Placenta Accreta Spectrum Detection Using an MRI-based Hybrid CNN-Transformer Model

TL;DR

This study introduces a hybrid 3D deep learning model combining CNN and Transformer architectures to improve MRI-based detection of Placenta Accreta Spectrum, demonstrating high accuracy and potential to assist radiologists.

Contribution

The paper presents a novel hybrid 3D CNN-Transformer model for PAS detection from MRI scans, outperforming other architectures in accuracy.

Findings

Achieved 84.3% accuracy on independent test set

Hybrid model outperforms other 3D architectures

Potential to improve diagnostic consistency

Abstract

Placenta Accreta Spectrum (PAS) is a serious obstetric condition that can be challenging to diagnose with Magnetic Resonance Imaging (MRI) due to variability in radiologists' interpretations. To overcome this challenge, a hybrid 3D deep learning model for automated PAS detection from volumetric MRI scans is proposed in this study. The model integrates a 3D DenseNet121 to capture local features and a 3D Vision Transformer (ViT) to model global spatial context. It was developed and evaluated on a retrospective dataset of 1,133 MRI volumes. Multiple 3D deep learning architectures were also evaluated for comparison. On an independent test set, the DenseNet121-ViT model achieved the highest performance with a five-run average accuracy of 84.3%. These results highlight the strength of hybrid CNN-Transformer models as a computer-aided diagnosis tool. The model's performance demonstrates a clear potential to assist radiologists by providing a robust decision support to improve diagnostic consistency across interpretations, and ultimately enhance the accuracy and timeliness of PAS diagnosis.