Molecular PET/CT imaging-guided radiation therapy treatment planning

Deep Learning of radiology-genomics integration for computational oncology: A mini review

In the field of computational oncology, patient status is often assessed using radiology-genomics, which includes two key technologies and data, such as radiology and genomics. Recent advances in deep learning have facilitated the integration of radiology-genomics data, and even new omics data, significantly improving the robustness and accuracy of clinical predictions. These factors are driving artificial intelligence (AI) closer to practical clinical applications. In particular, deep learning models are crucial in identifying new radiology-genomics biomarkers and therapeutic targets, supported by explainable AI (xAI) methods. This review focuses on recent developments in deep learning for radiology-genomics integration, highlights current challenges, and outlines some research directions for multimodal integration and biomarker discovery of radiology-genomics or radiology-omics that are urgently needed in computational oncology.

A user-friendly deep learning application for accurate lung cancer diagnosis

BACKGROUND

Accurate diagnosis and subsequent delineated treatment planning require the experience of clinicians in the handling of their case numbers. However, applying deep learning in image processing is useful in creating tools that promise faster high-quality diagnoses, but the accuracy and precision of 3-D image processing from 2-D data may be limited by factors such as superposition of organs, distortion and magnification, and detection of new pathologies. The purpose of this research is to use radiomics and deep learning to develop a tool for lung cancer diagnosis.

METHODS

This study applies radiomics and deep learning in the diagnosis of lung cancer to help clinicians accurately analyze the images and thereby provide the appropriate treatment planning. 86 patients were recruited from Bach Mai Hospital, and 1012 patients were collected from an open-source database. First, deep learning has been applied in the process of segmentation by U-NET and cancer classification via the use of the DenseNet model. Second, the radiomics were applied for measuring and calculating diameter, surface area, and volume. Finally, the hardware also was designed by connecting between Arduino Nano and MFRC522 module for reading data from the tag. In addition, the displayed interface was created on a web platform using Python through Streamlit.

RESULTS

The applied segmentation model yielded a validation loss of 0.498, a train loss of 0.27, a cancer classification validation loss of 0.78, and a training accuracy of 0.98. The outcomes of the diagnostic capabilities of lung cancer (recognition and classification of lung cancer from chest CT scans) were quite successful.

CONCLUSIONS

The model provided means for storing and updating patients' data directly on the interface which allowed the results to be readily available for the health care providers. The developed system will improve clinical communication and information exchange. Moreover, it can manage efforts by generating correlated and coherent summaries of cancer diagnoses.

Deep Bayesian Quantization for Supervised Neuroimage Search

Neuroimage retrieval plays a crucial role in providing physicians with access to previous similar cases, which is essential for case-based reasoning and evidence-based medicine. Due to low computation and storage costs, hashing-based search techniques have been widely adopted for establishing image retrieval systems. However, these methods often suffer from nonnegligible quantization loss, which can degrade the overall search performance. To address this issue, this paper presents a compact coding solution namely Deep Bayesian Quantization (DBQ), which focuses on deep compact quantization that can estimate continuous neuroimage representations and achieve superior performance over existing hashing solutions. Specifically, DBQ seamlessly combines the deep representation learning and the representation compact quantization within a novel Bayesian learning framework, where a proxy embedding-based likelihood function is developed to alleviate the sampling issue for traditional similarity supervision. Additionally, a Gaussian prior is employed to reduce the quantization losses. By utilizing pre-computed lookup tables, the proposed DBQ can enable efficient and effective similarity search. Extensive experiments conducted on 2, 008 structural MRI scans from three benchmark neuroimage datasets demonstrate that our method outperforms previous state-of-the-arts.

Automated detection, delineation and quantification of whole-body bone metastasis using FDG-PET/CT images

Non-small cell lung cancer (NSCLC) patients with the metastatic spread of disease to the bone have high morbidity and mortality. Stereotactic ablative body radiotherapy increases the progression free survival and overall survival of these patients with oligometastases. FDG-PET/CT, a functional imaging technique combining positron emission tomography (PET) with 18 F-fluorodeoxyglucose (FDG) and computer tomography (CT) provides improved staging and identification of treatment response. It is also associated with reduction in size of the radiotherapy tumour volume delineation compared with CT based contouring in radiotherapy, thus allowing for dose escalation to the target volume with lower doses to the surrounding organs at risk. FDG-PET/CT is increasingly being used for the clinical management of NSCLC patients undergoing radiotherapy and has shown high sensitivity and specificity for the detection of bone metastases in these patients. Here, we present a software tool for detection, delineation and quantification of bone metastases using FDG-PET/CT images. The tool extracts standardised uptake values (SUV) from FDG-PET images for auto-segmentation of bone lesions and calculates volume of each lesion and associated mean and maximum SUV. The tool also allows automatic statistical validation of the auto-segmented bone lesions against the manual contours of a radiation oncologist. A retrospective review of FDG-PET/CT scans of more than 30 candidate NSCLC patients was performed and nine patients with one or more metastatic bone lesions were selected for the present study. The SUV threshold prediction model was designed by splitting the cohort of patients into a subset of 'development' and 'validation' cohorts. The development cohort yielded an optimum SUV threshold of 3.0 for automatic detection of bone metastases using FDG-PET/CT images. The validity of the derived optimum SUV threshold on the validation cohort demonstrated that auto-segmented and manually contoured bone lesions showed strong concordance for volume of bone lesion (r = 0.993) and number of detected lesions (r = 0.996). The tool has various applications in radiotherapy, including but not limited to studies determining optimum SUV threshold for accurate and standardised delineation of bone lesions and in scientific studies utilising large patient populations for instance for investigation of the number of metastatic lesions that can be treated safety with an ablative dose of radiotherapy without exceeding the normal tissue toxicity.

