Tissue segmentation of head and neck CT images for treatment planning: a multiatlas approach combined with intensity modeling

Gaussian filter facilitated deep learning-based architecture for accurate and efficient liver tumor segmentation for radiation therapy

Purpose

Addressing the challenges of unclear tumor boundaries and the confusion between cysts and tumors in liver tumor segmentation, this study aims to develop an auto-segmentation method utilizing Gaussian filter with the nnUNet architecture to effectively distinguish between tumors and cysts, enhancing the accuracy of liver tumor auto-segmentation.

Methods

Firstly, 130 cases of liver tumorsegmentation challenge 2017 (LiTS2017) were used for training and validating nnU-Net-based auto-segmentation model. Then, 14 cases of 3D-IRCADb dataset and 25 liver cancer cases retrospectively collected in our hospital were used for testing. The dice similarity coefficient (DSC) was used to evaluate the accuracy of auto-segmentation model by comparing with manual contours.

Results

The nnU-Net achieved an average DSC value of 0.86 for validation set (20 LiTS cases) and 0.82 for public testing set (14 3D-IRCADb cases). For clinical testing set, the standalone nnU-Net model achieved an average DSC value of 0.75, which increased to 0.81 after post-processing with the Gaussian filter (P<0.05), demonstrating its effectiveness in mitigating the influence of liver cysts on liver tumor segmentation.

Conclusion

Experiments show that Gaussian filter is beneficial to improve the accuracy of liver tumor segmentation in clinic.

Deep learning based automatic segmentation of the Internal Pudendal Artery in definitive radiotherapy treatment planning of localized prostate cancer

Background and purpose

Radiation-induced erectile dysfunction (RiED) commonly affects prostate cancer patients, prompting clinical trials across institutions to explore dose-sparing to internal-pudendal-arteries (IPA) for preserving sexual potency. IPA, challenging to segment, isn't conventionally considered an organ-at-risk (OAR). This study proposes a deep learning (DL) auto-segmentation model for IPA, using Computed Tomography (CT) and Magnetic Resonance Imaging (MRI) or CT alone to accommodate varied clinical practices.

Materials and methods

A total of 86 patients with CT and MRI images and noisy IPA labels were recruited in this study. We split the data into 42/14/30 for model training, testing, and a clinical observer study, respectively. There were three major innovations in this model: 1) we designed an architecture with squeeze-and-excite blocks and modality attention for effective feature extraction and production of accurate segmentation, 2) a novel loss function was used for training the model effectively with noisy labels, and 3) modality dropout strategy was used for making the model capable of segmentation in the absence of MRI.

Results

Test dataset metrics were DSC 61.71 ± 7.7 %, ASD 2.5 ± .87 mm, and HD95 7.0 ± 2.3 mm. AI segmented contours showed dosimetric similarity to expert physician's contours. Observer study indicated higher scores for AI contours (mean = 3.7) compared to inexperienced physicians' contours (mean = 3.1). Inexperienced physicians improved scores to 3.7 when starting with AI contours.

Conclusion

The proposed model achieved good quality IPA contours to improve uniformity of segmentation and to facilitate introduction of standardized IPA segmentation into clinical trials and practice.

Factors associated with meniscus volume in knees free of degenerative features

OBJECTIVES

To explore factors that were associated with meniscus volume in knees free of radiographic osteoarthritis (OA) features and symptoms of OA.

METHODS

In the third Rotterdam Study cohort, clinical, radiographic, and magnetic resonance data were obtained at baseline (BL) and after 5 years of follow-up. Meniscus volumes and their change over time were calculated after semi-automatic segmentation on Magnetic Resonance Imaging. Knees with radiographic OA features (Kellgren and Lawrence>0) or clinical diagnosis of OA (American College of Rheumatology) at BL were excluded. Ten OA risk factors were adjusted in the multivariable analysis (generalized estimating equations), treating two knees within subjects as repeated measurements.

RESULTS

From 1065 knees (570 subjects), the average (standard deviation) age and Body mass index (BMI) of included subjects were 54.3 (3.7) years and 26.5 (4.4) kg/m2. At BL, nine factors (varus alignment, higher BMI, meniscus pathologies, meniscus extrusion, cartilage lesions, injury, greater physical activity level, quadriceps muscle strength, and higher age) were significantly associated with greater meniscus volume. Five factors (injury, meniscus pathologies, meniscus extrusion, higher age, and change of BMI) were significantly associated with meniscus volume loss.

CONCLUSIONS

Modifiable factors (varus alignment, BMI, physical activity level, and quadriceps muscle strength) and non-modifiable factors (higher age, injury, meniscus pathologies, meniscus extrusion, and cartilage lesions) were all associated with meniscus volume or meniscus volume loss over time.

A clinical evaluation of the performance of five commercial artificial intelligence contouring systems for radiotherapy

Purpose/objectives

Auto-segmentation with artificial intelligence (AI) offers an opportunity to reduce inter- and intra-observer variability in contouring, to improve the quality of contours, as well as to reduce the time taken to conduct this manual task. In this work we benchmark the AI auto-segmentation contours produced by five commercial vendors against a common dataset.

Methods and materials

The organ at risk (OAR) contours generated by five commercial AI auto-segmentation solutions (Mirada (Mir), MVision (MV), Radformation (Rad), RayStation (Ray) and TheraPanacea (Ther)) were compared to manually-drawn expert contours from 20 breast, 20 head and neck, 20 lung and 20 prostate patients. Comparisons were made using geometric similarity metrics including volumetric and surface Dice similarity coefficient (vDSC and sDSC), Hausdorff distance (HD) and Added Path Length (APL). To assess the time saved, the time taken to manually draw the expert contours, as well as the time to correct the AI contours, were recorded.

Results

There are differences in the number of CT contours offered by each AI auto-segmentation solution at the time of the study (Mir 99; MV 143; Rad 83; Ray 67; Ther 86), with all offering contours of some lymph node levels as well as OARs. Averaged across all structures, the median vDSCs were good for all systems and compared favorably with existing literature: Mir 0.82; MV 0.88; Rad 0.86; Ray 0.87; Ther 0.88. All systems offer substantial time savings, ranging between: breast 14-20 mins; head and neck 74-93 mins; lung 20-26 mins; prostate 35-42 mins. The time saved, averaged across all structures, was similar for all systems: Mir 39.8 mins; MV 43.6 mins; Rad 36.6 min; Ray 43.2 mins; Ther 45.2 mins.

Conclusions

All five commercial AI auto-segmentation solutions evaluated in this work offer high quality contours in significantly reduced time compared to manual contouring, and could be used to render the radiotherapy workflow more efficient and standardized.

Quantitative Assessment of COVID-19 Lung Disease Severity: A Segmentation-based Approach

We present the use of mean Hounsfield units within lungs as a metric of disease severity for the comparison of image analysis models in patients with COPD and COVID. We used this metric to assess the performance of a novel 3D global context attention network for image segmentation that produces lung masks from thoracic HRCT scans. Results showed that the mean Hounsfield units enable a detailed comparison of our 3D implementation of the GC-Net model to the V-Net segmentation algorithm. We implemented a biomimetic data augmentation strategy and used a quantitative severity metric to assess its performance. Framing our investigation around lung segmentation for patients with respiratory diseases allows analysis of the strengths and weaknesses of the implemented models in this context.Clinical Relevance - Mean Hounsfield units within the lung volume can be used as an objective measure of respiratory disease severity for the comparison of CT scan analysis algorithms.

