, where an existing model is easily adapted to semi-automatically incorporate delineations of new organs when they appear. Experiments on a large in-house dataset show that the proposed method performs on par with baseline models, while greatly reducing the training time and eliminating the hassle of maintaining multiple models in practice.

A Feasibility Study of Deep Learning-Based Auto-Segmentation Directly Used in VMAT Planning Design and Optimization for Cervical Cancer

Purpose

To investigate the dosimetric impact on target volumes and organs at risk (OARs) when unmodified auto-segmented OAR contours are directly used in the design of treatment plans.

Materials and Methods

A total of 127 patients with cervical cancer were collected for retrospective analysis, including 105 patients in the training set and 22 patients in the testing set. The 3D U-net architecture was used for model training and auto-segmentation of nine types of organs at risk. The auto-segmented and manually segmented organ contours were used for treatment plan optimization to obtain the AS-VMAT (automatic segmentations VMAT) plan and the MS-VMAT (manual segmentations VMAT) plan, respectively. Geometric accuracy between the manual and predicted contours were evaluated using the Dice similarity coefficient (DSC), mean distance-to-agreement (MDA), and Hausdorff distance (HD). The dose volume histogram (DVH) and the gamma passing rate were used to identify the dose differences between the AS-VMAT plan and the MS-VMAT plan.

Results

Average DSC, MDA and HD₉₅ across all OARs were 0.82–0.96, 0.45–3.21 mm, and 2.30–17.31 mm on the testing set, respectively. The D_99% in the rectum and the Dmean in the spinal cord were 6.04 Gy (P = 0.037) and 0.54 Gy (P = 0.026) higher, respectively, in the AS-VMAT plans than in the MS-VMAT plans. The V₂₀, V₃₀, and V₄₀ in the rectum increased by 1.35% (P = 0.027), 1.73% (P = 0.021), and 1.96% (P = 0.008), respectively, whereas the V₁₀ in the spinal cord increased by 1.93% (P = 0.011). The differences in other dosimetry parameters were not statistically significant. The gamma passing rates in the clinical target volume (CTV) were 92.72% and 98.77%, respectively, using the 2%/2 mm and 3%/3 mm criteria, which satisfied the clinical requirements.

Conclusions

The dose distributions of target volumes were unaffected when auto-segmented organ contours were used in the design of treatment plans, whereas the impact of automated segmentation on the doses to OARs was complicated. We suggest that the auto-segmented contours of tissues in close proximity to the target volume need to be carefully checked and corrected when necessary.

All You Need Is a Few Dots to Label CT Images for Organ Segmentation

Image segmentation is used to analyze medical images quantitatively for diagnosis and treatment planning. Since manual segmentation requires considerable time and effort from experts, research to automatically perform segmentation is in progress. Recent studies using deep learning have improved performance but need many labeled data. Although there are public datasets for research, manual labeling is required in an area where labeling is not performed to train a model. We propose a deep-learning-based tool that can easily create training data to alleviate this inconvenience. The proposed tool receives a CT image and the pixels of organs the user wants to segment as inputs and extract the features of the CT image using a deep learning network. Then, pixels that have similar features are classified to the identical organ. The advantage of the proposed tool is that it can be trained with a small number of labeled data. After training with 25 labeled CT images, our tool shows competitive results when it is compared to the state-of-the-art segmentation algorithms, such as UNet and DeepNetV3.

Deep learning-based automatic delineation of anal cancer gross tumour volume: a multimodality comparison of CT, PET and MRI

BACKGROUND

Accurate target volume delineation is a prerequisite for high-precision radiotherapy. However, manual delineation is resource-demanding and prone to interobserver variation. An automatic delineation approach could potentially save time and increase delineation consistency. In this study, the applicability of deep learning for fully automatic delineation of the gross tumour volume (GTV) in patients with anal squamous cell carcinoma (ASCC) was evaluated for the first time. An extensive comparison of the effects single modality and multimodality combinations of computed tomography (CT), positron emission tomography (PET), and magnetic resonance imaging (MRI) have on automatic delineation quality was conducted.

MATERIAL AND METHODS

18F-fluorodeoxyglucose PET/CT and contrast-enhanced CT (ceCT) images were collected for 86 patients with ASCC. A subset of 36 patients also underwent a study-specific 3T MRI examination including T2- and diffusion-weighted imaging. The resulting two datasets were analysed separately. A two-dimensional U-Net convolutional neural network (CNN) was trained to delineate the GTV in axial image slices based on single or multimodality image input. Manual GTV delineations constituted the ground truth for CNN model training and evaluation. Models were evaluated using the Dice similarity coefficient (Dice) and surface distance metrics computed from five-fold cross-validation.