Clinical use of positron emission tomography for radiotherapy planning - Medical physics considerations

PET/CT imaging plays an increasing role in radiotherapy treatment planning. The aim of this article was to identify the major use cases and technical as well as medical physics challenges during integration of these data into treatment planning. Dedicated aspects, such as (i) PET/CT-based radiotherapy simulation, (ii) PET-based target volume delineation, (iii) functional avoidance to optimized organ-at-risk sparing and (iv) functionally adapted individualized radiotherapy are discussed in this article. Furthermore, medical physics aspects to be taken into account are summarized and presented in form of check-lists.

Decentralized Distributed Multi-institutional PET Image Segmentation Using a Federated Deep Learning Framework

PURPOSE

The generalizability and trustworthiness of deep learning (DL)-based algorithms depend on the size and heterogeneity of training datasets. However, because of patient privacy concerns and ethical and legal issues, sharing medical images between different centers is restricted. Our objective is to build a federated DL-based framework for PET image segmentation utilizing a multicentric dataset and to compare its performance with the centralized DL approach.

METHODS

PET images from 405 head and neck cancer patients from 9 different centers formed the basis of this study. All tumors were segmented manually. PET images converted to SUV maps were resampled to isotropic voxels (3 × 3 × 3 mm3) and then normalized. PET image subvolumes (12 × 12 × 12 cm3) consisting of whole tumors and background were analyzed. Data from each center were divided into train/validation (80% of patients) and test sets (20% of patients). The modified R2U-Net was used as core DL model. A parallel federated DL model was developed and compared with the centralized approach where the data sets are pooled to one server. Segmentation metrics, including Dice similarity and Jaccard coefficients, percent relative errors (RE%) of SUVpeak, SUVmean, SUVmedian, SUVmax, metabolic tumor volume, and total lesion glycolysis were computed and compared with manual delineations.

RESULTS

The performance of the centralized versus federated DL methods was nearly identical for segmentation metrics: Dice (0.84 ± 0.06 vs 0.84 ± 0.05) and Jaccard (0.73 ± 0.08 vs 0.73 ± 0.07). For quantitative PET parameters, we obtained comparable RE% for SUVmean (6.43% ± 4.72% vs 6.61% ± 5.42%), metabolic tumor volume (12.2% ± 16.2% vs 12.1% ± 15.89%), and total lesion glycolysis (6.93% ± 9.6% vs 7.07% ± 9.85%) and negligible RE% for SUVmax and SUVpeak. No significant differences in performance (P > 0.05) between the 2 frameworks (centralized vs federated) were observed.

CONCLUSION

The developed federated DL model achieved comparable quantitative performance with respect to the centralized DL model. Federated DL models could provide robust and generalizable segmentation, while addressing patient privacy and legal and ethical issues in clinical data sharing.

A Bayesian approach to tissue-fraction estimation for oncological PET segmentation

Tumor segmentation in oncological PET is challenging, a major reason being the partial-volume effects (PVEs) that arise due to low system resolution and finite voxel size. The latter results in tissue-fraction effects (TFEs), i.e. voxels contain a mixture of tissue classes. Conventional segmentation methods are typically designed to assign each image voxel as belonging to a certain tissue class. Thus, these methods are inherently limited in modeling TFEs. To address the challenge of accounting for PVEs, and in particular, TFEs, we propose a Bayesian approach to tissue-fraction estimation for oncological PET segmentation. Specifically, this Bayesian approach estimates the posterior mean of the fractional volume that the tumor occupies within each image voxel. The proposed method, implemented using a deep-learning-based technique, was first evaluated using clinically realistic 2D simulation studies with known ground truth, in the context of segmenting the primary tumor in PET images of patients with lung cancer. The evaluation studies demonstrated that the method accurately estimated the tumor-fraction areas and significantly outperformed widely used conventional PET segmentation methods, including a U-net-based method, on the task of segmenting the tumor. In addition, the proposed method was relatively insensitive to PVEs and yielded reliable tumor segmentation for different clinical-scanner configurations. The method was then evaluated using clinical images of patients with stage IIB/III non-small cell lung cancer from ACRIN 6668/RTOG 0235 multi-center clinical trial. Here, the results showed that the proposed method significantly outperformed all other considered methods and yielded accurate tumor segmentation on patient images with Dice similarity coefficient (DSC) of 0.82 (95% CI: 0.78, 0.86). In particular, the method accurately segmented relatively small tumors, yielding a high DSC of 0.77 for the smallest segmented cross-section of 1.30 cm². Overall, this study demonstrates the efficacy of the proposed method to accurately segment tumors in PET images.

