Digital Pathology AI
B

Biomy

Biomy makes DeepPathFinder, cloud software that uses AI to map immune and cancer cells on tissue slides for drug research. Drug companies, contract research organizations, clinical laboratories and research groups use it to look for patterns that could become biomarkers: signs that predict which patients will respond to a treatment.

The software finds and counts cells on H&E and multi marker stained slides, scores IHC markers such as HER2, ER, PgR and Ki67, predicts gene changes such as BRAF, KRAS and MSI high status from a routine slide, and studies how cells cluster within a tumor. It is sold for research only, not for clinical use.

Since January 2025, Biomy and NEC have marketed it together as a platform for biomarker discovery. Biomy also works with Chugai Pharmaceutical on AI programs to support cancer pathology diagnosis, and the contract research organization Shin Nippon Biomedical Laboratories formed a capital alliance with it in 2024. In 2026 it began building Virtual Cell, a foundation model of the tumor environment, with spatial data from 10x Genomics and technical collaboration with NVIDIA, under a Japanese government AI program.

Biomy is a Tokyo company founded in 2019 and holds a Japanese medical device marketing license. No price is published.

AI Health Index verifiedNovember 8, 2026
Compare Biomy with other vendors
Founded
2019
Headquarters
Tokyo, Japan
Categories
pathology-ai, drug-discovery
Indexed Products
DeepPathFinder
Buyer Segments
Biopharma research and development, Contract research organizations, Clinical laboratories (research use), Academic researchers
Assessment

Capability Axes

An AI Health Index grade measures what a buyer can verify from public sources on the date shown. It is not a rating of how good the product is. A vendor can build an excellent system and grade low on an axis because it publishes nothing an outsider can check. How grades read

AI Capability
AA on AI CentralityThe artificial intelligence is the product. Remove the model and there is nothing left to sell.
Vendor Published

The models are the product. DeepPathFinder is deep learning analysis of pathology slides, finding and counting immune and cancer cells and their spatial patterns. The biomarker discovery services Biomy offers with NEC are built on it. Biomy sells no scanner, laboratory service or data product that would stand without the models.

DD on Autonomy and Oversight ModelNo oversight structure is published. An absolute claim that the system does not err grades here too, because a buyer who believes it will not build the review step that would catch a failure.
Vendor Published

There is no published oversight structure. DeepPathFinder is labeled for research use only, which keeps it out of patient care. But Biomy describes no review of its cell detections or biomarker outputs, and no confidence threshold. Nor does it say how a result is meant to be checked before a researcher relies on it in a study or in deciding how to group patients.

BB on Model and Technology TransparencyThe approach or the suppliers are named without the version and update discipline behind them. Naming a supplier is the entry to this band both here and on Model Supply Chain Disclosure, which ask different questions of the same disclosure: who receives the data, and what produces the output.
Vendor Published

The training approach is described, without architecture, versions or update practice. Biomy says DeepPathFinder's models are trained on pathologist annotations together with labels taken from immunofluorescence and multiplex IHC on the same tissue, which lets them pick out cells on H&E that a reader cannot tell apart. The models predict gene changes such as BRAF, KRAS and MSI high status from morphology and derive features such as lymphocyte and fibroblast density in stroma and the distance of each lymphocyte from the tumor.

Biomy is developing a Virtual Cell foundation model trained on spatial transcriptomics data from 10x Genomics' Xenium platform. No model architecture, training data volume, version or update practice is published.

BB on Model Supply Chain DisclosureSubstantial partial disclosure, or a chain that is structurally short: an in house build, a cleared model that cannot be quietly swapped, or a deployment where the transfer does not occur at all. Naming the model provider exits the band below into this one; the axis rises from here on the completeness of the party list and on the terms that govern data once it arrives.
Vendor Published

Biomy develops DeepPathFinder's models itself with academic collaborators, and no outside model provider is named or implied. Its home page shows AWS, Microsoft and NVIDIA among its collaborators, without saying which hosts customer data, and its Virtual Cell work draws on spatial data from 10x Genomics and technical collaboration with NVIDIA.