RESULTS

CNN-generated automatic delineations demonstrated good agreement with the ground truth, resulting in mean Dice scores of 0.65-0.76 and 0.74-0.83 for the 86 and 36-patient datasets, respectively. For both datasets, the highest mean Dice scores were obtained using a multimodal combination of PET and ceCT (0.76-0.83). However, models based on single modality ceCT performed comparably well (0.74-0.81). T2W-only models performed acceptably but were somewhat inferior to the PET/ceCT and ceCT-based models.

CONCLUSION

CNNs provided high-quality automatic GTV delineations for both single and multimodality image input, indicating that deep learning may prove a versatile tool for target volume delineation in future patients with ASCC.

A model to guide the management and decision of re-planning during radiotherapy for cervical cancer

BACKGROUND

To establish a model to predict whether re-planning is needed in the process of cervical cancer radiotherapy.

METHODS

We collected the clinical indexes of 132 patients diagnosed with cervical cancer receiving concurrent chemotherapy and radiotherapy, including 33 factors about tumor markers [carcinoembryonic antigen (CEA), cancer antigen 125 (CA-125), squamous cell carcinoma antigen (SCC)], tumor volume, rectal volume, bladder volume, volumes receiving 30-50 Gy in organs-at-risk (OARs), and the maximum dose (Dmax) received by 1-2 cc in OARs. We established a multivariate model for re-planning evaluation via principal component analysis, and then verified the model based on the internal data.

RESULTS

We identified the dose index (P1), tumor size index (P2), and volumes receiving 30-50 Gy in OARs and the tumor (P3) as the three most weighted factors of the re-planning model. We set the cut-off for the re-planning modification requirement at 1. The model was consistent with R = 0.12P1 + 0.21P2 + 0.31P3, and it performed accurately that area under the test set characteristics curve (AUC) =0.826].

CONCLUSIONS

Our proposed method can help to reduce image re-examination during treatment, decrease toxicities in OARs, shorten the radiotherapy course, lessen oncologists' efforts, and save medical resources.

Automatic Segmentation of Clinical Target Volume and Organs-at-Risk for Breast Conservative Radiotherapy Using a Convolutional Neural Network

Objective

Delineation of clinical target volume (CTV) and organs at risk (OARs) is important for radiotherapy but is time-consuming. We trained and evaluated a U-ResNet model to provide fast and consistent auto-segmentation.

Methods

We collected 160 patients’ CT scans with breast cancer who underwent breast-conserving surgery (BCS) and were treated with radiotherapy. CTV and OARs were delineated manually and were used for model training. The dice similarity coefficient (DSC) and 95th percentile Hausdorff distance (95HD) were used to assess the performance of our model. CTV and OARs were randomly selected as ground truth (GT) masks, and artificial intelligence (AI) masks were generated by the proposed model. Two clinicians randomly compared CTV score differences of the contour. The consistency between two clinicians was tested. Time cost for auto-delineation was evaluated.

Results

The mean DSC values of the proposed method were 0.94, 0.95, 0.94, 0.96, 0.96 and 0.93 for breast CTV, contralateral breast, heart, right lung, left lung and spinal cord, respectively. The mean 95HD values were 4.31mm, 3.59mm, 4.86mm, 3.18mm, 2.79mm and 4.37mm for the above structures, respectively. The average CTV scores for AI and GT were 2.89 versus 2.92 when evaluated by oncologist A (P=0.612), and 2.75 versus 2.83 by oncologist B (P=0.213), with no statistically significant differences. The consistency between two clinicians was poor (kappa=0.282). The time for auto-segmentation of CTV and OARs was 10.03 s.

Conclusion

Our proposed model (U-ResNet) can improve the efficiency and accuracy of delineation compared with U-Net, performing equally well with the segmentation generated by oncologists.

Fully automated multiorgan segmentation of female pelvic magnetic resonance images with coarse-to-fine convolutional neural network

PURPOSE

Brachytherapy combined with external beam radiotherapy (EBRT) is the standard treatment for cervical cancer and has been shown to improve overall survival rates compared to EBRT only. Magnetic resonance (MR) imaging is used for radiotherapy (RT) planning and image guidance due to its excellent soft tissue image contrast. Rapid and accurate segmentation of organs at risk (OAR) is a crucial step in MR image-guided RT. In this paper, we propose a fully automated two-step convolutional neural network (CNN) approach to delineate multiple OARs from T2-weighted (T2W) MR images.

