Classification and evaluation strategies of auto-segmentation approaches for PET: Report of AAPM task group No. 211

The Applications of Radiomics in Precision Diagnosis and Treatment of Oncology: Opportunities and Challenges

Medical imaging can assess the tumor and its environment in their entirety, which makes it suitable for monitoring the temporal and spatial characteristics of the tumor. Progress in computational methods, especially in artificial intelligence for medical image process and analysis, has converted these images into quantitative and minable data associated with clinical events in oncology management. This concept was first described as radiomics in 2012. Since then, computer scientists, radiologists, and oncologists have gravitated towards this new tool and exploited advanced methodologies to mine the information behind medical images. On the basis of a great quantity of radiographic images and novel computational technologies, researchers developed and validated radiomic models that may improve the accuracy of diagnoses and therapy response assessments. Here, we review the recent methodological developments in radiomics, including data acquisition, tumor segmentation, feature extraction, and modelling, as well as the rapidly developing deep learning technology. Moreover, we outline the main applications of radiomics in diagnosis, treatment planning and evaluations in the field of oncology with the aim of developing quantitative and personalized medicine. Finally, we discuss the challenges in the field of radiomics and the scope and clinical applicability of these methods.

Joint Tumor Segmentation in PET-CT Images Using Co-Clustering and Fusion Based on Belief Functions

Precise delineation of target tumor is a key factor to ensure the effectiveness of radiation therapy. While hybrid positron emission tomography-computed tomography (PET-CT) has become a standard imaging tool in the practice of radiation oncology, many existing automatic/semi-automatic methods still perform tumor segmentation on mono-modal images. In this paper, a co-clustering algorithm is proposed to concurrently segment 3D tumors in PET-CT images, considering that the two complementary imaging modalities can combine functional and anatomical information to improve segmentation performance. The theory of belief functions is adopted in the proposed method to model, fuse, and reason with uncertain and imprecise knowledge from noisy and blurry PET-CT images. To ensure reliable segmentation for each modality, the distance metric for the quantification of clustering distortions and spatial smoothness is iteratively adapted during the clustering procedure. On the other hand, to encourage consistent segmentation between different modalities, a specific context term is proposed in the clustering objective function. Moreover, during the iterative optimization process, clustering results for the two distinct modalities are further adjusted via a belief-functions-based information fusion strategy. The proposed method has been evaluated on a data set consisting of 21 paired PET-CT images for non-small cell lung cancer patients. The quantitative and qualitative evaluations show that our proposed method performs well compared with the state-of-the-art methods.

Simultaneous cosegmentation of tumors in PET-CT images using deep fully convolutional networks

PURPOSE

To investigate the use and efficiency of 3-D deep learning, fully convolutional networks (DFCN) for simultaneous tumor cosegmentation on dual-modality nonsmall cell lung cancer (NSCLC) and positron emission tomography (PET)-computed tomography (CT) images.

METHODS

We used DFCN cosegmentation for NSCLC tumors in PET-CT images, considering both the CT and PET information. The proposed DFCN-based cosegmentation method consists of two coupled three-dimensional (3D)-UNets with an encoder-decoder architecture, which can communicate with the other in order to share complementary information between PET and CT. The weighted average sensitivity and positive predictive values denoted as Scores, dice similarity coefficients (DSCs), and the average symmetric surface distances were used to assess the performance of the proposed approach on 60 pairs of PET/CTs. A Simultaneous Truth and Performance Level Estimation Algorithm (STAPLE) of 3 expert physicians' delineations were used as a reference. The proposed DFCN framework was compared to 3 graph-based cosegmentation methods.

RESULTS

Strong agreement was observed when using the STAPLE references for the proposed DFCN cosegmentation on the PET-CT images. The average DSCs on CT and PET are 0.861 ± 0.037 and 0.828 ± 0.087, respectively, using DFCN, compared to 0.638 ± 0.165 and 0.643 ± 0.141, respectively, when using the graph-based cosegmentation method. The proposed DFCN cosegmentation using both PET and CT also outperforms the deep learning method using either PET or CT alone.

CONCLUSIONS

The proposed DFCN cosegmentation is able to outperform existing graph-based segmentation methods. The proposed DFCN cosegmentation shows promise for further integration with quantitative multimodality imaging tools in clinical trials.

Active contour algorithm with discriminant analysis for delineating tumors in positron emission tomography

In the context of cancer delineation using positron emission tomography datasets, we present an innovative approach which purpose is to tackle the real-time, three-dimensional segmentation task in a full, or at least nearly full automatized way. The approach comprises a preliminary initialization phase where the user highlights a region of interest around the cancer on just one slice of the tomographic dataset. The algorithm takes care of identifying an optimal and user-independent region of interest around the anomalous tissue and located on the slice containing the highest standardized uptake value so to start the successive segmentation task. The three-dimensional volume is then reconstructed using a slice-by-slice marching approach until a suitable automatic stop condition is met. On each slice, the segmentation is performed using an enhanced local active contour based on the minimization of a novel energy functional which combines the information provided by a machine learning component, the discriminant analysis in the present study. As a result, the whole algorithm is almost completely automatic and the output segmentation is independent from the input provided by the user. Phantom experiments comprising spheres and zeolites, and clinical cases comprising various body districts (lung, brain, and head and neck), and two different radio-tracers (18 F-fluoro-2-deoxy-d-glucose, and 11C-labeled Methionine) were used to assess the algorithm performances. Phantom experiments with spheres and with zeolites showed a dice similarity coefficient above 90% and 80%, respectively. Clinical cases showed high agreement with the gold standard (R² = 0.98). These results indicate that the proposed method can be efficiently applied in the clinical routine with potential benefit for the treatment response assessment, and targeting in radiotherapy.

