CNN-Based Quality Assurance for Automatic Segmentation of Breast Cancer in Radiotherapy

Deep learning for autosegmentation for radiotherapy treatment planning: State-of-the-art and novel perspectives

The rapid development of artificial intelligence (AI) has gained importance, with many tools already entering our daily lives. The medical field of radiation oncology is also subject to this development, with AI entering all steps of the patient journey. In this review article, we summarize contemporary AI techniques and explore the clinical applications of AI-based automated segmentation models in radiotherapy planning, focusing on delineation of organs at risk (OARs), the gross tumor volume (GTV), and the clinical target volume (CTV). Emphasizing the need for precise and individualized plans, we review various commercial and freeware segmentation tools and also state-of-the-art approaches. Through our own findings and based on the literature, we demonstrate improved efficiency and consistency as well as time savings in different clinical scenarios. Despite challenges in clinical implementation such as domain shifts, the potential benefits for personalized treatment planning are substantial. The integration of mathematical tumor growth models and AI-based tumor detection further enhances the possibilities for refining target volumes. As advancements continue, the prospect of one-stop-shop segmentation and radiotherapy planning represents an exciting frontier in radiotherapy, potentially enabling fast treatment with enhanced precision and individualization.

Artificial Intelligence Uncertainty Quantification in Radiotherapy Applications - A Scoping Review

Background/purpose

The use of artificial intelligence (AI) in radiotherapy (RT) is expanding rapidly. However, there exists a notable lack of clinician trust in AI models, underscoring the need for effective uncertainty quantification (UQ) methods. The purpose of this study was to scope existing literature related to UQ in RT, identify areas of improvement, and determine future directions.

Methods

We followed the PRISMA-ScR scoping review reporting guidelines. We utilized the population (human cancer patients), concept (utilization of AI UQ), context (radiotherapy applications) framework to structure our search and screening process. We conducted a systematic search spanning seven databases, supplemented by manual curation, up to January 2024. Our search yielded a total of 8980 articles for initial review. Manuscript screening and data extraction was performed in Covidence. Data extraction categories included general study characteristics, RT characteristics, AI characteristics, and UQ characteristics.

Results

We identified 56 articles published from 2015-2024. 10 domains of RT applications were represented; most studies evaluated auto-contouring (50%), followed by image-synthesis (13%), and multiple applications simultaneously (11%). 12 disease sites were represented, with head and neck cancer being the most common disease site independent of application space (32%). Imaging data was used in 91% of studies, while only 13% incorporated RT dose information. Most studies focused on failure detection as the main application of UQ (60%), with Monte Carlo dropout being the most commonly implemented UQ method (32%) followed by ensembling (16%). 55% of studies did not share code or datasets.

Conclusion

Our review revealed a lack of diversity in UQ for RT applications beyond auto-contouring. Moreover, there was a clear need to study additional UQ methods, such as conformal prediction. Our results may incentivize the development of guidelines for reporting and implementation of UQ in RT.

NRG Oncology Assessment of Artificial Intelligence Deep Learning-Based Auto-segmentation for Radiation Therapy: Current Developments, Clinical Considerations, and Future Directions

Deep learning neural networks (DLNN) in Artificial intelligence (AI) have been extensively explored for automatic segmentation in radiotherapy (RT). In contrast to traditional model-based methods, data-driven AI-based models for auto-segmentation have shown high accuracy in early studies in research settings and controlled environment (single institution). Vendor-provided commercial AI models are made available as part of the integrated treatment planning system (TPS) or as a stand-alone tool that provides streamlined workflow interacting with the main TPS. These commercial tools have drawn clinics' attention thanks to their significant benefit in reducing the workload from manual contouring and shortening the duration of treatment planning. However, challenges occur when applying these commercial AI-based segmentation models to diverse clinical scenarios, particularly in uncontrolled environments. Contouring nomenclature and guideline standardization has been the main task undertaken by the NRG Oncology. AI auto-segmentation holds the potential clinical trial participants to reduce interobserver variations, nomenclature non-compliance, and contouring guideline deviations. Meanwhile, trial reviewers could use AI tools to verify contour accuracy and compliance of those submitted datasets. In recognizing the growing clinical utilization and potential of these commercial AI auto-segmentation tools, NRG Oncology has formed a working group to evaluate the clinical utilization and potential of commercial AI auto-segmentation tools. The group will assess in-house and commercially available AI models, evaluation metrics, clinical challenges, and limitations, as well as future developments in addressing these challenges. General recommendations are made in terms of the implementation of these commercial AI models, as well as precautions in recognizing the challenges and limitations.