METHODS

We employ a coarse-to-fine segmentation strategy. The coarse segmentation step first identifies the approximate boundary of each organ of interest and crops the MR volume around the centroid of organ-specific region of interest (ROI). The cropped ROI volumes are then fed to organ-specific fine segmentation networks to produce detailed segmentation of each organ. A three-dimensional (3-D) U-Net is trained to perform the coarse segmentation. For the fine segmentation, a 3-D Dense U-Net is employed in which a modified 3-D dense block is incorporated into the 3-D U-Net-like network to acquire inter and intra-slice features and improve information flow while reducing computational complexity. Two sets of T2W MR images (221 cases for MR1 and 62 for MR2) were taken with slightly different imaging parameters and used for our network training and test. The network was first trained on MR1 which was a larger sample set. The trained model was then transferred to the MR2 domain via a fine-tuning approach. Active learning strategy was utilized for selecting the most valuable data from MR2 to be included in the adaptation via transfer learning.

RESULTS

The proposed method was tested on 20 MR1 and 32 MR2 test sets. Mean ± SD dice similarity coefficients are 0.93 ± 0.04, 0.87 ± 0.03, and 0.80 ± 0.10 on MR1 and 0.94 ± 0.05, 0.88 ± 0.04, and 0.80 ± 0.05 on MR2 for bladder, rectum, and sigmoid, respectively. Hausdorff distances (95th percentile) are 4.18 ± 0.52, 2.54 ± 0.41, and 5.03 ± 1.31 mm on MR1 and 2.89 ± 0.33, 2.24 ± 0.40, and 3.28 ± 1.08 mm on MR2, respectively. The performance of our method is superior to other state-of-the-art segmentation methods.

CONCLUSIONS

We proposed a two-step CNN approach for fully automated segmentation of female pelvic MR bladder, rectum, and sigmoid from T2W MR volume. Our experimental results demonstrate that the developed method is accurate, fast, and reproducible, and outperforms alternative state-of-the-art methods for OAR segmentation significantly (p < 0.05).

Automatic Segmentation of Pelvic Cancers Using Deep Learning: State-of-the-Art Approaches and Challenges

The recent rise of deep learning (DL) and its promising capabilities in capturing non-explicit detail from large datasets have attracted substantial research attention in the field of medical image processing. DL provides grounds for technological development of computer-aided diagnosis and segmentation in radiology and radiation oncology. Amongst the anatomical locations where recent auto-segmentation algorithms have been employed, the pelvis remains one of the most challenging due to large intra- and inter-patient soft-tissue variabilities. This review provides a comprehensive, non-systematic and clinically-oriented overview of 74 DL-based segmentation studies, published between January 2016 and December 2020, for bladder, prostate, cervical and rectal cancers on computed tomography (CT) and magnetic resonance imaging (MRI), highlighting the key findings, challenges and limitations.

Clinical application and improvement of a CNN-based autosegmentation model for clinical target volumes in cervical cancer radiotherapy

OBJECTIVE

Clinical target volume (CTV) autosegmentation for cervical cancer is desirable for radiation therapy. Data heterogeneity and interobserver variability (IOV) limit the clinical adaptability of such methods. The adaptive method is proposed to improve the adaptability of CNN-based autosegmentation of CTV contours in cervical cancer.

METHODS

This study included 400 cervical cancer treatment planning cases with CTV delineated by radiation oncologists from three hospitals. The datasets were divided into five subdatasets (80 cases each). The cases in datasets 1, 2, and 3 were delineated by physicians A, B, and C, respectively. The cases in datasets 4 and 5 were delineated by multiple physicians. Dataset 1 was divided into training (50 cases), validation (10 cases), and testing (20 cases) cohorts, and they were used to construct the pretrained model. Datasets 2-5 were regarded as host datasets to evaluate the accuracy of the pretrained model. In the adaptive process, the pretrained model was fine-tuned to measure improvements by gradually adding more training cases selected from the host datasets. The accuracy of the autosegmentation model on each host dataset was evaluated using the corresponding test cases. The Dice similarity coefficient (DSC) and 95% Hausdorff distance (HD_95) were used to evaluate the accuracy.

