Optimal number of atlases and label fusion for automatic multi-atlas-based brachial plexus contouring in radiotherapy treatment planning

The effect of nursing intervention combined with PD-1 inhibitor on platelets, white blood cells, tumor markers and quality of life in patients with lung cancer

Tumor immunotherapy has become one of the important directions in the field of anti-tumor research. Among them, programmed death molecule-1 (PD-1) and its ligand (PD-L1) inhibitors have attracted considerable attention. This study analyzed the application effects of PD-1 inhibitors assisted nursing intervention in patients with lung cancer (LC). Sixty-eight patients with LC were divided into research group and control group randomly. Control group was treated with PD-1 inhibitor chemotherapy. Research group was treated with PD-1 inhibitors as auxiliary nursing intervention. Platelets, immune function indexes, tumor markers, and white blood cells were analyzed. Clinical efficacy was evaluated by traditional Chinese medicine (TCM) symptom score, survival quality of karnofsky performance scale (KPS) score, living quality of quality of life (QOL) score, and nausea and vomiting classification. Hemoglobin (HB), platelet (PLT) and serum white blood cells (WBC) levels in the two groups were decreased after treatment. HB, PLT and WBC levels were enhanced in research group versus control group. Moreover, carcino-embryonic antigen (CEA), carbohydrate antigen 199 (CA199) and CA125 levels in both groups were reduced after treatment. Compared with before treatment, the levels of cluster of differentiation (CD)3+, CD4+, CD4+/CD8+ in control group and the research group increased, while the CD8+ content was significantly decreased after treatment. And their content of the research group was significantly higher/lower than that of the control group. TCM symptom score, KPS score, QOL score and nausea and vomiting classification were improved in research group compared to control group. PD-1 inhibitors assisted nursing intervention can improve the living quality of patients with LC after chemotherapy.

Enhancing the Contouring Efficiency for Head and Neck Cancer Radiotherapy Using Atlas-based Auto-segmentation and Scripting

BACKGROUND/AIM

Intensity-modulated radiation therapy can deliver a highly conformal dose to a target while minimizing the dose to the organs at risk (OARs). Delineating the contours of OARs is time-consuming, and various automatic contouring software programs have been employed to reduce the delineation time. However, some software operations are manual, and further reduction in time is possible. This study aimed to automate running atlas-based auto-segmentation (ABAS) and software operations using a scripting function, thereby reducing work time.

MATERIALS AND METHODS

Dice coefficient and Hausdorff distance were used to determine geometric accuracy. The manual delineation, automatic delineation, and modification times were measured. While modifying the contours, the degree of subjective correction was rated on a four-point scale.

RESULTS

The model exhibited generally good geometric accuracy. However, some OARs, such as the chiasm, optic nerve, retina, lens, and brain require improvement. The average contour delineation time was reduced from 57 to 29 min (p<0.05). The subjective revision degree results indicated that all OARs required minor modifications; only the submandibular gland, thyroid, and esophagus were rated as modified from scratch.

CONCLUSION

The ABAS model and scripted automation in head and neck cancer reduced the work time and software operations. The time can be further reduced by improving contour accuracy.

Impact of Dose Calculation Algorithms and Radiobiological Parameters on Prediction of Cardiopulmonary Complications in Left Breast Radiation Therapy

Background

Breast cancer requires evaluating treatment plans using dosimetric and biological parameters. Considering radiation dose distribution and tissue response, healthcare professionals can optimize treatment plans for better outcomes.

Objective

This study aimed to evaluate the effects of the different Dose Calculation Algorithms (DCAs) and Biologically Model-Related Parameters (BMRPs) on the prediction of cardiopulmonary complications due to left breast radiotherapy.

