Role of Artificial Intelligence in PET/CT Imaging for Management of Lymphoma

Veziroglu, Eren M.; Farhadi, Faraz; Hasani, Navid; Nikpanah, Moozhan; Roschewski, Mark; Summers, Ronald M.; Saboury, Babak

doi:10.1053/j.semnuclmed.2022.11.003

Cited by 11 publications

(3 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We do not know of others evaluating deep learning-based biomarker extraction from PET/CT scans of HNC. However, there is evidence that PET/CT biomarkers can be extracted for 68 Ga-PSMA PET/CT scans of prostate cancer (total lesion volume and uptake) and 18 F-FDG PET/CT scans of lymphoma (total metabolic tumor volume) (27,28). These results support the indication of this work that AI can safely be used for PET/CT biomarker extraction.…”

Section: Discussionsupporting

confidence: 79%

Clinical Evaluation of Deep Learning for Tumor Delineation on¹⁸F-FDG PET/CT of Head and Neck Cancer

Kovacs,

Ladefoged,

Andersen

et al. 2024

J Nucl Med

View full text Add to dashboard Cite

Artificial intelligence (AI) may decrease 18 F-FDG PET/CT-based gross tumor volume (GTV) delineation variability and automate tumorvolume-derived image biomarker extraction. Hence, we aimed to identify and evaluate promising state-of-the-art deep learning methods for head and neck cancer (HNC) PET GTV delineation. Methods: We trained and evaluated deep learning methods using retrospectively included scans of HNC patients referred for radiotherapy between January 2014 and December 2019 (ISRCTN16907234). We used 3 test datasets: an internal set to compare methods, another internal set to compare AI-to-expert variability and expert interobserver variability (IOV), and an external set to compare internal and external AI-to-expert variability. Expert PET GTVs were used as the reference standard. Our benchmark IOV was measured using the PET GTV of 6 experts. The primary outcome was the Dice similarity coefficient (DSC). ANOVA was used to compare methods, a paired t test was used to compare AI-to-expert variability and expert IOV, an unpaired t test was used to compare internal and external AI-toexpert variability, and post hoc Bland-Altman analysis was used to evaluate biomarker agreement. Results: In total, 1,220 18 F-FDG PET/CT scans of 1,190 patients (mean age 6 SD, 63 6 10 y; 858 men) were included, and 5 deep learning methods were trained using 5-fold cross-validation (n 5 805). The nnU-Net method achieved the highest similarity (DSC, 0.80 [95% CI, 0.77-0.86]; n 5 196). We found no evidence of a difference between expert IOV and AI-to-expert variability (DSC, 0.78 for AI vs. 0.82 for experts; mean difference of 0.04 [95% CI, 20.01 to 0.09]; P 5 0.12; n 5 64). We found no evidence of a difference between the internal and external AI-to-expert variability (DSC, 0.80 internally vs. 0.81 externally; mean difference of 0.004 [95% CI, 20.05 to 0.04]; P 5 0.87; n 5 125). PET GTV-derived biomarkers of AI were in good agreement with experts. Conclusion: Deep learning can be used to automate 18 F-FDG PET/CT tumorvolume-derived imaging biomarkers, and the deep-learning-based volumes have the potential to assist clinical tumor volume delineation in radiation oncology.

show abstract

Section: Discussionsupporting

confidence: 79%

Clinical Evaluation of Deep Learning for Tumor Delineation on¹⁸F-FDG PET/CT of Head and Neck Cancer

Kovacs,

Ladefoged,

Andersen

et al. 2024

J Nucl Med

View full text Add to dashboard Cite

show abstract

“…Despite limited efforts focusing on this scope for the time being, it is expected that the field of artificial intelligence will dominate many aspects of molecular imaging implementation, especially in areas of uncertainty [131]. Notably, the value of machine learning and radiomics has been established in other forms of hematologic malignancies [132,133]. In an attempt to improve the diagnostic performance of [ 18 F]FDG PET/CT in detecting bone marrow lesions in leukemic patients, Li et al conducted a retrospective study of 41 patients with acute leukemia [134].…”