Impact of 90Y PET gradient-based tumor segmentation on voxel-level dosimetry in liver radioembolization

BACKGROUND

The purpose was to validate ⁹⁰Y PET gradient-based tumor segmentation in phantoms and to evaluate the impact of the segmentation method on reported tumor absorbed dose (AD) and biological effective dose (BED) in ⁹⁰Y microsphere radioembolization (RE) patients. A semi-automated gradient-based method was applied to phantoms and patient tumors on the ⁹⁰Y PET with the initial bounding volume for gradient detection determined from a registered diagnostic CT or MR; this PET-based segmentation (PS) was compared with radiologist-defined morphologic segmentation (MS) on CT or MRI. AD and BED volume histogram metrics (D90, D70, mean) were calculated using both segmentations and concordance/correlations were investigated. Spatial concordance was assessed using Dice similarity coefficient (DSC) and mean distance to agreement (MDA). PS was repeated to assess intra-observer variability.

RESULTS

In phantoms, PS demonstrated high accuracy in lesion volumes (within 15%), AD metrics (within 11%), high spatial concordance relative to morphologic segmentation (DSC > 0.86 and MDA < 1.5 mm), and low intra-observer variability (DSC > 0.99, MDA < 0.2 mm, AD/BED metrics within 2%). For patients (58 lesions), spatial concordance between PS and MS was degraded compared to in-phantom (average DSC = 0.54, average MDA = 4.8 mm); the average mean tumor AD was 226 ± 153 and 197 ± 138 Gy, respectively for PS and MS. For patient AD metrics, the best Pearson correlation (r) and concordance correlation coefficient (ccc) between segmentation methods was found for mean AD (r = 0.94, ccc = 0.92), but worsened as the metric approached the minimum dose (for D90, r = 0.77, ccc = 0.69); BED metrics exhibited a similar trend. Patient PS showed low intra-observer variability (average DSC = 0.81, average MDA = 2.2 mm, average AD/BED metrics within 3.0%).

CONCLUSIONS

⁹⁰Y PET gradient-based segmentation led to accurate/robust results in phantoms, and showed high concordance with MS for reporting mean tumor AD/BED in patients. However, tumor coverage metrics such as D90 exhibited worse concordance between segmentation methods, highlighting the need to standardize segmentation methods when reporting AD/BED metrics from post-therapy ⁹⁰Y PET. Estimated differences in reported AD/BED metrics due to segmentation method will be useful for interpreting RE dosimetry results in the literature including tumor response data.

The Use of Quantitative Imaging in Radiation Oncology: A Quantitative Imaging Network (QIN) Perspective

Modern radiation therapy is delivered with great precision, in part by relying on high-resolution multidimensional anatomic imaging to define targets in space and time. The development of quantitative imaging (QI) modalities capable of monitoring biologic parameters could provide deeper insight into tumor biology and facilitate more personalized clinical decision-making. The Quantitative Imaging Network (QIN) was established by the National Cancer Institute to advance and validate these QI modalities in the context of oncology clinical trials. In particular, the QIN has significant interest in the application of QI to widen the therapeutic window of radiation therapy. QI modalities have great promise in radiation oncology and will help address significant clinical needs, including finer prognostication, more specific target delineation, reduction of normal tissue toxicity, identification of radioresistant disease, and clearer interpretation of treatment response. Patient-specific QI is being incorporated into radiation treatment design in ways such as dose escalation and adaptive replanning, with the intent of improving outcomes while lessening treatment morbidities. This review discusses the current vision of the QIN, current areas of investigation, and how the QIN hopes to enhance the integration of QI into the practice of radiation oncology.

External validation of a prognostic model incorporating quantitative PET image features in oesophageal cancer

AIM

Enhanced prognostic models are required to improve risk stratification of patients with oesophageal cancer so treatment decisions can be optimised. The primary aim was to externally validate a published prognostic model incorporating PET image features. Transferability of the model was compared using only clinical variables.

METHODS

This was a Transparent Reporting of a multivariate prediction model for Individual Prognosis Or Diagnosis (TRIPOD) type 3 study. The model was validated against patients treated with neoadjuvant chemoradiotherapy according to the Neoadjuvant chemoradiotherapy plus surgery versus surgery alone for oesophageal or junctional cancer (CROSS) trial regimen using pre- and post-harmonised image features. The Kaplan-Meier method with log-rank significance tests assessed risk strata discrimination. A Cox proportional hazards model assessed model calibration. Primary outcome was overall survival (OS).

RESULTS

Between 2010 and 2015, 449 patients were included in the development (n = 302), internal validation (n = 101) and external validation (n = 46) cohorts. No statistically significant difference in OS between patient quartiles was demonstrated in prognostic models incorporating PET image features (X² = 1.42, df = 3, p = 0.70) or exclusively clinical variables (age, disease stage and treatment; X² = 1.19, df = 3, p = 0.75). The calibration slope β of both models was not significantly different from unity (p = 0.29 and 0.29, respectively). Risk groups defined using only clinical variables suggested differences in OS, although these were not statistically significant (X² = 0.71, df = 2, p = 0.70).

CONCLUSION

The prognostic model did not enable significant discrimination between the validation risk groups, but a second model with exclusively clinical variables suggested some transferable prognostic ability. PET harmonisation did not significantly change the results of model validation.

