(111 days)
Intended Use:
The system is a diagnostic ultrasound imaging system used by qualified and trained healthcare professionals for ultrasound imaging, human body fluid flow analysis and puncture and biopsy guidance.
Indications to Use:
The clinical applications and exam types include:
Fetal (including Obstetrics), Abdominal, Pediatric, Intra-operative Neuro (also known as Neurosurgery), Laparoscopic, Small Organ (also known as Small Parts), Adult Cephalic is also known as Adult Trans-cramial), Neonatal Cephalic, Trans-rectal, Trans-vaginal, Musculo-skeletal (Conventional and Superficial), Cardiac Adult, Transesophageal (Cardiac) and Peripheral Vessel (also known as Peripheral Vascular).
The Ultrasound System 2300 is a multi-purpose mobile, software-controlled diagnostic ultrasound system with an on-screen display for thermal and mechanical indices related to potential bio-effect mechanisms which are offered in different configurations/ models intended for urology, general imaging, surgical and anesthesiology applications.
The system consists of a mobile console (engine) that provides digital acquisition, processing and display capabilities. The user interface includes a conventional keyboard or a glass touchpad, a 19" Clinical Display Monitor (CDM). In addition, a variety of system accessories are available such as baskets, foot switch, printer start-up kit, remote control, and extra holders.
Here's a breakdown of the acceptance criteria and the study details for the Prostate Volume Assist (PVA) feature, as derived from the provided document:
Acceptance Criteria and Device Performance (Prostate Volume Assist - PVA)
| Acceptance Criteria | Reported Device Performance |
|---|---|
| The automatic initial caliper placement shall produce a prostate volume estimate that deviates no more than 22% on average from the volume estimate based on manually placed calipers. | For the 9018 transducer: Deviates 11% +/- 6% compared to volume calculation using manual placement (within acceptance criteria). |
| For the 9048 transducer: Deviates 7% +/- 15% compared to volume calculation using manual placement (within acceptance criteria). |
Study Details for Prostate Volume Assist (PVA)
-
Sample size used for the test set and the data provenance:
- Test Images Total: 975 (Healthy) + 1461 (Diseased) = 2436 images.
- Data Provenance:
- Czech Republic (for 9018 transducer data)
- Amsterdam, Holland (for 9048 transducer data)
- Retrospective/Prospective: Not explicitly stated, but the description "Data from a clinical end-user test in the Czech Republic" and "data acquired in Amsterdam, Holland" suggests retrospective use of collected data for the test set.
-
Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- Number of Experts: Not specified as a precise number (e.g., "3 experts"). It states "clinical experts validation testing" and "The human caliper setters scored the images individually."
- Qualifications of Experts: "The clinical personnel had an average of about 15 years' experience in ultrasound."
-
Adjudication method for the test set:
- The document implies individual scoring by "human caliper setters" rather than an explicit adjudication method like 2+1 or 3+1. "The human caliper setters scored the images individually." The comparison is then made against these individual manual placements.
-
If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:
- No MRMC comparative effectiveness study involving human readers improving with AI assistance was directly described. The study focused on validating the algorithm's performance against manual placement, indicating a standalone performance assessment of the AI. The PVA feature is described as "a workflow improvement to an existing prostate volume measurement and calculation tool" and "allows a faster and more efficient workflow," but specific effect sizes for human reader improvement with AI assistance (e.g., reduction in reading time, increase in accuracy) are not provided.
-
If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- Yes, a standalone performance assessment of the algorithm was done. The acceptance criteria and reported device performance directly evaluate "the automatic initial caliper placement" and "the prostate volume calculation of PVA" against manual placement, implying the algorithm's performance without human input for the initial placement. The final verification involved visual evaluation by clinical experts comparing the initial algorithmic placement to manual placement.
-
The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- Expert Manual Measurement: The ground truth for volume estimation was established by "manually placed calipers" by "clinical personnel" with extensive experience.
-
The sample size for the training set:
- Training Images Total: 505 (Healthy) + 13447 (Diseased) + 4104 (Synthesized data) = 18056 images.
-
How the ground truth for the training set was established:
- The document does not explicitly detail the method for establishing ground truth for the training set. It only mentions the types of images (healthy, diseased, synthesized) used for training. However, given that the validation uses expert manual measurements as ground truth, it is highly probable that the training data also utilized expert annotations or measurements, potentially with additional synthesized data to augment the dataset.
§ 892.1550 Ultrasonic pulsed doppler imaging system.
(a)
Identification. An ultrasonic pulsed doppler imaging system is a device that combines the features of continuous wave doppler-effect technology with pulsed-echo effect technology and is intended to determine stationary body tissue characteristics, such as depth or location of tissue interfaces or dynamic tissue characteristics such as velocity of blood or tissue motion. This generic type of device may include signal analysis and display equipment, patient and equipment supports, component parts, and accessories.(b)
Classification. Class II.