RESUMO
OBJECTIVE: Immunotherapy has dramatically altered the therapeutic landscape for oncology, but more research is needed to identify patients who are likely to achieve durable clinical benefit and those who may develop unacceptable side effects. We investigated the role of artificial intelligence in PET/SPECT-guided approaches for immunotherapy-treated patients. METHODS: We performed a scoping review of MEDLINE, CENTRAL, and Embase databases using key terms related to immunotherapy, PET/SPECT imaging, and AI/radiomics through October 12, 2022. RESULTS: Of the 217 studies identified in our literature search, 24 relevant articles were selected. The median (interquartile range) sample size of included patient cohorts was 63 (157). Primary tumors of interest were lung (n = 14/24, 58.3%), lymphoma (n = 4/24, 16.7%), or melanoma (n = 4/24, 16.7%). A total of 28 treatment regimens were employed, including anti-PD-(L)1 (n = 13/28, 46.4%) and anti-CTLA-4 (n = 4/28, 14.3%) monoclonal antibodies. Predictive models were built from imaging features using univariate radiomics (n = 7/24, 29.2%), radiomics (n = 12/24, 50.0%), or deep learning (n = 5/24, 20.8%) and were most often used to prognosticate (n = 6/24, 25.0%) or describe tumor phenotype (n = 5/24, 20.8%). Eighteen studies (75.0%) performed AI model validation. CONCLUSION: Preliminary results suggest broad potential for the application of AI-guided immunotherapy management after further validation of models on large, prospective, multicenter cohorts. CLINICAL RELEVANCE STATEMENT: This scoping review describes how artificial intelligence models are built to make predictions based on medical imaging and explores their application specifically in the PET and SPECT examination of immunotherapy-treated cancers. KEY POINTS: ⢠Immunotherapy has drastically altered the cancer treatment landscape but is known to precipitate response patterns that are not accurately accounted for by traditional imaging methods. ⢠There is an unmet need for better tools to not only facilitate in-treatment evaluation but also to predict, a priori, which patients are likely to achieve a good response with a certain treatment as well as those who are likely to develop side effects. ⢠Artificial intelligence applied to PET/SPECT imaging of immunotherapy-treated patients is mainly used to make predictions about prognosis or tumor phenotype and is built from baseline, pre-treatment images. Further testing is required before a true transition to clinical application can be realized.
RESUMO
ABSTRACT: Positron emission tomography (PET) is an established tool for molecular imaging of cancers, and its role in diagnosis, staging, and phenotyping continues to evolve and expand rapidly. PET imaging of increased glucose utilization with 18F-fluorodeoxyglucose is now entrenched in clinical oncology practice for improving prognostication and treatment response assessment. Additional critical processes for cancer cell survival can also be imaged by PET, helping to inform individualized treatment selections for patients by improving our understanding of cell survival mechanisms and identifying relevant active mechanisms in each patient. The critical importance of quantifying cell proliferation and DNA repair pathways for prognosis and treatment selection is highlighted by the nearly ubiquitous use of the Ki-67 index, an established histological quantitative measure of cell proliferation, and BRCA mutation testing for treatment selection. This review focuses on PET advances in imaging and quantifying cell proliferation and poly(ADP-ribose)polymerase expression that can be used to complement cancer phenotyping approaches that will identify the most effective treatments for each individual patient.
Assuntos
Proliferação de Células , Reparo do DNA , Neoplasias , Tomografia por Emissão de Pósitrons , Humanos , Tomografia por Emissão de Pósitrons/métodos , Neoplasias/diagnóstico por imagem , Neoplasias/patologia , Neoplasias/genética , Neoplasias/diagnóstico , Neoplasias/metabolismo , Fluordesoxiglucose F18 , Compostos Radiofarmacêuticos , Imagem Molecular/métodosRESUMO
Merkel cell carcinoma (MCC) is a neuroendocrine skin cancer with a high risk of recurrence and metastasis. Regular surveillance through physical exams and imaging studies is crucial for the timely detection of recurrences. MCC patients who produce antibodies to the Merkel cell polyomavirus oncoprotein may benefit from antibody testing in addition to routine imaging surveillance for the early detection of disease recurrence. The clinically available Anti MERKel cell panel (AMERK) is a sensitive tumor marker for Merkel cell polyomavirus positive MCC. Although AMERK is highly sensitive, imaging remains necessary to confirm the location of disease recurrence. MCC exhibits characteristic imaging features, making appropriate imaging modalities, and interpretation important for detection. We present 3 representative patient cases that highlight effective utilization of the AMERK test in addition to imaging for the early detection of MCC recurrence. The rise in the AMERK titer may occur before the disease reaches detectable size on computed tomography scans. Positron emission tomography (PET)-CT can serve as an alternative modality for the early detection of disease. Even subtle abnormalities in 18F-FDG uptake may be significant if accompanied by an increased AMERK titer. Alternative imaging modalities, such as 68Ga-DOTATATE PET-CT and magnetic resonance imaging, can be useful in revealing clinically occult disease in MCC patients. In summary, the AMERK antibody test, alongside imaging, enhances sensitivity in detecting recurrence. By combining these strategies of blood test and imaging, healthcare professionals can identify early signs of MCC recurrence, leading to prompt interventions and improved patient outcomes.
RESUMO
Genetic testing and molecular imaging have great promise in the accurate diagnosis and treatment of #prostate #cancer, but only if they can be developed and implemented to achieve equitable benefit for all men.
