Dual adversarial deconfounding autoencoder for joint batch-effects removal from multi-center and multi-scanner radiomics data.

Medical imaging represents the primary tool for investigating and monitoring several diseases, including cancer. The advances in quantitative image analysis have developed towards the extraction of biomarkers able to support clinical decisions. To produce robust results, multi-center studies are often set up. However, the imaging information must be denoised from confounding factors-known as batch-effect-like scanner-specific and center-specific influences. Moreover, in non-solid cancers, like lymphomas, effective biomarkers require an imaging-based representation of the disease that accounts for its multi-site spreading over the patient's body. In this work, we address the dual-factor deconfusion problem and we propose a deconfusion algorithm to harmonize the imaging information of patients affected by Hodgkin Lymphoma in a multi-center setting. We show that the proposed model successfully denoises data from domain-specific variability (p-value < 0.001) while it coherently preserves the spatial relationship between imaging descriptions of peer lesions (p-value = 0), which is a strong prognostic biomarker for tumor heterogeneity assessment. This harmonization step allows to significantly improve the performance in prognostic models with respect to state-of-the-art methods, enabling building exhaustive patient representations and delivering more accurate analyses (p-values < 0.001 in training, p-values < 0.05 in testing). This work lays the groundwork for performing large-scale and reproducible analyses on multi-center data that are urgently needed to convey the translation of imaging-based biomarkers into the clinical practice as effective prognostic tools. The code is available on GitHub at this https://github.com/LaraCavinato/Dual-ADAE .

The complementary role of PSMA expression and [18F]FDG PET/CT in predicting thyroid cancer outcome: from black and white to shades of gray, in the era of precision oncology.

BACKGROUND: The value of Prostate Specific Membrane Antigen (PSMA) in thyroid carcinoma (TC) is still unknown. We aimed to test the potential complementary role of PSMA expression and 2-[18F]fluoro-2-deoxy-D-glucose ([18F]FDG) uptake on PET/CT as biomarkers for TC outcome prediction. MATERIALS AND METHODS: From a retrospective cohort of TC patients we selected those fulfilling the following inclusion/exclusion criteria: thyroidectomy in our Institution, available primary tumor tissue PSMA immunostaining, [18F]FDG PET/CT and follow-up data. PSMA staining was visually assessed. PET/CT was considered positive in case of [18F]FDG uptake higher than the background at the site of TC confirmed by cyto-/histology, and/or follow-up. Disease recurrence, radioiodine refractoriness (RAI-R) and status at last follow-up (LFU) were used as outcome endpoints. RESULTS: We included 23 subjects. Disease recurrence occurred in 18 patients (median time 11 months, range 1-40); among these 12/18 developed RAI-R (median time 28 months, range 2-221), and 13/18 had evidence of disease at LFU. PSMA expression was negative in 6/23 cases. PET/CT was negative in 11/23 patients (7/11 experienced recurrence). PET/CT was positive in 9/12 patients showing RAI-R and 10/13 cases with evidence of disease at LFU. All patients with positive PET/CT had a positive PSMA immunostaining. Six out of 11 patients with negative PET/CT were positive at immunostaining, showing lower PSMA expression (median score of 30%, range 0-80%) than patients with positive PET/CT. The TC samples without PSMA expression belonged to patients who resulted negative also at PET/CT (3 experienced recurrence, 2 were RAI-R, and 1 had disease at LFU). Four out of 11 patients who resulted negative at PET/CT exhibited very high PSMA expression (≥ 70%) and although 3 of them experienced recurrence, none resulted RAI-R, and only 1 had persistent disease at LFU. CONCLUSIONS: Primary tumor PSMA expression and [18F]FDG uptake seem to play a complementary prognostic role in TC. The majority of patients who expressed PSMA recurred. In the intermediate ATA risk class, patients with negative PSMA immunostaining recurred less than patients expressing PSMA. Additionally, although patients with a negative [18F]FDG PET/CT had a favourable long-term outcome, PSMA assessment might be useful to timely identify subjects at higher risk of recurrence.

