Development of a new fully three-dimensional methodology for tumours delineation in functional images

A semiautomatic segmentation method framework for pelvic bone tumors based on CT-MR multimodal images

The pelvic structure is complex and the tumor is poorly defined from the surrounding tissues. Finding the exact tumor resection margin based on the surgeon's clinical experience alone is a time-consuming and difficult task, which is a major factor leading to surgical failure. An accurate method for segmenting pelvic bone tumors is needed. In this paper, a semiautomatic segmentation method for pelvic bone tumors based on CT-MR multimodal images is presented. The method combines multiple medical prior knowledge and image segmentation algorithms. Finally, the segmentation results are visualized in three dimensions. We tested the proposed method on a collection of 10 cases (97 tumor MR images in total). The segmentation results were compared with the manual annotation of the physicians. On average, our method has an accuracy of 0.9358, a recall of 0.9278, an IOU value of 0.8697, a Dice value of 0.9280, and an AUC value of 0.9632. The average error of the 3D model was within the allowable range of the surgery. The proposed algorithm can accurately segment bone tumors in pelvic MR images regardless of tumor location, size, and other factors. It provides the possibility to assist pelvic bone tumor preservation surgery.

Enhancing Radiotherapy Workflow for Head and Neck Cancer with Artificial Intelligence: A Systematic Review

BACKGROUND

Head and neck cancer (HNC) is characterized by complex-shaped tumors and numerous organs at risk (OARs), inducing challenging radiotherapy (RT) planning, optimization, and delivery. In this review, we provided a thorough description of the applications of artificial intelligence (AI) tools in the HNC RT process.

METHODS

The PubMed database was queried, and a total of 168 articles (2016-2022) were screened by a group of experts in radiation oncology. The group selected 62 articles, which were subdivided into three categories, representing the whole RT workflow: (i) target and OAR contouring, (ii) planning, and (iii) delivery.

RESULTS

The majority of the selected studies focused on the OARs segmentation process. Overall, the performance of AI models was evaluated using standard metrics, while limited research was found on how the introduction of AI could impact clinical outcomes. Additionally, papers usually lacked information about the confidence level associated with the predictions made by the AI models.

CONCLUSIONS

AI represents a promising tool to automate the RT workflow for the complex field of HNC treatment. To ensure that the development of AI technologies in RT is effectively aligned with clinical needs, we suggest conducting future studies within interdisciplinary groups, including clinicians and computer scientists.

Proton boron capture therapy (PBCT) induces cell death and mitophagy in a heterotopic glioblastoma model

Despite aggressive therapeutic regimens, glioblastoma (GBM) represents a deadly brain tumor with significant aggressiveness, radioresistance and chemoresistance, leading to dismal prognosis. Hypoxic microenvironment, which characterizes GBM, is associated with reduced therapeutic effectiveness. Moreover, current irradiation approaches are limited by uncertain tumor delineation and severe side effects that comprehensively lead to unsuccessful treatment and to a worsening of the quality of life of GBM patients. Proton beam offers the opportunity of reduced side effects and a depth-dose profile, which, unfortunately, are coupled with low relative biological effectiveness (RBE). The use of radiosensitizing agents, such as boron-containing molecules, enhances proton RBE and increases the effectiveness on proton beam-hit targets. We report a first preclinical evaluation of proton boron capture therapy (PBCT) in a preclinical model of GBM analyzed via μ-positron emission tomography/computed tomography (μPET-CT) assisted live imaging, finding a significant increased therapeutic effectiveness of PBCT versus proton coupled with an increased cell death and mitophagy. Our work supports PBCT and radiosensitizing agents as a scalable strategy to treat GBM exploiting ballistic advances of proton beam and increasing therapeutic effectiveness and quality of life in GBM patients.

matRadiomics: A Novel and Complete Radiomics Framework, from Image Visualization to Predictive Model

