Recurrence and metastasis of breast cancer (RMBC) have a decisive impact on patient survival, necessitating reliable biomarkers for its early prediction. This study used machine learning to evaluate blood microbiome profiles as predictive biomarkers of RMBC. A retrospective predictive analysis was conducted on 288 participants, including 96 patients with breast cancer and 192 healthy controls. After 7 years of follow-up, patients were classified into disease-free survival (DFS, n = 88) and RMBC (n = 8) groups. Blood microbiome composition was analysed using 16S rRNA sequencing, followed by quality control. The Synthetic Minority Oversampling Technique (SMOTE) was employed to address class imbalance. Eleven machine learning models were trained using leave-one-out cross-validation (LOOCV) and k-fold cross-validation, and evaluated based on the area under the receiver operating characteristic curve (AUROC), recall, precision, F1-score, and Matthews correlation coefficient (MCC). Alpha diversity was significantly lower in DFS and RMBC groups than in the healthy control group (p < 0.05), while beta diversity analysis revealed distinct clustering. The random forest achieved an AUROC of 0.94, a recall of 0.81, an F1-score of 0.83, and an MCC of 0.88. Enterobacter, Bacteroides, Klebsiella, and Bifidobacterium were among the key microbial genera predicting RMBC in the top five models. Blood microbiome profiling shows potential as a non-invasive RMBC biomarker. Machine learning effectively distinguished RMBC, warranting further validation.

Heterogeneity in skeletal maturation is influenced by a complex interplay of factors, including genetic predispositions, the nutritional and growth status of the child, the onset of precocious puberty, hormonal variations, conditions related to pediatric endocrinology and metabolic disorders, and ailments affecting the musculoskeletal system [1-3]. The assessment of bone age, especially through methods that examine growth plates, is crucial not only for identifying precocious puberty and providing benchmarks for growth trajectories and future height predictions but also for managing conditions such as adolescent idiopathic scoliosis and determining the appropriate timing for orthopedic interventions in children with skeletal anomalies [3-6]. Thus, the appraisal of bone age using standardized methods is paramount for diagnosing, managing, and developing effective therapeutic strategies for these conditions.

The use of endoscopic images for the accurate assessment of ulcerative colitis (UC) severity is crucial to determining appropriate treatment. However, experts may interpret these images differently, leading to inconsistent diagnoses. This study aims to address the issue by introducing a standardization method based on deep learning. We collected 254 rectal endoscopic images from 115 patients with UC, and five experts in endoscopic image interpretation assigned classification labels based on the Ulcerative Colitis Endoscopic Index of Severity (UCEIS) scoring system. Interobserver variance analysis of the five experts yielded an intraclass correlation coefficient of 0.8431 for UCEIS scores and a kappa coefficient of 0.4916 when the UCEIS scores were transformed into UC severity measures. To establish a consensus, we created a model that considered only the images and labels on which more than half of the experts agreed. This consensus model achieved an accuracy of 0.94 when tested with 50 images. Compared with models trained from individual expert labels, the consensus model demonstrated the most reliable prediction results.

With the increasing use of flattening filter free (FFF) beams, it is important to evaluate the impact on the skin dose and target coverage of breast cancer treatments. This study aimed to compare skin doses of treatments using FFF and flattening filter (FF) beams for breast cancer. The study established treatment plans for left breast of an anthropomorphic phantom using Halcyon’s 6-MV FFF beam and TrueBeam’s 6-MV FF beam. Volumetric modulated arc therapy (VMAT) with varying numbers of arcs and intensity modulated radiation therapy (IMRT) were employed, and skin doses were measured at five points using Gafchromic EBT3 film. Each measurement was repeated three times, and averaged to reduce uncertainty. All plans were compared in terms of plan quality to ensure homogeneous target coverage. The study found that when using VMAT with two, four, and six arcs, in-field doses were 19%, 15%, and 6% higher, respectively, when using Halcyon compared to TrueBeam. Additionally, when using two arcs for VMAT, in-field doses were 10% and 15% higher compared to four and six arcs when using Halcyon. Finally, in-field dose from Halcyon using IMRT was about 1% higher than when using TrueBeam. Our research confirmed that when treating breast cancer with FFF beams, skin dose is higher than with traditional FF beams. Moreover, number of arcs used in VMAT treatment with FFF beams affects skin dose to the patient. To maintain a skin dose similar to that of FF beams when using Halcyon, it may be worth considering increasing the number of arcs.

In radiation therapy (RT) for skin cancer, tissue-equivalent substances called boluses are widely used to ensure the delivery of an adequate dose to the skin surface and to provide a radioprotective effect for normal tissue. The aim of this study was to develop a new type of three-dimensional (3D) bolus for RT involving body parts with irregular geometries and to evaluate its clinical feasibility. Two 3D-printed boluses were designed for two patients with squamous cell carcinoma (SCC) of their distal extremities based on computed tomography (CT) images and printed with polylactic acid (PLA). The clinical feasibility of the boluses was evaluated by measuring the in vivo skin dose at the tumor site with optically stimulated luminescence detectors (OSLDs) and comparing the results with the prescribed and calculated doses from the Eclipse treatment planning system (TPS). The average measured dose distribution for the two patients was 94.75% of the prescribed dose and 98.8% of the calculated dose. In addition, the average measured dose during repeated treatments was 189.5 ± 3.7 cGy, thus demonstrating the excellent reproducibility of the proposed approach. Overall, the customized 3D-printed boluses for the RT of distal extremities accurately delivered doses to skin tumors with improved reproducibility.

The objective of this study is to explore innovative integration within the field of anatomy education by leveraging HoloLens 2 Augmented Reality Head-Mounted Display (AR HMD) technology and real-time cloud rendering. Initial 3D datasets, comprising extensive anatomical information for each bone, were obtained through the 3D scanning of a full-body cadaver of Korean male origin. Subsequently, these datasets underwent refinement processes aimed at enhancing visual fidelity and optimizing polygon counts, utilizing Blender software. Unity was employed for the development of the Metaverse platform, incorporating tailored 3D User Experience (UX) and User Interface (UI) components to facilitate interactive anatomy education via imported cadaver models. Integration with real-time remote rendering cloud servers, such as Azure, was implemented to augment the performance and rendering capabilities of the HoloLens 2 AR HMD. The extended reality (XR) content uses the Photon Cloud network for real-time data synchronization and HoloLens 2 voice functionality. The metaverse platform supports user interaction through room creation and joining, with various tools for bone manipulation, color differentiation, and surface output. Collaboration features enable sharing and synchronization of model states. The study highlights the importance of technological innovation in anatomy education for future medical professionals. The proposed content aims to address limitations of traditional methods and enhance learning experiences. Continued efforts in developing and improving such technologies are crucial to equip learners with essential skills for adaptation in the evolving healthcare landscape.