aBSI is intended to be used by trained healthcare professionals and researchers for acceptance, transfer, storage, image display, manipulation, quantification and reporting of digital medical images acquired using nuclear medicine (NM) imaging. The device provides general Picture Archiving and Communications System (PACS) tools as well as a clinical application for oncology including lesion marking and quantitative analysis.

Device Description

The aBSI is a software-only medical device that provides a fully quantitative assessment of a patient's skeletal disease on a bone scan, as the fraction of the total skeleton weight. The user of this product is typically a health-care professional using the software to view the patient images and analysis results.

AI/ML Overview

Here's a breakdown of the acceptance criteria and study information for the aBSI device, based on the provided text:

Acceptance Criteria and Device Performance

The document doesn't explicitly define a table of "acceptance criteria" with specific performance thresholds. Instead, it refers to the device's performance through verification testing and clinical studies, demonstrating its ability to quantify the Bone Scan Index (BSI) and its association with clinical outcomes.

However, based on the performance data presented, here's an inferred table of performance aspects and reported findings:

Performance Aspect	Reported Device Performance
BSI Calculation Linearity & Accuracy	Demonstrated during analytical validation studies. (Specific metrics not provided in the summary, but implied to be acceptable.)
BSI Calculation Precision	Demonstrated during analytical validation studies. (Specific metrics not provided in the summary, but implied to be acceptable.)
Reproducibility (different cameras)	Demonstrated during analytical validation studies. (Specific metrics not provided in the summary, but implied to be acceptable.)
Reproducibility (multiple images)	Demonstrated during analytical validation studies. (Specific metrics not provided in the summary, but implied to be acceptable.)
Reproducibility (repeated bone scans)	Demonstrated during patient study. (Specific metrics not provided in the summary, but implied to be acceptable.)
Hotspot Detection Algorithm Improvement	Improved algorithm from predicate. Clinical performance testing demonstrated "substantially equivalent performance" to the predicate, implying improvement while maintaining equivalence.
Association with Overall Survival (Study I)	Automated BSI (median=1.07; range: 0-32.60) was significantly associated with OS (HR:1.20; 95%CI:1.14-1.26; P<0.001). Median OS by automated aBSI quartile (lowest to highest) was 34.7, 27.3, 21.7, and 13.3 months, respectively.Automated aBSI remained independently associated with OS in a multivariate model (HR:1.06; 95%CI:1.01-1.11; P=0.03).
Association with Symptomatic Progression	Independently associated with symptomatic progression (HR:1.18: 95%Cl:1.13-1.23: P<0.001).
Association with Time to Opiate Use for Pain	Independently associated with time to opiate use for pain (HR:1.21: 95%Cl:1.15-1.29; P<0.001).
Association with OS (Study II)	An increase in aBSI was associated with OS at a Kendall's Tau of 0.52 when the aBSI increased by 0.6.The total quantitative assessment of increase in skeletal disease burden, with aBSI assessment, has the same association with overall survival as that defined by PCWG criteria (Kendall's Tau 0.52 for both aBSI increase and PCWG criteria for radiographic bone progression).
Comparison to PCWG Criteria	Of 169 patients, 90 (53%) had progression that met PCWG criteria. The total aBSI increase in these patients was 1.22 [IQR: 0.65-2.49] and a median relative increase of 109% [IQR: 40-377%]. The association with time to radiographic bone progression was 0.52 for both aBSI increase and PCWG criteria, indicating similar performance.

Study Details

2. Sample size(s) used for the test set and the data provenance:

Study I (Clinical Data):
- Sample Size: 721 evaluable patients.
- Data Provenance: Prospective, multi-site, international (241 sites in 37 countries, including the US). Part of a Phase 3 study (10TASQ10) for metastatic castration-resistant prostate cancer (mCRPC).
Study II (Clinical Data):
- Sample Size: 169 patients with bone scans available for aBSI analysis (from an initial 257 assessed patients).
- Data Provenance: Retrospective study at Memorial Sloan Kettering Cancer Center (MSKCC) – single site, from Phase II/II clinical trials of agents targeting the androgen receptor (AR) signaling axis for metastatic prostate cancer.
Bench Testing: No specific sample sizes for "test sets" are provided for linearity, accuracy, precision, or reproducibility studies. These are implied to be laboratory-based validation efforts, likely using standardized phantoms or controlled datasets that don't involve human patients as a "test set" in the clinical sense.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

The document does not explicitly state the number or qualifications of experts used to establish ground truth for the test sets in the clinical studies.

