Validation of a Multifocal Segmentation Method for Measuring Metabolic Tumor Volume in Hodgkin Lymphoma

Camacho, Mariana; Etchebehere, Elba; Tardelli, Natalia Rocha; Delamain, Márcia Torresan; Verçosa, Alinne Fernanda Amaral; Takahashi, Maria Emília Seren; Brunetto, S. Q.; Metze, Irene Gyongyver Heidemarie Lorand; Souza, Cármino Antonio De; Cerci, Juliano Júlio; Ramos, Celso Darío

doi:10.2967/jnmt.119.231118

Cited by 14 publications

(17 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The images were processed using the software Syngo.via (Siemens Healthineers, Erlangen, Germany). In order to determine the main parameters, i.e., MTV and TLG, we used the special tool multi-foci segmentation (MFS) that automatically registered/delineated contours around each metabolically active focus as the sum of all voxels within VOI after determining the SUV background reference over the liver [ 24 ]. The threshold of FDG uptake was 41% of the SUV maximum inside, as recommended by the European Association of Nuclear Medicine.…”

Section: Methodsmentioning

confidence: 99%

AuNP Aptasensor for Hodgkin Lymphoma Monitoring

Slyusarenko

Shalaev²,

Valitova³

et al. 2022

Biosensors

View full text Add to dashboard Cite

A liquid biopsy based on circulating small extracellular vesicles (SEVs) has not yet been used in routine clinical practice due to the lack of reliable analytic technologies. Recent studies have demonstrated the great diagnostic potential of nanozyme-based systems for the detection of SEV markers. Here, we hypothesize that CD30-positive Hodgkin and Reed–Sternberg (HRS) cells secrete CD30 + SEVs; therefore, the relative amount of circulating CD30 + SEVs might reflect classical forms of Hodgkin lymphoma (cHL) activity and can be measured by using a nanozyme-based technique. A AuNP aptasensor analytics system was created using aurum nanoparticles (AuNPs) with peroxidase activity. Sensing was mediated by competing properties of DNA aptamers to attach onto surface of AuNPs inhibiting their enzymatic activity and to bind specific markers on SEVs surface. An enzymatic activity of AuNPs was evaluated through the color reaction. The study included characterization of the components of the analytic system and its functionality using transmission and scanning electron microscopy, nanoparticle tracking analysis (NTA), dynamic light scattering (DLS), and spectrophotometry. AuNP aptasensor analytics were optimized to quantify plasma CD30 + SEVs. The developed method allowed us to differentiate healthy donors and cHL patients. The results of the CD30 + SEV quantification in the plasma of cHL patients were compared with the results of disease activity assessment by positron emission tomography/computed tomography (PET-CT) scanning, revealing a strong positive correlation. Moreover, two cycles of chemotherapy resulted in a statistically significant decrease in CD30 + SEVs in the plasma of cHL patients. The proposed AuNP aptasensor system presents a promising new approach for monitoring cHL patients and can be modified for the diagnostic testing of other diseases.

show abstract

Section: Methodsmentioning

confidence: 99%

AuNP Aptasensor for Hodgkin Lymphoma Monitoring

Slyusarenko

Shalaev²,

Valitova³

et al. 2022

Biosensors

View full text Add to dashboard Cite

show abstract

“…Among potential biomarkers, metabolic tumour volume seems to be especially promising for clinicians as it represents a measure for the whole-body tumour burden. This principal attractiveness has led to several studies examining metabolic tumour volume and total lesion values for various solid and haematological malignancies, e.g., 18 F-FDG PET/CT scans and their prognostic impact for tumour entities such as cervical cancer [3], head and neck [4,5], pancreatic cancer [6], Hodgkin's lymphoma [7], ovarian [8] and prostate cancer (PCa) [9].…”

Section: Introductionmentioning

confidence: 99%

Metabolic Tumour Volume from PSMA PET/CT Scans of Prostate Cancer Patients during Chemotherapy—Do Different Software Solutions Deliver Comparable Results?

Hartrampf

Heinrich

Seitz

et al. 2020

JCM

View full text Add to dashboard Cite

(1) Background: Prostate-specific membrane antigen (PSMA)-derived tumour volume (PSMA-TV) and total lesion PSMA (TL-PSMA) from PSMA PET/CT scans are promising biomarkers for assessing treatment response in prostate cancer (PCa). Currently, it is unclear whether different software tools for assessing PSMA-TV and TL-PSMA produce comparable results. (2) Methods: 68Ga-PSMA PET/CT scans from n = 21 patients with castration-resistant PCa (CRPC) receiving chemotherapy were identified from our single-centre database. PSMA-TV and TL-PSMA were calculated with Syngo.via (Siemens) as well as the freely available Beth Israel plugin for FIJI (Fiji Is Just ImageJ) before and after chemotherapy. While statistical comparability was illustrated and quantified via Bland-Altman diagrams, the clinical agreement was estimated by matching PSMA-TV, TL-PSMA and relative changes of both variables during chemotherapy with changes in serum PSA (ΔPSA) and PERCIST (Positron Emission Response Criteria in Solid Tumors). (3) Results: Comparing absolute PSMA-TV and TL-PSMA as well as Bland–Altman plotting revealed a good statistical comparability of both software algorithms. For clinical agreement, classifying therapy response did not differ between PSMA-TV and TL-PSMA for both software solutions and showed highly positive correlations with BR. (4) Conclusions: due to the high levels of statistical and clinical agreement in our CRPC patient cohort undergoing taxane chemotherapy, comparing PSMA-TV and TL-PSMA determined by Syngo.via and FIJI appears feasible.