FAP expression in alpha cells of Langherhans insulae-implications for FAPI radiopharmaceuticals' use.

PURPOSE: Radiopharmaceuticals targeting fibroblast activation protein (FAP) alpha are increasingly studied for diagnostic and therapeutic applications. We discovered FAP expression at immunohistochemistry (IHC) in the alpha cells of the Langerhans insulae of few patients. Therefore, we planned an investigation aimed at describing FAP expression in the pancreas and discussing the implications for radioligand applications. METHODS: We retrospectively included 40 patients from 2 institutions (20 pts each) according to the following inclusion/exclusion criteria: (i) pathology proven pancreatic ductal adenocarcinoma and neuroendocrine tumors (NET), 10 pts per each group at each center; (ii) and availability of paraffin-embedded tissue; and (iii) clinical-pathological records. We performed IHC analysis and applied a semiquantitative visual scoring system (0, negative staining; 1, present in less than 30%; 2, present in more than 30% of the area). FAP expression was assessed according to histology-NET (n = 20) vs ductal adenocarcinoma (n = 20)-and to previous treatments within the adenocarcinoma group. The local ethics committee approved the study (No. INT 21/16, 28 January 2016). RESULTS: The population consisted of 24 males and 16 females, with a median age of 68 and a range of 14-84 years; 8/20 adenocarcinoma patients received chemotherapy. In all the Langerhans insulae (40/40), pancreatic alpha cells were found to express FAP, with a score of 2. No difference was found among NET (20/20) and adenocarcinoma (20/20), nor according to neoadjuvant chemotherapy in the adenocarcinoma cohort (received or not received). CONCLUSION: Pancreatic Langerhans islet alpha cells normally express FAP. This is not expected to influence the diagnostic accuracy of FAP-targeting tracers. In the therapeutic setting, our results suggest the need to better elucidate FAPI radioligands' effects on the Langerhans insulae function.

Explainable domain transfer of distant supervised cancer subtyping model via imaging-based rules extraction.

Image texture analysis has for decades represented a promising opportunity for cancer assessment and disease progression evaluation, evolving in a discipline, i.e., radiomics. However, the road to a complete translation into clinical practice is still hampered by intrinsic limitations. As purely supervised classification models fail in devising robust imaging-based biomarkers for prognosis, cancer subtyping approaches would benefit from the employment of distant supervision, for instance exploiting survival/recurrence information. In this work, we assessed, tested, and validated the domain-generality of our previously proposed Distant Supervised Cancer Subtyping model on Hodgkin Lymphoma. We evaluate the model performance on two independent datasets coming from two hospitals, comparing and analyzing the results. Although successful and consistent, the comparison confirmed the instability of radiomics due to an across-center lack of reproducibility, leading to explainable results in one center and poor interpretability in the other. We thus propose a Random Forest-based Explainable Transfer Model for testing the domain-invariance of imaging biomarkers extracted from retrospective cancer subtyping. In doing so, we tested the predictive ability of cancer subtyping in a validation and perspective setting, which led to successful results and supported the domain-generality of the proposed approach. On the other hand, the extraction of decision rules enables to draw of risk factors and robust biomarkers to inform clinical decisions. This work shows the potentialities of the Distant Supervised Cancer Subtyping model to be further evaluated in larger multi-center datasets, to reliably translate radiomics into medical practice. The code is available at this GitHub repository.

The Development of an Intelligent Agent to Detect and Non-Invasively Characterize Lung Lesions on CT Scans: Ready for the "Real World"?