Study I: Ground truth for overall survival, progression-free survival, and opioid-induced survival would typically be established by clinical follow-up and documented patient outcomes, not directly by image review experts for the aBSI.
Study II: The comparison was against PCWG (Prostate Cancer Working Group) criteria for radiographic progression. PCWG criteria involve clinical interpretation, but the specific number of human readers or their qualifications used to apply these criteria for the 169-patient test set is not mentioned.

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

The document does not specify any adjudication method (e.g., 2+1, 3+1) for establishing ground truth in the clinical studies. For the clinical outcomes (e.g., overall survival), these are typically determined by the course of the disease and patient records, not through an adjudication process by image readers. For PCWG criteria, it's not detailed how consensus or disagreement was handled.

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 MRMC comparative effectiveness study involving human readers with and without AI assistance is mentioned in the provided text. The clinical studies focused on the performance of the aBSI algorithm itself in relation to clinical outcomes and PCWG criteria, rather than comparing human reader performance.

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

Yes, standalone performance was assessed. The reported clinical studies (Study I and Study II) evaluate the aBSI algorithm's performance (its quantitative assessment of BSI) as a standalone predictor or correlate of clinical outcomes (OS, progression, opiate use) and against PCWG criteria. The device is a "software-only medical device that provides a fully quantitative assessment."

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

Study I: The "ground truth" was clinical outcomes data (overall survival, progression-free survival, opioid-induced survival) rather than a direct image-based expert consensus.
Study II: The "ground truth" for comparison was PCWG criteria for radiographic progression (which represents consensus clinical guidelines for assessing progression) and overall survival (outcomes data).

8. The sample size for the training set:

The document does not provide any information about the sample size used for training the aBSI algorithm. It only details the studies used for clinical evaluation and verification.

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

The document does not provide any information on how ground truth was established for the training set, as details about the training process are not included in this 510(k) summary.

Summary

{0}------------------------------------------------

August 5, 2019

Image /page/0/Picture/1 description: The image shows the logo of the U.S. Food and Drug Administration (FDA). The logo consists of two parts: the Department of Health & Human Services logo on the left and the FDA logo on the right. The FDA logo features the letters "FDA" in a blue square, followed by the words "U.S. FOOD & DRUG ADMINISTRATION" in blue text.

EXINI Diagnostics AB % Donna-Bea Tillman, Ph.D. Senior Consultant Biologics Consulting Group, Inc. 1555 King Street. Suite 300 ALEXANDRIA VA 22314

Re: K191262

Trade/Device Name: aBSI Regulation Number: 21 CFR 892.2050 Regulation Name: Picture archiving and communications system Regulatory Class: Class II Product Code: LLZ Dated: May 9, 2019 Received: May 10, 2019

Dear Dr. Tillman:

We have reviewed your Section 510(k) premarket notification of intent to market the device referenced above and have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to legally marketed predicate devices marketed in interstate commerce prior to May 28, 1976, the enactment date of the Medical Device Amendments, or to devices that have been reclassified in accordance with the provisions of the Federal Food, Drug, and Cosmetic Act (Act) that do not require approval of a premarket approval application (PMA). You may, therefore, market the device, subject to the general controls provisions of the Act. Although this letter refers to your product as a device, please be aware that some cleared products may instead be combination products. The 510(k) Premarket Notification Database located at https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn.cfm identifies combination product submissions. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration. Please note: CDRH does not evaluate information related to contract liability warranties. We remind you, however, that device labeling must be truthful and not misleading.

If your device is classified (see above) into either class II (Special Controls) or class III (PMA), it may be subject to additional controls. Existing major regulations affecting your device can be found in the Code of Federal Regulations, Title 21, Parts 800 to 898. In addition, FDA may publish further announcements concerning your device in the Federal Register.

Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part 801); medical device reporting of medical device-related adverse events) (21 CFR 803) for

{1}------------------------------------------------

devices or postmarketing safety reporting (21 CFR 4, Subpart B) for combination products (see https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-reportingcombination-products); good manufacturing practice requirements as set forth in the quality systems (QS) regulation (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.

Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR Part 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to https://www.fda.gov/medical-device-safety/medical-device-reportingmdr-how-report-medical-device-problems.