When the platform is sold with NEC, NEC's image analysis is combined with Biomy's, without saying who processes which images. No subprocessor list is published.

CC on Clinical and Operational EvidenceNamed customers, or vendor reported percentages with no method, denominator or reference standard. Scale of use is recorded here and is not treated as evidence of benefit.
Vendor Published

Research is listed by title, without customers or figures on Biomy's site. Biomy lists ASCO abstracts from 2023, 2024 and 2025, including AI quantification of tumor infiltrating lymphocytes in triple negative breast cancer, a prognostic study of the same, and lymphocyte scores in ovarian cancer linked to PARP inhibitor outcomes. It names academic collaborators at the University of Tokyo and at Keio, Akita and Juntendo universities.

No customer, validation cohort, agreement with pathologists or performance figure is set out on its site or in its announcements.

DD on AI Safety and PHI StewardshipNothing published on how protected information moves through the system.
Vendor Published

Nothing Biomy publishes covers how patient data moves through the product. Its privacy policy promises appropriate security for personal information collected through its website.

Nothing says how long uploaded slides are kept on the cloud platform, whether they train Biomy's models, or how training data from its academic partners was de identified. No safety engineering for the models is published.

Regulatory and Compliance
DD on HIPAA and BAA PostureNo statement of status and no privacy document that reaches the product. Both halves are absent at this grade: a service level privacy document on its own lifts a vendor to the band above even where no status is stated. A website privacy notice, including one that says it does not cover customer data, does not reach the product, so a vendor whose only document is that notice and who states no status grades here.
Vendor Published

No privacy document covers the product, and no HIPAA position is stated. Biomy's privacy policy, written under Japan's Act on the Protection of Personal Information and undated, covers the personal information of customers and people who contact it. It does not address pathology images or patient data processed in DeepPathFinder.

No HIPAA position, business associate agreement or data processing agreement is published.

DD on Security Certifications and Trust CenterControls are asserted with nothing independent behind them, or nothing is published. Read the note before concluding anything: this is the grade most often corrected on a second pass, because assurance material frequently sits on a parent domain or inside an old announcement rather than on the product pages.
Vendor Published

Biomy publishes no security audit or certification. Its privacy policy promises appropriate security measures. No ISO/IEC 27001 certificate, SOC 2 report, penetration testing statement or trust center appears on its site. Certifications held by its cloud partners would be the host's, not Biomy's.

CC on FDA and Regulatory StatusNo device claim is made and the product is scoped accordingly. Most administrative and operational products sit here and are not penalized for it, because this axis grades the appropriateness of the positioning rather than possession of a clearance. A stated limit on use, such as research use only or a clause that the product gives no medical advice, beside marketing that sells the product for clinical decisions also sits here, with both quoted, because the buyer has to ask which one governs.
Vendor Published

Biomy makes no device claim, and the product is labeled for research. Biomy states that DeepPathFinder is for research use only and not for clinical use. The FDA's databases list no Biomy device.

Biomy holds a second class medical device marketing license from the Tokyo Metropolitan Government (13B2X10585, January 2024) and says it is preparing quality management and vigilance systems for software medical devices. Its memorandum with Chugai covers developing AI programs to support cancer pathology diagnosis, including assessment of response to neoadjuvant therapy. Its partnership with NEC, which holds a Japanese license to make and sell Class I medical devices, includes support for device approval. No Biomy product is presented as cleared or approved anywhere.

CC on AI Governance and Bias DisclosureResponsible artificial intelligence is committed to in policy language with no evaluation behind it. Most of the index sits here.
Vendor Published

Research is cited, but there is no evaluation across groups and no governance process. Biomy points to conference abstracts and academic collaborations. It publishes no results by tissue type, stain, scanner, laboratory or patient group, and describes no process for evaluating models before release or monitoring them afterward.

