First implementation of an innovative infra-red camera system integrated into a mobile CBCT scanner for applicator tracking in brachytherapy-Initial performance characterization.

PURPOSE: To enable a real-time applicator guidance for brachytherapy, we used for the first time infra-red tracking cameras (OptiTrack, USA) integrated into a mobile cone-beam computed tomography (CBCT) scanner (medPhoton, Austria). We provide the first description of this prototype and its performance evaluation. METHODS: We performed assessments of camera calibration and camera-CBCT registration using a geometric calibration phantom. For this purpose, we first evaluated the effects of intrinsic parameters such as camera temperature or gantry rotations on the tracked marker positions. Afterward, calibrations with various settings (sample number, field of view coverage, calibration directions, calibration distances, and lighting conditions) were performed to identify the requirements for achieving maximum tracking accuracy based on an in-house phantom. The corresponding effects on camera-CBCT registration were determined as well by comparing tracked marker positions to the positions determined via CBCT. Long-term stability was assessed by comparing tracking and a ground-truth on a weekly basis for 6 weeks. RESULTS: Robust tracking with positional drifts of 0.02 ± 0.01 mm was feasible using the system after a warm-up period of 90 min. However, gantry rotations affected the tracking and led to inaccuracies of up to 0.70 mm. We identified that 4000 samples and full coverage were required to ensure a robust determination of marker positions and camera-CBCT registration with geometric deviations of 0.18 ± 0.03 mm and 0.42 ± 0.07 mm, respectively. Long-term stability showed deviations of more than two standard deviations from the initial calibration after 3 weeks. CONCLUSION: We implemented for the first time a standalone combined camera-CBCT system for tracking in brachytherapy. The system showed high potential for establishing corresponding workflows.

"sCT-Feasibility" - a feasibility study for deep learning-based MRI-only brain radiotherapy.

BACKGROUND: Radiotherapy (RT) is an important treatment modality for patients with brain malignancies. Traditionally, computed tomography (CT) images are used for RT treatment planning whereas magnetic resonance imaging (MRI) images are used for tumor delineation. Therefore, MRI and CT need to be registered, which is an error prone process. The purpose of this clinical study is to investigate the clinical feasibility of a deep learning-based MRI-only workflow for brain radiotherapy, that eliminates the registration uncertainty through calculation of a synthetic CT (sCT) from MRI data. METHODS: A total of 54 patients with an indication for radiation treatment of the brain and stereotactic mask immobilization will be recruited. All study patients will receive standard therapy and imaging including both CT and MRI. All patients will receive dedicated RT-MRI scans in treatment position. An sCT will be reconstructed from an acquired MRI DIXON-sequence using a commercially available deep learning solution on which subsequent radiotherapy planning will be performed. Through multiple quality assurance (QA) measures and reviews during the course of the study, the feasibility of an MRI-only workflow and comparative parameters between sCT and standard CT workflow will be investigated holistically. These QA measures include feasibility and quality of image guidance (IGRT) at the linear accelerator using sCT derived digitally reconstructed radiographs in addition to potential dosimetric deviations between the CT and sCT plan. The aim of this clinical study is to establish a brain MRI-only workflow as well as to identify risks and QA mechanisms to ensure a safe integration of deep learning-based sCT into radiotherapy planning and delivery. DISCUSSION: Compared to CT, MRI offers a superior soft tissue contrast without additional radiation dose to the patients. However, up to now, even though the dosimetrical equivalence of CT and sCT has been shown in several retrospective studies, MRI-only workflows have still not been widely adopted. The present study aims to determine feasibility and safety of deep learning-based MRI-only radiotherapy in a holistic manner incorporating the whole radiotherapy workflow. TRIAL REGISTRATION: NCT06106997.

DEGRO guideline for personalized radiotherapy of brain metastases and leptomeningeal carcinomatosis in patients with breast cancer.

