Explore the vast range of titles available.

Representing patterns as labeled graphs is becoming increasingly common in the broad field of computational intelligence. Accordingly, a wide repertoire of pattern recognition tools, such as classifiers and knowledge discovery procedures, are nowadays available and tested for various datasets of labeled graphs. However, the design of effective learning procedures operating in the space of labeled graphs is still a challenging problem, especially from the computational complexity viewpoint. In this paper, we present a major improvement of a general-purpose classifier for graphs, which is conceived on an interplay between dissimilarity representation, clustering, information-theoretic techniques, and evolutionary optimization algorithms. The improvement focuses on a specific key subroutine devised to compress the input data. We prove different theorems which are fundamental to the setting of the parameters controlling such a compression operation. We demonstrate the effectiveness of the resulting classifier by benchmarking the developed variants on well-known datasets of labeled graphs, considering as distinct performance indicators the classification accuracy, computing time, and parsimony in terms of structural complexity of the synthesized classification models. The results show state-of-the-art standards in terms of test set accuracy and a considerable speed-up for what concerns the computing time.

A recurrent neural network (RNN) is a universal approximator of dynamical systems, whose performance often depends on sensitive hyperparameters. Tuning them properly may be difficult and, typically, based on a trial-and-error approach. In this work, we adopt a graph-based framework to interpret and characterize internal dynamics of a class of RNNs called echo state networks (ESNs). We design principled unsupervised methods to derive hyperparameters configurations yielding maximal ESN performance, expressed in terms of prediction error and memory capacity. In particular, we propose to model time series generated by each neuron activations with a horizontal visibility graph, whose topological properties have been shown to be related to the underlying system dynamics. Successively, horizontal visibility graphs associated with all neurons become layers of a larger structure called a multiplex. We show that topological properties of such a multiplex reflect important features of ESN dynamics that can be used to guide the tuning of its hyperparamers. Results obtained on several benchmarks and a real-world dataset of telephone call data records show the effectiveness of the proposed methods.

Optimal therapy following breast-conserving surgery in older adults with low-risk, early-stage breast cancer remains uncertain. The EUROPA trial aims to compare the effects of radiotherapy and endocrine therapy as single-modality treatments on health-related quality of life (HRQOL) and ipsilateral breast tumour recurrence (IBTR) outcomes in this population. This non-inferiority, phase 3, randomised study was conducted at 18 academic hospitals across Italy (17 centres) and Slovenia (one centre). Eligible patients were women aged 70 years or older with histologically confirmed, stage I, luminal A-like breast cancer, who had undergone breast-conserving surgery and had an Eastern Cooperative Oncology Group performance status of 0 or 1. Patients were randomly assigned (1:1) to receive single-modality endocrine therapy or radiotherapy. Endocrine therapy consisted of daily oral aromatase inhibitors or tamoxifen, for a total planned duration of 5–10 years as per clinical discretion, while radiotherapy was administered as either whole breast or partial breast irradiation, delivered in 5–15 fractions. Randomisation was stratified by health status according to the Geriatric 8 (G8) screening tool and by age, with allocation concealed and no blinding. The co-primary endpoints were the change in HRQOL, assessed by the global health status (GHS) scale of the European Organisation for Research and Treatment of Cancer Quality of Life Questionnaire 30-item core module at 24 months, and 5-year IBTR rates (not reported here). This preplanned interim analysis was performed once at least 152 patients completed the 24-month GHS HRQOL assessment. The safety population comprised patients who received the study intervention at least once after randomisation. The study is registered with ClinicalTrials.gov, NCT04134598, and is ongoing and actively recruiting. Between March 4, 2021, and June 14, 2024, 731 women were randomly assigned to receive radiotherapy (n=365) or endocrine therapy (n=366). This analysis included 104 patients in the radiotherapy group and 103 in the endocrine therapy group, with a median follow-up of 23·9 months (IQR 22·9–24·2). Patients were predominantly White (204 [99%] of 207) and the median age was 75·0 years (IQR 73·0–80·0) in the radiotherapy group and 74·0 years (72·0–80·0) in the endocrine therapy group. 86 patients in the radiotherapy group and 75 in the endocrine therapy group completed the 24-month HRQOL assessment. The mean baseline GHS score was 71·9 (SD 19·1) in the radiotherapy group and 75·5 (19·3) in the endocrine therapy group. At 24 months, the age-adjusted, G8 score-adjusted mean change from baseline in GHS was –3·40 (95% CI –7·82 to 1·03; p=0·13) in the radiotherapy group and –9·79 (–14·45 to –5·13; p<0·0001) in the endocrine therapy group, with an adjusted mean difference of 6·39 (0·14 to 12·65; p=0·045) favouring radiotherapy. Treatment-related adverse events were less frequent in the radiotherapy group (65 [67%] of 97 patients) compared with the endocrine therapy group (76 [85%] of 89). The most common grade 3–4 adverse events were arthralgia (six [7%] of 89 in the endocrine therapy group vs 0 of 97 in the radiotherapy group), pelvic organ prolapse (three [3%] vs 0), fatigue, hot flashes, myalgia, bone pain, and fractures (two [2%] vs 0 for each). Serious adverse events were reported in 15 (15%) patients in the radiotherapy group and 13 (15%) in the endocrine therapy group. There were no treatment-related deaths in either group. Endocrine therapy was associated with a greater reduction in HRQOL, as measured by GHS, compared with radiotherapy at 24 months. While these interim results suggest radiotherapy might better preserve HRQOL in older women with low-risk early breast cancer, further data on disease control outcomes and final patient accrual are needed to draw definitive conclusions. Fondazione Radioterapia Oncologica.

