Artificial Neural Network-Based System for PET Volume Segmentation

Application of Artificial Intelligence in Orthodontics: Current State and Future Perspectives

In recent years, there has been the notable emergency of artificial intelligence (AI) as a transformative force in multiple domains, including orthodontics. This review aims to provide a comprehensive overview of the present state of AI applications in orthodontics, which can be categorized into the following domains: (1) diagnosis, including cephalometric analysis, dental analysis, facial analysis, skeletal-maturation-stage determination and upper-airway obstruction assessment; (2) treatment planning, including decision making for extractions and orthognathic surgery, and treatment outcome prediction; and (3) clinical practice, including practice guidance, remote care, and clinical documentation. We have witnessed a broadening of the application of AI in orthodontics, accompanied by advancements in its performance. Additionally, this review outlines the existing limitations within the field and offers future perspectives.

Artificial intelligence in molecular imaging

AI has, to varying degrees, affected all aspects of molecular imaging, from image acquisition to diagnosis. During the last decade, the advent of deep learning in particular has transformed medical image analysis. Although the majority of recent advances have resulted from neural-network models applied to image segmentation, a broad range of techniques has shown promise for image reconstruction, image synthesis, differential-diagnosis generation, and treatment guidance. Applications of AI for drug design indicate the way forward for using AI to facilitate molecular-probe design, which is still in its early stages. Deep-learning models have demonstrated increased efficiency and image quality for PET reconstruction from sinogram data. Generative adversarial networks (GANs), which are paired neural networks that are jointly trained to generate and classify images, have found applications in modality transformation, artifact reduction, and synthetic-PET-image generation. Some AI applications, based either partly or completely on neural-network approaches, have demonstrated superior differential-diagnosis generation relative to radiologists. However, AI models have a history of brittleness, and physicians and patients may not trust AI applications that cannot explain their reasoning. To date, the majority of molecular-imaging applications of AI have been confined to research projects, and are only beginning to find their ways into routine clinical workflows via commercialization and, in some cases, integration into scanner hardware. Evaluation of actual clinical products will yield more realistic assessments of AI’s utility in molecular imaging.

On the performance of lung nodule detection, segmentation and classification

Computed tomography (CT) screening is an effective way for early detection of lung cancer in order to improve the survival rate of such a deadly disease. For more than two decades, image processing techniques such as nodule detection, segmentation, and classification have been extensively studied to assist physicians in identifying nodules from hundreds of CT slices to measure shapes and HU distributions of nodules automatically and to distinguish their malignancy. Thanks to new parallel computation, multi-layer convolution, nonlinear pooling operation, and the big data learning strategy, recent development of deep-learning algorithms has shown great progress in lung nodule screening and computer-assisted diagnosis (CADx) applications due to their high sensitivity and low false positive rates. This paper presents a survey of state-of-the-art deep-learning-based lung nodule screening and analysis techniques focusing on their performance and clinical applications, aiming to help better understand the current performance, the limitation, and the future trends of lung nodule analysis.

Artificial Intelligence for Response Evaluation With PET/CT

Positron emission tomography (PET)/computed tomography (CT) are nuclear diagnostic imaging modalities that are routinely deployed for cancer staging and monitoring. They hold the advantage of detecting disease related biochemical and physiologic abnormalities in advance of anatomical changes, thus widely used for staging of disease progression, identification of the treatment gross tumor volume, monitoring of disease, as well as prediction of outcomes and personalization of treatment regimens. Among the arsenal of different functional imaging modalities, nuclear imaging has benefited from early adoption of quantitative image analysis starting from simple standard uptake value normalization to more advanced extraction of complex imaging uptake patterns; thanks to application of sophisticated image processing and machine learning algorithms. In this review, we discuss the application of image processing and machine/deep learning techniques to PET/CT imaging with special focus on the oncological radiotherapy domain as a case study and draw examples from our work and others to highlight current status and future potentials.

The prognostic role of end-of-treatment FDG-PET/CT in diffuse large B cell lymphoma: a pilot study application of neural networks to predict time-to-event

PURPOSE

To evaluate the prognostic role of end-of-treatment (EoT) FDG-PET/CT parameters in diffuse large B cell lymphoma (DLBCL), and then to explore a pilot application of Neural Networks (NN) in predicting time-to-relapse.

METHODS

For conventional survival analysis, parameters as Deauville score (DS) and quantitative extension of DS (qPET) were correlated to adverse events as relapse or progression in the follow-up. To build NN and conventional multi-regression models (MM) for time-to-event prediction, patients with residual FDG uptake (DS ≥ 2) and an adverse event were divided into a training and a test group. Models developed on the training group were evaluated in the test group. Pearson correlation coefficient (R) and mean relative error between observed and forecasted time-to-event were calculated.

