Purpose
The aim of this systematic review was to analyse literature on artificial intelligence (AI) and radiomics, including all medical imaging modalities, for oncological and non-oncological ...applications, in order to assess how far the image mining research stands from routine medical application. To do this, we applied a trial phases classification inspired from the drug development process.
Methods
Among the articles we considered for inclusion from PubMed were multimodality AI and radiomics investigations, with a validation analysis aimed at relevant clinical objectives. Quality assessment of selected papers was performed according to the QUADAS-2 criteria. We developed the phases classification criteria for image mining studies.
Results
Overall 34,626 articles were retrieved, 300 were selected applying the inclusion/exclusion criteria, and 171 high-quality papers (QUADAS-2 ≥ 7) were identified and analysed. In 27/171 (16%), 141/171 (82%), and 3/171 (2%) studies the development of an AI-based algorithm, radiomics model, and a combined radiomics/AI approach, respectively, was described. A total of 26/27(96%) and 1/27 (4%) AI studies were classified as phase II and III, respectively. Consequently, 13/141 (9%), 10/141 (7%), 111/141 (79%), and 7/141 (5%) radiomics studies were classified as phase 0, I, II, and III, respectively. All three radiomics/AI studies were categorised as phase II trials.
Conclusions
The results of the studies are promising but still not mature enough for image mining tools to be implemented in the clinical setting and be widely used. The transfer learning from the well-known drug development process, with some specific adaptations to the image mining discipline could represent the most effective way for radiomics and AI algorithms to become the standard of care tools.
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
GaGa-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 (I
2
-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 (I
2
= 88.56% and I
2
= 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 (I
2
= 89.18% and I
2
= 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
18
FFDG 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.
Purpose
Several patients experience unexplained persistent symptoms after SARS-CoV-2 recovering. We aimed at evaluating if 2-deoxy-2-
18
Ffluoro-D-glucose (
18
FFDG) was able to demonstrate a ...persistent inflammatory process.
Methods
Recovered adult COVID-19 patients, who complained unexplained persisting symptoms for more than 30 days during the follow-up visits, were invited to participate in the study. Patients fulfilling inclusion criteria were imaged by
18
FFDG positron emission tomography/computed tomography (
18
FFDG-PET/CT). Whole-body
18
FFDG-PET/CT, performed according to good clinical practice, was qualitatively (comparison with background/liver) and semi-quantitatively (target-to-blood pool ratio calculated as average SUVmax artery/average SUVmean inferior vena cava) analyzed. Negative follow-up
18
FFDG-PET/CT images of oncologic patients matched for age/sex served as controls. Mann-Whitney test was used to test differences between groups. SPSS version 26 was used for analyses.
Results
Ten recovered SARS-CoV-2 patients (seven male and three females, median age 52 years, range 46–80) with persisting symptoms were enrolled in the study. Common findings at visual analysis were increased
18
FFDG uptake in bone marrow and blood vessels (8/10 and 6/10 cases, respectively).
18
FFDG uptake in bone marrow did not differ between cases and controls (
p
= 0.16). The total vascular score was similar in the two groups (
p
= 0.95). The target-to-blood pool ratio resulted higher in recovered SARS-CoV-2 patients than in controls.
Conclusion
Although the total vascular score was similar in the two groups, the target-to-blood pool ratio was significantly higher in three vascular regions (thoracic aorta, right iliac artery, and femoral arteries) in the recovered COVID-19 cohort than in controls, suggesting that SARS-CoV-2 induces vascular inflammation, which may be responsible for persisting symptoms.
•Interest has grown in texture analysis and machine learning in medical imaging.•Computerized systems play a growing role in thyroid nodule characterization.•Quantitative image analysis can improve ...diagnostic accuracy of thyroid nodules.•Methodological issues need to be solved in texture analysis and machine learning.•Quantitative image analysis should be standardized and validated on large scale.
In thyroid imaging, “texture” refers to the echographic appearence of the parenchyma or a nodule. However, definition of the image characteristics is operator dependent and influenced by the operator’s experience. In a more objective texture analysis, a variety of mathematical methods are used to describe image inhomogeneity, allowing assessment of an image by means of quantitative parameters. Moreover, this approach may be used to develop an efficient computer-aided diagnosis (CAD) system to yield a second opinion when differentiating malignant and benign thyroid lesions. The aim of this review is to summarize the available literature data on texture analysis, with and without CAD, in patients with suspected thyroid nodules or differentiated thyroid cancer, and to assess the current state of the approach.
Purpose
The present study hypothesised that whole-body 18FFDG-PET/CT might provide insight into the pathophysiology of long COVID.
Methods
We prospectively enrolled 13 adult long COVID patients who ...complained for at least one persistent symptom for >30 days after infection recovery. A group of 26 melanoma patients with negative PET/CT matched for sex/age was used as controls (2:1 control to case ratio). Qualitative and semi-quantitative analysis of whole-body images was performed. Fisher exact and Mann-Whitney tests were applied to test differences between the two groups. Voxel-based analysis was performed to compare brain metabolism in cases and controls. Cases were further grouped according to prevalent symptoms and analysed accordingly.
