Radiology & Imaging AI
T

Treatment Pad

Treatment Pad is an iPad and iPhone app that uses computer vision to produce before and after photographs for cosmetic physicians and aesthetic clinics. Its patent pending technology automates three jobs: camera and photo alignment, background removal and the sorting of a patient's photo series. In the split screen camera, the reference photo sits in one pane and the live view in the other, and the app shows the detected rotation of the face, including upward and downward tilt since version 1.8.0, so the clinician can match the earlier angle before taking the shot. After capture, the layout editor finds landmarks such as the eyes and nose and aligns the pair, with a grid for small corrections and linked zoom that keeps the same area in view in both images.

Photos go straight into patient albums in Apple Photos, named by the patient's identifier, and stay on the device unless the practice exports or syncs them. Staff can blur identifying features, apply up to five branded templates and export split images, single images or video animations. The download is free. Pro Layouts at $9.99 a month removes the watermark, and Pro + AI Camera at $29.99 a month adds the guided camera. The app also runs on Apple silicon Macs and Apple Vision Pro.

Treatment Pad was founded in July 2019, with Australian cosmetic practitioner Dr. Nora as lead researcher, and says hundreds of clinics use it. Its developer, Ashraf Samy, also publishes Diagnosis Pad, whose ambient differentials technology is slated to power real time analysis in a later release.

AI Health Index verifiedNovember 19, 2026
Compare Treatment Pad with other vendors
Founded
2019
Headquarters
—
Categories
radiology-and-imaging-ai
Indexed Products
Treatment Pad AI Layout Camera, Layout Editor, AI Camera, Pro Layouts, Pro + AI Camera
Buyer Segments
Cosmetic physicians, Aesthetic medicine practices, Cosmetic clinic photography teams
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
BB on AI CentralityThe model is the engine of a core module. The platform carries other value, but this capability does not exist without it.
Vendor Published

Computer vision carries the two jobs the paid camera tier sells. During capture, the live camera estimates the rotation of the face, upward and downward tilt included, so the clinician can match a prior shot before pressing the shutter. After capture, facial landmarks drive automatic alignment of the selected pair, and automatic background removal, on by default since iOS 15, prepares it for presentation.

Much of the app stands without a model: patient albums, the split screen, the template editor, date stamping and export all serve a user who positions images by hand. The pricing follows that split. Pro Layouts sells watermark removal on its own, while Pro + AI Camera at $29.99 a month bundles the live guidance, so the higher tier depends on the vision system for its main function.

BB on Autonomy and Oversight ModelThe oversight structure is described and one part is missing, commonly the threshold at which the system stops or what happens after it is wrong.
Vendor Published

A practitioner picks the reference photo, frames the patient and takes the new shot; the app never captures on its own. The rotation readout updates live during framing, and the alignment control applies the automated adjustment only when the operator selects a pair in the gallery and taps it. A grid overlay supports small manual corrections, and the clinician can toggle background removal, lock both panes to zoom together, apply a blur or switch templates before saving or sharing.

Every comparison is reviewed on screen by the person who made it. What stays open is the point at which the estimate becomes unreliable: the camera shows orientation feedback with no confidence cue or acceptance threshold, and an automatic shutter is held back until it passes a clinical trial.

CC on Model and Technology TransparencyThe architecture is described in general terms with nothing identified. Proprietary is asserted rather than explained.
Vendor Published

Facial feature detection drives alignment. The software marks landmarks such as the eyes and nose and uses their positions to bring before and after images into register, while a separate live orientation step reads the rotation of the face in the camera preview. Photo orientation and capture timestamps feed the cataloging step that groups a patient's series. The company calls the technology patent pending computer vision.

The feature history runs through the app's releases: background removal arrived in January 2022, face detection memory fixes in 2024, gallery accuracy improvements in October 2025 and up and down rotation detection in version 1.8.0. Nothing identifies the model family, whether the detector is built on Apple's on device frameworks or trained in house, the training image population, or which release changed a model rather than the interface.

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

The chain is short by design. Alignment, rotation detection and background removal run on the iPhone, iPad, Mac or Vision Pro that holds the original photos, and the app's privacy terms state that it neither logs usage nor sends data through third party tools. The App Store privacy label matches, listing no data collected.

Apple is the one outside party in normal use: it checks the subscription at least once every two weeks without personal data, and it can pass anonymized crash and diagnostic logs back to the developer. Any further transfer is the practice's own choice of share sheet, USB cable or cloud sync service. No inference request leaves the device, which keeps patient images away from any model provider, although the origin of the face detection components is not named.