RESULTS

FDG-PET/CT data of 308 patients with DLBCL were analyzed. DS and qPET were prognostic factors in conventional univariate analysis. Positive and negative predictive values, respectively, were 55% and 83% for DS 4-5, 89% and 82% for positive qPET. Focusing on 37 relapsed patients with a residual FDG uptake, R between observed and forecasted time-to-event was of 0.63 in the NN model and 0.49 in the MM. Mean relative error in predicting time-to-event was of 58% for NN and 67% for MM.

CONCLUSIONS

EoT FDG-PET/CT visual score (DS) is a strong outcome predictor in DLBCL in a large monocentric cohort. The semi-quantitative parameter qPET may increase this prognostic performance. A pilot NN model applied on residual FDG uptake parameters seems to predict time-to-event in the follow-up.

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.

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.

Current Methods to Define Metabolic Tumor Volume in Positron Emission Tomography: Which One is Better?

Numerous methods to segment tumors using ¹⁸F-fluorodeoxyglucose positron emission tomography (FDG PET) have been introduced. Metabolic tumor volume (MTV) refers to the metabolically active volume of the tumor segmented using FDG PET, and has been shown to be useful in predicting patient outcome and in assessing treatment response. Also, tumor segmentation using FDG PET has useful applications in radiotherapy treatment planning. Despite extensive research on MTV showing promising results, MTV is not used in standard clinical practice yet, mainly because there is no consensus on the optimal method to segment tumors in FDG PET images. In this review, we discuss currently available methods to measure MTV using FDG PET, and assess the advantages and disadvantages of the methods.

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.

On the Reliability of Automatic Volume Delineation in Low-Contrast [(18)F]FMISO-PET Imaging

Hypoxia is a marker of poor prognosis in malignant tumors independent from the selected therapeutic method and the therapy should be intensified in such tumors. Hypoxia imaging with positron emission tomography (PET) is limited by low contrast to noise ratios with every available tracer. In radiation oncology appropriate delineation is required to allow therapy and intensification. While manual segmentation results are highly dependent from experience and observers condition (high inter- and intra observer variability), threshold- and gradient-based algorithms for automatic segmentation frequently fail in low contrast data sets. Likewise, calibration of these algorithms using phantoms is not useful. Complex computational models such as swarm intelligence-based algorithms are promising tools for optimized segmentation results and allow observer independent interpretation of multimodal and multidimensional imaging data.

Random Walk and Graph Cut for Co-Segmentation of Lung Tumor on PET-CT Images

Accurate lung tumor delineation plays an important role in radiotherapy treatment planning. Since the lung tumor has poor boundary in positron emission tomography (PET) images and low contrast in computed tomography (CT) images, segmentation of tumor in the PET and CT images is a challenging task. In this paper, we effectively integrate the two modalities by making fully use of the superior contrast of PET images and superior spatial resolution of CT images. Random walk and graph cut method is integrated to solve the segmentation problem, in which random walk is utilized as an initialization tool to provide object seeds for graph cut segmentation on the PET and CT images. The co-segmentation problem is formulated as an energy minimization problem which is solved by max-flow/min-cut method. A graph, including two sub-graphs and a special link, is constructed, in which one sub-graph is for the PET and another is for CT, and the special link encodes a context term which penalizes the difference of the tumor segmentation on the two modalities. To fully utilize the characteristics of PET and CT images, a novel energy representation is devised. For the PET, a downhill cost and a 3D derivative cost are proposed. For the CT, a shape penalty cost is integrated into the energy function which helps to constrain the tumor region during the segmentation. We validate our algorithm on a data set which consists of 18 PET-CT images. The experimental results indicate that the proposed method is superior to the graph cut method solely using the PET or CT is more accurate compared with the random walk method, random walk co-segmentation method, and non-improved graph cut method.