PURPOSE: The aim of this review was to evaluate the existing evidence for radiotherapy for brain metastases in breast cancer patients and provide recommendations for the use of radiotherapy for brain metastases and leptomeningeal carcinomatosis. MATERIALS AND METHODS: For the current review, a PubMed search was conducted including articles from 01/1985 to 05/2023. The search was performed using the following terms: (brain metastases OR leptomeningeal carcinomatosis) AND (breast cancer OR breast) AND (radiotherapy OR ablative radiotherapy OR radiosurgery OR stereotactic OR radiation). CONCLUSION AND RECOMMENDATIONS: Despite the fact that the biological subtype of breast cancer influences both the occurrence and relapse patterns of breast cancer brain metastases (BCBM), for most scenarios, no specific recommendations regarding radiotherapy can be made based on the existing evidence. For a limited number of BCBM (1-4), stereotactic radiosurgery (SRS) or fractionated stereotactic radiotherapy (SRT) is generally recommended irrespective of molecular subtype and concurrent/planned systemic therapy. In patients with 5-10 oligo-brain metastases, these techniques can also be conditionally recommended. For multiple, especially symptomatic BCBM, whole-brain radiotherapy (WBRT), if possible with hippocampal sparing, is recommended. In cases of multiple asymptomatic BCBM (≥ 5), if SRS/SRT is not feasible or in disseminated brain metastases (> 10), postponing WBRT with early reassessment and reevaluation of local treatment options (8-12 weeks) may be discussed if a HER2/Neu-targeting systemic therapy with significant response rates in the central nervous system (CNS) is being used. In symptomatic leptomeningeal carcinomatosis, local radiotherapy (WBRT or local spinal irradiation) should be performed in addition to systemic therapy. In patients with disseminated leptomeningeal carcinomatosis in good clinical condition and with only limited or stable extra-CNS disease, craniospinal irradiation (CSI) may be considered. Data regarding the toxicity of combining systemic therapies with cranial and spinal radiotherapy are sparse. Therefore, no clear recommendations can be given, and each case should be discussed individually in an interdisciplinary setting.

FEN1 Inhibition as a Potential Novel Targeted Therapy against Breast Cancer and the Prognostic Relevance of FEN1.

To improve breast cancer treatment and to enable new strategies for therapeutic resistance, therapeutic targets are constantly being studied. Potential targets are proteins of DNA repair and replication and genomic integrity, such as Flap Endonuclease 1 (FEN1). This study investigated the effects of FEN1 inhibitor FEN1-IN-4 in combination with ionizing radiation on cell death, clonogenic survival, the cell cycle, senescence, doubling time, DNA double-strand breaks and micronuclei in breast cancer cells, breast cells and healthy skin fibroblasts. Furthermore, the variation in the baseline FEN1 level and its influence on treatment prognosis was investigated. The cell lines show specific response patterns in the aspects studied and have heterogeneous baseline FEN1 levels. FEN1-IN-4 has cytotoxic, cytostatic and radiosensitizing effects, expressed through increasing cell death by apoptosis and necrosis, G2M share, senescence, double-strand breaks and a reduced survival fraction. Nevertheless, some cells are less affected by the cytotoxicity and fibroblasts show a rather limited response. In vivo, high FEN1 mRNA expression worsens the prognosis of breast cancer patients. Due to the increased expression in breast cancer tissue, FEN1 could represent a new tumor and prognosis marker and FEN1-IN-4 may serve as a new potent agent in personalized medicine and targeted breast cancer therapy.

Effects of serial radon spa therapy on pain and peripheral immune status in patients suffering from musculoskeletal disorders- results from a prospective, randomized, placebo-controlled trial.

In this randomized, placebo-controlled cross-over trial we aimed to investigate if radon spa therapy exerts more pain relief than exposure to warm water alone. In addition, immunological parameters were assessed in both treatment groups. In the RAD-ON02 trial, 116 patients suffering from musculoskeletal disorders (MSDs) received either serial radon spa or solely warm water baths. Pain intensity was assessed by determination of different pain parameters on a visual analogue scale and by pressure point dolorimetry at baseline and at weeks 4, 12 and 24. The longitudinal immune status of the patients was analyzed by a flow cytometry-based assay from peripheral blood at the time points of pain assessments. There were no side effects attributable to radon exposure observed. However, radon spa was superior to warm water applications at week 4 in terms of pain reduction. Pain and morning stiffness at the time of assessment were significantly reduced after radon spa (p<0.001, p<0.01) but not after warm water baths. The dolorimetry resulted in a significantly higher exerted pressure strength in patients after radon spa (p<0.001), but not after warm water applications. During the long-term follow-up, both treatment modalities reduced pain to a similar degree and pain modulation was not distorted by the participants' intake of analgesics. No significant changes in the immune status attributable specifically to radon were found, even though the increase in regulatory T cell counts occurs earlier after radon baths than after sole warm water baths and a higher level of significance is reached after radon spa at week 24. Serial radon spa has additive pain-relieving effects. The immunological parameters assessed in our study appear not to be directly linked to the pain reduction caused by radon exposure, at least in MSD patients with predominantly degenerative diseases. Clinical trial registration: https://www.clinicaltrialsregister.eu/ctr-search/search?query=rad-on02, identifier 2016-002085-31; https://drks.de/search/de/trial, identifier DRKS00016019.