RESULTS

Before and after adaptive improvements, the average DSC values on the host datasets were 0.818 versus 0.882, 0.763 versus 0.810, 0.727 versus 0.772, and 0.679 versus 0.789, which are improvements of 7.82%, 6.16%, 6.19%, and 16.05%, respectively. The average HD_95 values were 11.143 mm versus 6.853 mm, 22.402 mm versus 14.076 mm, 28.145 mm versus 16.437 mm, and 33.034 mm versus 16.441 mm, which are improvements of 37.94%, 37.17%, 41.60%, and 50.23%, respectively.

CONCLUSION

The proposed method improved the adaptability of the CNN-based autosegmentation model when applied to host datasets.

An Adversarial Deep-Learning-Based Model for Cervical Cancer CTV Segmentation With Multicenter Blinded Randomized Controlled Validation

Purpose

To propose a novel deep-learning-based auto-segmentation model for CTV delineation in cervical cancer and to evaluate whether it can perform comparably well to manual delineation by a three-stage multicenter evaluation framework.

Methods

An adversarial deep-learning-based auto-segmentation model was trained and configured for cervical cancer CTV contouring using CT data from 237 patients. Then CT scans of additional 20 consecutive patients with locally advanced cervical cancer were collected to perform a three-stage multicenter randomized controlled evaluation involving nine oncologists from six medical centers. This evaluation system is a combination of objective performance metrics, radiation oncologist assessment, and finally the head-to-head Turing imitation test. Accuracy and effectiveness were evaluated step by step. The intra-observer consistency of each oncologist was also tested.

Results

In stage-1 evaluation, the mean DSC and the 95HD value of the proposed model were 0.88 and 3.46 mm, respectively. In stage-2, the oncologist grading evaluation showed the majority of AI contours were comparable to the GT contours. The average CTV scores for AI and GT were 2.68 vs. 2.71 in week 0 (P = .206), and 2.62 vs. 2.63 in week 2 (P = .552), with no significant statistical differences. In stage-3, the Turing imitation test showed that the percentage of AI contours, which were judged to be better than GT contours by ≥5 oncologists, was 60.0% in week 0 and 42.5% in week 2. Most oncologists demonstrated good consistency between the 2 weeks (P > 0.05).

Conclusions

The tested AI model was demonstrated to be accurate and comparable to the manual CTV segmentation in cervical cancer patients when assessed by our three-stage evaluation framework.

Effects of sample size and data augmentation on U-Net-based automatic segmentation of various organs

Deep learning has demonstrated high efficacy for automatic segmentation in contour delineation, which is crucial in radiation therapy planning. However, the collection, labeling, and management of medical imaging data can be challenging. This study aims to elucidate the effects of sample size and data augmentation on the automatic segmentation of computed tomography images using U-Net, a deep learning method. For the chest and pelvic regions, 232 and 556 cases are evaluated, respectively. We investigate multiple conditions by changing the sum of the training and validation datasets across a broad range of values: 10-200 and 10-500 cases for the chest and pelvic regions, respectively. A U-Net is constructed, and horizontal-flip data augmentation, which produces left and right inverse images resulting in twice the number of images, is compared with no augmentation for each training session. All lung cases and more than 100 prostate, bladder, and rectum cases indicate that adding horizontal-flip data augmentation is almost as effective as doubling the number of cases. The slope of the Dice similarity coefficient (DSC) in all organs decreases rapidly until approximately 100 cases, stabilizes after 200 cases, and shows minimal changes as the number of cases is increased further. The DSCs stabilize at a smaller sample size with the incorporation of data augmentation in all organs except the heart. This finding is applicable to the automation of radiation therapy for rare cancers, where large datasets may be difficult to obtain.

Artificial intelligence in radiation oncology

Artificial intelligence (AI) is a computer science that tries to mimic human-like intelligence in machines that use computer software and algorithms to perform specific tasks without direct human input. Machine learning (ML) is a subunit of AI that uses data-driven algorithms that learn to imitate human behavior based on a previous example or experience. Deep learning is an ML technique that uses deep neural networks to create a model. The growth and sharing of data, increasing computing power, and developments in AI have initiated a transformation in healthcare. Advances in radiation oncology have produced a significant amount of data that must be integrated with computed tomography imaging, dosimetry, and imaging performed before each fraction. Of the many algorithms used in radiation oncology, has advantages and limitations with different computational power requirements. The aim of this review is to summarize the radiotherapy (RT) process in workflow order by identifying specific areas in which quality and efficiency can be improved by ML. The RT stage is divided into seven stages: patient evaluation, simulation, contouring, planning, quality control, treatment application, and patient follow-up. A systematic evaluation of the applicability, limitations, and advantages of AI algorithms has been done for each stage.

