Search Results

DeepContour is a deep learning based medical imaging software that allows trained healthcare professionals to use DeepContour as a tool to automatically process CT images. In addition, DeepCoutour is suitable for the following conditions:

1. Creation of contours using deep-learning algorithms , support quantitative analysis, organ HU distribution statistics, transfer contour files to TPS, and create management archives for patients.
2. Analvze the anatomical structure at different anatomical positions.
3. Rigid and elastic registration based on CT.
4. 3D reconstruction, editing and other visual tools based on organ contours

DeepContour is a deep learning based medical imaging software that allows trained healthcare professionals to use DeepContour as a tool to automatically process CT images. DeepContour contouring workflow supports CT input data and produces RTSTRUCT outputs. The organ segmentation can also be combined into templates, which can be customized by different hospitals according to their needs. DeepContour provides an interactive contouring application to edit and review the contours automatically generated by DeepContour.

Here's a breakdown of the acceptance criteria and study details for the DeepContour (V1.0) device, based on the provided FDA 510(k) Summary:

Acceptance Criteria and Reported Device Performance

1. A table of acceptance criteria and the reported device performance

The document does not explicitly state "acceptance criteria" as a set of predefined quantitative thresholds the device must meet. Instead, the study's aim is to demonstrate that DeepContour's performance is equivalent to or better than the predicate devices. The primary metric used for this comparison is the Dice coefficient, and the implicit acceptance criterion is that DeepContour's performance is not significantly worse than the predicates.

The equivalence definition is stated as: "the lower bound of 95th percentile confidence interval of the subject device segmentation is greater than 0.1 Dice lower than the mean of predicate device segmentation."

Below is a table summarizing the reported Dice coefficients for DeepContour and the predicate devices for a selection of structures. It also includes the summary Average Symmetric Surface Distance (ASSD) comparison.

Table 1: Acceptance Criteria (Implicit) and Reported Device Performance

Table 5: Clinical performance comparison (Peking Union Medical College Hospital) - Selected Structures

| Structure: | DeepContour | AI-Rad CAI-Rad
Companion Organs RT
(K221305) | Contour ProtégéAI
(K223774) |
|--------------------------|---------------------|----------------------------------------------------|--------------------------------|
| Brain | 0.98±0.01(0.97) | 0.93±0.11 | 0.98 ± 0.01 |
| BrainStem | 0.91±0.03(0.89) | 0.90±0.02 | 0.82 ± 0.09 |
| Eye_L | 0.89±0.02(0.88) | 0.81±0.06 | 0.87 ± 0.06 |
| Lung_L | 0.98±0.05(0.96) | 0.92±0.16 | 0.96 ± 0.02 |
| Heart | 0.93±0.16(0.90) | 0.91±0.06 | 0.90 ± 0.07 |
| Liver | 0.96±0.07(0.95) | 0.86±0.17 | 0.93 ± 0.07 |
| Kidney_L | 0.92±0.03(0.91) | 0.82±0.13 | 0.92 ± 0.05 |
| Pancreas | 0.86±0.01(0.86) | 0.87±0.03 | 0.45 ± 0.22 |
| Bladder | 0.95±0.15(0.93) | 0.87±0.15 | 0.52 ± 0.19 |
| Prostate | 0.87±0.02(0.85) | 0.74 ± 0.12 | 0.85 ± 0.06 |
| SpinalCord | 0.93±0.01(0.92) | 0.66 ± 0.14 | 0.63±0.16 |

Table 6: Clinical performance comparison (LCTSC American public datasets) - Selected Structures

| Structure: | DeepContour | AI-Rad CAI-Rad
Companion Organs RT
(K221305) | Contour
ProtégéAI
(K223774) |
|------------|-----------------|----------------------------------------------------|-----------------------------------|
| SpinalCord | 0.92±0.02(0.91) | 0.64±0.13 | 0.62 ± 0.21 |
| Lung L | 0.97±0.15(0.96) | 0.90±0.13 | 0.95 ± 0.05 |
| Heart | 0.92±0.11(0.90) | 0.91±0.04 | 0.90 ± 0.04 |
| Esophagus | 0.89±0.13(0.86) | 0.75±0.13 | 0.68 ± 0.19 |

