Anatomy-Guided Multitask Learning for MRI-Based Classification of Placenta Accreta Spectrum and its Subtypes

TL;DR

This paper introduces a novel CNN architecture for efficient one-stage multiclass diagnosis of Placenta Accreta Spectrum and its subtypes from MRI images, improving prenatal diagnosis accuracy.

Contribution

The study presents a new multitask CNN model with anatomical feature integration for simultaneous classification of PAS subtypes, advancing beyond traditional binary or multi-stage methods.

Findings

Achieved state-of-the-art performance on clinical MRI dataset

Efficient one-stage multiclass diagnosis of PAS and subtypes

Enhanced model attention through anatomical feature integration

Abstract

Placenta Accreta Spectrum Disorders (PAS) pose significant risks during pregnancy, frequently leading to postpartum hemorrhage during cesarean deliveries and other severe clinical complications, with bleeding severity correlating to the degree of placental invasion. Consequently, accurate prenatal diagnosis of PAS and its subtypes-placenta accreta (PA), placenta increta (PI), and placenta percreta (PP)-is crucial. However, existing guidelines and methodologies predominantly focus on the presence of PAS, with limited research addressing subtype recognition. Additionally, previous multi-class diagnostic efforts have primarily relied on inefficient two-stage cascaded binary classification tasks. In this study, we propose a novel convolutional neural network (CNN) architecture designed for efficient one-stage multiclass diagnosis of PAS and its subtypes, based on 4,140 magnetic resonance imaging (MRI) slices. Our model features two branches: the main classification branch utilizes a residual block architecture comprising multiple residual blocks, while the second branch integrates anatomical features of the uteroplacental area and the adjacent uterine serous layer to enhance the model's attention during classification. Furthermore, we implement a multitask learning strategy to leverage both branches effectively. Experiments conducted on a real clinical dataset demonstrate that our model achieves state-of-the-art performance.