Medical Image Retrieval Using Empirical Mode Decomposition with Deep Convolutional Neural Network

Content-based medical image retrieval (CBMIR) systems attempt to search medical image database to narrow the semantic gap in medical image analysis. The efficacy of high-level medical information representation using features is a major challenge in CBMIR systems. Features play a vital role in the accuracy and speed of the search process. In this paper, we propose a deep convolutional neural network- (CNN-) based framework to learn concise feature vector for medical image retrieval. The medical images are decomposed into five components using empirical mode decomposition (EMD). The deep CNN is trained in a supervised way with multicomponent input, and the learned features are used to retrieve medical images. The IRMA dataset, containing 11,000 X-ray images, 116 classes, is used to validate the proposed method. We achieve a total IRMA error of 43.21 and a mean average precision of 0.86 for retrieval task and IRMA error of 68.48 and F1 measure of 0.66 on classification task, which is the best result compared with existing literature for this dataset.

Artificial intelligence in radiotherapy

Artificial intelligence (AI) has already been implemented widely in the medical field in the recent years. This paper first reviews the background of AI and radiotherapy. Then it explores the basic concepts of different AI algorithms and machine learning methods, such as neural networks, that are available to us today and how they are being implemented in radiotherapy and diagnostic processes, such as medical imaging, treatment planning, patient simulation, quality assurance and radiation dose delivery. It also explores the ongoing research on AI methods that are to be implemented in radiotherapy in the future. The review shows very promising progress and future for AI to be widely used in various areas of radiotherapy. However, basing on various concerns such as availability and security of using big data, and further work on polishing and testing AI algorithms, it is found that we may not ready to use AI primarily in radiotherapy at the moment.

Medical Image Retrieval Using Multi-Texton Assignment

In this paper, we present a multi-texton representation method for medical image retrieval, which utilizes the locality constraint to encode each filter bank response within its local-coordinate system consisting of the k nearest neighbors in texton dictionary and subsequently employs spatial pyramid matching technique to implement feature vector representation. Comparison with the traditional nearest neighbor assignment followed by texton histogram statistics method, our strategies reduce the quantization errors in mapping process and add information about the spatial layout of texton distributions and, thus, increase the descriptive power of the image representation. We investigate the effects of different parameters on system performance in order to choose the appropriate ones for our datasets and carry out experiments on the IRMA-2009 medical collection and the mammographic patch dataset. The extensive experimental results demonstrate that the proposed method has superior performance.

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.

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

PURPOSE

The purpose of this educational report is to provide an overview of the present state-of-the-art PET auto-segmentation (PET-AS) algorithms and their respective validation, with an emphasis on providing the user with help in understanding the challenges and pitfalls associated with selecting and implementing a PET-AS algorithm for a particular application.

APPROACH

A brief description of the different types of PET-AS algorithms is provided using a classification based on method complexity and type. The advantages and the limitations of the current PET-AS algorithms are highlighted based on current publications and existing comparison studies. A review of the available image datasets and contour evaluation metrics in terms of their applicability for establishing a standardized evaluation of PET-AS algorithms is provided. The performance requirements for the algorithms and their dependence on the application, the radiotracer used and the evaluation criteria are described and discussed. Finally, a procedure for algorithm acceptance and implementation, as well as the complementary role of manual and auto-segmentation are addressed.

FINDINGS

A large number of PET-AS algorithms have been developed within the last 20 years. Many of the proposed algorithms are based on either fixed or adaptively selected thresholds. More recently, numerous papers have proposed the use of more advanced image analysis paradigms to perform semi-automated delineation of the PET images. However, the level of algorithm validation is variable and for most published algorithms is either insufficient or inconsistent which prevents recommending a single algorithm. This is compounded by the fact that realistic image configurations with low signal-to-noise ratios (SNR) and heterogeneous tracer distributions have rarely been used. Large variations in the evaluation methods used in the literature point to the need for a standardized evaluation protocol.

CONCLUSIONS

Available comparison studies suggest that PET-AS algorithms relying on advanced image analysis paradigms provide generally more accurate segmentation than approaches based on PET activity thresholds, particularly for realistic configurations. However, this may not be the case for simple shape lesions in situations with a narrower range of parameters, where simpler methods may also perform well. Recent algorithms which employ some type of consensus or automatic selection between several PET-AS methods have potential to overcome the limitations of the individual methods when appropriately trained. In either case, accuracy evaluation is required for each different PET scanner and scanning and image reconstruction protocol. For the simpler, less robust approaches, adaptation to scanning conditions, tumor type, and tumor location by optimization of parameters is necessary. The results from the method evaluation stage can be used to estimate the contouring uncertainty. All PET-AS contours should be critically verified by a physician. A standard test, i.e., a benchmark dedicated to evaluating both existing and future PET-AS algorithms needs to be designed, to aid clinicians in evaluating and selecting PET-AS algorithms and to establish performance limits for their acceptance for clinical use. The initial steps toward designing and building such a standard are undertaken by the task group members.

