Artificial Intelligence Analysis Using MRI and PET Imaging in Gliomas: A Narrative Review.

The lack of early detection and a high rate of recurrence/progression after surgery are defined as the most common causes of a very poor prognosis of Gliomas. The developments of quantification systems with special regards to artificial intelligence (AI) on medical images (CT, MRI, PET) are under evaluation in the clinical and research context in view of several applications providing different information related to the reconstruction of imaging, the segmentation of tissues acquired, the selection of features, and the proper data analyses. Different approaches of AI have been proposed as the machine and deep learning, which utilize artificial neural networks inspired by neuronal architectures. In addition, new systems have been developed using AI techniques to offer suggestions or make decisions in medical diagnosis, emulating the judgment of radiologist experts. The potential clinical role of AI focuses on the prediction of disease progression in more aggressive forms in gliomas, differential diagnosis (pseudoprogression vs. proper progression), and the follow-up of aggressive gliomas. This narrative Review will focus on the available applications of AI in brain tumor diagnosis, mainly related to malignant gliomas, with particular attention to the postoperative application of MRI and PET imaging, considering the current state of technical approach and the evaluation after treatment (including surgery, radiotherapy/chemotherapy, and prognostic stratification).

A comparison of visual assessment and semi-quantification for the diagnostic and prognostic use of [18F]flortaucipir PET in a memory clinic cohort.

PURPOSE: [18F]Flortaucipir PET is a powerful diagnostic and prognostic tool for Alzheimer's disease (AD). Tau status definition is mainly based in the literature on semi-quantitative measures while in clinical settings visual assessment is usually preferred. We compared visual assessment with established semi-quantitative measures to classify subjects and predict the risk of cognitive decline in a memory clinic population. METHODS: We included 245 individuals from the Geneva Memory Clinic who underwent [18F]flortaucipir PET. Amyloid status was available for 207 individuals and clinical follow-up for 135. All scans were blindly evaluated by three independent raters who visually classified the scans according to Braak stages. Standardized uptake value ratio (SUVR) values were obtained from a global meta-ROI to define tau positivity, and the Simplified Temporo-Occipital Classification (STOC) was applied to obtain semi-quantitatively tau stages. The agreement between measures was tested using Cohen's kappa (k). ROC analysis and linear mixed-effects models were applied to test the diagnostic and prognostic values of tau status and stages obtained with the visual and semi-quantitative approaches. RESULTS: We found good inter-rater reliability in the visual interpretation of tau Braak stages, independently from the rater's expertise (k>0.68, p<0.01). A good agreement was equally found between visual and SUVR-based classifications for tau status (k=0.67, p<0.01). All tau-assessment modalities significantly discriminated amyloid-positive MCI and demented subjects from others (AUC>0.80) and amyloid-positive from negative subjects (AUC>0.85). Linear mixed-effect models showed that tau-positive individuals presented a significantly faster cognitive decline than the tau-negative group (p<0.01), independently from the classification method. CONCLUSION: Our results show that visual assessment is reliable for defining tau status and stages in a memory clinic population. The high inter-rater reliability, the substantial agreement, and the similar diagnostic and prognostic performance of visual rating and semi-quantitative methods demonstrate that [18F]flortaucipir PET can be robustly assessed visually in clinical practice.

The impact of tau deposition and hypometabolism on cognitive impairment and longitudinal cognitive decline.

INTRODUCTION: Tau and neurodegeneration strongly correlate with cognitive impairment, as compared to amyloid. However, their contribution in explaining cognition and predicting cognitive decline in memory clinics remains unclarified. METHODS: We included 94 participants with Mini-Mental State Examination (MMSE), tau positron emission tomography (PET), amyloid PET, fluorodeoxyglucose (FDG) PET, and MRI scans from Geneva Memory Center. Linear regression and mediation analyses tested the independent and combined association between biomarkers, cognitive performance, and decline. Linear mixed-effects and Cox proportional hazards models assessed biomarkers' prognostic values. RESULTS: Metabolism had the strongest association with cognition (r = 0.712; p < 0.001), followed by tau (r = -0.682; p < 0.001). Neocortical tau showed the strongest association with cognitive decline (r = -0.677; p < 0.001). Metabolism mediated the association between tau and cognition and marginally mediated the one with decline. Tau positivity represented the strongest risk factor for decline (hazard ratio = 32). DISCUSSION: Tau and neurodegeneration synergistically contribute to global cognitive impairment while tau drives decline. The tau PET superior prognostic value supports its implementation in memory clinics. HIGHLIGHTS: Hypometabolism has the strongest association with concurrent cognitive impairment. Neocortical tau pathology is the main determinant of cognitive decline over time. FDG-PET has a superior value compared to MRI as a measure of neurodegeneration. The prognostic value of tau-PET exceeded all other neuroimaging modalities.