Radiomics aims to support clinical decisions through its workflow, which is divided into: (i) target identification and segmentation, (ii) feature extraction, (iii) feature selection, and (iv) model fitting. Many radiomics tools were developed to fulfill the steps mentioned above. However, to date, users must switch different software to complete the radiomics workflow. To address this issue, we developed a new free and user-friendly radiomics framework, namely matRadiomics, which allows the user: (i) to import and inspect biomedical images, (ii) to identify and segment the target, (iii) to extract the features, (iv) to reduce and select them, and (v) to build a predictive model using machine learning algorithms. As a result, biomedical images can be visualized and segmented and, through the integration of Pyradiomics into matRadiomics, radiomic features can be extracted. These features can be selected using a hybrid descriptive–inferential method, and, consequently, used to train three different classifiers: linear discriminant analysis, k-nearest neighbors, and support vector machines. Model validation is performed using k-fold cross-Validation and k-fold stratified cross-validation. Finally, the performance metrics of each model are shown in the graphical interface of matRadiomics. In this study, we discuss the workflow, architecture, application, future development of matRadiomics, and demonstrate its working principles in a real case study with the aim of establishing a reference standard for the whole radiomics analysis, starting from the image visualization up to the predictive model implementation.

Feasibility on the Use of Radiomics Features of 11[C]-MET PET/CT in Central Nervous System Tumours: Preliminary Results on Potential Grading Discrimination Using a Machine Learning Model

Background/Aim: Nowadays, Machine Learning (ML) algorithms have demonstrated remarkable progress in image-recognition tasks and could be useful for the new concept of precision medicine in order to help physicians in the choice of therapeutic strategies for brain tumours. Previous data suggest that, in the central nervous system (CNS) tumours, amino acid PET may more accurately demarcate the active disease than paramagnetic enhanced MRI, which is currently the standard method of evaluation in brain tumours and helps in the assessment of disease grading, as a fundamental basis for proper clinical patient management. The aim of this study is to evaluate the feasibility of ML on 11[C]-MET PET/CT scan images and to propose a radiomics workflow using a machine-learning method to create a predictive model capable of discriminating between low-grade and high-grade CNS tumours. Materials and Methods: In this retrospective study, fifty-six patients affected by a primary brain tumour who underwent 11[C]-MET PET/CT were selected from January 2016 to December 2019. Pathological examination was available in all patients to confirm the diagnosis and grading of disease. PET/CT acquisition was performed after 10 min from the administration of 11C-Methionine (401–610 MBq) for a time acquisition of 15 min. 11[C]-MET PET/CT images were acquired using two scanners (24 patients on a Siemens scan and 32 patients on a GE scan). Then, LIFEx software was used to delineate brain tumours using two different semi-automatic and user-independent segmentation approaches and to extract 44 radiomics features for each segmentation. A novel mixed descriptive-inferential sequential approach was used to identify a subset of relevant features that correlate with the grading of disease confirmed by pathological examination and clinical outcome. Finally, a machine learning model based on discriminant analysis was used in the evaluation of grading prediction (low grade CNS vs. high-grade CNS) of 11[C]-MET PET/CT. Results: The proposed machine learning model based on (i) two semi-automatic and user-independent segmentation processes, (ii) an innovative feature selection and reduction process, and (iii) the discriminant analysis, showed good performance in the prediction of tumour grade when the volumetric segmentation was used for feature extraction. In this case, the proposed model obtained an accuracy of ~85% (AUC ~79%) in the subgroup of patients who underwent Siemens tomography scans, of 80.51% (AUC 65.73%) in patients who underwent GE tomography scans, and of 70.31% (AUC 64.13%) in the whole patients’ dataset (Siemens and GE scans). Conclusions: This preliminary study on the use of an ML model demonstrated to be feasible and able to select radiomics features of 11[C]-MET PET with potential value in prediction of grading of disease. Further studies are needed to improve radiomics algorithms to personalize predictive and prognostic models and potentially support the medical decision process.

