MICSI-PET

{0} **FDA** U.S. FOOD & DRUG ADMINISTRATION September 11, 2026 Microstructure Imaging, Inc. % Adam Heroux Consultant Highland Biomedical, Inc. 4190 Grove St. Denver, Colorado 80211 Re: K261305 Trade/Device Name: MICSI-PET Regulation Number: 21 CFR 892.1200 Regulation Name: Emission computed tomography system Regulatory Class: Class II Product Code: KPS, LLZ Dated: August 10, 2026 Received: August 11, 2026 Dear Adam Heroux: 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 (the 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 available 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. U.S. Food & Drug Administration 10903 New Hampshire Avenue Silver Spring, MD 20993 www.fda.gov {1} K261305 - Adam Heroux Page 2 Additional information about changes that may require a new premarket notification are provided in the FDA guidance documents entitled "Deciding When to Submit a 510(k) for a Change to an Existing Device" (https://www.fda.gov/media/99812/download) and "Deciding When to Submit a 510(k) for a Software Change to an Existing Device" (https://www.fda.gov/media/99785/download). Your device is also subject to, among other requirements, the Quality Management System Regulation (QMSR) (21 CFR Part 820), which includes, but is not limited to, ISO 13485 clause 7.3 (Design controls), ISO 13485 clause 8.3 (Nonconforming product), ISO 13485 clause 8.5.2 (Corrective action), and ISO 13485 clause 8.5.3 (Preventative action). Please note that regardless of whether a change requires premarket review, the QMSR requires device manufacturers to review and approve changes to device design and production (ISO 13485 clause 7.3 and ISO 13485 clause 7.5) and document changes and approvals in the Medical Device File (ISO 13485 clause 4.2.3). 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 (reporting of medical device-related adverse events) (21 CFR Part 803) for devices or postmarketing safety reporting (21 CFR Part 4, Subpart B) for combination products (see https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-reporting-combination-products); good manufacturing practice requirements as set forth in the Quality Management System Regulation (QMSR) (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR Part 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR Parts 1000-1050. All medical devices, including Class I and unclassified devices and combination product device constituent parts are required to be in compliance with the final Unique Device Identification System rule ("UDI Rule"). The UDI Rule requires, among other things, that a device bear a unique device identifier (UDI) on its label and package (21 CFR 801.20(a)) unless an exception or alternative applies (21 CFR 801.20(b)) and that the dates on the device label be formatted in accordance with 21 CFR 801.18. The UDI Rule (21 CFR 830.300(a) and 830.320(b)) also requires that certain information be submitted to the Global Unique Device Identification Database (GUDID) (21 CFR Part 830 Subpart E). For additional information on these requirements, please see the UDI System webpage at https://www.fda.gov/medical-devices/device-advice-comprehensive-regulatory-assistance/unique-device-identification-system-udi-system. Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR 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-devices/medical-device-safety/medical-device-reporting-mdr-how-report-medical-device-problems. For comprehensive regulatory information about medical devices and radiation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medical-devices/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 {2} K261305 - Adam Heroux Page 3 the DICE website (https://www.fda.gov/medical-devices/device-advice-comprehensive-regulatory-assistance/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, Daniel M. Krainak, Ph.D. Assistant Director DHT8C: Division of Radiological Imaging and Radiation Therapy Devices OHT8: Office of Radiological Health Office of Product Evaluation and Quality Center for Devices and Radiological Health Enclosure {3} | Indications for Use | | | | --- | --- | --- | | Please type in the marketing application/submission number, if it is known. This textbox will be left blank for original applications/submissions. | K261305 | ? | | Please provide the device trade name(s). | | ? | | MICSI-PET | | | | Please provide your Indications for Use below. | | ? | | MICSI-PET is an image processing software that can be used for image enhancement in PET images. It computes quantitative metrics including regional SUVr (Standardized Uptake Value ratio), Centiloid