OrbitNet-A fully automated orbit multi-organ segmentation model based on transformer in CT images

The delineation of orbital organs is a vital step in orbital diseases diagnosis and preoperative planning. However, an accurate multi-organ segmentation is still a clinical problem which suffers from two limitations. First, the contrast of soft tissue is relatively low. It usually cannot clearly show the boundaries of organs. Second, the optic nerve and the rectus muscle are difficult to distinguish because they are spatially adjacent and have similar geometry. To address these challenges, we propose the OrbitNet model to automatically segment orbital organs in CT images. Specifically, we present a global feature extraction module based on the transformer architecture called FocusTrans encoder, which enhance the ability to extract boundary features. To make the network focus on the extraction of edge features in the optic nerve and rectus muscle, the SA block is used to replace the convolution block in the decoding stage. In addition, we use the structural similarity measure (SSIM) loss as a part of the hybrid loss function to learn the edge differences of the organs better. OrbitNet has been trained and tested on the CT dataset collected by the Eye Hospital of Wenzhou Medical University. The experimental results show that our proposed model achieved superior results. The average Dice Similarity Coefficient (DSC) is 83.9%, the value of average 95% Hausdorff Distance (HD95) is 1.62 mm, and the value of average Symmetric Surface Distance (ASSD) is 0.47 mm. Our model also has good performance on the MICCAI 2015 challenge dataset.

Comparison of atlas-based and deep learning methods for organs at risk delineation on head-and-neck CT images using an automated treatment planning system

BACKGROUND AND PURPOSE

To investigate the performance of head-and-neck (HN) organs-at-risk (OAR) automatic segmentation (AS) using four atlas-based (ABAS) and two deep learning (DL) solutions.

MATERIAL AND METHODS

All patients underwent iodine contrast-enhanced planning CT. Fourteen OAR were manually delineated. DL.1 and DL.2 solutions were trained with 63 mono-centric patients and > 1000 multi-centric patients, respectively. Ten and 15 patients with varied anatomies were selected for the atlas library and for testing, respectively. The evaluation was based on geometric indices (DICE coefficient and 95th percentile-Hausdorff Distance (HD_95%)), time needed for manual corrections and clinical dosimetric endpoints obtained using automated treatment planning.

RESULTS

Both DICE and HD_95% results indicated that DL algorithms generally performed better compared with ABAS algorithms for automatic segmentation of HN OAR. However, the hybrid-ABAS (ABAS.3) algorithm sometimes provided the highest agreement to the reference contours compared with the 2 DL. Compared with DL.2 and ABAS.3, DL.1 contours were the fastest to correct. For the 3 solutions, the differences in dose distributions obtained using AS contours and AS + manually corrected contours were not statistically significant. High dose differences could be observed when OAR contours were at short distances to the targets. However, this was not always interrelated.

CONCLUSION

DL methods generally showed higher delineation accuracy compared with ABAS methods for AS segmentation of HN OAR. Most ABAS contours had high conformity to the reference but were more time consuming than DL algorithms, especially when considering the computing time and the time spent on manual corrections.

Active shape model registration of ocular structures in computed tomography images

Purpose. The goal of this work is to create an active shape model segmentation method based on the statistical shape model of five regions of the globe on computed tomography (CT) scans and to use the method to categorize normal globe from globe injury. Methods. A set of 78 normal globes imaged with CT scans were manually segmented (vitreous cavity, lens, sclera, anterior chamber, and cornea) by two graders. A statistical shape model was created from the regions. An active shape model was trained using the manual segmentations and the statistical shape model and was assessed using leave-one-out cross validations. The active shape model was then applied to a set of globes with open globe injures, and the segmentations were compared to those of normal globes, in terms of the standard deviations away from normal. Results. The active shape model (ASM) segmentation compared well to ground truth, based on Dice similarity coefficient score in a leave-one-out experiment: 90.2% ± 2.1% for the cornea, 92.5% ± 3.5% for the sclera, 87.4% ± 3.7% for the vitreous cavity, 83.5% ± 2.3% for the anterior chamber, and 91.2% ± 2.4% for the lens. A preliminary set of CT scans of patients with open globe injury were segmented using the ASM and the shape of each region was quantified. The sclera and vitreous cavity were statistically different in shape from the normal. The Zone 1 and Zone 2 globes were statistically different than normal from the cornea and anterior chamber. Both results are consistent with the definition of the zonal injuries in OGI. Conclusion. The ASM results were found to be reproducible and accurately correlated with manual segmentations. The quantitative metrics derived from ASM of globes with OGI are consistent with existing medical knowledge in terms of structural deformation.

3D Lightweight Network for Simultaneous Registration and Segmentation of Organs-at-Risk in CT Images of Head and Neck Cancer

Image-guided radiation therapy (IGRT) is the most effective treatment for head and neck cancer. The successful implementation of IGRT requires accurate delineation of organ-at-risk (OAR) in the computed tomography (CT) images. In routine clinical practice, OARs are manually segmented by oncologists, which is time-consuming, laborious, and subjective. To assist oncologists in OAR contouring, we proposed a three-dimensional (3D) lightweight framework for simultaneous OAR registration and segmentation. The registration network was designed to align a selected OAR template to a new image volume for OAR localization. A region of interest (ROI) selection layer then generated ROIs of OARs from the registration results, which were fed into a multiview segmentation network for accurate OAR segmentation. To improve the performance of registration and segmentation networks, a centre distance loss was designed for the registration network, an ROI classification branch was employed for the segmentation network, and further, context information was incorporated to iteratively promote both networks' performance. The segmentation results were further refined with shape information for final delineation. We evaluated registration and segmentation performances of the proposed framework using three datasets. On the internal dataset, the Dice similarity coefficient (DSC) of registration and segmentation was 69.7% and 79.6%, respectively. In addition, our framework was evaluated on two external datasets and gained satisfactory performance. These results showed that the 3D lightweight framework achieved fast, accurate and robust registration and segmentation of OARs in head and neck cancer. The proposed framework has the potential of assisting oncologists in OAR delineation.

Stepwise deep neural network (stepwise-net) for head and neck auto-segmentation on CT images

OBJECTIVE

The current study aims to propose the auto-segmentation model on CT images of head and neck cancer using a stepwise deep neural network (stepwise-net).

MATERIAL AND METHODS

Six normal tissue structures in the head and neck region of 3D CT images: Brainstem, optic nerve, parotid glands (left and right), and submandibular glands (left and right) were segmented with deep learning. In addition to a conventional convolutional neural network (CNN) on U-net, a stepwise neural network (stepwise-network) was developed. The stepwise-network was based on 3D FCN. We designed two networks in the stepwise-network. One is identifying the target region for the segmentation with the low-resolution images. Then, the target region is cropped, which used for the input image for the prediction of the segmentation. These were compared with a clinical used atlas-based segmentation.

RESULTS

The DSCs of the stepwise-net was significantly higher than the atlas-based method for all organ at risk structures. Similarly, the JSCs of the stepwise-net was significantly higher than the atlas-based methods for all organ at risk structures. The Hausdorff distance (HD) was significantly smaller than the atlas-based method for all organ at-risk structures. For the comparison of the stepwise-net and U-net, the stepwise-net had a higher DSC and JSC and a smaller HD than the conventional U-net.

CONCLUSIONS

We found that the stepwise-network plays a role is superior to conventional U-net-based and atlas-based segmentation. Our proposed model that is a potentially valuable method for improving the efficiency of head and neck radiotherapy treatment planning.