A multi-modal vision-language pipeline strategy for contour quality assurance and adaptive optimization

Objective.Accurate delineation of organs-at-risk (OARs) is a critical step in radiotherapy. The deep learning generated segmentations usually need to be reviewed and corrected by oncologists manually, which is time-consuming and operator-dependent. Therefore, an automated quality assurance (QA) and adaptive optimization correction strategy was proposed to identify and optimize 'incorrect' auto-segmentations.Approach.A total of 586 CT images and labels from nine institutions were used. The OARs included the brainstem, parotid, and mandible. The deep learning generated contours were compared with the manual ground truth delineations. In this study, we proposed a novel contour quality assurance and adaptive optimization (CQA-AO) strategy, which consists of the following three main components: (1) the contour QA module classified the deep learning generated contours as either accepted or unaccepted; (2) the unacceptable contour categories analysis module provided the potential error reasons (five unacceptable category) and locations (attention heatmaps); (3) the adaptive correction of unacceptable contours module integrate vision-language representations and utilize convex optimization algorithms to achieve adaptive correction of 'incorrect' contours.Main results. In the contour QA tasks, the sensitivity (accuracy, precision) of CQA-AO strategy reached 0.940 (0.945, 0.948), 0.962 (0.937, 0.913), and 0.967 (0.962, 0.957) for brainstem, parotid and mandible, respectively. The unacceptable contour category analysis, the(FI,AccI,Fmicro,Fmacro)of CQA-AO strategy reached (0.901, 0.763, 0.862, 0.822), (0.855, 0.737, 0.837, 0.784), and (0.907, 0.762, 0.858, 0.821) for brainstem, parotid and mandible, respectively. After adaptive optimization correction, the DSC values of brainstem, parotid and mandible have been improved by 9.4%, 25.9%, and 13.5%, and Hausdorff distance values decreased by 62%, 70.6%, and 81.6%, respectively.Significance. The proposed CQA-AO strategy, which combines QA of contour and adaptive optimization correction for OARs contouring, demonstrated superior performance compare to conventional methods. This method can be implemented in the clinical contouring procedures and improve the efficiency of delineating and reviewing workflow.

Performance analysis and knowledge-based quality assurance of critical organ auto-segmentation for pediatric craniospinal irradiation

Craniospinal irradiation (CSI) is a vital therapeutic approach utilized for young patients suffering from central nervous system disorders such as medulloblastoma. The task of accurately outlining the treatment area is particularly time-consuming due to the presence of several sensitive organs at risk (OAR) that can be affected by radiation. This study aimed to assess two different methods for automating the segmentation process: an atlas technique and a deep learning neural network approach. Additionally, a novel method was devised to prospectively evaluate the accuracy of automated segmentation as a knowledge-based quality assurance (QA) tool. Involving a patient cohort of 100, ranging in ages from 2 to 25 years with a median age of 8, this study employed quantitative metrics centered around overlap and distance calculations to determine the most effective approach for practical clinical application. The contours generated by two distinct methods of atlas and neural network were compared to ground truth contours approved by a radiation oncologist, utilizing 13 distinct metrics. Furthermore, an innovative QA tool was conceptualized, designed for forthcoming cases based on the baseline dataset of 100 patient cases. The calculated metrics indicated that, in the majority of cases (60.58%), the neural network method demonstrated a notably higher alignment with the ground truth. Instances where no difference was observed accounted for 31.25%, while utilization of the atlas method represented 8.17%. The QA tool results showed that the two approaches achieved 100% agreement in 39.4% of instances for the atlas method and in 50.6% of instances for the neural network auto-segmentation. The results indicate that the neural network approach showcases superior performance, and its significantly closer physical alignment to ground truth contours in the majority of cases. The metrics derived from overlap and distance measurements have enabled clinicians to discern the optimal choice for practical clinical application.

Determination of output factor for CyberKnife using scintillation dosimetry and deep learning

Objective. Small-field dosimetry is an ongoing challenge in radiotherapy quality assurance (QA) especially for radiosurgery systems such as CyberKnifeTM. The objective of this work is to demonstrate the use of a plastic scintillator imaged with a commercial camera to measure the output factor of a CyberKnife system. The output factor describes the dose on the central axis as a function of collimator size, and is a fundamental part of CyberKnife QA and integral to the data used in the treatment planning system.Approach. A self-contained device consisting of a solid plastic scintillator and a camera was build in a portable Pelicase. Photographs were analysed using classical methods and with convolutional neural networks (CNN) to predict beam parameters which were then compared to measurements.Main results. Initial results using classical image processing to determine standard QA parameters such as percentage depth dose (PDD) were unsuccessful, with 34% of points failing to meet the Gamma criterion (which measures the distance between corresponding points and the relative difference in dose) of 2 mm/2%. However, when images were processed using a CNN trained on simulated data and a green scintillator sheet, 92% of PDD curves agreed with measurements with a microdiamond detector to within 2 mm/2% and 78% to 1%/1 mm. The mean difference between the output factors measured using this system and a microdiamond detector was 1.1%. Confidence in the results was enhanced by using the algorithm to predict the known collimator sizes from the photographs which it was able to do with an accuracy of less than 1 mm.Significance. With refinement, a full output factor curve could be measured in less than an hour, offering a new approach for rapid, convenient small-field dosimetry.

