Radioguided Surgery, a Cost-Effective Strategy for Treating Solitary Pulmonary Nodules: 20-Year Experience of a Single Center

Classification of Pulmonary Nodules in 2-[18F]FDG PET/CT Images with a 3D Convolutional Neural Network

Purpose

2-[18F]FDG PET/CT plays an important role in the management of pulmonary nodules. Convolutional neural networks (CNNs) automatically learn features from images and have the potential to improve the discrimination between malignant and benign pulmonary nodules. The purpose of this study was to develop and validate a CNN model for classification of pulmonary nodules from 2-[18F]FDG PET images.

Methods

One hundred thirteen participants were retrospectively selected. One nodule per participant. The 2-[18F]FDG PET images were preprocessed and annotated with the reference standard. The deep learning experiment entailed random data splitting in five sets. A test set was held out for evaluation of the final model. Four-fold cross-validation was performed from the remaining sets for training and evaluating a set of candidate models and for selecting the final model. Models of three types of 3D CNNs architectures were trained from random weight initialization (Stacked 3D CNN, VGG-like and Inception-v2-like models) both in original and augmented datasets. Transfer learning, from ImageNet with ResNet-50, was also used.

Results

The final model (Stacked 3D CNN model) obtained an area under the ROC curve of 0.8385 (95% CI: 0.6455-1.0000) in the test set. The model had a sensibility of 80.00%, a specificity of 69.23% and an accuracy of 73.91%, in the test set, for an optimised decision threshold that assigns a higher cost to false negatives.

Conclusion

A 3D CNN model was effective at distinguishing benign from malignant pulmonary nodules in 2-[18F]FDG PET images.

Supplementary Information

The online version contains supplementary material available at 10.1007/s13139-023-00821-6.

Radio-Guided Lung Surgery: A Feasible Approach for a Cancer Precision Medicine

BACKGROUND

Radio-guided surgery is a reliable approach used for localizing ground-glass opacities, lung nodules, and metastatic lymph nodes. Lung nodules, lymph node metastatic involvement, and ground-glass opacities often represent a challenge for surgical management and clinical work-up.

METHODS

PubMed research was conducted from January 1997 to June 2023 using the keywords "radioguided surgery and lung cancer".

RESULTS

Different studies were conducted with different tracers: technetium-99m-albumin macroaggregates, cyanoacrylate combined to technetium-99m-sulfur colloid, indium-111-pentetreotide, and fluorine-18-deoxyglucose. A study proposed naphthalocyanine radio-labeled with copper-64. Radio-guided surgery has been demonstrated to be a reliable approach in localizing a lesion, and has a low radiological burden for personnel exposure and low morbidity. The lack of necessity to conduct radio-guided surgery under fluoroscopy or echography makes this radio-guided surgery an easy way of performing precise surgical procedures.

CONCLUSIONS

Radio-guided surgery is a feasible approach useful for the intraoperative localization of ground-glass opacities, lung nodules, and metastatic lymph nodes. It is a valid alternative to the existing approaches due to its low cost, associated low morbidity, the possibility to perform the procedure after several hours, the low radiation dose applied, and the small amount of time that is required to perform it.

Adding predictive and diagnostic values of pulmonary ground-glass nodules on lung cancer via novel non-invasive tests

Pulmonary ground-glass nodules (GGNs) are highly associated with lung cancer. Extensive studies using thin-section high-resolution CT images have been conducted to analyze characteristics of different types of GGNs in order to evaluate and determine the predictive and diagnostic values of GGNs on lung cancer. Accurate prediction of their malignancy and invasiveness is critical for developing individualized therapies and follow-up strategies for a better clinical outcome. Through reviewing the recent 5-year research on the association between pulmonary GGNs and lung cancer, we focused on the radiologic and pathological characteristics of different types of GGNs, pointed out the risk factors associated with malignancy, discussed recent genetic analysis and biomarker studies (including autoantibodies, cell-free miRNAs, cell-free DNA, and DNA methylation) for developing novel diagnostic tools. Based on current progress in this research area, we summarized a process from screening, diagnosis to follow-up of GGNs.

Lung nodule radio-guided localization and uniportal video-assisted thoracoscopic surgery resection

Since the introduction of lung nodule radio-guided localization, multiport video-assisted thoracoscopic surgery resection has been widely described. To date, only one series has reported the use of uniportal approach. Our objective is to describe the experience of a single institution of lung nodule radio-guided localization and uniportal video-assisted thoracoscopic surgery resection. Retrospective cohort study based on data from medical records of patients between May 2012 and April 2019. Twenty-four patients were included, 13 were women (54.2%) with a median age of 59.5 years (range 19 and 81 years). Median nodule size was 7 mm (range 3-12 mm) and 19 (79.2%) patients had single lung nodule. The main indication was sub-centimetric nodule in 22 (91.6%) patients followed by a deep localization in 10 (41.6%) patients and sub-solid nodule in 9 (37.5%) patients. Median surgical time was 102.5 min (range 55-160 min). 4 (16.6%) patients had malignant neoplasm of the lung, 10 (41.7%) patients had lung metastases and 10 (41.7%) patients had benign lung lesions. The success rate found was 95.8%. Concordance analysis between palpation of the pulmonary nodule and the presence of the nodule in the histopathology was rated as poor, kappa value - 0.71 (P = 0.186) and between the resection of the pulmonary nodule according to the presence of the nodule in the pathology report was rated as good, Kappa value 0.625 (P = 0.001). Lung nodule radio-guided localization and uniportal video-assisted thoracoscopic surgery resection has a similar success rate and complications to those described by multiport video-assisted thoracoscopic surgery resections.