Challenges in Interpretation of Staging PET/CT in Thoracic Malignancies

Artificial Intelligence-Driven Single-Shot PET Image Artifact Detection and Disentanglement: Toward Routine Clinical Image Quality Assurance

PURPOSE

Medical imaging artifacts compromise image quality and quantitative analysis and might confound interpretation and misguide clinical decision-making. The present work envisions and demonstrates a new paradigm PET image Quality Assurance NETwork (PET-QA-NET) in which various image artifacts are detected and disentangled from images without prior knowledge of a standard of reference or ground truth for routine PET image quality assurance.

METHODS

The network was trained and evaluated using training/validation/testing data sets consisting of 669/100/100 artifact-free oncological 18 F-FDG PET/CT images and subsequently fine-tuned and evaluated on 384 (20% for fine-tuning) scans from 8 different PET centers. The developed DL model was quantitatively assessed using various image quality metrics calculated for 22 volumes of interest defined on each scan. In addition, 200 additional 18 F-FDG PET/CT scans (this time with artifacts), generated using both CT-based attenuation and scatter correction (routine PET) and PET-QA-NET, were blindly evaluated by 2 nuclear medicine physicians for the presence of artifacts, diagnostic confidence, image quality, and the number of lesions detected in different body regions.

RESULTS

Across the volumes of interest of 100 patients, SUV MAE values of 0.13 ± 0.04, 0.24 ± 0.1, and 0.21 ± 0.06 were reached for SUV mean , SUV max , and SUV peak , respectively (no statistically significant difference). Qualitative assessment showed a general trend of improved image quality and diagnostic confidence and reduced image artifacts for PET-QA-NET compared with routine CT-based attenuation and scatter correction.

CONCLUSION

We developed a highly effective and reliable quality assurance tool that can be embedded routinely to detect and correct for 18 F-FDG PET image artifacts in clinical setting with notably improved PET image quality and quantitative capabilities.

Automated procedure assessing the accuracy of HRCT-PET registration applied in functional virtual bronchoscopy

Background

Bronchoscopy serves as direct visualisation of the airway. Virtual bronchoscopy provides similar visual information using a non-invasive imaging procedure(s). Early and accurate image-guided diagnosis requires the possible highest performance, which might be approximated by combining anatomical and functional imaging. This communication describes an advanced functional virtual bronchoscopic (fVB) method based on the registration of PET images to high-resolution diagnostic CT images instead of low-dose CT images of lower resolution obtained from PET/CT scans. PET/CT and diagnostic CT data were collected from 22 oncological patients to develop a computer-aided high-precision fVB. Registration of segmented images was performed using elastix.

Results

For virtual bronchoscopy, we used an in-house developed segmentation method. The quality of low- and high-dose CT image registrations was characterised by expert’s scoring the spatial distance of manually paired corresponding points and by eight voxel intensity-based (dis)similarity parameters. The distribution of (dis)similarity parameter correlating best with anatomic scoring was bootstrapped, and 95% confidence intervals were calculated separately for acceptable and insufficient registrations. We showed that mutual information (MI) of the eight investigated (dis)similarity parameters displayed the closest correlation with the anatomy-based distance metrics used to characterise the quality of image registrations. The 95% confidence intervals of the bootstrapped MI distribution were [0.15, 0.22] and [0.28, 0.37] for insufficient and acceptable registrations, respectively. In case of any new patient, a calculated MI value of registered low- and high-dose CT image pair within the [0.28, 0.37] or the [0.15, 0.22] interval would suggest acceptance or rejection, respectively, serving as an aid for the radiologist.

Conclusion

A computer-aided solution was proposed in order to reduce reliance on radiologist’s contribution for the approval of acceptable image registrations.

Nuclear Imaging Study of the Pharmacodynamic Effects of Debio 1143, an Antagonist of Multiple Inhibitor of Apoptosis Proteins (IAPs), in a Triple-Negative Breast Cancer Model

Background

Debio 1143, a potent orally available SMAC mimetic, targets inhibitors of apoptosis proteins (IAPs) members and is currently in clinical trials. In this study, nuclear imaging evaluated the effects of Debio 1143 on tumor cell death and metabolism in a triple-negative breast cancer (TNBC) cell line (MDA-MB-231)-based animal model.

Methods

Apoptosis induced by Debio 1143 was assessed by FACS (caspase-3, annexin 5 (A5)), binding of ^99mTc-HYNIC-Annexin V, and a cell proliferation assay. ^99mTc-HYNIC-Annexin V SPECT and [¹⁸F]-FDG PET were also performed in mice xenografted with MDA-MB-231 cells.

Results

Debio 1143 induced early apoptosis both in vitro and in vivo 6 h after treatment. Debio 1143 inhibited tumor growth, which was associated with a decreased tumor [¹⁸F]-FDG uptake when measured during treatment.

Conclusions

This imaging study combining SPECT and PET showed the early proapoptotic effects of Debio 1143 resulting in a robust antitumor activity in a preclinical TNBC model. These imaging biomarkers represent valuable noninvasive tools for translational and clinical research in TNBC.

Nanoparticle-Based Magnetic Resonance Imaging on Tumor-Associated Macrophages and Inflammation

The inflammatory response, mediated by tissue-resident or newly recruited macrophages, is an underlying pathophysiological condition for many diseases, including diabetes, obesity, neurodegeneration, atherosclerosis, and cancer. Paradoxically, inflammation is a double-edged sword in oncology. Macrophages are, generally speaking, the major drivers of inflammatory insult. For many solid tumors, high density of cells expressing macrophage-associated markers have generally been found in association with a poor clinical outcome, characterized by inflamed microenvironment, a high level of dissemination and resistance to conventional chemotherapies. On another hand, radiation treatment also triggers an inflammatory response in tumors (often referred to as pseudoprogression), which can be associated with a positive treatment response. As such, non-invasive imaging of cancer inflammation and tumor-associated macrophages (TAMs) provides a revolutionary diagnostic tool and monitoring strategy for anti-inflammatory, immuno- and radiotherapies. Recently, quantitative T2-weighted magnetic resonance imaging (qT2wMRI), using injection of superparamagnetic iron oxide nanoparticles (SPIONs), has been reported for the assessment of TAMs non-invasively in animal models and in human trials. The SPIONs are magnetic resonance imaging (MRI) contrast agents that significantly decrease T2 MR relaxation times in inflamed tissues due to the macrophage-specific uptake and retention. It has been shown that macrophage-populated tumors and metastases will accumulate iron oxide nanoparticles and decrease T2-relaxation time that will result in a negative (dark) contrast in qT2wMRI. Non-invasive imaging of TAMs using SPION holds a great promise for staging the inflammatory microenvironment of primary and metastatic tumors as well monitoring the treatment response of cancer patients treated with radiation and immunotherapy.