A distributed feature selection pipeline for survival analysis using radiomics in non-small cell lung cancer patients.

Predictive modelling of cancer outcomes using radiomics faces dimensionality problems and data limitations, as radiomics features often number in the hundreds, and multi-institutional data sharing is ()often unfeasible. Federated learning (FL) and feature selection (FS) techniques combined can help overcome these issues, as one provides the means of training models without exchanging sensitive data, while the other identifies the most informative features, reduces overfitting, and improves model interpretability. Our proposed FS pipeline based on FL principles targets data-driven radiomics FS in a multivariate survival study of non-small cell lung cancer patients. The pipeline was run across datasets from three institutions without patient-level data exchange. It includes two FS techniques, Correlation-based Feature Selection and LASSO regularization, and Cox Proportional-Hazard regression with Overall Survival as endpoint. Trained and validated on 828 patients overall, our pipeline yielded a radiomic signature comprising "intensity-based energy" and "mean discretised intensity". Validation resulted in a mean Harrell C-index of 0.59, showcasing fair efficacy in risk stratification. In conclusion, we suggest a distributed radiomics approach that incorporates preliminary feature selection to systematically decrease the feature set based on data-driven considerations. This aims to address dimensionality challenges beyond those associated with data constraints and interpretability concerns.

May we routinely spare hippocampal region in primary central nervous system lymphoma during whole brain radiotherapy?

PURPOSE: One of the main limiting factors of whole-brain radiation therapy (WBRT) for primary central nervous system lymphoma (PCNSL) is the impairment of neurocognitive functions (NCFs), which is mainly caused by radiation-induced injury to the hippocampus. With a view to preventing NCF impairment and personalizing treatment, we explored the feasibility of sparing the hippocampus during WBRT by correlating the sites of PCNSL lesions with the hippocampus. METHODS AND MATERIALS: Pre-treatment MR images from patients who underwent WBRT between 2010 and January 2020-and post-radiotherapy images in cases of relapse-were imported into the Varian Eclipse treatment-planning system and registered with the simulation CT. We constructed three 3-dimensional envelopes around the hippocampus at distances of 5, 10 and 15 mm and also contoured primary lesions and recurrences. RESULTS: We analyzed 43 patients with 66 primary lesions: 9/66 (13.6%) involved the hippocampus and 11/66 (16.7%) were located within 5 mm of it. Thirty-six lesions (54.5%) were situated more than 15 mm from the hippocampus, while 10/66 (15.2%) were between 5 and 15 mm from it. The most common location was in deep brain structures (31%). Thirty-five of the 66 lesions relapsed: in field in 14/35 (40%) and outfield in 21/35 (60%) in different sites. Globally, 16/35 recurrences (45.7%) were located in the hippocampus or within 5 mm of it. CONCLUSION: These data show that routinely sparing the hippocampus is not feasible. This approach could be considered in selected patients, when the lesion is more than 15 mm from the hippocampus.

Leptin-mediated meta-inflammation may provide survival benefit in patients receiving maintenance immunotherapy for extensive-stage small cell lung cancer (ES-SCLC).

BACKGROUND: Only few ES-SCLC patients experience long-term survival benefit by maintenance IT. Adipokines-induced metabolic meta-inflammation has been related to enhanced responsiveness to IT in obese patients; however, their prognostic role in SCLC is currently controversial. METHODS: Pre-treatment CT scan was used for determining distribution of abdominal adiposity, and blood samples were collected at fasting for measuring glycemia, insulin, ghrelin, leptin and adipokines (TNF-α, IFN-γ, IL-6 and MCP-1). Patients with known history of DM type II or metabolic syndrome with HOMA index > 2.5 were considered insulin resistant (IR). RESULTS: In ES-SCLC pts receiving maintenance IT, increased leptin concentration and higher leptin/visceral adipose tissue (VAT) ratio were significantly associated with prolonged PFS. By applying a hierarchical clustering algorithm, we identified a cluster of patients characterized by higher leptin values and lower pro-inflammatory cytokines (TNF-α, IFN-γ and IL-6) who experienced longer PFS (13.2 vs 8.05 months; HR: 0.42 [0.18-0.93] p = 0.02) and OS (18.04 vs 12.09 mo; HR: 0.53 [0.25-1.29] p = 0.07). CONCLUSIONS: Adipokines can play a crucial role to determining effectiveness of anti-cancer immunotherapy. The role of metabolic immune dysfunctions needs further pre-clinical validation and is currently investigated in the larger prospective cohort.