A Registration Method Based on Contour Point Cloud for 3D Whole-Body PET and CT Images

The PET and CT fusion image, combining the anatomical and functional information, has important clinical meaning. An effective registration of PET and CT images is the basis of image fusion. This paper presents a multithread registration method based on contour point cloud for 3D whole-body PET and CT images. Firstly, a geometric feature-based segmentation (GFS) method and a dynamic threshold denoising (DTD) method are creatively proposed to preprocess CT and PET images, respectively. Next, a new automated trunk slices extraction method is presented for extracting feature point clouds. Finally, the multithread Iterative Closet Point is adopted to drive an affine transform. We compare our method with a multiresolution registration method based on Mattes Mutual Information on 13 pairs (246~286 slices per pair) of 3D whole-body PET and CT data. Experimental results demonstrate the registration effectiveness of our method with lower negative normalization correlation (NC = −0.933) on feature images and less Euclidean distance error (ED = 2.826) on landmark points, outperforming the source data (NC = −0.496, ED = 25.847) and the compared method (NC = −0.614, ED = 16.085). Moreover, our method is about ten times faster than the compared one.

Effect of different segmentation algorithms on metabolic tumor volume measured on 18F-FDG PET/CT of cervical primary squamous cell carcinoma

Background and purpose

It is known that fluorine-18 fluorodeoxyglucose PET/computed tomography (CT) segmentation algorithms have an impact on the metabolic tumor volume (MTV). This leads to some uncertainties in PET/CT guidance of tumor radiotherapy. The aim of this study was to investigate the effect of segmentation algorithms on the PET/CT-based MTV and their correlations with the gross tumor volumes (GTVs) of cervical primary squamous cell carcinoma.

Materials and methods

Fifty-five patients with International Federation of Gynecology and Obstetrics stage Ia∼IIb and histologically proven cervical squamous cell carcinoma were enrolled. A fluorine-18 fluorodeoxyglucose PET/CT scan was performed before definitive surgery. GTV was measured on surgical specimens. MTVs were estimated on PET/CT scans using different segmentation algorithms, including a fixed percentage of the maximum standardized uptake value (20∼60% SUV_max) threshold and iterative adaptive algorithm. We divided all patients into four different groups according to the SUV_max within target volume. The comparisons of absolute values and percentage differences between MTVs by segmentation and GTV were performed in different SUV_max subgroups. The optimal threshold percentage was determined from MTV_20%∼MTV_60%, and was correlated with SUV_max. The correlation of MTV_{iterative adaptive} with GTV was also investigated.

Results

MTV_50% and MTV_60% were similar to GTV in the SUV_max up to 5 (P>0.05). MTV_30%∼MTV_60% were similar to GTV (P>0.05) in the 5<SUV_max≤10 group. MTV_20%∼MTV_60% were similar to GTV (P>0.05) in the 10<SUV_max≤15 group. MTV_20% and MTV_30% were similar to GTV (P>0.05) in the SUV_max of at least 15 group. MTV_{iterative adaptive} was similar to GTV in both total and different SUV_max groups (P>0.05). Significant differences were observed among the fixed percentage method and the optimal threshold percentage was inversely correlated with SUV_max. The iterative adaptive segmentation algorithm led to the highest accuracy (6.66±50.83%). A significantly positive correlation was also observed between MTV_{iterative adaptive} and GTV (Pearson’s correlation r=0.87, P<0.0001).

Conclusion

MTV_{iterative adaptive} is independent of SUV_max, more accurate, and correlated with GTV. Iterative adaptive algorithm segmentation may be more suitable than the fixed percentage threshold method to estimate the tumor volume of cervical primary squamous cell carcinoma.

Functional magnetic resonance imaging techniques and their development for radiation therapy planning and monitoring in the head and neck cancers

Radiation therapy (RT), in particular intensity-modulated radiation therapy (IMRT), is becoming a more important nonsurgical treatment strategy in head and neck cancer (HNC). The further development of IMRT imposes more critical requirements on clinical imaging, and these requirements cannot be fully fulfilled by the existing radiotherapeutic imaging workhorse of X-ray based imaging methods. Magnetic resonance imaging (MRI) has increasingly gained more interests from radiation oncology community and holds great potential for RT applications, mainly due to its non-ionizing radiation nature and superior soft tissue image contrast. Beyond anatomical imaging, MRI provides a variety of functional imaging techniques to investigate the functionality and metabolism of living tissue. The major purpose of this paper is to give a concise and timely review of some advanced functional MRI techniques that may potentially benefit conformal, tailored and adaptive RT in the HNC. The basic principle of each functional MRI technique is briefly introduced and their use in RT of HNC is described. Limitation and future development of these functional MRI techniques for HNC radiotherapeutic applications are discussed. More rigorous studies are warranted to translate the hypotheses into credible evidences in order to establish the role of functional MRI in the clinical practice of head and neck radiation oncology.

PETSTEP: Generation of synthetic PET lesions for fast evaluation of segmentation methods

Purpose

This work describes PETSTEP (PET Simulator of Tracers via Emission Projection): a faster and more accessible alternative to Monte Carlo (MC) simulation generating realistic PET images, for studies assessing image features and segmentation techniques.

Methods

PETSTEP was implemented within Matlab as open source software. It allows generating three-dimensional PET images from PET/CT data or synthetic CT and PET maps, with user-drawn lesions and user-set acquisition and reconstruction parameters. PETSTEP was used to reproduce images of the NEMA body phantom acquired on a GE Discovery 690 PET/CT scanner, and simulated with MC for the GE Discovery LS scanner, and to generate realistic Head and Neck scans. Finally the sensitivity (S) and Positive Predictive Value (PPV) of three automatic segmentation methods were compared when applied to the scanner-acquired and PETSTEP-simulated NEMA images.