Changes of [18F]FDG-PET/CT quantitative parameters in tumor lesions by the Bayesian penalized-likelihood PET reconstruction algorithm and its influencing factors

Background

To compare the changes in quantitative parameters and the size and degree of ¹⁸F-fluorodeoxyglucose ([¹⁸F]FDG) uptake of malignant tumor lesions between Bayesian penalized-likelihood (BPL) and non-BPL reconstruction algorithms.

Methods

Positron emission tomography/computed tomography images of 86 malignant tumor lesions were reconstructed using the algorithms of ordered subset expectation maximization (OSEM), OSEM + time of flight (TOF), OSEM + TOF + point spread function (PSF), and BPL. [¹⁸F]FDG parameters of maximum standardized uptake value (SUVmax), SUVmean, metabolic tumor volume (MTV), total lesion glycolysis (TLG), and signal-to-background ratio (SBR) of these lesions were measured. Quantitative parameters between the different reconstruction algorithms were compared, and correlations between parameter variation and lesion size or the degree of [¹⁸F]FDG uptake were analyzed.

Results

After BPL reconstruction, SUVmax, SUVmean, and SBR were significantly increased, MTV was significantly decreased. The difference values of %ΔSUVmax, %ΔSUVmean, %ΔSBR, and the absolute value of %ΔMTV between BPL and OSEM + TOF were 40.00%, 38.50%, 33.60%, and 33.20%, respectively, which were significantly higher than those between BPL and OSEM + TOF + PSF. Similar results were observed in the comparison of OSEM and OSEM + TOF + PSF with BPL. The %ΔSUVmax, %ΔSUVmean, and %ΔSBR were all significantly negatively correlated with the size and degree of [¹⁸F]FDG uptake in the lesions, whereas significant positive correlations were observed for %ΔMTV and %ΔTLG.

Conclusion

The BPL reconstruction algorithm significantly increased SUVmax, SUVmean, and SBR and decreased MTV of tumor lesions, especially in small or relatively hypometabolic lesions.

Radiomics and machine learning applications in rectal cancer: Current update and future perspectives

The high incidence of rectal cancer in both sexes makes it one of the most common tumors, with significant morbidity and mortality rates. To define the best treatment option and optimize patient outcome, several rectal cancer biological variables must be evaluated. Currently, medical imaging plays a crucial role in the characterization of this disease, and it often requires a multimodal approach. Magnetic resonance imaging is the first-choice imaging modality for local staging and restaging and can be used to detect high-risk prognostic factors. Computed tomography is widely adopted for the detection of distant metastases. However, conventional imaging has recognized limitations, and many rectal cancer characteristics remain assessable only after surgery and histopathology evaluation. There is a growing interest in artificial intelligence applications in medicine, and imaging is by no means an exception. The introduction of radiomics, which allows the extraction of quantitative features that reflect tumor heterogeneity, allows the mining of data in medical images and paved the way for the identification of potential new imaging biomarkers. To manage such a huge amount of data, the use of machine learning algorithms has been proposed. Indeed, without prior explicit programming, they can be employed to build prediction models to support clinical decision making. In this review, current applications and future perspectives of artificial intelligence in medical imaging of rectal cancer are presented, with an imaging modality-based approach and a keen eye on unsolved issues. The results are promising, but the road ahead for translation in clinical practice is rather long.

Customized Efficient Neural Network for COVID-19 Infected Region Identification in CT Images

BACKGROUND

In the field of biomedical imaging, radiomics is a promising approach that aims to provide quantitative features from images. It is highly dependent on accurate identification and delineation of the volume of interest to avoid mistakes in the implementation of the texture-based prediction model. In this context, we present a customized deep learning approach aimed at addressing the real-time, and fully automated identification and segmentation of COVID-19 infected regions in computed tomography images.

METHODS

In a previous study, we adopted ENET, originally used for image segmentation tasks in self-driving cars, for whole parenchyma segmentation in patients with idiopathic pulmonary fibrosis which has several similarities to COVID-19 disease. To automatically identify and segment COVID-19 infected areas, a customized ENET, namely C-ENET, was implemented and its performance compared to the original ENET and some state-of-the-art deep learning architectures.