Variability and Repeatability of Quantitative Uptake Metrics in 18F-FDG PET/CT of Non-Small Cell Lung Cancer: Impact of Segmentation Method, Uptake Interval, and Reconstruction Protocol

There is increased interest in various new quantitative uptake metrics beyond SUV in oncologic PET/CT studies. The purpose of this study was to investigate the variability and test-retest ratio (TRT) of metabolically active tumor volume (MATV) measurements and several other new quantitative metrics in non-small cell lung cancer using ¹⁸F-FDG PET/CT with different segmentation methods, user interactions, uptake intervals, and reconstruction protocols. Methods: Ten patients with advanced non-small cell lung cancer received 2 series of 2 whole-body ¹⁸F-FDG PET/CT scans at 60 min after injection and at 90 min after injection. PET data were reconstructed with 4 different protocols. Eight segmentation methods were applied to delineate lesions with and without a tumor mask. MATV, SUV_max, SUV_mean, total lesion glycolysis, and intralesional heterogeneity features were derived. Variability and repeatability were evaluated using a generalized-estimating-equation statistical model with Bonferroni adjustment for multiple comparisons. The statistical model, including interaction between uptake interval and reconstruction protocol, was applied individually to the data obtained from each segmentation method. Results: Without masking, none of the segmentation methods could delineate all lesions correctly. MATV was affected by both uptake interval and reconstruction settings for most segmentation methods. Similar observations were obtained for the uptake metrics SUV_max, SUV_mean, total lesion glycolysis, homogeneity, entropy, and zone percentage. No effect of uptake interval was observed on TRT metrics, whereas the reconstruction protocol affected the TRT of SUV_max Overall, segmentation methods showing poor quantitative performance in one condition showed better performance in other (combined) conditions. For some metrics, a clear statistical interaction was found between the segmentation method and both uptake interval and reconstruction protocol. Conclusion: All segmentation results need to be reviewed critically. MATV and other quantitative uptake metrics, as well as their TRT, depend on segmentation method, uptake interval, and reconstruction protocol. To obtain quantitative reliable metrics, with good TRT performance, the optimal segmentation method depends on local imaging procedure, the PET/CT system, or reconstruction protocol. Rigid harmonization of imaging procedure and PET/CT performance will be helpful in mitigating this variability.

Novel Quantitative PET Techniques for Clinical Decision Support in Oncology

Quantitative image analysis has deep roots in the usage of positron emission tomography (PET) in clinical and research settings to address a wide variety of diseases. It has been extensively employed to assess molecular and physiological biomarkers in vivo in healthy and disease states, in oncology, cardiology, neurology, and psychiatry. Quantitative PET allows relating the time-varying activity concentration in tissues/organs of interest and the basic functional parameters governing the biological processes being studied. Yet, quantitative PET is challenged by a number of degrading physical factors related to the physics of PET imaging, the limitations of the instrumentation used, and the physiological status of the patient. Moreover, there is no consensus on the most reliable and robust image-derived PET metric(s) that can be used with confidence in clinical oncology owing to the discrepancies between the conclusions reported in the literature. There is also increasing interest in the use of artificial intelligence based techniques, particularly machine learning and deep learning techniques in a variety of applications to extract quantitative features (radiomics) from PET including image segmentation and outcome prediction in clinical oncology. These novel techniques are revolutionizing clinical practice and are now offering unique capabilities to the clinical molecular imaging community and biomedical researchers at large. In this report, we summarize recent developments and future tendencies in quantitative PET imaging and present example applications in clinical decision support to illustrate its potential in the context of clinical oncology.

A smart and operator independent system to delineate tumours in Positron Emission Tomography scans

Positron Emission Tomography (PET) imaging has an enormous potential to improve radiation therapy treatment planning offering complementary functional information with respect to other anatomical imaging approaches. The aim of this study is to develop an operator independent, reliable, and clinically feasible system for biological tumour volume delineation from PET images. Under this design hypothesis, we combine several known approaches in an original way to deploy a system with a high level of automation. The proposed system automatically identifies the optimal region of interest around the tumour and performs a slice-by-slice marching local active contour segmentation. It automatically stops when a "cancer-free" slice is identified. User intervention is limited at drawing an initial rough contour around the cancer region. By design, the algorithm performs the segmentation minimizing any dependence from the initial input, so that the final result is extremely repeatable. To assess the performances under different conditions, our system is evaluated on a dataset comprising five synthetic experiments and fifty oncological lesions located in different anatomical regions (i.e. lung, head and neck, and brain) using PET studies with 18F-fluoro-2-deoxy-d-glucose and 11C-labeled Methionine radio-tracers. Results on synthetic lesions demonstrate enhanced performances when compared against the most common PET segmentation methods. In clinical cases, the proposed system produces accurate segmentations (average dice similarity coefficient: 85.36 ± 2.94%, 85.98 ± 3.40%, 88.02 ± 2.75% in the lung, head and neck, and brain district, respectively) with high agreement with the gold standard (determination coefficient R² = 0.98). We believe that the proposed system could be efficiently used in the everyday clinical routine as a medical decision tool, and to provide the clinicians with additional information, derived from PET, which can be of use in radiation therapy, treatment, and planning.

