# Machine Learning–Guided Detection of Malignancy of Lung Nodules With Molecular Imaging–Guided Surgery

## TL;DR

This study shows that combining machine learning and molecular imaging during lung cancer surgery can quickly and accurately determine if a lung nodule is malignant.

## Contribution

The novel contribution is the development and validation of an AI-guided optical biopsy algorithm for intraoperative lung nodule assessment.

## Key findings

- The algorithm achieved 93.8% sensitivity and 100% specificity in identifying malignant nodules.
- It determined malignancy in under 2 minutes, significantly faster than traditional frozen section analysis.
- Key factors like TBR and patient smoking history were strongly associated with malignancy.

## Abstract

This cohort study evaluates use of a machine learning algorithm with molecular imaging to analyze imaging data during lung cancer surgery to determine the malignant potential of nodules.

Can a combination of machine learning–guided image recognition and molecular imaging technology optically biopsy lung nodules?

This cohort study with 322 patients evaluates the use of machine learning–based algorithms in conjunction with robust nomograms during intraoperative molecular imaging (IMI)–guided lung cancer resections. Results suggest that the algorithm can identify and estimate malignant potential of an indeterminate lung nodule in a fast and efficient manner, with an area under the curve of 0.865 to 0.893 for malignant nodule assessment.

These findings suggest availability and implementation of artificial intelligence or machine learning–guided optical biopsy represents an area of new development in surgical oncology. The combination of computational processing power and IMI can serve as a useful adjunct for fast clinical decision-making intraoperatively.

Over 1 million pulmonary nodules are discovered each year in the US, and many of these undergo molecular imaging–guided surgery to obtain a diagnosis. Locating a small nodule and determining its malignant potential is technically challenging and is prone to human error.

To demonstrate use of a machine learning (ML) algorithm with molecular imaging to analyze imaging data during lung cancer surgery to determine malignant potential of nodules.

Data were retrospectively analyzed from a prospectively collected database. Between 2014 and 2021, patients at the hospital of the University of Pennsylvania with lung nodules were included in the study. Patients in the model development set were randomly allocated into training and validation sets in an 8:2 ratio. Data were analyzed from January 2014 and December 2021.

Algorithmic tumor to background ratio (TBR) detection was implemented for individual images using Image Processing Toolkit. Developed nomogram and artificial intelligence (AI) image analyzer were combined as an optical biopsy algorithm and tested prospectively between 2021 and 2024.

A total of 322 patients with lung nodules were included in the study, of whom 279 had complete clinical data for data analysis (175 [62.7%] female). The nomograms and image segmentation technology were developed using a large database of IMI videos (1014 video sequences) and demonstrated an area under the curve of 0.865 to 0.893 for malignant nodule assessment. On multivariate logistic regression analysis, patient smoking history of greater than 5 pack-years (patient pack-years [PPY] >5), ex vivo back table TBR greater than 2.0, ex vivo bisected tumor lesions TBR greater than 2.4, and in situ (inside the chest) fluorescence were found to have statistically significant associations with malignancy on final pathology. Prospective testing in an independent set of 61 consecutive patients during IMI-guided cancer surgery demonstrated a sensitivity of 93.8%, specificity of 100%, positive predictive value of 100%, and negative predictive value of 71%. The study algorithm determined malignant potential of the lesion in less than 2 minutes (mean [SD], 1.8 [0.17] minutes) compared with a mean (SD) of 34 (11) minutes with frozen section analysis.

In this cohort study of patients with indeterminate lung nodules, intraoperative imaging data analyzed by AI accurately determined if a nodule was malignant. This has the potential to improve the diagnostic challenges that occur at the time of surgery