Search Results

LOGIQ E10 is intended for use by a qualified physician for ultrasound evaluation of Fetal/Obstetrics; Abdominal (including Renal, Gynecology/Pelvic); Pediatric; Small Organ (Breast, Testes, Thyroid); Neonatal Cephalic, Adult Cephalic; Cardiac (Adult and Pediatric); Peripheral Vascular; Musculo-skeletal Conventional and Superficial; Urology (including Prostate); Transrectal; Transvaginal; Tranesophageal and Intraoperative (Abdominal and Vascular).

Modes of operation include: B, M, PW Doppler, CW Doppler, Color Doppler, Color M Doppler, Power Doppler, Harmonic Imaging, Coded Pulse, 3D/4D Imaging mode, Elastography, Shear Wave Elastography, Attenuation Imaging and combined modes: B/M, B/Color, B/PWD, B/Color/PWD, B/Power/PWD.

The LOGIQ E10 is intended to be used in a hospital or medical clinic.

Device Description

The LOGIQ E10 is a full featured, Track 3, general purpose diagnostic ultrasound system which consists of a mobile console approximately 585 mm wide (keyboard), 991 mm deep and 1300 mm high that provides digital acquisition, processing and display capability. The user interface includes a computer keyboard, specialized controls, 12-inch high-resolution color touch screen and 23.8-inch High Contrast LED LCD monitor.

AI/ML Overview

Here's an analysis of the acceptance criteria and supporting studies for the LOGIQ E10 ultrasound system, derived from the provided FDA 510(k) Clearance Letter:

1. Table of Acceptance Criteria and Reported Device Performance

Feature/Metric	Acceptance Criteria	Reported Device Performance
Auto Abdominal Color Assistant 2.0
Overall Model Detection Accuracy	$\ge 80%$	$94.8%$
Sensitivity (True Positive Rate)	$\ge 80%$	$0.91$
Specificity (True Negative Rate)	$\ge 80%$	$0.98$
DICE Similarity Coefficient (Segmentation Accuracy)	$\ge 0.80$	$0.82$
Auto Aorta Measure Assistant (Long View AP Measurement)
Average Accuracy	Not explicitly stated as a target percentage, but implied by strong performance metrics	$87.2%$ (95% CI of $\pm 1.98%$)
Average Absolute Error	Not explicitly stated as a target	$0.253$ cm (95% CI of $0.049$ cm)
Limits of Agreement	Not explicitly stated as a target range	$(-0.15, 0.60)$ cm (95% CI of $(-0.26, 0.71)$)
Auto Aorta Measure Assistant (Short View AP Measurement)
Average Accuracy	Not explicitly stated as a target percentage, but implied by strong performance metrics	$92.9%$ (95% CI of $\pm 2.02%$)
Average Absolute Error	Not explicitly stated as a target	$0.128$ cm (95% CI of $0.037$ cm)
Limits of Agreement	Not explicitly stated as a target range	$(-0.21, 0.36)$ cm (95% CI of $(-0.29, 0.45)$)
Auto Aorta Measure Assistant (Short View Trans Measurement)
Average Accuracy	Not explicitly stated as a target percentage, but implied by strong performance metrics	$86.9%$ (95% CI of $\pm 6.25%$)
Average Absolute Error	Not explicitly stated as a target	$0.235$ cm (95% CI of $0.110$ cm)
Limits of Agreement	Not explicitly stated as a target range	$(-0.86, 0.69)$ cm (95% CI of $(-1.06, 0.92)$)
Auto Common Bile Duct (CBD) Measure Assistant (Porta Hepatis measurement accuracy without segmentation scroll edit)
Average Accuracy	Not explicitly stated as a target percentage, but implied by strong performance metrics	$59.85%$ (95% CI of $\pm 17.86%$)
Average Absolute Error	Not explicitly stated as a target	$1.66$ mm (95% CI of $1.02$ mm)
Limits of Agreement	Not explicitly stated as a target range	$(-4.75, 4.37)$ mm (95% CI of $(-6.17, 5.79)$)
*Auto Common Bile Duct (CBD) Measure Assistant (Porta Hepatis measurement accuracy with* segmentation scroll edit)**
Average Accuracy	Not explicitly stated as a target percentage, but implied by strong performance metrics	$80.56%$ (95% CI of $\pm 8.83%$)
Average Absolute Error	Not explicitly stated as a target	$0.91$ mm (95% CI of $0.45$ mm)
Limits of Agreement	Not explicitly stated as a target range	$(-1.96, 3.25)$ mm (95% CI of $(-2.85, 4.14)$)
Ultrasound Guided Fat Fraction (UGFF)
Correlation Coefficient with MRI-PDFF (Japan Cohort)	Strong correlation confirmed	$0.87$
Offset (UGFF vs MRI-PDFF, Japan Cohort)	Not explicitly stated as a target	$-0.32%$
Limits of Agreement (UGFF vs MRI-PDFF, Japan Cohort)	Not explicitly stated as a target range	$-6.0%$ to $5.4%$
% Patients within $\pm 8.4%$ difference (Japan Cohort)	Not explicitly stated as a target	$91.6%$
Correlation Coefficient with MRI-PDFF (US/EU Cohort)	Strong correlation confirmed	$0.90$
Offset (UGFF vs MRI-PDFF, US/EU Cohort)	Not explicitly stated as a target	$-0.1%$
Limits of Agreement (UGFF vs MRI-PDFF, US/EU Cohort)	Not explicitly stated as a target range	$-3.6%$ to $3.4%$
% Patients within $\pm 4.6%$ difference (US/EU Cohort)	Not explicitly stated as a target	$95.0%$
Correlation Coefficient with UDFF (EU Cohort)	Strong correlation confirmed	$0.88$
Offset (UGFF vs UDFF, EU Cohort)	Not explicitly stated as a target	$-1.2%$
Limits of Agreement (UGFF vs UDFF, EU Cohort)	Not explicitly stated as a target range	$-5.0%$ to $2.6%$
% Patients within $\pm 4.7%$ difference (EU Cohort)	Not explicitly stated as a target	All patients