[Management of the patient with extensive stage microcytoma. The importance of collaboration between oncology and radiotherapy.] / Gestione del paziente con microcitoma a stadio esteso. L'importanza della collaborazione tra oncologia e radioterapia.

Small cell lung cancer (SCLC) represents one of the most complex challenges in the oncological field, with a very slow advancement in research, contrary to the rapid evolutionary of the disease. For nearly two years, the mainstay of treatment for extensive-stage disease (ES-SCLC) has been the combination of platinum-based chemotherapy and immunotherapy, following the approval of atezolizumab and subsequently durvalumab, based on a modest, but significant improvement in overall survival compared to chemotherapy alone. The poor prognosis after the failure of first-line treatment explains the need to maximize the duration and efficacy of up-front systemic therapies, in particular, the emerging role of radiotherapy, also in ES-SCLC. On 10 November 2022, a meeting concerning the integrated treatment of patients with ES-SCLC was held in Rome and was attended by 12 specialists in oncology and radiotherapy from various centers in Lazio, under the direction of Federico Cappuzzo, Emilio Bria and Sara Ramella. The aim of the meeting was to share their clinical experience and to provide a series of practical indications in order to support physicians in the correct integration between first-line chemo-immunotherapy and radiotherapy treatments in ES-SCLC.

Multidisciplinary management of difficult/aggressive growth-hormone pituitary neuro-endocrine tumors.

Growth Hormone-secreting adenomas exhibits variable biological behavior and heterogeneous natural history, ranging from small adenomas and mild disease, to invasive and aggressive neoplasms with more severe clinical picture. Patients not cured or controlled after neurosurgical and first-generation somatostatin receptor ligands (SRL) therapy could require multiple surgical, medical and/or radiation treatments to achieve disease control. To date, no clinical, laboratory, histopathological, or neuroradiological markers are able to define the aggressiveness or predict the disease prognosis in patients with acromegaly. Therefore, the management of these patients requires careful evaluation of laboratory assessments, diagnostic criteria, neuroradiology examinations, and neurosurgical approaches to choose an effective and patient-tailored medical therapy. A multidisciplinary approach is particularly useful in difficult/aggressive acromegaly to schedule multimodal treatment, which includes radiation therapy, chemotherapy with temozolomide and other, recent emerging treatments. Herein, we describe the role of the different members of the multidisciplinary team according to our personal experience; a flow-chart for the therapeutic approach of difficult/aggressive acromegaly patients is proposed.

Magnetic resonance imaging-derived parameters to predict response to regorafenib in recurrent glioblastoma.

PURPOSE: Regorafenib is a multikinase inhibitor, approved as a preferred regimen for recurrent glioblastoma (rGB). Although its effects on prolonging survival could seem modest, it is still unclear whether a subset of patients, potentially identifiable by imaging biomarkers, might experience a more substantial positive effect. Our aim was to evaluate the potential value of magnetic resonance imaging-derived parameters as non-invasive biomarkers to predict response to regorafenib in patients with rGB. METHODS: 20 patients with rGB underwent conventional and advanced MRI at diagnosis (before surgery), at recurrence and at first follow-up (3 months) during regorafenib. Maximum relative cerebral blood volume (rCBVmax) value, intra-tumoral susceptibility signals (ITSS), apparent diffusion coefficient (ADC) values, and contrast-enhancing tumor volumes were tested for correlation with response to treatment, progression-free survival (PFS), and overall survival (OS). Response at first follow-up was assessed according to Response Assessment in Neuro-Oncology (RANO) criteria. RESULTS: 8/20 patients showed stable disease at first follow-up. rCBVmax values of the primary glioblastoma (before surgery) significantly correlated to treatment response; specifically, patients with stable disease displayed higher rCBVmax compared to progressive disease (p = 0.04, 2-group t test). Moreover, patients with stable disease showed longer PFS (p = 0.02, 2-group t test) and OS (p = 0.04, 2-group t test). ITSS, ADC values, and contrast-enhancing tumor volumes showed no correlation with treatment response, PFS nor OS. CONCLUSION: Our results suggest that rCBVmax of the glioblastoma at diagnosis could serve as a non-invasive biomarker of treatment response to regorafenib in patients with rGB.