Detection of sentinel lymph node in vulvar cancer using 99mTc-labeled colloid lymphoscintigraphy, blue dye, and indocyanine-green fluorescence: a meta-analysis of studies published in 2010-2020.

OBJECTIVES: Sentinel lymph node (SLN) biopsy is widely accepted in the surgical staging of early vulvar cancer, although the most accurate method for its identification is not yet defined. This meta-analysis aimed to determine the technique with the highest pooled detection rate (DR) for the identification of SLN and compare the average number of SLNs detected by planar lymphoscintigraphy (PL), single-photon emission computed tomography/computed tomography (SPECT/CT), blue dye and indocyanine green (ICG) fluorescence. METHODS: The meta-analysis was conducted according to the PRISMA guideline. The search string was: "sentinel" and "vulv*", with date restriction from 1st January 2010 until Dec 31st, 2020. Three investigators selected studies based on: (1) a study cohort or a subset of a minimum of 10 patients with vulvar cancer undergoing either PL, SPECT/CT, blue-dye, or ICG fluorescence for the identification of SLN; (2) the possibility to extrapolate the DR or the average number of SLNs detected by a single technique (3) no evidence of other malignancies in the patient history. RESULTS: A total of 30 studies were selected. In a per-patient and a per-groin analysis, the DR for SLN of PL was respectively 96.13% and 92.57%; for the blue dye was 90.44% and 66.21%; for the ICG, the DR was 91.90% and 94.80%. The pooled DR of SPECT/CT was not calculated, since only two studies were performed in this setting. At a patient-based analysis, no significant difference was documented among PL, blue dye, and ICG (p = 0.28). At a per-groin analysis, PL and ICG demonstrated a significantly higher DR compared to blue dye (p < 0.05). The average number of SLNs, on a per-patient analysis, was available only for PL and ICG with a median number of 2.61 and 1.78 lymph nodes detected, respectively, and no significant statistical difference. CONCLUSIONS: This meta-analysis favors the use of ICG and PL alone and in combination over blue dye for the identification of the SLN in vulvar cancer. Future studies may investigate whether the combined approach allows the highest DR of SLN in patients with vulvar cancer.

FDG PET in the differential diagnosis of degenerative parkinsonian disorders: usefulness of voxel-based analysis in clinical practice.

BACKGROUND: The early differential diagnosis among neurodegenerative parkinsonian disorders becomes essential to set up the correct clinical-therapeutic approach. The increased utilization of [18F] fluoro-deoxy-glucose positron emission tomography (FDG PET) and the pressure for cost-effectiveness request a systematic evaluation and a validation of its utility in clinical practice. This retrospective study aims to consider the contribution, in terms of increasing accuracy and increasing diagnostic confidence, of voxel-based FDG PET analyses in the differential diagnosis of these disorders, including Parkinson's disease, multiple system atrophy, progressive supranuclear palsy, and cortico-basal syndrome. METHOD: Eighty-three subjects with a clinically confirmed diagnosis of degenerative parkinsonian disorders who underwent FDG brain PET/CT were selected. A voxel-based analysis was set up using statistical parametric mapping (SPM) on MATLAB to produce maps of brain hypometabolism and relative hypermetabolism. Four nuclear physicians (two expert and two not expert), blinded to the patients' symptoms, other physicians' evaluations, and final clinical diagnosis, independently evaluated all data by visual assessment and by adopting metabolic maps. RESULTS: In not-expert evaluators, the support of both hypometabolism and hypermetabolism maps results in a significant increase in diagnostic accuracy as well as clinical confidence. In expert evaluators, the increase in accuracy and in diagnostic confidence is mainly supported by hypometabolism maps alone. CONCLUSIONS: In this study, we demonstrated the additional value of combining voxel-based analyses with qualitative assessment of brain PET images. Moreover, maps of relative hypermetabolism can also make their contribution in clinical practice, particularly for less experienced evaluators.

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.

Cerebral amyloid load determination in a clinical setting: interpretation of amyloid biomarker discordances aided by tau and neurodegeneration measurements.