Assuntos
Biomarcadores Tumorais , Medicina de Precisão , Neoplasias da Próstata , Humanos , Neoplasias da Próstata/terapia , Neoplasias da Próstata/diagnóstico , Neoplasias da Próstata/genética , Medicina de Precisão/métodos , Masculino , Acessibilidade aos Serviços de SaúdeRESUMO
Prostate-specific membrane antigen-positron emission tomography (PSMA-PET) is transforming the management of patients with prostate cancer. In appropriately selected patients, PSMA-PET offers superior sensitivity and specificity compared to conventional imaging (e.g., computed tomography and bone scintigraphy) as well as choline and fluciclovine PET, with the added benefit of consolidating bone and soft tissue evaluation into a single study. Despite being a newly available imaging tool, PSMA-PET has established indications, interpretation guidelines, and reporting criteria, which will be reviewed. The prostate cancer care team, from imaging specialists to those delivering treatment, should have knowledge of physiologic PSMA radiotracer uptake, patterns of disease spread, and the strengths and limitations of PSMA-PET. In this review, current and emerging applications of PSMA-PET, including appropriateness use criteria as well as image interpretation and pitfalls, will be provided with an emphasis on clinical implications.
Assuntos
Próstata , Neoplasias da Próstata , Masculino , Humanos , Tomografia por Emissão de Pósitrons combinada à Tomografia Computadorizada/métodos , Radioisótopos de Gálio , Neoplasias da Próstata/diagnóstico por imagem , Neoplasias da Próstata/terapia , Tomografia por Emissão de PósitronsRESUMO
BACKGROUND: Lesion detection is one of the most important clinical tasks in positron emission tomography (PET) for oncology. An anthropomorphic model observer (MO) designed to replicate human observers (HOs) in a detection task is an important tool for assessing task-based image quality. The channelized Hotelling observer (CHO) has been the most popular anthropomorphic MO. Recently, deep learning MOs (DLMOs), mostly based on convolutional neural networks (CNNs), have been investigated for various imaging modalities. However, there have been few studies on DLMOs for PET. PURPOSE: The goal of the study is to investigate whether DLMOs can predict HOs better than conventional MOs such as CHO in a two-alternative forced-choice (2AFC) detection task using PET images with real anatomical variability. METHODS: Two types of DLMOs were implemented: (1) CNN DLMO, and (2) CNN-SwinT DLMO that combines CNN and Swin Transformer (SwinT) encoders. Lesion-absent PET images were reconstructed from clinical data, and lesion-present images were reconstructed with adding simulated lesion sinogram data. Lesion-present and lesion-absent PET image pairs were labeled by eight HOs consisting of four radiologists and four image scientists in a 2AFC detection task. In total, 2268 pairs of lesion-present and lesion-absent images were used for training, 324 pairs for validation, and 324 pairs for test. CNN DLMO, CNN-SwinT DLMO, CHO with internal noise, and non-prewhitening matched filter (NPWMF) were compared in the same train-test paradigm. For comparison, six quantitative metrics including prediction accuracy, mean squared errors (MSEs) and correlation coefficients, which measure how well a MO predicts HOs, were calculated in a 9-fold cross-validation experiment. RESULTS: In terms of the accuracy and MSE metrics, CNN DLMO and CNN-SwinT DLMO showed better performance than CHO and NPWMF, and CNN-SwinT DLMO showed the best performance among the MOs evaluated. CONCLUSIONS: DLMO can predict HOs more accurately than conventional MOs such as CHO in PET lesion detection. Combining SwinT and CNN encoders can improve the DLMO prediction performance compared to using CNN only.
RESUMO
PURPOSE: While 177Lu-PSMA-617 (LuPSMA) is an effective therapy for many patients with metastatic castration-resistant prostate cancer (mCRPC), biomarkers associated with outcomes are not well defined. We hypothesized that prostate cancer mutational profile may associate with clinical activity of LuPSMA. We devised a study to evaluate associations between mCRPC mutational profile with LuPSMA clinical outcomes. METHODS: This was a multicenter retrospective analysis of patients with mCRPC with next-generation sequencing (NGS) who received LuPSMA. PSA50 response (ie, ≥50% decline in prostate-specific antigen [PSA]) rate, PSA progression free survival (PSA PFS), and overall survival (OS) were compared between genetically defined subgroups. RESULTS: One hundred twenty-six patients with NGS results who received at least one cycle of LuPSMA were identified. The median age was 73 (IQR, 68-78) years, 124 (98.4%) received ≥1 prior androgen receptor-signaling inhibitor, and 121 (96%) received ≥1 taxane-based chemotherapy regimen. Fifty-eight (46%) patients with a DNA damage repair gene mutation (DNA damage response group) and 59 (46.8%) with a mutation in TP53, RB1, or PTEN tumor suppressor genes (TSG group) were identified. After adjusting for relevant confounders, the presence of ≥1 TSG mutation was associated with shorter PSA PFS (hazard ratio [HR], 1.93 [95% CI, 1.05 to 3.54]; P = .034) and OS (HR, 2.65 [95% CI, 1.15 to 6.11]; P = .023). There was improved OS favoring the DNA damage response group (HR, 0.37 [95% CI, 0.14 to 0.97]; P = .044) on multivariable analysis. Univariate analysis of patients with ATM mutations had significantly higher rates of PSA50 response, PSA PFS, and OS. CONCLUSION: Outcomes on LuPSMA varied on the basis of mutational profile. Prospective studies to define the clinical activity of LuPSMA in predefined genomic subgroups are justified.