Textural features of cervical cancers on FDG-PET/CT associate with survival and local relapse in patients treated with definitive chemoradiotherapy

We retrospectively reviewed the records of 142 patients with stage IB–IIIB cervical cancer who underwent ¹⁸F-FDG-PET/CT before external beam radiotherapy plus intracavitary brachytherapy and concurrent chemotherapy. The patients were divided into training and validation cohorts to confirm the reliability of predictors for recurrence. Kaplan–Meier analysis was performed and a Cox regression model was used to examine the effects of variables on overall survival (OS), progression-free survival (PFS), distant metastasis-free survival (DMFS), and pelvic relapse-free survival (PRFS). High gray-level run emphasis (HGRE) derived from gray-level run-length matrix most accurately and consistently predicted the presence of pelvic residual or recurrent tumors for both cohorts. In multivariate analysis, stages IIIA–IIIB (P = 0.001, hazard ratio [HR] = 4.07) and a low HGRE (P < 0.0001, HR = 4.34) were prognostic factors for low OS, whereas a low HGRE (P = 0.001, HR = 2.86) and nonsquamous cell histology (P = 0.003, HR = 2.76) were prognostic factors for inferior PFS. The nonsquamous cell histology (P < 0.0001, HR = 9.19) and a low HGRE (P = 0.001, HR = 4.69) were predictors for low PRFS. In cervical cancer patients receiving definitive chemoradiotherapy, pretreatment textural features on ¹⁸F-FDG-PET/CT can supplement the prognostic information.

The developing role of FDG PET imaging for prognostication and radiotherapy target volume delineation in non-small cell lung cancer

Advancements in functional imaging technology have allowed new possibilities in contouring of target volumes, monitoring therapy, and predicting treatment outcome in non-small cell lung cancer (NSCLC). Consequently, the role of ¹⁸F-fluorodeoxyglucose positron emission tomography (FDG PET) has expanded in the last decades from a stand-alone diagnostic tool to a versatile instrument integrated with computed tomography (CT), with a prominent role in lung cancer radiotherapy. This review outlines the most recent literature on developments in FDG PET imaging for prognostication and radiotherapy target volume delineation (TVD) in NSCLC. We also describe the challenges facing the clinical implementation of these developments and present new ideas for future research.

Comparison of SUVmax and SUVpeak based segmentation to determine primary lung tumour volume on FDG PET-CT correlated with pathology data

PURPOSE

The aim of the study was to compare simple SUVmax and SUVpeak based segmentation methods for calculating the lung tumour volume, compared to a pathology ground truth.

METHODS

Thirty patients diagnosed with early stage Non-Small Cell lung cancer (NSCLC) underwent surgical resection in the Netherlands between 2006 and 2008. FDG PET-CT scans for these patients were acquired within a median of 20 days before surgery. The tumour volume for each percentage SUVmax and SUVpeak threshold, with and without background correction, was calculated for each patient. The percentage threshold that provided the tumour volume that corresponded best with the pathology volume was considered to be the optimal threshold. The optimal thresholds were plotted as a function of tumour volume using a power law function and cross validated using the leave-one-out technique.

RESULTS

The mean optimal percentage threshold was 50% ± 10% and 62% ± 15% for the SUVmax and SUVpeak without background correction respectively and 47% ± 10% and 60 ± 15% for the SUVmax and SUVpeak with background correction respectively. The optimal threshold curves could be fitted well with power law function. After cross validation the correlation between the effective tumour diameter in pathology and autosegmentation was 0.900 and 0.905 for the SUVmax and SUVpeak without background correction respectively and 0.913 and 0.908 for the SUVmax and SUVpeak with background correction respectively.

CONCLUSION

No benefit was shown on clinical data for the SUVpeak based segmentation method over a SUVmax based one. Both methods can be used to determine the tumour volumes in resected NSCLC tumours.

Molecular Imaging-Guided Radiotherapy for the Treatment of Head-and-Neck Squamous Cell Carcinoma: Does it Fulfill the Promises?

With the routine use of intensity modulated radiation therapy for the treatment of head-and-neck squamous cell carcinoma allowing highly conformed dose distribution, there is an increasing need for refining both the selection and the delineation of gross tumor volumes (GTV). In this framework, molecular imaging with positron emission tomography and magnetic resonance imaging offers the opportunity to improve diagnostic accuracy and to integrate tumor biology mainly related to the assessment of tumor cell density, tumor hypoxia, and tumor proliferation into the treatment planning equation. Such integration, however, requires a deep comprehension of the technical and methodological issues related to image acquisition, reconstruction, and segmentation. Until now, molecular imaging has had a limited value for the selection of nodal GTV, but there are increasing evidences that both FDG positron emission tomography and diffusion-weighted magnetic resonance imaging has a potential value for the delineation of the primary tumor GTV, effecting on dose distribution. With the apprehension of the heterogeneity in tumor biology through molecular imaging, growing evidences have been collected over the years to support the concept of dose escalation/dose redistribution using a planned heterogeneous dose prescription, the so-called "dose painting" approach. Validation trials are ongoing, and in the coming years, one may expect to position the dose painting approach in the armamentarium for the treatment of patients with head-and-neck squamous cell carcinoma.

Radiomics in Nuclear Medicine Applied to Radiation Therapy: Methods, Pitfalls, and Challenges

Radiomics is a recent area of research in precision medicine and is based on the extraction of a large variety of features from medical images. In the field of radiation oncology, comprehensive image analysis is crucial to personalization of treatments. A better characterization of local heterogeneity and the shape of the tumor, depicting individual cancer aggressiveness, could guide dose planning and suggest volumes in which a higher dose is needed for better tumor control. In addition, noninvasive imaging features that could predict treatment outcome from baseline scans could help the radiation oncologist to determine the best treatment strategies and to stratify patients as at low risk or high risk of recurrence. Nuclear medicine molecular imaging reflects information regarding biological processes in the tumor thanks to a wide range of radiotracers. Many studies involving ¹⁸F-fluorodeoxyglucose positron emission tomography suggest an added value of radiomics compared with the use of conventional PET metrics such as standardized uptake value for both tumor diagnosis and prediction of recurrence or treatment outcome. However, these promising results should not hide technical difficulties that still currently prevent the approach from being widely studied or clinically used. These difficulties mostly pertain to the variability of the imaging features as a function of the acquisition device and protocol, the robustness of the models with respect to that variability, and the interpretation of the radiomic models. Addressing the impact of the variability in acquisition and reconstruction protocols is needed, as is harmonizing the radiomic feature calculation methods, to ensure the reproducibility of studies in a multicenter context and their implementation in a clinical workflow. In this review, we explain the potential impact of positron emission tomography radiomics for radiation therapy and underline the various aspects that need to be carefully addressed to make the most of this promising approach.