Accurate and robust auto-segmentation of head and neck organ-at-risks based on a novel CNN fine-tuning workflow

PURPOSE

Obvious inconsistencies in auto-segmentations exist among various AI software. In this study, we have developed a novel convolutional neural network (CNN) fine-tuning workflow to achieve precise and robust localized segmentation.

METHODS

The datasets include Hubei Cancer Hospital dataset, Cetuximab Head and Neck Public Dataset, and Québec Public Dataset. Seven organs-at-risks (OARs), including brain stem, left parotid gland, esophagus, left optic nerve, optic chiasm, mandible, and pharyngeal constrictor, were selected. The auto-segmentation results from four commercial AI software were first compared with the manual delineations. Then a new multi-scale lightweight residual CNN model with an attention module (named as HN-Net) was trained and tested on 40 samples and 10 samples from Hubei Cancer Hospital, respectively. To enhance the network's accuracy and generalization ability, the fine-tuning workflow utilized an uncertainty estimation method for automatic selection of candidate samples of worthiness from Cetuximab Head and Neck Public Dataset for further training. The segmentation performances were evaluated on the Hubei Cancer Hospital dataset and/or the entire Québec Public Dataset.

RESULTS

A maximum difference of 0.13 and 0.7 mm in average Dice value and Hausdorff distance value for the seven OARs were observed by four AI software. The proposed HN-Net achieved an average Dice value of 0.14 higher than that of the AI software, and it also outperformed other popular CNN models (HN-Net: 0.79, U-Net: 0.78, U-Net++: 0.78, U-Net-Multi-scale: 0.77, AI software: 0.65). Additionally, the HN-Net fine-tuning workflow by using the local datasets and external public datasets further improved the automatic segmentation with the average Dice value by 0.02.

CONCLUSION

The delineations of commercial AI software need to be carefully reviewed, and localized further training is necessary for clinical practice. The proposed fine-tuning workflow could be feasibly adopted to implement an accurate and robust auto-segmentation model by using local datasets and external public datasets.

Deep Learning for Fully Automatic Tumor Segmentation on Serially Acquired Dynamic Contrast-Enhanced MRI Images of Triple-Negative Breast Cancer

Accurate tumor segmentation is required for quantitative image analyses, which are increasingly used for evaluation of tumors. We developed a fully automated and high-performance segmentation model of triple-negative breast cancer using a self-configurable deep learning framework and a large set of dynamic contrast-enhanced MRI images acquired serially over the patients' treatment course. Among all models, the top-performing one that was trained with the images across different time points of a treatment course yielded a Dice similarity coefficient of 93% and a sensitivity of 96% on baseline images. The top-performing model also produced accurate tumor size measurements, which is valuable for practical clinical applications.

A network score-based metric to optimize the quality assurance of automatic radiotherapy target segmentations

Background and purpose

Existing methods for quality assurance of the radiotherapy auto-segmentations focus on the correlation between the average model entropy and the Dice Similarity Coefficient (DSC) only. We identified a metric directly derived from the output of the network and correlated it with clinically relevant metrics for contour accuracy.

Materials and Methods

Magnetic Resonance Imaging auto-segmentations were available for the gross tumor volume for cervical cancer brachytherapy (106 segmentations) and for the clinical target volume for rectal cancer external-beam radiotherapy (77 segmentations). The nnU-Net's output before binarization was taken as a score map. We defined a metric as the mean of the voxels in the score map above a threshold (λ). Comparisons were made with the mean and standard deviation over the score map and with the mean over the entropy map. The DSC, the 95th Hausdorff distance, the mean surface distance (MSD) and the surface DSC were computed for segmentation quality. Correlations between the studied metrics and model quality were assessed with the Pearson correlation coefficient (r). The area under the curve (AUC) was determined for detecting segmentations that require reviewing.

Results

For both tasks, our metric (λ = 0.30) correlated more strongly with the segmentation quality than the mean over the entropy map (for surface DSC, r > 0.65 vs. r < 0.60). The AUC was above 0.84 for detecting MSD values above 2 mm.

Conclusions

Our metric correlated strongly with clinically relevant segmentation metrics and detected segmentations that required reviewing, indicating its potential for automatic quality assurance of radiotherapy target auto-segmentations.

