A novel technology to integrate imaging and clinical markers for non-invasive diagnosis of lung cancer

Abstract

This study presents a non-invasive, automated, clinical diagnostic system for early diagnosis of lung cancer that integrates imaging data from a single computed tomography scan and breath bio-markers obtained from a single exhaled breath to quickly and accurately classify lung nodules. CT imaging and breath volatile organic compounds data were collected from 47 patients. Spherical Harmonics-based shape features to quantify the shape complexity of the pulmonary nodules, 7th-Order Markov Gibbs Random Field based appearance model to describe the spatial non-homogeneities in the pulmonary nodule, and volumetric features (size) of pulmonary nodules were calculated from CT images. 27 VOCs in exhaled breath were captured by a micro-reactor approach and quantied using mass spectrometry. CT and breath markers were input into a deep-learning autoencoder classifier with a leave-one-subject-out cross validation for nodule classification. To mitigate the limitation of a small sample size and validate the methodology for individual markers, retrospective CT scans from 467 patients with 727 pulmonary nodules, and breath samples from 504 patients were analyzed. The CAD system achieved 97.8% accuracy, 97.3% sensitivity, 100% specificity, and 99.1% area under curve in classifying pulmonary nodules.

3D multi‐resolution attention capsule network for diagnosing multi‐pathological types of pulmonary nodules

“…The difference between 3D MRA‐CapsNet‐DL_B and the best SVM fusion model is only 0.73%. Compared with some binary classification methods in literatures, 39–42 although our results are partially suboptimal, our performed four‐classification task is more difficult than the binary classification tasks. In addition, the constructed aided diagnosis model does not need to design and extract traditional manual features, nor does it use additional supplementary information such as serum biomarkers, and it can achieve good and stable performance in the classification of multiple pathological types of pulmonary nodules by only using CT image information.…”

“…In order to more comprehensively verify the classification performance of the constructed 3D MRA‐CapsNet‐DL aided diagnosis model, we compared the 3D MRA‐CapsNet‐DL model with six multi‐modal fusion models 16,17,39–42 . The comparison results are shown in Table 6.…”

“…In order to more comprehensively verify the classification performance of the constructed 3D MRA-CapsNet-DL aided diagnosis model, we compared the 3D MRA-CapsNet-DL model with six multi-modal fusion models. 16,17,[39][40][41][42] The comparison results are shown in Table 6. Compared with the two models constructed in literature, 16 the aided diagnosis models based on 3D MRA-CapsNet-DL do not use serum biomarker information and has a larger number of classifications, but still achieves higher and more stable AUC scores.…”

Deep learning facilitates multi-data type analysis and predictive biomarker discovery in cancer precision medicine

“…Zhou et al used an autoencoder-based DL to learn the latent representative features of MS data and thereby detected paragangliomas and ovarian cancer with accuracies> 95% [76] . Shaffie et al implemented a DL autoencoder classifier framework using CT scan images and breath-based volatile metabolic marker data as inputs to achieve over 97.8% accuracy in lung cancer diagnosis [77] . Furthermore, DL models can facilitate network inference, including metabolite–metabolite interactions within a biochemical pathway.…”

Emerging Approaches to Complement Low-Dose Computerized Tomography for Lung Cancer Screening: A Narrative Review

“…Blood-based molecular biomarkers and radiomics have been employed in combination to diagnose early-stage lung cancer with improved sensitivity and specificity [ 6 ]. Similarly, combining information from LDCT and volatolomics can improve the accuracy of lung cancer detection [ 31 ]. Further studies will be needed to better understand the most efficacious approach to integrating these modalities into LDCT.…”