Prognostic Score in Radiotherapy Practice for Palliative Treatments (PROPHET) Study for Bone Metastases: An Investigation Into the Clinical Effect on Treatment Prescription.

Purpose: Bone metastases frequently occur during malignant disease. Palliative radiation therapy (PRT) is a crucial part of palliative care because it can relieve pain and improve patients' quality of life. Often, a clinician's survival estimation is too optimistic. Prognostic scores (PSs) can help clinicians tailor PRT indications to avoid over- or undertreatment. Although the PS is supposed to aid radiation oncologists (ROs) in palliative-care scenarios, it is unclear what type of support, and to what extent, could impact daily clinical practice. Methods and Materials: A national-based investigation of the prescriptive decisions on simulated clinical cases was performed in Italy. Nine clinical cases from real-world clinical practice were selected for this study. Each case description contained complete information regarding the parameters defining the prognosis class according to the PS (in particular, the Mizumoto Prognostic Score, a validated PS available in literature and already applied in some clinical trials). Each case description contained complete information regarding the parameters defining the prognosis class according to the PS. ROs were interviewed through questionnaires, each comprising the same 3 questions per clinical case, asking (1) the prescription after detailing the clinical case features but not the PS prognostic class definition; (2) whether the RO wanted to change the prescription once the PS prognostic class definition was revealed; and (3) in case of a change of the prescription, a new prescriptive option. Three RO categories were defined: dedicated to PRT (RO-d), nondedicated to PRT (RO-nd), and resident in training (IT). Interviewed ROs were distributed among different regions of the country. Results: Conversion rates, agreements, and prescription trends were investigated. The PS determined a statistically significant 11.12% of prescription conversion among ROs. The conversion was higher for the residents and significantly higher for worse prognostic scenario subgroups, respectively. The PS improved prescriptive agreement among ROs (particularly for worse-prognostic-scenario subgroups). Moreover, PS significantly increased standard prescriptive approaches (particularly for worse-clinical-case presentations). Conclusions: To the best of our knowledge, the PROPHET study is the first to directly evaluate the potential clinical consequences of the regular application of any PS. According to the Prophet study, a prognostic score should be integrated into the clinical practice of palliative radiation therapy for bone metastasis and training programs in radiation oncology.

Clinical Stage III NSCLC Patients Treated with Neoadjuvant Therapy and Surgery: The Prognostic Role of Nodal Characteristics.

BACKGROUND: The aim of this study is to analyze the prognostic factors in patients that underwent induction therapy and surgery for clinical stage III NSCLC. METHODS: Clinical and pathological characteristics of stage III NSCLC patients for N2 involvement that underwent neoadjuvant treatment (NAD) and surgery from 1/01/1998 to 31/12/2017 were collected and retrospectively analyzed. Tumor characteristics, yClinical, yPathological stage and lymph node characteristics were correlated to Overall Survival (OS). RESULTS: The analysis was conducted on 180 patients. Five-year OS (5YOS) was 50.9%. Univariable analysis results revealed old age (p = 0.003), clinical N2 post-NAD (p = 0.01), pneumonectomy (0.005), persistent pathological N2 (p = 0.039, HR 1.9, 95% CI 1.09−2.68) and adjuvant therapy absence (p = 0.049) as significant negative prognostic factors. Multivariable analysis confirmed pN0N1 (p = 0.02, HR 0.29, 95% CI 0.13−0.62) as a favorable independent prognostic factor and adjuvant therapy absence (p = 0.012, HR 2.61, 95% CI 1.23−5.50) as a negative prognostic factor. Patients with persistent N2 presented a 5YOS of 35.3% vs. 55.8% in pN0N1 patients. Regarding lymph node parameters, the lymph node ratio (NR) significantly correlated with OS: 5YOS of 67.6% in patients with NR < 50% vs. 29.5% in NR > 50% (p = 0.029). CONCLUSION: Clinical response aided the stratification of prognosis in patients that underwent multimodal treatment for stage III NSCLC. Adjuvant therapy seemed to be an important option in these patients, while node ratio was a strong prognosticator in patients with persistent nodal involvement.

