Development and Implementation of an Innovative Framework for Automated Radiomics Analysis in Neuroimaging

Radiomics represents an innovative approach to medical image analysis, enabling comprehensive quantitative evaluation of radiological images through advanced image processing and Machine or Deep Learning algorithms. This technique uncovers intricate data patterns beyond human visual detection. Traditionally, executing a radiomic pipeline involves multiple standardized phases across several software platforms. This could represent a limit that was overcome thanks to the development of the matRadiomics application. MatRadiomics, a freely available, IBSI-compliant tool, features its intuitive Graphical User Interface (GUI), facilitating the entire radiomics workflow from DICOM image importation to segmentation, feature selection and extraction, and Machine Learning model construction. In this project, an extension of matRadiomics was developed to support the importation of brain MRI images and segmentations in NIfTI format, thus extending its applicability to neuroimaging. This enhancement allows for the seamless execution of radiomic pipelines within matRadiomics, offering substantial advantages to the realm of neuroimaging.

Complex central venous catheter for dialysis: interventional radiology experience in insertion and management of their complications

BACKGROUND

CVCs are defined 'complex' when they are inserted through non-conventional accesses or positioned in non-usual sites or substituted by IR endovascular procedures. We report our experience in using diagnostic and interventional radiology techniques for complex CVC insertion and management; we recommend some precautions and techniques that could lead to long-term availability of central venous access and to avoid non-conventional sites CVC insertion.

METHODS

We retrospectively evaluated 617 patients, between January 2010 and December 2019, (mean age 71 ± 13; male 448/617), treated in our department for insertion of tunnelled CVC for haemodialysis.

RESULTS

Among 617 patients, 241 cases (39%) are considered 'complex' because they required either a PTA with or without stenting to restore/maintain venous access or had an unusual positioning site or required unconventional access. A direct correlation between CT angiography and PTA (r = 0.95; p-value <0.001) and an inverse correlation between CT angiography and unconventional 'rescue' access (r = -0.92; p-value <0.001) were found.

CONCLUSIONS

Precise pre-operative planning of treatment in a multidisciplinary setting and diagnostic and interventional radiology procedures knowledge allows reducing complex catheterisms in haemodialysis patient.

A Critical Analysis of the Robustness of Radiomics to Variations in Segmentation Methods in 18F-PSMA-1007 PET Images of Patients Affected by Prostate Cancer

BACKGROUND

Radiomics shows promising results in supporting the clinical decision process, and much effort has been put into its standardization, thus leading to the Imaging Biomarker Standardization Initiative (IBSI), that established how radiomics features should be computed. However, radiomics still lacks standardization and many factors, such as segmentation methods, limit study reproducibility and robustness.

AIM

We investigated the impact that three different segmentation methods (manual, thresholding and region growing) have on radiomics features extracted from 18F-PSMA-1007 Positron Emission Tomography (PET) images of 78 patients (43 Low Risk, 35 High Risk). Segmentation was repeated for each patient, thus leading to three datasets of segmentations. Then, feature extraction was performed for each dataset, and 1781 features (107 original, 930 Laplacian of Gaussian (LoG) features, 744 wavelet features) were extracted. Feature robustness and reproducibility were assessed through the intra class correlation coefficient (ICC) to measure agreement between the three segmentation methods. To assess the impact that the three methods had on machine learning models, feature selection was performed through a hybrid descriptive-inferential method, and selected features were given as input to three classifiers, K-Nearest Neighbors (KNN), Support Vector Machines (SVM), Linear Discriminant Analysis (LDA), Random Forest (RF), AdaBoost and Neural Networks (NN), whose performance in discriminating between low-risk and high-risk patients have been validated through 30 times repeated five-fold cross validation.

CONCLUSIONS

Our study showed that segmentation methods influence radiomics features and that Shape features were the least reproducible (average ICC: 0.27), while GLCM features the most reproducible. Moreover, feature reproducibility changed depending on segmentation type, resulting in 51.18% of LoG features exhibiting excellent reproducibility (range average ICC: 0.68-0.87) and 47.85% of wavelet features exhibiting poor reproducibility that varied between wavelet sub-bands (range average ICC: 0.34-0.80) and resulted in the LLL band showing the highest average ICC (0.80). Finally, model performance showed that region growing led to the highest accuracy (74.49%), improved sensitivity (84.38%) and AUC (79.20%) in contrast with manual segmentation.

Radiomics Analyses to Predict Histopathology in Patients with Metastatic Testicular Germ Cell Tumors before Post-Chemotherapy Retroperitoneal Lymph Node Dissection

BACKGROUND

The identification of histopathology in metastatic non-seminomatous testicular germ cell tumors (TGCT) before post-chemotherapy retroperitoneal lymph node dissection (PC-RPLND) holds significant potential to reduce treatment-related morbidity in young patients, addressing an important survivorship concern.

AIM

To explore this possibility, we conducted a study investigating the role of computed tomography (CT) radiomics models that integrate clinical predictors, enabling personalized prediction of histopathology in metastatic non-seminomatous TGCT patients prior to PC-RPLND. In this retrospective study, we included a cohort of 122 patients.

METHODS

Using dedicated radiomics software, we segmented the targets and extracted quantitative features from the CT images. Subsequently, we employed feature selection techniques and developed radiomics-based machine learning models to predict histological subtypes. To ensure the robustness of our procedure, we implemented a 5-fold cross-validation approach. When evaluating the models' performance, we measured metrics such as the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, precision, and F-score.

RESULT

Our radiomics model based on the Support Vector Machine achieved an optimal average AUC of 0.945.

CONCLUSIONS

The presented CT-based radiomics model can potentially serve as a non-invasive tool to predict histopathological outcomes, differentiating among fibrosis/necrosis, teratoma, and viable tumor in metastatic non-seminomatous TGCT before PC-RPLND. It has the potential to be considered a promising tool to mitigate the risk of over- or under-treatment in young patients, although multi-center validation is critical to confirm the clinical utility of the proposed radiomics workflow.