Prospectively-validated deep learning model for segmenting swallowing and chewing structures in CT

Objective.Delineating swallowing and chewing structures aids in radiotherapy (RT) treatment planning to limit dysphagia, trismus, and speech dysfunction. We aim to develop an accurate and efficient method to automate this process.Approach.CT scans of 242 head and neck (H&N) cancer patients acquired from 2004 to 2009 at our institution were used to develop auto-segmentation models for the masseters, medial pterygoids, larynx, and pharyngeal constrictor muscle using DeepLabV3+. A cascaded framework was used, wherein models were trained sequentially to spatially constrain each structure group based on prior segmentations. Additionally, an ensemble of models, combining contextual information from axial, coronal, and sagittal views was used to improve segmentation accuracy. Prospective evaluation was conducted by measuring the amount of manual editing required in 91 H&N CT scans acquired February-May 2021.Main results. Medians and inter-quartile ranges of Dice similarity coefficients (DSC) computed on the retrospective testing set (N = 24) were 0.87 (0.85-0.89) for the masseters, 0.80 (0.79-0.81) for the medial pterygoids, 0.81 (0.79-0.84) for the larynx, and 0.69 (0.67-0.71) for the constrictor. Auto-segmentations, when compared to two sets of manual segmentations in 10 randomly selected scans, showed better agreement (DSC) with each observer than inter-observer DSC. Prospective analysis showed most manual modifications needed for clinical use were minor, suggesting auto-contouring could increase clinical efficiency. Trained segmentation models are available for research use upon request viahttps://github.com/cerr/CERR/wiki/Auto-Segmentation-models.Significance.We developed deep learning-based auto-segmentation models for swallowing and chewing structures in CT and demonstrated its potential for use in treatment planning to limit complications post-RT. To the best of our knowledge, this is the only prospectively-validated deep learning-based model for segmenting chewing and swallowing structures in CT. Segmentation models have been made open-source to facilitate reproducibility and multi-institutional research.

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.

Automatic segmentation of organs at risk and tumors in CT images of lung cancer from partially labelled datasets with a semi-supervised conditional nnU-Net

BACKGROUND AND OBJECTIVE

Accurately and reliably defining organs at risk (OARs) and tumors are the cornerstone of radiation therapy (RT) treatment planning for lung cancer. Almost all segmentation networks based on deep learning techniques rely on fully annotated data with strong supervision. However, existing public imaging datasets encountered in the RT domain frequently include singly labelled tumors or partially labelled organs because annotating full OARs and tumors in CT images is both rigorous and tedious. To utilize labelled data from different sources, we proposed a dual-path semi-supervised conditional nnU-Net for OARs and tumor segmentation that is trained on a union of partially labelled datasets.

METHODS

The framework employs the nnU-Net as the base model and introduces a conditioning strategy by incorporating auxiliary information as an additional input layer into the decoder. The conditional nnU-Net efficiently leverages prior conditional information to classify the target class at the pixelwise level. Specifically, we employ the uncertainty-aware mean teacher (UA-MT) framework to assist in OARs segmentation, which can effectively leverage unlabelled data (images from a tumor labelled dataset) by encouraging consistent predictions of the same input under different perturbations. Furthermore, we individually design different combinations of loss functions to optimize the segmentation of OARs (Dice loss and cross-entropy loss) and tumors (Dice loss and focal loss) in a dual path.

RESULTS

The proposed method is evaluated on two publicly available datasets of the spinal cord, left and right lung, heart, esophagus, and lung tumor, in which satisfactory segmentation performance has been achieved in term of both the region-based Dice similarity coefficient (DSC) and the boundary-based Hausdorff distance (HD).

CONCLUSIONS

The proposed semi-supervised conditional nnU-Net breaks down the barriers between nonoverlapping labelled datasets and further alleviates the problem of "data hunger" and "data waste" in multi-class segmentation. The method has the potential to help radiologists with RT treatment planning in clinical practice.

Weaving attention U-net: A novel hybrid CNN and attention-based method for organs-at-risk segmentation in head and neck CT images

PURPOSE

In radiotherapy planning, manual contouring is labor-intensive and time-consuming. Accurate and robust automated segmentation models improve the efficiency and treatment outcome. We aim to develop a novel hybrid deep learning approach, combining convolutional neural networks (CNNs) and the self-attention mechanism, for rapid and accurate multi-organ segmentation on head and neck computed tomography (CT) images.

METHODS

Head and neck CT images with manual contours of 115 patients were retrospectively collected and used. We set the training/validation/testing ratio to 81/9/25 and used the 10-fold cross-validation strategy to select the best model parameters. The proposed hybrid model segmented 10 organs-at-risk (OARs) altogether for each case. The performance of the model was evaluated by three metrics, that is, the Dice Similarity Coefficient (DSC), Hausdorff distance 95% (HD95), and mean surface distance (MSD). We also tested the performance of the model on the head and neck 2015 challenge dataset and compared it against several state-of-the-art automated segmentation algorithms.

RESULTS

The proposed method generated contours that closely resemble the ground truth for 10 OARs. On the head and neck 2015 challenge dataset, the DSC scores of these OARs were 0.91 ± 0.02, 0.73 ± 0.10, 0.95 ± 0.03, 0.76 ± 0.08, 0.79 ± 0.05, 0.87 ± 0.05, 0.86 ± 0.08, 0.87 ± 0.03, and 0.87 ± 0.07 for brain stem, chiasm, mandible, left/right optic nerve, left/right submandibular, and left/right parotid, respectively. Our results of the new weaving attention U-net (WAU-net) demonstrate superior or similar performance on the segmentation of head and neck CT images.

CONCLUSIONS

We developed a deep learning approach that integrates the merits of CNNs and the self-attention mechanism. The proposed WAU-net can efficiently capture local and global dependencies and achieves state-of-the-art performance on the head and neck multi-organ segmentation task.

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.

Are changes in meniscus volume and extrusion associated to knee osteoarthritis development? A structural equation model

OBJECTIVE

To explore the interplay between (changes in) medial meniscus volume, meniscus extrusion and radiographic knee osteoarthritis (OA) development over 30 months follow-up (FU).

METHODS

Data from the PRevention of knee Osteoarthritis in Overweight Females study were used. This cohort included 407 middle-aged women with a body mass index ≥27 kg/m², who were free of knee OA at baseline. Demographics were collected by questionnaires at baseline. All menisci at both baseline and FU were automatically segmented from MRI scans to obtain the meniscus volume and the change over time (delta volume). Baseline and FU meniscus body extrusion was quantitatively measured on mid-coronal proton density MR images. A structural equation model was created to assess the interplay between both medial meniscus volume and central extrusion at baseline, delta volume, delta extrusion, and incident radiographic knee OA at FU.

RESULTS

The structural equation modeling yielded a fair to good fit of the data. The direct effects of both medial meniscus volume and extrusion at baseline on incident OA were statistically significant (Estimate = 0.124, p = 0.029, and Estimate = 0.194, p < 0.001, respectively). Additional indirect effects on incident radiographic OA through delta meniscus volume or delta meniscus extrusion were not statistically significant.

CONCLUSION

Baseline medial meniscus volume and extrusion were associated to incidence of radiographic knee OA at FU in middle-aged overweight and obese women, while their changes were not involved in these effects. To prevent knee OA, interventions might need to target the onset of meniscal pathologies rather than their progression.

Comparison of atlas-based auto-segmentation accuracy for radiotherapy in prostate cancer

•

Auto-contouring accuracy and contouring time were evaluated using two procedures.

•

Dice coefficient was better for the multiple atlases procedure than for one atlas.