Different Impacts of DNA-PK and mTOR Kinase Inhibitors in Combination with Ionizing Radiation on HNSCC and Normal Tissue Cells.

Despite substantial advancements in understanding the pathomechanisms of head and neck squamous cell carcinoma (HNSCC), effective therapy remains challenging. The application of kinase inhibitors (KIs) in HNSCC, specifically mTOR and DNA-PK inhibitors, can increase radiosensitivity and therefore presents a promising strategy when used simultaneously with ionizing radiation (IR) in cancer treatment. Our study focused on the selective DNA-PK-inhibitor AZD7648; the selective mTOR-inhibitor Sapanisertib; and CC-115, a dual inhibitor targeting both mTOR and DNA-PK. The impact of these KIs on HNSCC and normal tissue cells was assessed using various analytical methods including cell death studies, cell cycle analysis, real-time microscopy, colony-forming assays and immunohistochemical staining for γH2AX and downstream mTOR protein p-S6. We detected a strong inhibition of IR-induced DNA double-strand break (DSB) repair, particularly in AZD7648-treated HNSCC, whereas normal tissue cells repaired DNA DSB more efficiently. Additionally, AZD7648 + IR treatment showed a synergistic decline in cell proliferation and clonogenicity, along with an elevated G2/M arrest and cell death in the majority of HNSCC cell lines. CC-115 + IR treatment led to an elevation in G2/M arrest, increased cell death, and a synergistic reduction in cell proliferation, though the effect was notably lower compared to the AZD7648 + IR- treated group. Sapanisertib led to a high cellular toxicity in both HNSCC and normal tissue cells, even in non-irradiated cells. Regarding cell proliferation and the induction of apoptosis and necrosis, Sapanisertib + IR was beneficial only in HPV+ HNSCC. Overall, this study highlights the potential of AZD7648 as a radiosensitizing agent in advanced-stage HPV-positive and negative HNSCC, offering a promising therapeutic strategy. However, the dual mTOR/DNA-PK-I CC-115 did not provide a distinct advantage over the use of selective KIs in our investigations, suggesting limited benefits for its application in KI + IR therapy. Notably, the selective mTOR-inhibitor Sapanisertib was only beneficial in HPV+ HNSCC and should not be applied in HPV- cases.

Neutrophils in HNSCC Can Be Associated with Both a Worse or Favorable Prognosis.

The prognostic significance of tumor-infiltrating neutrophils in head and neck squamous cell carcinoma (HNSCC) is poorly understood. It is unclear how the presence of neutrophils affects prognosis due to their polarization into cytotoxic N1 or immunosuppressive N2. Therefore, we determined the number of CD66b+ neutrophil granulocytes separately in the stromal and epithelial compartments in cancer tissues from 397 patients with HNSCC. Tumor samples from six historical patient groups were processed into tissue microarrays and stained immunohistochemically. In total, 21.9% were HPV positive (p16+). Neutrophil counts were much lower in the stromal compartment (372 ± 812) than in the epithelial cancer compartment (1040 ± 1477) (p < 0.001), with large differences between groups. In three groups with high neutrophil infiltration, high rates were associated with a favorable prognosis, whereas in two groups, high rates were a negative prognostic factor. In p16- oropharyngeal and hypopharyngeal cancer high infiltration was associated with a favorable prognosis. Cancers with an exclusion of neutrophils in the epithelial compartment were associated with improved prognosis. In oropharyngeal and hypopharyngeal HPV-negative cancer high neutrophil infiltration rates were clearly associated with prolonged survival. Neutrophil granulocytes in HNSCC may contribute to a favorable or unfavorable prognosis.

Quality requirements for MRI simulation in cranial stereotactic radiotherapy: a guideline from the German Taskforce "Imaging in Stereotactic Radiotherapy".