Artificial Intelligence for Classifying the Relationship between Impacted Third Molar and Mandibular Canal on Panoramic Radiographs

The purpose of this investigation was to evaluate the diagnostic performance of two convolutional neural networks (CNNs), namely ResNet-152 and VGG-19, in analyzing, on panoramic images, the rapport that exists between the lower third molar (MM3) and the mandibular canal (MC), and to compare this performance with that of an inexperienced observer (a sixth year dental student). Utilizing the k-fold cross-validation technique, 142 MM3 images, cropped from 83 panoramic images, were split into 80% as training and validation data and 20% as test data. They were subsequently labeled by an experienced radiologist as the gold standard. In order to compare the diagnostic capabilities of CNN algorithms and the inexperienced observer, the diagnostic accuracy, sensitivity, specificity, and positive predictive value (PPV) were determined. ResNet-152 achieved a mean sensitivity, specificity, PPV, and accuracy, of 84.09%, 94.11%, 92.11%, and 88.86%, respectively. VGG-19 achieved 71.82%, 93.33%, 92.26%, and 85.28% regarding the aforementioned characteristics. The dental student's diagnostic performance was respectively 69.60%, 53.00%, 64.85%, and 62.53%. This work demonstrated the potential use of deep CNN architecture for the identification and evaluation of the contact between MM3 and MC in panoramic pictures. In addition, CNNs could be a useful tool to assist inexperienced observers in more accurately identifying contact relationships between MM3 and MC on panoramic images.

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.

An Overview of In Vitro Assays of 64Cu-, 68Ga-, 125I-, and 99mTc-Labelled Radiopharmaceuticals Using Radiometric Counters in the Era of Radiotheranostics

Radionuclides are unstable isotopes that mainly emit alpha (α), beta (β) or gamma (γ) radiation through radiation decay. Therefore, they are used in the biomedical field to label biomolecules or drugs for diagnostic imaging applications, such as positron emission tomography (PET) and/or single-photon emission computed tomography (SPECT). A growing field of research is the development of new radiopharmaceuticals for use in cancer treatments. Preclinical studies are the gold standard for translational research. Specifically, in vitro radiopharmaceutical studies are based on the use of radiopharmaceuticals directly on cells. To date, radiometric β- and γ-counters are the only tools able to assess a preclinical in vitro assay with the aim of estimating uptake, retention, and release parameters, including time- and dose-dependent cytotoxicity and kinetic parameters. This review has been designed for researchers, such as biologists and biotechnologists, who would like to approach the radiobiology field and conduct in vitro assays for cellular radioactivity evaluations using radiometric counters. To demonstrate the importance of in vitro radiopharmaceutical assays using radiometric counters with a view to radiogenomics, many studies based on ⁶⁴Cu-, ⁶⁸Ga-, ¹²⁵I-, and ^99mTc-labeled radiopharmaceuticals have been revised and summarized in this manuscript.

Phenotyping the Histopathological Subtypes of Non-Small-Cell Lung Carcinoma: How Beneficial Is Radiomics?

The aim of this study was to investigate the usefulness of radiomics in the absence of well-defined standard guidelines. Specifically, we extracted radiomics features from multicenter computed tomography (CT) images to differentiate between the four histopathological subtypes of non-small-cell lung carcinoma (NSCLC). In addition, the results that varied with the radiomics model were compared. We investigated the presence of the batch effects and the impact of feature harmonization on the models' performance. Moreover, the question on how the training dataset composition influenced the selected feature subsets and, consequently, the model's performance was also investigated. Therefore, through combining data from the two publicly available datasets, this study involves a total of 152 squamous cell carcinoma (SCC), 106 large cell carcinoma (LCC), 150 adenocarcinoma (ADC), and 58 no other specified (NOS). Through the matRadiomics tool, which is an example of Image Biomarker Standardization Initiative (IBSI) compliant software, 1781 radiomics features were extracted from each of the malignant lesions that were identified in CT images. After batch analysis and feature harmonization, which were based on the ComBat tool and were integrated in matRadiomics, the datasets (the harmonized and the non-harmonized) were given as an input to a machine learning modeling pipeline. The following steps were articulated: (i) training-set/test-set splitting (80/20); (ii) a Kruskal-Wallis analysis and LASSO linear regression for the feature selection; (iii) model training; (iv) a model validation and hyperparameter optimization; and (v) model testing. Model optimization consisted of a 5-fold cross-validated Bayesian optimization, repeated ten times (inner loop). The whole pipeline was repeated 10 times (outer loop) with six different machine learning classification algorithms. Moreover, the stability of the feature selection was evaluated. Results showed that the batch effects were present even if the voxels were resampled to an isotropic form and whether feature harmonization correctly removed them, even though the models' performances decreased. Moreover, the results showed that a low accuracy (61.41%) was reached when differentiating between the four subtypes, even though a high average area under curve (AUC) was reached (0.831). Further, a NOS subtype was classified as almost completely correct (true positive rate ~90%). The accuracy increased (77.25%) when only the SCC and ADC subtypes were considered, as well as when a high AUC (0.821) was obtained-although harmonization decreased the accuracy to 58%. Moreover, the features that contributed the most to models' performance were those extracted from wavelet decomposed and Laplacian of Gaussian (LoG) filtered images and they belonged to the texture feature class.. In conclusion, we showed that our multicenter data were affected by batch effects, that they could significantly alter the models' performance, and that feature harmonization correctly removed them. Although wavelet features seemed to be the most informative features, an absolute subset could not be identified since it changed depending on the training/testing splitting. Moreover, performance was influenced by the chosen dataset and by the machine learning methods, which could reach a high accuracy in binary classification tasks, but could underperform in multiclass problems. It is, therefore, essential that the scientific community propose a more systematic radiomics approach, focusing on multicenter studies, with clear and solid guidelines to facilitate the translation of radiomics to clinical practice.

