Principles of artificial intelligence in radiooncology.

PURPOSE: In the rapidly expanding field of artificial intelligence (AI) there is a wealth of literature detailing the myriad applications of AI, particularly in the realm of deep learning. However, a review that elucidates the technical principles of deep learning as relevant to radiation oncology in an easily understandable manner is still notably lacking. This paper aims to fill this gap by providing a comprehensive guide to the principles of deep learning that is specifically tailored toward radiation oncology. METHODS: In light of the extensive variety of AI methodologies, this review selectively concentrates on the specific domain of deep learning. It emphasizes the principal categories of deep learning models and delineates the methodologies for training these models effectively. RESULTS: This review initially delineates the distinctions between AI and deep learning as well as between supervised and unsupervised learning. Subsequently, it elucidates the fundamental principles of major deep learning models, encompassing multilayer perceptrons (MLPs), convolutional neural networks (CNNs), recurrent neural networks (RNNs), transformers, generative adversarial networks (GANs), diffusion-based generative models, and reinforcement learning. For each category, it presents representative networks alongside their specific applications in radiation oncology. Moreover, the review outlines critical factors essential for training deep learning models, such as data preprocessing, loss functions, optimizers, and other pivotal training parameters including learning rate and batch size. CONCLUSION: This review provides a comprehensive overview of deep learning principles tailored toward radiation oncology. It aims to enhance the understanding of AI-based research and software applications, thereby bridging the gap between complex technological concepts and clinical practice in radiation oncology.

Discovery of novel macrocyclic derivatives as potent and selective cyclin-dependent kinase 2 inhibitors.

Cyclin-dependent kinase 2 (CDK2) is a member of CDK family of kinases (CDKs) that regulate the cell cycle. Its inopportune or over-activation leads to uncontrolled cell cycle progression and drives numerous types of cancers, especially ovarian, uterine, gastric cancer, as well as those associated with amplified CCNE1 gene. However, developing selective lead compound as CDK2 inhibitors remains challenging owing to similarities in the ATP pockets among different CDKs. Herein, we described the optimization of compound 1, a novel macrocyclic inhibitor targeting CDK2/5/7/9, aiming to discover more selective and metabolically stable lead compound as CDK2 inhibitor. Molecular dynamic (MD) simulations were performed for compound 1 and 9 to gain insights into the improved selectivity against CDK5. Further optimization efforts led to compound 22, exhibiting excellent CDK2 inhibitory activity, good selectivity over other CDKs and potent cellular effects. Based on these characterizations, we propose that compound 22 holds great promise as a potential lead candidate for drug development.

System analysis based on Anoikis-related genes identifies MAPK1 as a novel therapy target for osteosarcoma with neoadjuvant chemotherapy.

BACKGROUND: Osteosarcoma (OS) is the most common bone malignant tumor in children, and its prognosis is often poor. Anoikis is a unique mode of cell death.However, the effects of Anoikis in OS remain unexplored. METHOD: Differential analysis of Anoikis-related genes was performed based on the metastatic and non-metastatic groups. Then LASSO logistic regression and SVM-RFE algorithms were applied to screen out the characteristic genes. Later, Univariate and multivariate Cox regression was conducted to identify prognostic genes and further develop the Anoikis-based risk score. In addition, correlation analysis was performed to analyze the relationship between tumor microenvironment, drug sensitivity, and prognostic models. RESULTS: We established novel Anoikis-related subgroups and developed a prognostic model based on three Anoikis-related genes (MAPK1, MYC, and EDIL3). The survival and ROC analysis results showed that the prognostic model was reliable. Besides, the results of single-cell sequencing analysis suggested that the three prognostic genes were closely related to immune cell infiltration. Subsequently, aberrant expression of two prognostic genes was identified in osteosarcoma cells. Nilotinib can promote the apoptosis of osteosarcoma cells and down-regulate the expression of MAPK1. CONCLUSIONS: We developed a novel Anoikis-related risk score model, which can assist clinicians in evaluating the prognosis of osteosarcoma patients in clinical practice. Analysis of the tumor immune microenvironment and chemotherapeutic drug sensitivity can provide necessary insights into subsequent mechanisms. MAPK1 may be a valuable therapeutic target for neoadjuvant chemotherapy in osteosarcoma.

Calibration by differentiation - Self-supervised calibration for X-ray microscopy using a differentiable cone-beam reconstruction operator.