RESULTS

The experimental results demonstrate the effectiveness of our approach. Considering the performance obtained in terms of similarity of the result of the segmentation to the gold standard (dice similarity coefficient ~75%), our proposed methodology can be used for the identification and delineation of COVID-19 infected areas without any supervision of a radiologist, in order to obtain a volume of interest independent from the user.

CONCLUSIONS

We demonstrated that the proposed customized deep learning model can be applied to rapidly identify, and segment COVID-19 infected regions to subsequently extract useful information for assessing disease severity through radiomics analyses.

Automatic Segmentation of Mandible from Conventional Methods to Deep Learning-A Review

Medical imaging techniques, such as (cone beam) computed tomography and magnetic resonance imaging, have proven to be a valuable component for oral and maxillofacial surgery (OMFS). Accurate segmentation of the mandible from head and neck (H&N) scans is an important step in order to build a personalized 3D digital mandible model for 3D printing and treatment planning of OMFS. Segmented mandible structures are used to effectively visualize the mandible volumes and to evaluate particular mandible properties quantitatively. However, mandible segmentation is always challenging for both clinicians and researchers, due to complex structures and higher attenuation materials, such as teeth (filling) or metal implants that easily lead to high noise and strong artifacts during scanning. Moreover, the size and shape of the mandible vary to a large extent between individuals. Therefore, mandible segmentation is a tedious and time-consuming task and requires adequate training to be performed properly. With the advancement of computer vision approaches, researchers have developed several algorithms to automatically segment the mandible during the last two decades. The objective of this review was to present the available fully (semi)automatic segmentation methods of the mandible published in different scientific articles. This review provides a vivid description of the scientific advancements to clinicians and researchers in this field to help develop novel automatic methods for clinical applications.

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.

Artificial intelligence for molecular neuroimaging

In recent years, artificial intelligence (AI) or the study of how computers and machines can gain intelligence, has been increasingly applied to problems in medical imaging, and in particular to molecular imaging of the central nervous system. Many AI innovations in medical imaging include improving image quality, segmentation, and automating classification of disease. These advances have led to an increased availability of supportive AI tools to assist physicians in interpreting images and making decisions affecting patient care. This review focuses on the role of AI in molecular neuroimaging, primarily applied to positron emission tomography (PET) and single photon emission computed tomography (SPECT). We emphasize technical innovations such as AI in computed tomography (CT) generation for the purposes of attenuation correction and disease localization, as well as applications in neuro-oncology and neurodegenerative diseases. Limitations and future prospects for AI in molecular brain imaging are also discussed. Just as new equipment such as SPECT and PET revolutionized the field of medical imaging a few decades ago, AI and its related technologies are now poised to bring on further disruptive changes. An understanding of these new technologies and how they work will help physicians adapt their practices and succeed with these new tools.

Early Monitoring Response to Therapy in Patients with Brain Lesions Using the Cumulative SUV Histogram

Gamma Knife treatment is an alternative to traditional brain surgery and whole-brain radiation therapy for treating cancers that are inaccessible via conventional treatments. To assess the effectiveness of Gamma Knife treatments, functional imaging can play a crucial role. The aim of this study is to evaluate new prognostic indices to perform an early assessment of treatment response to therapy using positron emission tomography imaging. The parameters currently used in nuclear medicine assessments can be affected by statistical fluctuation errors and/or cannot provide information on tumor extension and heterogeneity. To overcome these limitations, the Cumulative standardized uptake value (SUV) Histogram (CSH) and Area Under the Curve (AUC) indices were evaluated to obtain additional information on treatment response. For this purpose, the absolute level of [11C]-Methionine (MET) uptake was measured and its heterogeneity distribution within lesions was evaluated by calculating the CSH and AUC indices. CSH and AUC parameters show good agreement with patient outcomes after Gamma Knife treatments. Furthermore, no relevant correlations were found between CSH and AUC indices and those usually used in the nuclear medicine environment. CSH and AUC indices could be a useful tool for assessing patient responses to therapy.