CT Rendering and Radiomic Analysis in Post-Chemotherapy Retroperitoneal Lymph Node Dissection for Testicular Cancer to Anticipate Difficulties for Young Surgeons

Post-chemotherapy retroperitoneal lymph node dissection (PC-RPLND) in non-seminomatous germ-cell tumor (NSTGCTs) is a complex procedure. We evaluated whether 3D computed tomography (CT) rendering and their radiomic analysis help predict resectability by junior surgeons. The ambispective analysis was performed between 2016-2021. A prospective group (A) of 30 patients undergoing CT was segmented using the 3D Slicer software while a retrospective group (B) of 30 patients was evaluated with conventional CT (without 3D reconstruction). CatFisher's exact test showed a p-value of 0.13 for group A and 1.0 for Group B. The difference between the proportion test showed a p-value of 0.009149 (IC 0.1-0.63). The proportion of the correct classification showed a p-value of 0.645 (IC 0.55-0.87) for A, and 0.275 (IC 0.11-0.43) for Group B. Furthermore, 13 shape features were extracted: elongation, flatness, volume, sphericity, and surface area, among others. Performing a logistic regression with the entire dataset, n = 60, the results were: Accuracy: 0.7 and Precision: 0.65. Using n = 30 randomly chosen, the best result obtained was Accuracy: 0.73 and Precision: 0.83, with a p-value: 0.025 for Fisher's exact test. In conclusion, the results showed a significant difference in the prediction of resectability with conventional CT versus 3D reconstruction by junior surgeons versus experienced surgeons. Radiomic features used to elaborate an artificial intelligence model improve the prediction of resectability. The proposed model could be of great support in a university hospital, allowing it to plan the surgery and to anticipate complications.

Anti-Arthritic and Anti-Cancer Activities of Polyphenols: A Review of the Most Recent In Vitro Assays

Polyphenols have gained widespread attention as they are effective in the prevention and management of various diseases, including cancer diseases (CD) and rheumatoid arthritis (RA). They are natural organic substances present in fruits, vegetables, and spices. Polyphenols interact with various kinds of receptors and membranes. They modulate different signal cascades and interact with the enzymes responsible for CD and RA. These interactions involve cellular machinery, from cell membranes to major nuclear components, and provide information on their beneficial effects on health. These actions provide evidence for their pharmaceutical exploitation in the treatment of CD and RA. In this review, we discuss different pathways, modulated by polyphenols, which are involved in CD and RA. A search of the most recent relevant publications was carried out with the following criteria: publication date, 2012-2022; language, English; study design, in vitro; and the investigation of polyphenols present in extra virgin olive, grapes, and spices in the context of RA and CD, including, when available, the underlying molecular mechanisms. This review is valuable for clarifying the mechanisms of polyphenols targeting the pathways of senescence and leading to the development of CD and RA treatments. Herein, we focus on research reports that emphasize antioxidant properties.

Radiomics Analysis on Gadoxetate Disodium-Enhanced MRI Predicts Response to Transarterial Embolization in Patients with HCC

Objectives: To explore the potential of radiomics on gadoxetate disodium-enhanced MRI for predicting hepatocellular carcinoma (HCC) response after transarterial embolization (TAE). Methods: This retrospective study included cirrhotic patients treated with TAE for unifocal HCC naïve to treatments. Each patient underwent gadoxetate disodium-enhanced MRI. Radiomics analysis was performed by segmenting the lesions on portal venous (PVP), 3-min transitional, and 20-min hepatobiliary (HBP) phases. Clinical data, laboratory variables, and qualitative features based on LI-RADSv2018 were assessed. Reference standard was based on mRECIST response criteria. Two different radiomics models were constructed, a statistical model based on logistic regression with elastic net penalty (model 1) and a computational model based on a hybrid descriptive-inferential feature extraction method (model 2). Areas under the ROC curves (AUC) were calculated. Results: The final population included 51 patients with HCC (median size 20 mm). Complete and objective responses were obtained in 14 (27.4%) and 29 (56.9%) patients, respectively. Model 1 showed the highest performance on PVP for predicting objective response with an AUC of 0.733, sensitivity of 100%, and specificity of 40.0% in the test set. Model 2 demonstrated similar performances on PVP and HBP for predicting objective response, with an AUC of 0.791, sensitivity of 71.3%, specificity of 61.7% on PVP, and AUC of 0.790, sensitivity of 58.8%, and specificity of 90.1% on HBP. Conclusions: Radiomics models based on gadoxetate disodium-enhanced MRI can achieve good performance for predicting response of HCCs treated with TAE.

Radiomics Analysis of Brain [18F]FDG PET/CT to Predict Alzheimer's Disease in Patients with Amyloid PET Positivity: A Preliminary Report on the Application of SPM Cortical Segmentation, Pyradiomics and Machine-Learning Analysis

BACKGROUND

Early in-vivo diagnosis of Alzheimer's disease (AD) is crucial for accurate management of patients, in particular, to select subjects with mild cognitive impairment (MCI) that may evolve into AD, and to define other types of MCI non-AD patients. The application of artificial intelligence to functional brain [¹⁸F]fluorodeoxyglucose (FDG) positron emission tomography (PET)/computed tomography(CT) aiming to increase diagnostic accuracy in the diagnosis of AD is still undetermined. In this field, we propose a radiomics analysis on advanced imaging segmentation method Statistical Parametric Mapping (SPM)-based completed with a Machine-Learning (ML) application to predict the diagnosis of AD, also by comparing the results with following Amyloid-PET and final clinical diagnosis.

METHODS

From July 2016 to September 2017, 43 patients underwent PET/CT scans with FDG and Florbetaben brain PET/CT and at least 24 months of clinical/instrumental follow-up. Patients were retrospectively evaluated by a multidisciplinary team (MDT = Neurologist, Psychologist, Radiologist, Nuclear Medicine Physician, Laboratory Clinic) at the G. Giglio Institute in Cefalù, Italy. Starting from the cerebral segmentations applied by SPM on the main cortical macro-areas of each patient, Pyradiomics was used for the feature extraction process; subsequently, an innovative descriptive-inferential mixed sequential approach and a machine learning algorithm (i.e., discriminant analysis) were used to obtain the best diagnostic performance in prediction of amyloid deposition and the final diagnosis of AD.

RESULTS

A total of 11 radiomics features significantly predictive of cortical beta-amyloid deposition (n = 6) and AD (n = 5) were found. Among them, two higher-order features (original_glcm_Idmn and original_glcm_Id), extracted from the limbic enthorinal cortical area (ROI-1) in the FDG-PET/CT images, predicted the positivity of Amyloid-PET/CT scans with maximum values of sensitivity (SS), specificity (SP), precision (PR) and accuracy (AC) of 84.92%, 75.13%, 73.75%, and 79.56%, respectively. Conversely, for the prediction of the clinical-instrumental final diagnosis of AD, the best performance was obtained by two higher-order features (original_glcm_MCC and original_glcm_Maximum Probability) extracted from ROI-2 (frontal cortex) with a SS, SP, PR and AC of 75.16%, 80.50%, 77.68%, and 78.05%, respectively, and by one higher-order feature (original_glcm_Idmn) extracted from ROI-3 (medial Temporal cortex; SS = 80.88%, SP = 76.85%, PR = 75.63%, AC = 78.76%.