Including anatomical and functional information in MC simulation of PET and SPECT brain studies. Brain-VISET: a voxel-based iterative method

Monte Carlo (MC) simulation provides a flexible and robust framework to efficiently evaluate and optimize image processing methods in emission tomography. In this work we present Brain-VISET (Voxel-based Iterative Simulation for Emission Tomography), a method that aims to simulate realistic [ (99m) Tc]-SPECT and [ (18) F]-PET brain databases by including anatomical and functional information. To this end, activity and attenuation maps generated using high-resolution anatomical images from patients were used as input maps in a MC projector to simulate SPECT or PET sinograms. The reconstructed images were compared with the corresponding real SPECT or PET studies in an iterative process where the activity inputs maps were being modified at each iteration. Datasets of 30 refractory epileptic patients were used to assess the new method. Each set consisted of structural images (MRI and CT) and functional studies (SPECT and PET), thereby allowing the inclusion of anatomical and functional variability in the simulation input models. SPECT and PET sinograms were obtained using the SimSET package and were reconstructed with the same protocols as those employed for the clinical studies. The convergence of Brain-VISET was evaluated by studying the behavior throughout iterations of the correlation coefficient, the quotient image histogram and a ROI analysis comparing simulated with real studies. The realism of generated maps was also evaluated. Our findings show that Brain-VISET is able to generate realistic SPECT and PET studies and that four iterations is a suitable number of iterations to guarantee a good agreement between simulated and real studies.

A review on segmentation of positron emission tomography images

Positron Emission Tomography (PET), a non-invasive functional imaging method at the molecular level, images the distribution of biologically targeted radiotracers with high sensitivity. PET imaging provides detailed quantitative information about many diseases and is often used to evaluate inflammation, infection, and cancer by detecting emitted photons from a radiotracer localized to abnormal cells. In order to differentiate abnormal tissue from surrounding areas in PET images, image segmentation methods play a vital role; therefore, accurate image segmentation is often necessary for proper disease detection, diagnosis, treatment planning, and follow-ups. In this review paper, we present state-of-the-art PET image segmentation methods, as well as the recent advances in image segmentation techniques. In order to make this manuscript self-contained, we also briefly explain the fundamentals of PET imaging, the challenges of diagnostic PET image analysis, and the effects of these challenges on the segmentation results.

Lesion detection and characterization with context driven approximation in thoracic FDG PET-CT images of NSCLC studies

We present a lesion detection and characterization method for (18)F-fluorodeoxyglucose positron emission tomography-computed tomography (FDG PET-CT) images of the thorax in the evaluation of patients with primary nonsmall cell lung cancer (NSCLC) with regional nodal disease. Lesion detection can be difficult due to low contrast between lesions and normal anatomical structures. Lesion characterization is also challenging due to similar spatial characteristics between the lung tumors and abnormal lymph nodes. To tackle these problems, we propose a context driven approximation (CDA) method. There are two main components of our method. First, a sparse representation technique with region-level contexts was designed for lesion detection. To discriminate low-contrast data with sparse representation, we propose a reference consistency constraint and a spatial consistent constraint. Second, a multi-atlas technique with image-level contexts was designed to represent the spatial characteristics for lesion characterization. To accommodate inter-subject variation in a multi-atlas model, we propose an appearance constraint and a similarity constraint. The CDA method is effective with a simple feature set, and does not require parametric modeling of feature space separation. The experiments on a clinical FDG PET-CT dataset show promising performance improvement over the state-of-the-art.

Automatic detection and classification of nasopharyngeal carcinoma on PET/CT with support vector machine

PURPOSE

Positron emission tomography/computed tomography (PET/CT) has established values for imaging of head and neck cancers, including the nasopharyngeal carcinoma (NPC), utilizing both morphologic and functional information. In this paper, we introduce a computerized system for automatic detection of NPC, targeting both the primary tumor and regional nodal metastasis, on PET/CT.

METHODS

Candidate lesions were extracted based on the features from both PET and CT images and a priori knowledge of anatomical features and subsequently classified by a support vector machine algorithm. The system was validated with 25 PET/CT examinations from 10 patients suffering from NPC. Lesions manually contoured by experienced radiologists were used as the gold standard.

RESULTS

Results showed that the system successfully identified all 53 hypermetabolic lesions larger than 1 cm in size and excluded normal physiological uptake in brown fat, muscles, bone marrow, brain, and salivary glands.

CONCLUSION

The system combined both imaging features and a priori clinical knowledge for classification between pathological and physiological uptake. Preliminary results showed that the system was highly accurate and promising for adoption in clinical use.

[Metabolically active volumes automatic delineation methodologies in PET imaging: review and perspectives]

PET imaging is now considered a gold standard tool in clinical oncology, especially for diagnosis purposes. More recent applications such as therapy follow-up or tumor targeting in radiotherapy require a fast, accurate and robust metabolically active tumor volumes delineation on emission images, which cannot be obtained through manual contouring. This clinical need has sprung a large number of methodological developments regarding automatic methods to define tumor volumes on PET images. This paper reviews most of the methodologies that have been recently proposed and discusses their framework and methodological and/or clinical validation. Perspectives regarding the future work to be done are also suggested.