Feasibility of Using F-FDG PET/CT Radiomics and Machine Learning to Detect Drug-Induced Interstitial Lung Disease.

Background: Bleomycin is an oncolytic and antibiotic agent used to treat various human cancers because of its antitumor activity. Unfortunately, up to 46% of the patients treated with bleomycin develop drug-induced interstitial lung disease (DIILD) and potentially life-threatening interstitial pulmonary fibrosis. Tools and biomarkers for predicting and detecting DIILD are limited. Therefore, we aimed to evaluate the feasibility of F-FDG PET/CT, PET radiomics, and machine learning in distinguishing DIILD in an explorative pilot study.

Methods: Eighteen Hodgkin's lymphoma (HL) patients, of whom 10 developed DIILD after treatment with bleomycin, were retrospectively included. Five diffuse large B-cell lymphoma (DLBCL) patients were included as a control group since they were not treated with bleomycin. All patients underwent F-FDG PET/CT scans before (baseline) and during treatment (interim). Structural changes were assessed by changes in Hounsfield Units (HUs). The F-FDG PET scans were used to assess metabolic changes by examining the feasibility of 504 radiomics features, including the mean activity of the lungs (SUVmean). A Random Forest (RF) classifier evaluated the identification and prediction of DIILD based on PET radiomics features.

Results: HL patients who developed DIILD showed a significant increase in standard SUV metrics (SUVmean; = 0.012, median increase 37.4%), and in some regional PET radiomics features (texture strength; = 0.009, median increase 101.6% and zone distance entropy; = 0.019, median increase 18.5%), while this was not found in HL patients who did not develop DIILD and DLBCL patients. The RF classifier correctly identified DIILD in 72.2% of the patients and predicted the development of DIILD correctly in 50% of the patients. There were no significant differences in HUs over time within all three patient groups.

Conclusions: Our explorative longitudinal pilot study suggests that certain regional F-FDG PET radiomics features can effectively identify DIILD in HL patients treated with bleomycin, as significant longitudinal increases were observed in SUVmean, texture strength, and zone distance entropy after the development of DIILD. The metabolic activity of these features did not significantly increase over time in DLBCL patients and HL patients who did not develop DIILD. This indicates that F-FDG PET radiomics, with and without machine learning, might serve as potential biomarkers for detecting DIILD.