Search Results

Segment 3DPrint is a software for review and segmentation of images from a medical scanner as well as of medical 3D models. Segment 3DPrint is intended to generate 3D models for diagnostic purposes in both paediativ and adult populations in the field of orthopaedic, maxillofacial, and cardiovascular applications. The models can be used for visualisation, measuring, and treatment planning. Output from Segment 3DPrint can be used to fabrical replical replical replical replical replical replical replical replical by use of additive manufacturing methods. Segment 3DPrint is intended to be used by trained professionals in conjunction with expert clinical judgement.

Seqment 3DPrint is a software for review and segmentation of images from a medical scanner as well as of medical 3D models. Segment 3DPrint is intended to generate 3D models for diagnostic purposes. The models can be used for visualisation, measuring, and treatment planning. Output from Segment 3DPrint can be used to fabricate physical replicas, by use of additive manufacturing methods.

Here's an analysis of the acceptance criteria and study details for the Segment 3DPrint device based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

2. Sample Size Used for the Test Set and Data Provenance

• Test Set for AI Bone Segmentation: 21 data sets.
• Test Set for Print Accuracy (3D Models): 12 models (representing complex structures and worst-case scenarios).
• Data Provenance: Studies were performed in Europe. The text does not specify exact countries or whether the data was retrospective or prospective. It mentions "a great variety of data (such as scanner model, image quality, and anatomy)" was included.

3. Number of Experts Used to Establish Ground Truth for the Test Set and Their Qualifications

The text mentions "agreement between reference segmentation by expert readers." However, it does not specify the number of experts used or their specific qualifications (e.g., "radiologist with 10 years of experience").

4. Adjudication Method for the Test Set

The text does not explicitly state the adjudication method used for establishing ground truth (e.g., 2+1, 3+1, none). It only refers to "reference segmentation by expert readers."

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done

No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study comparing human readers with AI assistance versus without AI assistance was not explicitly described in the provided text. The studies focused on the standalone performance of the device's segmentation and 3D printing accuracy.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done

Yes, a standalone performance evaluation was largely conducted.

• The "AI bone segmentation algorithm was trained on 20 data sets, and 21 data sets were used for its validation." The reported metrics (Dice, Jaccard, distances) are measures of this algorithm's performance against ground truth.
• The "device validation study validates digital models and 3D models from additive manufacturing" with reported accuracy for the generated models.
• The device is described as a "support tool" for "medically trained professionals" but the performance results are for the algorithm's output directly.

7. The Type of Ground Truth Used

The ground truth for the AI bone segmentation was established by "reference segmentation by expert readers" (expert consensus). For the 3D model accuracy, the text implies that the "validation or application studies using established methods as reference standards" were used, but the exact nature of this reference standard for physical replica accuracy is not fully detailed beyond implying measurement against the physical object vs. the digital model.

8. The Sample Size for the Training Set

• AI Bone Segmentation: 20 data sets.
• 3D Models/Print: The text mentions "The device validation study validates digital models and 3D models... In total 12 models... were printed." This appears to be a validation set rather than a training set for print accuracy itself. The training set for the 3D model generation process is not explicitly stated.

9. How the Ground Truth for the Training Set Was Established

The text states that the "AI bone segmentation algorithm was trained on 20 data sets." It can be inferred that the ground truth for these 20 training data sets would have been established in a similar manner to the validation set, likely through "expert readers" creating reference segmentations. However, the document does not explicitly detail the ground truth establishment method for the training set.

Ask a specific question about this device