High-resolution X-ray microscopy (XRM) is gaining interest for biological investigations of extremely small-scale structures. XRM imaging of bones in living mice could provide new insights into the emergence and treatment of osteoporosis by observing osteocyte lacunae, which are holes in the bone of few micrometres in size. Imaging living animals at that resolution, however, is extremely challenging and requires very sophisticated data processing converting the raw XRM detector output into reconstructed images. This paper presents an open-source, differentiable reconstruction pipeline for XRM data which analytically computes the final image from the raw measurements. In contrast to most proprietary reconstruction software, it offers the user full control over each processing step and, additionally, makes the entire pipeline deep learning compatible by ensuring differentiability. This allows fitting trainable modules both before and after the actual reconstruction step in a purely data-driven way using the gradient-based optimizers of common deep learning frameworks. The value of such differentiability is demonstrated by calibrating the parameters of a simple cupping correction module operating on the raw projection images using only a self-supervisory quality metric based on the reconstructed volume and no further calibration measurements. The retrospective calibration directly improves image quality as it avoids cupping artefacts and decreases the difference in grey values between outer and inner bone by 68-94%. Furthermore, it makes the reconstruction process entirely independent of the XRM manufacturer and paves the way to explore modern deep learning reconstruction methods for arbitrary XRM and, potentially, other flat-panel computed tomography systems. This exemplifies how differentiable reconstruction can be leveraged in the context of XRM and, hence, is an important step towards the goal of reducing the resolution limit of in vivo bone imaging to the single micrometre domain.

Effect of benzo[a]pyrene on proliferation and metastasis of oral squamous cell carcinoma cells: A transcriptome analysis based on RNA-seq.

Benzo[a]pyrene (BaP), a representative polycyclic aromatic hydrocarbon compound, is a carcinogen that causes head and neck cancers. Despite intensive research, the molecular mechanism of BaP in the development of oral squamous cell carcinoma (OSCC) remains largely unknown. In the present study, the SCC-9 human OSCC cell line was cultured in vitro, separated into treatment groups, and treated with dimethyl sulfoxide or BaP at various concentrations. The malignant behavior ascribed to the BaP treatment was investigated by cell proliferation, clony formation assay, and Transwell assays. Furthermore, transcriptome sequencing was performed to detect the differentially expressed genes, followed by quantitative real-time PCR to measure the expression levels of nine of these genes. Moreover, the Gene Ontology (GO) term and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analyses showed the biological processes and signaling pathways in which the target genes were involved. Significant effects on SCC-9 cell proliferation, tumorigenicity, cell migration, and invasion were observed after exposure to 8 µM BaP. Additional results revealed that BaP inhibited apoptosis in a dose-dependent manner. The transcriptome sequencing results showed 137 upregulated genes and 135 downregulated genes induced by BaP, associated with tumor-related biological processes and signaling pathways, mainly including transcriptional dysregulation in cancer, the tumor necrosis factor signaling pathway, metabolism of xenobiotics by cytochrome P450, mitogen-activated protein kinase signaling pathway, and so forth. Our study demonstrates that BaP may regulate the expression of certain genes involved in tumor-associated signaling pathways, thereby promoting the proliferative, tumorigenic, and metastatic behaviors of OSCC cells while suppressing their apoptosis.

Limited angle tomography for transmission X-ray microscopy using deep learning.

In transmission X-ray microscopy (TXM) systems, the rotation of a scanned sample might be restricted to a limited angular range to avoid collision with other system parts or high attenuation at certain tilting angles. Image reconstruction from such limited angle data suffers from artifacts because of missing data. In this work, deep learning is applied to limited angle reconstruction in TXMs for the first time. With the challenge to obtain sufficient real data for training, training a deep neural network from synthetic data is investigated. In particular, U-Net, the state-of-the-art neural network in biomedical imaging, is trained from synthetic ellipsoid data and multi-category data to reduce artifacts in filtered back-projection (FBP) reconstruction images. The proposed method is evaluated on synthetic data and real scanned chlorella data in 100° limited angle tomography. For synthetic test data, U-Net significantly reduces the root-mean-square error (RMSE) from 2.55 × 10-3 µm-1 in the FBP reconstruction to 1.21 × 10-3 µm-1 in the U-Net reconstruction and also improves the structural similarity (SSIM) index from 0.625 to 0.920. With penalized weighted least-square denoising of measured projections, the RMSE and SSIM are further improved to 1.16 × 10-3 µm-1 and 0.932, respectively. For real test data, the proposed method remarkably improves the 3D visualization of the subcellular structures in the chlorella cell, which indicates its important value for nanoscale imaging in biology, nanoscience and materials science.