show abstract

“…For subjects in group A, having a low tumor burden, all regions of elevated tracer uptake were segmented semi-automatically using 45% of region SUVmax thresholding [ 19 ]. For subjects in group B, which included cases of high tumor burden, all high-uptake sites with SUVmax above the average liver uptake within a PERCIST-based reference region [ 27 ] were segmented with an incremental connected component algorithm [ 28 ] using 45% of SUVmax thresholding, of which up to one hundred sites per subject with the highest SUVmax were annotated. For each subject in group B, at least ten suspicious uptake sites were annotated when present, additionally labeling sites with lower SUVmax if necessary.…”

Section: Methodsmentioning

confidence: 99%

“…A multi-task convolutional neural network was trained to both classify PET/CT regions of interest as uptake suspicious or nonsuspicious for cancer and assign them an anatomical location classification. In addition to expert-annotated findings, regions of interest with SUVmax above 1 which were not labeled by the experts as suspicious were generated automatically with an incremental connected component algorithm [ 28 ], labeled as nonsuspicious, and used for training. These were generated using 45% of SUVmax thresholding and only for subjects in group A or subjects in group B with up to nine suspicious findings, i.e., for PET/CT images where all suspicious findings were annotated and remaining image regions could be considered physiological uptake.…”

Section: Methodsmentioning

confidence: 99%

“…In addition, we assessed the ability of the algorithm to determine the N and M stage from 68 Ga-PSMA-11 PET/CT images fully automatically. For each test set subject, we first segmented all regions with SUVmax above 1 using an incremental connected component algorithm [ 28 ] and 45% of SUVmax thresholding. These regions were then processed by the convolutional neural network, classified as nonsuspicious or suspicious, and assigned an anatomical location label.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Whole-body uptake classification and prostate cancer staging in 68Ga-PSMA-11 PET/CT using dual-tracer learning

Capobianco

Sibille

Chantadisai

et al. 2021

Eur J Nucl Med Mol Imaging

View full text Add to dashboard Cite

Purpose In PSMA-ligand PET/CT imaging, standardized evaluation frameworks and image-derived parameters are increasingly used to support prostate cancer staging. Clinical applicability remains challenging wherever manual measurements of numerous suspected lesions are required. Deep learning methods are promising for automated image analysis, typically requiring extensive expert-annotated image datasets to reach sufficient accuracy. We developed a deep learning method to support image-based staging, investigating the use of training information from two radiotracers. Methods In 173 subjects imaged with 68Ga-PSMA-11 PET/CT, divided into development (121) and test (52) sets, we trained and evaluated a convolutional neural network to both classify sites of elevated tracer uptake as nonsuspicious or suspicious for cancer and assign them an anatomical location. We evaluated training strategies to leverage information from a larger dataset of 18F-FDG PET/CT images and expert annotations, including transfer learning and combined training encoding the tracer type as input to the network. We assessed the agreement between the N and M stage assigned based on the network annotations and expert annotations, according to the PROMISE miTNM framework. Results In the development set, including 18F-FDG training data improved classification performance in four-fold cross validation. In the test set, compared to expert assessment, training with 18F-FDG data and the development set yielded 80.4% average precision [confidence interval (CI): 71.1–87.8] for identification of suspicious uptake sites, 77% (CI: 70.0–83.4) accuracy for anatomical location classification of suspicious findings, 81% agreement for identification of regional lymph node involvement, and 77% agreement for identification of metastatic stage. Conclusion The evaluated algorithm showed good agreement with expert assessment for identification and anatomical location classification of suspicious uptake sites in whole-body 68Ga-PSMA-11 PET/CT. With restricted PSMA-ligand data available, the use of training examples from a different radiotracer improved performance. The investigated methods are promising for enabling efficient assessment of cancer stage and tumor burden.

show abstract

Validation of a Multifocal Segmentation Method for Measuring Metabolic Tumor Volume in Hodgkin Lymphoma

Cited by 14 publications

References 16 publications

AuNP Aptasensor for Hodgkin Lymphoma Monitoring

AuNP Aptasensor for Hodgkin Lymphoma Monitoring

Metabolic Tumour Volume from PSMA PET/CT Scans of Prostate Cancer Patients during Chemotherapy—Do Different Software Solutions Deliver Comparable Results?

Whole-body uptake classification and prostate cancer staging in 68Ga-PSMA-11 PET/CT using dual-tracer learning

Contact Info

Product

Resources

About