Segment 3DPrint

Segment 3DPrint is a medical software designed for reviewing and segmenting medical images to generate accurate 3D models for diagnostic purposes, visualization, measurement, and treatment planning across orthopaedic, maxillofacial, and cardiovascular applications. It utilizes various image processing techniques, including manual, semi-automatic, and AI-driven segmentation algorithms, to create digital models from medical scans which can also be used to fabricate precise physical replicas via additive manufacturing for enhanced clinical utility.

Segment 3DPrint is a software application designed for medically trained professionals to review and segment images obtained from medical scanners, as well as existing medical 3D models. Its primary purpose is to generate three-dimensional models for diagnostic use in both paediatric and adult populations. These models are applicable in orthopaedic, maxillofacial, and cardiovascular fields, aiding in visualization, measurement, and treatment planning. Furthermore, the output from Segment 3DPrint can be utilized to fabricate physical replicas of anatomical structures through additive manufacturing methods, enhancing preoperative planning and patient understanding. The software operates on a standard PC platform with a Windows operating system, allowing users to interact via a graphical user interface to import images from various sources, including portable media and network storage. The software employs digital processing to render 3D objects, offering manual, semi-automatic, and AI-driven segmentation capabilities. For instance, its AI bone segmentation algorithm, trained on 20 datasets and validated on 21 distinct datasets, demonstrated high accuracy with a maximum 95th percentile surface distance of less than 1 mm between ground truth and AI-generated segmentation. Performance data from bench and clinical studies indicate that the final 3D models and physical replicas produced using low force stereolithography achieve an accuracy of less than 1 mm, suitable for clinical use across its intended applications. The validation studies involved diverse patient cases, including complex structures, ensuring robustness and reliability for clinical decision support when used in conjunction with expert clinical judgement.

AI Regulatory Concerns

Powered by

Jev reads the full FDA letter and returns calibrated concern probabilities per regulatory category. These are AI estimates, not regulatory advice.

• Q1. How does the performance of Segment 3DPrint's semi-automatic segmentation algorithms, particularly for soft tissues in cardiovascular or maxillofacial applications, compare to fully manual segmentation in terms of time-efficiency and accuracy?; What specific AI architecture is used for the bone segmentation algorithm, and how was the 'great variety of data' ensured during training and validation to minimize bias and maximize generalizability across different scanner models and patient demographics?; Beyond the stated <1mm accuracy for physical replicas, what is the typical variability or range of accuracy observed across different anatomical regions (e.g., complex cardiovascular structures vs. simpler orthopaedic bones) and additive manufacturing methods?; Are there any known limitations or contraindications for using Segment 3DPrint, for example, with specific image qualities, artifacts, or patient conditions that might compromise model accuracy?; How does Segment 3DPrint integrate with existing clinical workflows, such as Picture Archiving and Communication Systems (PACS) or surgical navigation tools, and what is the typical learning curve for medically trained professionals to achieve proficiency?