Radioligand theranostics (RT) in oncology use cancer-type specific biomarkers and molecular imaging (MI), including positron emission tomography (PET), single-photon emission computed tomography (SPECT) and planar scintigraphy, for patient diagnosis, therapy, and personalized management. While the definition of theranostics was initially restricted to a single compound allowing visualization and therapy simultaneously, the concept has been widened with the development of theranostic pairs and the combination of nuclear medicine with different types of cancer therapies. Here, we review the clinical applications of different theranostic radiopharmaceuticals in managing different tumor types (differentiated thyroid, neuroendocrine prostate, and breast cancer) that support the combination of innovative oncological therapies such as gene and cell-based therapies with RT.

Prostate-specific membrane antigen (PSMA) positron emission tomography/computed tomography (PSMA-PET/CT) scans can facilitate diagnosis and treatment of prostate disease. Radiomics signature (RS) is widely used for the analysis of overall survival (OS) in cancer diseases. This study aims at investigating the role of radiomics features (RFs) and RS from pretherapeutic gallium-68 (⁶⁸Ga)-PSMA-PET/CT findings and patient-specific clinical parameters to analyze overall survival of prostate cancer (PC) patients when treated with lutethium-177 (¹⁷⁷Lu)-PSMA. A cohort of 83 patients with advanced PC was retrospectively analyzed. Average values of 73 RFs of 2070 malignant hotspots as well as 22 clinical parameters were analyzed for each patient. From the Cox proportional hazard model, the least absolute shrinkage and selection operator (LASSO) regularization method is used to select most relevant features (standardized uptake value (SUV)_Min and kurtosis with the coefficients of 0.984 and −0.118, respectively) and to calculate the RS from the RFs. Kaplan–Meier (KM) estimator was used to analyze the potential of RFs and conventional clinical parameters, such as metabolic tumor volume (MTV) and standardized uptake value (SUV) for the prediction of survival. As a result, SUV_Min, kurtosis, the calculated RS, SUV_Mean, as well as Hemoglobin (Hb)1, C-reactive protein (CRP)1, and ECOG1 (clinical parameters) achieved p-values less than 0.05, which suggest the potential of findings from ⁶⁸Ga-PSMA-PET/CT scans as well as patient-specific clinical parameters for the prediction of OS for patients with advanced PC treated with ¹⁷⁷Lu-PSMA therapy.

Background: Labelled with lutetium-177, the urea-based small molecules PSMA I&T and PSMA-617 are the two agents most frequently used for radioligand therapy (RLT) in patients with advanced metastatic castration-resistant and prostate-specific membrane antigen (PSMA) expressing prostate cancer (mCRPC). In this matched-pair analysis, we aimed to compare the toxicity and efficacy of both agents for PSMA-directed RLT. Materials and methods: A total of 110 mCRPC patients from two centres were accrued, 55 individuals treated with [¹⁷⁷Lu]Lu-PSMA I&T, and a matched cohort of 55 patients treated with [¹⁷⁷Lu]Lu-PSMA-617. Matching criteria included age at the first cycle, Gleason score, prostate-specific antigen (PSA) values, and previous taxane-based chemotherapy. Using common terminology criteria for adverse events (CTCAE v. 5.0), toxicity profiles were investigated (including bone marrow and renal toxicity). Overall survival (OS) between both groups was compared. Results: Toxicity assessment revealed grade III anaemia in a single patient (1.8%) for [¹⁷⁷Lu]Lu-PSMA I&T and five (9.1%) for [¹⁷⁷Lu]Lu-PSMA-617. In addition, one (1.9%) grade III thrombopenia for [¹⁷⁷Lu]Lu-PSMA-617 was recorded. Apart from that, no other grade III/IV toxicities were present. A median OS of 12 months for patients treated with [¹⁷⁷Lu]Lu-PSMA I&T did not differ significantly when compared to patients treated with [¹⁷⁷Lu]Lu-PSMA-617 (median OS, 13 months; P = 0.89). Conclusion: In this matched-pair analysis of patients receiving one of the two agents most frequently applied for PSMA RLT, the rate of clinically relevant toxicities was low for both compounds. In addition, no relevant differences for OS were observed.

