corad

A chest X-ray finding highlighter that runs in the background on your reading workstation. Press a hotkey while a film is on screen; it grabs the monitor, runs a model on the CPU, and shows a heat map with the 14 findings ranked. It never sends a byte anywhere.

Download for Windows · 120 MB   Other downloads

version 0.1.0 · 2026-09-18 · sha256 in the table below

The model inside the download is encrypted. A free account gives you a short-lived licence file that unlocks it; renewing is one click on your account page. The licence check is offline: the app still never connects to anything.

Research tool. Not a medical device, not cleared by any regulator, not a second reader. Its heat maps are coarse class-activation maps that say roughly where the network looked. Do not use it to make clinical decisions.

Download

Windows, self-contained

Unzip anywhere, double-click Corad.cmd. Python, the model and every library are inside the folder. Nothing is installed and no admin rights are needed.

corad-0.1.0-windows-x64.zip

Any machine with Python 3.11

Linux, macOS or Windows with your own Python 3.11 (the app ships as 3.11 bytecode). pip install -r requirements-app.txt, then python -m corad run.

corad-0.1.0-python311.zip

Model bundle only

For updating the model under an existing install: replace models/current/. The app checks the SHA-256 in model.json before loading.

corad-model-corad-v1.zip
filesizesha256
corad-0.1.0-python311.zip28 MBb3300702feb8a77ac79efddcb6f63a671334d44cd155c168af6c6d579e9f24ae
corad-model-corad-v1.zip28 MBe0c06f4e6eed23512d05d308809faca9f3bcc8acc9802d4df748dba090997fb5
corad-0.1.0-windows-x64.zip120 MBd20f9f4407bf28dcd0b120242fb4bc437a488cece67304b676ed9019568f2b4e

SHA256SUMS · releases.json · all files

Check a download on Windows with certutil -hashfile corad-0.1.0-windows-x64.zip SHA256, on Linux or macOS with sha256sum.

Using it

Ctrl+Alt+XGrab the monitor under the cursor, auto-crop to the film, analyse
Ctrl+Alt+RDrag a box around the film yourself, analyse that
Ctrl+Alt+QQuit

The result window shows the film with heat for the selected finding and the 14 findings ranked on the right. Click a finding or use the arrow keys to switch. A red bar means the probability is above that finding's operating point. H toggles the heat, Esc closes. Corad-Analyze.cmd accepts a dropped PNG, JPG or DICOM file. Hotkeys and a watched folder can be changed in corad.ini (see corad.ini.example).

How it stays local

Run Corad-Verify.cmd after unzipping. It tries a TCP connection, a UDP packet, a DNS lookup and an HTTP fetch and reports each one blocked, then times one inference on your CPU.

Model

DenseNet-121 initialised from torchxrayvision's multi-dataset backbone and fine-tuned at 512 px on the public NIH ChestX-ray14 set for 14 findings: Atelectasis, Cardiomegaly, Consolidation, Edema, Effusion, Emphysema, Fibrosis, Hernia, Infiltration, Mass, Nodule, Pleural Thickening, Pneumonia, Pneumothorax. Mean AUC on NIH's official patient-level test list: 0.766. Bundle corad-v1, model sha256 9ec7602308c1446ce79067d1a6de5584ddf360952311c879897bcb4c0560095e. Per-finding numbers, operating points and localisation scores are in the bundle's model.json and in the README inside every download.

The heat map is a class activation map, 16×16, upsampled. It lands on or next to the finding about half the time on NIH's radiologist-boxed films. Cardiomegaly, Effusion, Edema and Hernia are the reliable findings; Infiltration, Pneumonia and Nodule are weak, as they are for every model trained on these labels.