Cardiotoxicity and cardiac monitoring following the use of radiotheranostics agents including 177Lu-PSMA for prostate cancer and 177Lu-DOTATATE for neuroendocrine tumors

A convolutional neural network-based system for fully automatic segmentation of whole-body [68Ga]Ga-PSMA PET images in prostate cancer

PURPOSE

The aim of this study was development and evaluation of a fully automated tool for the detection and segmentation of mPCa lesions in whole-body [68Ga]Ga-PSMA-11 PET scans by using a nnU-Net framework.

METHODS

In this multicenter study, a cohort of 412 patients from three different center with all indication of PCa who underwent [68Ga]Ga-PSMA-11 PET/CT were enrolled. Two hundred cases of center 1 dataset were used for training the model. A fully 3D convolutional neural network (CNN) is proposed which is based on the self-configuring nnU-Net framework. A subset of center 1 dataset and cases of center 2 and center 3 were used for testing of model. The performance of the segmentation pipeline that was developed was evaluated by comparing the fully automatic segmentation mask with the manual segmentation of the corresponding internal and external test sets in three levels including patient-level scan classification, lesion-level detection, and voxel-level segmentation. In addition, for comparison of PET-derived quantitative biomarkers between automated and manual segmentation, whole-body PSMA tumor volume (PSMA-TV) and total lesions PSMA uptake (TL-PSMA) were calculated.

RESULTS

In terms of patient-level classification, the model achieved an accuracy of 83%, sensitivity of 92%, PPV of 77%, and NPV of 91% for the internal testing set. For lesion-level detection, the model achieved an accuracy of 87-94%, sensitivity of 88-95%, PPV of 98-100%, and F1-score of 93-97% for all testing sets. For voxel-level segmentation, the automated method achieved average values of 65-70% for DSC, 72-79% for PPV, 53-58% for IoU, and 62-73% for sensitivity in all testing sets. In the evaluation of volumetric parameters, there was a strong correlation between the manual and automated measurements of PSMA-TV and TL-PSMA for all centers.

CONCLUSIONS

The deep learning networks presented here offer promising solutions for automatically segmenting malignant lesions in prostate cancer patients using [68Ga]Ga-PSMA PET. These networks achieve a high level of accuracy in whole-body segmentation, as measured by the DSC and PPV at the voxel level. The resulting segmentations can be used for extraction of PET-derived quantitative biomarkers and utilized for treatment response assessment and radiomic studies.

Dosing lutetium Lu 177-dotatate for a hemodialysis patient

Lu177-dotatate (Lutathera™) is a radioactive drug approved for the treatment of adults with gastro-entero-pancreatic neuroendocrine tumors and is predominantly renally excreted. Currently all patients receive 7400 MBq (200 mCi), and there are no guidelines for treating hemodialysis patients. We measured radioactivity prior to and post administration of two cycles of Lu177-dotatate in a hemodialysis patient, and radiation exposure to staff. We reduced the standard 7400 MBq by 33% for the first cycle and patient radioactivity fell by 40% following postdilution hemodiafiltration started 6 h post dosing, and by 45% for the second cycle and radioactivity fell by 47% with postdilution hemodiafiltration started 5 h post administration. By reducing the initial administered radioactivity, coupled with early dialysis, and choosing postdilution hemodiafiltration we were able to achieve radioactivity retention curves similar to those from patients with normal renal function receiving the standard administration of 7400 MBq.

Molecular Imaging Biomarkers in Cardiooncology: A View on Established Technologies and Future Perspectives

Novel therapeutic options have significantly improved survival and long-term outcomes in many cancer entities. Unfortunately, this improvement in outcome is often accompanied by new and increasingly relevant therapy-related cardiovascular toxicity. In this context, cardiooncology has emerged as a new field of interdisciplinary individual patient care. Important tasks are pretherapeutic risk stratification and early detection and treatment of cardiotoxicity, which comprises cardiac damage in relation to cardiovascular comorbidities, the tumor disease, and cancer treatment. Clinical manifestations can cover a broad spectrum, ranging from subtle and usually asymptomatic abnormalities to serious acute or chronic complications. Typical manifestations include acute and chronic heart failure, myo- and pericarditis, arrythmias, ischemia, and endothelial damage. They can be related to almost all current cancer treatments, including cytotoxic chemotherapy, targeted therapy, immunotherapy, hormonal therapy, and radiotherapy. Molecular imaging biomarkers can aid in pretherapeutic cardiooncologic assessment for primary prevention and personalized surveillance, detection, and differential diagnosis of cardiotoxic complications. Potential advantages over conventional diagnostics are the higher detection sensitivity for subtle changes in cardiac homeostasis, higher reproducibility, and better observer independence. Hybrid imaging with highly sensitive PET/MRI may be particularly suited for early diagnosis. Important technologies that are encouraged in current multidisciplinary guidelines are equilibrium radionuclide angiography for evaluation of ventricular function and chamber morphology, as well as myocardial perfusion imaging for additional detection of ischemia. Novel modalities that may detect even earlier signs of cardiotoxicity comprise 123I-metaiodobenzylguanidine SPECT to visualize sympathetic innervation, 18F-FDG and somatostatin receptor (68Ga-DOTATOC/DOTATATE) PET to indicate a metabolic shift and inflammation, and 68Ga-fibroblast activation protein inhibitor PET to monitor cardiac remodeling. In addition, PET imaging of mitochondrial function has recently been introduced in preclinical models and will potentially broaden the field of application through higher sensitivity and specificity and by enabling higher individualization of diagnostic concepts.

New Insights in PRRT: Lessons From 2021

Peptide receptor radionuclide therapy (PRRT) using radiolabeled somatostatin analogs has been used for over two decades for the treatment of well-differentiated neuroendocrine tumors (NETs), and the publication of the NETTER-1 trials has further strengthened its clinical use. However, many aspects of this treatment are still under discussion. The purpose of this review is to collect and discuss the new available evidence, published in 2021, on the use of ¹⁷⁷Lu-Oxodotreotide (DOTATATE) or ⁹⁰Y-Edotreotide (DOTATOC) in adult patients with NETs focusing on the following hot topics: 1) PRRT use in new clinical settings, broaden its indications; 2) the short- and long-term safety; and 3) the identification of prognostic and predictive factors. The review suggests a possible future increase of PRRT applications, using it in other NETs, as a neoadjuvant treatment, or for rechallenge. Regarding safety, available studies, even those with long follow-up, supported the low rates of adverse events, even though 1.8% of treated patients developed a second malignancy. Finally, there is a lack of prognostic and predictive factors for PRRT, with the exception of the crucial role of nuclear imaging for both patient selection and treatment response estimation.