Novel systemic therapies for breast cancer are being rapidly implemented into clinical practice. These drugs often have different mechanisms of action and side-effect profiles compared with traditional chemotherapy. Underpinning practice-changing clinical trials focused on the systemic therapies under investigation, thus there are sparse data available on radiotherapy. Integration of these new systemic therapies with radiotherapy is therefore challenging. Given this rapid, transformative change in breast cancer multimodal management, the multidisciplinary community must unite to ensure optimal, safe, and equitable treatment for all patients. The aim of this collaborative group of radiation, clinical, and medical oncologists, basic and translational scientists, and patient advocates was to: scope, synthesise, and summarise the literature on integrating novel drugs with radiotherapy for breast cancer; produce consensus statements on drug–radiotherapy integration, where specific evidence is lacking; and make best-practice recommendations for recording of radiotherapy data and quality assurance for subsequent studies testing novel drugs.

Recent advances in computing capability allowed the development of sophisticated predictive models to assess complex relationships within observational data, described as Artificial Intelligence. Medicine is one of the several fields of application and Radiation oncology could benefit from these approaches, particularly in patients’ medical records, imaging, baseline pathology, planning or instrumental data. Artificial Intelligence systems could simplify many steps of the complex workflow of radiotherapy such as segmentation, planning or delivery. However, Artificial Intelligence could be considered as a “black box” in which human operator may only understand input and output predictions and its application to the clinical practice remains a challenge. The low transparency of the overall system is questionable from manifold points of view (ethical included). Given the complexity of this issue, we collected the basic definitions to help the clinician to understand current literature, and overviewed experiences regarding implementation of AI within radiotherapy clinical workflow, aiming to describe this field from the clinician perspective.

Recent findings from literature evidenced that metastatic prostate cancer often shows heterogeneous response to therapy, with persistent sensibility to systemic treatments after biochemical, clinical, or radiographic progression. This highlights the advantage of integrated approaches in which local ablative treatments (e.g., stereotactic body radiation therapy) could prolong clinical benefit of systemic therapies beyond oligo-progression. Of course, development of predictive biomarker could be helpful in order to select patients who could much benefit from this treatment strategy. Circulating tumor cell detection and analysis could also have a crucial role in this field. A joint effort of two prospective ongoing trials (ARTO, clinical.gov identifier NCT03449719 and PRIMERA, clinical.gov identifier NCT04188275) might help to improve criteria to select patients in whom a local ablative approach might confer significant benefit. In this commentary, we summarized recent data from literature to support this thesis.