Reproducibility of Baseline Tumour Metabolic Volume Measurements in Diffuse Large B-Cell LymphomA: Is There a Superior Method?

The metabolic tumour volume (MTV) is an independent prognostic indicator in diffuse large B-cell lymphoma (DLBCL). However, its measurement is not standardised and is subject to wide variations depending on the method used. This study aimed to compare the reproducibility of MTV measurement as well as the thresholds obtained for each method and their prognostic values. The baseline MTV was measured in 239 consecutive patients treated at Henri Becquerel Centre by two blinded evaluators. Eight methods were compared: 3 absolute (SUV (standardised uptake value) ≥ 2.5; SUV≥ liver SUVmax; SUV≥ PERCIST SUV), 1 percentage SUV threshold method (SUV ≥ 41% SUVmax) and 4 adaptive methods (Daisne, Nestle, Fitting, Black). The intraclass correlation coefficients were excellent, from 0.91 to 0.96, for the absolute SUV methods, Black and Nestle methods, and good for 41% SUVmax, Fitting and Daisne methods (0.82 to 0.88), with a significantly lower variability with absolute methods compared to 41% SUVmax (p < 0.04). Thresholds were found to be specific to each segmentation method and ranged from 295 to 552 cm³. There was a strong correlation between the MTV and patient prognosis regardless of the segmentation method used (p = 0.001 for PFS and OS). The largest inter-observer cut-off variability was observed in the 41% SUVmax method, which resulted in more inter-observer disagreements in the classification of patients between high and low MTV groups. MTV measurements based on absolute SUV criteria were found to be significantly more reproducible than those based on 41% SUVmax criteria. The threshold was specific for each of eight segmentation methods, but all predicted prognosis.

Radiomics analysis of 18F-Choline PET/CT in the prediction of disease outcome in high-risk prostate cancer: an explorative study on machine learning feature classification in 94 patients

OBJECTIVE

The aim of this study was (1) to investigate the application of texture analysis of choline PET/CT images in prostate cancer (PCa) patients and (2) to propose a machine-learning radiomics model able to select PET features predictive of disease progression in PCa patients with a same high-risk class at restaging.

MATERIAL AND METHODS

Ninety-four high-risk PCa patients who underwent restaging Cho-PET/CT were analyzed. Follow-up data were recorded for a minimum of 13 months after the PET/CT scan. PET images were imported in LIFEx toolbox to extract 51 features from each lesion. A statistical system based on correlation matrix and point-biserial-correlation coefficient has been implemented for features reduction and selection, while Discriminant analysis (DA) was used as a method for features classification in a whole sample and sub-groups for primary tumor or local relapse (T), nodal disease (N), and metastatic disease (M).

RESULTS

In the whole group, 2 feature (HISTO_Entropy_log10; HISTO_Energy_Uniformity) results were able to discriminate the occurrence of disease progression at follow-up, obtaining the best performance in DA classification (sensitivity 47.1%, specificity 76.5%, positive predictive value (PPV) 46.7%, and accuracy 67.6%). In the sub-group analysis, the best performance in DA classification for T was obtained by selecting 3 features (SUVmin; SHAPE_Sphericity; GLCM_Correlation) with a sensitivity of 91.6%, specificity 84.1%, PPV 79.1%, and accuracy 87%; for N by selecting 2 features (HISTO = _Energy Uniformity; GLZLM_SZLGE) with a sensitivity of 68.1%, specificity 91.4%, PPV 83%, and accuracy 82.6%; and for M by selecting 2 features (HISTO_Entropy_log10 - HISTO_Entropy_log2) with a sensitivity 64.4%, specificity 74.6%, PPV 40.6%, and accuracy 72.5%.

CONCLUSION

This machine learning model demonstrated to be feasible and useful to select Cho-PET features for T, N, and M with valuable association with high-risk PCa patients' outcomes.