(1) Background: Once lung lesions are identified on CT scans, they must be characterized by assessing the risk of malignancy. Despite the promising performance of computer-aided systems, some limitations related to the study design and technical issues undermine these tools' efficiency; an "intelligent agent" to detect and non-invasively characterize lung lesions on CT scans is proposed. (2) Methods: Two main modules tackled the detection of lung nodules on CT scans and the diagnosis of each nodule into benign and malignant categories. Computer-aided detection (CADe) and computer aided-diagnosis (CADx) modules relied on deep learning techniques such as Retina U-Net and the convolutional neural network; (3) Results: Tests were conducted on one publicly available dataset and two local datasets featuring CT scans acquired with different devices to reveal deep learning performances in "real-world" clinical scenarios. The CADe module reached an accuracy rate of 78%, while the CADx's accuracy, specificity, and sensitivity stand at 80%, 73%, and 85.7%, respectively; (4) Conclusions: Two different deep learning techniques have been adapted for CADe and CADx purposes in both publicly available and private CT scan datasets. Experiments have shown adequate performance in both detection and diagnosis tasks. Nevertheless, some drawbacks still characterize the supervised learning paradigm employed in networks such as CNN and Retina U-Net in real-world clinical scenarios, with CT scans from different devices with different sensors' fingerprints and spatial resolution. Continuous reassessment of CADe and CADx's performance is needed during their implementation in clinical practice.

Hybrid PET/MRI in Infection and Inflammation: An Update About the Latest Available Literature Evidence.

PET/MRI has been reported to be promising in the diagnosis and evaluation of infection and inflammation including brain disorders, bone and soft tissue infections and inflammations, cardiovascular, abdominal, and systemic diseases. However, evidence came out manly from anecdotal cases or small cohorts. The present review aimed to update the latest available evidence about the role of PET/MRI in infection and inflammation. The search (January, 1 2018-July, 8 2022) on PubMed produced 504 results. Sixty-five articles were selected and included in the qualitative synthesis. The number of publications on PET/MRI in the 3 years 2018-2020 was comparable, while it increased in 2021 and 2022 (from 11 to 17 and 15, respectively). [18F]FDG and 68Ga-DOTA-FAPI-04 were the most frequently used (42/65) and innovative radiopharmaceuticals, respectively. [18F]fluoride (9/65), translocator protein (TSPO)-targeted PET agents (6/65), CXCR4 receptor targeting tracer and ß-amyloid plaques binding radiopharmaceuticals (2/65 and 2/65, respectively) were also used. Most PET/MRI studies in the period 2018-2022 focused on inflammation (55/65), and cardiovascular diseases represented the most frequent field of interest (30/65), also when considering each year singularly. An increasing trend in bone and joint publications was observed in the considered period (12/65). Other topics included neurology (11/65), inflammatory bowel disease (8/65), and other (4/65). PET/MRI technology demonstrated to be useful in infection and inflammation, being superior to each single modality and/or facilitating diagnosis in a number of conditions (eg, cardiac sarcoidosis, myocarditis, endocarditis), and/or allowing to provide insightful information about disease biology and apply innovative radiopharmaceuticals (eg, neurology, atherosclerosis). Publications focused on PET/MRI in large vessel vasculitis and aortic diseases include both diagnostic and discovery objectives. The current review corroborates the potential of PET/MRI - combining in a single examination the high soft tissue contrast, high resolution, and functional information of MRI, with molecular data provided by PET technology - to positively impact on the management of infectious diseases and inflammatory conditions.

Image Embeddings Extracted from CNNs Outperform Other Transfer Learning Approaches in Classification of Chest Radiographs.

To identify the best transfer learning approach for the identification of the most frequent abnormalities on chest radiographs (CXRs), we used embeddings extracted from pretrained convolutional neural networks (CNNs). An explainable AI (XAI) model was applied to interpret black-box model predictions and assess its performance. Seven CNNs were trained on CheXpert. Three transfer learning approaches were thereafter applied to a local dataset. The classification results were ensembled using simple and entropy-weighted averaging. We applied Grad-CAM (an XAI model) to produce a saliency map. Grad-CAM maps were compared to manually extracted regions of interest, and the training time was recorded. The best transfer learning model was that which used image embeddings and random forest with simple averaging, with an average AUC of 0.856. Grad-CAM maps showed that the models focused on specific features of each CXR. CNNs pretrained on a large public dataset of medical images can be exploited as feature extractors for tasks of interest. The extracted image embeddings contain relevant information that can be used to train an additional classifier with satisfactory performance on an independent dataset, demonstrating it to be the optimal transfer learning strategy and overcoming the need for large private datasets, extensive computational resources, and long training times.