2. Sample Size for Test Set and Data Provenance

Auto Abdominal Color Assistant 2.0:
- Test Set Sample Size: 49 individual subjects, 1186 annotation images.
- Data Provenance: Retrospective, all data from the USA.
Auto Aorta Measure Assistant:
- Test Set Sample Size:
  - Long View Aorta: 36 subjects (11 Male, 25 Female).
  - Short View Aorta: 35 subjects (11 Male, 24 Female).
- Data Provenance: Retrospective, from Japan (15-16 subjects) and USA (20 subjects).
Auto Common Bile Duct (CBD) Measure Assistant:
- Test Set Sample Size: 25 subjects (11 Male, 14 Female).
- Data Provenance: Retrospective, from USA (40%) and Japan (60%).
Ultrasound Guided Fat Fraction (UGFF):
- Test Set Sample Size (Primary Study): 582 participants.
- Data Provenance (Primary Study): Retrospective, Japan.
- Test Set Sample Size (Confirmatory Study 1): 15 US patients + 5 EU patients (total 20).
- Data Provenance (Confirmatory Study 1): Retrospective, USA and EU.
- Test Set Sample Size (Confirmatory Study 2): 24 EU patients.
- Data Provenance (Confirmatory Study 2): Retrospective, EU.

3. Number of Experts and Qualifications for Ground Truth

Auto Abdominal Color Assistant 2.0: Not explicitly stated, but implies multiple "readers" to ground truth anatomical visibility. No specific qualifications are mentioned beyond "readers."
Auto Aorta Measure Assistant: Not explicitly stated, but implies multiple "readers" for measurements and an "arbitrator" to select the most accurate measurement. No specific qualifications are mentioned beyond "readers" and "arbitrator."
Auto Common Bile Duct (CBD) Measure Assistant: Not explicitly stated, but implies multiple "readers" for measurements and an "arbitrator" to select the most accurate measurement. No specific qualifications are mentioned beyond "readers" and "arbitrator."
Ultrasound Guided Fat Fraction (UGFF): Ground truth for the primary study was MRI Proton Density Fat Fraction (MRI-PDFF %). No human experts were involved in establishing the ground truth for UGFF, as it relies on MRI-PDFF as the reference. The correlation between UGFF and UDFF also used UDFF as a reference, not human experts.