Material and Methods

In this practical study, the treatment plans of 21 female patients were simulated in the Monaco Treatment Planning System (TPS) with a prescribed dose of 50 Gy in 25 fractions. Dose distribution was extracted using the three DCAs [Pencil Beam (PB), Collapsed Cone (CC), and Monte Carlo (MC)]. Cardiopulmonary complications were predicted by Normal Tissue Complication Probability (NTCP) calculations using different dosimetric and biological parameters. The Lyman-Kutcher-Burman (LKB) and Relative-Seriality (RS) models were used to calculate NTCP. The endpoint for NTCP calculation was pneumonitis, pericarditis, and late cardiac mortality. The ANOVA test was used for statistical analysis.

Results

In calculating Tumor Control Probability (TCP), a statistically significant difference was observed between the results of DCAs in the Poisson model. The PB algorithm estimated NTCP as less than others for all Pneumonia BMRPs.

Conclusion

The impact of DCAs and BMRPs differs in the estimation of TCP and NTCP. DCAs have a stronger influence on TCP calculation, providing more effective results. On the other hand, BMRPs are more effective in estimating NTCP. Consequently, parameters for radiobiological indices should be cautiously used s to ensure the appropriate consideration of both DCAs and BMRPs.

Comparison of Machine-Learning and Deep-Learning Methods for the Prediction of Osteoradionecrosis Resulting From Head and Neck Cancer Radiation Therapy

Purpose

Deep-learning (DL) techniques have been successful in disease-prediction tasks and could improve the prediction of mandible osteoradionecrosis (ORN) resulting from head and neck cancer (HNC) radiation therapy. In this study, we retrospectively compared the performance of DL algorithms and traditional machine-learning (ML) techniques to predict mandible ORN binary outcome in an extensive cohort of patients with HNC.

Methods and Materials

Patients who received HNC radiation therapy at the University of Texas MD Anderson Cancer Center from 2005 to 2015 were identified for the ML (n = 1259) and DL (n = 1236) studies. The subjects were followed for ORN development for at least 12 months, with 173 developing ORN and 1086 having no evidence of ORN. The ML models used dose-volume histogram parameters to predict ORN development. These models included logistic regression, random forest, support vector machine, and a random classifier reference. The DL models were based on ResNet, DenseNet, and autoencoder-based architectures. The DL models used each participant's dose cropped to the mandible. The effect of increasing the amount of available training data on the DL models' prediction performance was evaluated by training the DL models using increasing ratios of the original training data.

Results

The F1 score for the logistic regression model, the best-performing ML model, was 0.3. The best-performing ResNet, DenseNet, and autoencoder-based models had F1 scores of 0.07, 0.14, and 0.23, respectively, whereas the random classifier's F1 score was 0.17. No performance increase was apparent when we increased the amount of training data available for DL model training.

Conclusions

The ML models had superior performance to their DL counterparts. The lack of improvement in DL performance with increased training data suggests that either more data are needed for appropriate DL model construction or that the image features used in DL models are not suitable for this task.

Clinical target volume segmentation based on gross tumor volume using deep learning for head and neck cancer treatment

Accurate clinical target volume (CTV) delineation is important for head and neck intensity-modulated radiation therapy. However, delineation is time-consuming and susceptible to interobserver variability (IOV). Based on a manual contouring process commonly used in clinical practice, we developed a deep learning (DL)-based method to delineate a low-risk CTV with computed tomography (CT) and gross tumor volume (GTV) input and compared it with a CT-only input. A total of 310 patients with oropharynx cancer were randomly divided into the training set (250) and test set (60). The low-risk CTV and primary GTV contours were used to generate label data for the input and ground truth. A 3D U-Net with a two-channel input of CT and GTV (U-Net_GTV) was proposed and its performance was compared with a U-Net with only CT input (U-Net_CT). The Dice similarity coefficient (DSC) and average Hausdorff distance (AHD) were evaluated. The time required to predict the CTV was 0.86 s per patient. U-Net_GTV showed a significantly higher mean DSC value than U-Net_CT (0.80 ± 0.03 and 0.76 ± 0.05) and a significantly lower mean AHD value (3.0 ± 0.5 mm vs 3.5 ± 0.7 mm). Compared to the existing DL method with only CT input, the proposed GTV-based segmentation using DL showed a more precise low-risk CTV segmentation for head and neck cancer. Our findings suggest that the proposed method could reduce the contouring time of a low-risk CTV, allowing the standardization of target delineations for head and neck cancer.