Oligometastatic disease represents the proximal end of a metastatic spectrum. Metastasis-directed therapy (MDT) is increasingly used to treat oligometastatic disease despite the absence of level 1 evidence. We amalgamated individual patient data across trials to evaluate the effectiveness of MDT for oligometastatic prostate cancer. We conducted a systematic review and individual patient data meta-analysis. We systematically searched Embase, PubMed, CENTRAL, MEDLINE, and ClinicalTrials.gov to identify randomised trials of MDT enrolling patients with oligometastatic prostate cancer. Inclusion criteria were published randomised prospective trials enrolling patients with oligometastatic (up to five metastases) prostate cancer, in which investigators recorded sufficient data to evaluate progression-free survival and overall survival. This systematic review was conducted from database creation to Nov 3, 2023, and was updated on May 4, 2025. Data appraisal was conducted using Covidence with two investigators (CT and ADS) performing independent screens. Studies were evaluated using the Cochrane Collaboration's risk-of-bias assessment (version 2.0). Individual patient data were provided by investigators. Coprimary endpoints were progression-free survival and overall survival. Secondary endpoints were radiographic progression-free survival and castration resistance-free survival. The primary analysis was conducted in the subset of studies in which patients were randomly assigned to MDT plus standard of care (SOC) versus SOC. The primary analysis included a trial-level analysis using a random effects model and a patient-level analysis stratifying by trial. This meta-analysis is registered with PROSPERO (CRD42023479078). Of 2975 studies identified for screening, seven phase 2 studies randomly assigning 574 men were included. Six trials randomly assigning 472 patients to MDT plus SOC (n=248) versus SOC (n=224) were used to evaluate MDT and had a median follow-up time of 40·7 months (IQR 25·6–53·7). MDT was associated with improved progression-free survival (trial-level hazard ratio [HR] 0·44, [95% CI 0·35–0·56], p<0·0001; patient-level HR 0·45 [0·35–0·57], p<0·0001), radiographic progression-free survival (trial-level HR 0·60 [0·42–0·85], p=0·0039; patient-level HR 0·59 [0·46–0·76], p<0·0001), and castration resistance-free survival (trial-level HR 0·58 [95% CI 0·37–0·92], p=0·019; patient-level HR 0·58 [95% CI 0·37–0·91], p=0·017). The association between MDT and overall survival showed an HR of 0·63 (95% CI 0·39–1·00, p=0·051) in trial-level analyses and 0·64 (95% CI 0·40–1·01, p=0·057) in patient-level analyses. WOLVERINE showed a benefit with MDT for oligometastatic prostate cancer in progression-free survival, radiological progression-free survival, and castration resistance-free survival. Overall survival benefit was not significant and further research is needed. Philanthropic gift and National Cancer Institute.

Background HER2-targeting agents have dramatically changed the therapeutic landscape of HER2+ advanced breast cancer (ABC). Within a short time frame, the rapid introduction of new therapeutics has led to the approval of pertuzumab combined with trastuzumab and a taxane in first-line, and trastuzumab emtansine (T-DM1) in second-line. Thereby, evidence of T-DM1 efficacy following trastuzumab/pertuzumab combination is limited, with data from some retrospective reports suggesting lower activity. The purpose of the present study is to investigate T-DM1 efficacy in pertuzumab-pretreated and pertuzumab naïve HER2 positive ABC patients. We also aimed to provide evidence on the exposure to different drugs sequences including pertuzumab and T-DM1 in HER2 positive cell lines. Methods The biology of HER2 was investigated in vitro through sequential exposure of resistant HER2 + breast cancer cell lines to trastuzumab, pertuzumab, and their combination. In vitro experiments were paralleled by the analysis of data from 555 HER2 + ABC patients treated with T-DM1 and evaluation of T-DM1 efficacy in the 371 patients who received it in second line. Survival estimates were graphically displayed in Kaplan Meier curves, compared by log rank test and, when possibile, confirmed in multivariate models. Results We herein show evidence of lower activity of T-DM1 in two HER2+ breast cancer cell lines resistant to trastuzumab+pertuzumab, as compared to trastuzumab-resistant cells. Lower T-DM1 efficacy was associated with a marked reduction of HER2 expression on the cell membrane and its nuclear translocation. HER2 downregulation at the membrane level was confirmed in biopsies of four trastuzumab/pertuzumab-pretreated patients. Among the 371 patients treated with second-line T-DM1, median overall survival (mOS) from diagnosis of advanced disease and median progression-free survival to second-line treatment (mPFS2) were 52 and 6 months in 177 patients who received trastuzumab/pertuzumab in first-line, and 74 and 10 months in 194 pertuzumab-naïve patients ( p  = 0.0006 and 0.03 for OS and PFS2, respectively). Conclusions Our data support the hypothesis that the addition of pertuzumab to trastuzumab reduces the amount of available plasma membrane HER2 receptor, limiting the binding of T-DM1 in cancer cells. This may help interpret the less favorable outcomes of second-line T-DM1 in trastuzumab/pertuzumab pre-treated patients compared to their pertuzumab-naïve counterpart.

