Patient- and clinician-based evaluation of large language models for patient education in prostate cancer radiotherapy.

Background: This study aims to evaluate the capabilities and limitations of large language models (LLMs) for providing patient education for men undergoing radiotherapy for localized prostate cancer, incorporating assessments from both clinicians and patients.

Methods: Six questions about definitive radiotherapy for prostate cancer were designed based on common patient inquiries. These questions were presented to different LLMs [ChatGPT‑4, ChatGPT-4o (both OpenAI Inc.

Implant-based reconstruction and adjuvant radiotherapy in breast cancer patients-current status and DEGRO recommendations.

Purpose: The aim of this review is to give an overview of the results of prospective and retrospective studies using allogenic reconstruction and postmastectomy radiotherapy (PMRT) in breast cancer and to make recommendations regarding this interdisciplinary approach.

Materials And Methods: A PubMed search was conducted to extract relevant articles from 2000 to 2024. The search was performed using the following terms: (breast cancer) AND (reconstruction OR implant OR expander) AND (radiotherapy OR radiation).

Characterisation of GPR17-expressing oligodendrocyte precursors in human ischaemic lesions and correlation with reactive glial responses.

White matter damage and subsequent demyelination significantly contribute to long-term functional impairment after ischaemic stroke. Identifying novel pharmacological targets to restore myelin integrity by promoting the maturation of oligodendrocyte precursor cells (OPCs) into new myelinating oligodendrocytes may open new perspectives for ischaemic stroke treatment. In this respect, previous studies highlighted the role of the G protein-coupled membrane receptor 17 (GPR17) as a key regulator of OPC differentiation in experimental models of brain injury, including ischaemic stroke.

Personalized deep learning auto-segmentation models for adaptive fractionated magnetic resonance-guided radiation therapy of the abdomen.

Background: Manual contour corrections during fractionated magnetic resonance (MR)-guided radiotherapy (MRgRT) are time-consuming. Conventional population models for deep learning auto-segmentation might be suboptimal for MRgRT at MR-Linacs since they do not incorporate manual segmentation from treatment planning and previous fractions.

Purpose: In this work, we investigate patient-specific (PS) auto-segmentation methods leveraging expert-segmented planning and prior fraction MR images (MRIs) to improve auto-segmentation on consecutive treatment days.

MRgRT real-time target localization using foundation models for contour point tracking and promptable mask refinement.

. This study aimed to evaluate two real-time target tracking approaches for magnetic resonance imaging (MRI) guided radiotherapy (MRgRT) based on foundation artificial intelligence models..

Surface-based deep inspiration breath-hold radiotherapy in left-sided breast cancer: final results from the SAVE-HEART study.

Background: Adjuvant radiotherapy (RT) plays an essential role in the management of early breast cancer (BC), but can lead to cardiovascular and lung toxicities. RT in deep inspiration breath hold (DIBH) often allows better protection of organs at risk. This prospective study compares surface-guided DIBH with free breathing (FB) in patients with left-sided BC, by evaluating individual cardiovascular risks and treatment plan dosimetry.

Prompt gamma emission prediction using a long short-term memory network.

: To present a long short-term memory (LSTM)-based prompt gamma (PG) emission prediction method for proton therapy.: Computed tomography (CT) scans of 33 patients with a prostate tumor were included in the dataset. A set of 10histories proton pencil beam (PB)s was generated for Monte Carlo (MC) dose and PG simulation.

Patient-Specific Deep Learning Tracking Framework for Real-Time 2D Target Localization in Magnetic Resonance Imaging-Guided Radiation Therapy.

Purpose: We propose a tumor tracking framework for 2D cine magnetic resonance imaging (MRI) based on a pair of deep learning (DL) models relying on patient-specific (PS) training.

Methods And Materials: The chosen DL models are: (1) an image registration transformer and (2) an auto-segmentation convolutional neural network (CNN). We collected over 1,400,000 cine MRI frames from 219 patients treated on a 0.

Proton dose calculation with LSTM networks in presence of a magnetic field.

To present a long short-term memory (LSTM) network-based dose calculation method for magnetic resonance (MR)-guided proton therapy.35 planning computed tomography (CT) images of prostate cancer patients were collected for Monte Carlo (MC) dose calculation under a perpendicular 1.5 T magnetic field.

CCL22 as an independent prognostic factor in endometrial cancer patients.

