Artificial Intelligence in Breast Cancer: A Systematic Review on PET Imaging Clinical Applications.

BACKGROUND: 18F-FDG PET/CT imaging represents the most important functional imaging method in oncology. European Society of Medical Oncology and the National Comprehensive Cancer Network guidelines defined a crucial role of 18F-FDG PET/CT imaging for local/locally advanced breast cancer. The application of artificial intelligence on PET images might potentially contributes in the field of precision medicine. OBJECTIVE: This review aims to summarize the clinical indications and limitations of PET imaging for comprehensive artificial intelligence in relation to breast cancer subtype, hormone receptor status, proliferation rate, and lymphonodal (LN)/distant metastatic spread, based on recent literature. METHODS: A literature search of the Pubmed/Scopus/Google Scholar/Cochrane/EMBASE databases was carried out, searching for articles on the use of artificial intelligence and PET in breast tumors. The search was updated from January 2010 to October 2021 and was limited to original articles published in English and about humans. A combination of the search terms "artificial intelligence", "breast cancer", "breast tumor", "PET", "Positron emission tomography", "PET/CT", "PET/MRI", "radiomic"," texture analysis", "machine learning", "deep learning" was used. RESULTS: Twenty-three articles were selected following the PRISMA criteria from 139 records obtained from the Pubmed/Scopus/Google Scholar/Cochrane/EMBASE databases according to our research strategy. The QUADAS of 30 full-text articles assessed reported seven articles that were excluded for not being relevant to population and outcomes and/or for lower level of evidence. The majority of papers were at low risk of bias and applicability. The articles were divided per topic, such as the value of PET in the staging and re-staging of breast cancer patients, including new radiopharmaceuticals and simultaneous PET/MRI. CONCLUSION: Despite the current role of AI in this field remains still undefined, several applications for PET/CT imaging are under development, with some preliminary interesting results particularly focused on the staging phase that might be clinically translated after further validation studies.

Event-free survival after 68 Ga-PSMA-11 PET/CT in recurrent hormone-sensitive prostate cancer (HSPC) patients eligible for salvage therapy.

BACKGROUND/AIM: Prostate-specific-membrane-antigen/positron emission tomography (PSMA-PET) detects with high accuracy disease-recurrence, leading to changes in the management of biochemically-recurrent (BCR) prostate cancer (PCa). However, data regarding the oncological outcomes of patients who performed PSMA-PET are needed. The aim of this study was to evaluate the incidence of clinically relevant events during follow-up in patients who performed PSMA-PET for BCR after radical treatment. MATERIALS AND METHODS: This analysis included consecutive, hormone-sensitive, hormone-free, recurrent PCa patients (HSPC) enrolled through a prospective study. All patients were eligible for salvage therapy, having at least 24 months of follow-up after PSMA-PET. The primary endpoint was the Event-Free Survival (EFS), defined as the time between the PSMA-PET and the date of event/last follow-up. The Kaplan-Meier method was used to estimate the EFS curves. EFS was also investigated by Cox proportional hazards regression. Events were defined as death, radiological progression, or PSA recurrence after therapy. RESULTS: One-hundred and seventy-six (n = 176) patients were analyzed (median PSA 0.62 [IQR: 0.43-1.00] ng/mL; median follow-up of 35.4 [IQR: 26.5-40.3] months). The EFS was 78.8% at 1 year, 65.2% (2 years), and 52.2% (3 years). Patients experiencing events during study follow-up had a significantly higher median PSA (0.81 [IQR: 0.53-1.28] vs 0.51 [IQR: 0.36-0.80] ng/mL) and a lower PSA doubling time (PSAdt) (5.4 [IQR: 3.7-11.6] vs 12.7 [IQR: 6.6-24.3] months) (p < 0.001) compared to event-free patients. The Kaplan-Meier curves showed that PSA > 0.5 ng/mL, PSAdt ≤ 6 months, and a positive PSMA-PET result were associated with a higher event rate (p < 0.01). No significant differences of event rates were observed in patients who received changes in therapy management after PSMA-PET vs. patients who did not receive therapy changes. Finally, PSA > 0.5 ng/mL and PSAdt ≤ 6 months were statistically significant event-predictors in multivariate model (p < 0.001). CONCLUSION: Low PSA and long PSAdt were significant predictors of longer EFS. A lower incidence of events was observed in patients having negative PSMA-PET, since longer EFS was significantly more probable in case of a negative scan.