CONCLUSIONS

The results obtained in this preliminary study support advanced segmentation of cortical areas typically involved in early AD on FDG PET/CT brain images, and radiomics analysis for the identification of specific high-order features to predict Amyloid deposition and final diagnosis of AD.

[68Ga]DOTATOC PET/CT Radiomics to Predict the Response in GEP-NETs Undergoing [177Lu]DOTATOC PRRT: The “Theragnomics” Concept

Despite impressive results, almost 30% of NET do not respond to PRRT and no well-established criteria are suitable to predict response. Therefore, we assessed the predictive value of radiomics [68Ga]DOTATOC PET/CT images pre-PRRT in metastatic GEP NET. We retrospectively analyzed the predictive value of radiomics in 324 SSTR-2-positive lesions from 38 metastatic GEP-NET patients (nine G1, 27 G2, and two G3) who underwent restaging [68Ga]DOTATOC PET/CT before complete PRRT with [177Lu]DOTATOC. Clinical, laboratory, and radiological follow-up data were collected for at least six months after the last cycle. Through LifeX, we extracted 65 PET features for each lesion. Grading, PRRT number of cycles, and cumulative activity, pre- and post-PRRT CgA values were also considered as additional clinical features. [68Ga]DOTATOC PET/CT follow-up with the same scanner for each patient determined the disease status (progression vs. response in terms of stability/reduction/disappearance) for each lesion. All features (PET and clinical) were also correlated with follow-up data in a per-site analysis (liver, lymph nodes, and bone), and for features significantly associated with response, the Δradiomics for each lesion was assessed on follow-up [68Ga]DOTATOC PET/CT performed until nine months post-PRRT. A statistical system based on the point-biserial correlation and logistic regression analysis was used for the reduction and selection of the features. Discriminant analysis was used, instead, to obtain the predictive model using the k-fold strategy to split data into training and validation sets. From the reduction and selection process, HISTO_Skewness and HISTO_Kurtosis were able to predict response with an area under the receiver operating characteristics curve (AUC ROC), sensitivity, and specificity of 0.745, 80.6%, 67.2% and 0.722, 61.2%, 75.9%, respectively. Moreover, a combination of three features (HISTO_Skewness; HISTO_Kurtosis, and Grading) did not improve the AUC significantly with 0.744. SUVmax. However, it could not predict response to PRRT (p = 0.49, AUC 0.523). The presented preliminary “theragnomics” model proved to be superior to conventional quantitative parameters to predict the response of GEP-NET lesions in patients treated with complete [177Lu]DOTATOC PRRT, regardless of the lesion site.

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.

Diagnostic performance of qualitative and radiomics approach to parotid gland tumors: which is the added benefit of texture analysis?

OBJECTIVE

To investigate whether MRI-based texture analysis improves diagnostic performance for the diagnosis of parotid gland tumors compared to conventional radiological approach.

METHODS

Patients with parotid gland tumors who underwent salivary glands MRI between 2008 and 2019 were retrospectively selected. MRI analysis included a qualitative assessment by two radiologists (one of which subspecialized on head and neck imaging), and texture analysis on various sequences. Diagnostic performances including sensitivity, specificity, and area under the receiver operating characteristic curve (AUROC) of qualitative features, radiologists' diagnosis, and radiomic models were evaluated.

RESULTS

Final study cohort included 57 patients with 74 tumors (27 pleomorphic adenomas, 40 Warthin tumors, 8 malignant tumors). Sensitivity, specificity, and AUROC for the diagnosis of malignancy were 75%, 97% and 0.860 for non-subspecialized radiologist, 100%, 94% and 0.970 for subspecialized radiologist and 57.2%, 93.4%, and 0.927 using a MRI radiomics model obtained combining texture analysis on various MRI sequences. Sensitivity, specificity, and AUROC for the differential diagnosis between pleomorphic adenoma and Warthin tumors were 81.5%, 70%, and 0.757 for non-subspecialized radiologist, 81.5%, 95% and 0.882 for subspecialized radiologist and 70.8%, 82.5%, and 0.808 using a MRI radiomics model based on texture analysis of T₂ weighted sequence. A combined radiomics model obtained with all MRI sequences yielded a sensitivity of 91.5% for the diagnosis of pleomorphic adenoma.

CONCLUSION

MRI qualitative radiologist assessment outperforms radiomic analysis for the diagnosis of malignancy. MRI predictive radiomics models improves the diagnostic performance of non-subspecialized radiologist for the differential diagnosis between pleomorphic adenoma and Warthin tumor, achieving similar performance to the subspecialized radiologist.

ADVANCES IN KNOWLEDGE

Radiologists outperform radiomic analysis for the diagnosis of malignant parotid gland tumors, with some MRI qualitative features such as ill-defined margins, perineural spread, invasion of adjacent structures and enlarged lymph nodes being highly specific for malignancy. A radiomic model based on texture analysis of T₂ weighted images yields higher specificity for the diagnosis of pleomorphic adenoma compared to a radiologist non-subspecialized in head and neck radiology, thus minimizing false-positive pleomorphic adenoma diagnosis rate and reducing unnecessary surgical complications.

Artificial Neural Networks in Cardiovascular Diseases and its Potential for Clinical Application in Molecular Imaging

In medical imaging, Artificial Intelligence is described as the ability of a system to properly interpret and learn from external data, acquiring knowledge to achieve specific goals and tasks through flexible adaptation. The number of possible applications of Artificial Intelligence is also huge in clinical medicine and cardiovascular diseases. To describe for the first time in literature, the main results of articles about Artificial Intelligence potential for clinical applications in molecular imaging techniques, and to describe its advancements in cardiovascular diseases assessed with nuclear medicine imaging modalities. A comprehensive search strategy was used based on SCOPUS and PubMed databases. From all studies published in English, we selected the most relevant articles that evaluated the technological insights of AI in nuclear cardiology applications. Artificial Intelligence may improve patient care in many different fields, from the semi-automatization of the medical work, through the technical aspect of image preparation, interpretation, the calculation of additional factors based on data obtained during scanning, to the prognostic prediction and risk-- group selection. Myocardial implementation of Artificial Intelligence algorithms in nuclear cardiology can improve and facilitate the diagnostic and predictive process, and global patient care. Building large databases containing clinical and image data is a first but essential step to create and train automated diagnostic/prognostic models able to help the clinicians to make unbiased and faster decisions for precision healthcare.

