Prediction of Overall Disease Burden in (y)pN1 Breast Cancer Using Knowledge-Based Machine Learning Model.

BACKGROUND: We aimed to construct an expert knowledge-based Bayesian network (BN) model for assessing the overall disease burden (ODB) in (y)pN1 breast cancer patients and compare ODB across arms of ongoing trials. METHODS: Utilizing institutional data and expert surveys, we developed a BN model for (y)pN1 breast cancer. Expert-derived probabilities and disability weights for radiotherapy-related benefit (e.g., 7-year disease-free survival [DFS]) and toxicities were integrated into the model. ODB was defined as the sum of disability weights multiplied by probabilities. In silico predictions were conducted for Alliance A011202, PORT-N1, RAPCHEM, and RT-CHARM trials, comparing ODB, 7-year DFS, and side effects. RESULTS: In the Alliance A011202 trial, 7-year DFS was 80.1% in both arms. Axillary lymph node dissection led to higher clinical lymphedema and ODB compared to sentinel lymph node biopsy with full regional nodal irradiation (RNI). In the PORT-N1 trial, the control arm (whole-breast irradiation [WBI] with RNI or post-mastectomy radiotherapy [PMRT]) had an ODB of 0.254, while the experimental arm (WBI alone or no PMRT) had an ODB of 0.255. In the RAPCHEM trial, the radiotherapy field did not impact the 7-year DFS in ypN1 patients. However, there was a mild ODB increase with a larger irradiation field. In the RT-CHARM trial, we identified factors associated with the major complication rate, which ranged from 18.3% to 22.1%. CONCLUSIONS: The expert knowledge-based BN model predicted ongoing trial outcomes, validating reported results and assumptions. In addition, the model demonstrated the ODB in different arms, with an emphasis on quality of life.

Assessment of lymph node area coverage with total marrow irradiation and implementation of total marrow and lymphoid irradiation using automated deep learning-based segmentation.

BACKGROUND: Total marrow irradiation (TMI) and total marrow and lymphoid irradiation (TMLI) have the advantages. However, delineating target lesions according to TMI and TMLI plans is labor-intensive and time-consuming. In addition, although the delineation of target lesions between TMI and TMLI differs, the clinical distinction is not clear, and the lymph node (LN) area coverage during TMI remains uncertain. Accordingly, this study calculates the LN area coverage according to the TMI plan. Further, a deep learning-based model for delineating LN areas is trained and evaluated. METHODS: Whole-body regional LN areas were manually contoured in patients treated according to a TMI plan. The dose coverage of the delineated LN areas in the TMI plan was estimated. To train the deep learning model for automatic segmentation, additional whole-body computed tomography data were obtained from other patients. The patients and data were divided into training/validation and test groups and models were developed using the "nnU-NET" framework. The trained models were evaluated using Dice similarity coefficient (DSC), precision, recall, and Hausdorff distance 95 (HD95). The time required to contour and trim predicted results manually using the deep learning model was measured and compared. RESULTS: The dose coverage for LN areas by TMI plan had V100% (the percentage of volume receiving 100% of the prescribed dose), V95%, and V90% median values of 46.0%, 62.1%, and 73.5%, respectively. The lowest V100% values were identified in the inguinal (14.7%), external iliac (21.8%), and para-aortic (42.8%) LNs. The median values of DSC, precision, recall, and HD95 of the trained model were 0.79, 0.83, 0.76, and 2.63, respectively. The time for manual contouring and simply modified predicted contouring were statistically significantly different. CONCLUSIONS: The dose coverage in the inguinal, external iliac, and para-aortic LN areas was suboptimal when treatment is administered according to the TMI plan. This research demonstrates that the automatic delineation of LN areas using deep learning can facilitate the implementation of TMLI.

B-Cell-Mediated Immunity Predicts Survival of Patients With Estrogen Receptor-Positive Breast Cancer.

