So far, baseline Dynamic Contrast-Enhanced Magnetic Resonance Imaging (DCE-MRI) has played a key role for the application of sophisticated artificial intelligence-based models using Convolutional Neural Networks (CNNs) to extract quantitative imaging information as earlier indicators of pathological Complete Response (pCR) achievement in breast cancer patients treated with neoadjuvant chemotherapy (NAC). However, these models did not exploit the DCE-MRI exams in their full geometry as 3D volume but analysed only few individual slices independently, thus neglecting the depth information. This study aimed to develop an explainable 3D CNN, which fulfilled the task of pCR prediction before the beginning of NAC, by leveraging the 3D information of post-contrast baseline breast DCE-MRI exams. Specifically, for each patient, the network took in input a 3D sequence containing the tumor region, which was previously automatically identified along the DCE-MRI exam. A visual explanation of the decision-making process of the network was also provided. To the best of our knowledge, our proposal is competitive than other models in the field, which made use of imaging data alone, reaching a median AUC value of 81.8%, 95%CI [75.3%; 88.3%], a median accuracy value of 78.7%, 95%CI [74.8%; 82.5%], a median sensitivity value of 69.8%, 95%CI [59.6%; 79.9%] and a median specificity value of 83.3%, 95%CI [82.6%; 84.0%], respectively. The median and CIs were computed according to a 10-fold cross-validation scheme for 5 rounds. Finally, this proposal holds high potential to support clinicians on non-invasively early pursuing or changing patient-centric NAC pathways.

A 71-year-old male ex-smoker presented in October 2021 to our department with a brain and bone metastatic adenocarcinoma NSCLC. PDL1, ROS, EGFR, and ALK were negative. He underwent stereotactic radiotherapy for brain metastases. In November 2021, he started a chemotherapy (CHT) regimen with cisplatin (75 mg/m² every 21 days) and pemetrexed (500 mg/m² every 21 days), and ICI with Atezolizumab (1200 mg every 21 days). In July 2022, RT to the lung tumor and mediastinal nodal was performed with a total dose of 45 Gy in 15 fractions. He continued with immunotherapy until December 2022, when a grade 3–4 toxicity from immunotherapy was observed (hypothyroidism, psoriasis, and cystitis). He achieved a complete clinical response to the therapy. To date, the patient is alive, with a complete metabolic response, without treatment at 37 months from diagnosis.

Phosphorylated ACC (pACC), a downstream effector of the LKB1/AMPK pathway, may support tumor bioenergetics and exert a tumor-promoting role in glioblastoma (GBM). In the randomized REGOMA trial, pACC expression was associated with improved overall survival (OS) in GBM patients treated with regorafenib, but its validity in large cohorts is unclear. This study aimed to characterize pACC and phosphorylated AMPK (pAMPK) expression in a real-world GBM cohort and to assess their prognostic and predictive value in patients receiving second-line regorafenib or fotemustine/lomustine. In this retrospective, multicenter translational study, pACC and pAMPK were assessed by immunohistochemistry on FFPE tumor sections from 174 IDH-wild-type GBM patients treated with regorafenib (n = 84) or fotemustine/lomustine (n = 90). Staining was performed with a validated anti-pACC monoclonal antibody and quantified by digital pathology. Survival analyses included univariable and multivariable Cox proportional hazards models, with interaction testing. pACC and pAMPK were expressed in 85.6% and 95.4% of samples, respectively, with heterogeneous spatial patterns. Neither marker was significantly associated with OS in the univariable analyses, and neither retained independent prognostic value in multivariable analysis. Regorafenib was associated with significantly longer OS than alkylating agents (10.4 vs. 6.3 months; p = 0.0021). However, the treatment-by-pACC interaction test was not statistically significant (adjusted p = 0.610), providing no formal evidence of a differential treatment effect by pACC status. Although pACC-positive expression was enriched among patients experiencing longer overall survival under regorafenib, formal treatment-by-biomarker interaction was non-significant. These exploratory findings indicate that pACC is not an established predictive biomarker and warrant prospectively powered evaluation.

A 71-year-old male ex-smoker presented in October 2021 to our department with a brain and bone metastatic adenocarcinoma oncogene-negative, PDL1-negative NSCLC. He underwent stereotactic radiotherapy for brain metastases, and then chemotherapy with cisplatin and gemcitabine was administered, followed by immunotherapy with Nivolumab. In July 2022, RT to lung tumor and mediastinal nodal was performed with a total dose of 45Gy in 15 fractions. He continued with immunotherapy until December 2022, when a grade 3-4 toxicity from immunotherapy was ob-served (hypothyroidism, psoriasis, cystitis). He achieved a complete clinical response to the therapy. To date, the patient is alive, with a complete metabolic response, without treatment at 35 months from diagnosis.

Background/Objectives: Hypofractionated radiation therapy (Hypo-RT) schedules may offer radiobiological, patient convenience, and healthcare resource advantages over standard fractionated radiation therapy (S-RT) for glioblastoma (GBM). Additionally, simulated integrated boost (SIB) Hypo-RT is proven to be an effective and safe treatment. We report on our experience regarding progression-free survival (PFS), overall survival (OS), and RT-related toxicities in GBM patients treated with Hypo-RT and S-RT. Methods: Patients with IDH-wildtype GBM received either Hypo-RT (40.05-52.5 Gy/15 fractions) or S-RT (60-70 Gy/30 fractions). Volumetric modulated arc therapy was performed for all patients. Concomitant temozolomide (75 mg/m²/day) and adjuvant chemotherapy (TMZ 150-200 mg/m² for 5 days every 28 days) were administered. OS and PFS were estimated using the Kaplan-Meier method. Results: Ninety-five patients were treated (Hypo-RT: 52, S-RT: 43). With a median follow-up of 25 months (range 9-63), the median age was 65 and 54 years for the Hypo-RT and S-RT groups, respectively. All patients tolerated the treatment well; no significant adverse effects were observed in either group. No acute or late neurological side effects of grade ≥ 2 were reported during RT. Grade 3-4 hematologic toxicity occurred in five cases, all of which interrupted concomitant TMZ (all occurring in the S-RT arm). The time to progression for the S-RT and Hypo-RT groups was 13.7 and 11.1 months, respectively (p=0.243). Regarding OS, the S-RT group had a median OS of 28.8 months compared to 17.5 months in the Hypo-RT group (p=0.007). Conclusions: Although further investigations are ongoing, a statistically significant difference exists in OS between Hypo-RT and S-RT. Hypo-RT could potentially become the standard of care not only for elderly patients but also for those with poor prognosis. Additional investigation with more data is necessary in this context to determine the best standard approach.