Machine learning to distinguish lymphangioleiomyomatosis from other diffuse cystic lung diseases

Respir Investig. 2022 May;60(3):430-433. doi: 10.1016/j.resinv.2022.01.001. Epub 2022 Feb 16.


Patients with lymphangioleiomyomatosis (LAM) frequently experience delays in diagnosis, owing partly to the delayed characterization of imaging findings. This project aimed to develop a machine learning model to distinguish LAM from other diffuse cystic lung diseases (DCLDs). Computed tomography scans from patients with confirmed DCLDs were acquired from registry datasets and a recurrent convolutional neural network was trained for their classification. The final model provided sensitivity and specificity of 85% and 92%, respectively, for LAM, similar to the historical metrics of 88% and 97%, respectively, by experts. The proof-of-concept work holds promise as a clinically useful tool to assist in recognizing LAM.

Keywords: Computed tomography; Diffuse cystic lung diseases; Lymphangioleiomyomatosis; Machine learning.

MeSH terms

  • Humans
  • Lung Diseases* / diagnostic imaging
  • Lung Neoplasms* / diagnostic imaging
  • Lymphangioleiomyomatosis* / diagnostic imaging
  • Machine Learning
  • Tomography, X-Ray Computed / methods

Supplementary concepts

  • Cystic Disease Of Lung