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.

Deep Learning Network for Segmentation of the Prostate Gland With Median Lobe Enlargement in T2-weighted MR Images: Comparison With Manual Segmentation Method

PURPOSE

Aim of this study was to evaluate a fully automated deep learning network named Efficient Neural Network (ENet) for segmentation of prostate gland with median lobe enlargement compared to manual segmentation.

MATERIALS AND METHODS

One-hundred-three patients with median lobe enlargement on prostate MRI were retrospectively included. Ellipsoid formula, manual segmentation and automatic segmentation were used for prostate volume estimation using T2 weighted MRI images. ENet was used for automatic segmentation; it is a deep learning network developed for fast inference and high accuracy in augmented reality and automotive scenarios. Student t-test was performed to compare prostate volumes obtained with ellipsoid formula, manual segmentation, and automated segmentation. To provide an evaluation of the similarity or difference to manual segmentation, sensitivity, positive predictive value (PPV), dice similarity coefficient (DSC), volume overlap error (VOE), and volumetric difference (VD) were calculated.

RESULTS

Differences between prostate volume obtained from ellipsoid formula versus manual segmentation and versus automatic segmentation were statistically significant (P < 0.049318 and P < 0.034305, respectively), while no statistical difference was found between volume obtained from manual versus automatic segmentation (P = 0.438045). The performance of ENet versus manual segmentations was good providing a sensitivity of 93.51%, a PPV of 87.93%, a DSC of 90.38%, a VOE of 17.32% and a VD of 6.85%.

CONCLUSION

The presence of median lobe enlargement may lead to MRI volume overestimation when using the ellipsoid formula so that a segmentation method is recommended. ENet volume estimation showed great accuracy in evaluation of prostate volume similar to that of manual segmentation.

Deep Learning Whole-Gland and Zonal Prostate Segmentation on a Public MRI Dataset

BACKGROUND

Prostate volume, as determined by magnetic resonance imaging (MRI), is a useful biomarker both for distinguishing between benign and malignant pathology and can be used either alone or combined with other parameters such as prostate-specific antigen.

PURPOSE

This study compared different deep learning methods for whole-gland and zonal prostate segmentation.

STUDY TYPE

Retrospective.

POPULATION

A total of 204 patients (train/test = 99/105) from the PROSTATEx public dataset.

FIELD STRENGTH/SEQUENCE

A 3 T, TSE T₂ -weighted.

ASSESSMENT

Four operators performed manual segmentation of the whole-gland, central zone + anterior stroma + transition zone (TZ), and peripheral zone (PZ). U-net, efficient neural network (ENet), and efficient residual factorized ConvNet (ERFNet) were trained and tuned on the training data through 5-fold cross-validation to segment the whole gland and TZ separately, while PZ automated masks were obtained by the subtraction of the first two.

STATISTICAL TESTS

Networks were evaluated on the test set using various accuracy metrics, including the Dice similarity coefficient (DSC). Model DSC was compared in both the training and test sets using the analysis of variance test (ANOVA) and post hoc tests. Parameter number, disk size, training, and inference times determined network computational complexity and were also used to assess the model performance differences. A P < 0.05 was selected to indicate the statistical significance.

RESULTS

The best DSC (P < 0.05) in the test set was achieved by ENet: 91% ± 4% for the whole gland, 87% ± 5% for the TZ, and 71% ± 8% for the PZ. U-net and ERFNet obtained, respectively, 88% ± 6% and 87% ± 6% for the whole gland, 86% ± 7% and 84% ± 7% for the TZ, and 70% ± 8% and 65 ± 8% for the PZ. Training and inference time were lowest for ENet.

DATA CONCLUSION

Deep learning networks can accurately segment the prostate using T₂ -weighted images.

EVIDENCE LEVEL

4 TECHNICAL EFFICACY: Stage 2.

Radiomics and Prostate MRI: Current Role and Future Applications

Multiparametric prostate magnetic resonance imaging (mpMRI) is widely used as a triage test for men at a risk of prostate cancer. However, the traditional role of mpMRI was confined to prostate cancer staging. Radiomics is the quantitative extraction and analysis of minable data from medical images; it is emerging as a promising tool to detect and categorize prostate lesions. In this paper we review the role of radiomics applied to prostate mpMRI in detection and localization of prostate cancer, prediction of Gleason score and PI-RADS classification, prediction of extracapsular extension and of biochemical recurrence. We also provide a future perspective of artificial intelligence (machine learning and deep learning) applied to the field of prostate cancer.

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.

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.

Choline PET/CT features to predict survival outcome in high risk prostate cancer restaging: a preliminary machine-learning radiomics study

BACKGROUND

Radiomic features are increasingly utilized to evaluate tumor heterogeneity in PET imaging but to date its role has not been investigated for Cho-PET in prostate cancer. The potential application of radiomics features analysis using a machine-learning radiomics algorithm was evaluated to select 18F-Cho PET/CT imaging features to predict disease progression in PCa.

METHODS

We retrospectively analyzed high-risk PCa patients who underwent restaging 18F-Cho PET/CT from November 2013 to May 2018. 18F-Cho PET/CT studies and related structures containing volumetric segmentations were imported in the "CGITA" toolbox to extract imaging features from each lesion. A Machine-learning model has been adapted using NCA for feature selection, while DA was used as a method for feature classification and performance analysis.

RESULTS

106 imaging features were extracted for 46 lesions for a total of 4876 features analyzed. No significant differences between the training and validating sets in terms of age, sex, PSA values, lesion location and size (p > 0.05) were demonstrated by the machine-learning model. Thirteen features were able to discriminate FU disease status after NCA selection. Best performance in DA classification was obtained using the combination of the 13 selected features (sensitivity 74%, specificity 58% and accuracy 66%) compared to the use of all features (sensitivity 40%, specificity 52%, and accuracy 51%). Per-site performance of the 13 selected features in DA classification were as follow: T= sensitivity 63%, specificity 83%, accuracy 71%; N= sensitivity 87%, specificity 91% of and accuracy 90%; bone-M= sensitivity 33%, specificity 77% and accuracy 66%.