•

Contouring time of the multiple atlases procedure is clinically acceptable.

Atlas-based auto-segmentation (ABS) procedure used in radiotherapy can be classified into two groups, one using one atlas per patient (sSM) and the other using multiple atlases (sMM). This study evaluated auto-contouring accuracy and contouring time in patients with prostate cancer using the two procedures. The Dice similarity coefficient of sMM was significantly better than that of sSM (prostate [median, 0.81 (range, 0.66–0.91) vs. 0.64 (0.27–0.71), p < 0.01], seminal vesicles [0.49 (0.31–0.80) vs. 0.18 (0.01–0.60), p < 0.05], and rectum [0.81 (0.37–0.91) vs. 0.57 (0.31–0.77), p < 0.01]). The median contouring times were 2.6 (sMM) and 1.3 min (sSM).

Clinically Applicable Segmentation of Head and Neck Anatomy for Radiotherapy: Deep Learning Algorithm Development and Validation Study

BACKGROUND

Over half a million individuals are diagnosed with head and neck cancer each year globally. Radiotherapy is an important curative treatment for this disease, but it requires manual time to delineate radiosensitive organs at risk. This planning process can delay treatment while also introducing interoperator variability, resulting in downstream radiation dose differences. Although auto-segmentation algorithms offer a potentially time-saving solution, the challenges in defining, quantifying, and achieving expert performance remain.

OBJECTIVE

Adopting a deep learning approach, we aim to demonstrate a 3D U-Net architecture that achieves expert-level performance in delineating 21 distinct head and neck organs at risk commonly segmented in clinical practice.

METHODS

The model was trained on a data set of 663 deidentified computed tomography scans acquired in routine clinical practice and with both segmentations taken from clinical practice and segmentations created by experienced radiographers as part of this research, all in accordance with consensus organ at risk definitions.

RESULTS

We demonstrated the model's clinical applicability by assessing its performance on a test set of 21 computed tomography scans from clinical practice, each with 21 organs at risk segmented by 2 independent experts. We also introduced surface Dice similarity coefficient, a new metric for the comparison of organ delineation, to quantify the deviation between organ at risk surface contours rather than volumes, better reflecting the clinical task of correcting errors in automated organ segmentations. The model's generalizability was then demonstrated on 2 distinct open-source data sets, reflecting different centers and countries to model training.

CONCLUSIONS

Deep learning is an effective and clinically applicable technique for the segmentation of the head and neck anatomy for radiotherapy. With appropriate validation studies and regulatory approvals, this system could improve the efficiency, consistency, and safety of radiotherapy pathways.

Association between meniscal volume and development of knee osteoarthritis

OBJECTIVE

To assess the association between meniscal volume, its change over time and the development of knee OA after 30 months in overweight/obese women.

METHODS

Data from the PRevention of knee Osteoarthritis in Overweight Females study were used. This cohort included 407 women with a BMI ≥ 27 kg/m2, free of OA-related symptoms. The primary outcome measure was incident OA after 30 months, defined by one out of the following criteria: medial or lateral joint space narrowing (JSN)  ≥ 1.0 mm, incident radiographic OA [Kellgren and Lawrence (K&L)  ≥ 2], or incident clinical OA. The secondary outcomes were either of these items separately. Menisci at both baseline and follow-up were automatically segmented to obtain meniscal volume and delta-volumes. Generalized estimating equations were used to evaluate associations between the volume measures and the outcomes.

RESULTS

Medial and lateral baseline and delta-volumes were not significantly associated to the primary outcome. Lateral meniscal baseline volume was significantly associated to lateral JSN [odds ratio (OR) = 0.87; 95% CI: 0.75, 0.99], while other measures were not. Medial and lateral baseline volume were positively associated to K&L incidence (OR = 1.32 and 1.22; 95% CI: 1.15, 1.50 and 1.03, 1.45, respectively), while medial and lateral delta-volume were negatively associated to K&L incidence (OR = 0.998 and 0.997; 95% CI: 0.997, 1.000 and 0.996, 0.999, respectively). None of the meniscal measures were significantly associated to incident clinical OA.

CONCLUSION

Larger baseline meniscal volume and the decrease of meniscal volume over time were associated to the development of structural OA after 30 months in overweight and obese women.

Standardization of patient modeling in hyperthermia simulation studies: introducing the Erasmus Virtual Patient Repository

Purpose: Thermal dose-effect relations have demonstrated that clinical effectiveness of hyperthermia would benefit from more controlled heating of the tumor. Hyperthermia treatment planning (HTP) is a potent tool to study strategies enabling target conformal heating, but its accuracy is affected by patient modeling approximations. Homogeneous phantoms models are being used that do not match the body shape of patients in treatment position and often have unrealistic target volumes. As a consequence, simulation accuracy is affected, and performance comparisons are difficult. The aim of this study is to provide the first step toward standardization of HTP simulation studies in terms of patient modeling by introducing the Erasmus Virtual Patient Repository (EVPR): a virtual patient model database.Methods: Four patients with a tumor in the head and neck or the pelvis region were selected, and corresponding models were created using a clinical segmentation procedure. Using the Erasmus University Medical Center standard procedure, HTP was applied to these models and compared to HTP for commonly used surrogate models.Results: Although this study was aimed at presenting the EVPR database, our study illustrates that there is a non-negligible difference in the predicted SAR patterns between patient models and homogeneous phantom-based surrogate models. We further demonstrate the difference between actual and simplified target volumes being used today.Conclusion: Our study describes the EVPR for the research community as a first step toward standardization of hyperthermia simulation studies.

A Preliminary Experience of Implementing Deep-Learning Based Auto-Segmentation in Head and Neck Cancer: A Study on Real-World Clinical Cases

Purpose

While artificial intelligence has shown great promise in organs-at-risk (OARs) auto segmentation for head and neck cancer (HNC) radiotherapy, to reach the level of clinical acceptance of this technology in real-world routine practice is still a challenge. The purpose of this study was to validate a U-net-based full convolutional neural network (CNN) for the automatic delineation of OARs of HNC, focusing on clinical implementation and evaluation.

Methods

In the first phase, the CNN was trained on 364 clinical HNC patients’ CT images with annotated contouring from routine clinical cases by different oncologists. The automated delineation accuracy was quantified using the Dice similarity coefficient (DSC) and 95% Hausdorff distance (HD). To assess efficiency, the time required to edit the auto-contours to a clinically acceptable standard was evaluated by a questionnaire. For subjective evaluation, expert oncologists (more than 10 years’ experience) were randomly presented with automated delineations or manual contours of 15 OARs for 30 patient cases. In the second phase, the network was retrained with an additional 300 patients, which were generated by pre-trained CNN and edited by oncologists until to meet clinical acceptance.

Results

Based on DSC, the CNN performed best for the spinal cord, brainstem, temporal lobe, eyes, optic nerve, parotid glands and larynx (DSC >0.7). Higher conformity for the OARs delineation was achieved by retraining our architecture, largest DSC improvement on oral cavity (0.53 to 0.93). Compared with the manual delineation time, after using auto-contouring, this duration was significantly shortened from hours to minutes. In the subjective evaluation, two observes showed an apparent inclination on automatic OARs contouring, even for relatively low DSC values. Most of the automated OARs segmentation can reach the clinical acceptance level compared to manual delineations.

Conclusions

After retraining, the CNN developed for OARs automated delineation in HNC was proved to be more robust, efficiency and consistency in clinical practice. Deep learning-based auto-segmentation shows great potential to alleviate the labor-intensive contouring of OAR for radiotherapy treatment planning.