For comprehensive regulatory information about mediation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medicaldevices/device-advice-comprehensive-regulatory-assistance) and CDRH Learn (https://www.fda.gov/training-and-continuing-education/cdrh-learn). Additionally, you may contact the Division of Industry and Consumer Education (DICE) to ask a question about a specific regulatory topic. See the DICE website (https://www.fda.gov/medical-device-advice-comprehensive-regulatoryassistance/contact-us-division-industry-and-consumer-education-dice) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).

Sincerely.

For

Thalia T. Mills, Ph.D. Director Division of Radiological Health OHT7: Office of In Vitro Diagnostics and Radiological Health Office of Product Evaluation and Quality Center for Devices and Radiological Health

Enclosure

{2}------------------------------------------------

Indications for Use

510(k) Number (if known) K191262

Device Name aBSI

Indications for Use (Describe)

Type of Use (Select one or both, as applicable)

☑ Prescription Use (Part 21 CFR 801 Subpart D)
☐ Over-The-Counter Use (21 CFR 801 Subpart C)

CONTINUE ON A SEPARATE PAGE IF NEEDED.

This section applies only to requirements of the Paperwork Reduction Act of 1995.

DO NOT SEND YOUR COMPLETED FORM TO THE PRA STAFF EMAIL ADDRESS BELOW.

The burden time for this collection of information is estimated to average 79 hours per response, including the time to review instructions, search existing data sources, gather and maintain the data needed and complete and review the collection of information. Send comments regarding this burden estimate or any other aspect of this information collection, including suggestions for reducing this burden, to:

Department of Health and Human Services Food and Drug Administration Office of Chief Information Officer Paperwork Reduction Act (PRA) Staff PRAStaff@fda.hhs.gov

"An agency may not conduct or sponsor, and a person is not required to respond to, a collection of information unless it displays a currently valid OMB number."

{3}------------------------------------------------

In accordance with 21 CFR 807.87(h) and (21 CFR 807.92) the 510(k) Summary for the aBSV is provided below.

SUBMITTER 1.

Applicant: EXINI Diagnostics AB Ideon Science Park Scheelevägen 27 223 70 Lund Sweden Aseem Anand, Ph.D. Contact: Vice President EXINI Diagnostics AB Ideon Science Park, Scheelevägen 27, SE-223 70 Lund, Sweden Tel: +46706604084 aseem.anand@exini.com Donna-Bea Tillman, Ph.D. Submission Correspondent: Senior Consultant Biologics Consulting 1555 King Street, Suite 300 (410) 531-6542 dtillman(@biologicsconsulting.com

2. DEVICE

Date Prepared:

Device Trade Name:	aBSI
Device Common Name:	Picture Archiving and Communications System(PACS)
Classification Name	21 CFR 892.2050 System, Image Processing,Radiological
Regulatory Class:	II
Product Code:	LLZ

May 9, 2019

3. PREDICATE DEVICE

Predicate Device: EXINI (K122205) K191262

{4}------------------------------------------------

DEVICE DESCRIPTION 4.

INTENDED USE/INDICATIONS FOR USE ನ.

SUBSTANTIVE EQUIVALENCE 6.

Comparison of Indications

The image modality computed tomography (CT) has been removed from the intended use for aBSI compared to EXINI. The ability to also display CT images was a feature introduced in EXINI to allow for simultaneous viewing of both types of images. CT images are not required or used for BSI calculation and this feature was rarely used. Therefore, this feature has been removed and CT images are not accepted by the aBSI device. This change does not affect the fundamental intended use of the device, and EXINI can be used as a predicate for aBSI.

Technological Comparisons

The table below compares the key technological features of the subject devices to the predicate device