Automatic lesion detection and segmentation of 18F-FET PET in gliomas: A full 3D U-Net convolutional neural network study

INTRODUCTION

Amino-acids positron emission tomography (PET) is increasingly used in the diagnostic workup of patients with gliomas, including differential diagnosis, evaluation of tumor extension, treatment planning and follow-up. Recently, progresses of computer vision and machine learning have been translated for medical imaging. Aim was to demonstrate the feasibility of an automated 18F-fluoro-ethyl-tyrosine (18F-FET) PET lesion detection and segmentation relying on a full 3D U-Net Convolutional Neural Network (CNN).

METHODS

All dynamic 18F-FET PET brain image volumes were temporally realigned to the first dynamic acquisition, coregistered and spatially normalized onto the Montreal Neurological Institute template. Ground truth segmentations were obtained using manual delineation and thresholding (1.3 x background). The volumetric CNN was implemented based on a modified Keras implementation of a U-Net library with 3 layers for the encoding and decoding paths. Dice similarity coefficient (DSC) was used as an accuracy measure of segmentation.

RESULTS

Thirty-seven patients were included (26 [70%] in the training set and 11 [30%] in the validation set). All 11 lesions were accurately detected with no false positive, resulting in a sensitivity and a specificity for the detection at the tumor level of 100%. After 150 epochs, DSC reached 0.7924 in the training set and 0.7911 in the validation set. After morphological dilatation and fixed thresholding of the predicted U-Net mask a substantial improvement of the DSC to 0.8231 (+ 4.1%) was noted. At the voxel level, this segmentation led to a 0.88 sensitivity [95% CI, 87.1 to, 88.2%] a 0.99 specificity [99.9 to 99.9%], a 0.78 positive predictive value: [76.9 to 78.3%], and a 0.99 negative predictive value [99.9 to 99.9%].

CONCLUSIONS

With relatively high performance, it was proposed the first full 3D automated procedure for segmentation of 18F-FET PET brain images of patients with different gliomas using a U-Net CNN architecture.

Evaluation of prognostic models developed using standardised image features from different PET automated segmentation methods

Background

Prognosis in oesophageal cancer (OC) is poor. The 5-year overall survival (OS) rate is approximately 15%. Personalised medicine is hoped to increase the 5- and 10-year OS rates. Quantitative analysis of PET is gaining substantial interest in prognostic research but requires the accurate definition of the metabolic tumour volume. This study compares prognostic models developed in the same patient cohort using individual PET segmentation algorithms and assesses the impact on patient risk stratification.

Consecutive patients (n = 427) with biopsy-proven OC were included in final analysis. All patients were staged with PET/CT between September 2010 and July 2016. Nine automatic PET segmentation methods were studied. All tumour contours were subjectively analysed for accuracy, and segmentation methods with < 90% accuracy were excluded. Standardised image features were calculated, and a series of prognostic models were developed using identical clinical data. The proportion of patients changing risk classification group were calculated.

Results

Out of nine PET segmentation methods studied, clustering means (KM2), general clustering means (GCM3), adaptive thresholding (AT) and watershed thresholding (WT) methods were included for analysis. Known clinical prognostic factors (age, treatment and staging) were significant in all of the developed prognostic models. AT and KM2 segmentation methods developed identical prognostic models. Patient risk stratification was dependent on the segmentation method used to develop the prognostic model with up to 73 patients (17.1%) changing risk stratification group.

Conclusion

Prognostic models incorporating quantitative image features are dependent on the method used to delineate the primary tumour. This has a subsequent effect on risk stratification, with patients changing groups depending on the image segmentation method used.

Electronic supplementary material

The online version of this article (10.1186/s13550-018-0379-3) contains supplementary material, which is available to authorized users.

Biological imaging for individualized therapy in radiation oncology: part I physical and technical aspects

Recently, there has been an increase in the imaging modalities available for radiotherapy planning and radiotherapy prognostic outcome: dual energy computed tomography (CT), dynamic contrast enhanced CT, dynamic contrast enhanced magnetic resonance imaging (MRI), diffusion-weighted MRI, positron emission tomography-CT, dynamic contrast enhanced ultrasound, MR spectroscopy and positron emission tomography-MR. These techniques enable more precise gross tumor volume definition than CT alone and moreover allow subvolumes within the gross tumor volume to be defined which may be given a boost dose or an individual voxelized dose prescription may be derived. With increased plan complexity care must be taken to immobilize the patient in an accurate and reproducible manner. Moreover the physical and technical limitations of the entire treatment planning chain need to be well characterized and understood, interdisciplinary collaboration ameliorated (physicians and physicists within nuclear medicine, radiology and radiotherapy) and image protocols standardized.