PURPOSE: The estrogen receptor-positive (ER+) breast cancer (BC), which constitutes the majority of BC cases, exhibits highly heterogeneous clinical behavior. To aid precision treatments, we aimed to find molecular subtypes of ER+ BC representing the tumor microenvironment and prognosis. METHODS: We analyzed RNA-seq data of 113 patients with BC and classified them according to the PAM50 intrinsic subtypes using gene expression profiles. Among them, we further focused on 44 patients with luminal-type (ER+) BC for subclassification. The Cancer Genome Atlas (TCGA) data of patients with BC were used as a validation data set to verify the new classification. We estimated the immune cell composition using CIBERSORT and further analyzed its association with clinical or molecular parameters. RESULTS: Principal component analysis clearly divided the patients into two subgroups separately from the luminal A and B classification. The top differentially expressed genes between the subgroups were distinctly characterized by immunoglobulin and B-cell-related genes. We could also cluster a separate cohort of patients with luminal-type BC from TCGA into two subgroups on the basis of the expression of a B-cell-specific gene set, and patients who were predicted to have high B-cell immune activity had better prognoses than other patients. CONCLUSION: Our transcriptomic approach emphasize a molecular phenotype of B-cell immunity in ER+ BC that may help to predict disease prognosis. Although further researches are required, B-cell immunity for patients with ER+ BC may be helpful for identifying patients who are good responders to chemotherapy or immunotherapy.

The Impact of PM2.5 on Radiation-induced Pneumonitis in Patients With Breast Cancer.

BACKGROUND/AIM: Exposure to particulate matter (PM) air pollution is known to adversely affect respiratory disease, but no study has examined its effect on radiation-induced pneumonitis (RIP) in patients with breast cancer. PATIENTS AND METHODS: We conducted a retrospective review of 2,736 patients with breast cancer who received postoperative radiation therapy (RT) between 2017 and 2020 in a single institution. The distance between the PM measurement station and our institution was only 3.43 km. PM data, including PM2.5 and PM10, were retrieved from the open dataset in the official government database. RESULTS: Overall incidence rate of RIP was 1.74%. After adjusting for age, RT technique, regional irradiation, fractionation and boost, the average value of PM2.5 was significantly associated with a higher risk of RIP (p=0.047) when patients received ≥20 fractions of RT. Specifically, PM2.5 ≥35 (µg/m3) showed a significantly higher risk of RIP (p=0.019) in patients with ≥20 fractions of RT. CONCLUSION: This is the first study to reveal the association between PM2.5 and RIP in patients with breast cancer who received 20 fractions or more of postoperative RT. We demonstrated that high PM2.5 levels around the RT institution were associated with RIP, suggesting that reducing PM air pollution may be a modifiable risk factor.

Estimating the risk and benefit of radiation therapy in (y)pN1 stage breast cancer patients: A Bayesian network model incorporating expert knowledge (KROG 22-13).

BACKGROUND: We aimed to evaluate the risk and benefit of (y)pN1 breast cancer patients in a Bayesian network model. METHOD: We developed a Bayesian network (BN) model comprising three parts: pretreatment, intervention, and risk/benefit. The pretreatment part consisted of clinical information from a tertiary medical center. The intervention part regarded the field of radiotherapy. The risk/benefit component encompasses radiotherapy (RT)-related side effects and effectiveness, including factors such as recurrence, cardiac toxicity, lymphedema, and radiation pneumonitis. These factors were evaluated in terms of disability weights and probabilities from a nationwide expert survey. The overall disease burden (ODB) was calculated as the sum of the probability multiplied by the disability weight. A higher value of ODB indicates a greater disease burden for the patient. RESULTS: Among the 58 participants, a BN model utilizing discretization and clustering techniques revealed five distinct clusters. Overall, factors associated with breast reconstruction and RT exhibited high discrepancies (24-34 %), while RT-related side effects demonstrated low discrepancies (3-11 %) among the experts. When incorporating recurrence and RT-related side effects, the mean ODB of (y)pN1 patients was 0.258 (range, 0.244-0.337), with a higher tendency observed in triple-negative breast cancer (TNBC) or mastectomy cases. The ODB for TNBC patients undergoing mastectomy without postmastectomy radiotherapy was 0.327, whereas for non-TNBC patients undergoing breast conserving surgery with RT, the disease burden was 0.251. There was an increasing trend in ODB as the field of RT increased. CONCLUSION: We developed a Bayesian network model based on an expert survey, which helps to understand treatment patterns and enables precise estimations of RT-related risk and benefit in (y)pN1 patients.