KEY POINTS

• Artificial intelligence applications are feasible and useful to select Cho-PET features. • Our model demonstrated the presence of specific features for T, N, and M with valuable association with high-risk PCa patients' outcomes. • Further prospective studies are necessary to confirm our results and to develop the application of artificial intelligence in PET imaging of PCa.

Deep Learning-Based Methods for Prostate Segmentation in Magnetic Resonance Imaging

Magnetic Resonance Imaging-based prostate segmentation is an essential task for adaptive radiotherapy and for radiomics studies whose purpose is to identify associations between imaging features and patient outcomes. Because manual delineation is a time-consuming task, we present three deep-learning (DL) approaches, namely UNet, efficient neural network (ENet), and efficient residual factorized convNet (ERFNet), whose aim is to tackle the fully-automated, real-time, and 3D delineation process of the prostate gland on T2-weighted MRI. While UNet is used in many biomedical image delineation applications, ENet and ERFNet are mainly applied in self-driving cars to compensate for limited hardware availability while still achieving accurate segmentation. We apply these models to a limited set of 85 manual prostate segmentations using the k-fold validation strategy and the Tversky loss function and we compare their results. We find that ENet and UNet are more accurate than ERFNet, with ENet much faster than UNet. Specifically, ENet obtains a dice similarity coefficient of 90.89% and a segmentation time of about 6 s using central processing unit (CPU) hardware to simulate real clinical conditions where graphics processing unit (GPU) is not always available. In conclusion, ENet could be efficiently applied for prostate delineation even in small image training datasets with potential benefit for patient management personalization.

Deep learning approach for the segmentation of aneurysmal ascending aorta

Diagnosis of ascending thoracic aortic aneurysm (ATAA) is based on the measurement of the maximum aortic diameter, but size is not a good predictor of the risk of adverse events. There is growing interest in the development of novel image-derived risk strategies to improve patient risk management towards a highly individualized level. In this study, the feasibility and efficacy of deep learning for the automatic segmentation of ATAAs was investigated using UNet, ENet, and ERFNet techniques. Specifically, CT angiography done on 72 patients with ATAAs and different valve morphology (i.e., tricuspid aortic valve, TAV, and bicuspid aortic valve, BAV) were semi-automatically segmented with Mimics software (Materialize NV, Leuven, Belgium), and then used for training of the tested deep learning models. The segmentation performance in terms of accuracy and time inference were compared using several parameters. All deep learning models reported a dice score higher than 88%, suggesting a good agreement between predicted and manual ATAA segmentation. We found that the ENet and UNet are more accurate than ERFNet, with the ENet much faster than UNet. This study demonstrated that deep learning models can rapidly segment and quantify the 3D geometry of ATAAs with high accuracy, thereby facilitating the expansion into clinical workflow of personalized approach to the management of patients with ATAAs.

Lung Segmentation on High-Resolution Computerized Tomography Images Using Deep Learning: A Preliminary Step for Radiomics Studies

BACKGROUND

The aim of this work is to identify an automatic, accurate, and fast deep learning segmentation approach, applied to the parenchyma, using a very small dataset of high-resolution computed tomography images of patients with idiopathic pulmonary fibrosis. In this way, we aim to enhance the methodology performed by healthcare operators in radiomics studies where operator-independent segmentation methods must be used to correctly identify the target and, consequently, the texture-based prediction model.

METHODS

Two deep learning models were investigated: (i) U-Net, already used in many biomedical image segmentation tasks, and (ii) E-Net, used for image segmentation tasks in self-driving cars, where hardware availability is limited and accurate segmentation is critical for user safety. Our small image dataset is composed of 42 studies of patients with idiopathic pulmonary fibrosis, of which only 32 were used for the training phase. We compared the performance of the two models in terms of the similarity of their segmentation outcome with the gold standard and in terms of their resources' requirements.

RESULTS

E-Net can be used to obtain accurate (dice similarity coefficient = 95.90%), fast (20.32 s), and clinically acceptable segmentation of the lung region.