Accurate Magnetic Resonance Imaging (MRI) simulation is fundamental for high-precision stereotactic radiosurgery and fractionated stereotactic radiotherapy, collectively referred to as stereotactic radiotherapy (SRT), to deliver doses of high biological effectiveness to well-defined cranial targets. Multiple MRI hardware related factors as well as scanner configuration and sequence protocol parameters can affect the imaging accuracy and need to be optimized for the special purpose of radiotherapy treatment planning. MRI simulation for SRT is possible for different organizational environments including patient referral for imaging as well as dedicated MRI simulation in the radiotherapy department but require radiotherapy-optimized MRI protocols and defined quality standards to ensure geometrically accurate images that form an impeccable foundation for treatment planning. For this guideline, an interdisciplinary panel including experts from the working group for radiosurgery and stereotactic radiotherapy of the German Society for Radiation Oncology (DEGRO), the working group for physics and technology in stereotactic radiotherapy of the German Society for Medical Physics (DGMP), the German Society of Neurosurgery (DGNC), the German Society of Neuroradiology (DGNR) and the German Chapter of the International Society for Magnetic Resonance in Medicine (DS-ISMRM) have defined minimum MRI quality requirements as well as advanced MRI simulation options for cranial SRT.

Machine Learning-assisted immunophenotyping of peripheral blood identifies innate immune cells as best predictor of response to induction chemo-immunotherapy in head and neck squamous cell carcinoma - knowledge obtained from the CheckRad-CD8 trial.

PURPOSE: Individual prediction of treatment response is crucial for personalized treatment in multimodal approaches against head-and-neck squamous cell carcinoma (HNSCC). So far, no reliable predictive parameters for treatment schemes containing immunotherapy have been identified. This study aims to predict treatment response to induction chemo-immunotherapy based on the peripheral blood immune status in patients with locally advanced HNSCC. METHODS: The peripheral blood immune phenotype was assessed in whole blood samples in patients treated in the phase II CheckRad-CD8 trial as part of the pre-planned translational research program. Blood samples were analyzed by multicolor flow cytometry before (T1) and after (T2) induction chemo-immunotherapy with cisplatin/docetaxel/durvalumab/tremelimumab. Machine Learning techniques were used to predict pathological complete response (pCR) after induction therapy. RESULTS: The tested classifier methods (LDA, SVM, LR, RF, DT, and XGBoost) allowed a distinct prediction of pCR. Highest accuracy was achieved with a low number of features represented as principal components. Immune parameters obtained from the absolute difference (lT2-T1l) allowed the best prediction of pCR. In general, less than 30 parameters and at most 10 principal components were needed for highly accurate predictions. Across several datasets, cells of the innate immune system such as polymorphonuclear cells, monocytes, and plasmacytoid dendritic cells are most prominent. CONCLUSIONS: Our analyses imply that alterations of the innate immune cell distribution in the peripheral blood following induction chemo-immuno-therapy is highly predictive for pCR in HNSCC.

Investigating the impact of breast positioning control on physical treatment parameters in multi-catheter breast brachytherapy.

PURPOSE: To assess the effects of a workflow for reproducible patient and breast positioning on implant stability during high-dose-rate multi-catheter breast brachytherapy. METHODS: Thirty patients were treated with our new positioning control workflow. Implant stability was evaluated based on a comparison of planning-CTs to control-CTs acquired halfway through the treatment. To assess geometric stability, button-button distance variations as well as Euclidean dwell position deviations were evaluated. The latter were also quantified within various separated regions within the breast to investigate the location-dependency of implant alterations. Furthermore, dosimetric variations to target volume and organs at risk (ribs, skin) as well as isodose volume changes were analyzed. Results were compared to a previously treated cohort of 100 patients. RESULTS: With the introduced workflow, the patient fraction affected by button-button distance variations > 5 mm and by dwell position deviations > 7 mm were reduced from 37% to 10% and from 30% to 6.6%, respectively. Implant stability improved the most in the lateral to medial breast regions. Only small stability enhancements were observed regarding target volume dosimetry, but the stability of organ at risk exposure became substantially higher. D0.2ccm skin dose variations > 12.4% and D0.1ccm rib dose variations > 6.7% were reduced from 11% to 0% and from 16% to 3.3% of all patients, respectively. CONCLUSION: Breast positioning control improved geometric and dosimetric implant stability for individual patients, and thus enhanced physical plan validity in these cases.

European Association of Urology Guidelines on Muscle-invasive and Metastatic Bladder Cancer: Summary of the 2023 Guidelines.