	EXINI (predicate device)	aBSI (subject device)	Discussion of Differences
Intended user	Health care professionals andresearchers	Same	-
Intended useenvironment	Health care clinics	Same	-
Classification	System, Image Processing,Radiological (LLZ)21 CFR 892.2050	Same	-
Installation	Product CDs or downloadableinstallation files	Cloud-based service andaccess with personal log-in.	Does not affect the clinicaluse of the device
Operating system	Microsoft Windows	Microsoft Windows ormacOS with Chrome browser	Does not affect the clinicaluse of the device
	EXINI (predicate device)	aBSI (subject device)	Discussion of Differences
DICOMcompatibility	DICOM 3:• Whole body bone scans• Static (partial) bone scans• SPECT/CT	DICOM 3:• Whole body bone scans• SPECT	Static (partial) bone scansand CT images are notrequired or used for BSIcalculation.
Image upload	Via DICOM SCP or folder onlocal computer or network	Via folder on local computeror network	Does not affect the clinicaluse of the device
Support formultiple BoneScans	Yes, if multiple scans areprovided, the images areautomatically aligned vertically	Same	-
Colormaps	A selection of commonly usedcolormaps	Sub-Selection of previouslyprovided colormaps.	Optimal colormapscontinue to be provided
Zoom	Manually adjustable image sizeZoom	Automatically adjusted imagesizeZoom	To improve the efficiencyof aBSI automaticadjustment of images toscreen size
Windowing	• Automatic adjustment ofmaximum and minimumthresholds for image windowing• Manual adjustment ofmaximum and minimumthresholds	• Automatic adjustment ofmaximum and minimumthresholds for imagewindowing (same)• Manual adjustment ofmaximum and minimumthresholds has a wider range	Both devices shownormalized images atstartup and haveadjustable min and maxthresholds for imagewindowing.
Intensity display	Local intensity displayed atmouse pointer when hoveringover image	Local intensity displayed inleft corner of the image whenhovering over image	To improve visibility ofthe intensity
Image layouts	• Anterior and posterior imagesshown side by side• Mirror tool for switchingbetween the anterior andposterior image in the sameimage frame	• Anterior and posteriorimages shown side by side	Removal of feature doesnot impact clinical utilityof the device
Image QualityControl	• Total image intensitydisplayed• Skeletal image countdisplayed	• Total image intensitydisplayed	Both devices display totalimage intensities. Totalimage intensity is thecommon way of assessingimage quality, thereforetotal skeletal intensity isnot needed.
Hotspot display	• Hotspots displayed in image• Hotspot involvements aredisplayed in tables. One tableper scan.	• Hotspots displayed in image	Both devices displayhotspots in the images.
	EXINI (predicate device)	aBSI (subject device)	Discussion of Differences
Segmentation ofskeletal atlas	Segmentation of skeletal atlascovering the area from the skulldown to ¾ of the femur andhumerus.	Segmentation refined, andskeletal area covered by theatlas increased to cover theentire femur and humerus.	Allows for detection ofhotspots further out in thelimbs.
Normalization	Images are normalized so thathealthy bone tissue intensitiesare automatically set to apredefined level.	Same	-
Hotspot detection	Algorithm to detect highintensity regions of interestwithin the skeletal atlas.	Improved algorithm to detectof high intensity regions ofinterest within the skeletalatlas.	Results of clinicalperformance testingdemonstrate substantiallyequivalent performance.
Summary pageexport	Supported	Supported	-
CSV export	N/A	Supported	This feature wasimplemented to facilitateaBSI use in researchstudies.

Technological Comparison Table 1:

{5}------------------------------------------------

{6}------------------------------------------------

The EXINI was cleared in 2012 with BSI quantification as an integral feature. Since its clearance, the device algorithm has evolved, and the device is now hosted in cloud infrastructure. However, the essential BSI quantification feature of the device remained substantially equivalent.

PERFORMANCE DATA 7.

Biocompatibility Testing

There are no direct or indirect patient-contacting components of the subject device. Therefore, patient contact information is not needed for this device.

Electrical safety and electromagnetic compatibility (EMC)

Not applicable. The subject device is a software-only device. It contains no electric components, generates no electrical emissions, and uses no electrical energy of any type.

Software Verification and Validation Testing

Software verification and validation testing were conducted and documentation was provided as recommended by FDA's Guidance for Industry and FDA Staff, "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices." The software for this device was considered as a moderate level of concern because, although unlikely, an incorrect BSI value could potentially contribute to the risk of an incorrect therapy decision or delay in the delivery of appropriate care.

{7}------------------------------------------------

Bench Testing

EXINI Diagnostics conducted verification to demonstrate the performance of the device, including:

. A set of analytical validation studies to evaluate the performance of the aBSI v3.4 in quantifying bone scans, including:
- Linearity & Accuracy of BSI calculation o
- Precision of BSI calculation O
- Reproducibility with different cameras O
- o Reproducibility with multiple images
Patient study to demonstrate Reproducibility of BSI calculation with Repeated Bone Scans
Comparison testing using a phantom simulation to compare the bone scan index determined with predicate EXINI 1.7 to that the subject device aBSI.

Animal Testing

Not applicable. Animal studies are not necessary to establish the substantial equivalence of this device.