COVID-19 vaccination, implications for PET/CT image interpretation and future perspectives.

Introduction: The present paper aims to systematically review the literature on COVID-19 vaccine-related findings in patients undergoing PET/CT. Methods: The search algorithms included the following combination of terms: "PET" OR "positron emission tomography" AND "COVID"; "PET" OR "positron emission tomography" AND "COVID" AND "vaccination"; "PET" OR "positron emission tomography" AND "COVID", AND "autoimmune". Results: We selected 17 articles which were assessed for quality and included in the systematic analysis. The most frequent vaccine-related signs on PET/CT were the deltoid [18F]FDG uptake and axillary hypermetabolic lymph nodes, which were described in 8-71% and 7-90% of the patients, respectively. Similarly, frequency of these findings using other tracers than [18F]FDG was greatly variable. This large variability was related to the variability in time elapsed between vaccination and PET/CT, and the criteria used to define positivity. In addition, vaccine-related findings were detected more frequently in young and immunocompetent patients than in elderly and immunocompromised ones. Discussion: Therefore, awareness on vaccination status (timing, patient characteristics, and concurrent therapies) and knowledge on patterns of radiopharmaceutical uptake are necessary to properly interpret PET/CT findings.

The Impact of COVID-19 on Nuclear Medicine in Europe.

The COVID-19 pandemic has profoundly changed hospital activities, including nuclear medicine (NM) practice. This review aimed to determine and describe the impact of COVID-19 on NM in Europe and critically discuss actions and strategies applied to face the pandemic. A literature search for relevant articles was performed on PubMed, covering COVID-19 studies published up until January 21, 2021. The findings were summarized according to general and specific activities within the NM departments. The pandemic strongly challenged NM departments: a reduction in the workforce has been experienced in almost every center in Europe due to personnel diagnosed with COVID-19 and other reasons related to the coronavirus. NM departments introduced procedures to limit COVID-19 transmission, including environmental and personal hygiene, social distancing, rescheduling of non-high-priority procedures, the correct use of personal protective equipment, and prompt identification of suspect COVID-19 cases. A proportion of the departments experienced a delay in radiopharmaceuticals supply or technical assistance during the pandemic. Furthermore, the pandemic resulted in a significant reduction of diagnostic and therapeutic NM procedures, as well as a reduced level of care for patients affected by diseases other than COVID-19, such as cancer or acute cardiovascular disease. Telemedicine services have been set up to maintain medical assistance for patients. COVID-19 pandemic has reshaped human work resources, patient's diagnostic and therapeutic management, operative models, radiopharmaceutical supplies, teaching, training and research of NM departments. Limits of availability of resources emerged. Nonetheless, we have to provide continuity in care, especially for fragile patients, maintaining infection control measures. Challenges that have been faced should reshape our vision and get us prepared for the future.

Application of FLIC model to predict adverse events onset in neuroendocrine tumors treated with PRRT.

To develop predictive models of side effect occurrence in GEPNET treated with PRRT. Metastatic GEPNETs patients treated in our centre with PRRT (177Lu-Oxodotreotide) from 2019 to 2020 were considered. Haematological, liver and renal toxicities were collected and graded according to CTCAE v5. Patients were grouped according with ECOG-PS, number of metastatic sites, previous treatment lines and therapies received before PRRT. A FLIC model with backward selection was used to detect the most relevant predictors. A subsampling approach was implemented to assess variable selection stability and model performance. Sixty-seven patients (31 males, 36 females, mean age 63) treated with PRRT were considered and followed up for 30 weeks from the beginning of the therapy. They were treated with PRRT as third or further lines in 34.3% of cases. All the patients showed at least one G1-G2, meanwhile G3-G5 were rare events. No renal G3-G4 were reported. Line of PRRT administration, age, gender and ECOG-PS were the main predictors of haematological, liver and renal CTCAE. The model performance, expressed by AUC, was > 65% for anaemia, creatinine and eGFR. The application of FLIC model can be useful to improve GEPNET decision-making, allowing clinicians to identify the better therapeutic sequence to avoid PRRT-related adverse events, on the basis of patient characteristics and previous treatment lines.