Contouring quality assurance methodology based on multiple geometric features against deep learning auto-segmentation

BACKGROUND

Contouring error is one of the top failure modes in radiation treatment. Multiple efforts have been made to develop tools to automatically detect segmentation errors. Deep learning-based auto-segmentation (DLAS) has been used as a baseline for flagging manual segmentation errors, but those efforts are limited to using only one or two contour comparison metrics.

PURPOSE

The purpose of this research is to develop an improved contouring quality assurance system to identify and flag manual contouring errors.

METHODS AND MATERIALS

DLAS contours were used as a reference to compare with manually segmented contours. A total of 27 geometric agreement metrics were determined from the comparisons between the two segmentation approaches. Feature selection was performed to optimize the training of a machine learning classification model to identify potential contouring errors. A public dataset with 339 cases was used to train and test the classifier. Four independent classifiers were trained using five-fold cross validation, and the predictions from each classifier were ensembled using soft voting. The trained model was validated on a held-out testing dataset. An additional independent clinical dataset with 60 cases was used to test the generalizability of the model. Model predictions were reviewed by an expert to confirm or reject the findings.

RESULTS

The proposed machine learning multiple features (ML-MF) approach outperformed traditional nonmachine-learning-based approaches that are based on only one or two geometric agreement metrics. The machine learning model achieved recall (precision) values of 0.842 (0.899), 0.762 (0.762), 0.727 (0.842), and 0.773 (0.773) for Brainstem, Parotid_L, Parotid_R, and mandible contours, respectively compared to 0.526 (0.909), 0.619 (0.765), 0.682 (0.882), 0.773 (0.568) for an approach based solely on Dice similarity coefficient values. In the external validation dataset, 66.7, 93.3, 94.1, and 58.8% of flagged cases were confirmed to have contouring errors by an expert for Brainstem, Parotid_L, Parotid_R, and mandible contours, respectively.

CONCLUSIONS

The proposed ML-MF approach, which includes multiple geometric agreement metrics to flag manual contouring errors, demonstrated superior performance in comparison to traditional methods. This method is easy to implement in clinical practice and can help to reduce the significant time and labor costs associated with manual segmentation and review.

A Survey of Convolutional Neural Network in Breast Cancer

Problems

For people all over the world, cancer is one of the most feared diseases. Cancer is one of the major obstacles to improving life expectancy in countries around the world and one of the biggest causes of death before the age of 70 in 112 countries. Among all kinds of cancers, breast cancer is the most common cancer for women. The data showed that female breast cancer had become one of the most common cancers.

Aims

A large number of clinical trials have proved that if breast cancer is diagnosed at an early stage, it could give patients more treatment options and improve the treatment effect and survival ability. Based on this situation, there are many diagnostic methods for breast cancer, such as computer-aided diagnosis (CAD).

Methods

We complete a comprehensive review of the diagnosis of breast cancer based on the convolutional neural network (CNN) after reviewing a sea of recent papers. Firstly, we introduce several different imaging modalities. The structure of CNN is given in the second part. After that, we introduce some public breast cancer data sets. Then, we divide the diagnosis of breast cancer into three different tasks: 1. classification; 2. detection; 3. segmentation.

Conclusion

Although this diagnosis with CNN has achieved great success, there are still some limitations. (i) There are too few good data sets. A good public breast cancer dataset needs to involve many aspects, such as professional medical knowledge, privacy issues, financial issues, dataset size, and so on. (ii) When the data set is too large, the CNN-based model needs a sea of computation and time to complete the diagnosis. (iii) It is easy to cause overfitting when using small data sets.

Application of MRI-Based Radiomics in Preoperative Prediction of NF2 Alteration in Intracranial Meningiomas

Purpose

This study aimed to investigate the feasibility of predicting NF2 mutation status based on the MR radiomic analysis in patients with intracranial meningioma.

Methods

This retrospective study included 105 patients with meningiomas, including 60 NF2-mutant samples and 45 wild-type samples. Radiomic features were extracted from magnetic resonance imaging scans, including T1-weighted, T2-weighted, and contrast T1-weighted images. Student’s t-test and LASSO regression were performed to select the radiomic features. All patients were randomly divided into training and validation cohorts in a 7:3 ratio. Five linear models (RF, SVM, LR, KNN, and xgboost) were trained to predict the NF2 mutational status. Receiver operating characteristic curve and precision-recall analyses were used to evaluate the model performance. Student’s t-tests were then used to compare the posterior probabilities of NF2 mut/loss prediction for patients with different NF2 statuses.