Comparative clinical studies of primary chemoradiotherapy versus S-1 and nedaplatin chemotherapy against stage IVb oesophageal squamous cell carcinoma: a multicentre open-label randomised controlled trial

INTRODUCTION

Oesophageal squamous cell carcinoma (OSCC) is one of the most commonly occurring devastating tumours worldwide, including in China. To date, the standard care of patients with stage IV OSCC is systemic chemotherapy and palliative care, which results in poor prognosis. However, no consensus has been established regarding the role of radiotherapy in targeting the primary tumour in patients with stage IVa OSCC. Thus, the aim of this study is to assess the effectiveness of primary radiotherapy combined with S-1 and nedaplatin (NPD) chemotherapy in the patients with stage IV OSCC.

METHODS AND ANALYSIS

The study is a multicentre, open-label, randomised controlled trial. A total of 180 eligible patients with stage IV OSCC will be randomised into a study group (90 patients) and a control group (90 patients). Patients in the study group will receive radiotherapy to the primary tumour at a dose of 50.4 Gy combined with 4-6 cycles of S-1 and NPD chemotherapy. In the control group, patients will only receive 4-6 cycles of S-1 and NPD chemotherapy. The primary and secondary outcomes will be measured. The differences between the two groups will be statistically analysed with regard to overall survival, the progression-free survival and safety. All outcomes will be ascertained before treatment, after treatment and after the follow-up period.The results of this study will provide evidence on the role of radiotherapy in patients with stage IV OSCC in China, which will show new options for patients with advanced oesophageal cancer.

ETHICS AND DISSEMINATION

This study was approved by the Institutional Ethics Committee of The First Hospital Affiliated of Zhengzhou University (approval number: SS-2018-04).

TRIAL REGISTRATION

The trial has been registered at the Chinese Clinical Trial Registry (ChiCTR1800015765) on 1 November 2018; retrospectively registered, http://www.chictr.org.cn/index.aspx.

Long non-coding RNAs and microRNAs as crucial regulators in cardio-oncology

Cancer is one of the leading causes of morbidity and mortality worldwide. Significant improvements in the modern era of anticancer therapeutic strategies have increased the survival rate of cancer patients. Unfortunately, cancer survivors have an increased risk of cardiovascular diseases, which is believed to result from anticancer therapies. The emergence of cardiovascular diseases among cancer survivors has served as the basis for establishing a novel field termed cardio-oncology. Cardio-oncology primarily focuses on investigating the underlying molecular mechanisms by which anticancer treatments lead to cardiovascular dysfunction and the development of novel cardioprotective strategies to counteract cardiotoxic effects of cancer therapies. Advances in genome biology have revealed that most of the genome is transcribed into non-coding RNAs (ncRNAs), which are recognized as being instrumental in cancer, cardiovascular health, and disease. Emerging studies have demonstrated that alterations of these ncRNAs have pathophysiological roles in multiple diseases in humans. As it relates to cardio-oncology, though, there is limited knowledge of the role of ncRNAs. In the present review, we summarize the up-to-date knowledge regarding the roles of long non-coding RNAs (lncRNAs) and microRNAs (miRNAs) in cancer therapy-induced cardiotoxicities. Moreover, we also discuss prospective therapeutic strategies and the translational relevance of these ncRNAs.

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

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

A Systematic Review of Cost-Effectiveness Analyses for Hepatocellular Carcinoma Treatment

BACKGROUND

Hepatocellular carcinoma (HCC) is associated with significant financial burden for patients and payers. The objective of this study was to review economic models to identify, evaluate, and compare cost-effectiveness estimates for HCC treatments.