Table 7: Clinical performance comparison (Pancreas-CT American public datasets) - Selected Structures

| Structure: | DeepContour | AI-Rad CAI-Rad
Companion Organs RT
(K221305) | Contour
ProtégéAI
(K223774) |
|------------|-----------------|----------------------------------------------------|-----------------------------------|
| Spleen | 0.90±0.05(0.88) | 0.91±0.12 | 0.89 ± 0.08 |
| Pancreas | 0.85±0.03(0.83) | 0.84±0.02 | 0.43 ± 0.25 |
| Kidney_L | 0.93±0.02(0.91) | 0.84±0.03 | 0.92 ± 0.17 |
| Liver | 0.97±0.03(0.97) | 0.85±0.13 | 0.92 ± 0.06 |
| Stomach | 0.85±0.02(0.84) | 0.80±0.05 | 0.81 ± 0.17 |

2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

• Sample Size: 203 CT images.
  • 100 clinical datasets
  • 103 American public datasets (60 from LCTSC, 43 from Pancreas-CT)
• Data Provenance:
  • 100 clinical datasets: Retrospectively collected from Peking Union Medical College Hospital (China).
  • 103 American public datasets: Publicly available datasets originally from American sources.
    • 2017 Lung CT Segmentation Challenge (LCTSC): 60 thoracic CT scan patients.
    • Pancreas-CT (PCT): 43 abdominal contrast-enhanced CT scan patients.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)

• For the 100 clinical datasets (China): Two radiation oncologists with more than 10 years of clinical practice established the ground truth annotations. Their detailed CVs are in Appendix 2 (not provided in the input, but referenced).
• For the 103 American public datasets: Annotated by American doctors. (Specific qualifications not detailed in the provided text).

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set

• For the 100 clinical datasets (China): The ground truth was established by two radiation oncologists. A third qualified internal staff member was available to adjudicate if needed. This implies a 2+1 adjudication method if there was disagreement.
• For the 103 American public datasets: No explicit adjudication method is mentioned, only that they were "annotated by American doctors."

5. 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

The provided text does not describe a Multi-Reader Multi-Case (MRMC) comparative effectiveness study involving human readers with and without AI assistance to measure improvement in human performance. The study focuses on the standalone performance of the AI algorithm (DeepContour) compared to predicate devices.

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

Yes, a standalone performance study was done. The entire "Performance comparison" section (Tables 5, 6, 7, and 8) details the Dice coefficients and ASSD values for the DeepContour algorithm, directly comparing its segmentation performance against the ground truth and the predicate devices. There is no human reader involved in generating the DeepContour results reported in these tables.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)

• For the 100 clinical datasets (China): Expert consensus (two radiation oncologists applying RTOG and clinical guidelines using manual annotation, with a third available for adjudication).
• For the 103 American public datasets: Expert annotation by American doctors. (Implied expert consensus or single expert annotation from the original dataset creation process, as described by the original publications).

8. The sample size for the training set

• # of Datasets: 800 CT images.
  • 200 for head and neck region
  • 200 for chest region
  • 200 for abdomen region
  • 200 for pelvic region
  • (Out of these, 160 cases per region were used for training, and 40 cases per region for validation.)

9. How the ground truth for the training set was established

The initial segmentations were reviewed and corrected by two radiation oncologists for model training, with a third qualified internal staff member available to adjudicate if needed. This indicates an expert review and correction process, likely similar to the 2+1 adjudication method used for the test set ground truth.