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.

Analysis of Geometric Performance and Dosimetric Impact of Using Automatic Contour Segmentation for Radiotherapy Planning

Purpose: To analyze geometric discrepancy and dosimetric impact in using contours generated by auto-segmentation (AS) against manually segmented (MS) clinical contours. Methods: A 48-subject prostate atlas was created and another 15 patients were used for testing. Contours were generated using a commercial atlas-based segmentation tool and compared to their clinical MS counterparts. The geometric correlation was evaluated using the Dice similarity coefficient (DSC) and Hausdorff distance (HD). Dosimetric relevance was evaluated for a subset of patients by assessing the DVH differences derived by optimizing plan dose using the AS and MS contours, respectively, and evaluating with respect to each. A paired t-test was employed for statistical comparison. The discrepancy in plan quality with respect to clinical dosimetric endpoints was evaluated. The analysis was repeated for head/neck (HN) with a 31-subject atlas and 15 test cases. Results: Dice agreement between AS and MS differed significantly across structures: from (L:0.92/R: 0.91) for the femoral heads to seminal vesical of 0.38 in the prostate cohort, and from 0.98 for the brain, to 0.36 for the chiasm of the HN group. Despite the geometric disagreement, the paired t-tests showed the lack of statistical evidence for systematic differences in dosimetric plan quality yielded by the AS and MS approach for the prostate cohort. In HN cases, statistically significant differences in dosimetric endpoints were observed in structures with small volumes or elongated shapes such as cord (p = 0.01) and esophagus (p = 0.04). The largest absolute dose difference of 11 Gy was seen in the mean pharynx dose. Conclusion: Varying AS performance among structures suggests a differential approach of using AS on a subset of structures and focus MS on the rest. The discrepancy between geometric and dosimetric-end-point driven evaluation also indicates the clinical utility of AS contours in optimization and evaluating plan quality despite of suboptimal geometrical accuracy.

FocusNetv2: Imbalanced large and small organ segmentation with adversarial shape constraint for head and neck CT images

Radiotherapy is a treatment where radiation is used to eliminate cancer cells. The delineation of organs-at-risk (OARs) is a vital step in radiotherapy treatment planning to avoid damage to healthy organs. For nasopharyngeal cancer, more than 20 OARs are needed to be precisely segmented in advance. The challenge of this task lies in complex anatomical structure, low-contrast organ contours, and the extremely imbalanced size between large and small organs. Common segmentation methods that treat them equally would generally lead to inaccurate small-organ labeling. We propose a novel two-stage deep neural network, FocusNetv2, to solve this challenging problem by automatically locating, ROI-pooling, and segmenting small organs with specifically designed small-organ localization and segmentation sub-networks while maintaining the accuracy of large organ segmentation. In addition to our original FocusNet, we employ a novel adversarial shape constraint on small organs to ensure the consistency between estimated small-organ shapes and organ shape prior knowledge. Our proposed framework is extensively tested on both self-collected dataset of 1,164 CT scans and the MICCAI Head and Neck Auto Segmentation Challenge 2015 dataset, which shows superior performance compared with state-of-the-art head and neck OAR segmentation methods.

Automatic segmentation and applicator reconstruction for CT-based brachytherapy of cervical cancer using 3D convolutional neural networks

In this study, we present deep learning-based approaches to automatic segmentation and applicator reconstruction with high accuracy and efficiency in the planning computed tomography (CT) for cervical cancer brachytherapy (BT). A novel three-dimensional (3D) convolutional neural network (CNN) architecture was proposed and referred to as DSD-UNET. The dataset of 91 patients received CT-based BT of cervical cancer was used to train and test DSD-UNET model for auto-segmentation of high-risk clinical target volume (HR-CTV) and organs at risk (OARs). Automatic applicator reconstruction was achieved with DSD-UNET-based segmentation of applicator components followed by 3D skeletonization and polynomial curve fitting. Digitization of the channel paths for tandem and ovoid applicator in the planning CT was evaluated utilizing the data from 32 patients. Dice similarity coefficient (DSC), Jaccard Index (JI), and Hausdorff distance (HD) were used to quantitatively evaluate the accuracy. The segmentation performance of DSD-UNET was compared with that of 3D U-Net. Results showed that DSD-UNET method outperformed 3D U-Net on segmentations of all the structures. The mean DSC values of DSD-UNET method were 86.9%, 82.9%, and 82.1% for bladder, HR-CTV, and rectum, respectively. For the performance of automatic applicator reconstruction, outstanding segmentation accuracy was first achieved for the intrauterine and ovoid tubes (average DSC value of 92.1%, average HD value of 2.3 mm). Finally, HDs between the channel paths determined automatically and manually were 0.88 ± 0.12 mm, 0.95 ± 0.16 mm, and 0.96 ± 0.15 mm for the intrauterine, left ovoid, and right ovoid tubes, respectively. The proposed DSD-UNET method outperformed the 3D U-Net and could segment HR-CTV, bladder, and rectum with relatively good accuracy. Accurate digitization of the channel paths could be achieved with the DSD-UNET-based method. The proposed approaches could be useful to improve the efficiency and consistency of treatment planning for cervical cancer BT.

Glenoid bone strain after anatomical total shoulder arthroplasty: In vitro measurements with micro-CT and digital volume correlation

Glenoid implant loosening remains a major source of failure and concern after anatomical total shoulder arthroplasty (aTSA). It is assumed to be associated with eccentric loading and excessive bone strain, but direct measurement of bone strain after aTSA is not available yet. Therefore, our objective was to develop an in vitro technique for measuring bone strain around a loaded glenoid implant. A custom loading device (1500 N) was designed to fit within a micro-CT scanner, to use digital volume correlation for measuring displacement and calculating strain. Errors were evaluated with three pairs of unloaded scans. The average displacement random error of three pairs of unloaded scans was 6.1 µm. Corresponding systematic and random errors of strain components were less than 806.0 µε and 2039.9 µε, respectively. The average strain accuracy (MAER) and precision (SDER) were 694.3 µε and 440.3 µε, respectively. The loaded minimum principal strain (8738.9 µε) was 12.6 times higher than the MAER (694.3 µε) on average, and was above the MAER for most of the glenoid bone volume (98.1%). Therefore, this technique proves to be accurate and precise enough to eventually compare glenoid implant designs, fixation techniques, or to validate numerical models of specimens under similar loading.

[Multi-scale 3D convolutional neural network-based segmentation of head and neck organs at risk]

OBJECTIVE

To establish an algorithm based on 3D convolution neural network to segment the organs at risk (OARs) in the head and neck on CT images.

METHODS

We propose an automatic segmentation algorithm of head and neck OARs based on V-Net. To enhance the feature expression ability of the 3D neural network, we combined the squeeze and exception (SE) module with the residual convolution module in V-Net to increase the weight of the features that has greater contributions to the segmentation task. Using a multi-scale strategy, we completed organ segmentation using two cascade models for location and fine segmentation, and the input image was resampled to different resolutions during preprocessing to allow the two models to focus on the extraction of global location information and local detail features respectively.

RESULTS

Our experiments on segmentation of 22 OARs in the head and neck indicated that compared with the existing methods, the proposed method achieved better segmentation accuracy and efficiency, and the average segmentation accuracy was improved by 9%. At the same time, the average test time was reduced from 33.82 s to 2.79 s.

CONCLUSIONS

The 3D convolution neural network based on multi-scale strategy can effectively and efficiently improve the accuracy of organ segmentation and can be potentially used in clinical setting for segmentation of other organs to improve the efficiency of clinical treatment.

