(30 days)
"Atomica Planner" is stand-alone software indicated for use by highly qualified dental professionals in the preoperative simulation-based planning of implant placements, and designing patients' 3D model surgical guides to support dental treatment surgeries (such as teeth replacement for Adult patients with missing/damaged teeth: taking into account dental functional & esthetic aspects).
" Atomica Planner" image-processing functions & tools provide users with 2D/3D visualization & segmentation for imported medical digital imaging (DICOM) datasets (acquired originally by optical/medical scanners, such as CT) to enhance the image-guided detection of suitable implant placements based on the evaluation of intraoral surrounding tissue. System users can also export patient plan dataset output with final surgical instructions PDF report, and the designed surgical guide 3D models in the imaging (STL) file format which is compatible with a wide range of 3rd parties manufacturing systems.
"Atomica Planner" system is intended to be used only by highly-qualified dental professionals with sufficient training in implantology & surgical dentistry as well as practical experience with using digital imaging technologies and in an environment suitable for reading diagnostic dental DICOM data sets.
"Atomica Planner" is a standalone desktop application intended for pre-operative simulation-based planning of implant placements & dental surgical treatment (such as teeth replacement with missing/damaged teeth; taking into account dental functional & esthetic aspects). The system is intended to be used only by well-trained and highly qualified dental professionals, based mainly on medical digital image processing functions & tools (2D/3D visualization & segmentation). A project file is created from the patient's imported medical imaging (DICOM) dataset (generated originally by medical/optical scanners, such as CT) to support dental professionals in the implant placements detection and suitable sleeves/drills types selection according to the image-guided anatomical measurements/evaluations of (surrounding/adjacent roots & nerves, available bone mass/density, and variations in maxilla & mandible). System users can export their plan dataset outputs with final surgical instructions PDF report, and the designed surgical guide 3D models in the imaging (STL) file format which is compatible with a wide range of manufacturing systems. The software is designed to run on standard "PC" platforms that meet the identified minimum (SW/HW) requirements and the environment of use of the device is the "Professional Healthcare Facility". Results produced by " Atomica Planner's visualization-based diagnosis & planning tools for dental implant treatments are mainly dependent on the interpretation of qualified & well-trained dental professionals. "Atomica Planner" is a stand-alone software medical device and does not contact the human body, nor does it directly control or integrate with any physical or digital life-sustaining medical devices.
The Atomica Planner device did not conduct a clinical study to establish performance criteria or compare itself against human readers. Instead, the performance of the device was established through non-clinical verification and validation activities, demonstrating its similarity and equivalence to a legally marketed predicate device, "3Shape Implant Studio" (K202256).
Here's a breakdown of the information provided regarding acceptance criteria and performance studies:
1. Table of Acceptance Criteria and Reported Device Performance
No specific quantitative acceptance criteria or detailed device performance metrics (e.g., accuracy percentages, F1-scores, precision, recall) are explicitly provided in the document. The document primarily focuses on demonstrating equivalence through functional and design similarities to the predicate device and adherence to recognized standards.
However, the "Software Performance Characteristics" section and the "Summary of Non-Clinical Performance Testing" implicitly define the acceptance criteria through the successful execution of validation activities, indicating that the device achieves its intended functionalities and operates reliably within specified technical and quality standards.
The reported device performance is qualitative, asserting that:
- "All the software specifications have met the acceptance criteria."
- "All V&V results ensure the 'Atomica Planner' software device's effectiveness and reliability."
- "The 'Atomica Planner' software medical device is as effective as and performs as the legally marketed predicate device, and with no significant technical differences."
- "The comparison of intended use, technological characteristics, performance specifications, device hazards as well as verification and validation results demonstrate that the 'Atomica Planner' software device is safe, effective, and as performs as the (US Legally Marketed) predicate device."
2. Sample Size Used for the Test Set and Data Provenance
- Test Set Sample Size: Not explicitly stated. The document mentions "patients' DICOM datasets" were used for validation, but the number of such datasets is not provided.
- Data Provenance: The medical digital imaging (DICOM) datasets are acquired "originally by optical/medical scanners, such as CT." The origin (country/institution) and whether the data is retrospective or prospective are not specified.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications
- Number of Experts: Not explicitly stated for establishing ground truth for the test set.
- Qualifications of Experts: The device is "intended to be used only by highly-qualified dental professionals with sufficient training in implantology & surgical dentistry as well as practical experience with using digital imaging technologies and in an environment suitable for reading diagnostic dental DICOM data sets." While these are the intended users, it's not explicitly stated that such experts established the ground truth for the validation datasets.
4. Adjudication Method for the Test Set
Not specified.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done
No. The document explicitly states: "No clinical studies were carried out for 'Atomica Planner'." Therefore, no MRMC comparative effectiveness study was performed, and no effect size of human readers improving with AI vs. without AI assistance is reported.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done
Yes, implicitly. The performance testing was "non-clinical" and part of "verification and validation activities." The device is described as "stand-alone software" with "actual results of implemented (real-world) Software Functional dynamic tests/verification" including "Code review/Unit, module, integration, and E2E System tests." These tests evaluate the inherent functionality and performance of the software itself. The conclusion that the device "is as effective as and performs as the legally marketed predicate device, and with no significant technical differences" implies a standalone evaluation of its core functions.
7. The Type of Ground Truth Used
The document does not explicitly define how "ground truth" was established for the datasets used in testing. However, given it's a planning and visualization tool, the "ground truth" would likely be derived from:
- Conformance to standards: Ensuring DICOM compliance, accurate rendering, and appropriate measurement calculations.
- Expected output: Verifying that the software's outputs (e.g., implant placements, measurements, surgical guide designs) align with what would be expected for given input DICOM data, likely based on established dental implantology principles and potentially previous expert planning for similar cases.
- Functional correctness: Verification of each module's correct operation (e.g., segmentation module correctly segments, implant module correctly places implants as per user input).
8. The Sample Size for the Training Set
Not applicable. The document describes a "verification and validation" process, not a machine learning model training process. Therefore, there is no mention of a "training set." The software relies on predefined algorithms and image processing techniques rather than learning from a dataset.
9. How the Ground Truth for the Training Set Was Established
Not applicable, as there is no training set for a machine learning model.
§ 892.2050 Medical image management and processing system.
(a)
Identification. A medical image management and processing system is a device that provides one or more capabilities relating to the review and digital processing of medical images for the purposes of interpretation by a trained practitioner of disease detection, diagnosis, or patient management. The software components may provide advanced or complex image processing functions for image manipulation, enhancement, or quantification that are intended for use in the interpretation and analysis of medical images. Advanced image manipulation functions may include image segmentation, multimodality image registration, or 3D visualization. Complex quantitative functions may include semi-automated measurements or time-series measurements.(b)
Classification. Class II (special controls; voluntary standards—Digital Imaging and Communications in Medicine (DICOM) Std., Joint Photographic Experts Group (JPEG) Std., Society of Motion Picture and Television Engineers (SMPTE) Test Pattern).