Art and digital technologies to support resilience during the oncological journey: The Art4ART project.

Introduction: New digital technologies can become a tool for welcoming the patient through the artistic dimension. Cancer patients, in particular, need support that accompanies and supports them throughout their treatment. Materials and methods: The Art4ART project consist in the structural proposal to cancer patients of a web-based digital platform containing several forms of art as video-entertainments; a multimedia immersive room; an art-based welcoming of the patients with several original paintings; an environment with a peacefulness vertical garden; a reconceptualization of the chemotherapy-infusion seats. Data regarding patients' preference and choices will be stored and analysed also using artificial intelligence (AI) algorithm to measure and predict impact indicators regarding clinical outcomes (survival and toxicity), psychological indicators. Moreover, the same digital platform will contribute to a better organization of the activities. Discussion: Through the systematic acquisition of patient preferences and through integration with other clinical parameters, it will be possible to measure the clinical, psychological, organisational, and social impact of the newly implemented Art4ART project. The use of digital technology leads us to apply the reversal of viewpoint from therapeutic acts to patient-centred care.

Clinical and NGS predictors of response to regorafenib in recurrent glioblastoma.

Predictive factors for response to regorafenib in recurrent glioblastoma, IDH-wildtype, are scarcely recognized. The objective of this study was to identify molecular predictive factors for response to regorafenib using a clinically available platform. We analyzed a prospective cohort of 30 patients harboring recurrent glioblastoma, IDH-wildtype, and treated with regorafenib. Next-generation sequencing (NGS) analysis was performed on DNA extracted from paraffin-embedded tissues using a clinically available platform. Moreover, MGMT methylation and EGFRvIII expression analyses were performed. Six-month progression-free survival (PFS) was 30% and median overall survival (OS) was 7.5 months, in line with literature data. NGS analysis revealed a mutation in the EGFR pathway in 18% of cases and a mutation in the mitogen-activated protein-kinase (MAPK) pathway in 18% of cases. In the remaining cases, no mutations were detected. Patients carrying MAPK pathway mutation had a poor response to regorafenib treatment, with a significantly shorter PFS and a nonsignificantly shorter OS compared to EGFR-mutated patients (for PFS, 2.5 vs 4.5 months, p = 0.0061; for OS, 7 vs 9 months, p = 0.1076). Multivariate analysis confirmed that MAPK pathway mutations independently predicted a shorter PFS after regorafenib treatment (p = 0.0188). The negative prognostic role of MAPK pathway alteration was reinforced when we combined EGFR-mutated with EGFRvIII-positive cases. Recurrent glioblastoma tumors with an alteration in MAPK pathway could belong to the mesenchymal subtype and respond poorly to regorafenib treatment, while EGFR-altered cases have a better response to regorafenib. We thus provide a molecular selection criterion easy to implement in the clinical practice.

Assessment of Sexual Dysfunction in Cervical Cancer Patients after Different Treatment Modality: A Systematic Review.