METHODS

A systematic search of the PubMed, Embase, and Cochrane Library databases to identify economic evaluations was performed and studies that modeled treatments for HCC reporting costs and cost effectiveness were included. Risk of bias was assessed qualitatively, considering costing approach, reported study perspective, and funding received. Intervention costs were adjusted to 2021 US dollars for comparison. For studies reporting quality-adjusted life-years (QALYs), we conducted analyses stratified by comparison type to assess cost effectiveness at the time of the analysis.

RESULTS

A total of 27 studies were included. Non-curative versus non-curative therapy comparisons were used in 20 (74.1%) studies, curative versus curative comparisons were used in 5 (18.5%) studies, and curative versus non-curative comparisons were used in 2 (7.4%) studies. Therapy effectiveness was estimated using a QALY measure in 20 (74.1%) studies, while 7 (25.9%) studies only assessed life-years gained (LYG). A health sector perspective was used in 26 (96.3%) of the evaluations, with only 1 study including costs beyond this perspective. Median intervention cost was $53,954 (range $4550-$4,760,835), with a median incremental cost of $6546 (range - $72,441 to $1,279,764). In cost-utility analyses, 11 (55%) studies found the intervention cost effective using a $100,000/QALY threshold at the time of the study, with an incremental cost-effectiveness ratio (ICER) ranging from - $1,176,091 to $1,152,440 when inflated to 2021 US dollars.

CONCLUSION

The majority of HCC treatments were found to be cost effective, but with significant variation and with few studies considering indirect costs. Standards for value assessment for HCC treatments may help improve consistency and comparability.

Evaluating Automatic Segmentation for Swallowing-Related Organs for Head and Neck Cancer

Purpose: To evaluate the accuracy of deep-learning-based auto-segmentation of the superior constrictor, middle constrictor, inferior constrictor, and larynx in comparison with a traditional multi-atlas-based method. Methods and Materials: One hundred and five computed tomography image datasets from 83 head and neck cancer patients were retrospectively collected and the superior constrictor, middle constrictor, inferior constrictor, and larynx were analyzed for deep-learning versus multi-atlas-based segmentation. Eighty-three computed tomography images (40 diagnostic computed tomography and 43 planning computed tomography) were used for training the convolutional neural network, and for atlas-based model training. The remaining 22 computed tomography datasets were used for validation of the atlas-based auto-segmentation versus deep-learning-based auto-segmentation contours, both of which were compared with the corresponding manual contours. Quantitative measures included Dice similarity coefficient, recall, precision, Hausdorff distance, 95th percentile of Hausdorff distance, and mean surface distance. Dosimetric differences between the auto-generated contours and manual contours were evaluated. Subjective evaluation was obtained from 3 clinical observers to blindly score the autosegmented structures based on the percentage of slices that require manual modification. Results: The deep-learning-based auto-segmentation versus atlas-based auto-segmentation results were compared for the superior constrictor, middle constrictor, inferior constrictor, and larynx. The mean Dice similarity coefficient values for the 4 structures were 0.67, 0.60, 0.65, and 0.84 for deep-learning-based auto-segmentation, whereas atlas-based auto-segmentation has Dice similarity coefficient results at 0.45, 0.36, 0.50, and 0.70, respectively. The mean 95th percentile of Hausdorff distance (cm) for the 4 structures were 0.41, 0.57, 0.59, and 0.54 for deep-learning-based auto-segmentation, but 0.78, 0.95, 0.96, and 1.23 for atlas-based auto-segmentation results, respectively. Similar mean dose differences were obtained from the 2 sets of autosegmented contours compared to manual contours. The dose–volume discrepancies and the average modification rates were higher with the atlas-based auto-segmentation contours. Conclusion: Swallowing-related structures are more accurately generated with DL-based versus atlas-based segmentation when compared with manual contours.