Results

Nine features had nonzero coefficients in the LASSO regression model. No significant differences was observed in the clinical features. Nine features showed significant differences in patients with different NF2 statuses. Among all machine learning algorithms, SVM showed the best performance. The area under curve and accuracy of the predictive model were 0.85; the F1-score of the precision-recall curve was 0.80. The model risk was assessed by plotting calibration curves. The p-value for the H-L goodness of fit test was 0.411 (p&gt; 0.05), which indicated that the difference between the obtained model and the perfect model was statistically insignificant. The AUC of our model in external validation was 0.83.

Conclusion

A combination of radiomic analysis and machine learning showed potential clinical utility in the prediction of preoperative NF2 status. These findings could aid in developing customized neurosurgery plans and meningioma management strategies before postoperative pathology.

Quality assurance for automatically generated contours with additional deep learning

OBJECTIVE

Deploying an automatic segmentation model in practice should require rigorous quality assurance (QA) and continuous monitoring of the model's use and performance, particularly in high-stakes scenarios such as healthcare. Currently, however, tools to assist with QA for such models are not available to AI researchers. In this work, we build a deep learning model that estimates the quality of automatically generated contours.

METHODS

The model was trained to predict the segmentation quality by outputting an estimate of the Dice similarity coefficient given an image contour pair as input. Our dataset contained 60 axial T2-weighted MRI images of prostates with ground truth segmentations along with 80 automatically generated segmentation masks. The model we used was a 3D version of the EfficientDet architecture with a custom regression head. For validation, we used a fivefold cross-validation. To counteract the limitation of the small dataset, we used an extensive data augmentation scheme capable of producing virtually infinite training samples from a single ground truth label mask. In addition, we compared the results against a baseline model that only uses clinical variables for its predictions.

RESULTS

Our model achieved a mean absolute error of 0.020 ± 0.026 (2.2% mean percentage error) in estimating the Dice score, with a rank correlation of 0.42. Furthermore, the model managed to correctly identify incorrect segmentations (defined in terms of acceptable/unacceptable) 99.6% of the time.

CONCLUSION

We believe that the trained model can be used alongside automatic segmentation tools to ensure quality and thus allow intervention to prevent undesired segmentation behavior.

Deep learning-based automatic segmentation for size and volumetric measurement of breast cancer on magnetic resonance imaging

Purpose

In clinical work, accurately measuring the volume and the size of breast cancer is significant to develop a treatment plan. However, it is time-consuming, and inter- and intra-observer variations among radiologists exist. The purpose of this study was to assess the performance of a Res-UNet convolutional neural network based on automatic segmentation for size and volumetric measurement of mass enhancement breast cancer on magnetic resonance imaging (MRI).

Materials and methods

A total of 1,000 female breast cancer patients who underwent preoperative 1.5-T dynamic contrast-enhanced MRI prior to treatment were selected from January 2015 to October 2021 and randomly divided into a training cohort (n = 800) and a testing cohort (n = 200). Compared with the masks named ground truth delineated manually by radiologists, the model performance on segmentation was evaluated with dice similarity coefficient (DSC) and intraclass correlation coefficient (ICC). The performance of tumor (T) stage classification was evaluated with accuracy, sensitivity, and specificity.

Results

In the test cohort, the DSC of automatic segmentation reached 0.89. Excellent concordance (ICC > 0.95) of the maximal and minimal diameter and good concordance (ICC > 0.80) of volumetric measurement were shown between the model and the radiologists. The trained model took approximately 10–15 s to provide automatic segmentation and classified the T stage with an overall accuracy of 0.93, sensitivity of 0.94, 0.94, and 0.75, and specificity of 0.95, 0.92, and 0.99, respectively, in T1, T2, and T3.

Conclusions

Our model demonstrated good performance and reliability for automatic segmentation for size and volumetric measurement of breast cancer, which can be time-saving and effective in clinical decision-making.

Explaining the dosimetric impact of contouring errors in head and neck radiotherapy

Objective. Auto-contouring of organs at risk (OAR) is becoming more common in radiotherapy. An important issue in clinical decision making is judging the quality of the auto-contours. While recent studies considered contour quality by looking at geometric errors only, this does not capture the dosimetric impact of the errors. In this work, we studied the relationship between geometrical errors, the local dose and the dosimetric impact of the geometrical errors.Approach. For 94 head and neck patients, unmodified atlas-based auto-contours and clinically used delineations of the parotid glands and brainstem were retrieved. VMAT plans were automatically optimized on the auto-contours and evaluated on both contours. We defined the dosimetric impact on evaluation (DIE) as the difference in the dosimetric parameter of interest between the two contours. We developed three linear regression models to predict the DIE using: (1) global geometric metrics, (2) global dosimetric metrics, (3) combined local geometric and dosimetric metrics. For model (3), we next determined the minimal amount of editing information required to produce a reliable prediction. Performance was assessed by the root mean squared error (RMSE) of the predicted DIE using 5-fold cross-validation.Main results. In model (3), the median RMSE of the left parotid was 0.4 Gy using 5% of the largest editing vectors. For the right parotid and brainstem the results were 0.5 Gy using 10% and 0.4 Gy using 1% respectively. The median RMS of the DIE was 0.6 Gy, 0.7 Gy and 0.9 Gy for the left parotid, the right parotid and the brainstem, respectively. Model (3), combining local dosimetric and geometric quantities, outperformed the models that used only geometric or dosimetric information.Significance. We showed that the largest local errors plus the local dose suffice to accurately predict the dosimetric impact, opening the door to automated dosimetric QA of auto-contours.