Head and neck multi-organ auto-segmentation on CT images aided by synthetic MRI

PURPOSE

Because the manual contouring process is labor-intensive and time-consuming, segmentation of organs-at-risk (OARs) is a weak link in radiotherapy treatment planning process. Our goal was to develop a synthetic MR (sMR)-aided dual pyramid network (DPN) for rapid and accurate head and neck multi-organ segmentation in order to expedite the treatment planning process.

METHODS

Forty-five patients' CT, MR, and manual contours pairs were included as our training dataset. Nineteen OARs were target organs to be segmented. The proposed sMR-aided DPN method featured a deep attention strategy to effectively segment multiple organs. The performance of sMR-aided DPN method was evaluated using five metrics, including Dice similarity coefficient (DSC), Hausdorff distance 95% (HD95), mean surface distance (MSD), residual mean square distance (RMSD), and volume difference. Our method was further validated using the 2015 head and neck challenge data.

RESULTS

The contours generated by the proposed method closely resemble the ground truth manual contours, as evidenced by encouraging quantitative results in terms of DSC using the 2015 head and neck challenge data. Mean DSC values of 0.91 ± 0.02, 0.73 ± 0.11, 0.96 ± 0.01, 0.78 ± 0.09/0.78 ± 0.11, 0.88 ± 0.04/0.88 ± 0.06 and 0.86 ± 0.08/0.85 ± 0.1 were achieved for brain stem, chiasm, mandible, left/right optic nerve, left/right parotid, and left/right submandibular, respectively.

CONCLUSIONS

We demonstrated the feasibility of sMR-aided DPN for head and neck multi-organ delineation on CT images. Our method has shown superiority over the other methods on the 2015 head and neck challenge data results. The proposed method could significantly expedite the treatment planning process by rapidly segmenting multiple OARs.

Variability and reproducibility in deep learning for medical image segmentation

Medical image segmentation is an important tool for current clinical applications. It is the backbone of numerous clinical diagnosis methods, oncological treatments and computer-integrated surgeries. A new class of machine learning algorithm, deep learning algorithms, outperforms the results of classical segmentation in terms of accuracy. However, these techniques are complex and can have a high range of variability, calling the reproducibility of the results into question. In this article, through a literature review, we propose an original overview of the sources of variability to better understand the challenges and issues of reproducibility related to deep learning for medical image segmentation. Finally, we propose 3 main recommendations to address these potential issues: (1) an adequate description of the framework of deep learning, (2) a suitable analysis of the different sources of variability in the framework of deep learning, and (3) an efficient system for evaluating the segmentation results.

Auto-segmentation of organs at risk for head and neck radiotherapy planning: From atlas-based to deep learning methods

Radiotherapy (RT) is one of the basic treatment modalities for cancer of the head and neck (H&N), which requires a precise spatial description of the target volumes and organs at risk (OARs) to deliver a highly conformal radiation dose to the tumor cells while sparing the healthy tissues. For this purpose, target volumes and OARs have to be delineated and segmented from medical images. As manual delineation is a tedious and time-consuming task subjected to intra/interobserver variability, computerized auto-segmentation has been developed as an alternative. The field of medical imaging and RT planning has experienced an increased interest in the past decade, with new emerging trends that shifted the field of H&N OAR auto-segmentation from atlas-based to deep learning-based approaches. In this review, we systematically analyzed 78 relevant publications on auto-segmentation of OARs in the H&N region from 2008 to date, and provided critical discussions and recommendations from various perspectives: image modality - both computed tomography and magnetic resonance image modalities are being exploited, but the potential of the latter should be explored more in the future; OAR - the spinal cord, brainstem, and major salivary glands are the most studied OARs, but additional experiments should be conducted for several less studied soft tissue structures; image database - several image databases with the corresponding ground truth are currently available for methodology evaluation, but should be augmented with data from multiple observers and multiple institutions; methodology - current methods have shifted from atlas-based to deep learning auto-segmentation, which is expected to become even more sophisticated; ground truth - delineation guidelines should be followed and participation of multiple experts from multiple institutions is recommended; performance metrics - the Dice coefficient as the standard volumetric overlap metrics should be accompanied with at least one distance metrics, and combined with clinical acceptability scores and risk assessments; segmentation performance - the best performing methods achieve clinically acceptable auto-segmentation for several OARs, however, the dosimetric impact should be also studied to provide clinically relevant endpoints for RT planning.

Recent technological advancements in radiofrequency- andmicrowave-mediated hyperthermia for enhancing drug delivery

Hyperthermia therapy is a potent enhancer of chemotherapy and radiotherapy. In particular, microwave (MW) and radiofrequency (RF) hyperthermia devices provide a variety of heating approaches that can treat most cancers regardless the size. This review introduces the physics of MW/RF hyperthermia, the current state-of-the-art systems for both localized and regional heating, and recent advancements in hyperthermia treatment guidance using real-time computational simulations and magnetic resonance thermometry. Clinical trials involving RF/MW hyperthermia as adjuvant for chemotherapy are also presented per anatomical site. These studies favor the use of adjuvant hyperthermia since it significantly improves curative and palliative clinical outcomes. The main challenge of hyperthermia is the distribution of state-of-the-art heating systems. Nevertheless, we anticipate that recent technology advances will expand the use of hyperthermia to chemotherapy centers for enhanced drug delivery. These new technologies hold great promise not only for (image-guided) perfusion modulation and sensitization for cytotoxic drugs, but also for local delivery of various compounds using thermosensitive liposomes.

Fully automated 3D segmentation and separation of multiple cervical vertebrae in CT images using a 2D convolutional neural network

BACKGROUND AND OBJECTIVE

We investigated a novel method using a 2D convolutional neural network (CNN) to identify superior and inferior vertebrae in a single slice of CT images, and a post-processing for 3D segmentation and separation of cervical vertebrae.

METHODS

The cervical spines of patients (N == 17, 1684 slices) from Severance and Gangnam Severance Hospitals (S/GSH) and healthy controls (N == 24, 3490 slices) from Seoul National University Bundang Hospital (SNUBH) were scanned by using various volumetric CT protocols. To prepare gold standard masks of cervical spine in CT images, each spine was segmented by using conventional image-processing methods and manually corrected by an expert. The gold standard masks were preprocessed and labeled into superior and inferior cervical vertebrae separately in the axial slices. The 2D U-Net model was trained by using the disease dataset (S/GSH) and additional validation was performed by using the healthy control dataset (SNUBH), and then the training and validation were repeated by switching the two datasets.

RESULTS

In case of the model was trained with the disease dataset (S/GSH) and validated with the healthy control (SNUBH), the mean and standard deviation (SD) of the Dice similarity coefficient (DSC), Jaccard similarity coefficient (JSC), mean surface distance (MSD), and Hausdorff surface distance (HSD) were 94.37%% ± 1.45%, 89.47%% ± 2.55%, 0.33 ± 0.12 mm and 20.89 ± 3.98 mm, and 88.67%% ± 5.82%, 80.83%% ± 8.09%, 1.05 ± 0.63 mm and 29.17 ± 19.74 mm, respectively. In case of the model was trained with the healthy control (SNUBH) and validated with the disease dataset (S/GSH), the mean and SD of DSC, JSC, MSD, and HSD were 96.23%% ± 1.55%, 92.95%% ± 2.58%, 0.39 ± 0.20 mm and 16.23 ± 6.72 mm, and 93.15%% ± 3.09%, 87.54%% ± 5.11%, 0.38 ± 0.17 mm and 20.85 ± 7.11 mm, respectively.