Training and Validation of Deep Learning-Based Auto-Segmentation Models for Lung Stereotactic Ablative Radiotherapy Using Retrospective Radiotherapy Planning Contours

PURPOSE

Deep learning-based auto-segmented contour (DC) models require high quality data for their development, and previous studies have typically used prospectively produced contours, which can be resource intensive and time consuming to obtain. The aim of this study was to investigate the feasibility of using retrospective peer-reviewed radiotherapy planning contours in the training and evaluation of DC models for lung stereotactic ablative radiotherapy (SABR).

METHODS

Using commercial deep learning-based auto-segmentation software, DC models for lung SABR organs at risk (OAR) and gross tumor volume (GTV) were trained using a deep convolutional neural network and a median of 105 contours per structure model obtained from 160 publicly available CT scans and 50 peer-reviewed SABR planning 4D-CT scans from center A. DCs were generated for 50 additional planning CT scans from center A and 50 from center B, and compared with the clinical contours (CC) using the Dice Similarity Coefficient (DSC) and 95% Hausdorff distance (HD).

RESULTS

Comparing DCs to CCs, the mean DSC and 95% HD were 0.93 and 2.85mm for aorta, 0.81 and 3.32mm for esophagus, 0.95 and 5.09mm for heart, 0.98 and 2.99mm for bilateral lung, 0.52 and 7.08mm for bilateral brachial plexus, 0.82 and 4.23mm for proximal bronchial tree, 0.90 and 1.62mm for spinal cord, 0.91 and 2.27mm for trachea, and 0.71 and 5.23mm for GTV. DC to CC comparisons of center A and center B were similar for all OAR structures.

CONCLUSIONS

The DCs developed with retrospective peer-reviewed treatment contours approximated CCs for the majority of OARs, including on an external dataset. DCs for structures with more variability tended to be less accurate and likely require using a larger number of training cases or novel training approaches to improve performance. Developing DC models from existing radiotherapy planning contours appears feasible and warrants further clinical workflow testing.

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.

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.

J. Kotte AN, Bol GH, T. van den Berg CA. Clinical implementation of MRI-based organs-at-risk auto-segmentation with convolutional networks for prostate radiotherapy

BACKGROUND

Structure delineation is a necessary, yet time-consuming manual procedure in radiotherapy. Recently, convolutional neural networks have been proposed to speed-up and automatise this procedure, obtaining promising results. With the advent of magnetic resonance imaging (MRI)-guided radiotherapy, MR-based segmentation is becoming increasingly relevant. However, the majority of the studies investigated automatic contouring based on computed tomography (CT).

PURPOSE

In this study, we investigate the feasibility of clinical use of deep learning-based automatic OARs delineation on MRI.

MATERIALS AND METHODS

We included 150 patients diagnosed with prostate cancer who underwent MR-only radiotherapy. A three-dimensional (3D) T1-weighted dual spoiled gradient-recalled echo sequence was acquired with 3T MRI for the generation of the synthetic-CT. The first 48 patients were included in a feasibility study training two 3D convolutional networks called DeepMedic and dense V-net (dV-net) to segment bladder, rectum and femurs. A research version of an atlas-based software was considered for comparison. Dice similarity coefficient, 95% Hausdorff distances (HD95), and mean distances were calculated against clinical delineations. For eight patients, an expert RTT scored the quality of the contouring for all the three methods. A choice among the three approaches was made, and the chosen approach was retrained on 97 patients and implemented for automatic use in the clinical workflow. For the successive 53 patients, Dice, HD95 and mean distances were calculated against the clinically used delineations.

RESULTS

DeepMedic, dV-net and the atlas-based software generated contours in 60 s, 4 s and 10-15 min, respectively. Performances were higher for both the networks compared to the atlas-based software. The qualitative analysis demonstrated that delineation from DeepMedic required fewer adaptations, followed by dV-net and the atlas-based software. DeepMedic was clinically implemented. After retraining DeepMedic and testing on the successive patients, the performances slightly improved.