scores for amyloid and tau PET, and z-scores compared to normative controls. | | | | Please select the types of uses (select one or both, as applicable). | ☑ Prescription Use (21 CFR 801 Subpart D) ☐ Over-The-Counter Use (21 CFR 801 Subpart C) | ? | | Please select the age group(s) for which the device(s) is to be used. | ☐ Neonates/Newborns (Birth to < 29 days old) ☐ Infants (29 days old to < 2 years old) ☐ Children (2 years old to < 12 years old) ☐ Adolescents (12 years old to < 22 years old) ☑ Adults (22 years old and greater) | ? | {4} MiCSI 510(k)# K261305 510(k) Summary 11SEP2026 # Contact Details 21 CFR 807.92(a)(1) Applicant Information: Microstructure Imaging, Inc. 370 Jay St, FL 7 Brooklyn, NY 11201 United States 718-801-2324 Dr. Gregory Lemberskiy gregory.lemberskiy@micsi.com Correspondent: Highland Biomedical, Inc. 4190 Grove St Denver, CO 80211 United States 617-823-0515 Adam Heroux adam.heroux@highlandbiomed.com # Device Name 21 CFR 807.92(a)(2) Device Trade Name: MICSI-PET Classification/Common Name: Emission computed tomography system Regulation Number: 21 CFR 892.1200 Product Code(s): KPS, LLZ Device Class: Class II # Legally Marketed Predicate Devices 21 CFR 807.92(a)(3) Predicate Device # K211964 Predicate Trade Name: SubtlePET Regulation Number: 21 CFR 892.1200 Product Code: KPS, LLZ Reference Device: Reference Device # K233620 Reference Trade Name: MIM - Centiloid Scaling Regulation Number: 21 CFR 892.2050 Reference Product Code: LLZ # Device Description Summary 21 CFR 807.92(a)(4) MICSI-PET Super-Resolution (MICSI-PET) is a Software as a Medical Device (SaMD) intended to enhance positron emission tomography (PET) brain images using super-resolution techniques and to compute standardized quantitative metrics for amyloid and tau PET imaging. The software supports three PET tracer categories: amyloid (Florbetapir, Florbetaben, {5} MiCSI 510(k)# K261305 510(k) Summary 11SEP2026 Flutemetamol, PiB), tau (Flortaucipir), and FDG. The device is intended to be used by radiologists and nuclear medicine physicians in an imaging center, clinic, or hospital. The device is compatible with the DICOM 3.0 standard. The subject device has no direct user interface. The DICOM images obtained from a compatible PET/CT and/or PET/MR scanner are streamed from the scanner to the designated DICOM destination, e.g., picture archiving and communication system (PACS), then to a DICOM router and processor. It is within this router and processor where the subject device performs super-resolution enhancement and quantitative analysis. The software requires MR images (T1-weighted) for anatomical reference which are co-registered to PET images during processing; the MR images are used both to guide the super-resolution algorithm and to perform atlas-based brain segmentation for quantitative analysis. Once the processing is complete, the device outputs are then routed to the target PACS (which can be the same one as before or a new DICOM destination) where the intended user can view the enhanced images, quantitative reports, and the original images. Image processing time varies as it is dependent on the central processing unit (CPU), input image size, and the selected processing configuration. When multiple jobs have been submitted to MICSI-PET, they are processed sequentially based on the order received. ### Intended Use/Indications for Use 21 CFR 807.92(a)(5) MICSI-PET is an image processing software that can be used for image enhancement in PET images. It computes quantitative metrics including regional SUVr (Standardized Uptake Value ratio), Centiloid scores for amyloid and tau PET, and z-scores compared to normative controls. ### Indications for Use Comparison 21 CFR 807.92(a)(5) The indications for use for the subject device are substantially similar to those for the predicate device. Both the proposed device and the predicate are intended to process and enhance PET images. MICSI-PET compared to the reference predicate has a narrower scope but is substantially equivalent to the indications associated with Centiloid scoring, and the computation of z-scores. ### Technological Comparison 21 CFR 807.92(a)(6) The following information provides a summary of how the technological characteristics of the devices compare. MICSI-PET is similar to the predicate with the following characteristics: - Same intended use environment and user - Similar output of enhanced PET imaging - Both software process FDG and Amyloid Tracer cases {6} MICSI 510(k)# K261305 510(k) Summary 11SEP2026 MICSI-PET has the following differences from the predicate and reference