CONCLUSIONS

The results demonstrated that our fully automated method achieved comparable accuracies with inter- and intra-observer variabilities of manual segmentation by human experts, which is time consuming.

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

PURPOSE

We introduced and evaluated an end-to-end organs-at-risk (OARs) segmentation model that can provide accurate and consistent OARs segmentation results in much less time.

METHODS

We collected 105 patients' Computed Tomography (CT) scans that diagnosed locally advanced cervical cancer and treated with radiotherapy in one hospital. Seven organs, including the bladder, bone marrow, left femoral head, right femoral head, rectum, small intestine and spinal cord were defined as OARs. The annotated contours of the OARs previously delineated manually by the patient's radiotherapy oncologist and confirmed by the professional committee consisted of eight experienced oncologists before the radiotherapy were used as the ground truth masks. A multi-class segmentation model based on U-Net was designed to fulfil the OARs segmentation task. The Dice Similarity Coefficient (DSC) and 95th Hausdorff Distance (HD) are used as quantitative evaluation metrics to evaluate the proposed method.

RESULTS

The mean DSC values of the proposed method are 0.924, 0.854, 0.906, 0.900, 0.791, 0.833 and 0.827 for the bladder, bone marrow, femoral head left, femoral head right, rectum, small intestine, and spinal cord, respectively. The mean HD values are 5.098, 1.993, 1.390, 1.435, 5.949, 5.281 and 3.269 for the above OARs respectively.

CONCLUSIONS

Our proposed method can help reduce the inter-observer and intra-observer variability of manual OARs delineation and lessen oncologists' efforts. The experimental results demonstrate that our model outperforms the benchmark U-Net model and the oncologists' evaluations show that the segmentation results are highly acceptable to be used in radiation therapy planning.

Predictive value of SAR based quality indicators for head and neck hyperthermia treatment quality

PURPOSE

Hyperthermia treatment quality determines treatment effectiveness as shown by the clinically derived thermal-dose effect relations. SAR based optimization factors are used as possible surrogate for temperature, since they are not affected by thermal tissue properties uncertainty and variations. Previously, target coverage (TC) at the 25% and 50% iso-SAR level was shown predictive for treatment outcome in superficial hyperthermia and the target-to-hot-spot-quotient (THQ) was shown to highly correlate with predictive temperature in deep pelvic hyperthermia. Here, we investigate the correlation with temperature for THQ and TC using an 'intermediate' scenario: semi-deep hyperthermia in the head & neck region using the HYPERcollar3D.

METHODS

Fifteen patient-specific models and two different planning approaches were used, including random perturbations to circumvent optimization bias. The predicted SAR indicators were compared to predicted target temperature distribution indicators T50 and T90, i.e., the median and 90th percentile temperature respectively.

RESULTS

The intra-patient analysis identified THQ, TC25 and TC50 as good temperature surrogates: with a mean correlation coefficient R²_T50 = 0.72 and R²_T90=0.66. The inter-patient analysis identified the highest correlation with TC25 (R²_T50 = 0.76, R²_T90=0.54) and TC50 (R²_T50 = 0.74, R²_T90 = 0.56).

CONCLUSION

Our investigation confirmed the validity of our current strategy for deep hyperthermia in the head & neck based on a combination of THQ and TC25. TC50 was identified as the best surrogate since it enables optimization and patient inclusion decision making using one single parameter.

Radiomics and Machine Learning for Radiotherapy in Head and Neck Cancers

Introduction: An increasing number of parameters can be considered when making decisions in oncology. Tumor characteristics can also be extracted from imaging through the use of radiomics and add to this wealth of clinical data. Machine learning can encompass these parameters and thus enhance clinical decision as well as radiotherapy workflow. Methods: We performed a description of machine learning applications at each step of treatment by radiotherapy in head and neck cancers. We then performed a systematic review on radiomics and machine learning outcome prediction models in head and neck cancers. Results: Machine Learning has several promising applications in treatment planning with automatic organ at risk delineation improvements and adaptative radiotherapy workflow automation. It may also provide new approaches for Normal Tissue Complication Probability models. Radiomics may provide additional data on tumors for improved machine learning powered predictive models, not only on survival, but also on risk of distant metastasis, in field recurrence, HPV status and extra nodal spread. However, most studies provide preliminary data requiring further validation. Conclusion: Promising perspectives arise from machine learning applications and radiomics based models, yet further data are necessary for their implementation in daily care.

The potential of constrained SAR focusing for hyperthermia treatment planning: analysis for the head & neck region

Clinical trials have shown that hyperthermia is a potent adjuvant to conventional cancer treatments, but the temperatures currently achieved in the clinic are still suboptimal. Hyperthermia treatment planning simulations have potential to improve the heating profile of phased-array applicators. An important open challenge is the development of an effective optimization procedure that enables uniform heating of the target region while keeping temperature below a threshold in healthy tissues. In this work, we analyzed the effectiveness and efficiency of a recently proposed optimization approach, i.e. focusing via constrained power optimization (FOCO), using 3D simulations of twelve clinical patient specific models. FOCO performance was compared against a clinically used particle swarm based optimization approach. Evaluation metrics were target coverage at the 25% iso-SAR level, target hotspot quotient, median target temperature (T50) and computational requirements. Our results show that, on average, constrained power focusing performs slightly better than the clinical benchmark ([Formula: see text]T50 [Formula: see text] °C), but outperforms this clinical benchmark for large target volumes ([Formula: see text]40 cm[Formula: see text], [Formula: see text]T50 [Formula: see text] °C). In addition, the results are achieved in a shorter time ([Formula: see text]%) and are repeatable because the approach is formulated as a convex optimization problem.

AnatomyNet: Deep learning for fast and fully automated whole-volume segmentation of head and neck anatomy

PURPOSE

Radiation therapy (RT) is a common treatment option for head and neck (HaN) cancer. An important step involved in RT planning is the delineation of organs-at-risks (OARs) based on HaN computed tomography (CT). However, manually delineating OARs is time-consuming as each slice of CT images needs to be individually examined and a typical CT consists of hundreds of slices. Automating OARs segmentation has the benefit of both reducing the time and improving the quality of RT planning. Existing anatomy autosegmentation algorithms use primarily atlas-based methods, which require sophisticated atlas creation and cannot adequately account for anatomy variations among patients. In this work, we propose an end-to-end, atlas-free three-dimensional (3D) convolutional deep learning framework for fast and fully automated whole-volume HaN anatomy segmentation.

METHODS

Our deep learning model, called AnatomyNet, segments OARs from head and neck CT images in an end-to-end fashion, receiving whole-volume HaN CT images as input and generating masks of all OARs of interest in one shot. AnatomyNet is built upon the popular 3D U-net architecture, but extends it in three important ways: (a) a new encoding scheme to allow autosegmentation on whole-volume CT images instead of local patches or subsets of slices, (b) incorporating 3D squeeze-and-excitation residual blocks in encoding layers for better feature representation, and (c) a new loss function combining Dice scores and focal loss to facilitate the training of the neural model. These features are designed to address two main challenges in deep learning-based HaN segmentation: (a) segmenting small anatomies (i.e., optic chiasm and optic nerves) occupying only a few slices, and (b) training with inconsistent data annotations with missing ground truth for some anatomical structures.