Background To report on the discriminative ability of a simulation Computed Tomography (CT)-based radiomics signature for predicting response to treatment in patients undergoing neoadjuvant chemo-radiation for locally advanced adenocarcinoma of the rectum. Methods Consecutive patients treated at the Universities of Tübingen (from 1/1/07 to 31/12/10, explorative cohort) and Florence (from 1/1/11 to 31/12/17, external validation cohort) were considered in our dual-institution, retrospective analysis. Long-course neoadjuvant chemo-radiation was performed according to local policy. On simulation CT, the rectal Gross Tumor Volume was manually segmented. A feature selection process was performed yielding mineable data through an in-house developed software (written in Python 3.6). Model selection and hyper-parametrization of the model was performed using a fivefold cross validation approach. The main outcome measure of the study was the rate of pathologic good response, defined as the sum of Tumor regression grade (TRG) 3 and 4 according to Dworak’s classification. Results Two-hundred and one patients were included in our analysis, of whom 126 (62.7%) and 75 (37.3%) cases represented the explorative and external validation cohorts, respectively. Patient characteristics were well balanced between the two groups. A similar rate of good response to neoadjuvant treatment was obtained in in both cohorts (46% and 54.7%, respectively; p  = 0.247). A total of 1150 features were extracted from the planning scans. A 5-metafeature complex consisting of Principal component analysis (PCA)-clusters (whose main components are LHL Grey-Level-Size-Zone: Large Zone Emphasis, Elongation, HHH Intensity Histogram Mean, HLL Run-Length: Run Level Variance and HHH Co-occurence: Cluster Tendency) in combination with 5-nearest neighbour model was the most robust signature. When applied to the explorative cohort, the prediction of good response corresponded to an average Area under the curve (AUC) value of 0.65 ± 0.02. When the model was tested on the external validation cohort, it ensured a similar accuracy, with a slightly lower predictive ability (AUC of 0.63). Conclusions Radiomics-based, data-mining from simulation CT scans was shown to be feasible and reproducible in two independent cohorts, yielding fair accuracy in the prediction of response to neoadjuvant chemo-radiation.

Although systemic therapy represents the standard of care for polymetastatic kidney cancer, stereotactic body radiation therapy (SBRT) may play a relevant role in the oligometastatic setting. We conducted a multicenter study including oligometastatic kidney cancer treated with SBRT. We retrospectively analyzed 207 patients who underwent 245 SBRT treatments on 385 lesions, including 165 (42.9%) oligorecurrent (OR) and 220 (57.1%) oligoprogressive (OP) lesions. Most common sites were lung (30.9%) for OR group, and bone (32.7%) for OP group. Among 78 (31.8%) patients receiving concomitant systemic therapy, sunitinib (61.5%) and pazopanib (15.4%) were the most common for OR patients, while sunitinib (49.2%) and nivolumab (20.0%) for OP patients. End points were local control (LC), progression free survival (PFS), overall survival (OS), time to next systemic therapy (TTNS) and toxicity. Median follow-up was 18.6 months. 1, 2 and 3-year LC rates were 89.4%, 80.1% and 76.6% in OR patients, and 82.7%, 76.9% and 64.3% in those with OP, respectively. LC for OP group was influenced by clear cell histology (p = 0.000), total number of lesions (p = 0.004), systemic therapy during SBRT (p = 0.012), and SBRT dose (p = 0.012). Median PFS was 37.9 months. 1, 2- and 3-year OS was 92.7%, 86.4% and 81.8%, respectively. Median TTNS was 15.8 months for OR patients, and 13.9 months for OP patients. No grade 3 or higher toxicities were reported for both groups. SBRT may be considered an effective safe option in the multidisciplinary management of both OR and OP metastases from kidney cancer.