Purpose: Bone scintigraphy is the standard of reference in bone metastases in prostate cancer patients. However, new radiotracers employed in prostate-specific membrane antigen (PSMA)-ligands has led to the growing importance of PET/CT as diagnostic tool. The aim of our study was to investigate the difference between bone scan and PSMA-PET/CT for the detection of bone metastases in prostate cancer. Methods: Thirty patients with bone metastases originating from prostate cancer were examined by ^99mTc-MDP bone scan and ⁶⁸Ga-PSMA-PET/CT within an average of 21 days. Bone scans were analyzed visually according to the number of lesions and using the software package ExiniBONE by Exini Diagnostics. PET/CT data was analyzed visually. Numbers of detected lesions were compared for the different methods for the whole patient and for different regions. In addition, results were compared to serum prostate-specific antigen (PSA), alkaline phosphatase (ALP), bone alkaline phosphatase (bALP), pro gastrin releasing peptide (pGRP) and eastern cooperative oncology group (ECOG) performance status. Results: In the bone scans, visual and semiautomatic lesion detection showed similar results with an average of 19.4 and 17.8 detected bone lesion per patient. However, in PSMA-PET/CT, on average double the numbers of lesions (40.0) were detected. The largest differences were found in the thorax and pelvis, which can be explained by the advantages of tomographic imaging. Bland-Altman analysis showed greater differences in patients with large numbers of bone metastases. Conclusion: No significant difference was found when using semiautomatic analysis compared to visual reading for bone scans. Fewer bone metastases were detected in bone scans than in PSMA-PET/CT. However, in none of our patients would the difference have led to clinical consequences. Therefore, it seems that for patients undergoing PSMA-PET/CT, there is no need to perform additional bone scans if the appropriate PET/CT protocols are applied.

Gallium-68 prostate-specific membrane antigen positron emission tomography (⁶⁸Ga-PSMA-PET) is a highly sensitive method to detect prostate cancer (PC) metastases. Visual discrimination between malignant and physiologic/unspecific tracer accumulation by a nuclear medicine (NM) specialist is essential for image interpretation. In the future, automated machine learning (ML)-based tools will assist physicians in image analysis. The aim of this work was to develop a tool for analysis of ⁶⁸Ga-PSMA-PET images and to compare its efficacy to that of human readers. Five different ML methods were compared and tested on multiple positron emission tomography/computed tomography (PET/CT) data-sets. Forty textural features extracted from both PET- and low-dose CT data were analyzed. In total, 2419 hotspots from 72 patients were included. Comparing results from human readers to those of ML-based analyses, up to 98% area under the curve (AUC), 94% sensitivity (SE), and 89% specificity (SP) were achieved. Interestingly, textural features assessed in native low-dose CT increased the accuracy significantly. Thus, ML based on ⁶⁸Ga-PSMA-PET/CT radiomics features can classify hotspots with high precision, comparable to that of experienced NM physicians. Additionally, the superiority of multimodal ML-based analysis considering all PET and low-dose CT features was shown. Morphological features seemed to be of special additional importance even though they were extracted from native low-dose CTs.

The importance of machine learning (ML) in the clinical environment increases constantly. Differentiation of pathological from physiological tracer-uptake in positron emission tomography/computed tomography (PET/CT) images is considered time-consuming and attention intensive, hence crucial for diagnosis and treatment planning. This study aimed at comparing and validating supervised ML algorithms to classify pathological uptake in prostate cancer (PC) patients based on prostate-specific membrane antigen (PSMA)-PET/CT. Retrospective analysis of ⁶⁸Ga-PSMA-PET/CTs of 72 PC patients resulted in a total of 77 radiomics features from 2452 manually delineated hotspots for training and labeled pathological (1629) or physiological (823) as ground truth (GT). As the held-out test dataset, 331 hotspots (path.:128, phys.: 203) were delineated in 15 other patients. Three ML classifiers were trained and ranked to assess classification performance. As a result, a high overall average performance (area under the curve (AUC) of 0.98) was achieved, especially to detect pathological uptake (0.97 mean sensitivity). However, there is still room for improvement to detect physiological uptake (0.82 mean specificity), especially for glands. The ML algorithm applied to manually delineated lesions predicts hotspot labels with high accuracy on unseen data and may be an important tool to assist in clinical diagnosis.