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

Scale of use is the main figure: the company says hundreds of clinics worldwide use the app, without naming them or giving a count. The clearest workflow account comes from clinical lead Dr. Nora, who describes shooting a full set in a minute or less in her Australian practice and using linked zoom to show the lips after an injection before pulling back to the whole face.

Coverage in the Australian trade title Spa and Clinic describes the same aim, matching pairs side by side with little manual work. On the App Store the app holds 3.0 stars from 11 ratings, with one body sculpting clinic calling it the best before and after app it has used. None of this measures alignment accuracy, capture time against a baseline or consistency between operators.

BB on AI Safety and PHI StewardshipCategorical commitments are published, such as no training on customer data, without the retention schedule behind them.
Vendor Published

Patient photos are processed and kept on the device, with every image saved locally and none sent online. The app asks for photo library access only to run the layout editor, camera access only for the guided camera, and location access only if the operator turns on location data for new photos. Usage logging and third party tracking are ruled out in the app's privacy terms.

Staff can blur identifying features before export, a step the company presents as a way to deidentify patients in marketing images, and can delete originals through Apple Photos. Retention is the practice's own decision: photos stay as long as its library and any sync service keep them. There is no stated procedure for a safety incident involving the vision features, such as a misaligned comparison that misstates a result.

Regulatory and Compliance
BB on HIPAA and BAA PostureBusiness associate status is stated and supported by a substantive privacy document, with the agreement or its scope not fully published. For a vendor outside the United States, an equivalent regime documented to this depth grades here. A vendor whose product does not process protected health information grades here too when it says so plainly and explains the scope, with a service privacy document behind it: stating a position a buyer can rely on is the posture this axis grades, and the band above is closed to it because there is no agreement to publish.
Vendor Published

The developer never receives patient photos, and that is the basis of the product's position. Images are saved into the practice's own Apple Photos library in albums named by patient identifier, and the privacy terms, which cover the app as well as the website, state that the app sends no data and uses no tracking tools. Apple's subscription check carries no personal data.

HIPAA goes unmentioned, there is no statement of business associate status, and neither paid tier comes with a business associate agreement, which fits a product that holds no protected health information on the developer's side. The exposure sits with the clinic: iCloud Photos sync, shared iPads and exported comparisons fall under the practice's own safeguards and whatever terms govern its storage provider.

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

Local processing narrows what a clinic has to evaluate, since no developer server stores patient images. The controls in place are permission scoping, with the photo library opened for layouts, the camera for capture and location only by choice, plus the protections of the device itself: the passcode, encryption and management settings of the iPhone, iPad or Mac the practice supplies. Apple's anonymized crash logs are kept apart from patient photos.

The App Store seller is the individual developer Ashraf Samy. There is no SOC 2 report, ISO/IEC 27001 certificate, penetration test or trust center, and the subscription terms set no security scope for a clinic that deploys the app across several devices and staff accounts.

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

The product on sale captures, aligns and formats cosmetic treatment photographs, and its outputs are images for a patient album, a consultation or a practice portfolio. Nothing in the current app measures, scores or interprets the face, and no device claim is made for it. Two signals point to a different product later.

The App Store listing holds back an automatic camera until it passes a clinical trial in the medical field, and the company plans real time analysis built on Diagnosis Pad's ambient differentials technology. Neither feature ships today, and no US pathway, exemption or registration is named for either one. On the App Store the app is filed under Medical and rated 4+.

DD on AI Governance and Bias DisclosureNothing published on how model behavior is governed or tested. Multilingual operation with no subgroup performance sits here when the vendor markets recognition quality as a strength, because a caller the system failed to understand leaves no complaint and no record.
Vendor Published

Pose guidance depends on detecting facial orientation in a live preview, and alignment depends on finding usable landmarks in both photos, so results turn on skin tone, lighting, makeup, swelling after treatment and facial anatomy. The operator can filter the gallery by orientation and correct an alignment with the grid when the automatic result is off. Releases since 2022 have reworked face detection, rotation and background removal, each described as a feature change.

There are no test results by skin tone, age, lighting condition or post procedure swelling, no evaluation policy for model updates and no governance material a clinic could take to its own review. Consistency across the range of complexions an aesthetic practice sees is not shown anywhere.

CC on AI Liability and RecourseMechanisms exist that let someone challenge an output, such as audit trails, source traceability or review before commit, with nothing standing behind the output and no route for the harmed party.
Vendor Published

Every result can be checked before it leaves the app. The layout editor shows the aligned pair side by side, the grid allows manual adjustment, and the operator can change the crop, background or template and save a revised layout to the patient album. Because the originals stay in Apple Photos, a poor comparison can be regenerated from scratch. Behind the output there is nothing.