Results

PETSTEP produced 3D phantom and clinical images within 4 and 6 min respectively on a single core 2.7 GHz computer. PETSTEP images of the NEMA phantom had mean intensities within 2% of the scanner-acquired image for both background and largest insert, and 16% larger background Full Width at Half Maximum. Similar results were obtained when comparing PETSTEP images to MC simulated data. The S and PPV obtained with simulated phantom images were statistically significantly lower than for the original images, but led to the same conclusions with respect to the evaluated segmentation methods.

Conclusions

PETSTEP allows fast simulation of synthetic images reproducing scanner-acquired PET data and shows great promise for the evaluation of PET segmentation methods.

An update on novel quantitative techniques in the context of evolving whole-body PET imaging

Since its foundation PET has established itself as one of the standard imaging modalities enabling the quantitative assessment of molecular targets in vivo. In the past two decades, quantitative PET has become a necessity in clinical oncology. Despite introduction of various measures for quantification and correction of PET parameters, there is debate on the selection of the appropriate methodology in specific diseases and conditions. In this review, we have focused on these techniques with special attention to topics such as static and dynamic whole body PET imaging, tracer kinetic modeling, global disease burden, texture analysis and radiomics, dual time point imaging and partial volume correction.

Content-based medical image retrieval: a survey of applications to multidimensional and multimodality data

Medical imaging is fundamental to modern healthcare, and its widespread use has resulted in the creation of image databases, as well as picture archiving and communication systems. These repositories now contain images from a diverse range of modalities, multidimensional (three-dimensional or time-varying) images, as well as co-aligned multimodality images. These image collections offer the opportunity for evidence-based diagnosis, teaching, and research; for these applications, there is a requirement for appropriate methods to search the collections for images that have characteristics similar to the case(s) of interest. Content-based image retrieval (CBIR) is an image search technique that complements the conventional text-based retrieval of images by using visual features, such as color, texture, and shape, as search criteria. Medical CBIR is an established field of study that is beginning to realize promise when applied to multidimensional and multimodality medical data. In this paper, we present a review of state-of-the-art medical CBIR approaches in five main categories: two-dimensional image retrieval, retrieval of images with three or more dimensions, the use of nonimage data to enhance the retrieval, multimodality image retrieval, and retrieval from diverse datasets. We use these categories as a framework for discussing the state of the art, focusing on the characteristics and modalities of the information used during medical image retrieval.

Registration of PET and CT images based on multiresolution gradient of mutual information demons algorithm for positioning esophageal cancer patients

Accurate registration of  18F−FDG PET (positron emission tomography) and CT (computed tomography) images has important clinical significance in radiation oncology. PET and CT images are acquired from  18F−FDG PET/CT scanner, but the two acquisition processes are separate and take a long time. As a result, there are position errors in global and deformable errors in local caused by respiratory movement or organ peristalsis. The purpose of this work was to implement and validate a deformable CT to PET image registration method in esophageal cancer to eventually facilitate accurate positioning the tumor target on CT, and improve the accuracy of radiation therapy. Global registration was firstly utilized to preprocess position errors between PET and CT images, achieving the purpose of aligning these two images on the whole. Demons algorithm, based on optical flow field, has the features of fast process speed and high accuracy, and the gradient of mutual information‐based demons (GMI demons) algorithm adds an additional external force based on the gradient of mutual information (GMI) between two images, which is suitable for multimodality images registration. In this paper, GMI demons algorithm was used to achieve local deformable registration of PET and CT images, which can effectively reduce errors between internal organs. In addition, to speed up the registration process, maintain its robustness, and avoid the local extremum, multiresolution image pyramid structure was used before deformable registration. By quantitatively and qualitatively analyzing cases with esophageal cancer, the registration scheme proposed in this paper can improve registration accuracy and speed, which is helpful for precisely positioning tumor target and developing the radiation treatment planning in clinical radiation therapy application.

PACS numbers: 87.57.nj, 87.57.Q‐, 87.57.uk

Attenuation Correction Strategies for Positron Emission Tomography/Computed Tomography and 4-Dimensional Positron Emission Tomography/Computed Tomography

This article discusses attenuation correction strategies in positron emission tomography/computed tomography (PET/CT) and 4-dimensional PET/CT imaging. Average CT scan derived from averaging the high temporal resolution CT images is effective in improving the registration of the CT and the PET images and quantification of the PET data. It underscores list-mode data acquisition in 4-dimensional PET, and introduces 4-dimensional CT, popular in thoracic treatment planning, to 4-dimensional PET/CT.