CONCLUSION

High conformality for OARs delineation was achieved with two in-house trained networks, obtaining a significant speed-up of the delineation procedure. Comparison of different approaches has been performed leading to the succesful adoption of one of the neural networks, DeepMedic, in the clinical workflow. DeepMedic maintained in a clinical setting the accuracy obtained in the feasibility study.

How many models/atlases are needed as priors for capturing anatomic population variations?

Many medical image processing and analysis operations can benefit a great deal from prior information encoded in the form of models/atlases to capture variations over a population in form, shape, anatomic layout, and image appearance of objects. However, two fundamental questions have not been addressed in the literature: "How many models/atlases are needed for optimally encoding prior information to address the differing body habitus factor in that population?" and "Images of how many subjects in the given population are needed to optimally harness prior information?" We propose a method to seek answers to these questions. We assume that there is a well-defined body region of interest and a subject population under consideration, and that we are given a set of representative images of the body region for the population. After images are trimmed to the exact body region, a hierarchical agglomerative clustering algorithm partitions the set of images into a specified number of groups by using pairwise image (dis)similarity as a cost function. Optionally the images may be pre-registered among themselves prior to this partitioning operation. We define a measure called Residual Dissimilarity (RD) to determine the goodness of each partition. We then ascertain how RD varies as a function of the number of elements in the partition for finding the optimum number(s) of groups. Breakpoints in this function are taken as the recommended number of groups/models/atlases. Our results from analysis of sizeable CT data sets of adult patients from two body regions - thorax (346) and head and neck (298) - can be summarized as follows. (1) A minimum of 5 to 8 groups (or models/atlases) seems essential to properly capture information about differing anatomic forms and body habitus. (2) A minimum of 150 images from different subjects in a population seems essential to cover the anatomical variations for a given body region. (3) In grouping, body habitus variations seem to override differences due to other factors such as gender, with/without contrast enhancement in image acquisition, and presence of moderate pathology. This method may be helpful for constructing high quality models/atlases from a sufficiently large population of images and in optimally selecting the training image sets needed in deep learning strategies.

Comparison of MRI-based automated segmentation methods and functional neurosurgery targeting with direct visualization of the Ventro-intermediate thalamic nucleus at 7T

The ventro-intermediate nucleus (Vim), as part of the motor thalamic nuclei, is a commonly used target in functional stereotactic neurosurgery for treatment of drug-resistant tremor. As it cannot be directly visualized on routinely used magnetic resonance imaging (MRI), its clinical targeting is performed using indirect methods. Recent literature suggests that the Vim can be directly visualized on susceptibility-weighted imaging (SWI) acquired at 7 T. Our work aims to assess the distinguishable Vim on 7 T SWI in both healthy-population and patients and, using it as a reference, to compare it with: (1) The clinical targeting, (2) The automated parcellation of thalamic subparts based on 3 T diffusion MRI (dMRI), and (3) The multi-atlas segmentation techniques. In 95.2% of the data, the manual outline was adjacent to the inferior lateral border of the dMRI-based motor-nuclei group, while in 77.8% of the involved cases, its ventral part enclosed the Guiot points. Moreover, the late MRI signature in the patients was always observed in the anterior part of the manual delineation and it overlapped with the multi-atlas outline. Overall, our study provides new insight on Vim discrimination through MRI and imply novel strategies for its automated segmentation, thereby opening new perspectives for standardizing the clinical targeting.

Automatic Intracranial Segmentation: Is the Clinician Still Needed?

INTRODUCTION

Stereotactic hypofractionated radiotherapy is an effective treatment for brain metastases in oligometastatic patients. Its planning is however time-consuming because of the number of organs at risk to be manually segmented. This study evaluates 2 automated segmentation commercial software.