Machine learning-based detection of aberrant deep learning segmentations of target and organs at risk for prostate radiotherapy using a secondary segmentation algorithm

Objective.The output of a deep learning (DL) auto-segmentation application should be reviewed, corrected if needed and approved before being used clinically. This verification procedure is labour-intensive, time-consuming and user-dependent, which potentially leads to significant errors with impact on the overall treatment quality. Additionally, when the time needed to correct auto-segmentations approaches the time to delineate target and organs at risk from scratch, the usability of the DL model can be questioned. Therefore, an automated quality assurance framework was developed with the aim to detect in advance aberrant auto-segmentations.Approach. Five organs (prostate, bladder, anorectum, femoral head left and right) were auto-delineated on CT acquisitions for 48 prostate patients by an in-house trained primary DL model. An experienced radiation oncologist assessed the correctness of the model output and categorised the auto-segmentations into two classes whether minor or major adaptations were needed. Subsequently, an independent, secondary DL model was implemented to delineate the same structures as the primary model. Quantitative comparison metrics were calculated using both models' segmentations and used as input features for a machine learning classification model to predict the output quality of the primary model.Main results. For every organ, the approach of independent validation by the secondary model was able to detect primary auto-segmentations that needed major adaptation with high sensitivity (recall = 1) based on the calculated quantitative metrics. The surface DSC and APL were found to be the most indicated parameters in comparison to standard quantitative metrics for the time needed to adapt auto-segmentations.Significance. This proposed method includes a proof of concept for the use of an independent DL segmentation model in combination with a ML classifier to improve time saving during QA of auto-segmentations. The integration of such system into current automatic segmentation pipelines can increase the efficiency of the radiotherapy contouring workflow.

Extrathyroidal Extension Prediction of Papillary Thyroid Cancer With Computed Tomography Based Radiomics Nomogram: A Multicenter Study

OBJECTIVES

To develop and validate a Computed Tomography (CT) based radiomics nomogram for preoperative predicting of extrathyroidal extension (ETE) in papillary thyroid cancer (PTC) patients.

METHODS

A total of 153 patients were randomly assigned to training and internal test sets (7:3). 46 patients were recruited to serve as an external test set. A radiologist with 8 years of experience segmented the images. Radiomics features were extracted from each image and Delta-radiomics features were calculated. Features were selected by using one way analysis of variance and the least absolute shrinkage and selection operator in the training set. K-nearest neighbor, logistic regression, decision tree, linear-support vector machine (linear -SVM), gaussian-SVM, and polynomial-SVM were used to build 6 radiomics models. Next, a radiomics signature score (Rad-score) was constructed by using the linear combination of selected features weighted by their corresponding coefficients. Finally, a nomogram was constructed combining the clinical risk factors with Rad-scores. Receiver operating characteristic (ROC) curve, decision curve analysis (DCA), and calibration curve were performed on the three sets to evaluate the nomogram's performance.

RESULTS

4 radiomics features were selected. The six models showed the certain value of radiomics, with area under the curves (AUCs) from 0.642 to 0.701. The nomogram combining the Rad-score and clinical risk factors (radiologists' interpretation) showed good performance (internal test set: AUC 0.750; external test set: AUC 0.797). Calibration curve and DCA demonstrated good performance of the nomogram.

CONCLUSION

Our radiomics nomogram incorporating the radiomics and radiologists' interpretation has utility in the identification of ETE in PTC patients.

Implementation of web-based open-source radiotherapy delineation software (WORDS) in organs at risk contouring training for newly qualified radiotherapists: quantitative comparison with conventional one-to-one coaching approach

BACKGROUND

Due to the role expansion of radiotherapists in dosimetric aspect, radiotherapists have taken up organs at risk (OARs) contouring work in many clinical settings. However, training of newly qualified radiotherapists in OARs contouring can be time consuming, it may also cause extra burden to experienced radiotherapists. As web-based open-source radiotherapy delineation software (WORDS) has become more readily available, it has provided a free and interactive alternative to conventional one-to-one coaching approach during OARs contouring training. The present study aims to evaluate the effectiveness of WORDS in training OARs contouring skills of newly qualified radiotherapists, compared to those trained by conventional one-to-one coaching approach.