Dosimetric Impact of Intrafraction Motion in Online-Adaptive Intensity Modulated Proton Therapy for Cervical Cancer

PURPOSE

A method was recently developed for online-adaptive intensity modulated proton therapy (IMPT) in patients with cervical cancer. The advantage of this approach, relying on the use of tight margins, is challenged by the intrafraction target motion. The purpose of this study was to evaluate the dosimetric effect of intrafraction motion on the target owing to changes in bladder filling in patients with cervical cancer treated with online-adaptive IMPT.

METHODS AND MATERIALS

In 10 patients selected to have large uterus motion induced by bladder filling, the intrafraction anatomic changes were simulated for several prefraction durations for online (automated) contouring and planning. For each scenario, the coverage of the primary target was evaluated with margins of 2.5 and 5 mm.

RESULTS

Using a 5- mm planning target volume margin, median accumulated D98% was greater than 42.75 Gy_RBE1.1 (95% of the prescribed dose) in the case of a prefraction duration of 5 and 10 minutes. For a prefraction duration of 15 minutes, this parameter deteriorated to 42.6 Gy_RBE1.1. When margins were reduced to 2.5 mm, only a 5-minute duration resulted in median target D98% above 42.75 Gy_RBE1.1. In addition, smaller bladders were found to be associated with larger dose degradations compared with larger bladders.

CONCLUSIONS

This study indicates that intrafraction anatomic changes can have a substantial dosimetric effect on target coverage in an online-adaptive IMPT scenario for patients subject to large uterus motion. A margin of 5 mm was sufficient to compensate for the intrafraction motion due to bladder filling for up to 10 minutes of prefraction time. However, compensation for the uncertainties that were disregarded in this study, by using margins or robust optimization, is also required. Furthermore, a large bladder volume restrains intrafraction target motion and is recommended for treating patients in this scenario. Assuming that online-adaptive IMPT remains beneficial as long as narrow margins are used (5 mm or below), this study demonstrates its feasibility with regard to intrafraction motion.

Randomized multi-reader evaluation of automated detection and segmentation of brain tumors in stereotactic radiosurgery with deep neural networks

Background

Stereotactic radiosurgery (SRS), a validated treatment for brain tumors, requires accurate tumor contouring. This manual segmentation process is time-consuming and prone to substantial inter-practitioner variability. Artificial intelligence (AI) with deep neural networks have increasingly been proposed for use in lesion detection and segmentation but have seldom been validated in a clinical setting.

Methods

We conducted a randomized, cross-modal, multi-reader, multispecialty, multi-case study to evaluate the impact of AI assistance on brain tumor SRS. A state-of-the-art auto-contouring algorithm built on multi-modality imaging and ensemble neural networks was integrated into the clinical workflow. Nine medical professionals contoured the same case series in two reader modes (assisted or unassisted) with a memory washout period of 6 weeks between each section. The case series consisted of 10 algorithm-unseen cases, including five cases of brain metastases, three of meningiomas, and two of acoustic neuromas. Among the nine readers, three experienced experts determined the ground truths of tumor contours.

Results

With the AI assistance, the inter-reader agreement significantly increased (Dice similarity coefficient [DSC] from 0.86 to 0.90, P < 0.001). Algorithm-assisted physicians demonstrated a higher sensitivity for lesion detection than unassisted physicians (91.3% vs 82.6%, P = .030). AI assistance improved contouring accuracy, with an average increase in DSC of 0.028, especially for physicians with less SRS experience (average DSC from 0.847 to 0.865, P = .002). In addition, AI assistance improved efficiency with a median of 30.8% time-saving. Less-experienced clinicians gained prominent improvement on contouring accuracy but less benefit in reduction of working hours. By contrast, SRS specialists had a relatively minor advantage in DSC, but greater time-saving with the aid of AI.

Conclusions

Deep learning neural networks can be optimally utilized to improve accuracy and efficiency for the clinical workflow in brain tumor SRS.

