Better Diagnostics Caries Assist (BDCA) Version 1.0
K241725Better Diagnostics AI Corp · cleared 2025-03-11 · product code MYN · Radiology
Premarket evidence — what FDA accepted
Device typesamd
source quote (p.6)
“Better Diagnostics Caries Assist (BDCA) Version 1.0 is a computer-aided detection (CADe) software designed for the automated detection of carious lesions in Bitewings and periapical dental radiographs.”
AlgorithmComputer Vision Models (CV Models) with three parts: Pre-Processing Module, Core Module, and Post-Processing Module. The models are hosted on a cloud computing platform and are responsible for image processing, providing a binary indication for carious findings and outputting bounding box coordinates.
source quote (p.6)
“Computer Vision Models (CV Models): These models are hosted on a cloud computing platform and are responsible for image processing. They provide a binary indication to determine the presence or absence of carious findings. If carious findings are detected, the software will output the coordinates of the bounding boxes for each finding. If no carious lesions are found, the output will not contain any bounding boxes and will have a message stating "No Suspected: Caries Detected" Al models have three parts: Pre-Processing Module: Standardization of image to specific height and width to maintain consistency for AI model. Finds out the type of image including IOPA, Bitewings or other types. BDCA v1.0 can only process Bitewings and IOPA images for patients over age 18. All other types of images will be rejected. Core Module: This module provides carious lesion annotations and co-ordinates to draw bounding boxes. Post-Processing Module: includes cleanup process to remove outliers/incorrect annotations from the images.”
Adaptive (vs locked)FDA source did not state this
PCCPFDA source did not state this
Cybersecurity addressedYes
source quote (p.13)
“identification and mitigation of device-related hazards via cybersecurity and risk management”
Validation studies (2)
Standalone
n=1,298 images
endpoints: sensitivity at both the surface and image levels; specificity at both the surface and image levels
standards: IEC 62304 Edition 1.1 2015-06 Medical device software - Software life cycle processes, IEC 62366-1:2015: Medical devices-Part 1: Application of usability engineering to medical devices., ISO 14971 Third Edition 2019-12 Medical Devices - Application of risk management to medical devices., ISO 15223-1:2021: Medical devices Symbols to be used with information to be supplied by the manufacturer.
Reader study (MRMC)
n=328 images
endpoints: diagnostic performance of the model using Alternative Free Response Operating Characteristic (AFROC); sensitivity at the image and surface levels for comparing the performance between readers aided by BDCA v1.0 and reader unaided by BDCA v1.0; specificity at the image and surface levels for comparing the performance between readers aided by BDCA v1.0 and reader unaided by BDCA v1.0
standards: IEC 62304 Edition 1.1 2015-06 Medical device software - Software life cycle processes, IEC 62366-1:2015: Medical devices-Part 1: Application of usability engineering to medical devices., ISO 14971 Third Edition 2019-12 Medical Devices - Application of risk management to medical devices., ISO 15223-1:2021: Medical devices Symbols to be used with information to be supplied by the manufacturer.
Reported performance (30 observations)
sensitivity0.892CI [86.15%, 92.13%]
source quote (p.15)
“BW Surface Level: The BDCA achieved a sensitivity of 89.2% with an adjusted 95% CI of [86.15%, 92.13%]”
specificity0.995CI [99.32%, 99.57%]
source quote (p.15)
“and a specificity of 99.5% with a CI of [99.32%, 99.57%].”
aurocas written: “auc”0.848
source quote (p.17)
“The results from the aided groups, displaying AUCs of 0.848 for BW and 0.845 for IOPA images, significantly surpass those of the unaided groups, which recorded AUCs of 0.806 and 0.807, respectively.”
sensitivityas written: “IOPA Surface Level Sensitivity”0.882CI [85.27%, 90.78%]
source quote (p.15)
“IOPA Surface Level: The device reached a sensitivity of 88.2% with a CI of [85.27%, 90.78%]”
specificityas written: “IOPA Surface Level Specificity”0.991CI [98.88%, 99.31%]
source quote (p.16)
“and a specificity of 99.1% with a CI of [98.88%, 99.31%]”
sensitivityas written: “BW Image Level Sensitivity (Conservative)”0.81CI [76.15%, 85.18%]
source quote (p.16)
“BW Image Level: Sensitivity under conservative conditions was reported at 81.0%, with a CI of [76.15%, 85.18%]”
sensitivityas written: “BW Image Level Sensitivity (Optimistic)”0.919CI [88.33%, 94.71%]
source quote (p.16)
“and under optimistic conditions, it improved to 91.9%, with a CI of [88.33%, 94.71%].”
specificityas written: “BW Image Level Specificity”0.984CI [96.20%, 99.44%]
source quote (p.16)
“Specificity remained consistent at 98.4% across definitions with a CI of [96.20%, 99.44%].”
sensitivityas written: “IOPA Image Level Sensitivity (Conservative)”0.831CI [78.87%, 86.80%]
source quote (p.16)
“IOPA Image Level: Sensitivity was remarkably high at 83.1% with a CI of [78.87%, 86.80%] under conservative conditions”
sensitivityas written: “IOPA Image Level Sensitivity (Optimistic)”0.918CI [88.54%, 94.42%]
source quote (p.16)
“and under optimistic conditions, it improved to 91.8%, with a CI of [88.54%, 94.42%]”
specificityas written: “IOPA Image Level Specificity”0.984CI [96.20%, 99.44%]
source quote (p.16)
“Specificity was also impressive at 98.4% with a CI of [96.20%, 99.44%].”
