Opportunities › DICOM imaging viewer and segmentation › Proposed app
Sliceway
Browser DICOM viewer with AI organ segmentation you can edit and review
- Score
- 43
- confidence 32
- Evidence
- 1
- items on the page
- Rivals
- 0
- named in sources
- First version
- 60 d
- estimate
- Type
- Desktop app
- PWA: runs in the browser, installs on Mac and Windows
- Market since
- 2004
- Mature market · AI estimate
ScreensConcept
Desktop app: Radiologists work with dense multi-slice studies, perform segmentation edits and 3D reviews requiring large screens and precise mouse control. Sample screens on a computer, in the proposed brand. Their numbers are sample data.
CT Chest Abdomen
Loaded locally412 slices
About this appAI proposal
Sliceway opens CT, MRI and PET studies in the browser, with scrolling stacks, multiplanar views and a 3D view. It runs an automated segmentation model on a study and shows the organs as colored layers over the images.
Every result can be edited. Brush, erase, grow or smooth a region, then compare it with the model's first pass. Fuse a PET with a CT and see both in the same slice. Volumes update as you edit.
It is for radiologists, imaging technicians and hospital teams who want a modern viewer without vendor software. This is a proposal for research and review use; clinical use would need regulatory clearance first.
- Tagline
- See the scan, segment it in minutes, correct what matters.
- Voice
- PreciseCalmPlain
- Why this name
- A scan is read slice by slice, and 'way' suggests a clear route through the study. Two plain words, easy to say.
In the first version
Members say which features they would use. It tells PWAS what people want; it changes no score.
Automated organ segmentation
Run an open-source model such as TotalSegmentator on a study and get labeled structures as overlays.
No member yet
Editable results
Brush, erase, smooth and grow regions. The original model output is kept so you can compare and revert.
No member yet
MPR and 3D view
Axial, coronal and sagittal views linked by a crosshair, plus a 3D rendering of selected structures.
No member yet
PET/CT fusion
Align two series and blend them with adjustable opacity and color maps in every plane.
No member yet
Brand identityAI proposal
Check the name against trademark registers before using it.
Palette
#14232BDeep Slate · primary, dark surface#F4F1EAPaper · surface#17252CInk · text#1F8A8ATeal · accent#E0A030Amber · data highlight
Typography
Aa
Sliceway
ABCDEFGHIJKLMNOPQRSTUVWXYZ 0123456789
See the scan, segment it in minutes, correct what matters.
PricingAI proposal
The material gives no competitor prices. These tiers are a starting point to test, following the freemium and subscription ideas in the opportunity.
Viewer
Free
- DICOM viewing, MPR
- Local-only studies
- Manual segmentation tools
Pro
$79 a month
- Automated segmentation
- PET/CT fusion and 3D view
- Review links
- Export masks and volumes
Team
$349 a month
- Up to 10 users
- Shared studies and audit log
- Private storage connection
- Priority support
What it could be worthEstimate
What a software business making this much sells for today, from real deals. Pick a monthly revenue.
If it makes
Worth about
$194,000
Sale range $132,000 to $263,000
$120,000 a year in revenue
From 87 software businesses listed and sold on Empire Flippers in the last year, revenue vetted by the broker: they sell for about 19× their monthly revenue, most between 13× and 26×.
Measured on profit, the middle deal is 32× monthly net profit: about 2.7 years of profit.
An estimate, not an offer or financial advice. A real price depends on profit, growth, churn, how much of the work is the owner's, and the buyer.
How it would growAI proposal
How the product would reach new customers through its own use, and how the first ones would be found. A plan to test, not a result.
- Built-in loop
- Shared outputs. Users send review links with segmentations and notes to colleagues, referring physicians and tumor board members, who open them in the browser without installing anything.
- Do they become customers?
- Recipients see the product and may be clinicians who need it too, but a link opened once is exposure only. Test whether recipients start their own free account.
- First customers
- Medical imaging research groups at university hospitals that already run open-source segmentation models and need an easier viewer to edit and review results.
- Where to reach them
- Open-source communities: Post in imaging-research forums and the GitHub discussions of segmentation projects, offering free access for edits.
- Direct outreach: Email radiology research leads and imaging physicists with a demo on their own anonymized scan.
- Conferences: Show workflow demos at radiology research meetups and imaging informatics events.
- First milestone
- Five research groups on paid Pro plans within 90 days, each segmenting at least 20 studies.
Why people already pay for this
- VerifiedGitHub repository gained 300 stars in 62 days
Tech stack
Every proposal builds on the same PWA base, installable from the browser on any phone or computer. Dashed boxes are what this app adds.
- AppNext.js and TypeScript
- PWAManifest and service worker
- UITailwind CSS
- Data and authSupabase Postgres
- PaymentsStripe
- EmailResend
- HostingVercel
- This app · Imaging engineOpen-source web DICOM rendering librariesNeeded for slice stacks, MPR, volume rendering and fusion in the browser.
- This app · GPU inferenceServerless GPU compute for segmentation modelsModels like TotalSegmentator need GPUs that Vercel does not provide.
RisksAI inference
- RegulatoryClinical diagnostic use likely needs medical device clearance. The first version must be positioned for research and review, with clear labeling.
- DataPatient images are sensitive. Hospitals will demand privacy compliance, audit logs and options to keep data on their own systems.
- TechnicalLarge studies strain browser memory and upload time. 3D rendering and fusion alignment must work on ordinary hospital hardware.
- AISegmentation errors can look plausible. Editing, comparison to the original and clear model versioning are essential.
- Intellectual propertyOpen-source model licenses may restrict commercial use or require attribution. They must be checked before charging for them.
Everything marked AI proposal or AI inference was written by a model from the evidence on the opportunity page. The proposed name must be checked against trademark registers before it is used.