CVAI Catalog

·

View Catalog

PPG2ABP

BUET (Ibtehaz & Rahman)

PPG / wearable

Filter catalog by Modality:
PPG / Wearable

Blood pressure estimation

Filter catalog by Disease / Trait:
Cardiac Function & Hemodynamics

Generation

Filter catalog by Task Type:
Generation

Regression

Filter catalog by Task Type:
Regression

CNN (1D)

Filter catalog by Architecture:
Convolutional (CNN)

Keras

Filter catalog by Framework:
TensorFlow / Keras

MIT

Filter catalog by License:
Permissive

Translates a raw PPG waveform into a full continuous arterial blood-pressure waveform, from which systolic, diastolic, and mean arterial pressure are derived. Uses a two-stage cascaded 1D convolutional network in a U-Net style, with a coarse approximation stage followed by a refinement stage. Meets BHS Grade A and AAMI accuracy standards for diastolic and mean arterial pressure. Developed at BUET.

memory Specifications

category

Architecture

CNN (1D)

Two-stage cascaded fully-convolutional 1D network (ApproximateNetwork + RefinementNetwork, U-Net-style)

code

Framework

Keras

calendar_month

Added to catalog

2026-07-10

gavel License

MIT

check_small Open source check_small Commercial use OK check_small Modifications allowed Attribution required No share-alike requirement

License for model weights only. Associated code may be licensed seperately, check code source for specific terms.

description Publication

database Training & evaluation data

USA

ICU waveform database containing synchronized PPG and invasive arterial blood pressure (ABP) recordings, used to train PPG2ABP.

science Capabilities & performance

ABP waveform

Generation Blood pressure estimation
4.604 MAE MIMIC-II Waveform Database · internal

Diastolic blood pressure (DBP)

Regression Blood pressure estimation
3.449 MAE MIMIC-II Waveform Database · internal

Mean arterial pressure (MAP)

Regression Blood pressure estimation
2.31 MAE MIMIC-II Waveform Database · internal

Systolic blood pressure (SBP)

Regression Blood pressure estimation
5.727 MAE MIMIC-II Waveform Database · internal