Motion management in positron emission tomography/computed tomography for radiation treatment planning

Hybrid positron emission tomography (PET)/computed tomography (CT) scanners combine, in a unique gantry, 2 of the most important diagnostic imaging systems, a CT and a PET tomograph, enabling anatomical (CT) and functional (PET) studies to be performed in a single study session. Furthermore, as the 2 scanners use the same spatial coordinate system, the reconstructed CT and PET images are spatially co-registered, allowing an accurate localization of the functional signal over the corresponding anatomical structure. This peculiarity of the hybrid PET/CT system results in improved tumor characterization for oncological applications, and more recently, it was found to be also useful for target volume definition (TVD) and treatment planning in radiotherapy (RT) applications. In fact, the use of combined PET/CT information has been shown to improve the RT treatment plan when compared with that obtained by a CT alone. A limiting factor to the accuracy of TVD by PET/CT is organ and tumor motion, which is mainly due to patient respiration. In fact, respiratory motion has a degrading effect on PET/CT image quality, and this is also critical for TVD, as it can lead to possible tumor missing or undertreatment. Thus, the management of respiratory motion is becoming an increasingly essential component in RT treatment planning; indeed, it has been recognized that the use of personalized motion information can improve TVD and, consequently, permit increased tumor dosage while sparing surrounding healthy tissues and organs at risk. This review describes the methods used for motion management in PET/CT for radiation treatment planning. The article covers the following: (1) problems caused by organ and lesion motion owing to respiration, and the artifacts generated on CT, PET, and PET/CT images; (2) data acquisition and processing techniques used to manage respiratory motion in PET/CT studies; and (3) the use of personalized motion information for TVD and radiation treatment planning.

Impact of 18F-FDG PET/CT on target volume delineation in recurrent or residual gynaecologic carcinoma

Background

To evaluate the impact of ¹⁸F-FDG PET/CT on target volume delineation in gynaecological cancer.

Methods

F-FDG PET/CT based RT treatment planning was performed in 10 patients with locally recurrent (n = 5) or post-surgical residual gynaecological cancer (n = 5). The gross tumor volume (GTV) was defined by 4 experienced radiation oncologists first using contrast enhanced CT (GTV_CT) and secondly using the fused ¹⁸F-FDG PET/CT datasets (GTV_PET/CT). In addition, the GTV was delineated using the signal-to-background (SBR) ratio-based adaptive thresholding technique (GTV_SBR). Overlap analysis were conducted to assess geographic mismatches between the GTVs delineated using the different techniques. Inter- and intra-observer variability were also assessed.

Results

The mean GTV_CT (43.65 cm³) was larger than the mean GTV_PET/CT (33.06 cm³), p = 0.02. In 6 patients, GTV_PET/CT added substantial tumor extension outside the GTV_CT even though 90.4% of the GTV_PET/CT was included in the GTV_CT and 30.2% of the GTV_CT was found outside the GTV_PET/CT. The inter- and intra-observer variability was not significantly reduced with the inclusion of ¹⁸F-FDG PET imaging (p = 0.23 and p = 0.18, respectively). The GTV_SBR was smaller than GTV_CT p ≤ 0.005 and GTV_PET/CT p ≤ 0.005.

Conclusions

The use of ¹⁸F-FDG PET/CT images for target volume delineation of recurrent or post-surgical residual gynaecological cancer alters the GTV in the majority of patients compared to standard CT-definition. The use of SBR-based auto-delineation showed significantly smaller GTVs. The use of PET/CT based target volume delineation may improve the accuracy of RT treatment planning in gynaecologic cancer.

Comparative methods for PET image segmentation in pharyngolaryngeal squamous cell carcinoma

Purpose

Several methods have been proposed for the segmentation of ¹⁸F-FDG uptake in PET. In this study, we assessed the performance of four categories of ¹⁸F-FDG PET image segmentation techniques in pharyngolaryngeal squamous cell carcinoma using clinical studies where the surgical specimen served as the benchmark.

Methods

Nine PET image segmentation techniques were compared including: five thresholding methods; the level set technique (active contour); the stochastic expectation-maximization approach; fuzzy clustering-based segmentation (FCM); and a variant of FCM, the spatial wavelet-based algorithm (FCM-SW) which incorporates spatial information during the segmentation process, thus allowing the handling of uptake in heterogeneous lesions. These algorithms were evaluated using clinical studies in which the segmentation results were compared to the 3-D biological tumour volume (BTV) defined by histology in PET images of seven patients with T3–T4 laryngeal squamous cell carcinoma who underwent a total laryngectomy. The macroscopic tumour specimens were collected “en bloc”, frozen and cut into 1.7- to 2-mm thick slices, then digitized for use as reference.

Results

The clinical results suggested that four of the thresholding methods and expectation-maximization overestimated the average tumour volume, while a contrast-oriented thresholding method, the level set technique and the FCM-SW algorithm underestimated it, with the FCM-SW algorithm providing relatively the highest accuracy in terms of volume determination (−5.9 ± 11.9%) and overlap index. The mean overlap index varied between 0.27 and 0.54 for the different image segmentation techniques. The FCM-SW segmentation technique showed the best compromise in terms of 3-D overlap index and statistical analysis results with values of 0.54 (0.26–0.72) for the overlap index.

Conclusion

The BTVs delineated using the FCM-SW segmentation technique were seemingly the most accurate and approximated closely the 3-D BTVs defined using the surgical specimens. Adaptive thresholding techniques need to be calibrated for each PET scanner and acquisition/processing protocol, and should not be used without optimization.

[Single French centre retrospective analysis of local control after high dose radiotherapy with or without chemotherapy and local control for Pancoast tumours]

PURPOSE

Superior sulcus non-small cell lung cancer represents less than 5% of all lung cancers and is a challenge for the physicians because of clinical presentation, treatments related toxicities and poor prognosis. The aim of this preliminary retrospective report is to present outcomes of patients affected by a superior sulcus non-small cell lung cancer, treated by high dose radiotherapy (>60 Gy) with or with our chemotherapy.