Section: The Value Of Artificial Intelligencementioning

confidence: 99%

PET/CT in leukemia: utility and future directions

Al-Ibraheem,

Allouzi,

Abdlkadir

et al. 2024

Nuclear Medicine Communications

View full text Add to dashboard Cite

2-Deoxy-2-[18F]fluoro-d-glucose PET/computed tomography ([18F]FDG PET/CT) has proven to be a sensitive method for the detection and evaluation of hematologic malignancies, especially lymphoma. The increasing incidence and mortality rates of leukemia have raised significant concerns. Through the utilization of whole-body imaging, [18F]FDG PET/CT provides a thorough assessment of the entire bone marrow, complementing the limited insights provided by biopsy samples. In this regard, [18F]FDG PET/CT has the ability to assess diverse types of leukemia The utilization of [18F]FDG PET/CT has been found to be effective in evaluating leukemia spread beyond the bone marrow, tracking disease relapse, identifying Richter’s transformation, and assessing the inflammatory activity associated with acute graft versus host disease. However, its role in various clinical scenarios in leukemia remains unacknowledged. Despite their less common use, some novel PET/CT radiotracers are being researched for potential use in specific scenarios in leukemia patients. Therefore, the objectives of this review are to provide a thorough assessment of the current applications of [18F]FDG PET/CT in the staging and monitoring of leukemia patients, as well as the potential for an expanding role of PET/CT in leukemia patients.

show abstract

“…This discrepancy could be due to the larger sample size of the current study (within participant comparison n=12 vs. n=9 [23]; between participant comparison 28 vs. 9 [23] injured legs), our careful pair matching of participant characteristics between groups (vs. greater body mass and age of the previously injured compared to uninjured athletes in [23]), or the differences in image analysis methods (human vs. automated algorithm [23]). Whilst manual aponeurosis analysis may be considered more subjective than automated methods, identifying the BF LH aponeurosis is a highly complex pattern recognition task for which humans are highly evolved [25] and designing automated methods of image analysis with equivalent accuracy/validity to human remains a challenge [33]. The human analysis of aponeurosis size in the current study was conducted blind for participant and leg assignation and we demonstrated excellent reliability (CV W 3.6 to 4.0%) of the entire measurement procedure (scanning and human analysis) on a cohort of nine independent participants, further illustrating the rigorous approach taken in the current study.…”

Section: Accepted Manuscriptmentioning

confidence: 99%

Smaller Biceps Femoris Aponeurosis Size in Legs with a History of Hamstring Strain Injury

Balshaw,

McDermott,

Massey

et al. 2024

Int J Sports Med

View full text Add to dashboard Cite

Biceps femoris long head (BFLH) aponeurosis size was compared between legs with and without prior hamstring strain injury (HSI) using within-group (injured vs. uninjured legs of previous unilateral HSI athletes) and between-group (previously injured legs of HSI athletes vs. legs of No prior HSI athletes) approaches. Currently healthy competitive male athletes with Prior HSI history (n=23; ≥1 verified BFLH injury; including a sub-group with unilateral HSI history; most recent HSI 1.6 ± 1.2 years ago) and pair-matched athletes with No prior HSI history (n=23) were MRI scanned. Anonymised axial images were manually segmented to quantify BFLH aponeurosis and muscle size. Prior unilateral HSI athletes’ BFLH aponeurosis maximum width, aponeurosis area, and aponeurosis:muscle area ratio was 14.0-19.6% smaller in previously injured vs. contralateral uninjured legs (paired t-test, 0.008≤p≤0.044). BFLH aponeurosis maximum width and area were also 9.4-16.5% smaller in previously injured legs (n=28) from prior HSI athletes vs. legs (n=46) of No prior HSI athletes (unpaired t-test, 0.001≤p≤0.044). BFLH aponeurosis size was smaller in legs with Prior HSI vs. those without prior HSI. These findings suggest BFLH aponeurosis size, especially maximum width, could be a potential cause or consequence of HSI, with prospective evidence needed to support or refute these possibilities.

show abstract

Role of Artificial Intelligence in PET/CT Imaging for Management of Lymphoma

Cited by 11 publications

References 63 publications

Clinical Evaluation of Deep Learning for Tumor Delineation on¹⁸F-FDG PET/CT of Head and Neck Cancer

Clinical Evaluation of Deep Learning for Tumor Delineation on¹⁸F-FDG PET/CT of Head and Neck Cancer

PET/CT in leukemia: utility and future directions

Smaller Biceps Femoris Aponeurosis Size in Legs with a History of Hamstring Strain Injury

Contact Info

Product

Resources

About

Role of Artificial Intelligence in PET/CT Imaging for Management of Lymphoma

Cited by 11 publications

References 63 publications

Clinical Evaluation of Deep Learning for Tumor Delineation on18F-FDG PET/CT of Head and Neck Cancer

Clinical Evaluation of Deep Learning for Tumor Delineation on18F-FDG PET/CT of Head and Neck Cancer

PET/CT in leukemia: utility and future directions

Smaller Biceps Femoris Aponeurosis Size in Legs with a History of Hamstring Strain Injury

Contact Info

Product

Resources

About

Clinical Evaluation of Deep Learning for Tumor Delineation on¹⁸F-FDG PET/CT of Head and Neck Cancer

Clinical Evaluation of Deep Learning for Tumor Delineation on¹⁸F-FDG PET/CT of Head and Neck Cancer