Head and neck: normal variations and benign findings in FDG positron emission tomography/computed tomography imaging

Artificial intelligence and radiomics in the diagnosis of intraosseous lesions of the gnathic bones: A systematic review

BACKGROUND

The purpose of this systematic review (SR) is to gather evidence on the use of machine learning (ML) models in the diagnosis of intraosseous lesions in gnathic bones and to analyze the reliability, impact, and usefulness of such models. This SR was performed in accordance with the PRISMA 2022 guidelines and was registered in the PROSPERO database (CRD42022379298).

METHODS

The acronym PICOS was used to structure the inquiry-focused review question "Is Artificial Intelligence reliable for the diagnosis of intraosseous lesions in gnathic bones?" The literature search was conducted in various electronic databases, including PubMed, Embase, Scopus, Cochrane Library, Web of Science, Lilacs, IEEE Xplore, and Gray Literature (Google Scholar and ProQuest). Risk of bias assessment was performed using PROBAST, and the results were synthesized by considering the task and sampling strategy of the dataset.

RESULTS

Twenty-six studies were included (21 146 radiographic images). Ameloblastomas, odontogenic keratocysts, dentigerous cysts, and periapical cysts were the most frequently investigated lesions. According to TRIPOD, most studies were classified as type 2 (randomly divided). The F1 score was presented in only 13 studies, which provided the metrics for 20 trials, with a mean of 0.71 (±0.25).

CONCLUSION

There is no conclusive evidence to support the usefulness of ML-based models in the detection, segmentation, and classification of intraosseous lesions in gnathic bones for routine clinical application. The lack of detail about data sampling, the lack of a comprehensive set of metrics for training and validation, and the absence of external testing limit experiments and hinder proper evaluation of model performance.

FDG-PET/CT Variants and Pitfalls in Haematological Malignancies

Hematologic malignancies represent a vast group of hematopoietic and lymphoid cancers that typically involve the blood, the bone marrow, and the lymphatic organs. Due to extensive research and well defined and standardized response criteria, the role of [¹⁸F]FDG-PET/CT is well defined in these malignancies. Never the less, the reliability of visual and quantitative interpretation of PET/CT may be impaired by several factors including inconsistent scanning protocols and image reconstruction methods. Furthermore, the uptake of [¹⁸F]FDG not only reflects tissue glucose consumption by malignant lesions, but also in other situations such as in inflammatory lesions, local and systemic infections, benign tumors, reactive thymic hyperplasia, histiocytic infiltration, among others; or following granulocyte colony stimulating factors therapy, radiation therapy, chemotherapy or surgical interventions, all of which are a potential source of false-positive or negative interpretations. Therefore it is of paramount importance for the Nuclear Medicine Physician to be familiar with, not only the normal distribution of [¹⁸F]FDG in the body, but also with the most frequent findings that may hamper a correct interpretation of the scan, which could ultimately alter the patients management. In this review, we describe these myriad of situations so the interpreting physician can be familiar with them, providing tools for their correct identification and interpretation when possible.

[18F]PARPi Imaging Is Not Affected by HPV Status In Vitro

Background

Human papillomavirus- (HPV-) associated oropharyngeal squamous cell carcinomas (OPSCCs) are clinically and pathologically distinct from HPV-negative tumors. Here, we explore whether HPV affects functional biomarkers, including γH2AX, RAD51, and PARP1. Moreover, the role of [18F]PARPi as a broadly applicable imaging tool for head and neck carcinomas is investigated.

Methods

HPV-positive and HPV-negative cell lines were used to evaluate the γH2AX, RAD51, and PARP1 expression with immunoblotting and immunofluorescence. Effects of external beam ionizing radiation were investigated in vitro, and survival was investigated via colony-formation assay. [18F]PARPi uptake experiments were performed on HPV-negative and HPV-positive cell lines to quantify PARP1 expression. PARP1 IHC and γH2AX foci were quantified using patient-derived oropharyngeal tumor specimens.

Results

Differences in DNA repair were detected, showing higher RAD51 and γH2AX expression in HPV-positive cell lines. Clonogenic assays confirm HPV-positive cell lines to be significantly more radiosensitive. PARP1 expression levels were similar, irrespective of HPV status. Consequently, [18F]PARPi uptake assays demonstrated that this tracer is internalized in cell lines independently from their HPV status.

Conclusion

The HPV status, often used clinically to stratify patients, did not affect PARP1 levels, suggesting that PARP imaging can be performed in both HPV-positive and HPV-negative patients. This study confirms that the PET imaging agent [18F]PARPi could serve as a general clinical tool for oropharyngeal cancer patients.

Fluorine-18 labeled poly (ADP-ribose) polymerase1 inhibitor as a potential alternative to 2-deoxy-2-[18F]fluoro-d-glucose positron emission tomography in oral cancer imaging

OBJECTIVES

The evaluation of disease extent and post-therapy surveillance of head and neck cancer using 2-deoxy-2-[18F]fluoro-d-glucose ([18F]FDG) PET is often complicated by physiological uptake in normal tissues of the head and neck region, especially after surgery or radiotherapy. However, irrespective of low positive predictive values, [18F]FDG PET remains the standard of care to stage the disease and monitor recurrences. Here, we report the preclinical use of a targeted poly (ADP-ribose) polymerase1 (PARP1) binding PET tracer, fluorine-18 labeled poly (ADP-ribose) polymerase1 inhibitor ([18F]PARPi), as a potential alternative with greater specificity.

METHODS

Using an orthotopic xenograft mouse model injected with either FaDu or Cal 27 (human squamous cell carcinoma cell lines) we performed PET/CT scans with the 2 tracers and compared the results. Gamma counts and autoradiography were also assessed and correlated with histology.

RESULTS

The average retained activity of [18F]PARPi across cell lines in tumor-bearing tongues was 0.9 ± 0.3%ID/g, 4.1 times higher than in control (0.2 ± 0.04%ID/g). Autoradiography and histology confirmed that the activity arose almost exclusively from the tumor areas, with a signal/normal tissue around a ratio of 42.9 ± 21.4. In vivo, [18F]PARPi-PET allowed delineation of tumor from healthy tissue (p < .005), whereas [18F]FDG failed to do so (p = .209).

CONCLUSIONS AND IMPLICATIONS FOR PATIENT CARE

We demonstrate that [18F]PARPi is more specific to tongue tumor tissue than [18F]FDG. [18F]PARPi PET allows for the straightforward delineation of oral cancer in mouse models, suggesting that clinical translation could result in improved imaging of head and neck cancer when compared to [18F]FDG.