PATIENTS AND METHODS

All adult inoperable or unresectable patients (≥18 years) with a clinical and radiological diagnosis of superior sulcus non-small cell lung cancer treated in our department by radiotherapy with or without chemotherapy were retrospectively analysed. Primary endpoint was the local control. Overall survival, metastasis free survival and toxicity rates were also analysed and reported.

RESULTS

From January 1999 to June 2009, 12 patients were treated by exclusive high-dose radiochemotherapy. Median age was 53 years (range: 33-64 years); mean follow-up time was 20 months (range: 2-75 months). Mean local control, overall survival and metastasis free survival were 20.2, 22 and 20 months, respectively. At the time of this analysis, seven patients died of cancer and three of them presented only a metastatic disease progression. One patient died of acute cardiac failure 36 months after the end of radiochemotherapy and was disease free. Treatment was well tolerated and any acute and/or late G3-4 toxicity was recorded (NCI-CTC v 3.0 score).

CONCLUSION

This analysis confirms the interest of exclusive high-dose radiochemotherapy in treating inoperable superior sulcus non-small cell lung cancer patients, in achieving good local control and overall survival rates.

Functional and molecular image guidance in radiotherapy treatment planning optimization

Functional and molecular imaging techniques are increasingly being developed and used to quantitatively map the spatial distribution of parameters, such as metabolism, proliferation, hypoxia, perfusion, and ventilation, onto anatomically imaged normal organs and tumor. In radiotherapy optimization, these imaging modalities offer the promise of increased dose sparing to high-functioning subregions of normal organs or dose escalation to selected subregions of the tumor as well as the potential to adapt radiotherapy to functional changes that occur during the course of treatment. The practical use of functional/molecular imaging in radiotherapy optimization must take into cautious consideration several factors whose influences are still not clearly quantified or well understood including patient positioning differences between the planning computed tomography and functional/molecular imaging sessions, image reconstruction parameters and techniques, image registration, target/normal organ functional segmentation, the relationship governing the dose escalation/sparing warranted by the functional/molecular image intensity map, and radiotherapy-induced changes in the image intensity map over the course of treatment. The clinical benefit of functional/molecular image guidance in the form of improved local control or decreased normal organ toxicity has yet to be shown and awaits prospective clinical trials addressing this issue.

A novel fuzzy C-means algorithm for unsupervised heterogeneous tumor quantification in PET

PURPOSE

Accurate and robust image segmentation was identified as one of the most challenging issues facing PET quantification in oncological imaging. This difficulty is compounded by the low spatial resolution and high noise characteristics of PET images. The fuzzy C-means (FCM) clustering algorithm was largely used in various medical image segmentation approaches. However, the algorithm is sensitive to both noise and intensity heterogeneity since it does not take into account spatial contextual information.

METHODS

To overcome this limitation, a new fuzzy segmentation technique adapted to typical noisy and low resolution oncological PET data is proposed. PET images smoothed using a nonlinear anisotropic diffusion filter are added as a second input to the proposed FCM algorithm to incorporate spatial information (FCM-S). In addition, a methodology was developed to integrate the a trous wavelet transform in the standard FCM algorithm (FCM-SW) to allow handling of heterogeneous lesions' uptake. The algorithm was applied to the simulated data of the NCAT phantom, incorporating heterogeneous lesions in the lung and clinical PET/CT images of 21 patients presenting with histologically proven nonsmall-cell lung cancer (NSCLC) and 7 patients presenting with laryngeal squamous cell carcinoma (LSCC) to assess its performance for segmenting tumors with arbitrary size, shape, and tracer uptake. For NSCLC patients, the maximal tumor diameters measured from the macroscopic examination of the surgical specimen served as the ground truth for comparison with the maximum diameter estimated by the segmentation technique, whereas for LSCC patients, the 3D macroscopic tumor volume was considered as the ground truth for comparison with the corresponding PET-based volume. The proposed algorithm was also compared to the classical FCM segmentation technique.

RESULTS

There is a good correlation (R2 = 0.942) between the actual maximal diameter of primary NSCLC tumors estimated using the proposed PET segmentation procedure and those measured from the macroscopic examination, and the regression line agreed well with the line of identity (slope = 1.08) for the group analysis of the clinical data. The standard FCM algorithm seems to underestimate actual maximal diameters of the clinical data, resulting in a mean error of -4.6 mm (relative error of -10.8 +/- 23.1%) for all data sets. The mean error of maximal diameter estimation was reduced to 0.1 mm (0.9 +/- 14.4%) using the proposed FCM-SW algorithm. Likewise, the mean relative error on the estimated volume for LSCC patients was reduced from 21.7 +/- 22.0% for FCM to 8.6 +/- 28.3% using the proposed FCM-SW technique.

CONCLUSIONS

A novel unsupervised PET image segmentation technique that allows the quantification of lesions in the presence of heterogeneity of tracer uptake was developed and evaluated. The technique is being further refined and assessed in clinical setting to delineate treatment volumes for the purpose of PET-guided radiation therapy treatment planning but could find other applications in clinical oncology such as the assessment of response to treatment.

The brain MR Image segmentation techniques and use of diagnostic packages

RATIONALE AND OBJECTIVES

This article provides a survey of segmentation methods for medical images. Usually, classification of segmentation methods is done based on the approaches adopted and the domain of application.