Objectives: The chemokine CCL22 is recognized for recruiting immunosuppressive regulatory T-cells (Treg) that contribute to disease progression in various tumor entities helping them to evade the host immune response. Our study aims to identify the expressing cell types and to evaluate the prognostic significance of CCL22 secretion and its association with Treg invasion in endometrial cancer (EC), an immunogenic cancer.

Methods: Specimens from 275 patients with EC and 28 healthy controls were screened immunohistochemically for CCL22.

IL-10R inhibition reprograms tumor-associated macrophages and reverses drug resistance in multiple myeloma.

Multiple myeloma (MM) is the cancer of plasma cells within the bone marrow and remains incurable. Tumor-associated macrophages (TAMs) within the tumor microenvironment often display a pro-tumor phenotype and correlate with tumor proliferation, survival, and therapy resistance. IL-10 is a key immunosuppressive cytokine that leads to recruitment and development of TAMs.

Tumor board simulation improves interdisciplinary decision-making in medical students.

Introduction: Training of interdisciplinary clinical reasoning and decision-making skills, essential in daily clinical practice in oncological specialties, are still underrepresented in medical education. Therefore, at LMU University Hospital Munich, we implemented a didactically modified tumor board simulation with experts from five different disciplines (medical oncology, pathology, radiation oncology, radiology, and surgery) presenting patient cases into a one-week course on the basic principles of oncology. In this survey, we examined the self-assessed impact of our course on the interdisciplinary decision-making skills of medical students.

Targeted RT study: results on early toxicity of targeted therapies and radiotherapy.

Purpose/objective: Currently, there are few prospective data on the tolerability of combining targeted therapies (TT) with radiation therapy (RT). The objective of this prospective study was to assess the feasibility and toxicity of pairing RT with concurrent TT in cancer patients. The aim was to enhance the existing evidence base for the simultaneous administration of targeted substances together with radiotherapy.

MRI-based ventilation and perfusion imaging to predict radiation-induced pneumonitis in lung tumor patients at a 0.35T MR-Linac.

Background And Purpose: Radiation-induced pneumonitis (RP), diagnosed 6-12 weeks after treatment, is a complication of lung tumor radiotherapy. So far, clinical and dosimetric parameters have not been reliable in predicting RP. We propose using non-contrast enhanced magnetic resonance imaging (MRI) based functional parameters acquired over the treatment course for patient stratification for improved follow-up.

Factors influencing pathological complete response and tumor regression in neoadjuvant radiotherapy and chemotherapy for high-risk breast cancer.

Background: Pathological complete response (pCR) is a well-established prognostic factor in breast cancer treated with neoadjuvant systemic therapy (naST). The determining factors of pCR are known to be intrinsic subtype, proliferation index, grading, clinical tumor and nodal stage as well as type of systemic therapy. The addition of neoadjuvant radiotherapy (naRT) to this paradigm might improve response, freedom from disease, toxicity and cosmetic outcome compared to adjuvant radiotherapy.

Re-irradiation treatment regimens for patients with recurrent glioma - Evaluation of the optimal dose and best concurrent therapy.

Purpose: Re-irradiation (reRT) is an effective treatment modality for patients with recurrent glioma. Data on dose escalation, the use of simulated integrated boost and concomitant therapy to reRT are still scarce. In this monocentric cohort of n = 223 patients we investigated the influence of reRT dose escalation as well as the concomitant use of bevacizumab (BEV) with regard to post-recurrence survival (PRS) and risk of radionecrosis (RN).

Expression of Intracellular Galectin-8 and -9 in Endometrial Cancer.

Endometrial cancer (EC) is a common gynecological cancer worldwide. Treatment has been improved in recent years; however, in advanced stages, therapeutic options are still limited. The expression of galectins is increased in several tumor types and that they are involved in important cell processes.

Dose prescription for stereotactic body radiotherapy: general and organ-specific consensus statement from the DEGRO/DGMP Working Group Stereotactic Radiotherapy and Radiosurgery.

Purpose And Objective: To develop expert consensus statements on multiparametric dose prescriptions for stereotactic body radiotherapy (SBRT) aligning with ICRU report 91. These statements serve as a foundational step towards harmonizing current SBRT practices and refining dose prescription and documentation requirements for clinical trial designs.

Materials And Methods: Based on the results of a literature review by the working group, a two-tier Delphi consensus process was conducted among 24 physicians and physics experts from three European countries.