DD on AI Liability and RecourseNothing published on what happens when the system is wrong.
Vendor Published

What happens when the system is wrong goes unaddressed. No error rate, review step, warranty, remedy or correction route for DeepPathFinder outputs appears on Biomy's site, and the product is labeled for research use only.

Integration and Deployment
DD on EHR and Interoperability DepthNo integration evidence. A connector described as available on request grades here until one exists.
Vendor Published

The company publishes no integration. DeepPathFinder is a cloud platform for research analysis. No image management system, scanner, laboratory system, data format or interface is named for bringing slides in or sending results to a customer's research systems.

CC on Deployment Model and Data ResidencyA single hosted option with location implied rather than committed.
Vendor Published

DeepPathFinder is described as cloud based, and where it runs is implied, not stated. Biomy names AWS, Microsoft and NVIDIA among its technology partners. Nothing published says which cloud hosts customer slides, in which region, or whether images leave Japan.

Commercial
CC on Commercial TransparencyNo price is published and the posture is discoverable: a buyer can establish how the product is sold and what drives the cost before contacting the vendor. Most of the index sits here.
Vendor Published

No price is published, but the outline of how the product is sold can be worked out. DeepPathFinder is offered to drug companies and laboratories as cloud software and through biomarker discovery services. Since January 2025 it has been marketed together with NEC.

No license basis, per slide or per study price is published.

CC on Setting and Specialty CoverageCoverage is claimed broadly without specifics, or stated clearly with nothing validating it yet.
Vendor Published

Where DeepPathFinder applies is stated, but nothing on Biomy's pages validates it. It analyzes H&E and multiplex immunohistochemistry slides for tumor microenvironment research, scores HER2, ER, PgR and Ki67 stains, and predicts BRAF, KRAS and MSI high status, for research use only. Its listed abstracts cover triple negative breast cancer and ovarian cancer.

The company sells biomarker discovery for drug development, alone and with NEC, and pitches the software to drug companies and clinical laboratories. No validation by tissue type, stain or disease is published.

Alternatives

Alternatives to Biomy

Other products that do the same kind of work as Biomy, and what each one does.

All Biomy alternatives, with prices →

Lunit SCOPE is the pathology AI line of Lunit, the Seoul medical AI company. Drug companies, contract research organizations and digital pathology platforms use it to measure cancer biomarkers on tissue slides for research and trials.

Imagene AI reads routine stained lung cancer slides and predicts which gene changes a tumor carries, without using more tissue for sequencing.

Bioptimus is a Paris company that builds AI foundation models for pathology and biology. Drug companies, research groups and pathology software makers license them as a base for their own tools.

Noetik builds AI models of how tumors behave and licenses them to drug companies for cancer research. The models help researchers find targets, run virtual experiments and predict which patients will respond to a therapy.

PictorLabs, which now styles its name Pictor Labs, makes software that stains tissue images with AI instead of chemicals, and a tissue intelligence platform built on it.

Tribun Health sells CaloPix, software that pathology laboratories use to manage cases and review scanned slides on screen.

Commercial

Pricing

Vendor-published figures are labeled as such. Figures labeled “Estimated” are derived from third-party sources and have not been confirmed by the vendor.

Entry Price Pricing Basis BAA Tier Implementation Source
Not published
Cloud research software (DeepPathFinder) and biomarker discovery services for biopharma, sold directly and with NEC; no unit of charge or price published. Not published. The privacy policy covers website and inquiry data; no data processing or business associate agreement is published. Not published. Vendor Published

Biomy describes DeepPathFinder as research use software for biopharma and laboratories and offers biomarker discovery services, including jointly with NEC since January 2025, without a price, unit of charge or license term. How pricing differs when the platform is sold through NEC is not published.

Biomy pricing in full →