State-of-the-art of FAPI-PET imaging: a systematic review and meta-analysis.

INTRODUCTION: Fibroblast activation protein-α (FAPα) is overexpressed on cancer-associated fibroblasts in approximately 90% of epithelial neoplasms, representing an appealing target for therapeutic and molecular imaging applications. [68 Ga]Ga-labelled radiopharmaceuticals-FAP-inhibitors (FAPI)-have been developed for PET. We systematically reviewed and meta-analysed published literature to provide an overview of its clinical role. MATERIALS AND METHODS: The search, limited to January 1st, 2018-March 31st, 2021, was performed on MedLine and Embase databases using all the possible combinations of terms "FAP", "FAPI", "PET/CT", "positron emission tomography", "fibroblast", "cancer-associated fibroblasts", "CAF", "molecular imaging", and "fibroblast imaging". Study quality was assessed using the QUADAS-2 criteria. Patient-based and lesion-based pooled sensitivities/specificities of FAPI PET were computed using a random-effects model directly from the STATA "metaprop" command. Between-study statistical heterogeneity was tested (I2-statistics). RESULTS: Twenty-three studies were selected for systematic review. Investigations on staging or restaging head and neck cancer (n = 2, 29 patients), abdominal malignancies (n = 6, 171 patients), various cancers (n = 2, 143 patients), and radiation treatment planning (n = 4, 56 patients) were included in the meta-analysis. On patient-based analysis, pooled sensitivity was 0.99 (95% CI 0.97-1.00) with negligible heterogeneity; pooled specificity was 0.87 (95% CI 0.62-1.00), with negligible heterogeneity. On lesion-based analysis, sensitivity and specificity had high heterogeneity (I2 = 88.56% and I2 = 97.20%, respectively). Pooled sensitivity for the primary tumour was 1.00 (95% CI 0.98-1.00) with negligible heterogeneity. Pooled sensitivity/specificity of nodal metastases had high heterogeneity (I2 = 89.18% and I2 = 95.74%, respectively). Pooled sensitivity in distant metastases was good (0.93 with 95% CI 0.88-0.97) with negligible heterogeneity. CONCLUSIONS: FAPI-PET appears promising, especially in imaging cancers unsuitable for [18F]FDG imaging, particularly primary lesions and distant metastases. However, high-level evidence is needed to define its role, specifically to identify cancer types, non-oncological diseases, and clinical settings for its applications.

Radiomics and gene expression profile to characterise the disease and predict outcome in patients with lung cancer.

OBJECTIVE: The objectives of our study were to assess the association of radiomic and genomic data with histology and patient outcome in non-small cell lung cancer (NSCLC). METHODS: In this retrospective single-centre observational study, we selected 151 surgically treated patients with adenocarcinoma or squamous cell carcinoma who performed baseline [18F] FDG PET/CT. A subgroup of patients with cancer tissue samples at the Institutional Biobank (n = 74/151) was included in the genomic analysis. Features were extracted from both PET and CT images using an in-house tool. The genomic analysis included detection of genetic variants, fusion transcripts, and gene expression. Generalised linear model (GLM) and machine learning (ML) algorithms were used to predict histology and tumour recurrence. RESULTS: Standardised uptake value (SUV) and kurtosis (among the PET and CT radiomic features, respectively), and the expression of TP63, EPHA10, FBN2, and IL1RAP were associated with the histotype. No correlation was found between radiomic features/genomic data and relapse using GLM. The ML approach identified several radiomic/genomic rules to predict the histotype successfully. The ML approach showed a modest ability of PET radiomic features to predict relapse, while it identified a robust gene expression signature able to predict patient relapse correctly. The best-performing ML radiogenomic rule predicting the outcome resulted in an area under the curve (AUC) of 0.87. CONCLUSIONS: Radiogenomic data may provide clinically relevant information in NSCLC patients regarding the histotype, aggressiveness, and progression. Gene expression analysis showed potential new biomarkers and targets valuable for patient management and treatment. The application of ML allows to increase the efficacy of radiogenomic analysis and provides novel insights into cancer biology.