Ask a specific question about this device

ArcherQA is a software product intended to provide quality assurance of a radiation treatment plan generated by a commercial treatment planning system (TPS) by allowing a clinician to re-calculate dose parameters with dose calculation algorithms independent from the commercial TPS and compare the two set of dose information. ArcherQA is not a TPS or a radiation delivery device. It is to be used only by trained radiation oncology personnel for quality assurance purposes.

ArcherQA (v1.0) is a standalone software product used within a radiation therapy clinic for quality assurance ( Q A ) and treatment plan verification via recalculation of the dose with a GPU-based independent Monte Carlo dose calculation algorithm. ArcherQA is neither a radiation delivery device (e.g. a linear accelerator) nor a Treatment Planning System (TPS). ArcherQA cannot design or transmit instructions to a delivery device or control any other medical device. ArcherQA is an analysis tool meant solely for QA purposes when used by trained medical professionals. Being a software-only QA tool, ArcherQA never comes into contact with patients. ArcherQA performs dose calculation verifications for radiation treatment plans by independently calculating radiation dose. Using both algorithm and hardware-enhanced Monte Carlo methods, ArcherQA can verify the final dose for radiotherapy plans. The calculation is based on read-in treatment plans that are initially calculated by a TPS. ArcherQA supports photon and electron dose calculation. The treatment modalities that can be evaluated by ArcherQA include: three-dimensional conformal radiotherapy (3D CRT), intensity-modulated radiotherapy (IMRT), volumetric modulated arc therapy (VMAT), stereotactic radiosurgery (SRS), stereotactic body radiotherapy (SBRT). ArcherQA also performs dose delivery OA by using the measurement data recorded in a linear accelerator's delivery log files to compare with calculated the delivery dose. This is presented to the end user in a software component of ArcherQA called Fraction Check.

Here's an analysis of the provided text to extract the acceptance criteria and study details for ArcherOA (V1.0):

1. Table of Acceptance Criteria and Reported Device Performance

The provided FDA letter and 510(k) summary do not explicitly state quantitative acceptance criteria or a direct comparison table with specific performance metrics (e.g., accuracy percentages, gamma pass rates with thresholds). Instead, the performance is described in a more general qualitative manner, focusing on agreement with a predicate device.

Table 1: ArcherQA Performance Claims

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

• Sample Size for Test Set: 30 randomly selected samples.
• Data Provenance: "From available database." The document does not specify the country of origin of this data, nor does it explicitly state whether it was retrospective or prospective. Given it was "available," it is highly likely to be retrospective data.

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

The document does not specify the number of experts or their qualifications used to establish ground truth for the test set. The comparison was made against a predicate device (SciMoCa) which itself performs dose calculations. The assumption is that the SciMoCa calculations served as a reference or a "truth" proxy for comparison.

4. Adjudication Method for the Test Set

The document describes "bench testing against the predicate device SciMoCa" and demonstrating "good agreement." This implies a direct comparison method rather than an expert adjudication process for the test set ground truth. The predicate device's output was the reference point.

5. 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, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not conducted. The device (ArcherQA) is a standalone software for quality assurance and dose calculation verification; it does not involve human readers directly improving their performance with or without AI assistance in the way an MRMC study typically assesses. Its purpose is to verify the output of a commercial Treatment Planning System (TPS).

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

Yes, a standalone performance evaluation was done. The "bench testing against the predicate device SciMoCa" directly assesses the algorithm's performance in calculating dose parameters independently, without human intervention in the calculation process.

7. The Type of Ground Truth Used

The "ground truth" for the test set was implicitly the dose calculations generated by the predicate device, SciMoCa. The study aimed to show "good agreement" between ArcherQA's calculations and SciMoCa's calculations.

8. The Sample Size for the Training Set

The document does not provide information regarding the sample size used for any training set. It focuses solely on the validation against the predicate device. As a dose calculation verification software, it might not have a "training set" in the traditional machine learning sense that predicts an outcome, but rather relies on established physics models (Monte Carlo).

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

Since information about a training set is not provided, details on how its ground truth was established are also not available in the supplied text.

Ask a specific question about this device