METHODS

Nine newly qualified radiotherapists (licensed in 2017 - 2018) were enrolled to the conventional one-to-one coaching group (control group), while 11 newly qualified radiotherapists (licensed in 2019 - 2021) were assigned to WORDS training group (measured group). Ten OARs were selected to be contoured in this 3-phases quantitative study. Participants were required to undergo phase 1 OARs contouring in the beginning of the training session. Afterwards, conventional one-to-one training or WORDS training session was provided to participants according to their assigned group. Then the participants did phase 2 and 3 OARs contouring which were separated 1 week apart. Phase 1 - 3 OARs contouring aimed to demonstrate participants' pre-training OARs contouring ability, post-training OARs contouring ability and knowledge retention after one-week interval respectively using either training approach. To prevent bias, the computed tomography dataset for OARs contouring in each phase were different. Variations in the contouring scores for the selected OARs were evaluated between 3 phases using Kruskal-Wallis tests with Dunn tests for pairwise comparisons. Variations in the contouring scores between control and measured group in phase 1 - 3 contouring were analyzed using Wilcoxon signed-rank test. A p-value < 0.05 was considered to be statistically significant.

RESULTS

In both control group and measured group, significant improvement (p < 0.05) in phase 2 and 3 contouring scores have been observed comparing to phase 1 contouring scores. In comparison of contouring scores between control group and measured group, no significant differences (p > 0.05) were observed in all OARs between both groups.

CONCLUSIONS

The results in this study have demonstrated that the outcome of OARs contouring training using WORDS is comparable to the conventional training approach. In addition, WORDS can offer flexibility to newly qualified radiotherapists to practice OARs contouring at will, as well as reduce staff training burden of experienced radiotherapists.

Automatic radiotherapy delineation quality assurance on prostate MRI with deep learning in a multicentre clinical trial

Volume delineation quality assurance (QA) is particularly important in clinical trial settings where consistent protocol implementation is required, as outcomes will affect future as well current patients. Currently, where feasible, this is conducted manually, which is time consuming and resource intensive. Although previous studies mostly focused on automating delineation QA on CT, magnetic resonance imaging (MRI) is being increasingly used in radiotherapy treatment. In this work, we propose to perform automatic delineation QA on prostate MRI for both the clinical target volume (CTV) and organs-at-risk (OARs) by using delineations generated by 3D Unet variants as benchmarks for QA. These networks were trained on a small gold standard atlas set and applied on a multicentre radiotherapy clinical trial dataset to generate benchmark delineations. Then, a QA stage was designed to recommend 'pass', 'minor correction' and 'major correction' for each manual delineation in the trial set by thresholding its Dice similarity coefficient to the network generated delineation. Among all 3D Unet variants explored, the Unet with anatomical gates in an AtlasNet architecture performed the best in delineation QA, achieving an area under the receiver operating characteristics curve of 0.97, 0.92, 0.89 and 0.97 for identifying unacceptable (major correction) delineations with a sensitivity of 0.93, 0.73, 0.74 and 0.90 at a specificity of 0.93, 0.86, 0.86 and 0.95 for bladder, prostate CTV, rectum and gel spacer respectively. To the best of our knowledge, this is the first study to propose automated delineation QA for a multicentre radiotherapy clinical trial with treatment planning MRI. The methods proposed in this work can potentially improve the accuracy and consistency of CTV and OAR delineation in radiotherapy treatment planning.

Clinical implementation of deep-learning based auto-contouring tools-Experience of three French radiotherapy centers

Deep-learning (DL)-based auto-contouring solutions have recently been proposed as a convincing alternative to decrease workload of target volumes and organs-at-risk (OAR) delineation in radiotherapy planning and improve inter-observer consistency. However, there is minimal literature of clinical implementations of such algorithms in a clinical routine. In this paper we first present an update of the state-of-the-art of DL-based solutions. We then summarize recent recommendations proposed by the European society for radiotherapy and oncology (ESTRO) to be followed before any clinical implementation of artificial intelligence-based solutions in clinic. The last section describes the methodology carried out by three French radiation oncology departments to deploy CE-marked commercial solutions. Based on the information collected, a majority of OAR are retained by the centers among those proposed by the manufacturers, validating the usefulness of DL-based models to decrease clinicians' workload. Target volumes, with the exception of lymph node areas in breast, head and neck and pelvic regions, whole breast, breast wall, prostate and seminal vesicles, are not available in the three commercial solutions at this time. No implemented workflows are currently available to continuously improve the models, but these can be adapted/retrained in some solutions during the commissioning phase to best fit local practices. In reported experiences, automatic workflows were implemented to limit human interactions and make the workflow more fluid. Recommendations published by the ESTRO group will be of importance for guiding physicists in the clinical implementation of patient specific and regular quality assurances.