Flexible thin broadband microwave absorber based on a pyramidal periodic structure of lossy composite.

Microwave absorber with broadband absorption and thin thickness is one of the main research interests in this field. A flexible ultrathin and broadband microwave absorber comprising multiwall carbon nanotubes, spherical carbonyl iron, and silicone rubber is fabricated in a newly proposed pyramidal spatial periodic structure (SPS). The SPS with equivalent thickness of 3.73 mm covers the -10 dB and -15 dB absorption bandwidth in the frequency range 2-40 GHz and 10-40 GHz, respectively. The excellent absorption performance is achieved by concentration and dissipation of the electromagnetic field inside different parts of the magnetic-dielectric lossy protrusions in different frequency ranges.

In vivo long-term investigation of tumor bearing mKate2 by an in-house fluorescence molecular imaging system.

BACKGROUND: Optical imaging is one of the most common, low-cost imaging tools used for investigating the tumor biological behavior in vivo. This study explores the feasibility and sensitivity of a near infrared fluorescent protein mKate2 for a long-term non-invasive tumor imaging in BALB/c nude mice, by using a low-power optical imaging system. METHODS: In this study, breast cancer cell line MDA-MB-435s expressing mKate2 and MDA-MB-231 expressing a dual reporter gene firefly luciferase (fLuc)-GFP were used as cell models. Tumor cells were implanted in different animal body compartments including subcutaneous, abdominal and deep tissue area and closely monitored in real-time. A simple and low-power optical imaging system was set up to image both fluorescence and bioluminescence in live animals. RESULTS: The presence of malignant tissue was further confirmed by histopathological assay. Considering its lower exposure time and no need of substrate injection, mKate2 is considered a superior choice for subcutaneous imaging compared with fLuc. On the contrary, fLuc has shown to be a better option when monitoring the tumor in a diffusive area such as abdominal cavity. Furthermore, both reporter genes have shown good stability and sensitivity for deep tissue imaging, i.e. tumor within the liver. In addition, fLuc has shown to be an excellent method for detecting tumor cells in the lung. CONCLUSIONS: The combination of mKate2 and fLuc offers a superior choice for long-term non-invasive real-time investigation of tumor biological behavior in vivo.

The Comparison of Hydrochloric Acid and Phosphoric Acid Treatments in the Preparation of Montmorillonite Catalysts for RNA Synthesis.

The treatment of clay minerals with a preliminary acid wash and titration to pH 7 has proven to generate catalysts for the most interesting of oligomerization reactions in which activated RNA-nucleotides generate oligomers up to 40-mers. Significantly, not all clay minerals become catalytic following this treatment and none are catalytic in the absence of such treatment. The washing procedure has been modified and explored further using phosphoric acid and the outcomes are compared to those obtained when clay samples are prepared following a hydrochloric acid wash.

Comparison of Pediatric Forearm Fracture Fixation Between Single- and Double-Elastic Stable Intramedullary Nailing.

The purpose of this study was to evaluate and compare the outcome of single- and double-elastic stable intramedullary nailing (ESIN) for the treatment of pediatric both-bone forearm fractures. We retrospectively analyzed 49 children with both-bone forearm fractures treated with ESIN. Twenty-four patients were treated with single-ESIN (S-ESIN) to fixate the radius only, and the other 25 patients were treated with double-ESIN (D-ESIN) to fixate the radius and ulna. The duration of surgery, times of fluoroscopy, cost of hospitalization, period of castoff, union time, radiographic outcomes, clinical results, and postoperative complications were compared. The duration of surgery, times of fluoroscopy, and cost of hospitalization were significantly lower in the S-ESIN group; however, the average period of castoff was longer in the S-ESIN group. The incidence of delayed union of the ulna was significantly higher in the D-ESIN than in the S-ESIN group. Although the mean angulation deformity of the ulna in the S-ESIN group was significantly larger than in the D-ESIN group, both of them were acceptable (<10 degrees). Despite this, there was no difference in the loss of forearm motion and complication rates between the 2 groups. In conclusion, our data suggest that S-ESIN to fixate the radius alone remains an equally effective fixation method in the pediatric population compared with both-bone fixation and is our treatment of choice.

A New Method for Cone-Beam Computed Tomography Geometric Parameters Estimation.