The first MICCAI challenge on PET tumor segmentation

INTRODUCTION

Automatic functional volume segmentation in PET images is a challenge that has been addressed using a large array of methods. A major limitation for the field has been the lack of a benchmark dataset that would allow direct comparison of the results in the various publications. In the present work, we describe a comparison of recent methods on a large dataset following recommendations by the American Association of Physicists in Medicine (AAPM) task group (TG) 211, which was carried out within a MICCAI (Medical Image Computing and Computer Assisted Intervention) challenge.

MATERIALS AND METHODS

Organization and funding was provided by France Life Imaging (FLI). A dataset of 176 images combining simulated, phantom and clinical images was assembled. A website allowed the participants to register and download training data (n = 19). Challengers then submitted encapsulated pipelines on an online platform that autonomously ran the algorithms on the testing data (n = 157) and evaluated the results. The methods were ranked according to the arithmetic mean of sensitivity and positive predictive value.

RESULTS

Sixteen teams registered but only four provided manuscripts and pipeline(s) for a total of 10 methods. In addition, results using two thresholds and the Fuzzy Locally Adaptive Bayesian (FLAB) were generated. All competing methods except one performed with median accuracy above 0.8. The method with the highest score was the convolutional neural network-based segmentation, which significantly outperformed 9 out of 12 of the other methods, but not the improved K-Means, Gaussian Model Mixture and Fuzzy C-Means methods.

CONCLUSION

The most rigorous comparative study of PET segmentation algorithms to date was carried out using a dataset that is the largest used in such studies so far. The hierarchy amongst the methods in terms of accuracy did not depend strongly on the subset of datasets or the metrics (or combination of metrics). All the methods submitted by the challengers except one demonstrated good performance with median accuracy scores above 0.8.

Prediction of outcome using pretreatment 18F-FDG PET/CT and MRI radiomics in locally advanced cervical cancer treated with chemoradiotherapy

PURPOSE

The aim of this study is to determine if radiomics features from ¹⁸fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT) and magnetic resonance imaging (MRI) images could contribute to prognoses in cervical cancer.

METHODS

One hundred and two patients (69 for training and 33 for testing) with locally advanced cervical cancer (LACC) receiving chemoradiotherapy (CRT) from 08/2010 to 12/2016 were enrolled in this study. ¹⁸F-FDG PET/CT and MRI examination [T1, T2, T1C, diffusion-weighted imaging (DWI)] were performed for each patient before CRT. Primary tumor volumes were delineated with the fuzzy locally adaptive Bayesian algorithm in the PET images and with 3D Slicer™ in the MRI images. Radiomics features (intensity, shape, and texture) were extracted and their prognostic value was compared with clinical parameters for recurrence-free and locoregional control.

RESULTS

In the training cohort, median follow-up was 3.0 years (range, 0.43-6.56 years) and relapse occurred in 36% of patients. In univariate analysis, FIGO stage (I-II vs. III-IV) and metabolic response (complete vs. non-complete) were probably associated with outcome without reaching statistical significance, contrary to several radiomics features from both PET and MRI sequences. Multivariate analysis in training test identified Grey Level Non Uniformity_GLRLM in PET and Entropy_GLCM in ADC maps from DWI MRI as independent prognostic factors. These had significantly higher prognostic power than clinical parameters, as evaluated in the testing cohort with accuracy of 94% for predicting recurrence and 100% for predicting lack of loco-regional control (versus ~50-60% for clinical parameters).

CONCLUSIONS

In LACC treated with CRT, radiomics features such as EntropyGLCM and GLNUGLRLM from functional imaging DWI-MRI and PET, respectively, are independent predictors of recurrence and loco-regional control with significantly higher prognostic power than usual clinical parameters. Further research is warranted for their validation, which may justify more aggressive treatment in patients identified with high probability of recurrence.

Anatomic, functional and molecular imaging in lung cancer precision radiation therapy: treatment response assessment and radiation therapy personalization

This article reviews key imaging modalities for lung cancer patients treated with radiation therapy (RT) and considers their actual or potential contributions to critical decision-making. An international group of researchers with expertise in imaging in lung cancer patients treated with RT considered the relevant literature on modalities, including computed tomography (CT), magnetic resonance imaging (MRI) and positron emission tomography (PET). These perspectives were coordinated to summarize the current status of imaging in lung cancer and flag developments with future implications. Although there are no useful randomized trials of different imaging modalities in lung cancer, multiple prospective studies indicate that management decisions are frequently impacted by the use of complementary imaging modalities, leading both to more appropriate treatments and better outcomes. This is especially true of ¹⁸F-fluoro-deoxyglucose (FDG)-PET/CT which is widely accepted to be the standard imaging modality for staging of lung cancer patients, for selection for potentially curative RT and for treatment planning. PET is also more accurate than CT for predicting survival after RT. PET imaging during RT is also correlated with survival and makes response-adapted therapies possible. PET tracers other than FDG have potential for imaging important biological process in tumors, including hypoxia and proliferation. MRI has superior accuracy in soft tissue imaging and the MRI Linac is a rapidly developing technology with great potential for online monitoring and modification of treatment. The role of imaging in RT-treated lung cancer patients is evolving rapidly and will allow increasing personalization of therapy according to the biology of both the tumor and dose limiting normal tissues.

Tumour functional sphericity from PET images: prognostic value in NSCLC and impact of delineation method

PURPOSE

Sphericity has been proposed as a parameter for characterizing PET tumour volumes, with complementary prognostic value with respect to SUV and volume in both head and neck cancer and lung cancer. The objective of the present study was to investigate its dependency on tumour delineation and the resulting impact on its prognostic value.