Distributed learning: a reliable privacy-preserving strategy to change multicenter collaborations using AI.

PURPOSE: The present scoping review aims to assess the non-inferiority of distributed learning over centrally and locally trained machine learning (ML) models in medical applications. METHODS: We performed a literature search using the term "distributed learning" OR "federated learning" in the PubMed/MEDLINE and EMBASE databases. No start date limit was used, and the search was extended until July 21, 2020. We excluded articles outside the field of interest; guidelines or expert opinion, review articles and meta-analyses, editorials, letters or commentaries, and conference abstracts; articles not in the English language; and studies not using medical data. Selected studies were classified and analysed according to their aim(s). RESULTS: We included 26 papers aimed at predicting one or more outcomes: namely risk, diagnosis, prognosis, and treatment side effect/adverse drug reaction. Distributed learning was compared to centralized or localized training in 21/26 and 14/26 selected papers, respectively. Regardless of the aim, the type of input, the method, and the classifier, distributed learning performed close to centralized training, but two experiments focused on diagnosis. In all but 2 cases, distributed learning outperformed locally trained models. CONCLUSION: Distributed learning resulted in a reliable strategy for model development; indeed, it performed equally to models trained on centralized datasets. Sensitive data can get preserved since they are not shared for model development. Distributed learning constitutes a promising solution for ML-based research and practice since large, diverse datasets are crucial for success.

Increased incidence of interstitial pneumonia detected on [18F]-FDG-PET/CT in asymptomatic cancer patients during COVID-19 pandemic in Lombardy: a casualty or COVID-19 infection?

PURPOSE: The study aimed to compare the incidence of interstitial pneumonia on [18F]-FDG PET/CT scans between two 6-month periods: (a) the COVID-19 pandemic peak and (b) control period. Secondly, we compared the incidence of interstitial pneumonia on [18F]-FDG PET/CT and epidemiological data from the regional registry of COVID-19 cases. Additionally, imaging findings and the intensity of [18F]-FDG PET/CT uptake in terms of maximum standardized uptake value (SUVmax) were compared. METHODS: We retrospectively analyzed [18F]-FDG PET/CT scans performed in cancer patients referred to nuclear medicine of Humanitas Gavazzeni in Bergamo from December 2019 to May 2020 and from December 2018 to May 2019. The per month incidence of interstitial pneumonia at imaging and the epidemiological data were assessed. To evaluate the differences between the two symmetric groups (period of COVID-19 pandemic and control), the stratified Cochran-Mantel-Haenszel test was used. Chi-square test or Fisher's exact test and t test or Wilcoxon test were performed to compare the distributions of categorical and continuous variables, respectively. RESULTS: Overall, 1298 patients were included in the study. The two cohorts-COVID-19 pandemic (n = 575) and control (n = 723)-did not statistically differ in terms of age, disease, or scan indication (p > 0.05). Signs of interstitial pneumonia were observed in 24 (4.2%) and 14 patients (1.9%) in the COVID-19 period and the control period, respectively, with a statistically significant difference (p = 0.013). The level of statistical significance improved further when the period from January to May was considered, with a peak in March (7/83 patients, 8.4% vs 3/134 patients, 2.2%, p = 0.001). The curve of interstitial pneumonia diagnosis overlapped with the COVID-19 incidence in the area of Lombardy (Spearman correlation index was equal to 1). Imaging data did not differ among the two cohorts. CONCLUSIONS: Significant increase of interstitial lung alterations at [18F]-FDG PET/CT has been demonstrated during the COVID-19 pandemic. Additionally, the incidence curve of imaging abnormalities resulted in resembling the epidemiological data of the general population. These data support the rationale to adopt [18F]-FDG PET/CT as sentinel modality to identify suspicious COVID-19 cases to be referred for additional confirmatory testing. Nuclear medicine physicians and staff should continue active surveillance of interstitial pneumonia findings, especially when new infection peak is expected.