Investigating the potential of deep learning for patient-specific quality assurance of salivary gland contours using EORTC-1219-DAHANCA-29 clinical trial data

INTRODUCTION

Manual quality assurance (QA) of radiotherapy contours for clinical trials is time and labor intensive and subject to inter-observer variability. Therefore, we investigated whether deep-learning (DL) can provide an automated solution to salivary gland contour QA.

MATERIAL AND METHODS

DL-models were trained to generate contours for parotid (PG) and submandibular glands (SMG). Sørensen-Dice coefficient (SDC) and Hausdorff distance (HD) were used to assess agreement between DL and clinical contours and thresholds were defined to highlight cases as potentially sub-optimal. 3 types of deliberate errors (expansion, contraction and displacement) were gradually applied to a test set, to confirm that SDC and HD were suitable QA metrics. DL-based QA was performed on 62 patients from the EORTC-1219-DAHANCA-29 trial. All highlighted contours were visually inspected.

RESULTS

Increasing the magnitude of all 3 types of errors resulted in progressively severe deterioration/increase in average SDC/HD. 19/124 clinical PG contours were highlighted as potentially sub-optimal, of which 5 (26%) were actually deemed clinically sub-optimal. 2/19 non-highlighted contours were false negatives (11%). 15/69 clinical SMG contours were highlighted, with 7 (47%) deemed clinically sub-optimal and 2/15 non-highlighted contours were false negatives (13%). For most incorrectly highlighted contours causes for low agreement could be identified.

CONCLUSION

Automated DL-based contour QA is feasible but some visual inspection remains essential. The substantial number of false positives were caused by sub-optimal performance of the DL-model. Improvements to the model will increase the extent of automation and reliability, facilitating the adoption of DL-based contour QA in clinical trials and routine practice.

Clinical feasibility of deep learning-based auto-segmentation of target volumes and organs-at-risk in breast cancer patients after breast-conserving surgery

Background

In breast cancer patients receiving radiotherapy (RT), accurate target delineation and reduction of radiation doses to the nearby normal organs is important. However, manual clinical target volume (CTV) and organs-at-risk (OARs) segmentation for treatment planning increases physicians’ workload and inter-physician variability considerably. In this study, we evaluated the potential benefits of deep learning-based auto-segmented contours by comparing them to manually delineated contours for breast cancer patients.

Methods

CTVs for bilateral breasts, regional lymph nodes, and OARs (including the heart, lungs, esophagus, spinal cord, and thyroid) were manually delineated on planning computed tomography scans of 111 breast cancer patients who received breast-conserving surgery. Subsequently, a two-stage convolutional neural network algorithm was used. Quantitative metrics, including the Dice similarity coefficient (DSC) and 95% Hausdorff distance, and qualitative scoring by two panels from 10 institutions were used for analysis. Inter-observer variability and delineation time were assessed; furthermore, dose-volume histograms and dosimetric parameters were also analyzed using another set of patient data.

Results

The correlation between the auto-segmented and manual contours was acceptable for OARs, with a mean DSC higher than 0.80 for all OARs. In addition, the CTVs showed favorable results, with mean DSCs higher than 0.70 for all breast and regional lymph node CTVs. Furthermore, qualitative subjective scoring showed that the results were acceptable for all CTVs and OARs, with a median score of at least 8 (possible range: 0–10) for (1) the differences between manual and auto-segmented contours and (2) the extent to which auto-segmentation would assist physicians in clinical practice. The differences in dosimetric parameters between the auto-segmented and manual contours were minimal.

Conclusions

The feasibility of deep learning-based auto-segmentation in breast RT planning was demonstrated. Although deep learning-based auto-segmentation cannot be a substitute for radiation oncologists, it is a useful tool with excellent potential in assisting radiation oncologists in the future.

Trial registration Retrospectively registered.

The Application of Deep Convolutional Neural Networks to Brain Cancer Images: A Survey

In recent years, improved deep learning techniques have been applied to biomedical image processing for the classification and segmentation of different tumors based on magnetic resonance imaging (MRI) and histopathological imaging (H&E) clinical information. Deep Convolutional Neural Networks (DCNNs) architectures include tens to hundreds of processing layers that can extract multiple levels of features in image-based data, which would be otherwise very difficult and time-consuming to be recognized and extracted by experts for classification of tumors into different tumor types, as well as segmentation of tumor images. This article summarizes the latest studies of deep learning techniques applied to three different kinds of brain cancer medical images (histology, magnetic resonance, and computed tomography) and highlights current challenges in the field for the broader applicability of DCNN in personalized brain cancer care by focusing on two main applications of DCNNs: classification and segmentation of brain cancer tumors images.