BACKGROUND: Alzheimer's disease (AD) diagnosis can be hindered by amyloid biomarkers discordances. OBJECTIVE: We aim to interpret discordances between amyloid positron emission tomography (Amy-PET) and cerebrospinal fluid (CSF) (Aß42 and Aß42/40), using Amy-PET semiquantitative analysis, [18F]fluorodeoxyglucose (FDG)-PET pattern, and CSF assays. METHOD: Thirty-six subjects with dementia or mild cognitive impairment, assessed by neuropsychological tests, structural and functional imaging, and CSF assays (Aß42, Aß42/40, p-tau, t-tau), were retrospectively examined. Amy-PET and FDG-PET scans were analyzed by visual assessment and voxel-based analysis. SUVR were calculated on Amy-PET scans. RESULTS: Groups were defined basing on the agreement among CSF Aß42 (A), CSF Aß42/40 Ratio (R), and Amy-PET (P) dichotomic results ( ±). In discordant groups, CSF assays, Amy-PET semiquantification, and FDG-PET patterns supported the diagnosis suggested by any two agreeing amyloid biomarkers. In groups with discordant CSF Aß42, the ratio always agrees with Amy-PET results, solving both false-negative and false-positive Aß42 results, with Aß42 levels close to the cut-off in A + R-P- subjects. The A + R + P- group presented high amyloid deposition in relevant areas, such as precuneus, posterior cingulate cortex (PCC) and dorsolateral frontal inferior cortex at semiquantitative analysis. CONCLUSION: The amyloid discordant cases could be overcome by combining CSF Aß42, CSF ratio, and Amy-PET results. The concordance of any 2 out of the 3 biomarkers seems to reveal the remaining one as a false result. A cut-off point review could avoid CSF Aß42 false-negative results. The regional semiquantitative Amy-PET analysis in AD areas, such as precuneus and PCC, could increase the accuracy in AD diagnosis.

Initial results of the use of a novel semiquantitative parameter in three-phase bone scan to predict 99mTc-HMPAO-labeled leukocyte scintigraphy in patients with unilateral total knee replacement.

OBJECTIVES: The aim of the study was to predict the results of 99mTc-hexamethylpropyleneamine oxime (HMPAO)-labeled autologous leukocytes scintigraphy assessing count ratios in the perfusion (Pr) and blood-pool (BPr) phase images in three-phase bone scan (3PBSr) between the prosthetic knee and the 'healthy' knee and a novel semiquantitative parameter (P/BP ratio) in patients with unilateral knee arthroplasty. METHODS: Patients with unilateral knee arthroplasty and available 3PBS and 99mTc-HMPAO-labeled autologous leukocytes scintigraphic images were searched in two hospitals (A and B). In center A, the perfusion phase was not available. Regions of interest (ROI) were delineated in the perfusion (P) and blood-pool (BP) phase images, incorporating the prosthetic region and applying an isocontour (40% of the maximum pixel activity); corresponding mirror ROIs were placed on the healthy knee. The P/BP ratio was calculated as {[(Pr/BPr) × 100] - 100}. Receiver operator curves (ROCs) were generated for each semiquantitative parameter to identify the optimal cutoff for predicting the results of the autologous leukocytes scintigraphy. RESULTS: In the whole group (79 patients), BPr demonstrated an area under the curve (AUC) of 0.722 (optimal cutoff = 1.43). In center A (52 patients), BPr demonstrated an AUC of 0.737 (cutoff = 1.43), whereas, in center B (27 patients), AUC for BPr was 0.718 (cutoff = 1.6). A better diagnostic performance was obtained selecting Pr (AUC = 0.918; cutoff = 2.34) and P/BP ratio (AUC = 0.947; cutoff = 26.5%) for the discrimination between septic and aseptic loosening. CONCLUSIONS: The novel P/BP ratio seems to be a promising semiquantitative parameter to predict septic loosening. These findings warrant confirmation in larger patient samples.

Clinical Impact of 18F-FDG PET/CT in the Diagnostic Workup of Pancreatic Ductal Adenocarcinoma: A Systematic Review.

In this review, the performance of fluorodeoxyglucose (FDG)-positron emission tomography (PET)/computed tomography (CT) in the diagnostic workup of pancreatic ductal adenocarcinoma (PDAC) is evaluated. A comprehensive literature search up to September 2020 was performed, selecting studies with the presence of: sample size ≥10 patients and index test (i.e., "FDG" or "18F-FDG" AND "pancreatic adenocarcinoma" or "pancreas cancer" AND "PET" or "positron emission tomography"). The methodological quality was evaluated using the revised quality assessment of diagnostic accuracy studies (QUADAS-2) tool and presented according to the preferred reporting items for systematic reviews and meta-analyses (PRISMA) guidelines. Basic data (authors, year of publication, country and study design), patients' characteristics (number of enrolled subjects and age), disease phase, type of treatment and grading were retrieved. Forty-six articles met the adopted research criteria. The articles were divided according to the considered clinical context. Namely, besides conventional anatomical imaging, such as computed tomography (CT) and magnetic resonance imaging (MRI), molecular imaging with FDG PET/CT is an important tool in PDAC, for all disease stages. Further prospective studies will be necessary to confirm the cost-effectiveness of such imaging techniques by testing its real potential improvement in the clinical management of PDAC.