Automatic Segmentation of Clinical Target Volumes for Post-Modified Radical Mastectomy Radiotherapy Using Convolutional Neural Networks

Background

This study aims to construct and validate a model based on convolutional neural networks (CNNs), which can fulfil the automatic segmentation of clinical target volumes (CTVs) of breast cancer for radiotherapy.

Methods

In this work, computed tomography (CT) scans of 110 patients who underwent modified radical mastectomies were collected. The CTV contours were confirmed by two experienced oncologists. A novel CNN was constructed to automatically delineate the CTV. Quantitative evaluation metrics were calculated, and a clinical evaluation was conducted to evaluate the performance of our model.

Results

The mean Dice similarity coefficient (DSC) of the proposed model was 0.90, and the 95th percentile Hausdorff distance (95HD) was 5.65 mm. The evaluation results of the two clinicians showed that 99.3% of the chest wall CTV slices could be accepted by clinician A, and this number was 98.9% for clinician B. In addition, 9/10 of patients had all slices accepted by clinician A, while 7/10 could be accepted by clinician B. The score differences between the AI (artificial intelligence) group and the GT (ground truth) group showed no statistically significant difference for either clinician. However, the score differences in the AI group were significantly different between the two clinicians. The Kappa consistency index was 0.259. It took 3.45 s to delineate the chest wall CTV using the model.

Conclusion

Our model could automatically generate the CTVs for breast cancer. AI-generated structures of the proposed model showed a trend that was comparable, or was even better, than those of human-generated structures. Additional multicentre evaluations should be performed for adequate validation before the model can be completely applied in clinical practice.

Evaluation of deep learning-based auto-segmentation algorithms for delineating clinical target volume and organs at risk involving data for 125 cervical cancer patients

Objective

To evaluate the accuracy of a deep learning‐based auto‐segmentation mode to that of manual contouring by one medical resident, where both entities tried to mimic the delineation "habits" of the same clinical senior physician.

Methods

This study included 125 cervical cancer patients whose clinical target volumes (CTVs) and organs at risk (OARs) were delineated by the same senior physician. Of these 125 cases, 100 were used for model training and the remaining 25 for model testing. In addition, the medical resident instructed by the senior physician for approximately 8 months delineated the CTVs and OARs for the testing cases. The dice similarity coefficient (DSC) and the Hausdorff Distance (HD) were used to evaluate the delineation accuracy for CTV, bladder, rectum, small intestine, femoral‐head‐left, and femoral‐head‐right.

Results

The DSC values of the auto‐segmentation model and manual contouring by the resident were, respectively, 0.86 and 0.83 for the CTV (P < 0.05), 0.91 and 0.91 for the bladder (P > 0.05), 0.88 and 0.84 for the femoral‐head‐right (P < 0.05), 0.88 and 0.84 for the femoral‐head‐left (P < 0.05), 0.86 and 0.81 for the small intestine (P < 0.05), and 0.81 and 0.84 for the rectum (P > 0.05). The HD (mm) values were, respectively, 14.84 and 18.37 for the CTV (P < 0.05), 7.82 and 7.63 for the bladder (P > 0.05), 6.18 and 6.75 for the femoral‐head‐right (P > 0.05), 6.17 and 6.31 for the femoral‐head‐left (P > 0.05), 22.21 and 26.70 for the small intestine (P > 0.05), and 7.04 and 6.13 for the rectum (P > 0.05). The auto‐segmentation model took approximately 2 min to delineate the CTV and OARs while the resident took approximately 90 min to complete the same task.

Conclusion

The auto‐segmentation model was as accurate as the medical resident but with much better efficiency in this study. Furthermore, the auto‐segmentation approach offers additional perceivable advantages of being consistent and ever improving when compared with manual approaches.

Automatic contouring system for cervical cancer using convolutional neural networks

PURPOSE

To develop a tool for the automatic contouring of clinical treatment volumes (CTVs) and normal tissues for radiotherapy treatment planning in cervical cancer patients.

METHODS

An auto-contouring tool based on convolutional neural networks (CNN) was developed to delineate three cervical CTVs and 11 normal structures (seven OARs, four bony structures) in cervical cancer treatment for use with the Radiation Planning Assistant, a web-based automatic plan generation system. A total of 2254 retrospective clinical computed tomography (CT) scans from a single cancer center and 210 CT scans from a segmentation challenge were used to train and validate the CNN-based auto-contouring tool. The accuracy of the tool was evaluated by calculating the Sørensen-dice similarity coefficient (DSC) and mean surface and Hausdorff distances between the automatically generated contours and physician-drawn contours on 140 internal CT scans. A radiation oncologist scored the automatically generated contours on 30 external CT scans from three South African hospitals.