METHODS

Five segmentation methods were considered: two thresholds (40% and 50% of SUV_max), ant colony optimization, fuzzy locally adaptive Bayesian (FLAB), and gradient-aided region-based active contour. The accuracy of each method in extracting sphericity was evaluated using a dataset of 176 simulated, phantom and clinical PET images of tumours with associated ground truth. The prognostic value of sphericity and its complementary value with respect to volume for each segmentation method was evaluated in a cohort of 87 patients with stage II/III lung cancer.

RESULTS

Volume and associated sphericity values were dependent on the segmentation method. The correlation between segmentation accuracy and sphericity error was moderate (|ρ| from 0.24 to 0.57). The accuracy in measuring sphericity was not dependent on volume (|ρ| < 0.4). In the patients with lung cancer, sphericity had prognostic value, although lower than that of volume, except for that derived using FLAB for which when combined with volume showed a small improvement over volume alone (hazard ratio 2.67, compared with 2.5). Substantial differences in patient prognosis stratification were observed depending on the segmentation method used.

CONCLUSION

Tumour functional sphericity was found to be dependent on the segmentation method, although the accuracy in retrieving the true sphericity was not dependent on tumour volume. In addition, even accurate segmentation can lead to an inaccurate sphericity value, and vice versa. Sphericity had similar or lower prognostic value than volume alone in the patients with lung cancer, except when determined using the FLAB method for which there was a small improvement in stratification when the parameters were combined.

Delineation of the primary tumour Clinical Target Volumes (CTV-P) in laryngeal, hypopharyngeal, oropharyngeal and oral cavity squamous cell carcinoma: AIRO, CACA, DAHANCA, EORTC, GEORCC, GORTEC, HKNPCSG, HNCIG, IAG-KHT, LPRHHT, NCIC CTG, NCRI, NRG Oncology, PHNS, SBRT, SOMERA, SRO, SSHNO, TROG consensus guidelines

PURPOSE

Few studies have reported large inter-observer variations in target volume selection and delineation in patients treated with radiotherapy for head and neck squamous cell carcinoma. Consensus guidelines have been published for the neck nodes (see Grégoire et al., 2003, 2014), but such recommendations are lacking for primary tumour delineation. For the latter, two main schools of thoughts are prevailing, one based on geometric expansion of the Gross Tumour Volume (GTV) as promoted by DAHANCA, and the other one based on anatomical expansion of the GTV using compartmentalization of head and neck anatomy.

METHOD

For each anatomic location within the larynx, hypopharynx, oropharynx and oral cavity, and for each T-stage, the DAHANCA proposal has been comprehensively reviewed and edited to include anatomic knowledge into the geometric Clinical Target Volume (CTV) delineation concept. A first proposal was put forward by the leading authors of this publication (VG and CG) and discussed with opinion leaders in head and neck radiation oncology from Europe, Asia, Australia/New Zealand, North America and South America to reach a worldwide consensus.

RESULTS

This consensus proposes two CTVs for the primary tumour, the so called CTV-P1 and CVT-P2, corresponding to a high and lower tumour burden, and which should be associated with a high and a lower dose prescription, respectively.

CONCLUSION

Implementation of these guidelines in the daily practice of radiation oncology should contribute to reduce treatment variations from clinicians to clinicians, facilitate the conduct of multi-institutional clinical trials, and contribute to improved care of patients with head and neck carcinoma.

Towards enhanced PET quantification in clinical oncology

Positron emission tomography (PET) has, since its inception, established itself as the imaging modality of choice for the in vivo quantitative assessment of molecular targets in a wide range of biochemical processes underlying tumour physiology. PET image quantification enables to ascertain a direct link between the time-varying activity concentration in organs/tissues and the fundamental parameters portraying the biological processes at the cellular level being assessed. However, the quantitative potential of PET may be affected by a number of factors related to physical effects, hardware and software system specifications, tracer kinetics, motion, scan protocol design and limitations in current image-derived PET metrics. Given the relatively large number of PET metrics reported in the literature, the selection of the best metric for fulfilling a specific task in a particular application is still a matter of debate. Quantitative PET has advanced elegantly during the last two decades and is now reaching the maturity required for clinical exploitation, particularly in oncology where it has the capability to open many avenues for clinical diagnosis, assessment of response to treatment and therapy planning. Therefore, the preservation and further enhancement of the quantitative features of PET imaging is crucial to ensure that the full clinical value of PET imaging modality is utilized in clinical oncology. Recent advancements in PET technology and methodology have paved the way for faster PET acquisitions of enhanced sensitivity to support the clinical translation of highly quantitative four-dimensional (4D) parametric imaging methods in clinical oncology. In this report, we provide an overview of recent advances and future trends in quantitative PET imaging in the context of clinical oncology. The pros/cons of the various image-derived PET metrics will be discussed and the promise of novel methodologies will be highlighted.

Structure and location preserving topological representation with applications on CT segmentation

Contour tree represents the nesting relations of the individual components in the image; however, it neglects the geometric structure of the terrain. In this paper, we propose a new topological representation that provides the nesting and spatial relations of regions for CT image interpretation. The tree is constructed based on the signed distance transformation of binary CT image, and combines intensity based contour tree and a new gradient based topology tree. We also investigate the application of the topological representation as a constraint in target object segmentation. Ten non-small cell lung tumor CT studies were used for segmentation accuracy evaluation. The image representation results showed that the proposed tree structure retained the nesting and spatial relations of the tissues or objects in the CT image. The segmentation results demonstrated its usability in the separation of adjacent objects with similar intensity distributions.

A framework based on hidden Markov trees for multimodal PET/CT image co-segmentation

PURPOSE

The purpose of this study was to investigate the use of a probabilistic quad-tree graph (hidden Markov tree, HMT) to provide fast computation, robustness and an interpretational framework for multimodality image processing and to evaluate this framework for single gross tumor target (GTV) delineation from both positron emission tomography (PET) and computed tomography (CT) images.