PET/CT radiomics in breast cancer: Mind the step.

The aim of the present review was to assess the current status of positron emission tomography/computed tomography (PET/CT) radiomics research in breast cancer, and in particular to analyze the strengths and weaknesses of the published papers in order to identify challenges and suggest possible solutions and future research directions. Various combinations of the terms "breast", "radiomic", "PET", "radiomics", "texture", and "textural" were used for the literature search, extended until 8 July 2019, within the PubMed/MEDLINE database. Twenty-six articles fulfilling the inclusion/exclusion criteria were retrieved in full text and analyzed. The studies had technical and clinical objectives, including diagnosis, biological characterization (correlation with histology, molecular subtypes and IHC marker expression), prediction of response to neoadjuvant chemotherapy, staging, and outcome prediction. We reviewed and discussed the selected investigations following the radiomics workflow steps related to the clinical, technical, analysis, and reporting issues. Most of the current evidence on the clinical role of PET/CT radiomics in breast cancer is at the feasibility level. Harmonized methods in image acquisition, post-processing and features calculation, predictive models and classifiers trained and validated on sufficiently representative datasets, adherence to consensus guidelines, and transparent reporting will give validity and generalizability to the results.

Climbing the steps of the evidence-based medicine pyramid: highlights from Annals of Nuclear Medicine 2019.

We aimed to provide an overview on research path in nuclear medicine climbing the steps of the Evidence-Based Medicine (EBM) pyramid using review of 14 subjectively selected papers out of 111 published in the Annals of Nuclear Medicine during January-December 2019. Following the structure of the EBM hierarchy, we chose at least one study for each step of the pyramid from the basis (pre-clinical research, expert opinion, case report and case series), to the middle (case-control and cohort studies, randomised controlled trials), towards the top (meta-analyses and systematic reviews). Additionally, we collected information on the promoter of each included study: investigator-initiated trials (IITs) vs industry-sponsored trials (ISTs). We found that pre-clinical studies are primarily focused on the development of novel molecular targets in cancer, with promising results. At the same time, clinical investigations deal with cardiological, neurological, infectious and oncological applications using both SPECT and PET modalities. Additionally, radionuclide therapy gained interest and is experiencing comprehensive clinical implementation. Our overview confirms the current central role of IITs as compared with ISTs. Challenges and future directions in Nuclear Medicine research are discussed.

Radiomics of MRI for pretreatment prediction of pathologic complete response, tumor regression grade, and neoadjuvant rectal score in patients with locally advanced rectal cancer undergoing neoadjuvant chemoradiation: an international multicenter study.

OBJECTIVE: To investigate whether pretreatment MRI-based radiomics of locally advanced rectal cancer (LARC) and/or the surrounding mesorectal compartment (MC) can predict pathologic complete response (pCR), neoadjuvant rectal (NAR) score, and tumor regression grade (TRG). METHODS: One hundred thirty-two consecutive patients with LARC who underwent neoadjuvant chemoradiation and total mesorectal excision (TME) were retrospectively collected from 2 centers in the USA and Italy. The primary tumor and surrounding MC were segmented on the best available T2-weighted sequence (axial, coronal, or sagittal). Three thousand one hundred ninety radiomic features were extracted using a python package. The most salient radiomic features as well as MRI parameter and clinical-based features were selected using recursive feature elimination. A logistic regression classifier was built to distinguish between any 2 binned categories in the considered endpoints: pCR, NAR, and TRG. Repeated k-fold validation was performed and AUCs calculated. RESULTS: There were 24, 87, and 21 T4, T3, and T2 LARCs, respectively (median age 63 years, 32 to 86). For NAR and TRG, the best classification performance was obtained using both the tumor and MC segmentations. The AUCs for classifying NAR 0 versus 2, pCR, and TRG 0/1 versus 2/3 were 0.66 (95% CI, 0.60-0.71), 0.80 (95% CI, 0.74-0.85), and 0.80 (95% CI, 0.77-0.82), respectively. CONCLUSION: Radiomics of pretreatment MRIs can predict pCR, TRG, and NAR score in patients with LARC undergoing neoadjuvant treatment and TME with moderate accuracy despite extremely heterogenous image data. Both the tumor and MC contain important prognostic information. KEY POINTS: • Machine learning of rectal cancer on images from the pretreatment MRI can predict important patient outcomes with moderate accuracy. • The tumor and the tissue around it both contain important prognostic information.