aurocas written: “MRMC IOPA Aided AUC”0.845
source quote (p.17)
“The results from the aided groups, displaying AUCs of 0.848 for BW and 0.845 for IOPA images, significantly surpass those of the unaided groups, which recorded AUCs of 0.806 and 0.807, respectively.”
aurocas written: “MRMC BW Unaided AUC”0.806
source quote (p.17)
“The results from the aided groups, displaying AUCs of 0.848 for BW and 0.845 for IOPA images, significantly surpass those of the unaided groups, which recorded AUCs of 0.806 and 0.807, respectively.”
aurocas written: “MRMC IOPA Unaided AUC”0.807
source quote (p.17)
“The results from the aided groups, displaying AUCs of 0.848 for BW and 0.845 for IOPA images, significantly surpass those of the unaided groups, which recorded AUCs of 0.806 and 0.807, respectively.”
sensitivityas written: “MRMC BW Aided Sensitivity (Image Level)”0.509
source quote (p.18)
“For BW images, the aided sensitivity is quantified at 0.509, an increase from the unaided sensitivity of 0.444.”
sensitivityas written: “MRMC BW Unaided Sensitivity (Image Level)”0.444
source quote (p.18)
“For BW images, the aided sensitivity is quantified at 0.509, an increase from the unaided sensitivity of 0.444.”
sensitivityas written: “MRMC IOPA Aided Sensitivity (Image Level)”0.619
source quote (p.18)
“Similarly, for IOPA images, aided sensitivity rises to 0.619 from 0.564 in unaided conditions.”
sensitivityas written: “MRMC IOPA Unaided Sensitivity (Image Level)”0.564
source quote (p.18)
“Similarly, for IOPA images, aided sensitivity rises to 0.619 from 0.564 in unaided conditions.”
specificityas written: “MRMC BW Aided Specificity (Image Level)”0.682
source quote (p.18)
“For BW images, the overall specificity increased slightly from 0.634 in unaided conditions to 0.682 in aided conditions.”
specificityas written: “MRMC BW Unaided Specificity (Image Level)”0.634
source quote (p.18)
“For BW images, the overall specificity increased slightly from 0.634 in unaided conditions to 0.682 in aided conditions.”
specificityas written: “MRMC IOPA Aided Specificity (Image Level)”0.844
source quote (p.18)
“the specificity analysis for IOPA images shows a more pronounced improvement under aided conditions, with specificity increasing from 0.813 to 0.844.”
specificityas written: “MRMC IOPA Unaided Specificity (Image Level)”0.813
source quote (p.18)
“the specificity analysis for IOPA images shows a more pronounced improvement under aided conditions, with specificity increasing from 0.813 to 0.844.”
sensitivityas written: “MRMC BW Aided Sensitivity (Surface Level)”0.763
source quote (p.18)
“For BW Images, the overall sensitivity under aided conditions is significantly higher (0.763) compared to unaided conditions (0.707)”
sensitivityas written: “MRMC BW Unaided Sensitivity (Surface Level)”0.707
source quote (p.18)
“For BW Images, the overall sensitivity under aided conditions is significantly higher (0.763) compared to unaided conditions (0.707)”
sensitivityas written: “MRMC IOPA Aided Sensitivity (Surface Level)”0.746
source quote (p.18)
“For IOPA Images, aided conditions show a higher overall sensitivity (0.746) than unaided conditions (0.691)”
sensitivityas written: “MRMC IOPA Unaided Sensitivity (Surface Level)”0.691
source quote (p.18)
“For IOPA Images, aided conditions show a higher overall sensitivity (0.746) than unaided conditions (0.691)”
specificityas written: “MRMC BW Aided Specificity (Surface Level)”0.98
source quote (p.18)
“For BW Images, the overall specificity under aided conditions shows an increase to 0.980 from 0.974 in unaided conditions.”
specificityas written: “MRMC BW Unaided Specificity (Surface Level)”0.974
source quote (p.18)
“For BW Images, the overall specificity under aided conditions shows an increase to 0.980 from 0.974 in unaided conditions.”
specificityas written: “MRMC IOPA Aided Specificity (Surface Level)”0.983
source quote (p.19)
“for IOPA Images, the overall specificity under aided conditions is slightly improved at 0.983 compared to 0.979 in unaided conditions.”
specificityas written: “MRMC IOPA Unaided Specificity (Surface Level)”0.979
source quote (p.19)
“for IOPA Images, the overall specificity under aided conditions is slightly improved at 0.983 compared to 0.979 in unaided conditions.”
Each value carries its own analysis unit and task — never compare or pool across devices. Source: 510(k) summary PDF.
Predicate network
Postmarket — what happened after clearance
0
recalls in product code, 24mo
0
MAUDE reports in code, 12mo
-100%
vs code's own 3-yr baseline
0
drift signals on this device
Recall and MAUDE counts are product-code-level (reports aren't reliably attributable to one device). Signals are descriptive observables with sources — never a judgment that the device is unsafe or drifting. Snapshot 2026-07-08.
Reimbursement — how devices like this got paid
Not yet tracked — no payment pathway indexed for this clearance (the reimbursement corpus is a growing seed set).