METHODS

We exploited joint statistical dependencies between hidden states to handle the data stack using multi-observation, multi-resolution of HMT and Bayesian inference. This framework was applied to segmentation of lung tumors in PET/CT datasets taking into consideration simultaneously the CT and the PET image information. PET and CT images were considered using either the original voxels intensities, or after wavelet/contourlet enhancement. The Dice similarity coefficient (DSC), sensitivity (SE), positive predictive value (PPV) were used to assess the performance of the proposed approach on one simulated and 15 clinical PET/CT datasets of non-small cell lung cancer (NSCLC) cases. The surrogate of truth was a statistical consensus (obtained with the Simultaneous Truth and Performance Level Estimation algorithm) of three manual delineations performed by experts on fused PET/CT images. The proposed framework was applied to PET-only, CT-only and PET/CT datasets, and were compared to standard and improved fuzzy c-means (FCM) multimodal implementations.

RESULTS

A high agreement with the consensus of manual delineations was observed when using both PET and CT images. Contourlet-based HMT led to the best results with a DSC of 0.92 ± 0.11 compared to 0.89 ± 0.13 and 0.90 ± 0.12 for Intensity-based HMT and Wavelet-based HMT, respectively. Considering PET or CT only in the HMT led to much lower accuracy. Standard and improved FCM led to comparatively lower accuracy than HMT, even when considering multimodal implementations.

CONCLUSIONS

We evaluated the accuracy of the proposed HMT-based framework for PET/CT image segmentation. The proposed method reached good accuracy, especially with pre-processing in the contourlet domain.

Toward a standard for the evaluation of PET-Auto-Segmentation methods following the recommendations of AAPM task group No. 211: Requirements and implementation

Purpose

The aim of this paper is to define the requirements and describe the design and implementation of a standard benchmark tool for evaluation and validation of PET‐auto‐segmentation (PET‐AS) algorithms. This work follows the recommendations of Task Group 211 (TG211) appointed by the American Association of Physicists in Medicine (AAPM).

Methods

The recommendations published in the AAPM TG211 report were used to derive a set of required features and to guide the design and structure of a benchmarking software tool. These items included the selection of appropriate representative data and reference contours obtained from established approaches and the description of available metrics. The benchmark was designed in a way that it could be extendable by inclusion of bespoke segmentation methods, while maintaining its main purpose of being a standard testing platform for newly developed PET‐AS methods. An example of implementation of the proposed framework, named PETASset, was built. In this work, a selection of PET‐AS methods representing common approaches to PET image segmentation was evaluated within PETASset for the purpose of testing and demonstrating the capabilities of the software as a benchmark platform.

Results

A selection of clinical, physical, and simulated phantom data, including “best estimates” reference contours from macroscopic specimens, simulation template, and CT scans was built into the PETASset application database. Specific metrics such as Dice Similarity Coefficient (DSC), Positive Predictive Value (PPV), and Sensitivity (S), were included to allow the user to compare the results of any given PET‐AS algorithm to the reference contours. In addition, a tool to generate structured reports on the evaluation of the performance of PET‐AS algorithms against the reference contours was built. The variation of the metric agreement values with the reference contours across the PET‐AS methods evaluated for demonstration were between 0.51 and 0.83, 0.44 and 0.86, and 0.61 and 1.00 for DSC, PPV, and the S metric, respectively. Examples of agreement limits were provided to show how the software could be used to evaluate a new algorithm against the existing state‐of‐the art.

Conclusions

PETASset provides a platform that allows standardizing the evaluation and comparison of different PET‐AS methods on a wide range of PET datasets. The developed platform will be available to users willing to evaluate their PET‐AS methods and contribute with more evaluation datasets.

[18]Fluorodeoxyglucose Positron Emission Tomography for the Textural Features of Cervical Cancer Associated with Lymph Node Metastasis and Histological Type

BACKGROUND

In this study, we investigated the correlation between the lymph node (LN) status or histological types and textural features of cervical cancers on ¹⁸F-fluorodeoxyglucose positron emission tomography/computed tomography.

METHODS

We retrospectively reviewed the imaging records of 170 patients with International Federation of Gynecology and Obstetrics stage IB-IVA cervical cancer. Four groups of textural features were studied in addition to the maximum standardized uptake value (SUV_max), metabolic tumor volume, and total lesion glycolysis (TLG). Moreover, we studied the associations between the indices and clinical parameters, including the LN status, clinical stage, and histology. Receiver operating characteristic curves were constructed to evaluate the optimal predictive performance among the various textural indices. Quantitative differences were determined using the Mann-Whitney U test. Multivariate logistic regression analysis was performed to determine the independent factors, among all the variables, for predicting LN metastasis.

RESULTS

Among all the significant indices related to pelvic LN metastasis, homogeneity derived from the gray-level co-occurrence matrix (GLCM) was the sole independent predictor. By combining SUV_max, the risk of pelvic LN metastasis can be scored accordingly. The TLG_mean was the independent feature of positive para-aortic LNs. Quantitative differences between squamous and nonsquamous histology can be determined using short-zone emphasis (SZE) from the gray-level size zone matrix (GLSZM).

CONCLUSION

This study revealed that in patients with cervical cancer, pelvic or para-aortic LN metastases can be predicted by using textural feature of homogeneity from the GLCM and TLG_mean, respectively. SZE from the GLSZM is the sole feature associated with quantitative differences between squamous and nonsquamous histology.