This work demonstrates a new approach for geometric parameters estimation of cone-beam computed tomography system from the coordinates of the centroids of 2 projected point sources sampled over 360 degrees. Nonlinear object expression was derived for the coordinates of the centroids in terms of the geometric parameters after a slice of reasonable simplification, which aims to improve the convergence and robustness of the nonlinear object expression. All of the geometric parameters could be precisely estimated from the nonlinear object expression using the annealing algorithm. The simulations and experiments indicate more excellent convergence, robustness, and precision of our approach compared with other methods. Furthermore, our approach is insensitive to the initial value; namely, we do not need to set the value close to the true value to guarantee the convergence of the approach.

Percutaneous posterior transdiscal oblique screw fixation with lateral interbody fusion: a radiological and cadaveric study.

PURPOSE: To design and investigate a novel technique of percutaneous posterior transdiscal oblique screw fixation with lateral interbody fusion. METHODS: CT scans of 45 patients were collected and imported into Mimics software for three-dimensional (3D) reconstruction. Cylinders were drawn to simulate the trajectory of the oblique screw. Six measurements were obtained for each unit to design a right size cage: a the distance between the intersection of the simulated trajectory of the screw with the inferior border of the upper vertebra and its anteroinferior corner; b the distance between the intersection of the simulated trajectory of the screw with the superior border of the inferior vertebra and its anterosuperior corner; h the height of the intervertebral space; θ the angle between simulated trajectory of screw and the upper endplate of inferior vertebra; uw: the width of the inferior endplate of upper vertebra; iw: the width of upper endplate of inferior vertebra. Three intact adult fresh-frozen cadaveric specimens were obtained, percutaneous posterior transdiscal oblique screw fixation was performed under X-ray apparatus, and interbody cage was implanted by assistance with special self-retaining retractor system and endoscope. RESULTS: According to the results of data measured from 3D images, trapezoid shape interbody cages with suitable size were designed. Percutaneous posterior oblique screw fixation with lateral interbody fusion was performed on three cadaveric specimens successfully. CONCLUSION: Using specially designed trapezoid shape interbody cages, assisted by intra-operative image intensification and endoscope, it is feasible to perform percutaneous posterior transdiscal oblique screw fixation with lateral interbody fusion technique.

Two-view topogram-based anatomy-guided CT reconstruction for prospective risk minimization.

To facilitate a prospective estimation of the effective dose of an CT scan prior to the actual scanning in order to use sophisticated patient risk minimizing methods, a prospective spatial dose estimation and the known anatomical structures are required. To this end, a CT reconstruction method is required to reconstruct CT volumes from as few projections as possible, i.e. by using the topograms, with anatomical structures as correct as possible. In this work, an optimized CT reconstruction model based on a generative adversarial network (GAN) is proposed. The GAN is trained to reconstruct 3D volumes from an anterior-posterior and a lateral CT projection. To enhance anatomical structures, a pre-trained organ segmentation network and the 3D perceptual loss are applied during the training phase, so that the model can then generate both organ-enhanced CT volume and organ segmentation masks. The proposed method can reconstruct CT volumes with PSNR of 26.49, RMSE of 196.17, and SSIM of 0.64, compared to 26.21, 201.55 and 0.63 using the baseline method. In terms of the anatomical structure, the proposed method effectively enhances the organ shapes and boundaries and allows for a straight-forward identification of the relevant anatomical structures. We note that conventional reconstruction metrics fail to indicate the enhancement of anatomical structures. In addition to such metrics, the evaluation is expanded with assessing the organ segmentation performance. The average organ dice of the proposed method is 0.71 compared with 0.63 for the baseline model, indicating the enhancement of anatomical structures.

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.

Multicenter privacy-preserving model training for deep learning brain metastases autosegmentation.

OBJECTIVES: This work aims to explore the impact of multicenter data heterogeneity on deep learning brain metastases (BM) autosegmentation performance, and assess the efficacy of an incremental transfer learning technique, namely learning without forgetting (LWF), to improve model generalizability without sharing raw data. MATERIALS AND METHODS: A total of six BM datasets from University Hospital Erlangen (UKER), University Hospital Zurich (USZ), Stanford, UCSF, New York University (NYU), and BraTS Challenge 2023 were used. First, the performance of the DeepMedic network for BM autosegmentation was established for exclusive single-center training and mixed multicenter training, respectively. Subsequently privacy-preserving bilateral collaboration was evaluated, where a pretrained model is shared to another center for further training using transfer learning (TL) either with or without LWF. RESULTS: For single-center training, average F1 scores of BM detection range from 0.625 (NYU) to 0.876 (UKER) on respective single-center test data. Mixed multicenter training notably improves F1 scores at Stanford and NYU, with negligible improvement at other centers. When the UKER pretrained model is applied to USZ, LWF achieves a higher average F1 score (0.839) than naive TL (0.570) and single-center training (0.688) on combined UKER and USZ test data. Naive TL improves sensitivity and contouring accuracy, but compromises precision. Conversely, LWF demonstrates commendable sensitivity, precision and contouring accuracy. When applied to Stanford, similar performance was observed. CONCLUSION: Data heterogeneity (e.g., variations in metastases density, spatial distribution, and image spatial resolution across centers) results in varying performance in BM autosegmentation, posing challenges to model generalizability. LWF is a promising approach to peer-to-peer privacy-preserving model training.

