From Radiologist Report to Image Label: Assessing Latent Dirichlet Allocation in Training Neural Networks for Orthopedic Radiograph Classification

TL;DR

This study explores using Latent Dirichlet Allocation to generate labels from radiologist reports for training neural networks on orthopedic radiographs, finding limited success in label accuracy but promising results in feature detection.

Contribution

The paper demonstrates the application of LDA for automated labeling of radiographs and evaluates its effectiveness in training neural networks for orthopedic image classification.

Findings

LDA-generated labels enabled training of neural networks.

Neural networks achieved up to 91% accuracy in feature detection.

LDA was not sufficiently accurate for reliable radiograph labeling.

Abstract

Background: Radiography (X-rays) is the dominant modality in orthopedics, and improving the interpretation of radiographs is clinically relevant. Machine learning (ML) has revolutionized data analysis and has been applied to medicine, with some success, in the form of natural language processing (NLP) and artificial neural networks (ANN). Latent Dirichlet allocation (LDA) is an NLP method that automatically categorizes documents into topics. Successfully applying ML to orthopedic radiography could enable the creation of computer-aided decision systems for use in the clinic. We studied how an automated ML pipeline could classify orthopedic trauma radiographs from radiologist reports. Methods: Wrist and ankle radiographs from Danderyd Hospital in Sweden taken between 2002 and 2015, with radiologist reports. LDA was used to create image labels for radiographs from the radiologist reports. Radiographs and labels were used to train an image recognition ANN. The ANN outcomes were manually reviewed to get an accurate estimate of the method's utility and accuracy. Results: Image Labels generated via LDA could successfully train the ANN. The ANN reached an accuracy between 91% and 60% compared to a gold standard, depending on the label. Conclusions: We found that LDA was unsuited to label orthopedic radiographs from reports with high accuracy. However, despite this, the ANN could learn to detect some features in radiographs with high accuracy. The study also illustrates how ML and ANN can be applied to medical research.