An interpretable object detection based model for the diagnosis of neonatal lung diseases using Ultrasound images

TL;DR

This paper introduces an interpretable deep learning model using Faster R-CNN to detect specific lung ultrasound features in neonates, aiding early diagnosis of respiratory diseases with high accuracy and clinical trust.

Contribution

The study presents a novel multi-class object detection approach for LUS features, enhancing interpretability and clinical trust in automated neonatal lung disease diagnosis.

Findings

Achieved 86.4% mean average precision in detecting LUS features.

Outperformed single-stage models like RetinaNet in accuracy.

Facilitated early prediction of neonatal respiratory distress.

Abstract

Over the last few decades, Lung Ultrasound (LUS) has been increasingly used to diagnose and monitor different lung diseases in neonates. It is a non invasive tool that allows a fast bedside examination while minimally handling the neonate. Acquiring a LUS scan is easy, but understanding the artifacts concerned with each respiratory disease is challenging. Mixed artifact patterns found in different respiratory diseases may limit LUS readability by the operator. While machine learning (ML), especially deep learning can assist in automated analysis, simply feeding the ultrasound images to an ML model for diagnosis is not enough to earn the trust of medical professionals. The algorithm should output LUS features that are familiar to the operator instead. Therefore, in this paper we present a unique approach for extracting seven meaningful LUS features that can be easily associated with a specific pathological lung condition: Normal pleura, irregular pleura, thick pleura, Alines, Coalescent B-lines, Separate B-lines and Consolidations. These artifacts can lead to early prediction of infants developing later respiratory distress symptoms. A single multi-class region proposal-based object detection model faster-RCNN (fRCNN) was trained on lower posterior lung ultrasound videos to detect these LUS features which are further linked to four common neonatal diseases. Our results show that fRCNN surpasses single stage models such as RetinaNet and can successfully detect the aforementioned LUS features with a mean average precision of 86.4%. Instead of a fully automatic diagnosis from images without any interpretability, detection of such LUS features leave the ultimate control of diagnosis to the clinician, which can result in a more trustworthy intelligent system.