The App Store terms cover payment, renewal and restoring a purchase, refunds run through Apple, and support is a contact form on the website. No warranty on alignment accuracy, no obligation to fix a flawed comparison and no remedy for harm from a misleading before and after image appear in the terms, which matters for practices that publish these photos in their marketing.

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

Apple Photos is the working library, and patient records exist only as albums the practice names. The app reads from that library, saves edited comparisons into the selected album and dates each layout by the after photo's capture date, or by the current date if the operator prefers. Output leaves through the iOS share sheet, a USB transfer or a cloud sync service on the device, as split screen images, single images, JPG files or video animations.

The company calls the album step automatic patient record generation, but it creates photo albums rather than chart entries. There is no connection to an EHR, a practice management system or an aesthetic clinic platform, and nothing maps an album to a patient record in another system.

BB on Deployment Model and Data ResidencyOptions and residency are stated with isolation or the processing path left open.
Vendor Published

The app runs only on Apple hardware the practice owns: iPhone and iPad on version 15.6 or later, Macs with an M1 chip or later on macOS 12.5 or later, and Apple Vision Pro on visionOS 1.0 or later. It is designed for iPad. Capture, alignment and editing all run on the device, photos stay in its Apple Photos library until a practice exports or syncs them, and the app needs a connection only for Apple's subscription check every two weeks.

That pins the default location of patient images to the clinic's own hardware. Where secondary copies live is set by the practice, through iCloud Photos or another sync provider, and separation between clinics or practitioners depends on how devices and Apple IDs are assigned.

Commercial
AA on Commercial TransparencyPublished tiers with figures, a stated unit of charge, and a route to start without a sales conversation.
Vendor Published

Pricing is public and self service. The app is a free download from the App Store, with the layout editor and a watermark included. Pro Layouts costs $9.99 a month and removes the 'created with Treatment Pad' watermark. Pro + AI Camera costs $29.99 a month, removes the watermark and unlocks the guided camera that shows facial rotation beside a reference photo.

Apple bills the Apple ID that confirms the purchase, renewals and cancellations run through the App Store account settings, and a subscription can be restored on another device signed in to the same Apple ID. The unit of charge is one subscription per Apple ID, shared across the devices signed in to it, so a clinic with several staff accounts pays per account.

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

The product is built for cosmetic medicine, where clinics need repeatable views for the patient record, the consultation and the practice portfolio. Patient albums hold each series, the split screen supports the consultation, and templates carrying clinic branding serve social media and website galleries.

Clinical lead Dr. Nora's example centers the lips after an injection, then returns to the full face so the patient sees the change in context, and one App Store reviewer runs the app in a body sculpting clinic. Injectables are the use the company leads with. The interface is English only, and the app sells worldwide through the App Store. Image consistency and alignment accuracy have not been tested in any of these settings.

Alternatives

Alternatives to Treatment Pad

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

DentalMonitoring analyzes smartphone images of teeth and orthodontic appliances between office visits, for orthodontists and dental practices in 50 countries.

Philips Lumify is a handheld ultrasound transducer that plugs into a smart device the customer already owns, over USB on Android or Lightning on Apple hardware, with the app downloaded from the ordinary app stores.

Enlitic builds software that cleans up and standardizes medical imaging data for hospitals, radiology groups and archive operators.

Sonio makes prenatal ultrasound software for sonographers, maternal fetal medicine specialists and the obstetricians who read the scans, built as one platform with AI reading aids and a reporting and image management layer.

Clarius Mobile Health makes wireless handheld ultrasound scanners and the AI that runs on them.

MEDICAL IP builds AI segmentation and quantification software for medical imaging.

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
Free; paid plans from $9.99/month
$0 baseline
App Store subscription per Apple ID. Pro Layouts is $9.99 per month and removes the watermark. Pro + AI Camera is $29.99 per month and adds the guided camera. Neither App Store tier includes a business associate agreement. Photos are processed and stored on the practice's own device, and the developer receives no patient images. None. The app installs from the App Store on the practice's own iPhone, iPad, Mac or Apple Vision Pro. Vendor Published

Both paid tiers are listed on the US App Store, and Apple handles billing, renewal and cancellation. A subscriber restores a purchase on another device with the same Apple ID. The subscription covers the software only; the practice supplies the hardware and any photo backup or sync service.