RESULTS

The average DSC, mean surface distance, and Hausdorff distance of our CNN-based tool were 0.86/0.19 cm/2.02 cm for the primary CTV, 0.81/0.21 cm/2.09 cm for the nodal CTV, 0.76/0.27 cm/2.00 cm for the PAN CTV, 0.89/0.11 cm/1.07 cm for the bladder, 0.81/0.18 cm/1.66 cm for the rectum, 0.90/0.06 cm/0.65 cm for the spinal cord, 0.94/0.06 cm/0.60 cm for the left femur, 0.93/0.07 cm/0.66 cm for the right femur, 0.94/0.08 cm/0.76 cm for the left kidney, 0.95/0.07 cm/0.84 cm for the right kidney, 0.93/0.05 cm/1.06 cm for the pelvic bone, 0.91/0.07 cm/1.25 cm for the sacrum, 0.91/0.07 cm/0.53 cm for the L4 vertebral body, and 0.90/0.08 cm/0.68 cm for the L5 vertebral bodies. On average, 80% of the CTVs, 97% of the organ at risk, and 98% of the bony structure contours in the external test dataset were clinically acceptable based on physician review.

CONCLUSIONS

Our CNN-based auto-contouring tool performed well on both internal and external datasets and had a high rate of clinical acceptability.

Auto-segmentations by convolutional neural network in cervical and anorectal cancer with clinical structure sets as the ground truth

•

The network provided auto-segmentations with high overlap with ground truth volumes.

•

Evaluation of femoral heads/bladder auto-segmentations showed highest overlap.

•

Annotated structure sets from daily clinical practice is feasible as ground truth.

Background

It is time-consuming for oncologists to delineate volumes for radiotherapy treatment in computer tomography (CT) images. Automatic delineation based on image processing exists, but with varied accuracy and moderate time savings. Using convolutional neural network (CNN), delineations of volumes are faster and more accurate. We have used CTs with the annotated structure sets to train and evaluate a CNN.

Material and methods

The CNN is a standard segmentation network modified to minimize memory usage. We used CTs and structure sets from 75 cervical cancers and 191 anorectal cancers receiving radiation therapy at Skåne University Hospital 2014-2018. Five structures were investigated: left/right femoral heads, bladder, bowel bag, and clinical target volume of lymph nodes (CTVNs). Dice score and mean surface distance (MSD) (mm) evaluated accuracy, and one oncologist qualitatively evaluated auto-segmentations.

Results

Median Dice/MSD scores for anorectal cancer: 0.91–0.92/1.93–1.86 femoral heads, 0.94/2.07 bladder, and 0.83/6.80 bowel bag. Median Dice scores for cervical cancer were 0.93–0.94/1.42–1.49 femoral heads, 0.84/3.51 bladder, 0.88/5.80 bowel bag, and 0.82/3.89 CTVNs. With qualitative evaluation, performance on femoral heads and bladder auto-segmentations was mostly excellent, but CTVN auto-segmentations were not acceptable to a larger extent.

Discussion

It is possible to train a CNN with high overlap using structure sets as ground truth. Manually delineated pelvic volumes from structure sets do not always strictly follow volume boundaries and are sometimes inaccurately defined, which leads to similar inaccuracies in the CNN output. More data that is consistently annotated is needed to achieve higher CNN accuracy and to enable future clinical implementation.

Automated Radiation Treatment Planning for Cervical Cancer

The radiation treatment-planning process includes contouring, planning, and reviewing the final plan, and each component requires substantial time and effort from multiple experts. Automation of treatment planning can save time and reduce the cost of radiation treatment, and potentially provides more consistent and better quality plans. With the recent breakthroughs in computer hardware and artificial intelligence technology, automation methods for radiation treatment planning have achieved a clinically acceptable level of performance in general. At the same time, the automation process should be developed and evaluated independently for different disease sites and treatment techniques as they are unique from each other. In this article, we will discuss the current status of automated radiation treatment planning for cervical cancer for simple and complex plans and corresponding automated quality assurance methods. Furthermore, we will introduce Radiation Planning Assistant, a web-based system designed to fully automate treatment planning for cervical cancer and other treatment sites.