RESULTS

We collected 261 HaN CT images to train AnatomyNet and used MICCAI Head and Neck Auto Segmentation Challenge 2015 as a benchmark dataset to evaluate the performance of AnatomyNet. The objective is to segment nine anatomies: brain stem, chiasm, mandible, optic nerve left, optic nerve right, parotid gland left, parotid gland right, submandibular gland left, and submandibular gland right. Compared to previous state-of-the-art results from the MICCAI 2015 competition, AnatomyNet increases Dice similarity coefficient by 3.3% on average. AnatomyNet takes about 0.12 s to fully segment a head and neck CT image of dimension 178 × 302 × 225, significantly faster than previous methods. In addition, the model is able to process whole-volume CT images and delineate all OARs in one pass, requiring little pre- or postprocessing.

CONCLUSION

Deep learning models offer a feasible solution to the problem of delineating OARs from CT images. We demonstrate that our proposed model can improve segmentation accuracy and simplify the autosegmentation pipeline. With this method, it is possible to delineate OARs of a head and neck CT within a fraction of a second.

Technical Note: More accurate and efficient segmentation of organs-at-risk in radiotherapy with convolutional neural networks cascades

PURPOSE

Manual delineation of organs-at-risk (OARs) in radiotherapy is both time-consuming and subjective. Automated and more accurate segmentation is of the utmost importance in clinical application. The purpose of this study is to further improve the segmentation accuracy and efficiency with a novel network named convolutional neural networks (CNN) Cascades.

METHODS

CNN Cascades was a two-step, coarse-to-fine approach that consisted of a simple region detector (SRD) and a fine segmentation unit (FSU). The SRD first used a relative shallow network to define the region of interest (ROI) where the organ was located, and then, the FSU took the smaller ROI as input and adopted a deep network for fine segmentation. The imaging data (14,651 slices) of 100 head-and-neck patients with segmentations were used for this study. The performance was compared with the state-of-the-art single CNN in terms of accuracy with metrics of Dice similarity coefficient (DSC) and Hausdorff distance (HD) values.

RESULTS

The proposed CNN Cascades outperformed the single CNN on accuracy for each OAR. Similarly, for the average of all OARs, it was also the best with mean DSC of 0.90 (SRD: 0.86, FSU: 0.87, and U-Net: 0.85) and the mean HD of 3.0 mm (SRD: 4.0, FSU: 3.6, and U-Net: 4.4). Meanwhile, the CNN Cascades reduced the mean segmentation time per patient by 48% (FSU) and 5% (U-Net), respectively.

CONCLUSIONS

The proposed two-step network demonstrated superior performance by reducing the input region. This potentially can be an effective segmentation method that provides accurate and consistent delineation with reduced clinician interventions for clinical applications as well as for quality assurance of a multicenter clinical trial.

Evaluation of deep learning methods for parotid gland segmentation from CT images

The segmentation of organs at risk is a crucial and time-consuming step in radiotherapy planning. Good automatic methods can significantly reduce the time clinicians have to spend on this task. Due to its variability in shape and low contrast to surrounding structures, segmenting the parotid gland is challenging. Motivated by the recent success of deep learning, we study the use of two-dimensional (2-D), 2-D ensemble, and three-dimensional (3-D) U-Nets for segmentation. The mean Dice similarity to ground truth is ∼0.83 for all three models. A patch-based approach for class balancing seems promising for false-positive reduction. The 2-D ensemble and 3-D U-Net are applied to the test data of the 2015 MICCAI challenge on head and neck autosegmentation. Both deep learning methods generalize well onto independent data (Dice 0.865 and 0.88) and are superior to a selection of model- and atlas-based methods with respect to the Dice coefficient. Since appropriate reference annotations are essential for training but often difficult and expensive to obtain, it is important to know how many samples are needed for training. We evaluate the performance after training with different-sized training sets and observe no significant increase in the Dice coefficient for more than 250 training cases.

Automation in intensity modulated radiotherapy treatment planning-a review of recent innovations

Radiotherapy treatment planning of complex radiotherapy techniques, such as intensity modulated radiotherapy and volumetric modulated arc therapy, is a resource-intensive process requiring a high level of treatment planner intervention to ensure high plan quality. This can lead to variability in the quality of treatment plans and the efficiency in which plans are produced, depending on the skills and experience of the operator and available planning time. Within the last few years, there has been significant progress in the research and development of intensity modulated radiotherapy treatment planning approaches with automation support, with most commercial manufacturers now offering some form of solution. There is a rapidly growing number of research articles published in the scientific literature on the topic. This paper critically reviews the body of publications up to April 2018. The review describes the different types of automation algorithms, including the advantages and current limitations. Also included is a discussion on the potential issues with routine clinical implementation of such software, and highlights areas for future research.

Personalized Anatomic Eye Model From T1-Weighted Volume Interpolated Gradient Echo Magnetic Resonance Imaging of Patients With Uveal Melanoma

PURPOSE

We present a 3-dimensional patient-specific eye model from magnetic resonance imaging (MRI) for proton therapy treatment planning of uveal melanoma (UM). During MRI acquisition of UM patients, the point fixation can be difficult and, together with physiological blinking, can introduce motion artifacts in the images, thus challenging the model creation. Furthermore, the unclear boundary of the small objects (eg, lens, optic nerve) near the muscle or of the tumors with hemorrhage and tantalum clips can limit model accuracy.

METHODS AND MATERIALS

A dataset of 37 subjects, including 30 healthy eyes of volunteers and 7 eyes of UM patients, was investigated. In our previous work, active shape model was successfully applied to retinoblastoma eye segmentation in T1-weighted 3T MRI. Here, we evaluate this method in a more challenging setting, based on 1.5T MRI acquisition and different datasets of awake adult eyes with UM. The lens and cornea together with the sclera, vitreous humor, and optic nerve were automatically segmented and validated against manual delineations of a senior ocular radiation oncologist, in terms of the Dice similarity coefficient and Hausdorff distance.

RESULTS

Leave-one-out cross validation (mixing both volunteers and UM patients) yielded median Dice similarity coefficient values (respective of Hausdorff distance) of 94.5% (1.64 mm) for the sclera, 92.2% (1.73 mm) for the vitreous humor, 88.3% (1.09 mm) for the lens, and 81.9% (1.86 mm) for the optic nerve. The average computation time for an eye was 10 seconds.

CONCLUSIONS

To our knowledge, our work is the first attempt to automatically segment adult eyes, including patients with UM. Our results show that automated active shape model segmentation can succeed in the presence of motion, tumors, and tantalum clips. These results are promising for inclusion in clinical practice.

Hierarchical Vertex Regression-Based Segmentation of Head and Neck CT Images for Radiotherapy Planning

Segmenting organs at risk from head and neck CT images is a prerequisite for the treatment of head and neck cancer using intensity modulated radiotherapy. However, accurate and automatic segmentation of organs at risk is a challenging task due to the low contrast of soft tissue and image artifact in CT images. Shape priors have been proved effective in addressing this challenging task. However, conventional methods incorporating shape priors often suffer from sensitivity to shape initialization and also shape variations across individuals. In this paper, we propose a novel approach to incorporate shape priors into a hierarchical learning-based model. The contributions of our proposed approach are as follows: 1) a novel mechanism for critical vertices identification is proposed to identify vertices with distinctive appearances and strong consistency across different subjects; 2) a new strategy of hierarchical vertex regression is also used to gradually locate more vertices with the guidance of previously located vertices; and 3) an innovative framework of joint shape and appearance learning is further developed to capture salient shape and appearance features simultaneously. Using these innovative strategies, our proposed approach can essentially overcome drawbacks of the conventional shape-based segmentation methods. Experimental results show that our approach can achieve much better results than state-of-the-art methods.