Artificial Intelligence-powered automatic volume calculation in medical images - available tools, performance and challenges for nuclear medicine.

Volumetry is crucial in oncology and endocrinology, for diagnosis, treatment planning, and evaluating response to therapy for several diseases. The integration of Artificial Intelligence (AI) and Deep Learning (DL) has significantly accelerated the automatization of volumetric calculations, enhancing accuracy and reducing variability and labor. In this review, we show that a high correlation has been observed between Machine Learning (ML) methods and expert assessments in tumor volumetry; Yet, it is recognized as more challenging than organ volumetry. Liver volumetry has shown progression in accuracy with a decrease in error. If a relative error below 10 % is acceptable, ML-based liver volumetry can be considered reliable for standardized imaging protocols if used in patients without major anomalies. Similarly, ML-supported automatic kidney volumetry has also shown consistency and reliability in volumetric calculations. In contrast, AI-supported thyroid volumetry has not been extensively developed, despite initial works in 3D ultrasound showing promising results in terms of accuracy and reproducibility. Despite the advancements presented in the reviewed literature, the lack of standardization limits the generalizability of ML methods across diverse scenarios. The domain gap, i. e., the difference in probability distribution of training and inference data, is of paramount importance before clinical deployment of AI, to maintain accuracy and reliability in patient care. The increasing availability of improved segmentation tools is expected to further incorporate AI methods into routine workflows where volumetry will play a more prominent role in radionuclide therapy planning and quantitative follow-up of disease evolution.

Methodological evaluation of original articles on radiomics and machine learning for outcome prediction based on positron emission tomography (PET).

AIM: Despite a vast number of articles on radiomics and machine learning in positron emission tomography (PET) imaging, clinical applicability remains limited, partly owing to poor methodological quality. We therefore systematically investigated the methodology described in publications on radiomics and machine learning for PET-based outcome prediction. METHODS: A systematic search for original articles was run on PubMed. All articles were rated according to 17 criteria proposed by the authors. Criteria with >2 rating categories were binarized into "adequate" or "inadequate". The association between the number of "adequate" criteria per article and the date of publication was examined. RESULTS: One hundred articles were identified (published between 07/2017 and 09/2023). The median proportion of articles per criterion that were rated "adequate" was 65% (range: 23-98%). Nineteen articles (19%) mentioned neither a test cohort nor cross-validation to separate training from testing. The median number of criteria with an "adequate" rating per article was 12.5 out of 17 (range, 4-17), and this did not increase with later dates of publication (Spearman's rho, 0.094; p = 0.35). In 22 articles (22%), less than half of the items were rated "adequate". Only 8% of articles published the source code, and 10% made the dataset openly available. CONCLUSION: Among the articles investigated, methodological weaknesses have been identified, and the degree of compliance with recommendations on methodological quality and reporting shows potential for improvement. Better adherence to established guidelines could increase the clinical significance of radiomics and machine learning for PET-based outcome prediction and finally lead to the widespread use in routine clinical practice.

The Medical Informatics Initiative and the Network University Medicine - Perspectives for Nuclear Medicine.

Digitization in the healthcare sector and the support of clinical workflows with artificial intelligence (AI), including AI-supported image analysis, represent a great challenge and equally a promising perspective for preclinical and clinical nuclear medicine. In Germany, the Medical Informatics Initiative (MII) and the Network University Medicine (NUM) are of central importance for this transformation. This review article outlines these structures and highlights their future role in enabling privacy-preserving federated multi-center analyses with interoperable data structures harmonized between site-specific IT infrastructures. The newly founded working group "Digitization and AI" in the German Society of Nuclear Medicine (DGN) as well as the Fach- und Organspezifische Arbeitsgruppe (FOSA, specialty- and organ-specific working group) founded for the field of nuclear medicine (FOSA Nuklearmedizin) within the NUM aim to initiate and coordinate measures in the context of digital medicine and (image-)data-driven analyses for the DGN.

Inferring FDG-PET-positivity of lymph node metastases in proven lung cancer from contrast-enhanced CT using radiomics and machine learning.

BACKGROUND: We evaluated the role of radiomics applied to contrast-enhanced computed tomography (CT) in the detection of lymph node (LN) metastases in patients with known lung cancer compared to 18F-fluorodeoxyglucose positron emission tomography (PET)/CT as a reference. METHODS: This retrospective analysis included 381 patients with 1,799 lymph nodes (450 malignant, 1,349 negative). The data set was divided into a training and validation set. A radiomics analysis with 4 filters and 6 algorithms resulting in 24 different radiomics signatures and a bootstrap algorithm (Bagging) with 30 bootstrap iterations was performed. A decision curve analysis was applied to generate a net benefit to compare the radiomics signature to two expert radiologists as one-by-one and as a prescreening tool in combination with the respective radiologist and only the radiologists. RESULTS: All 24 modeling methods showed good and reliable discrimination for malignant/benign LNs (area under the curve 0.75-0.87). The decision curve analysis showed a net benefit for the least absolute shrinkage and selection operator (LASSO) classifier for the entire probability range and outperformed the expert radiologists except for the high probability range. Using the radiomics signature as a prescreening tool for the radiologists did not improve net benefit. CONCLUSIONS: Radiomics showed good discrimination power irrespective of the modeling technique in detecting LN metastases in patients with known lung cancer. The LASSO classifier was a suitable diagnostic tool and even outperformed the expert radiologists, except for high probabilities. Radiomics failed to improve clinical benefit as a prescreening tool.

Point Spread Function Reconstruction for Integrated 18F-FET PET/MRI in Patients With Glioma: Does It Affect SUVs and Respective Tumor-to-Background Ratios?

PURPOSE: Semiquantitative F-FET PET assessment using the tumor's SUV or tumor-to-background ratios (TBRs) can separate gliomas from peritumoral tissue or progression from pseudoprogression. This study investigated if point spread function (PSF) reconstruction of F-FET PET data affects SUV-based dignity assessment. MATERIALS AND METHODS: This study is a retrospective analysis of 87 glioma patients (female, 36; male, 51; age, 48 [13-81] years) undergoing F-FET PET/MRI for staging (n = 17) or restaging (n = 70). PET was reconstructed using ordered-subset expectation maximization with and without PSF. Lesions were delineated with semiautomated background-adapted thresholding relative to SUVmax; background was delineated contralaterally. Comparative measurements with a National Electrical Manufacturers Association International Electrotechnical Commission PET body phantom (sphere-to-background ratios, 8:1 and 4:1) were performed. RESULTS: PSF showed significantly higher tumor SUVmax (median difference, +0.1; interquartile range, 0.04-0.18), SUVmean (+0.05; 0.03-0.08), TBRmax|mean (+0.1; 0.04-0.2), and TBRmean|mean (+0.06; 0.03-0.09) than non-PSF (P < 0.001). Background SUVmean was unaffected. In patients and phantom, differences between PSF and non-PSF increased with TBR and decreased with lesion's PET volume. Differences only exceeded 0.2 SUV for SUVmax or 0.1 SUV for SUVmean if TBR was greater than 3 and lesion's PET volume was less than 10 mL (d = 27 mm). Dignity assessment by PSF and non-PSF was concordant in all patients examined for staging (cutoff, TBRmean|mean > 1.6; positive, 14; negative, 3) and restaging (cutoff, TBRmax|mean > 2.0; positive, 67; negative, 3). CONCLUSIONS: PSF increased tumor SUVmax and SUVmean compared with non-PSF F-FET PET/MRI data, especially in small lesions with high TBR (>3). However, dignity assessment using established TBR cutoffs was not affected.