CONTEXT: We present an overview of the updated 2023 European Association of Urology (EAU) guidelines for muscle-invasive and metastatic bladder cancer (MMIBC). OBJECTIVE: To provide practical evidence-based recommendations and consensus statements on the clinical management of MMIBC with a focus on diagnosis and treatment. EVIDENCE ACQUISITION: A broad and comprehensive scoping exercise covering all areas of the MMIBC guidelines has been performed annually since 2017. Searches cover the Medline, EMBASE, and Cochrane Libraries databases for yearly guideline updates. A level of evidence and strength of recommendation are assigned. The evidence cutoff date for the 2023 MIBC guidelines was May 4, 2022. EVIDENCE SYNTHESIS: Patients should be counselled regarding risk factors for bladder cancer. Pathologists should describe tumour and lymph nodes in detail, including the presence of histological subtypes. The importance of the presence or absence of urothelial carcinoma (UC) in the prostatic urethra is emphasised. Magnetic resonance imaging (MRI) of the bladder is superior to computed tomography (CT) for disease staging, specifically in differentiating T1 from T2 disease, and may lead to a change in treatment approach in patients at high risk of an invasive tumour. Imaging of the upper urinary tract, lymph nodes, and distant metastasis is performed with CT or MRI; the additional value of flurodeoxyglucose positron emission tomography/CT still needs to be determined. Frail and comorbid patients should be evaluated by a multidisciplinary team. Postoperative histology remains the most important prognostic variable, while circulating tumour DNA appears to be an interesting predictive marker. Neoadjuvant systemic therapy remains cisplatin-based. In motivated and selected women and men, sexual organ-preserving cystectomy results in better functional outcomes without compromising oncological outcomes. Robotic and open cystectomy have comparable outcomes and should be combined with (extended) lymph node dissection. The diversion type is an individual choice after taking patient and tumour characteristics into account. Radical cystectomy remains a highly complex procedure with considerable morbidity and risk of mortality, although lower rates are observed for higher hospital volumes (>20 cases/yr). With proper patient selection, trimodal therapy (chemoradiation) has comparable outcomes to radical cystectomy. Adjuvant chemotherapy after surgery improves disease-specific survival and overall survival (OS) in patients with high-risk disease who did not receive neoadjuvant treatment, and is strongly recommended. There is a weak recommendation for adjuvant nivolumab, as OS data are not yet available. Health-related quality of life should be assessed using validated questionnaires at baseline and after treatment. Surveillance is needed to monitor for recurrent cancer and functional outcomes. Recurrences detected on follow-up seem to have better prognosis than symptomatic recurrences. CONCLUSIONS: This summary of the 2023 EAU guidelines provides updated information on the diagnosis and treatment of MMIBC for incorporation into clinical practice. PATIENT SUMMARY: The European Association of Urology guidelines panel on muscle-invasive and metastatic bladder cancer has released an updated version of the guideline containing information on diagnosis and treatment of this disease. Recommendations are based on studies published up to May 4, 2022. Surgical removal of the bladder and bladder preservation are discussed, as well as updates on the use of chemotherapy and immunotherapy in localised and metastatic disease.

Successful implementation of online educational lectures of the German Society for Radiation Oncology (DEGRO).

PURPOSE: Modern digital teaching formats have become increasingly important in recent years, in part due to the COVID-19 pandemic. In January 2021, an online-based webinar series was established by the German Society for Radiation Oncology (DEGRO) and the young DEGRO (yDEGRO) working group. In the monthly 120-minute courses, selected lecturers teach curricular content as preparation for the board certification exam for radiation oncology. METHODS: The evaluation of the 24 courses between 01.2021 and 12.2022 was performed using a standardized questionnaire with 21 items (recording epidemiological characteristics of the participants, didactic quality, content quality). A Likert scale (1-4) was used in combination with binary and open-ended questions. RESULTS: A combined total of 4200 individuals (1952 in 2021 and 2248 in 2022) registered for the courses, and out of those, 934 participants (455 in 2021 and 479 in 2022) later provided evaluations for the respective courses (36% residents, 35% specialists, 21% medical technicians for radiology [MTR], 8% medical physics experts [MPE]). After 2 years, 74% of the DEGRO Academy curriculum topics were covered by the monthly webinars. The overall rating by participants was positive (mean 2021: 1.33 and 2022: 1.25) and exceeded the curriculum offered at each site for 70% of participants. Case-based learning was identified as a particularly well-rated method. CONCLUSION: The DEGRO webinar expands the digital teaching opportunities in radiation oncology. The consistently high number of participants confirms the need for high-quality teaching and underlines the advantages of e­learning methods. Optimization opportunities were identified through reevaluation of feedback from course participants. In its design as a teaching format for a multiprofessional audience, the webinar series could be used as a practice model of online teaching for other disciplines.