The Additional Value of 18F-FDG PET and MRI in Patients with Glioma: A Review of the Literature from 2015 to 2020.

AIM: Beyond brain computed tomography (CT) scan, Magnetic Resonance Imaging (MRI) and Positron Emission Tomography (PET) hold paramount importance in neuro-oncology. The aim of this narrative review is to discuss the literature from 2015 to 2020, showing advantages or complementary information of fluorine-18 fluorodeoxyglucose (18F-FDG) PET imaging to the anatomical and functional data offered by MRI in patients with glioma. METHODS: A comprehensive Pubmed/MEDLINE literature search was performed to retrieve original studies, with a minimum of 10 glioma patients, published from 2015 until the end of April 2020, on the use of 18F-FDG PET in conjunction with MRI. RESULTS: Twenty-two articles were selected. Combined use of the two modalities improves the accuracy in predicting prognosis, planning treatments, and evaluating recurrence. CONCLUSION: According to the recent literature, 18F-FDG PET provides different and complementary information to MRI and may enhance performance in the whole management of gliomas. Therefore, integrated PET/MRI may be particularly useful in gliomas, since it could provide accurate morphological and metabolic information in one-shoot examination and improve the diagnostic value compared to each of procedures.

Comparison of 99mTc-Labeled Colloid SPECT/CT and Planar Lymphoscintigraphy in Sentinel Lymph Node Detection in Patients with Melanoma: A Meta-Analysis.

We compared the detection rate (DR) for sentinel lymph nodes (SLN), the number of SLNs and the subjects with additional SLNs of single-photon emission computed tomography (SPECT/CT) and planar lymphoscintigraphy (PL) in patients with melanoma. Furthermore, we evaluated the impact of SPECT/CT on surgical plans. Articles containing head-to-head comparisons between SPECT/CT and PL were searched in Pubmed/MEDLINE and Scopus. The literature search was updated until December 31st, 2019. DR was calculated on a per patient-based analysis; the studies were pooled by their odds ratios (ORs) with a random effects model to assess the significance of difference (p < 0.05). The number of additional SLNs (calculated as the relative risk) and pooled proportion of patients with additional SLNs were investigated. The pooled ratio of surgical procedures influenced by the SPECT/CT findings was calculated. Seventeen studies with 1438 patients were eligible for the calculation of DR of SPECT/CT and PL. The average DR was 98.28% (95% confidence interval (95% CI): 97.94-99.19%) for the SPECT/CT and 95.53% (95% CI: 92.55-97.77%) for the PL; OR of 2.31 (95% CI: 1.66-4.18, p < 0.001) in favor of the SPECT/CT. There was a relative risk of a higher number of SLNs (1.13) for the SPECT/CT and 17.87% of patients with additional SLNs were detected by SPECT/CT. The average impact of SPECT/CT on surgery resulted in 37.43% of cases. This meta-analysis favored SPECT/CT over PL for the identification of SLNs in patients with melanoma due to a higher DR, reproducibility, number of SLNs depicted, proportion of patients with additional SLNs and the impact on the surgical plan. However, PL remains a good option due to the high values of the DR for SLNs.

Sentinel Node Identification in Melanoma: Current Clinical Impact, New Emerging SPECT Radiotracers and Technological Advancements. An Update of the Last Decade.

BACKGROUND: Melanoma is the most lethal skin cancer with a mortality rate of 262 cases per 100.000 cases. The sentinel lymph node (SLN) is the first lymph node draining the tumor. SLN biopsy is a widely accepted procedure in the clinical setting since it provides important prognostic information, which helps patient management, and avoids the side effects of complete lymph node dissection. The rationale of identifying and removing the SLN relies on the low probability of subsequent metastatic nodes in case of a negative histological exam performed in the SLN. DISCUSSION: Recently, new analytical approaches, based on the evaluation of scintigraphic images are also exploring the possibility to predict the metastatic involvement of the SLN. 99mTc-labeled colloids are still the most commonly used radiotracers but new promising radiotracers, such as 99mTc- Tilmanocept, are now on the market. In the last decades, single photon emission computed tomography- computerized tomography (SPECT/CT) has gained wider diffusion in clinical departments and there is large evidence about its superior diagnostic accuracy over planar lymphoscintigraphy (PL) in the detection of SLN in patients with melanoma. Scientists are also investigating new hybrid techniques combining functional and anatomical images for the depiction of SLN but further evidence about their value is needed. CONCLUSION: This review examined the predictive and prognostic factors of lymphoscintigraphy for metastatic involvement of SLN, the currently available and emerging radiotracers and the evidence of the additional value of SPECT/CT over PL for the identification of SLN in patients with melanoma. Finally, the review discussed the most recent technical advances in the field.

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.