Background and Objectives: Cervical cancer is a leading cause of mortality among women. Chemo-radiation followed by interventional radiotherapy (IRT) is the standard of care for stage IB-IVA FIGO. Several studies have shown that image-guided adaptive IRT resulted in excellent local and pelvic control, but it is associated with vaginal toxicity and intercourse problems. The purpose of this review is to evaluate the dysfunctions of the sexual sphere in patients with cervical cancer undergoing different cervix cancer treatments. Materials and Methods: We performed a comprehensive literature search using Pub med, Scopus and Cochrane to identify all the full articles evaluating the dysfunctions of the sexual sphere. ClinicalTrials.gov was searched for ongoing or recently completed trials, and PROSPERO was searched for ongoing or recently completed systematic reviews. Results: One thousand three hundred fifty-six women included in five studies published from 2016 to 2022 were analyzed. The median age was 50 years (range 46-56 years). The median follow-up was 12 months (range 0-60). Cervical cancer diagnosis and treatment (radiotherapy, chemotherapy and surgery) negatively affected sexual intercourse. Sexual symptoms such as fibrosis, strictures, decreased elasticity and depth and mucosal atrophy promote sexual dysfunction by causing frigidity, lack of lubrication, arousal, orgasm and libido and dyspareunia. Conclusions: Physical, physiological and social factors all contribute to the modification of the sexual sphere. Cervical cancer survivors who were irradiated have lower sexual and vaginal function than the normal population. Although there are cures for reducing discomfort, effective communication about sexual dysfunctions following treatment is essential.

A predictive nomogram for trismus after radiotherapy for head and neck cancer.

BACKGROUND: The aim of this study is to develop a prediction model for trismus (maximal interincisal distance equal to or less than 35 mm) based on a multivariable analysis of dosimetric and clinical factors. METHODS: The maximum inter-incisal opening (MIO) of hean and neck cancer (HNC) patients who underwent radiotherapy (RT) ± concurrent chemotherapy with radical intent, was prospectively measured prior to RT (baseline) and 6 months post-RT. The outcome variable is trismus. The potential risk factors (clinical and dosimetric) were first screened by univariate analysis and then by multivariate analysis. At the end of this process, we used the features identified as relevant, to fit a logistic regression model and calculate the probability of observed trismus during the 6-month follow-up after RT. RESULTS: One hundred and four consecutive patients were included (mean age 63 years, range 25-87), 68 males, 36 females. In the univariate analysis, the MIO at baseline, as an independent variable, and several Vdoses of different masticatory structures were found as significant. Additionally, using a bivariate model, a feature selection process was performed. Finally, we considered as best performing model the MIO at baseline and V42 at masseter muscles. The area under curve (AUC) of Receiver Operating Characteristic (ROC) curve value was 0.8255 (95% CI 0.74-0.9). The Hosmer and Lemeshow goodness-of-fit test, used to calibrate our model, was not-significant. CONCLUSIONS: A prediction nomogram was developed to assess trismus risk in planning process. An external validation of the model is required to apply it for current clinical use.

Immunotherapy and radiotherapy in melanoma: a multidisciplinary comprehensive review.

Melanoma is an extremely aggressive tumor and is considered to be an extremely immunogenic tumor because compared to other cancers it usually presents a well-expressed lymphoid infiltration. The aim of this paper is to perform a multidisciplinary comprehensive review of the evidence available about the combination of radiotherapy and immunotherapy for melanoma. Radiation, in fact, can increase tumor antigens visibility and promote priming of T cells but can also exert immunosuppressive action on tumor microenvironment. Combining radiotherapy with immunotherapy provides an opportunity to increase immunostimulatory potential of radiation. We therefore provide the latest clinical evidence about radiobiological rationale, radiotherapy techniques, timing, and role both in advanced and systemic disease (with a special focus on ocular melanoma and brain, liver, and bone metastases) with a particular attention also in geriatric patients. The combination of immunotherapy and radiotherapy seems to be a safe therapeutic option, supported by a clear biological rationale, even though the available data confirm that radiotherapy is employed more for metastatic than for non-metastatic disease. Such a combination shows promising results in terms of survival outcomes; however, further studies, hopefully prospective, are needed to confirm such evidence.

Personalised support of brain tumour patients during radiotherapy based on psychological profile and quality of life.