Effect of Lactobacillus Rhamnosus GG for Regulation of Inflammatory Response in Radiation-Induced Enteritis.

The purpose of this study was to investigate the role of Lactobacillus rhamnosus GG (LGG) probiotics in radiation enteritis using in vivo mice. A total of 40 mice were randomly assigned to four groups: control, probiotics, radiotherapy (RT), and RT + probiotics. For the group of probiotics, 0.2 mL of solution that contained 1.0 × 108 colony-forming units (CFU) of LGG was used and orally administered daily until sacrifice. For RT, a single dose of 14 Gy was administered using a 6 mega-voltage photon beam to the abdominopelvic area. Mice were sacrifice at day 4 (S1) and day 7 (S2) after RT. Their jejunum, colon, and stool were collected. A multiplex cytokine assay and 16 s ribosomal RNA amplicon sequencing were then performed. Regarding cytokine concentrations in tissues, pro-inflammatory cytokines, such as tumor necrosis factor-α, interleukin-6 and monocyte chemotactic protein-1, showed significantly decreased protein levels in colon tissues of the RT + probiotics group than in the RT alone group (all p < 0.05). As for comparing microbial abundance through alpha-diversity and beta-diversity, no significant differences were observed between the RT + probiotics and RT alone groups, except for an increase in alpha-diversity in the stool of the RT + probiotics group. Upon analysis of differential microbes based on treatment, the dominance of anti-inflammatory-related microbes, such as Porphyromonadaceae, Bacteroides acidifaciens, and Ruminococcus, was observed in the jejunum, colon, and stool of the RT + probiotics group. With regard to predicted metabolic pathway abundances, the pathways associated with anti-inflammatory processes, such as biosynthesis of pyrimidine nucleotides, peptidoglycans, tryptophan, adenosylcobalamin, and propionate, were differentially identified in the RT + probiotics group compared to the RT alone group. Protective effects of probiotics on radiation enteritis were potentially derived from dominant anti-inflammation-related microbes and metabolites.

Assessment of deep learning-based auto-contouring on interobserver consistency in target volume and organs-at-risk delineation for breast cancer: Implications for RTQA program in a multi-institutional study.

PURPOSE: To quantify interobserver variation (IOV) in target volume and organs-at-risk (OAR) contouring across 31 institutions in breast cancer cases and to explore the clinical utility of deep learning (DL)-based auto-contouring in reducing potential IOV. METHODS AND MATERIALS: In phase 1, two breast cancer cases were randomly selected and distributed to multiple institutions for contouring six clinical target volumes (CTVs) and eight OAR. In Phase 2, auto-contour sets were generated using a previously published DL Breast segmentation model and were made available for all participants. The difference in IOV of submitted contours in phases 1 and 2 was investigated quantitatively using the Dice similarity coefficient (DSC) and Hausdorff distance (HD). The qualitative analysis involved using contour heat maps to visualize the extent and location of these variations and the required modification. RESULTS: Over 800 pairwise comparisons were analysed for each structure in each case. Quantitative phase 2 metrics showed significant improvement in the mean DSC (from 0.69 to 0.77) and HD (from 34.9 to 17.9 mm). Quantitative analysis showed increased interobserver agreement in phase 2, specifically for CTV structures (5-19 %), leading to fewer manual adjustments. Underlying IOV differences causes were reported using a questionnaire and hierarchical clustering analysis based on the volume of CTVs. CONCLUSION: DL-based auto-contours improved the contour agreement for OARs and CTVs significantly, both qualitatively and quantitatively, suggesting its potential role in minimizing radiation therapy protocol deviation.