Toward a deep learning-based magnetic resonance imaging only workflow for postimplant dosimetry in I-125 seed brachytherapy for prostate cancer.

BACKGROUND AND PURPOSE: The current standard imaging-technique for creating postplans in seed prostate brachytherapy is computed tomography (CT), that is associated with additional radiation exposure and poor soft tissue contrast. To establish a magnetic resonance imaging (MRI) only workflow combining improved tissue contrast and high seed detectability, a deep learning-approach for automatic seed segmentation on MRI-scans was developed. MATERIAL AND METHODS: Patients treated with I-125 seed brachytherapy received a postplan-CT and a 1.5 T MRI-scan on nominal day 30 after implantation. For MRI-based seed visualization, DIXON-sequences were acquired and deep learning-based quantitative susceptibility maps (QSM) were generated from 3D-gradient-echo-sequences from 20 patients. Seed segmentations created on CT served as ground truth. For automatic seed segmentation on MRI, a 3D nnU-net model was trained using QSM and DIXON, both solely and combined. RESULTS: Of the implanted seeds 94.8 ± 2.4% were detected with deep learning automatic segmentation entrained on both QSM and DIXON data. Models trained on the individual sequence data-sets performed worse with detection rates of 87.5 ± 2.6% or 88.6 ± 7.5% for QSM and DIXON respectively. The seed centers identified on CT versus QSM and DIXON were on average 1.8 ± 1.3 mm apart. Postimplant dosimetry for evaluation of positioning inaccuracies revealed only small variations of up to 0.4 ± 4.26 Gy in D90 (dose 90% of the prostate receives) between the standard CT-approach and our MRI-only workflow. CONCLUSION: The proposed deep learning-based MRI-only workflow provided a promisingly accurate and robust seed localization and thus has the potential to compete with current state-of-the-art CT-based postimplant dosimetry in the future.

Determinants Affecting the Clinical Implementation of a Molecularly Informed Molecular Tumor Board Recommendation: Experience from a Tertiary Cancer Center.

Molecular Tumor Boards (MTBs) converge state-of-the-art next-generation sequencing (NGS) methods with the expertise of an interdisciplinary team consisting of clinicians, pathologists, human geneticists, and molecular biologists to provide molecularly informed guidance in clinical decision making to the treating physician. In the present study, we particularly focused on elucidating the factors impacting on the clinical translation of MTB recommendations, utilizing data generated from gene panel mediated comprehensive genomic profiling (CGP) of 554 patients at the MTB of the Comprehensive Cancer Center Erlangen, Germany, during the years 2016 to 2020. A subgroup analysis of cases with available follow-up data (n = 332) revealed 139 cases with a molecularly informed MTB recommendation, which was successfully implemented in the clinic in 44 (31.7%) of these cases. Here, the molecularly matched treatment was applied in 45.4% (n = 20/44) of cases for ≥6 months and in 25% (n = 11/44) of cases for 12 months or longer (median time to treatment failure, TTF: 5 months, min: 1 month, max: 38 months, ongoing at data cut-off). In general, recommendations were preferentially implemented in the clinic when of high (i.e., tier 1) clinical evidence level. In particular, this was the case for MTB recommendations suggesting the application of PARP, PIK3CA, and IDH1/2 inhibitors. The main reason for non-compliance to the MTB recommendation was either the application of non-matched treatment modalities (n = 30)/stable disease (n = 7), or deteriorating patient condition (n = 22)/death of patient (n = 9). In summary, this study provides an insight into the factors affecting the clinical implementation of molecularly informed MTB recommendations, and careful considerations of these factors may guide future processes of clinical decision making.

Explainable convolutional neural networks for assessing head and neck cancer histopathology.