MATERIALS AND METHODS

This survey is conducted on the recent segmentation methods used in biomedical image processing and explores the methods useful for better segmentation. A critical appraisal of the current status of semiautomated and automated methods is made for the segmentation of anatomical medical images emphasizing the advantages and disadvantages. Computer-aided diagnosis (CAD) used by radiologists as a second opinion has become one of the major research areas in medical imaging and diagnostic radiology. A picture archiving communication system (PACS) is an integrated workflow system for managing images and related data that is designed to streamline operations throughout the whole patient care delivery process.

RESULTS

By using PACS, the medical image interpretation may be changed from conventional hard-copy images to soft-copy studies viewed on the systems workstations.

CONCLUSION

The automatic segmentations assist the doctors in making quick diagnosis. The CAD need not be comparable to that of physicians, but is surely complementary.

PET-guided delineation of radiation therapy treatment volumes: a survey of image segmentation techniques

Historically, anatomical CT and MR images were used to delineate the gross tumour volumes (GTVs) for radiotherapy treatment planning. The capabilities offered by modern radiation therapy units and the widespread availability of combined PET/CT scanners stimulated the development of biological PET imaging-guided radiation therapy treatment planning with the aim to produce highly conformal radiation dose distribution to the tumour. One of the most difficult issues facing PET-based treatment planning is the accurate delineation of target regions from typical blurred and noisy functional images. The major problems encountered are image segmentation and imperfect system response function. Image segmentation is defined as the process of classifying the voxels of an image into a set of distinct classes. The difficulty in PET image segmentation is compounded by the low spatial resolution and high noise characteristics of PET images. Despite the difficulties and known limitations, several image segmentation approaches have been proposed and used in the clinical setting including thresholding, edge detection, region growing, clustering, stochastic models, deformable models, classifiers and several other approaches. A detailed description of the various approaches proposed in the literature is reviewed. Moreover, we also briefly discuss some important considerations and limitations of the widely used techniques to guide practitioners in the field of radiation oncology. The strategies followed for validation and comparative assessment of various PET segmentation approaches are described. Future opportunities and the current challenges facing the adoption of PET-guided delineation of target volumes and its role in basic and clinical research are also addressed.

The clinical role of fusion imaging using PET, CT, and MR imaging

Multimodality image registration and fusion have a key role in routine diagnosis, staging, restaging, and the assessment of response to treatment, surgery, and radiotherapy planning of malignant disease. The complementarity between anatomic (CT and MR imaging) and molecular (SPECT and PET) imaging modalities is well established and the role of fusion imaging widely recognized as a central piece of the general tree of clinical decision making. Moreover, dual modality imaging technologies including SPECT/CT, PET/CT, and, in the future, PET/MR imaging, now represent the leading component of contemporary health care institutions. This article discusses recent advances in clinical multimodality imaging, the role of correlative fusion imaging in a clinical setting, and future opportunities and challenges facing the adoption of multimodality imaging.

18F-fluorocholine PET-guided target volume delineation techniques for partial prostate re-irradiation in local recurrent prostate cancer

BACKGROUND AND PURPOSE

We evaluate the contribution of (18)F-choline PET/CT in the delineation of gross tumour volume (GTV) in local recurrent prostate cancer after initial irradiation using various PET image segmentation techniques.

MATERIALS AND METHODS

Seventeen patients with local-only recurrent prostate cancer (median=5.7 years) after initial irradiation were included in the study. Rebiopsies were performed in 10 patients that confirmed the local recurrence. Following injection of 300 MBq of (18)F-fluorocholine, dynamic PET frames (3 min each) were reconstructed from the list-mode acquisition. Five PET image segmentation techniques were used to delineate the (18)F-choline-based GTVs. These included manual delineation of contours (GTV(man)) by two teams consisting of a radiation oncologist and a nuclear medicine physician each, a fixed threshold of 40% and 50% of the maximum signal intensity (GTV(40%) and GTV(50%)), signal-to-background ratio-based adaptive thresholding (GTV(SBR)), and a region growing (GTV(RG)) algorithm. Geographic mismatches between the GTVs were also assessed using overlap analysis.

RESULTS

Inter-observer variability for manual delineation of GTVs was high but not statistically significant (p=0.459). In addition, the volumes and shapes of GTVs delineated using semi-automated techniques were significantly higher than those of GTVs defined manually.

CONCLUSIONS

Semi-automated segmentation techniques for (18)F-choline PET-guided GTV delineation resulted in substantially higher GTVs compared to manual delineation and might replace the latter for determination of recurrent prostate cancer for partial prostate re-irradiation. The selection of the most appropriate segmentation algorithm still needs to be determined.

Preclinical Multimodality Imaging in Vivo

Multimodality small-animal molecular imaging has become increasingly important as transgenic and knockout mice are produced to model human diseases. With the ever-increasing number and importance of human disease models, particularly in rodents (mice and rats), the ability of high-resolution multimodality molecular imaging instrumentation to contribute unique information is becoming more common and necessary. Multimodality imaging with high spatial resolution and good sensitivity, which combines modalities and records sequentially or simultaneously complementary information, offers many advantages in certain research experiments. This article discusses the current trends and new horizons in preclinical multimodality imaging in-vivo and its role in biomedical research.