Dynamic Responses of Circulating T Cells After Stereotactic Body Radiation Therapy for Bone Metastasis in Patients With Breast Cancer.

PURPOSE: Preclinical studies have shown that radiation therapy modulates antitumor immune responses. However, circulating T-cell responses after radiation therapy in patients with cancer have been poorly characterized. This study aims to explore the changes in circulating T cells after stereotactic body radiation therapy (SBRT). METHODS AND MATERIALS: Peripheral blood samples of 30 patients with breast cancer who underwent SBRT for bone metastasis were analyzed using multicolor flow cytometry. Phenotypes of PD-1+ CD8+ T cells and regulatory T (TREG) cells were examined. Additionally, plasma protein levels were analyzed using a bead-based immunoassay. RESULTS: Circulating PD-1+ CD8+ T cells, which are enriched for tumor-specific clonotypes, were activated at 1 week after SBRT. However, circulating TREG cells were also activated after SBRT; this pattern was also evident among effector Foxp3hiCD45RA- TREG cells. We observed no difference in T-cell responses according to the fraction size and number. Notably, activation of TREG cells was more prominent in patients who experienced greater activation of PD-1+ CD8+ T cells. Plasma level changes in TGF-ß1, soluble CTLA-4, and soluble 4-1BB at 1 week after SBRT were associated with PD-1+ CD8+ T-cell responses. Activation of TREG cells at 1 week after SBRT was associated with worse progression-free survival. Clinical factors including molecular subtype were not associated with the T-cell responses. CONCLUSIONS: SBRT induced activation of both potentially tumor-specific CD8+ T cells and TREG cells, which were tightly associated with each other. These results may support the use of TREG cell-modulating strategies with SBRT to improve the antitumor immune response.

Association between gut microbial change and acute gastrointestinal toxicity in patients with prostate cancer receiving definitive radiation therapy.

BACKGROUND: This prospective study investigated the association between gut microbial changes and acute gastrointestinal toxicities in prostate cancer patients receiving definitive radiation therapy (RT). METHODS: Seventy-nine fecal samples were analyzed. Stool samples were collected at the following timepoints: pre-RT (prRT), 2 weeks after the start of RT (RT-2w), 5 weeks after the start of RT (RT-5w), 1 month after completion of RT (poRT-1 m), and 3 months after completion of RT (poRT-3 m). We computed the microbial community polarization index (MCPI) as an indicator of RT-induced dysbiosis. RESULTS: Patients experiencing toxicity had lower alpha diversity, especially at RT-2w (p = 0.037) and RT-5w (p = 0.003). Compared to patients without toxicity, the MCPI in those experiencing toxicities was significantly elevated (p = 0.019). In terms of predicted metabolic pathways, we found linearly decreasing pathways, including carbon fixation pathways in prokaryotes (p = 0.035) and the bacterial secretion system (p = 0.005), in patients who experienced toxicities. CONCLUSIONS: We showed RT-induced dysbiosis among patients who experienced toxicities. Reduced diversity and elevated RT-related MCPI could be helpfully used for developing individualized RT approaches.

Developing prompts from large language model for extracting clinical information from pathology and ultrasound reports in breast cancer.