METHODS

Patients were scanned in the treatment position. The computed tomography scan was registered on a magnetic resonance imaging and volumes were manually segmented by a clinician. Then 2 automated segmentations were performed (with iPlan and Smart Segmentation). RT STRUCT files were compared with Aquilab's Artistruct segment comparison module. We selected common segmented volume ratio as the main judging criterion. Secondary criteria were Dice-Sørensen coefficients, overlap ratio, and additional segmented volume.

RESULTS

Twenty consecutive patients were included. Agreement between manual and automated contouring was poor. Common segmented volumes ranged from 7.71% to 82.54%, Dice-Sørensen coefficient ranged from 0.0745 to 0.8398, overlap ratio ranged from 0.0414 to 0.7275, and additional segmented volume ranged from 9.80% to 92.25%. Each software outperformed the other on some organs while performing worse on others.

CONCLUSION

No software seemed clearly better than the other. Common segmented volumes were much too low for routine use in stereotactic hypofractionated brain radiotherapy. Manual editing is still needed.

Application of dual-energy CT to suppression of metal artefact caused by pedicle screw fixation in radiotherapy: a feasibility study using original phantom

The objective of the present study was the determination of the potential dosimetric benefits of using metal-artefact-suppressed dual-energy computed tomography (DECT) images for cases involving pedicle screw implants in spinal sites. A heterogeneous spinal phantom was designed for the investigation of the dosimetric effect of the pedicle-screw-related artefacts. The dosimetric comparisons were first performed using a conventional two-directional opposed (AP-PA) plan, and then a volumetric modulated arc therapy (VMAT) plan, which are both used for the treatment of spinal metastases in our institution. The results of Acuros^® XB dose-to-medium (Dm) and dose-to-water (Dw) calculations using different imaging options were compared with experimental measurements including the chamber and film dosimetries in the spinal phantom. A dual-energy composition image with a weight factor of  -0.2 and a dual-energy monochromatic image (DEMI) with an energy level of 180 keV were found to have superior abilities for artefact suppression. The Dm calculations revealed greater dosimetric effects of the pedicle screw-related artefacts compared to the Dw calculations. The results of conventional single-energy computed tomography showed that, although the pedicle screws were made from low-Z titanium alloy, the metal artefacts still have dosimetric effects, namely, an average (maximum) Dm error of 4.4% (5.6%) inside the spinal cord for a complex VMAT treatment plan. Our findings indicate that metal-artefact suppression using the proposed DECT (DEMI) approach is promising for improving the dosimetric accuracy near the implants and inside the spinal cord (average (maximum) Dm error of 1.1% (2.0%)).

Region-based diffuse optical tomography with registered atlas: in vivo acquisition of mouse optical properties

The reconstruction quality in the model-based optical tomography modalities can greatly benefit from a priori information of accurate tissue optical properties, which are difficult to be obtained in vivo with a conventional diffuse optical tomography (DOT) system alone. One of the solutions is to apply a priori anatomical structures obtained with anatomical imaging systems such as X-ray computed tomography (XCT) to constrain the reconstruction process of DOT. However, since X-ray offers low soft-tissue contrast, segmentation of abdominal organs from sole XCT images can be problematic. In order to overcome the challenges, the current study proposes a novel method of recovering a priori organ-oriented tissue optical properties, where anatomical structures of an in vivo mouse are approximately obtained by registering a standard anatomical atlas, i.e., the Digimouse, to the target XCT volume with the non-rigid image registration, and, in turn, employed to guide DOT for extracting the optical properties of inner organs. Simulative investigations have validated the methodological availability of such atlas-registration-based DOT strategy in revealing both a priori anatomical structures and optical properties. Further experiments have demonstrated the feasibility of the proposed method for acquiring the organ-oriented tissue optical properties of in vivo mice, making it as an efficient way of the reconstruction enhancement.