CONCLUSIONS

An artificial intelligence model demonstrated to be feasible and able to select a panel of 18F-Cho PET/CT features with valuable association with PCa patients' outcome.

Performance of Radiomics Features in the Quantification of Idiopathic Pulmonary Fibrosis from HRCT

BACKGROUND

Our study assesses the diagnostic value of different features extracted from high resolution computed tomography (HRCT) images of patients with idiopathic pulmonary fibrosis. These features are investigated over a range of HRCT lung volume measurements (in Hounsfield Units) for which no prior study has yet been published. In particular, we provide a comparison of their diagnostic value at different Hounsfield Unit (HU) thresholds, including corresponding pulmonary functional tests.

METHODS

We consider thirty-two patients retrospectively for whom both HRCT examinations and spirometry tests were available. First, we analyse the HRCT histogram to extract quantitative lung fibrosis features. Next, we evaluate the relationship between pulmonary function and the HRCT features at selected HU thresholds, namely -200 HU, 0 HU, and +200 HU. We model the relationship using a Poisson approximation to identify the measure with the highest log-likelihood.

RESULTS

Our Poisson models reveal no difference at the -200 and 0 HU thresholds. However, inferential conclusions change at the +200 HU threshold. Among the HRCT features considered, the percentage of normally attenuated lung at -200 HU shows the most significant diagnostic utility.

CONCLUSIONS

The percentage of normally attenuated lung can be used together with qualitative HRCT assessment and pulmonary function tests to enhance the idiopathic pulmonary fibrosis (IPF) diagnostic process.

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

Delineation of tumours in Positron Emission Tomography (PET) plays a crucial role in accurate diagnosis and radiotherapy treatment planning. In this context, it is of outmost importance to devise efficient and operator-independent segmentation algorithms capable of reconstructing the tumour three-dimensional (3D) shape. In previous work, we proposed a system for 3D tumour delineation on PET data (expressed in terms of Standardized Uptake Value - SUV), based on a two-step approach. Step 1 identified the slice enclosing the maximum SUV and generated a rough contour surrounding it. Such contour was then used to initialize step 2, where the 3D shape of the tumour was obtained by separately segmenting 2D PET slices, leveraging the slice-by-slice marching approach. Additionally, we combined active contours and machine learning components to improve performance. Despite its success, the slice marching approach poses unnecessary limitations that are naturally removed by performing the segmentation directly in 3D. In this paper, we migrate our system into 3D. In particular, the segmentation in step 2 is now performed by evolving an active surface directly in the 3D space. The key points of such an advancement are that it performs the shape reconstruction on the whole stack of slices simultaneously, naturally leveraging cross-slice information that could not be exploited before. Additionally, it does not require any specific stopping condition, as the active surface naturally reaches a stable topology once convergence is achieved. Performance of this fully 3D approach is evaluated on the same dataset discussed in our previous work, which comprises fifty PET scans of lung, head and neck, and brain tumours. The results have confirmed that a benefit is indeed achieved in practice for all investigated anatomical districts, both quantitatively, through a set of commonly used quality indicators (dice similarity coefficient >87.66%, Hausdorff distance < 1.48 voxel and Mahalanobis distance < 0.82 voxel), and qualitatively in terms of Likert score (>3 in 54% of the tumours).

18F-Florbetaben PET/CT to Assess Alzheimer's Disease: A new Analysis Method for Regional Amyloid Quantification

BACKGROUND AND PURPOSE

While AD can be definitively confirmed by postmortem histopathologic examination, in vivo imaging may improve the clinician's ability to identify AD at the earliest stage. The aim of the study was to test the performance of amyloid PET using new processing imaging algorithm for more precise diagnosis of AD.

METHODS

Amyloid PET results using a new processing imaging algorithm (MRI-Less and AAL Atlas) were correlated with clinical, cognitive status, CSF analysis, and other imaging. The regional SUVR using the white matter of cerebellum as reference region and scores from clinical and cognitive tests were used to create ROC curves. Leave-one-out cross-validation was carried out to validate the results.

RESULTS

Forty-four consecutive patients with clinical evidence of dementia, were retrospectively evaluated. Amyloid PET scan was positive in 26/44 patients with dementia. After integration with 18F-FDG PET, clinical data and CSF protein levels, 22 of them were classified as AD, the remaining 4 as vascular or frontotemporal dementia. Amyloid and FDG PET, CDR 1, CSF Tau, and p-tau levels showed the best true positive and true negative rates (amyloid PET: AUC = .85, sensitivity .91, specificity .79). A SUVR value of 1.006 in the inferior frontal cortex and of 1.03 in the precuneus region was the best cutoff SUVR value and showed a good correlation with the diagnosis of AD. Thirteen of 44 amyloid PET positive patients have been enrolled in clinical trials using antiamyloid approaches.

CONCLUSIONS

Amyloid PET using SPM-normalized SUVR analysis showed high predictive power for the differential diagnosis of AD.

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

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

Assessment of survival in patients with idiopathic pulmonary fibrosis using quantitative HRCT indexes

Background: The assessment of Idiopathic Pulmonary Fibrosis (IPF) using HRCT requires great experience and is limited by a significant inter-observer variability, even between trained radiologists. The evaluation of HRCT through automated quantitative analysis may hopefully solve this problem. The accuracy of CT-histogram derived indexes in the assessment of survival in IPF patients has been poorly studied. Methods: Forty-two patients with a diagnosis of IPF and a follow up time of 3 years were retrospectively collected; HRCT and Pulmonary Function Tests (PFTs) performed at diagnosis time were analysed; the extent of fibrotic disease was quantified on HRCT using kurtosis, skewness, Mean Lung Density (MLD), High attenuation areas (HAA%) and Fibrotic Areas (FA%). Univariate Cox regression was performed to assess hazard ratios for the explored variables and a multivariate model considering skewness, FVC, DLCO and age was created to test their prognostic value in assessing survival. Through ROC analysis, threshold values demonstrating the best sensitivity and specificity in predicting mortality were identified. They were used as cut-off points to graph Kaplan-Meier curves specific for the CT-indexes. Results: Kurtosis, skewness, MLD, HAA% and FA% were good predictors of mortality (HR 0.44, 0.74, 1.01, 1.12, 1.06; p = 0.03, p = 0.01, p = 0.02, p = 0.02 and p = 0.017 respectively). Skewness demonstrated the lowest Akaike’s information criterion value (55.52), proving to be the best CT variable for prediction of mortality. Significant survival differences considering proposed cut-off points were also demonstrated according to kurtosis (p = 0. 02), skewness (p = 0.005), MLD (p = 0.003), HAA% (p = 0.009) and FA% (p = 0.02) – obtained from quantitative HRCT analysis at diagnosis time. Conclusions: CT-histogram derived indexes may provide an accurate estimation of survival in IPF.

