Phosphorylation of the histone variant H2AX forms γ-H2AX that marks DNA double-strand break (DSB). Here, we generated the sequencing-based maps of H2AX and γ-H2AX positioning in resting and proliferating cells before and after ionizing irradiation. Genome-wide locations of possible endogenous and exogenous DSBs were identified based on γ-H2AX distribution in dividing cancer cells without irradiation and that in resting cells upon irradiation, respectively. γ-H2AX-enriched regions of endogenous origin in replicating cells included sub-telomeres and active transcription start sites, apparently reflecting replication- and transcription-mediated stress during rapid cell division. Surprisingly, H2AX itself, prior to phosphorylation, was specifically located at these endogenous hotspots. This phenomenon was only observed in dividing cancer cells but not in resting cells. Endogenous H2AX was concentrated on the transcription start site of actively transcribed genes but was irrelevant to pausing of RNA polymerase II (pol II), which precisely coincided with γ-H2AX of endogenous origin. γ-H2AX enrichment upon irradiation also coincided with actively transcribed regions, but unlike endogenous γ-H2AX, it extended into the gene body and was not specifically concentrated on the pausing site of pol II. Sub-telomeres were less responsive to external DNA damage than to endogenous stress. Our findings provide insight into DNA repair programs of cancer and may have implications for cancer therapy.

Target volume contouring for radiation therapy is considered significantly more challenging than the normal organ segmentation tasks as it necessitates the utilization of both image and text-based clinical information. Inspired by the recent advancement of large language models (LLMs) that can facilitate the integration of the textural information and images, here we present an LLM-driven multimodal artificial intelligence (AI), namely LLMSeg, that utilizes the clinical information and is applicable to the challenging task of 3-dimensional context-aware target volume delineation for radiation oncology. We validate our proposed LLMSeg within the context of breast cancer radiotherapy using external validation and data-insufficient environments, which attributes highly conducive to real-world applications. We demonstrate that the proposed multimodal LLMSeg exhibits markedly improved performance compared to conventional unimodal AI models, particularly exhibiting robust generalization performance and data-efficiency.

Background: In breast cancer patients receiving radiotherapy (RT), accurate target delineation and reduction of radiation doses to the nearby normal organs is important. However, manual clinical target volume (CTV) and organs-at-risk (OARs) segmentation for treatment planning increases physicians’ workload and inter-physician variability considerably. In this study, we evaluated the potential benefits of deep learning-based auto-segmented contours by comparing them to manually delineated contours for breast cancer patients. Methods: CTVs for bilateral breasts, regional lymph nodes, and OARs (including the heart, lungs, esophagus, spinal cord, and thyroid) were manually delineated on planning computed tomography scans of 111 breast cancer patients who received breast-conserving surgery. Subsequently, a two-stage convolutional neural network algorithm was used. Quantitative metrics, including the Dice similarity coefficient (DSC) and 95% Hausdorff distance, and qualitative scoring by two panels from 10 institutions were used for analysis. Inter-observer variability and delineation time were assessed; furthermore, dose-volume histograms and dosimetric parameters were also analyzed using another set of patient data. Results: The correlation between the auto-segmented and manual contours was acceptable for OARs, with a mean DSC higher than 0.80 for all OARs. In addition, the CTVs showed favorable results, with mean DSCs higher than 0.70 for all breast and regional lymph node CTVs. Furthermore, qualitative subjective scoring showed that the results were acceptable for all CTVs and OARs, with a median score of at least 8 (possible range: 0–10) for (1) the differences between manual and auto-segmented contours and (2) the extent to which auto-segmentation would assist physicians in clinical practice. The differences in dosimetric parameters between the auto-segmented and manual contours were minimal. Conclusions: The feasibility of deep learning-based auto-segmentation in breast RT planning was demonstrated. Although deep learning-based auto-segmentation cannot be a substitute for radiation oncologists, it is a useful tool with excellent potential in assisting radiation oncologists in the future. Trial registration Retrospectively registered.

Chung K, et al. Radiat Oncol J. 2015 Dec;33(4):337-343. http://dx.doi.org/10.3857/roj.2015.33.4.337