Automatic Pulmonary Nodule Detection Applying Deep Learning or Machine Learning Algorithms to the LIDC-IDRI Database: A Systematic Review

Abstract

The aim of this study was to provide an overview of the literature available on machine learning (ML) algorithms applied to the Lung Image Database Consortium Image Collection (LIDC-IDRI) database as a tool for the optimization of detecting lung nodules in thoracic CT scans. This systematic review was compiled according to Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Only original research articles concerning algorithms applied to the LIDC-IDRI database were included. The initial search yielded 1972 publications after removing duplicates, and 41 of these articles were included in this study. The articles were divided into two subcategories describing their overall architecture. The majority of feature-based algorithms achieved an accuracy >90% compared to the deep learning (DL) algorithms that achieved an accuracy in the range of 82.2%–97.6%. In conclusion, ML and DL algorithms are able to detect lung nodules with a high level of accuracy, sensitivity, and specificity using ML, when applied to an annotated archive of CT scans of the lung. However, there is no consensus on the method applied to determine the efficiency of ML algorithms.

The Performance of Deep Learning Algorithms on Automatic Pulmonary Nodule Detection and Classification Tested on Different Datasets That Are Not Derived from LIDC-IDRI: A Systematic Review

“…Several other studies have trained and tested deep learning algorithms on the large, publicly accessible LIDC-IDRI database [16] and, recently, a systematic review was published overviewing the different studies that have tested on this database [50]. However, to review deep learning performance it is also necessary to review studies that did not use the LIDC-IDRI, as CT scans may vary from region to region.…”

Machine Learning for Pulmonary and Critical Care Medicine: A Narrative Review

“…There were 135 papers duplicated between these two categories. Two systematic reviews were identified [18,19]. Given the narrative nature of this review, the final cohort of papers was hand-picked to provide the reader with the best general overview of the topic and was not meant to be comprehensive.…”

“…There are algorithms that assist with the detection, per se, of nodules (computer-aided detection or CAD), and those that assist with specific diagnosis (computeraided diagnosis or CADx) [25]. The extent of the work in CAD is reflected in the 2019 systematic [18]. There has also been extensive research into CADx, where the usual goal is to develop models that can distinguish between benign and malignant lesions based on imaging.…”

Künstliche Intelligenz in der Bildgebung der Lunge

“…Die Detektion von Lungenrundherden kann weiter verbessert werden, wenn zum Lernen neuronale Netzwerke (Convolutional Neural Network, ConvNet) herangezogen werden. Mit Hilfe von ConvNets lässt sich eine Genauigkeit von 82,2-97,6 % bei einer Sensitivität von 83,1-96,6 % und einer Spezifität von 71,4-98,2 % erreichen [26].…”