PURPOSE: We aimed to evaluate the time and cost of developing prompts using large language model (LLM), tailored to extract clinical factors in breast cancer patients and their accuracy. MATERIALS AND METHODS: We collected data from reports of surgical pathology and ultrasound from breast cancer patients who underwent radiotherapy from 2020 to 2022. We extracted the information using the Generative Pre-trained Transformer (GPT) for Sheets and Docs extension plugin and termed this the "LLM" method. The time and cost of developing the prompts with LLM methods were assessed and compared with those spent on collecting information with "full manual" and "LLM-assisted manual" methods. To assess accuracy, 340 patients were randomly selected, and the extracted information by LLM method were compared with those collected by "full manual" method. RESULTS: Data from 2,931 patients were collected. We developed 12 prompts for Extract function and 12 for Format function to extract and standardize the information. The overall accuracy was 87.7%. For lymphovascular invasion, it was 98.2%. Developing and processing the prompts took 3.5 hours and 15 minutes, respectively. Utilizing the ChatGPT application programming interface cost US $65.8 and when factoring in the estimated wage, the total cost was US $95.4. In an estimated comparison, "LLM-assisted manual" and "LLM" methods were time- and cost-efficient compared to the "full manual" method. CONCLUSION: Developing and facilitating prompts for LLM to derive clinical factors was efficient to extract crucial information from huge medical records. This study demonstrated the potential of the application of natural language processing using LLM model in breast cancer patients. Prompts from the current study can be re-used for other research to collect clinical information.

Development and benchmarking of a Korean audio speech recognition model for Clinician-Patient conversations in radiation oncology clinics.

BACKGROUND: The purpose of this study is to develop an audio speech recognition (ASR) deep learning model for transcribing clinician-patient conversations in radiation oncology clinics. METHODS: We finetuned the pre-trained English QuartzNet 15x5 model for the Korean language using a publicly available dataset of simulated situations between clinicians and patients. Subsequently, real conversations between a radiation oncologist and 115 patients in actual clinics were then prospectively collected, transcribed, and divided into training (30.26 h) and testing (0.79 h) sets. These datasets were used to develop the ASR model for clinics, which was benchmarked against other ASR models, including the 'Whisper large,' the 'Riva Citrinet-1024 Korean model,' and the 'Riva Conformer Korean model.' RESULTS: The pre-trained English ASR model was successfully fine-tuned and converted to recognize the Korean language, resulting in a character error rate (CER) of 0.17. However, we found that this performance was not sustained on the real conversation dataset. To address this, we further fine-tuned the model, resulting in an improved CER of 0.26. Other developed ASR models, including 'Whisper large,' the 'Riva Citrinet-1024 Korean model,' and the 'Riva Conformer Korean model.', showed a CER of 0.31, 0.28, and 0.25, respectively. On the general Korean conversation dataset, 'zeroth-korean,' our model showed a CER of 0.44, while the 'Whisper large,' the 'Riva Citrinet-1024 Korean model,' and the 'Riva Conformer Korean model' resulted in CERs of 0.26, 0.98, and 0.99, respectively. CONCLUSION: In conclusion, we developed a Korean ASR model to transcribe real conversations between a radiation oncologist and patients. The performance of the model was deemed acceptable for both specific and general purposes, compared to other models. We anticipate that this model will reduce the time required for clinicians to document the patient's chief complaints or side effects.

Genomic landscape of locally advanced rectal adenocarcinoma: Comparison between before and after neoadjuvant chemoradiation and effects of genetic biomarkers on clinical outcomes and tumor response.

PURPOSE: To explore genomic biomarkers in rectal cancer by performing whole-exome sequencing. MATERIALS AND METHODS: Pre-chemoradiation (CRT) biopsy and post-CRT surgical specimens were obtained from 27 patients undergoing neoadjuvant CRT followed by definitive resection. Exomes were sequenced to a mean coverage of 30×. Somatic single-nucleotide variants (SNVs) and insertions/deletions (indels) were identified. Tumor mutational burden was defined as the number of SNVs or indels. Mutational signatures were extracted and fitted to COSMIC reference signatures. Tumor heterogeneity was quantified with a mutant-allele tumor heterogeneity (MATH) score. Genetic biomarkers and frequently occurred copy number alterations (CNAs) were compared between pre- and post-CRT specimens. Their associations with tumor regression grade (TRG) and clinical outcomes were explored. RESULTS: Top five mutated genes were APC, TP53, NF1, KRAS, and NOTCH1 for pre-CRT samples and APC, TP53, NF1, CREBBP, and ATM for post-CRT samples. Several gene mutations including RUNX1, EGFR, and TP53 in pre-CRT samples showed significant association with clinical outcomes, but not with TRG. However, no such association was found in post-CRT samples. Discordance of driver mutation status was found between pre- and post-CRT samples. In tumor mutational burden analysis, higher number of SNVs or indels was associated with worse treatment outcomes. Six single-base substitution (SBS) signatures identified were SBS1, SBS30, SBS29, SBS49, SBS3, and SBS44. The MATH score decreased after CRT on paired analysis. Less than half of CNAs frequent in post-CRT samples were present in pre-CRT samples. CONCLUSION: Pre- and post-CRT samples showed different genomic landscape. Potential genetic biomarkers of pre-CRT samples found in the current analysis call for external validation.