PURPOSE: Although neural networks have shown remarkable performance in medical image analysis, their translation into clinical practice remains difficult due to their lack of interpretability. An emerging field that addresses this problem is Explainable AI. METHODS: Here, we aimed to investigate the ability of Convolutional Neural Networks (CNNs) to classify head and neck cancer histopathology. To this end, we manually annotated 101 histopathological slides of locally advanced head and neck squamous cell carcinoma. We trained a CNN to classify tumor and non-tumor tissue, and another CNN to semantically segment four classes - tumor, non-tumor, non-specified tissue, and background. We applied Explainable AI techniques, namely Grad-CAM and HR-CAM, to both networks and explored important features that contributed to their decisions. RESULTS: The classification network achieved an accuracy of 89.9% on previously unseen data. Our segmentation network achieved a class-averaged Intersection over Union score of 0.690, and 0.782 for tumor tissue in particular. Explainable AI methods demonstrated that both networks rely on features agreeing with the pathologist's expert opinion. CONCLUSION: Our work suggests that CNNs can predict head and neck cancer with high accuracy. Especially if accompanied by visual explanations, CNNs seem promising for assisting pathologists in the assessment of cancer sections.

Radiotherapy combined with docetaxel alters the immune phenotype of HNSCC cells and results in increased surface expression of CD137 and release of HMGB1 of specifically HPV-positive tumor cells.

PURPOSE: Human papilloma virus (HPV) positive head and neck squamous cell carcinoma (HNSCC) tumors respond significantly better to anticancer treatments. It is assumed to be due to a better response to radiotherapy (RT), and presumably to an increased immunogenicity. However, little is known how the immune phenotype of HNSCC tumor cells is modulated by standard treatment, namely by radiochemotherapy (RCT). METHODS: Therefore, we aimed to examine the impact of the HPV status on the immune phenotype of HNSCC cell lines following RCT with 5 × 3Gy or 1 × 19.3Gy and/or docetaxel, by analyzing cell death, release of damage-associated molecular patterns (DAMPs), surface expression of immune checkpoint molecules (ICMs) and the impact on activation of human monocyte-derived dendritic cells (hmDCs). RESULTS: Cell death induction and Hsp70 release following RCT was independent of the HPV status, and RCT significantly increased the expression of the immune suppressive ICMs PD-L1, PD-L2 and HVEM. An immune stimulatory ICM, CD137, was significantly increased following RCT only on HPV-positive cell lines, as well as the release of HMGB1. Although the treatment increased cell death and modulated ICM expression in HNSCC, the hmDCs were not activated after co-incubation with treated tumor cells. CONCLUSION: Our data with the HPV-dependent release of HMGB1 and increased expression of CD137 following RCT provide a hint for increased immunogenicity underlining the better prognosis for HPV positive tumors following RCT.

Benchmarking ChatGPT-4 on a radiation oncology in-training exam and Red Journal Gray Zone cases: potentials and challenges for ai-assisted medical education and decision making in radiation oncology.

Purpose: The potential of large language models in medicine for education and decision-making purposes has been demonstrated as they have achieved decent scores on medical exams such as the United States Medical Licensing Exam (USMLE) and the MedQA exam. This work aims to evaluate the performance of ChatGPT-4 in the specialized field of radiation oncology. Methods: The 38th American College of Radiology (ACR) radiation oncology in-training (TXIT) exam and the 2022 Red Journal Gray Zone cases are used to benchmark the performance of ChatGPT-4. The TXIT exam contains 300 questions covering various topics of radiation oncology. The 2022 Gray Zone collection contains 15 complex clinical cases. Results: For the TXIT exam, ChatGPT-3.5 and ChatGPT-4 have achieved the scores of 62.05% and 78.77%, respectively, highlighting the advantage of the latest ChatGPT-4 model. Based on the TXIT exam, ChatGPT-4's strong and weak areas in radiation oncology are identified to some extent. Specifically, ChatGPT-4 demonstrates better knowledge of statistics, CNS & eye, pediatrics, biology, and physics than knowledge of bone & soft tissue and gynecology, as per the ACR knowledge domain. Regarding clinical care paths, ChatGPT-4 performs better in diagnosis, prognosis, and toxicity than brachytherapy and dosimetry. It lacks proficiency in in-depth details of clinical trials. For the Gray Zone cases, ChatGPT-4 is able to suggest a personalized treatment approach to each case with high correctness and comprehensiveness. Importantly, it provides novel treatment aspects for many cases, which are not suggested by any human experts. Conclusion: Both evaluations demonstrate the potential of ChatGPT-4 in medical education for the general public and cancer patients, as well as the potential to aid clinical decision-making, while acknowledging its limitations in certain domains. Owing to the risk of hallucinations, it is essential to verify the content generated by models such as ChatGPT for accuracy.