Assessment of survival in patients with idiopathic pulmonary fibrosis using quantitative HRCT indexes

Background

The assessment of Idiopathic Pulmonary Fibrosis (IPF) using HRCT requires great experience and is limited by a significant inter-observer variability, even between trained radiologists. The evaluation of HRCT through automated quantitative analysis may hopefully solve this problem. The accuracy of CT-histogram derived indexes in the assessment of survival in IPF patients has been poorly studied.

Methods

Forty-two patients with a diagnosis of IPF and a follow up time of 3 years were retrospectively collected; HRCT and Pulmonary Function Tests (PFTs) performed at diagnosis time were analysed; the extent of fibrotic disease was quantified on HRCT using kurtosis, skewness, Mean Lung Density (MLD), High attenuation areas (HAA%) and Fibrotic Areas (FA%). Univariate Cox regression was performed to assess hazard ratios for the explored variables and a multivariate model considering skewness, FVC, DL_CO and age was created to test their prognostic value in assessing survival. Through ROC analysis, threshold values demonstrating the best sensitivity and specificity in predicting mortality were identified. They were used as cut-off points to graph Kaplan-Meier curves specific for the CT-indexes.

Results

Kurtosis, skewness, MLD, HAA% and FA% were good predictors of mortality (HR 0.44, 0.74, 1.01, 1.12, 1.06; p = 0.03, p = 0.01, p = 0.02, p = 0.02 and p = 0.017 respectively). Skewness demonstrated the lowest Akaike's information criterion value (55.52), proving to be the best CT variable for prediction of mortality. Significant survival differences considering proposed cut-off points were also demonstrated according to kurtosis (p = 0.02), skewness (p = 0.005), MLD (p = 0.003), HAA% (p = 0.009) and FA% (p = 0.02) - obtained from quantitative HRCT analysis at diagnosis time.

Conclusions

CT-histogram derived indexes may provide an accurate estimation of survival in IPF patients. They demonstrate a correlation with PFTs, highlighting their possible use in clinical practice.

[18F]FDG and [18F]FLT PET for the evaluation of response to neo-adjuvant chemotherapy in a model of triple negative breast cancer

Rationale

Pathological response to neo-adjuvant chemotherapy (NAC) represents a commonly used predictor of survival in triple negative breast cancer (TNBC) and the need to identify markers that predict response to NAC is constantly increasing. Aim of this study was to evaluate the potential usefulness of PET imaging with [¹⁸F]FDG and [¹⁸F]FLT for the discrimination of TNBC responders to Paclitaxel (PTX) therapy compared to the response assessed by an adapted Response Evaluation Criteria In Solid Tumors (RECIST) criteria based on tumor volume (Tumor Volume Response).

Methods

Nu/nu mice bearing TNBC lesions of different size were evaluated with [¹⁸F]FDG and [¹⁸F]FLT PET before and after PTX treatment. SUV_max, Metabolic Tumor Volume (MTV) and Total Lesion Glycolysis (TLG) and Proliferation (TLP) were assessed using a graph-based random walk algorithm.

Results

We found that in our TNBC model the variation of [¹⁸F]FDG and [¹⁸F]FLT SUV_max similarly defined tumor response to therapy and that SUV_max variation represented the most accurate parameter. Response evaluation using Tumor Volume Response (TVR) showed that the effectiveness of NAC with PTX was completely independent from lesions size at baseline.

Conclusions

Our study provided interesting results in terms of sensitivity and specificity of PET in TNBC, revealing the similar performances of [¹⁸F]FDG and [¹⁸F]FLT in the identification of responders to Paclitaxel.

A fully automatic approach for multimodal PET and MR image segmentation in gamma knife treatment planning

BACKGROUND AND OBJECTIVES

Nowadays, clinical practice in Gamma Knife treatments is generally based on MRI anatomical information alone. However, the joint use of MRI and PET images can be useful for considering both anatomical and metabolic information about the lesion to be treated. In this paper we present a co-segmentation method to integrate the segmented Biological Target Volume (BTV), using [¹¹C]-Methionine-PET (MET-PET) images, and the segmented Gross Target Volume (GTV), on the respective co-registered MR images. The resulting volume gives enhanced brain tumor information to be used in stereotactic neuro-radiosurgery treatment planning. GTV often does not match entirely with BTV, which provides metabolic information about brain lesions. For this reason, PET imaging is valuable and it could be used to provide complementary information useful for treatment planning. In this way, BTV can be used to modify GTV, enhancing Clinical Target Volume (CTV) delineation.

METHODS

A novel fully automatic multimodal PET/MRI segmentation method for Leksell Gamma Knife^® treatments is proposed. This approach improves and combines two computer-assisted and operator-independent single modality methods, previously developed and validated, to segment BTV and GTV from PET and MR images, respectively. In addition, the GTV is utilized to combine the superior contrast of PET images with the higher spatial resolution of MRI, obtaining a new BTV, called BTV_MRI. A total of 19 brain metastatic tumors, undergone stereotactic neuro-radiosurgery, were retrospectively analyzed. A framework for the evaluation of multimodal PET/MRI segmentation is also presented. Overlap-based and spatial distance-based metrics were considered to quantify similarity concerning PET and MRI segmentation approaches. Statistics was also included to measure correlation among the different segmentation processes. Since it is not possible to define a gold-standard CTV according to both MRI and PET images without treatment response assessment, the feasibility and the clinical value of BTV integration in Gamma Knife treatment planning were considered. Therefore, a qualitative evaluation was carried out by three experienced clinicians.