Imaging-Based Prediction of Molecular Therapy Targets in NSCLC by Radiogenomics and AI Approaches: A Systematic Review.

The objective of this systematic review was to analyze the current state of the art of imaging-derived biomarkers predictive of genetic alterations and immunotherapy targets in lung cancer. We included original research studies reporting the development and validation of imaging feature-based models. The overall quality, the standard of reporting and the advancements towards clinical practice were assessed. Eighteen out of the 24 selected articles were classified as "high-quality" studies according to the Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2). The 18 "high-quality papers" adhered to Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis (TRIPOD) with a mean of 62.9%. The majority of "high-quality" studies (16/18) were classified as phase II. The most commonly used imaging predictors were radiomic features, followed by visual qualitative computed tomography (CT) features, convolutional neural network-based approaches and positron emission tomography (PET) parameters, all used alone or combined with clinicopathologic features. The majority (14/18) were focused on the prediction of epidermal growth factor receptor (EGFR) mutation. Thirty-five imaging-based models were built to predict the EGFR status. The model's performances ranged from weak (n = 5) to acceptable (n = 11), to excellent (n = 18) and outstanding (n = 1) in the validation set. Positive outcomes were also reported for the prediction of ALK rearrangement, ALK/ROS1/RET fusions and programmed cell death ligand 1 (PD-L1) expression. Despite the promising results in terms of predictive performance, image-based models, suffering from methodological bias, require further validation before replacing traditional molecular pathology testing.

Computed tomography (CT)-derived radiomic features differentiate prevascular mediastinum masses as thymic neoplasms versus lymphomas.

OBJECTIVES: We aimed to assess the ability of radiomics, applied to not-enhanced computed tomography (CT), to differentiate mediastinal masses as thymic neoplasms vs lymphomas. METHODS: The present study was an observational retrospective trial. Inclusion criteria were pathology-proven thymic neoplasia or lymphoma with mediastinal localization, availability of CT. Exclusion criteria were age < 16 years and mediastinal lymphoma lesion < 4 cm. We selected 108 patients (M:F = 47:61, median age 48 years, range 17-79) and divided them into a training and a validation group. Radiomic features were used as predictors in linear discriminant analysis. We built different radiomic models considering segmentation software and resampling setting. Clinical variables were used as predictors to build a clinical model. Scoring metrics included sensitivity, specificity, accuracy and area under the curve (AUC). Wilcoxon paired test was used to compare the AUCs. RESULTS: Fifty-five patients were affected by thymic neoplasia and 53 by lymphoma. In the validation analysis, the best radiomics model sensitivity, specificity, accuracy and AUC resulted 76.2 ± 7.0, 77.8 ± 5.5, 76.9 ± 6.0 and 0.84 ± 0.06, respectively. In the validation analysis of the clinical model, the same metrics resulted 95.2 ± 7.0, 88.9 ± 8.9, 92.3 ± 8.5 and 0.98 ± 0.07, respectively. The AUCs of the best radiomic and the clinical model not differed. CONCLUSIONS: We developed and validated a CT-based radiomic model able to differentiate mediastinal masses on non-contrast-enhanced images, as thymic neoplasms or lymphoma. The proposed method was not affected by image postprocessing. Therefore, the present image-derived method has the potential to noninvasively support diagnosis in patients with prevascular mediastinal masses with major impact on management of asymptomatic cases.