devices: - Different tracers- the predicate device also includes the following tracers: 18F-DOPA, 18F-DCFPyL, Ga-68 Dotatate, and Ga-68 PSMA. MICSI-PET also includes the processing of Flortaucipir. - Different imaging anatomy - In addition to brain imaging, the reference device can process alternate anatomical locations while MICSI-PET is indicated for brain imaging. - Different software architecture - MICSI-PET utilizes physics-based software and MRI anatomical registration, whereas the predicate utilizes an AI/ML model to provide the enhanced imaging output. - Different functionality - while the predicate and reference have features not included in MICSI-PET, the functionality of image enhancement, centiloid display and z-scores are included in the predicate and reference devices. MICSI-PET has undergone software and performance testing to ensure that any differences in the technological characteristics do not raise different questions of safety and effectiveness ### Non-Clinical and/or Clinical Tests Summary & Conclusions 21 CFR 807.92(b) Summary of Non-clinical Testing: Non-clinical testing consisted of Software Verification and Validation testing at the unit, integration, and system level to demonstrate that software requirements were implemented. ### Rater Study: A retrospective, multi-rater study was conducted to Evaluate Quantitative and Qualitative performance of the device including Image Quality Enhancement, Reduction in Artifacts, Tracer Positivity, SNR, Median SUVr (mSUVr), STD SUVr (sSUVr), Median Z-Score, STD Z-Score, and SUVr Correlation. Qualitative-Quantitative Concordance testing was also conducted to demonstrate Visual vs Centiloid Positivity, and Visual vs Z-Score Positivity. ### Rater Study Results: - MICSI-PET improved reader-rated Image Quality relative to SOC across all tracers. The pooled mean Image Quality increased from 3.04 (SOC) to 4.59 (MICSI-PET) on a 5 point scale, corresponding to a paired mean improvement (MICSI-PET – SOC) of +1.55; - MICSI-PET reduced reader-rated Artifact Severity relative to SOC across all tracers. The pooled mean Artifact Severity decreased from 1.43 (SOC) to 1.11 (MICSI-PET) on a 3 {7} MICSI 510(k)# K261305 510(k) Summary 11SEP2026 point scale, corresponding to a paired mean improvement (SOC – MICSI-PET; positive indicates fewer artifacts) of +0.32 across N=664 paired reads - MICSI-PET maintained high overall agreement in reader binary tracer positivity classifications relative to SOC across amyloid and tau tracers. The pooled Tracer Positivity Agreement between SOC and MICSI-PET was 0.87, and the pooled McNemar test indicated no significant directional difference in positivity classification, p=0.203. Agreement was consistently high across individual tracers, FLP 0.87, FBB 0.86, FMT 0.88, and TAU 0.88. These results show that MICSI-PET generally preserved binary tracer positivity determinations relative to SOC. - MICSI-PET demonstrated statistically significant improvement in SNR relative to SOC, with statistically significant processing differences in mSUVr and sSUVr. - SUVr agreement met the acceptance criterion under both ROI frameworks (GAAIN reference ROIs and MICSI-derived ROIs), with R² values of [GAAIN: 0.997] and [MICSI: 0.995] across amyloid tracers. SUVr agreement met the acceptance criterion for the Universal ROI under both ROI frameworks. (GAAIN reference ROIs and MICSI-derived ROIs), with R² values of [GAAIN: 0.998] and [MICSI: 0.998]. SUVr agreement met the acceptance criterion using MICSI-derived cortical ROIs with R² values of [MICSI: 0.979]. - Z-scores met pre-defined acceptance criteria: For the amyloid aggregate, the SOC/GAAIN vs MICSI-PET/MICSI combined comparison yielded mZ 1.739 to 1.839 and sZ 1.080 to 0.975. The reciprocal combined comparison (SOC/MICSI vs MICSI-PET/GAAIN) yielded mZ 1.555 to 1.863 and sZ 0.985 to 1.038. For the tau Universal ROI, SOC/GAAIN vs MICSI-PET/MICSI: mZ changed from 1.973 to 1.100 and sZ changed from 1.079 to 1.092. SOC/MICSI vs MICSI-PET/GAAIN): mZ changed from 1.016 to 2.006 and sZ changed from 1.118 to 1.052. The opposing directions across the two combined comparisons are consistent with ROI framework differences shifting the absolute z-score scale; therefore, combined contrasts should be interpreted in the context of the ROI-only comparisons rather than as processing-only effects. - Across pooled amyloid and individual amyloid tracers, concordance between visual amyloid tracer positivity classification and centiloid values consistently exceeded the pre-specified acceptance threshold of AUC ≥ 0.80 under SOC and MICSI-PET