Results
In 4/13 long COVID patients, CT images showed lung abnormalities presenting mild 18FFDG uptake. Many healthy organs/parenchyma SUVs and SUV ratios significantly differed between the two groups (
p
≤ 0.05). Long COVID patients exhibited brain hypometabolism in the right parahippocampal gyrus and thalamus (uncorrected
p
< 0.001 at voxel level). Specific area(s) of hypometabolism characterised patients with persistent anosmia/ageusia, fatigue, and vascular uptake (uncorrected
p
< 0.005 at voxel level).
Conclusion
18FFDG PET/CT acknowledged the multi-organ nature of long COVID, supporting the hypothesis of underlying systemic inflammation. Whole-body images showed increased 18FFDG uptake in several “target” and “non-target” tissues. We found a typical pattern of brain hypometabolism associated with persistent complaints at the PET time, suggesting a different temporal sequence for brain and whole-body inflammatory changes. This evidence underlined the potential value of whole-body 18FFDG PET in disclosing the pathophysiology of long COVID.
Purpose
Radiomic features derived from the texture analysis of different imaging modalities e show promise in lesion characterisation, response prediction, and prognostication in lung cancer ...patients. The present study aimed to identify an images-based radiomic signature capable of predicting disease-free survival (DFS) in non-small cell lung cancer (NSCLC) patients undergoing surgery.
Methods
A cohort of 295 patients was selected. Clinical parameters (age, sex, histological type, tumour grade, and stage) were recorded for all patients. The endpoint of this study was DFS. Both computed tomography (CT) and fluorodeoxyglucose positron emission tomography (PET) images generated from the PET/CT scanner were analysed. Textural features were calculated using the LifeX package. Statistical analysis was performed using the R platform. The datasets were separated into two cohorts by random selection to perform training and validation of the statistical models. Predictors were fed into a multivariate Cox proportional hazard regression model and the receiver operating characteristic (ROC) curve as well as the corresponding area under the curve (AUC) were computed for each model built.
Results
The Cox models that included radiomic features for the CT, the PET, and the PET+CT images resulted in an AUC of 0.75 (95%CI: 0.65–0.85), 0.68 (95%CI: 0.57–0.80), and 0.68 (95%CI: 0.58–0.74), respectively. The addition of clinical predictors to the Cox models resulted in an AUC of 0.61 (95%CI: 0.51–0.69), 0.64 (95%CI: 0.53–0.75), and 0.65 (95%CI: 0.50–0.72) for the CT, the PET, and the PET+CT images, respectively.
Conclusions
A radiomic signature, for either CT, PET, or PET/CT images, has been identified and validated for the prediction of disease-free survival in patients with non-small cell lung cancer treated by surgery.
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.
Purpose
To evaluate the ability of CT and PET radiomics features to classify lung lesions as primary or metastatic, and secondly to differentiate histological subtypes of primary lung cancers.
...Methods
A cohort of 534 patients with lung lesions were retrospectively studied. Radiomics texture features were extracted using the LIFEx package from semiautomatically segmented PET and CT images. Histology data were recorded in all patients. The patient cohort was divided into a training and a validation group and linear discriminant analysis (LDA) was performed to classify the lesions using both direct and backward stepwise methods. The robustness of the procedure was tested by repeating the entire process 100 times with different assignments to the training and validation groups. Scoring metrics included analysis of the receiver operating characteristic curves in terms of area under the curve (AUC), sensitivity, specificity and accuracy.
Results
Radiomics features extracted from CT and PET datasets were able to differentiate primary tumours from metastases in both the training and the validation group (AUCs 0.79 ± 0.03 and 0.70 ± 0.04, respectively, from the CT dataset; AUCs 0.92 ± 0.01 and 0.91 ± 0.03, respectively, from the PET dataset). The AUC cut-off thresholds identified by LDA using direct and backward elimination strategies were −0.79 ± 0.06 and −0.81 ± 0.08, respectively (CT dataset) and −0.69 ± 0.05 and −0.68 ± 0.04, respectively (PET dataset). For differentiation between primary subgroups based on CT features, the AUCs in the training and validation groups were 0.81 ± 0.02 and 0.69 ± 0.04 for adenocarcinoma (Adc) vs. squamous cell carcinoma (Sqc) or “Other”, 0.85 ± 0.02 and 0.70 ± 0.05 for Sqc vs. Adc or Other, and 0.77 ± 0.03 and 0.57 ± 0.05 for Other vs. Adc or Sqc. The same analyses for the PET data revealed AUCs of 0.90 ± 0.10 and 0.80 ± 0.04, 0.80 ± 0.02 and 0.61 ± 0.06, and 0.97 ± 0.01 and 0.88 ± 0.04, respectively.
Conclusion
PET radiomics features were able to differentiate between primary and metastatic lung lesions and showed the potential to identify primary lung cancer subtypes.