A Survey of Practice Patterns for Clinical Nodal Staging Prior to Neoadjuvant Chemotherapy in Breast Cancer.

BACKGROUND: The importance of clinical staging in breast cancer has increased owing to the wide use of neoadjuvant systemic therapy (NST). This study aimed to investigate the current practice patterns regarding clinical nodal staging in breast cancer in real-world settings. MATERIALS AND METHODS: A web-based survey was administered to board-certified oncologists in Korea, including breast surgical, medical, and radiation oncologists, from January to April 2022. The survey included 19 general questions and 4 case-based questions. RESULTS: In total, 122 oncologists (45 radiation, 44 surgical, and 33 medical oncologists) completed the survey. Among them, 108 (88%) responded that clinical staging before NST was primarily performed by breast surgeons. All the respondents referred to imaging studies during nodal staging. Overall, 64 (52.5%) responders determined the stage strictly based on the radiology reports, whereas 58 (47.5%) made their own decision while noting radiology reports. Of those who made their own decisions, 88% referred to the number or size of the suspicious node. Of the 75 respondents involved in prescribing regimens for neoadjuvant chemotherapy, 58 (77.3%) responded that the reimbursement regulations in the selection of NST regimens affected nodal staging in clinical practice. In the case-based questions, high variability was observed among the clinicians in the same cases. CONCLUSIONS: Diverse assessments by specialists owing to the lack of a clear, harmonized staging system for the clinical nodal staging of breast cancer can lead to diverse practice patterns. Thus, practical, harmonized, and objective methods for clinical nodal staging and for the outcomes of post-NST response are warranted for appropriate treatment decisions and accurate outcome evaluation.

Evaluation of initial patient setup methods for breast cancer between surface-guided radiation therapy and laser alignment based on skin marking in the Halcyon system.

BACKGROUND: This study was conducted to evaluate the efficiency and accuracy of the daily patient setup for breast cancer patients by applying surface-guided radiation therapy (SGRT) using the Halcyon system instead of conventional laser alignment based on the skin marking method. METHODS AND MATERIALS: We retrospectively investigated 228 treatment fractions using two different initial patient setup methods. The accuracy of the residual rotational error of the SGRT system was evaluated by using an in-house breast phantom. The residual translational error was analyzed using the couch position difference in the vertical, longitudinal, and lateral directions between the reference computed tomography and daily kilo-voltage cone beam computed tomography acquired from the record and verification system. The residual rotational error (pitch, yaw, and roll) was also calculated using an auto rigid registration between the two images based on Velocity. The total setup time, which combined the initial setup time and imaging time, was analyzed to evaluate the efficiency of the daily patient setup for SGRT. RESULTS: The average residual rotational errors using the in-house fabricated breast phantom for pitch, roll, and yaw were 0.14°, 0.13°, and 0.29°, respectively. The average differences in the couch positions for laser alignment based on the skin marking method were 2.7 ± 1.6 mm, 2.0 ± 1.2 mm, and 2.1 ± 1.0 mm for the vertical, longitudinal, and lateral directions, respectively. For SGRT, the average differences in the couch positions were 1.9 ± 1.2 mm, 2.9 ± 2.1 mm, and 1.9 ± 0.7 mm for the vertical, longitudinal, and lateral directions, respectively. The rotational errors for pitch, yaw, and roll without the surface-guided radiation therapy approach were 0.32 ± 0.30°, 0.51 ± 0.24°, and 0.29 ± 0.22°, respectively. For SGRT, the rotational errors were 0.30 ± 0.22°, 0.51 ± 0.26°, and 0.19 ± 0.13°, respectively. The average total setup times considering both the initial setup time and imaging time were 314 s and 331 s, respectively, with and without SGRT. CONCLUSION: We demonstrated that using SGRT improves the accuracy and efficiency of initial patient setups in breast cancer patients using the Halcyon system, which has limitations in correcting the rotational offset.

