Skip to main content

LCD L40224: Automated Detection and Quantification of Brain MRIs

LCD L40224, Automated Detection and Quantification of Brain MRIs, is the Local Coverage Determination that CGS Administrators, LLC applies to claims from 2 states (KY, OH), effective 2026-01-19. The policy text runs 19 words. No other contractor publishes a policy with this title.

QuickIntell editorial content · Legacy registry date · Review not verified

Data effective
Data currency: Medicare Coverage Database LCD export release of September 24, 2026 (effective September 20, 2026). Next CMS release: weekly (Thursdays) for the MCD.
Contractor
CGS Administrators, LLC
States and territories
2
KY OH
Revision effective
2026-01-19
Original effective
2026-01-19
Policy text
19 words
Covered ICD-10 codes (articles)
0

Where this LCD applies

Each contract number is a jurisdiction on the remittance; the policy binds claims processed under these contracts and no others.

Contracts that apply LCD L40224
ContractContractorTypeStates
15102CGS Administrators, LLCMAC - Part BKY
15202CGS Administrators, LLCMAC - Part BOH
15101CGS Administrators, LLCMAC - Part AKY
15201CGS Administrators, LLCMAC - Part AOH

Billing and coding: diagnoses and procedure codes

Since 2019 the codes live in the companion article rather than the LCD. Billing and Coding A60245 (Billing and Coding: Automated Detection and Quantification of Brain Magnetic Resonance Imaging) carries the diagnosis and procedure lists the contractor loads as the claims edit. CPT codes are shown as bare numbers because the descriptors are licensed by the AMA; HCPCS Level II descriptors are public and shown.

A60245: Billing and Coding: Automated Detection and Quantification of Brain Magnetic Resonance Imaging (Billing and Coding)

Covered ICD-10-CM codes
0
0 groups
Non-covered ICD-10-CM codes
0
Procedure codes listed
2
Full article
cms.gov record

Procedure codes: 0865T, 0866T.

Coverage indications, limitations and medical necessity

This is a non-coverage policy for artificial intelligence assistive software tool for automated detection and quantification of the brain.

Summary of evidence (opening)

Background

There is interest in artificial intelligence algorithms (machine learning and deep learning) to provide automation of neuroimaging in effort to improve accuracy, reduce bias and aid in clinical decision-making. 1

Structural imaging has the potential to reduce variance and improve diagnostic and prognostic inferences from MRI scans. However, the tools must be trained and validated in a manner that provides generalizability to broader populations. When a single data set or small number of individuals are used to train the programs, the results may be overestimated. A systematic review was conducted that describes and compares the available tools, with the aim to assess their translational potential into real-world clinical settings. 2 Of 8 tools identified 2 were not approved for medical use and one had no associated references. Most of the tools were found to have been validated using a small number of cases and a single data set. They compared the tools based on the number of validation methods for which was conducted. None of the tools account for intrascanner variability resulting from differences in the scanners, magnetic field and acquisition parameters and therefore lack generalizability. The author concludes that the majority of available tools make use of multivariant machine learning methods and have potential to open up new possibilities in personalized medicine. However, they caution results should be interpreted with vigilance due to the limitations in these studies especially related to small sample size and poor methodology. They also caution that results must be interpreted in light of the patient’s clinical history and symptomatology.

The American Society of Functional Neuroradiology (ASFNR) and the American Society of Neuroradiology (ASNR) acknowledge the challenges with artificial intelligence in neurology an created an Artificial intelligence Workshop Technology Workgroup. 3 This group published a critical appraisal of Artificial Intelligence (AI)-enabled imaging tools using the levels of evidence system in the American Journal of Neuroradiology. They call for critical appraisal of enabled image tools throughout the life cycle from development to implementation using systematic, standardized and an objective approach that can verify both the technical and clinical efficacy of the tool. A challenge in developing AI models is access to comprehensive and large data sets that can be utilized to train the technology. This data should represent the intended population and provide a diverse group from which the data may be extrapolated. This paper provides a resource for clinicians to aid in critical assessment of AI technologies to ensure safe and effective implementation into healthcare practices.

The contractor cites 54 sources in the bibliography; the full summary and analysis of evidence are in the CMS record.

Dates, lineage and related policies

Original determination effective
2026-01-19
Current revision effective
2026-01-19
Last reviewed by the contractor
2025-11-12
MCD version
3

The contractor lists one National Coverage Determination as related: NCD 200.3 Monoclonal Antibodies Directed Against Amyloid for the Treatment of Alzheimer's Disease (AD). Where an NCD speaks, it controls; the LCD can only address what the NCD leaves open.

Other related documents: A60362 (Response to Comments).

Using this policy on a claim

Match the documented indication to the covered indications above before the service is scheduled, carry a diagnosis from the article's covered list on the claim line, and keep the elements the documentation section asks for in the record, because the contractor can request it later through medical review. A denial under this policy arrives as CARC 50 with remark N115; the LCD lookup guide walks through the appeal path and the Advance Beneficiary Notice rules, and the CGS Administrators, LLC hub lists every other active policy from the same contractor.

Frequently asked questions

What does LCD L40224 cover?

This is a non-coverage policy for artificial intelligence assistive software tool for automated detection and quantification of the brain. The full indications and limitations are reproduced on this page from the CMS Medicare Coverage Database export of September 24, 2026.

Which states does LCD L40224 apply to?

CGS Administrators, LLC applies it to Medicare claims in KY, OH. A Local Coverage Determination binds only the contractor that wrote it; the same service in another jurisdiction is judged under that contractor's own policy or, where none exists, claim by claim.

Which diagnosis codes support medical necessity under LCD L40224?

The current export links no billing and coding article with a diagnosis list to this LCD, so coverage is decided on the indications in the policy text and the documentation in the record rather than by an automated diagnosis edit.

How do I appeal a denial under LCD L40224?

The remittance carries claim adjustment reason code 50 with remark code N115, naming the LCD. Compare the documented indication with the policy's covered indications and the article's diagnosis list, then file a redetermination within 120 days with the record attached; if the service genuinely falls outside the policy, the patient can be billed only when a valid Advance Beneficiary Notice was obtained before the service.

Sources

Every figure on this page is taken from the CMS publications below, as released by the Centers for Medicare & Medicaid Services. Projection built 2026-10-02. Verify against the primary file before billing or contracting decisions.

Disclaimer

The policy text and code lists are reproduced from the CMS Medicare Coverage Database export as an operational reference. Verify against the current LCD and article on cms.gov before billing; coverage depends on the full record and the contractor. Not legal, clinical or billing advice.