This study investigated the value of some clinicopathological parameters and 18 F-fluorodeoxyglucose-positron emission tomography/computed tomography (18FDG-PET/CT) indices, including textural features, to predict event-free survival (EFS) in estrogen receptor-positive/human epidermal growth factor receptor 2-negative (ER+/HER2-) locally advanced breast cancer (BC) patients. FDG-PET/CT indices and clinicopathological parameters were assessed before neoadjuvant chemotherapy (NAC). After completion of chemotherapy, all patients had breast surgery with axillary lymph node dissection, followed by radiation therapy and endocrine therapy for 5 years. EFS was estimated using the Kaplan-Meier method. A Cox proportional hazard regression model was used for multivariate analysis. One hundred forty-three consecutive patients with stage II–III ER+/HER2- BC and without distant metastases at baseline PET were included. High standardized uptake values (SUVs), were associated with shorter EFS (HR = 3.51, P < 0.01 for SUVmax; HR = 2.76, P = 0.02 for SUVmean; and HR = 4.40 P < 0.01 for SUVpeak). Metabolically active tumor volume (MATV, HR = 3.47, P < 0.01) and total lesion glycolysis (TLG, HR = 3.10, P < 0.01) were also predictive of EFS. Homogeneity was not predictive (HR = 2.27, P = 0.07) and entropy had weak prediction (HR = 2.89, P = 0.02). Among clinicopathological parameters, EFS was shorter in progesterone receptor (PR)-negative tumor (vs. PR-positive tumor; HR = 3.25, P < 0.01); histology was predictive of EFS (lobular vs. ductal invasive carcinoma; HR = 3.74, P = 0.01) but not tumor grade (grade 3 vs. grade 1–2; HR = 1.64, P = 0.32). Pathological complete response after NAC was not correlated to the risk of relapse. Three parameters remained significantly associated with EFS in multivariate analysis. MATV (HR = 1.01, P < 0.01), progesterone receptor expression (HR = 2.90, P = 0.03) and tumor histology (HR = 3.80, P = 0.02). Baseline PET parameters measured before neoadjuvant treatment have prognostic values in ER+/HER2- locally advanced breast cancer patients. After multivariate analysis, metabolically active tumor volume remains significant while textural analysis of PET images is not of added value. Considering histopathological parameters, our study shows that patients with PR-negative or lobular invasive tumor have poorer prognosis than patients with PR-positive or ductal carcinoma, respectively.

Purpose: Triple-negative breast cancer (TNBC) is a biologically and clinically heterogeneous disease, associated with poorer outcomes when compared with other subtypes of breast cancer. Neoadjuvant chemotherapy (NAC) is often given before surgery, and achieving a pathological complete response (pCR) has been associated with patient outcomes. There is thus strong clinical interest in the ability to accurately predict pCR status using baseline data. Materials and Methods: A cohort of 57 TNBC patients who underwent FDG-PET/CT before NAC was analyzed to develop a machine learning (ML) algorithm predictive of pCR. A total of 241 predictors were collected for each patient: 11 clinical features, 11 histopathological features, 13 genomic features, and 206 PET features, including 195 radiomic features. The optimization criterion was the area under the ROC curve (AUC). Event-free survival (EFS) was estimated using the Kaplan–Meier method. Results: The best ML algorithm reached an AUC of 0.82. The features with the highest weight in the algorithm were a mix of PET (including radiomics), histopathological, genomic, and clinical features, highlighting the importance of truly multimodal analysis. Patients with predicted pCR tended to have a longer EFS than patients with predicted non-pCR, even though this difference was not significant, probably due to the small sample size and few events observed (p = 0.09). Conclusions: This study suggests that ML applied to baseline multimodal data can help predict pCR status after NAC for TNBC patients and may identify correlations with long-term outcomes. Patients predicted as non-pCR may benefit from concomitant treatment with immunotherapy or dose intensification.

Background: Immune checkpoint inhibitors (ICI) are currently the first-line treatment for patients with metastatic melanoma. We investigated the value of positron emission tomography (PET) response criteria to assess the therapeutic response to first-line ICI in this clinical context and explore the potential contribution of total tumor metabolic volume (TMTV) analysis. Methods: We conducted a retrospective study in patients treated with first-line ICI for advanced or metastatic melanoma, with 18F-FDG PET/CT performed at baseline and 3 months after starting treatment. Patients’ metabolic response was classified according to PERCIST5 and imPERCIST 5 criteria. TMTV was recorded for each examination. Results: Twenty-nine patients were included. The median overall survival (OS) was 51.2 months (IQR 13.6—not reached), and the OS rate at 2 years was 58.6%. Patients classified as responders (complete and partial response) had a 90.9% 2-year OS rate versus 38.9% for non-responders (stable disease and progressive disease) (p = 0.03), for PERCIST5 and imPERCIST 5 criteria. The median change in metabolic volume was 9.8% (IQR −59–+140%). No significant correlation between OS and changes in TMTV was found. Conclusion: The evaluation of response to immunotherapy using metabolic imaging with PERCIST5 and imPERCIST5 was significantly associated with OS in patients with advanced or metastatic melanoma.