Machine learning for drawability prediction in industrial settings faces significant challenges due to the high diversity of real-world geometries and the limited availability of directly usable historical data. Existing models often overfit to a limited family of geometries sharing the same parametrization, and consequently fail to generalize beyond that group to geometrically more diverse components. We propose geometry-based data augmentation methods and synthetic data generation to address generalization limitations. Both augmentation and machine learning model development utilize a base dataset derived from 90 real-world U-shaped parts, reflecting industry-relevant shape variability, within the common class of U-shaped deep drawing geometries. Evaluations with graph and point cloud models indicate that our geometry augmentation improves classification accuracy and reduces test accuracy variance, outperforming the isolated use of synthetic data and enabling improved generalization to unseen U-shaped geometries. Our best drawability classifier achieves almost 90% cross-validated accuracy by using augmented and synthetic data to expand a training set originally limited to 60 samples. Although the augmented geometries require simulation-based labeling and are loosely tailored to U-shaped sheet metal geometries, they contribute to more robust and generalizable model performance, with gains that can exceed the impact of the model choice in a sparse-data scenario. Hence, geometry data augmentation appears to emerge as a key enabler for foundation models capable of geometric generalization for data-driven tasks such as the drawability assessment investigated here. This, in turn, helps accelerate development processes.
This data article describes the Surgical Procedure Phase, Keypoint, and Instrument Recognition (PhaKIR) dataset, a collection of eight complete laparoscopic cholecystectomy videos acquired during routine minimally invasive procedures at three German medical centers. The recordings were captured with different monocular endoscopic camera systems at 25 frames per second and a resolution of 1920 × 1080 pixels, with durations ranging from 28 to 58 min. Segments showing regions outside the abdominal cavity were removed for anonymization, and the corresponding cut indices are provided. The dataset offers unified annotations for three interrelated tasks on the same complete surgical sequences: surgical phase recognition, annotated for every frame at 25 fps (485,875 frames), instrument keypoint estimation (19,435 frames), and instrument instance segmentation (19,435 frames), the latter two annotated at one frame per second (every 25th frame). Surgical phases follow the seven-phase Cholec80 scheme, extended by an undefined label for transitional frames. The instrument annotations distinguish 19 instrument classes as well as individual instances of the same class, with keypoint annotations comprising two to four class-dependent points labeled with COCO-style visibility states. Segmentation and keypoint labels were created manually using the Computer Vision Annotation Tool (CVAT), whereas phase labels were derived from documented phase-transition timestamps, and all annotations underwent a multi-stage review by a medically trained team. The data are provided in open formats (MP4, CSV, JSON, PNG) together with a frame-extraction script under the CC BY-NC-SA license and are available through controlled access upon request via the Zenodo platform. Because the dataset combines procedural context, instrument pose, and pixel-accurate instance segmentations within full-length recordings from multiple institutions, it can be reused for single-task or multi-task model development, for temporally aware approaches that exploit motion continuity, and for cross-institutional generalization protocols such as leave-one-hospital-out evaluation. The dataset served as the training resource for the PhaKIR Challenge at the Endoscopic Vision (EndoVis) Challenge at MICCAI 2024.
Reliable recognition and localization of surgical instruments in endoscopic video recordings are foundational for a wide range of applications in computer- and robot-assisted minimally invasive surgery (RAMIS), including surgical training, skill assessment, and autonomous assistance. However, robust performance under real-world conditions remains a significant challenge. Incorporating surgical context - such as the current procedural phase - has emerged as a promising strategy to improve robustness and interpretability. To address these challenges, we organized the Surgical Procedure Phase, Keypoint, and Instrument Recognition (PhaKIR) sub-challenge as part of the Endoscopic Vision (EndoVis) challenge at MICCAI 2024. We introduced a novel, multi-center dataset comprising thirteen full-length laparoscopic cholecystectomy videos collected from three distinct medical institutions, with unified annotations for three interrelated tasks: surgical phase recognition, instrument keypoint estimation, and instrument instance segmentation. Unlike existing datasets, ours enables joint investigation of instrument localization and procedural context within the same data while supporting the integration of temporal information across entire procedures. We report results and findings in accordance with the BIAS guidelines for biomedical image analysis challenges. The PhaKIR sub-challenge advances the field by providing a unique benchmark for developing temporally aware, context-driven methods in RAMIS and offers a high-quality resource to support future research in surgical scene understanding.
AI-generated text is nowadays produced at scale across domains and heterogeneous generation pipelines, making robustness to distribution shift a central requirement for supervised binary detectors. We train transformer-based detectors on HC3 PLUS and calibrate a single decision threshold by maximising balanced accuracy on held-out validation; this threshold is then kept fixed for all downstream test distributions, revealing domain- and generator-dependent error asymmetries under shift. We evaluate in-domain on HC3 PLUS, under cross-dataset transfer to the multi-domain, multi-generator M4 benchmark, and on the external AI-Text-Detection-Pile. Although base models achieve near-ceiling in-domain performance (up to 99.5
This recommendation provides a procedure for determining the carbonation depth on the surface of concrete by applying a pH indicator. This includes definitions of carbonation, carbonation depth and carbonation front, as well as descriptions of the different pH indicator solutions that can be used. Recommendations for testing laboratory-prepared specimens and those obtained from concrete structures are also given. This involves guidelines for sample preparation and/or extraction, CO2 exposure duration, carbonation depth determination and reporting of results. A section on data interpretation is also provided, as carbonation results are used for determining durability of concrete, as well as a criterion for materials selection or for carbon uptake calculations. The new Recommendation CPC-18R1 is intended to supersede the former RILEM recommendation CPC-18, particularly when prescribed as the preferred method for evaluating and reporting carbonation depths.