A real-world disproportionality analysis of the FDA adverse event reporting system events for ibuprofen.

INTRODUCTION: Ibuprofen is commonly used as an over-the-counter (OTC) antipyretic and analgesic. As the frequency of its use has increased, there has been a corresponding increase in reports of associated adverse events (AEs). However, these events have not been systematically reported in the literature. Meanwhile, the importance of effective pharmacovigilance in evaluating the benefits and risks of drugs is being recognized. METHODS: The data was obtained indirectly from FAERS using the OpenVigil 2 database, lexically mapped using software such as MySQL, Microsoft Excel, and the R language, and then subjected to four more rigorous algorithms to detect risk signals associated with ibuprofen AEs. RESULTS: By analyzing data from the past 18 years, 878 ibuprofen-related AEs were identified as primary AEs. Notably, unexpected reproductive system and breast diseases, etc., which were unexpected, were observed as important system organ classes (SOCs) associated with ibuprofen. Among the 651 preferred terms (PTs) that simultaneously satisfy the four arithmetic methods, renal tubular acidosis and lip oedema are proposed as new signals for ibuprofen AEs. CONCLUSION: This study explores the important and valuable potential AEs and ADRs of ibuprofen at the SOC and PT levels, respectively. To provide a reference on decision-making for ibuprofen to promote rational clinical dosing.

Metformin adverse event profile: a pharmacovigilance study based on the FDA Adverse Event Reporting System (FAERS) from 2004 to 2022.

BACKGROUND: Metformin has the potential for treating numerous diseases, but there are still many unrecognized and unreported adverse events (AEs). METHODS: We selected data from the United States FDA Adverse Event Reporting System (FAERS) database from the first quarter (Q1) of 2004 to the fourth quarter (Q4) of 2022 for disproportionality analysis to assess the association between metformin and related adverse events. RESULTS: In this study 10,500,295 case reports were collected from the FAERS database, of which 56,674 adverse events related to metformin were reported. A total of 643 preferred terms (PTs) and 27 system organ classes (SOCs) that were significant disproportionality conforming to the four algorithms simultaneously were included. The SOCs included metabolic and nutritional disorders (p = 0.00E + 00), gastrointestinal disorders (p = 0.00E + 00) and others. PT levels were screened for adverse drug reaction (ADR) signals such as acute pancreatitis (p = 0.00E + 00), melas syndrome, pemphigoid (p = 0.00E + 00), skin eruption (p = 0.00E + 00) and drug exposure during pregnancy (p = 0.00E + 00). CONCLUSION: Most of our results were consistent with the specification, but some new signals of adverse reactions such as acute pancreatitis were not included. Therefore, further studies are needed to validate unlabeled adverse reactions and provide important support for clinical monitoring and risk identification of metformin.

PRL1 and PRL3 promote macropinocytosis via its lipid phosphatase activity.

PRL1 and PRL3, members of the protein tyrosine phosphatase family, have been associated with cancer metastasis and poor prognosis. Despite extensive research on their protein phosphatase activity, their potential role as lipid phosphatases remains elusive. Methods: We conducted comprehensive investigations to elucidate the lipid phosphatase activity of PRL1 and PRL3 using a combination of cellular assays, biochemical analyses, and protein interactome profiling. Functional studies were performed to delineate the impact of PRL1/3 on macropinocytosis and its implications in cancer biology. Results: Our study has identified PRL1 and PRL3 as lipid phosphatases that interact with phosphoinositide (PIP) lipids, converting PI(3,4)P2 and PI(3,5)P2 into PI(3)P on the cellular membranes. These enzymatic activities of PRLs promote the formation of membrane ruffles, membrane blebbing and subsequent macropinocytosis, facilitating nutrient extraction, cell migration, and invasion, thereby contributing to tumor development. These enzymatic activities of PRLs promote the formation of membrane ruffles, membrane blebbing and subsequent macropinocytosis. Additionally, we found a correlation between PRL1/3 expression and glioma development, suggesting their involvement in glioma progression. Conclusions: Combining with the knowledge that PRLs have been identified to be involved in mTOR, EGFR and autophagy, here we concluded the physiological role of PRL1/3 in orchestrating the nutrient sensing, absorbing and recycling via regulating macropinocytosis through its lipid phosphatase activity. This mechanism could be exploited by tumor cells facing a nutrient-depleted microenvironment, highlighting the potential therapeutic significance of targeting PRL1/3-mediated macropinocytosis in cancer treatment.