CONCLUSIONS

We demonstrated that deep learning models can be efficiently applied to rapidly segment and quantify the parenchyma of patients with pulmonary fibrosis, without any radiologist supervision, in order to produce user-independent results.

Fully 3D Active Surface with Machine Learning for PET Image Segmentation

In order to tackle three-dimensional tumor volume reconstruction from Positron Emission Tomography (PET) images, most of the existing algorithms rely on the segmentation of independent PET slices. To exploit cross-slice information, typically overlooked in these 2D implementations, I present an algorithm capable of achieving the volume reconstruction directly in 3D, by leveraging an active surface algorithm. The evolution of such surface performs the segmentation of the whole stack of slices simultaneously and can handle changes in topology. Furthermore, no artificial stop condition is required, as the active surface will naturally converge to a stable topology. In addition, I include a machine learning component to enhance the accuracy of the segmentation process. The latter consists of a forcing term based on classification results from a discriminant analysis algorithm, which is included directly in the mathematical formulation of the energy function driving surface evolution. It is worth noting that the training of such a component requires minimal data compared to more involved deep learning methods. Only eight patients (i.e., two lung, four head and neck, and two brain cancers) were used for training and testing the machine learning component, while fifty patients (i.e., 10 lung, 25 head and neck, and 15 brain cancers) were used to test the full 3D reconstruction algorithm. Performance evaluation is based on the same dataset of patients discussed in my previous work, where the segmentation was performed using the 2D active contour. The results confirm that the active surface algorithm is superior to the active contour algorithm, outperforming the earlier approach on all the investigated anatomical districts with a dice similarity coefficient of 90.47 ± 2.36% for lung cancer, 88.30 ± 2.89% for head and neck cancer, and 90.29 ± 2.52% for brain cancer. Based on the reported results, it can be claimed that the migration into a 3D system yielded a practical benefit justifying the effort to rewrite an existing 2D system for PET imaging segmentation.

A preliminary PET radiomics study of brain metastases using a fully automatic segmentation method

Background

Positron Emission Tomography (PET) is increasingly utilized in radiomics studies for treatment evaluation purposes. Nevertheless, lesion volume identification in PET images is a critical and still challenging step in the process of radiomics, due to the low spatial resolution and high noise level of PET images. Currently, the biological target volume (BTV) is manually contoured by nuclear physicians, with a time expensive and operator-dependent procedure.

This study aims to obtain BTVs from cerebral metastases in patients who underwent L-[¹¹C]methionine (11C-MET) PET, using a fully automatic procedure and to use these BTVs to extract radiomics features to stratify between patients who respond to treatment or not. For these purposes, 31 brain metastases, for predictive evaluation, and 25 ones, for follow-up evaluation after treatment, were delineated using the proposed method. Successively, 11C-MET PET studies and related volumetric segmentations were used to extract 108 features to investigate the potential application of radiomics analysis in patients with brain metastases. A novel statistical system has been implemented for feature reduction and selection, while discriminant analysis was used as a method for feature classification.

Results

For predictive evaluation, 3 features (asphericity, low-intensity run emphasis, and complexity) were able to discriminate between responder and non-responder patients, after feature reduction and selection. Best performance in patient discrimination was obtained using the combination of the three selected features (sensitivity 81.23%, specificity 73.97%, and accuracy 78.27%) compared to the use of all features. Secondly, for follow-up evaluation, 8 features (SUV_mean, SUL_peak, SUV_min, SUL_peak prod-surface-area, SUV_mean prod-sphericity, surface mean SUV 3, SUL_peak prod-sphericity, and second angular moment) were selected with optimal performance in discriminant analysis classification (sensitivity 86.28%, specificity 87.75%, and accuracy 86.57%) outperforming the use of all features.

Conclusions

The proposed system is able i) to extract 108 features for each automatically segmented lesion and ii) to select a sub-panel of 11C-MET PET features (3 and 8 in the case of predictive and follow-up evaluation), with valuable association with patient outcome. We believe that our model can be useful to improve treatment response and prognosis evaluation, potentially allowing the personalization of cancer treatment plans.