PURPOSE: Psychological distress in primary malignant brain tumour (PMBT) patients is associated with poorer outcomes. Radiotherapy (RT) often induces side effects that significantly influence patients' quality of life (QoL), with potential impact on survival. We evaluated distress, anxiety, depression, and QoL over time to identify patients with difficulties in these areas who required more intense psychological support. METHODS: Psychological questionnaires-Distress Thermometer (DT), Hospital Anxiety and Depression Scale (HADS), and Functional Assessment of Cancer Therapy (FACT-G and FACT-Br)-were completed at the beginning (T0), in the middle (T1), directly after RT (T2), and 3 months after RT (T3). We personalised the psychological support provided for each patient with a minimum of three sessions ('typical' schedule) and a maximum of eight sessions ('intensive' schedule), depending on the patients' psychological profiles, clinical evaluations, and requests. Patients' survival was evaluated in the glioblastoma multiforme (GBM) patients, with an explorative intent. RESULTS: Fifty-nine consecutive PMBT patients receiving post-operative RT were included. For patients who were reported as 'not distressed' at T0, no statistically significant changes were noted. In contrast, patients who were 'distressed' at T0 showed statistically significant improvements in DT, HADS, FACT-G, and FACT-Br scores over time. 'Not distressed' patients required less psychological sessions over the study duration than 'distressed' patients. Interestingly, 'not distressed' GBM patients survived longer than 'distressed' GBM patients. CONCLUSIONS: Increased psychological support improved distress, mood, and QoL for patients identified as 'distressed', whereas psychological well-being was maintained with typical psychological support in patients who were identified as being 'not distressed'. These results encourage a standardisation of psychological support for all RT patients.

Predicting Radiotherapy Impact on Late Bladder Toxicity in Prostate Cancer Patients: An Observational Study.

BACKGROUND AND PURPOSE: The aim of our study was to elaborate a suitable model on bladder late toxicity in prostate cancer (PC) patients treated by radiotherapy with volumetric technique. MATERIALS AND METHODS: PC patients treated between September 2010 and April 2017 were included in the analysis. An observational study was performed collecting late toxicity data of any grade, according to RTOG and CTCAE 4.03 scales, cumulative dose volumes histograms were exported for each patient. Vdose, the value of dose to a specific volume of organ at risk (OAR), impact was analyzed through the Mann-Whitney rank-sum test. Logistic regression was used as the final model. The model performance was estimated by taking 1000 samples with replacement from the original dataset and calculating the AUC average. In addition, the calibration plot (Hosmer-Lemeshow goodness-of-fit test) was used to evaluate the performance of internal validation. RStudio Software version 3.3.1 and an in house developed software package "Moddicom" were used. RESULTS: Data from 175 patients were collected. The median follow-up was 39 months (min-max 3.00-113.00). We performed Mann-Whitney rank-sum test with continuity correction in the subset of patients with late bladder toxicity grade ≥ 2: a statistically significant p-value with a Vdose of 51.43 Gy by applying a logistic regression model (coefficient 4.3, p value 0.025) for the prediction of the development of late G ≥ 2 GU toxicity was observed. The performance for the model's internal validation was evaluated, with an AUC equal to 0.626. Accuracy was estimated through the elaboration of a calibration plot. CONCLUSIONS: Our preliminary results could help to optimize treatment planning procedures and customize treatments.

Radiosurgery or Fractionated Stereotactic Radiotherapy plus Whole-brain Radioherapy in Brain Oligometastases: A Long-term Analysis.

AIM: To analyze the outcome of patients with brain oligometastases treated by radiosurgery (SRS) or fractionated stereotactic radiotherapy (FSRT) after whole-brain radiotherapy (WBRT). PATIENTS AND METHODS: Overall survival (OS) and local control (LC) were evaluated in patients (patients) with 1-2 brain metastases. RESULTS: Forty-seven patients were selected. They were submitted to WBRT (median dose=3,750 cGy) followed by SRS (17 patients; median dose=1,500 cGy) or FSRT (30 patients; median dose=2,000 cGy). Median follow-up was 102 months (range=17-151); the median survival was 22 months for the SRS group and 16 months for the FSRT group. One-year and 5-year survival was 56% and 16%, respectively, in SRT and 62.1% and 3%, respectively, in FSRT. Neither treatment proved to significantly impact OS (p=0.4). The 1-year LC rates were 80% and 61.1% in the two groups, respectively (p=0.15). CONCLUSION: SRS or FSRT after WBRT could offer the same outcomes in patients with brain oligometasteses. Further investigation is warranted to confirm these data and define the optimal stereotactic modality.