Radiosensitivity is associated with antitumor immunity in estrogen receptor-negative breast cancer.

PURPOSE: This study evaluated radiosensitivity and the tumor microenvironment (TME) to identify characteristics of breast cancer patients who would benefit most from radiation therapy. METHODS: We analyzed 1903 records from the Molecular Taxonomy of Breast Cancer International Consortium cohort using the radiosensitivity index and gene expression deconvolution algorithms, CIBERSORT and xCell, that estimates the TME composition of tumor samples. In this study, patients were stratified according to TME and radiosensitivity. We performed integrative analyses of clinical and immuno-genomic data to characterize molecular features associated with radiosensitivity. RESULTS: Radiosensitivity was significantly associated with activation of antitumor immunity. In contrast, radioresistance was associated with a reactive stromal microenvironment. The immuno-genomic analysis revealed that estrogen receptor (ER) pathway activity was correlated with suppression of antitumor immunity. In ER-negative disease, the best prognosis was shown in the immune-high and radiosensitive group patients, and the lowest was in the immune-low and radioresistant group patients. In ER-positive disease, immune signature and radiosensitivity had no prognostic significance. CONCLUSION: Taken together, these results suggest that tumor radiosensitivity is associated with activation of antitumor immunity and a better prognosis, particularly in patients with ER-negative breast cancer.

Protocol for the postoperative radiotherapy in N1 breast cancer patients (PORT-N1) trial, a prospective multicenter, randomized, controlled, non-inferiority trial of patients receiving breast-conserving surgery or mastectomy.

BACKGROUND: Postoperative radiotherapy (PORT) could be useful for pN1 breast cancer patients who have undergone breast-conserving surgery (BCS) or mastectomy. However, the value of regional nodal irradiation (RNI) for BCS patients, and the indications for post-mastectomy radiotherapy (PMRT) for pN1 breast cancer mastectomy patients, have recently been challenged due to the absence of relevant trials in the era of modern systemic therapy. "PORT de-escalation" should be assessed in patients with pN1 breast cancer. METHODS: The PORT-N1 trial is a multicenter, randomized, phase 3 clinical trial for patients with pN1 breast cancer that compares the outcomes of control [whole-breast irradiation (WBI) and RNI/PMRT] and experimental (WBI alone/no PMRT) groups. PORT-N1 aims to demonstrate non-inferiority of the experimental group by comparing 7-year disease-free survival rates with the control group. Female breast cancer patients with pT1-3 N1 status after BCS or mastectomy are eligible. Participants will be randomly assigned to the two groups in a 1:1 ratio. Randomization will be stratified by surgery type (BCS vs. mastectomy) and histologic subtype (triple-negative vs. non-triple-negative). In patients who receive mastectomy, dissection of ≥5 nodes is required when there is one positive node, and axillary lymph node dissection when there are two or three positive nodes. Patients receiving neoadjuvant chemotherapy are not eligible. RNI includes a "high-tangent" or wider irradiation field. This study will aim to recruit 1106 patients. DISCUSSION: The PORT-N1 trial aims to verify that PORT de-escalation after BCS or mastectomy is safe for pN1 breast cancer patients in terms of oncologic outcomes and capable of reducing toxicity rates. This trial will provide information crucial for designing PORT de-escalation strategies for patients with pN1 breast cancer. TRIAL REGISTRATION: This trial was registered at ClinicalTrials.gov (NCT05440149) on June 30, 2022.

