Search

Background: Deep learning–based segmentation algorithms usually required large or multi‐institute data sets to improve the performance and ability of generalization. However, protecting patient privacy is a key concern in the multi‐institutional studies when conventional centralized learning (CL) is used. Purpose: To explores the feasibility of a proposed lesion delineation for stereotactic radiosurgery (SRS) scheme for federated learning (FL), which can solve decentralization and privacy protection concerns. Study Type: Retrospective. Subjects: 506 and 118 vestibular schwannoma patients aged 15–88 and 22–85 from two institutes, respectively; 1069 and 256 meningioma patients aged 12–91 and 23–85, respectively; 574 and 705 brain metastasis patients aged 26–92 and 28–89, respectively. Field Strength/Sequence: 1.5T, spin‐echo, and gradient‐echo [Correction added after first online publication on 21 August 2023. Field Strength has been changed to "1.5T" from "5T" in this sentence.]. Assessment: The proposed lesion delineation method was integrated into an FL framework, and CL models were established as the baseline. The effect of image standardization strategies was also explored. The dice coefficient was used to evaluate the segmentation between the predicted delineation and the ground truth, which was manual delineated by neurosurgeons and a neuroradiologist. Statistical Tests: The paired t‐test was applied to compare the mean for the evaluated dice scores (p < 0.05). Results: FL performed the comparable mean dice coefficient to CL for the testing set of Taipei Veterans General Hospital regardless of standardization and parameter; for the Taichung Veterans General Hospital data, CL significantly (p < 0.05) outperformed FL while using bi‐parameter, but comparable results while using single‐parameter. For the non‐SRS data, FL achieved the comparable applicability to CL with mean dice 0.78 versus 0.78 (without standardization), and outperformed to the baseline models of two institutes. Data Conclusion: The proposed lesion delineation successfully implemented into an FL framework. The FL models were applicable on SRS data of each participating institute, and the FL exhibited comparable mean dice coefficient to CL on non‐SRS dataset. Standardization strategies would be recommended when FL is used. Level of Evidence: 4 Technical Efficacy: Stage 1 [ABSTRACT FROM AUTHOR]

Prolyl‐tRNA synthetase (ProRS), belonging to the family of aminoacyl‐tRNA synthetases responsible for pairing specific amino acids with their respective tRNAs, is categorized into two distinct types: the eukaryote/archaeon‐like type (E‐type) and the prokaryote‐like type (P‐type). Notably, these types are specific to their corresponding cognate tRNAs. In an intriguing paradox, Thermus thermophilus ProRS (TtProRS) aligns with the E‐type ProRS but selectively charges the P‐type tRNAPro, featuring the bacterium‐specific acceptor‐stem elements G72 and A73. This investigation reveals TtProRS's notable resilience to the inhibitor halofuginone, a synthetic derivative of febrifugine emulating Pro‐A76, resembling the characteristics of the P‐type ProRS. Furthermore, akin to the P‐type ProRS, TtProRS identifies its cognate tRNA through recognition of the acceptor‐stem elements G72/A73, along with the anticodon elements G35/G36. However, in contrast to the P‐type ProRS, which relies on a strictly conserved R residue within the bacterium‐like motif 2 loop for recognizing G72/A73, TtProRS achieves this through a non‐conserved sequence, RTR, within the otherwise non‐interacting eukaryote‐like motif 2 loop. This investigation sheds light on the adaptive capacity of a typically conserved housekeeping enzyme to accommodate a novel substrate. [ABSTRACT FROM AUTHOR]

Background: The delineation of brain arteriovenous malformations (bAVMs) is crucial for subsequent treatment planning. Manual segmentation is time‐consuming and labor‐intensive. Applying deep learning to automatically detect and segment bAVM might help to improve clinical practice efficiency. Purpose: To develop an approach for detecting bAVM and segmenting its nidus on Time‐of‐flight magnetic resonance angiography using deep learning methods. Study Type: Retrospective. Subjects: 221 bAVM patients aged 7–79 underwent radiosurgery from 2003 to 2020. They were split into 177 training, 22 validation, and 22 test data. Field Strength/Sequence: 1.5 T, Time‐of‐flight magnetic resonance angiography based on 3D gradient echo. Assessment: The YOLOv5 and YOLOv8 algorithms were utilized to detect bAVM lesions and the U‐Net and U‐Net++ models to segment the nidus from the bounding boxes. The mean average precision, F1, precision, and recall were used to assess the model performance on the bAVM detection. To evaluate the model's performance on nidus segmentation, the Dice coefficient and balanced average Hausdorff distance (rbAHD) were employed. Statistical Tests: The Student's t‐test was used to test the cross‐validation results (P < 0.05). The Wilcoxon rank test was applied to compare the median for the reference values and the model inference results (P < 0.05). Results: The detection results demonstrated that the model with pretraining and augmentation performed optimally. The U‐Net++ with random dilation mechanism resulted in higher Dice and lower rbAHD, compared to that without that mechanism, across varying dilated bounding box conditions (P < 0.05). When combining detection and segmentation, the Dice and rbAHD were statistically different from the references calculated using the detected bounding boxes (P < 0.05). For the detected lesions in the test dataset, it showed the highest Dice of 0.82 and the lowest rbAHD of 5.3%. Data Conclusion: This study showed that pretraining and data augmentation improved YOLO detection performance. Properly limiting lesion ranges allows for adequate bAVM segmentation. Level of Evidence: 4 Technical Efficacy Stage: 1 [ABSTRACT FROM AUTHOR]

The combination of re-irradiation and bevacizumab has emerged as a potential therapeutic strategy for patients experiencing their first glioblastoma multiforme (GBM) recurrence. This study aims to assess the effectiveness of the re-irradiation and bevacizumab combination in treating second-progression GBM patients who are resistant to bevacizumab monotherapy. This retrospective study enrolled 64 patients who developed a second progression after single-agent bevacizumab therapy. The patients were divided into two groups: 35 underwent best supportive care (none-ReRT group), and 29 received bevacizumab and re-irradiation (ReRT group). The study measured the overall survival time after bevacizumab failure (OST-BF) and re-irradiation (OST-RT). Statistical tests were used to compare categorical variables, evaluate the difference in recurrence patterns between the two groups, and identify optimal cutoff points for re-irradiation volume. The results of the Kaplan–Meier survival analysis indicated that the re-irradiation (ReRT) group experienced a significantly higher survival rate and longer median survival time than the non-ReRT group. The median OST-BF and OST-RT were 14.5 months and 8.8 months, respectively, for the ReRT group, while the OST-BF for the none-ReRT group was 3.9 months (p < 0.001). The multivariable analysis identified the re-irradiation target volume as a significant factor for OST-RT. Moreover, the re-irradiation target volume exhibited excellent discriminatory ability in the area under the curve (AUC) analysis, with an optimal cutoff point of greater than 27.58 ml. These findings suggest that incorporating re-irradiation with bevacizumab therapy may be a promising treatment strategy for patients with recurrent GBM resistant to bevacizumab monotherapy. The re-irradiation target volume may serve as a valuable selection factor in determining which patients with recurrent GBM are likely to benefit from the combined re-irradiation and bevacizumab treatment modality. [ABSTRACT FROM AUTHOR]