RESULTS

The achieved experimental results showed that GTV and BTV segmentations are statistically correlated (Spearman's rank correlation coefficient: 0.898) but they have low similarity degree (average Dice Similarity Coefficient: 61.87 ± 14.64). Therefore, volume measurements as well as evaluation metrics values demonstrated that MRI and PET convey different but complementary imaging information. GTV and BTV could be combined to enhance treatment planning. In more than 50% of cases the CTV was strongly or moderately conditioned by metabolic imaging. Especially, BTV_MRI enhanced the CTV more accurately than BTV in 25% of cases.

CONCLUSIONS

The proposed fully automatic multimodal PET/MRI segmentation method is a valid operator-independent methodology helping the clinicians to define a CTV that includes both metabolic and morphologic information. BTV_MRI and GTV should be considered for a comprehensive treatment planning.

Predictive and Prognostic Value of Early Disease Progression by PET Evaluation in Advanced Non-Small Cell Lung Cancer

OBJECTIVE

To assess the predictive and prognostic value of progressive metabolic disease (PMD) by the use of early 18Fluorodeoxyglucose positron emission tomography (18FDG-PET) in patients with clinical stage IV non-small cell lung cancer (NSCLC) treated with first-line chemotherapy.

METHODS

An 18FDG-PET performed following the first cycle of chemotherapy (PET-1) was compared with a pretreatment 18FDG-PET (PET-0) and a computed tomography (CT) scan after the third cycle (CT-3). The primary endpoint was the positive predictive value (PPV) of PMD. Secondary endpoints included the prognostic value of PMD.

RESULTS

Eleven of 38 patients (29%) had a PMD by PET-1, and 15 (39%), including all patients with a PMD, experienced a progressive disease by CT-3. The PPV of PMD was 100% according to both the European Organization for Research and Treatment of Cancer (EORTC) criteria and the PET Response Criteria In Solid Tumors (PERCIST) (p value for both, <0.0001). Patients with a PMD by PET-1 had a median overall survival of 7.0 months versus 14.0 months for those without a PMD (p = 0.04, according to the EORTC criteria).

CONCLUSIONS

Early 18FDG-PET assessment deserves further investigation for the identification of NSCLC patients who do not benefit from first-line chemotherapy.

Evaluation of erlotinib treatment response in non-small cell lung cancer using metabolic and anatomic criteria

BACKGROUND

In this paper the clinical value of PET for early prediction of tumor response to erlotinib in patients with advanced or metastatic non-small cell lung cancer (NSCLC) after failure of at least one prior chemotherapy regimen is evaluated. The aim was to compare the early metabolic treatment response using European Organization for Research and Treatment of Cancer (EORTC) 1999 recommendations and PET Response Criteria in Solid Tumors (PERCIST), and the standard treatment response using Response Evaluation Criteria in Solid Tumors (RECIST).

METHODS

Twenty patients with stage IV NSCLC were enrolled prospectively. PET/CT studies were performed before, then 48 hours, and 45 days after the initiation of erlotinib treatment. The lesion with the highest uptake in each patient was evaluated according to EORTC 1999 recommendations, PERCIST and RECIST to assess metabolic and anatomic response. Response classifications were compared statistically using Wilcoxon signed-rank test. Disease-free survival (DFS) and overall survival (OS) were calculated by the Kaplan-Meier Test.

RESULTS

At 48 hours, the Kaplan-Meier analysis showed that EORTC proved to be a significant prognostic factor for predicting DFS and OS. At 45 days, there was a significant difference in response evaluation between RECIST and metabolic classifications. RECIST and PERCIST were significant prognostic factors for predicting DFS and OS. EORTC was not able to discriminate responder from non-responder patients.

CONCLUSIONS

This study shows that, according to the EORTC protocol, the PET exam is able to provide early identification of patients who benefit from Erlotinib treatment. Used at the end of therapy, PERCIST could be considered an appropriate metabolic evaluation method to discriminate responders from non-responders.

Correlation between histological grade and positron emission tomography parameters in cervical carcinoma

The aim of the present study was to evaluate the changes in cervical cancer glucose metabolism for different levels of cellular differentiation. The metabolic activity was measured by standardized uptake value (SUV), SUV normalized to lean body mass, metabolic tumor volume and total lesion glycolysis using fluorine-18 fluorodeoxyglucose positron emission tomography (PET). A correlation study of these values could be used to facilitate therapeutic choice and to improve clinical practice and outcome. This study considered 32 patients with diagnosed cervical cancers, at different International Federation of Gynecology and Obstetrics stages. Glucose metabolism was assessed by PET examination, and histological specimens were examined to determine their initial grade of differentiation. A correlation study of these values was evaluated. Histological examination showed that all cases were of squamous cell carcinoma. Regarding the differentiation of the tumor, 19 well- to moderately-differentiated tumors and 13 poorly-differentiated tumors were determined. Negative findings for correlations between metabolic parameters and initial grade of histological differentiation were found, and considering that histological grade has been shown to have no consistent prognostic value in cervical cancer treatment, PET imaging could play a significant role in cervical cancer prognosis.

Metabolic impact of partial volume correction of [18F]FDG PET-CT oncological studies on the assessment of tumor response to treatment

AIM

The aim of this work is to evaluate the metabolic impact of Partial Volume Correction (PVC) on the measurement of the Standard Uptake Value (SUV) from [18F]FDG PET-CT oncological studies for treatment monitoring purpose.

METHODS

Twenty-nine breast cancer patients with bone lesions (42 lesions in total) underwent [18F]FDG PET-CT studies after surgical resection of breast cancer primitives, and before (PET-II) chemotherapy and hormone treatment. PVC of bone lesion uptake was performed on the two [18F]FDG PET-CT studies, using a method based on Recovery Coefficients (RC) and on an automatic measurement of lesion metabolic volume. Body-weight average SUV was calculated for each lesion, with and without PVC. The accuracy, reproducibility, clinical feasibility and the metabolic impact on treatment response of the considered PVC method was evaluated.

RESULTS

The PVC method was found clinically feasible in bone lesions, with an accuracy of 93% for lesion sphere-equivalent diameter >1 cm. Applying PVC, average SUV values increased, from 7% up to 154% considering both PET-I and PET-II studies, proving the need of the correction. As main finding, PVC modified the therapy response classification in 6 cases according to EORTC 1999 classification and in 5 cases according to PERCIST 1.0 classification.

CONCLUSION

PVC has an important metabolic impact on the assessment of tumor response to treatment by [18F]FDG PET-CT oncological studies.