Volumetric changes in gray matter after radiotherapy detected with longitudinal magnetic resonance imaging in glioma patients.

BACKGROUND AND PURPOSE: We evaluated volumetric changes in the gray matter (GM) after radiotherapy (RT) and identified factors that were strongly associated with GM volume reduction. MATERIALS AND METHODS: A total of 461 magnetic resonance imagings (MRI) from 105 glioma patients treated with postoperative RT was retrospectively analyzed. Study patients' MRIs were collected at five time points: before RT and 1 month, 6 months, 1 year, and 2 years after RT. Using the 'FastSurfer' platform, a deep learning-based neuroimaging pipeline, 73 regions were automatically segmented from longitudinal MRIs and their volumetric changes were calculated. Regions were grouped into 10 functional fields. A multivariable linear mixed-effects model was established to identify the potential predictors of significant volume reduction. RESULTS: The median age was 50 years (range, 16-86 years). Forty-seven (44.8 %) patients were female and 68 (64.8 %) had glioblastoma. Postoperative RT was delivered at 54-60 Gy with or without concurrent chemotherapy. At 2 years after RT, the median volumetric changes in the overall, ipsilateral, and contralateral GM were -3.5%, -4.5%, and -2.4%, respectively. The functional fields of cognition and execution of movement showed the greatest volume reductions. In the multivariable linear mixed model, female sex (normalized coefficient = -0.14, P < 0.001) and the interaction between age at RT and days after RT (normalized coefficient = -6.48e-6, P < 0.001) were significantly associated with GM reduction. The older patients received RT, the greater volume reduction was seen over time. However, in patients with relatively younger age (e.g., 45, 50, and 60 years for hippocampus, Broca area, and Wernicke area, respectively), the volume was not significantly reduced. CONCLUSIONS: GM volume reduction was identified after RT that could lead to long-term treatment sequelae. Particularly for susceptible patients, individualized treatment and prevention strategies are needed.

Exploration of biomedical knowledge for recurrent glioblastoma using natural language processing deep learning models.

BACKGROUND: Efficient exploration of knowledge for the treatment of recurrent glioblastoma (GBM) is critical for both clinicians and researchers. However, due to the large number of clinical trials and published articles, searching for this knowledge is very labor-intensive. In the current study, using natural language processing (NLP), we analyzed medical research corpora related to recurrent glioblastoma to find potential targets and treatments. METHODS: We fine-tuned the 'SAPBERT', which was pretrained on biomedical ontologies, to perform question/answering (QA) and name entity recognition (NER) tasks for medical corpora. The model was fine-tuned with the SQUAD2 dataset and multiple NER datasets designed for QA task and NER task, respectively. Corpora were collected by searching the terms "recurrent glioblastoma" and "drug target", published from 2000 to 2020 in the Web of science (N = 288 articles). Also, clinical trial corpora were collected from 'clinicaltrial.gov' using the searching term of 'recurrent glioblastoma" (N = 587 studies). RESULTS: For the QA task, the model showed an F1 score of 0.79. For the NER task, the model showed F1 scores of 0.90 and 0.76 for drug and gene name recognition, respectively. When asked what the molecular targets were promising for recurrent glioblastoma, the model answered that RTK inhibitors or LPA-1 antagonists were promising. From collected clinical trials, the model summarized them in the order of bevacizumab, temozolomide, lomustine, and nivolumab. Based on published articles, the model found the many drug-gene pairs with the NER task, and we presented them with a circus plot and related summarization ( https://github.com/bigwiz83/NLP_rGBM ). CONCLUSION: Using NLP deep learning models, we could explore potential targets and treatments based on medical research and clinical trial corpora. The knowledge found by the models may be used for treating recurrent glioblastoma.