processing and under both MICSI and GAAIN ROI definitions. - Amyloid (pooled): AUCs were 0.909 (SOC+GAAIN) and 0.914 (SOC+MICSI), and 0.959 (MICSI-PET+GAAIN) and 0.959 (MICSI-PET+MICSI). - Florbetapir (FLP): AUCs were 0.934 (SOC+GAAIN) and 0.940 (SOC+MICSI), and 0.949(MICSI-PET+GAAIN) and 0.958 (MICSI-PET+MICSI). {8} MiCSI 510(k)# K261305 510(k) Summary 11SEP2026 ○ Florbetaben (FBB): AUCs were 0.870 (SOC+GAAIN) and 0.875 (SOC+MICSI), and 0.951 (MICSI-PET+GAAIN) and 0.953 (MICSI-PET+MICSI). ○ Flutemetamol (FMT): AUCs were 0.929 (SOC+GAAIN) and 0.933 (SOC+MICSI), and 0.969 (MICSI-PET+GAAIN) and 0.965 (MICSI-PET+MICSI). - Across pooled amyloid and individual amyloid tracers, concordance between visual amyloid tracer positivity classification and z-score values consistently exceeded the pre-specified acceptance threshold of AUC ≥ 0.80 under SOC and MICSI-PET processing and under both MICSI and GAAIN ROI definitions. ○ Amyloid (pooled): AUCs were 0.904 (SOC+GAAIN) and 0.911 (SOC+MICSI), and 0.951 (MICSI-PET+GAAIN) and 0.958 (MICSI-PET+MICSI). ○ Florbetapir (FLP): AUCs were 0.922 (SOC+GAAIN) and 0.940 (SOC+MICSI), and 0.930 (MICSI-PET+GAAIN) and 0.959 (MICSI-PET+MICSI). ○ Florbetaben (FBB): AUCs were 0.855 (SOC+GAAIN) and 0.868 (SOC+MICSI), and 0.939 (MICSI-PET+GAAIN) and 0.952 (MICSI-PET+MICSI). ○ Flutemetamol (FMT): AUCs were 0.927 (SOC+GAAIN) and 0.928 (SOC+MICSI), and 0.962 (MICSI-PET+GAAIN) and 0.963 (MICSI-PET+MICSI) - Across tau ROIs, concordance between visual tau tracer positivity classification and centiloid values generally met the pre-specified acceptance threshold of AUC ≥ 0.80, with the strongest performance in the meta-temporal and temporoparietal ROIs. ○ Universal: AUCs were 0.901 (SOC+GAAIN) and 0.840 (SOC+MICSI), and 0.872 (MICSI-PET+GAAIN) and 0.817 (MICSI-PET+MICSI). ○ Mesial: AUCs were 0.880 (SOC+GAAIN) and 0.878 (SOC+MICSI), and 0.879 (MICSI-PET+GAAIN) and 0.834 (MICSI-PET+MICSI). ○ Meta: AUCs were 0.902 (SOC+GAAIN) and 0.910 (SOC+MICSI), and 0.901 (MICSI-PET+GAAIN) and 0.907 (MICSI-PET+MICSI). ○ TemporoParietal: AUCs were 0.903 (SOC+GAAIN) and 0.864 (SOC+MICSI), and 0.872 (MICSI-PET+GAAIN) and 0.833 (MICSI-PET+MICSI). ○ Frontal: AUCs were 0.809 (SOC+GAAIN), with 0.759 (SOC+MICSI), 0.795 (MICSI-PET+GAAIN), and 0.770 (MICSI-PET+MICSI), indicating that frontal ROI concordance did not consistently meet the AUC ≥ 0.80 acceptance threshold across configurations. - Across tau ROIs, concordance between visual tau tracer positivity classification and z-score values similarly met the pre-specified acceptance threshold of AUC ≥ 0.80 for most ROIs, with strongest performance again in the meta-temporal and temporoparietal ROIs. ○ Universal: AUCs were 0.901 (SOC+GAAIN) and 0.864 (SOC+MICSI), and 0.869 (MICSI-PET+GAAIN) and 0.861 (MICSI-PET+MICSI). {9} MICSI 510(k)# K261305 510(k) Summary 11SEP2026 - ○ **Mesial:** AUCs were 0.899 (SOC+GAAIN) and 0.884 (SOC+MICSI), and 0.892 (MICSI-PET+GAAIN) and 0.860 (MICSI-PET+MICSI). - ○ **Meta:** AUCs were 0.925 (SOC+GAAIN) and 0.904 (SOC+MICSI), and 0.912 (MICSI-PET+GAAIN) and 0.907 (MICSI-PET+MICSI). - ○ **TemporoParietal:** AUCs were 0.902 (SOC+GAAIN) and 0.878 (SOC+MICSI), and 0.869 (MICSI-PET+GAAIN) and 0.858 (MICSI-PET+MICSI). - ○ **Frontal:** AUCs were 0.820 (SOC+GAAIN), with 0.726 (SOC+MICSI), 0.794 (MICSI-PET+GAAIN), and 0.754 (MICSI-PET+MICSI), indicating that frontal ROI concordance did not consistently meet the AUC ≥ 0.80 acceptance threshold across configurations. ### Rater Study Conclusion: The non-clinical bench performance testing demonstrated that MICSI-PET processing improved qualitative image quality and reduced artifact severity across all evaluated tracers while maintaining high agreement with standard-of-care (SOC) expert visual tracer positivity classifications. Quantitatively, MICSI-PET preserved expected SUVr relationships and showed strong concordance between continuous Centiloid and z-score measures and expert visual reads. Amyloid concordance met the pre-specified acceptance threshold across all evaluated configurations, while tau concordance generally met the acceptance threshold across the universal, mesial, meta-temporal, and temporoparietal ROI definitions. Taken together, these findings support that MICSI-PET is substantially equivalent to SOC processing, while providing enhanced visual interpretability and precise quantitative outputs. ### Overall Conclusions: The Non-Clinical and Rater Study testing have demonstrated that MICSI-PET shows substantially equivalent performance to the predicate device and is as safe and as effective for the proposed intended use.