Search Results

DP-50/DP-50T/DP-50Expert/DP-50S/DP-50Pro Digital Ultrasonic Diagnostic Imaging System is applicable for adults, pregnant women, pediatric patients and neonates. It is intended for use in fetal, abdominal, Intra-operative (abdominal, thoracic, and vascular),pediatric, small organ(breast, thyroid, testes, etc.), neonatal and adult cephalic, transvaginal, musculo-skeletal(conventional, superficial), cardiac(adult, pediatric), peripheral vascular . The system is designed to be used by a trained operator in a clinical setting.

The DP-50/DP-50T/DP-50Expert/DP-50S/DP-50Pro Digital Ultrasonic Diagnostic Imaging System is a general purpose, portable, software controlled, ultrasonic diagnostic system. Its function is to acquire and display ultrasound data in B-Mode, M-Mode, PW-Mode, Color-Mode, Power/Dirpower Mode, THI, Smart3D, 4D, iScape, Biopsy Guidance or the combined mode (i.e. B/M-Mode, B/PW-mode, B/PW/Color). This system is a Track 3 device that employs an array of probes that include Linear array, Convex array probe. The software of DP-50/DP-50T/DP-50Expert/DP-50S/DP-50Pro Digital Ultrasonic Diagnostic Imaging System is based on the main predicate DP-50, and it has a Moderate level of concern.

This is a 510(k) premarket notification for the Shenzhen Mindray Bio-medical Electronics Co., LTD DP-50/DP-50T/DP-50Expert/DP-50S/DP-50Pro Digital Ultrasonic Diagnostic Imaging System. The submission claims substantial equivalence to predicate devices, primarily the DP-50 Digital Ultrasonic Diagnostic Imaging System (K111435).

The document focuses on demonstrating substantial equivalence rather than presenting formal acceptance criteria with specific performance metrics for a new AI/algorithm. However, it implicitly defines acceptance based on the equivalence of its features and performance to predicate devices.

Here's an analysis of the provided information, focusing on aspects relevant to AI/algorithm performance if new features were indeed algorithm-driven. The new features such as "Smart 3D", "Smart Face", "Smart OB", "Smart Bladder", and "iNeedle" suggest the presence of algorithms or AI components.

Since this is a 510(k) premarket notification, formal "acceptance criteria" and detailed "study results" in the typical sense of a clinical trial for breakthrough devices demonstrating specific performance metrics are often replaced by comparisons to predicate devices and adherence to recognized standards.

1. Table of Acceptance Criteria and Reported Device Performance

Given that this is a 510(k) submission primarily relying on substantial equivalence, explicit quantitative acceptance criteria for each individual "smart" feature (e.g., Smart Face, Smart OB) are not provided in the document in the format of a clinical study. Instead, acceptance is implied by demonstrating that the performance and technological characteristics of the new features are the same as or comparable to those already cleared in predicate devices. The "S/D" column indicates if the feature is "Same" or "Different" from the predicate. For those marked "S" (Same), the implied acceptance criterion is "performance identical to the predicate device."

Here's an interpretation based on the provided comparative tables for the "new added special functions":

Study Details:

The document clearly states: "Clinical Studies: Not applicable. The subject of this submission, DP-50/DP-50T/DP-50Expert/DP-50S/DP-50Pro Digital Ultrasonic Diagnostic Imaging System, does not require clinical studies to support substantial equivalence."

This indicates that the submission relies entirely on non-clinical tests and comparisons to predicate devices previously cleared by the FDA. Therefore, detailed information regarding sample size, data provenance, expert ground truth, adjudication methods, or MRMC studies for performance evaluation of new AI/algorithm features is not provided within this document. The "studies" that prove the device meets acceptance criteria are explicitly non-clinical tests.

Here's an attempt to answer the remaining points based on the provided text, acknowledging the limitations for an AI/algorithm-specific evaluation:

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

• Sample Size (Test Set): Not applicable for clinical testing of algorithmic performance as no clinical studies were deemed necessary for this 510(k) submission.
• Data Provenance: Not applicable for clinical data. The submission relies on non-clinical tests which include evaluating the device's acoustic output, biocompatibility, cleaning and disinfection effectiveness, and electrical/mechanical safety based on recognized standards. The "data" proving performance for new features like Smart Face is the comparison of shared technological characteristics with existing cleared devices, rather than a dataset it was evaluated on.

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

Not applicable. No clinical ground truth was established by experts for a test set to prove the performance of the "Smart" features within this 510(k) submission. The performance claim for these features is based on technological equivalence to predicate devices already cleared.

4. Adjudication Method for the Test Set

Not applicable, as no clinical test set requiring expert adjudication for performance evaluation was conducted or submitted.

5. If a Multi Reader Multi Case (MRMC) Comparative Effectiveness Study was done

No. The document explicitly states "Not applicable" for clinical studies. Therefore, no MRMC comparative effectiveness study was conducted.

6. If a Standalone (i.e. algorithm only without human-in-the loop performance) was done

This aspect is not explicitly addressed for the "Smart" features. Given the absence of clinical studies and a reliance on substantial equivalence, standalone performance data for algorithms would likely not have been presented in this type of submission. The features are described as integrated into the ultrasonic system, implying a human operator interaction.

7. The Type of Ground Truth Used

Not applicable in the context of clinical ground truth (e.g., pathology, outcomes data). For the non-clinical tests conducted (acoustic output, safety, etc.), the "ground truth" would be established by the specifications of the relevant international and national standards (e.g., AAMI/ANSI ES60601-1, IEC 60601-2-37). For the "Smart" features, the "ground truth" for showing acceptable performance is the assertion that their technological characteristics are the same as already-cleared predicate devices.

8. The Sample Size for the Training Set

Not applicable. The document does not provide any information about training sets for potential AI/algorithm components within the "Smart" features. The submission relies on demonstrating substantial equivalence to predicate devices, not on proving the performance of a newly developed, independently trained algorithm.

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

Not applicable, as no training set information is provided.

Summary of AI/Algorithm Information (Implied):

The listed "Smart" features (Smart 3D, Free Xros M, iLive, iWorks, iScape View, iNeedle, iPage, HPRF, Smart Face, Smart OB, Smart Bladder) suggest algorithmic processing and potentially AI components. However, this 510(k) submission primarily leverages the concept of substantial equivalence to predicate devices. For each of these features, the conclusion is that "The technological characteristics... are the same. So they are substantial equivalent." This means that the device's acceptability for these features rests on the assertion that they function identically to existing, cleared technology, rather than on new performance studies with specific acceptance criteria.

Ask a specific question about this device