Comprehensive multimodal deep learning survival prediction enabled by a transformer architecture: A multicenter study in glioblastoma.

Background: This research aims to improve glioblastoma survival prediction by integrating MR images, clinical, and molecular-pathologic data in a transformer-based deep learning model, addressing data heterogeneity and performance generalizability. Methods: We propose and evaluate a transformer-based nonlinear and nonproportional survival prediction model. The model employs self-supervised learning techniques to effectively encode the high-dimensional MRI input for integration with nonimaging data using cross-attention. To demonstrate model generalizability, the model is assessed with the time-dependent concordance index (Cdt) in 2 training setups using 3 independent public test sets: UPenn-GBM, UCSF-PDGM, and Rio Hortega University Hospital (RHUH)-GBM, each comprising 378, 366, and 36 cases, respectively. Results: The proposed transformer model achieved a promising performance for imaging as well as nonimaging data, effectively integrating both modalities for enhanced performance (UCSF-PDGM test-set, imaging Cdt 0.578, multimodal Cdt 0.672) while outperforming state-of-the-art late-fusion 3D-CNN-based models. Consistent performance was observed across the 3 independent multicenter test sets with Cdt values of 0.707 (UPenn-GBM, internal test set), 0.672 (UCSF-PDGM, first external test set), and 0.618 (RHUH-GBM, second external test set). The model achieved significant discrimination between patients with favorable and unfavorable survival for all 3 datasets (log-rank P 1.9 × 10-8, 9.7 × 10-3, and 1.2 × 10-2). Comparable results were obtained in the second setup using UCSF-PDGM for training/internal testing and UPenn-GBM and RHUH-GBM for external testing (Cdt 0.670, 0.638, and 0.621). Conclusions: The proposed transformer-based survival prediction model integrates complementary information from diverse input modalities, contributing to improved glioblastoma survival prediction compared to state-of-the-art methods. Consistent performance was observed across institutions supporting model generalizability.

Generating synthetic computed tomography for radiotherapy: SynthRAD2023 challenge report.

Radiation therapy plays a crucial role in cancer treatment, necessitating precise delivery of radiation to tumors while sparing healthy tissues over multiple days. Computed tomography (CT) is integral for treatment planning, offering electron density data crucial for accurate dose calculations. However, accurately representing patient anatomy is challenging, especially in adaptive radiotherapy, where CT is not acquired daily. Magnetic resonance imaging (MRI) provides superior soft-tissue contrast. Still, it lacks electron density information, while cone beam CT (CBCT) lacks direct electron density calibration and is mainly used for patient positioning. Adopting MRI-only or CBCT-based adaptive radiotherapy eliminates the need for CT planning but presents challenges. Synthetic CT (sCT) generation techniques aim to address these challenges by using image synthesis to bridge the gap between MRI, CBCT, and CT. The SynthRAD2023 challenge was organized to compare synthetic CT generation methods using multi-center ground truth data from 1080 patients, divided into two tasks: (1) MRI-to-CT and (2) CBCT-to-CT. The evaluation included image similarity and dose-based metrics from proton and photon plans. The challenge attracted significant participation, with 617 registrations and 22/17 valid submissions for tasks 1/2. Top-performing teams achieved high structural similarity indices (≥0.87/0.90) and gamma pass rates for photon (≥98.1%/99.0%) and proton (≥97.3%/97.0%) plans. However, no significant correlation was found between image similarity metrics and dose accuracy, emphasizing the need for dose evaluation when assessing the clinical applicability of sCT. SynthRAD2023 facilitated the investigation and benchmarking of sCT generation techniques, providing insights for developing MRI-only and CBCT-based adaptive radiotherapy. It showcased the growing capacity of deep learning to produce high-quality sCT, reducing reliance on conventional CT for treatment planning.