4. Adjudication Method for the Test Set

Auto Abdominal Color Assistant 2.0: Not explicitly mentioned, however, the process described as "Readers to ground truth the 'anatomy' visible in static B-Mode image. (Before running AI)" and then comparing to AI predictions does not suggest an adjudication process for the ground truth generation itself beyond initial reader input. Confusion matrices were generated later.
Auto Aorta Measure Assistant: An "Arbitrator" was used to "select most accurate measurement among all readers" for the initial ground truth, which was then compared to AI baseline. This implies a 1 (arbitrator) + N (readers) adjudication method for measurement accuracy. For keystroke comparison, readers measured with and without AI.
Auto Common Bile Duct (CBD) Measure Assistant: An "Arbitrator" was used to "select most accurate measurement among all readers" for the initial ground truth, which was then compared to AI baseline. This implies a 1 (arbitrator) + N (readers) adjudication method for measurement accuracy. For keystroke comparison, readers measured with and without AI.
Ultrasound Guided Fat Fraction (UGFF): Ground truth was established by MRI-PDFF or comparison to UDFF. No human adjudication method was described for these.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

Auto Aorta Measure Assistant: Yes, a comparative study was performed by comparing keystroke counts with and without AI assistance for human readers.
- Effect Size:
  - Long View Aorta AP Measurement: Average reduction from $4.132 \pm 0.291$ keystrokes (without AI) to $1.236 \pm 0.340$ keystrokes (with AI).
  - Short View Aorta AP and Trans Measurement: Average reduction from $7.05 \pm 0.158$ keystrokes (without AI) to $2.307 \pm 1.0678$ keystrokes (with AI).
Auto Common Bile Duct (CBD) Measure Assistant: Yes, a comparative study was performed by comparing keystroke counts with and without AI assistance for human readers.
- Effect Size: Average reduction of $1.62 \pm 0.375$ keystrokes (mean and standard deviation) from manual to AI-assisted measurements.
Other features (Auto Abdominal Color Assistant 2.0, UGFF): The documentation does not describe a MRMC study for improved human reader performance with AI assistance for these features.

6. Standalone (Algorithm Only) Performance Study

Auto Abdominal Color Assistant 2.0: Yes, the model's accuracy (detection accuracy, sensitivity, specificity, DICE score) was evaluated in a standalone manner against the human-annotated ground truth.
Ultrasound Guided Fat Fraction (UGFF): Yes, the correlation and agreement of the UGFF algorithm's values were tested directly against an established reference standard (MRI-PDFF) and another device's derived fat fraction (UDFF).

7. Type of Ground Truth Used

Auto Abdominal Color Assistant 2.0: Expert consensus/annotations on B-Mode images, followed by comparison to AI predictions.
Auto Aorta Measure Assistant: Expert consensus on measurements (human readers with arbitrator selection) and keystroke counts from these manual measurements and AI-assisted measurements.
Auto Common Bile Duct (CBD) Measure Assistant: Expert consensus on measurements (human readers with arbitrator selection) and keystroke counts from these manual measurements and AI-assisted measurements.
Ultrasound Guided Fat Fraction (UGFF): Established clinical reference standard: MRI Proton Density Fat Fraction (MRI-PDFF %). For one confirmatory study, another cleared device's derived fat fraction (UDFF) was used as a comparative reference.

8. Sample Size for the Training Set

The document states that "The exams used for test/training validation purpose are separated from the ones used during training process" but does not provide the sample size for the training set itself for any of the AI features.

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

The document implies that the ground truth for training data would have been established similarly to the test data ground truth (e.g., expert annotation for Auto Abdominal Color Assistant, expert measurements for Auto Aorta/CBD Measure Assistants). However, the specific methodology for the training set's ground truth establishment (e.g., number of experts, adjudication, qualifications) is not detailed in the provided text. It only explicitly states that "Before the process of data annotation, all information displayed on the device is removed and performed on information extracted purely from Ultrasound B-mode images" for annotation. Independence of test and training data by exam site origin or overall separation is mentioned, but not the process for creating the training set ground truth.

Ask a Question

Ask a specific question about this device

Page 1 of 1