Voice input.Automatic structuring.Finalization.
Built by a radiologist who spent 20 years switching between the scan and the keyboard — and got tired of it.
Problem
- Read the study01
- Dictate02
- Proof the text03
- Finalize04
- Next study05
How this came to be.
I started working as a radiologist in 2008. Ukraine’s major cities were only beginning to assemble their CT and MRI fleets, and I was already watching how colleagues in the US and Europe did it. The workflow gap was striking: their output was higher not because they evaluated images better — because for over 25 years they had tools that cut reporting time and gave it back to the study itself.
That bothered me all these years. I tried everything available — general dictation apps, Google Speech-to-Text, every service I stumbled onto. None of it was built for radiology.
When LLMs became adequate, the window opened: the existing infrastructure was enough to build a solution for myself. I built a local app, used it for six months on my own studies — and at some point it hit me: "Sasha, you can let other people use this too."
My desk, 2015 — somewhere in the mountains of Georgia
And this is where the scaling problem begins — the way I work as a remote radiologist is fundamentally different from the way a radiologist works on-site at a clinic. RADVOICE is now in early testing: introducing the Ukrainian radiology community to voice reporting, gathering feedback, rewriting whatever does not match the realities of on-site work.
If you are a radiologist and you tried it — email me. That’s the point of this stage.
— O. Berezovskyi · radiologist
The radiologist’s day isn’t eaten by the scan. It’s eaten by the keyboard.
An average report is dozens of switches between DICOM and text, copying the template, patching leftover artefacts from previous cases, picking up the oncologist’s call mid-paragraph. Dictation tools have existed in the world for over 25 years and take most of that load off. But radiology workflow is its own genre: specific vocabulary, report structure, constant interaction with the scan and interruptions. General solutions don’t fit out of the box.
The result — text eats hours that should stay on the studies themselves.
- 01Read the study
- 02Dictate
- 03Proof the text
- 04Finalize
- 05Next study
RADVOICE removes the constant switching between image and text — and puts focus back where it belongs.
How it unfolds.
Pick a template
Many protocols ship built-in. Create your own — or send me a request and I will add yours. For clinics, a dedicated institutional set of protocols can be assembled, available only to its radiologists — that capability is already working.
Dictate
Two modes to choose from. Scribe — section-based: you dictate the report as one continuous transcript and the model maps it onto the template’s sections, then you refine by hand. The simpler flow, works on a phone too. Studio — field-by-field: you navigate the template’s fields with the keyboard or Philips SpeechMike buttons and dictate straight into each one, no mapping step; field text can be edited by voice. On a desktop with a physical keyboard it’s 2–3× faster.
Report assembly
A large language model distributes your dictated text across the structured report’s blocks.
Finalize the report
Output — a finished radiology report. Send it to your Medical Information System, save as a document, print, or email.
A report that will not let the critical slip.
Everything that matters stays in view: unmapped dictation fragments, the source of every sentence, and Safety Gate — a report-consistency check before finalization.
- 01
Any fragment of dictation that did not make it into the report is highlighted in the transcript — it cannot be lost quietly.
- 02
Hover a section of the report and its source lights up in the transcript, and vice versa. The origin of every sentence is one mouse-move away.
- 03
Safety Gate: before finalization a separate LLM pass re-reads the findings and the impression and looks for internal contradictions — an impression that asserts a side, grade, or diagnosis absent from the findings or at odds with them, or findings that hedge ("cannot be excluded") while the impression is categorical.
- 04
Alongside it, a deterministic check verifies the template’s mandatory checklist items and left/right consistency. None of the checks block — the final decision is always the radiologist’s.
Trusted by the community
Measurable outcomes: more reports, less keyboard, every day.
A direct line to the author.
Hellish Radiology, Cats & Wine ☢️🍷
A Telegram channel about Ukrainian radiology. Informal — that’s how it was meant.
@hotradiology →Oleksandr Berezovskyi
Radiologist · RADVOICE author
LinkedIn →
scan · donateSupport the project.
A free tier with limits and a paid tier for daily use are coming, otherwise the infrastructure this runs on won’t pay for itself. The Monobank jar is voluntary support that pushes that day further out.
Open jar →If you’ve read this far —
Then we’re probably colleagues :) Questions or ideas — reach out.