Clinical Data

Results from the two clinical studies comparing aBSI assessment to standard interpretation of bone scan demonstrated the utility of aBSI device against the state of the art (PCWG criteria) and essential clinical outcomes.

StudyNumber	Title	Objective	Design	Patients
I	Phase 3 validation of theautomated Bone Scan Indexassociation with overallsurvival in men with metastaticcastration-resistant prostatecancer	Association of aBSI withclinical outcome –overall survival,progression free survival,opioid induced survival	Prospective PlannedAnalysis – A multi-sitestudy phase III: NTC01234311	ProstateCancer(N=721)
II	Optimizing RadiographicProgression Free Survival byProstate Cancer WorkingGroup (PCWG) Criteria usingthe Automated Bone ScanIndex ( aBSI )	Comparison of aBSIincrease against countingnumber of new lesions(by PCWG criteria) inradiographic progression	Retrospective study atMemorial Sloan KetteringCancer Center – single site	ProstateCancer(N=169)

Study I involved a prospectively defined analysis of patients in a phase 3 international, multicenter study. This phase 3 study was a multicenter randomized, double-blind, placebocontrolled study of tasquinimod (10TASQ10) in metastation-resistant prostate cancer mCRPC patients. Study subjects were recruited at 241 sites in 37 countries (including the US).

{8}------------------------------------------------

Of the total 1245 phase 3 patients enrolled in 37 countries, 721 patients were evaluable with aBSI. The aBSI population was representative of the total study population based on baseline characteristics. Automated BSI (median=1.07; range: 0-32.60) was significantly associated with OS (HR:1.20; 95%CI:1.14-1.26; P<0.001). Median OS by automated aBSI quartile (lowest to highest) was 34.7, 27.3, 21.7, and 13.3 months, respectively. In a multivariate survival model, the automated aBSI remained independently associated with OS (HR:1.06; 95%CI:1.01-1.11; P=0.03). The automated BSI was also independently associated with symptomatic progression (HR:1.18: 95%Cl:1.13-1.23: P<0.001). and time to opiate use for pain (HR:1.21: 95%Cl:1.15-1.29; P<0.001). The results of Study I provide compelling evidence that the clinical performance of quantitative aBSI assessment is additive to the existing clinical parameters.

In Study II, patients at Memorial Sloan Kettering Cancer Center (MSKCC) with metastatic prostate cancer (mCRPC) were enrolled in Phase II/II clinical trials of agents targeting the androgen receptor (AR) signaling axis and were assessed retrospectively for this analysis. A total of 257 patients were assessed, of whom 169 had bone scans available for the aBSI analysis. The median aBSI at baseline was 3.1 (IOR: 1.3 - 7.1). An increase in aBSI was associated with OS at a Kendall's Tau of 0.52 when the aBSI increased by 0.6. An aBSI increase beyond 0.6 from first follow-up did not result in further improvement in the association with OS. The same association of time to radiographic bone progression was observed (0.52) with PCWG criteria. Of the 169 patients, 90 (53%) had progression in bone cancer that met the PCWG criteria. The total aBSI increase in patients that met the PCWG criteria was 1.22 [IQR: 0.65-2.49] and a median relative increase of 109% [IQR: 40-377%]. These results demonstrate that the total quantitative assessment of increase in skeletal disease burden, with aBSI assessment, has the same association with overall survival as that defined by PCWG criteria.

CONCLUSION 8.

Based on the detailed comparison between the predicate devices and the subject devices, the performance testing and clinical data, the aBSI can be found substantially equivalent to the predicate device.

Regulation Number and Section

§ 892.2050 Medical image management and processing system.

(a)
Identification. A medical image management and processing system is a device that provides one or more capabilities relating to the review and digital processing of medical images for the purposes of interpretation by a trained practitioner of disease detection, diagnosis, or patient management. The software components may provide advanced or complex image processing functions for image manipulation, enhancement, or quantification that are intended for use in the interpretation and analysis of medical images. Advanced image manipulation functions may include image segmentation, multimodality image registration, or 3D visualization. Complex quantitative functions may include semi-automated measurements or time-series measurements.(b)
Classification. Class II (special controls; voluntary standards—Digital Imaging and Communications in Medicine (DICOM) Std., Joint Photographic Experts Group (JPEG) Std., Society of Motion Picture and Television Engineers (SMPTE) Test Pattern).