Decision-support for treatment with 177Lu-PSMA: machine learning predicts response with high accuracy based on PSMA-PET/CT and clinical parameters.

BACKGROUND: Treatment with radiolabeled ligands to prostate-specific membrane antigen (PSMA) is gaining importance in the treatment of patients with advanced prostate carcinoma. Previous imaging with positron emission tomography/computed tomography (PET/CT) is mandatory. The aim of this study was to investigate the role of radiomics features in PSMA-PET/CT scans and clinical parameters to predict response to 177Lu-PSMA treatment given just baseline PSMA scans using state-of-the-art machine learning (ML) methods. METHODS: A total of 2,070 pathological hotspots annotated in 83 prostate cancer patients undergoing PSMA therapy were analyzed. Two main tasks are performed: (I) analyzing correlation of averaged (per patient) values of radiomics features of individual hotspots and clinical parameters with difference in prostate specific antigen levels (ΔPSA) in pre- and post-therapy as a therapy response indicator. (II) ML-based classification of patients into responders and non-responders based on averaged features values and clinical parameters. To achieve this, machine learning (ML) algorithms and linear regression tests are applied. Grid search, cross validation (CV) and permutation test were performed to assure that the results were significant. RESULTS: Radiomics features (PET_Min, PET_Correlation, CT_Min, CT_Busyness and CT_Coarseness) and clinical parameters such as Alp1 and Gleason score showed best correlations with ΔPSA. For the treatment response prediction task, 80% area under the curve (AUC), 75% sensitivity (SE), and 75% specificity (SP) were obtained, applying ML support vector machine (SVM) classifier with radial basis function (RBF) kernel on a selection of radiomics features and clinical parameters with strong correlations with ΔPSA. CONCLUSIONS: Machine learning based on 68Ga-PSMA PET/CT radiomics features holds promise for the prediction of response to 177Lu-PSMA treatment, given only base-line 68Ga-PSMA scan. In addition, it was shown that, the best correlating set of radiomics features with ΔPSA are superior to clinical parameters for this therapy response prediction task using ML classifiers.

Machine Learning Facilitates Hotspot Classification in PSMA-PET/CT with Nuclear Medicine Specialist Accuracy.

Gallium-68 prostate-specific membrane antigen positron emission tomography (68Ga-PSMA-PET) is a highly sensitive method to detect prostate cancer (PC) metastases. Visual discrimination between malignant and physiologic/unspecific tracer accumulation by a nuclear medicine (NM) specialist is essential for image interpretation. In the future, automated machine learning (ML)-based tools will assist physicians in image analysis. The aim of this work was to develop a tool for analysis of 68Ga-PSMA-PET images and to compare its efficacy to that of human readers. Five different ML methods were compared and tested on multiple positron emission tomography/computed tomography (PET/CT) data-sets. Forty textural features extracted from both PET- and low-dose CT data were analyzed. In total, 2419 hotspots from 72 patients were included. Comparing results from human readers to those of ML-based analyses, up to 98% area under the curve (AUC), 94% sensitivity (SE), and 89% specificity (SP) were achieved. Interestingly, textural features assessed in native low-dose CT increased the accuracy significantly. Thus, ML based on 68Ga-PSMA-PET/CT radiomics features can classify hotspots with high precision, comparable to that of experienced NM physicians. Additionally, the superiority of multimodal ML-based analysis considering all PET and low-dose CT features was shown. Morphological features seemed to be of special additional importance even though they were extracted from native low-dose CTs.

Role of textural heterogeneity parameters in patient selection for 177Lu-PSMA therapy via response prediction.

PURPOSE: Prostate cancer is most common tumor in men causing significant patient mortality and morbidity. In newer diagnostic/therapeutic agents PSMA linked ones are specifically important. Analysis of textural heterogeneity parameters is associated with determination of innately aggressive and therapy resistant cell lines thus emphasizing their importance in therapy planning. The objective of current study was to assess predictive ability of tumor textural heterogeneity parameters from baseline 68Ga-PSMA PET prior to 177Lu-PSMA therapy. RESULTS: Entropy showed a negative correlation (rs = -0.327, p = 0.006, AUC = 0.695) and homogeneity showed a positive correlation (rs = 0.315, p = 0.008, AUC = 0.683) with change in pre and post therapy PSA levels. CONCLUSIONS: Study showed potential for response prediction through baseline PET scan using textural features. It suggested that increase in heterogeneity of PSMA expression seems to be associated with an increased response to PSMA radionuclide therapy. MATERIALS AND METHODS: Retrospective analysis of 70 patients was performed. All patients had metastatic prostate cancer and were planned to undergo 177Lu-PSMA therapy. Pre-therapeutic 68Ga- PSMA PET scans were used for analysis. 3D volumes (VOIs) of 3 lesions each in bones and lymph nodes were manually delineated in static PET images. Five PET based textural heterogeneity parameters (COV, entropy, homogeneity, contrast, size variation) were determined. Results obtained were then compared with clinical parameters including pre and post therapy PSA, alkaline phosphate, bone specific alkaline phosphate levels and ECOG criteria. Spearman correlation was used to determine statistical dependence among variables. ROC analysis was performed to estimate the optimal cutoff value and AUC.

Unsupervised consensus cluster analysis of [18F]-fluoroethyl-L-tyrosine positron emission tomography identified textural features for the diagnosis of pseudoprogression in high-grade glioma.

RATIONALE: Timely detection of pseudoprogression (PSP) is crucial for the management of patients with high-grade glioma (HGG) but remains difficult. Textural features of O-(2-[18F]fluoroethyl)-L-tyrosine positron emission tomography (FET-PET) mirror tumor uptake heterogeneity; some of them may be associated with tumor progression. METHODS: Fourteen patients with HGG and suspected of PSP underwent FET-PET imaging. A set of 19 conventional and textural FET-PET features were evaluated and subjected to unsupervised consensus clustering. The final diagnosis of true progression vs. PSP was based on follow-up MRI using RANO criteria. RESULTS: Three robust clusters have been identified based on 10 predominantly textural FET-PET features. None of the patients with PSP fell into cluster 2, which was associated with high values for textural FET-PET markers of uptake heterogeneity. Three out of 4 patients with PSP were assigned to cluster 3 that was largely associated with low values of textural FET-PET features. By comparison, tumor-to-normal brain ratio (TNRmax) at the optimal cutoff 2.1 was less predictive of PSP (negative predictive value 57% for detecting true progression, p=0.07 vs. 75% with cluster 3, p=0.04). PRINCIPAL CONCLUSIONS: Clustering based on textural O-(2-[18F]fluoroethyl)-L-tyrosine PET features may provide valuable information in assessing the elusive phenomenon of pseudoprogression.

Labelling of ceftriaxone with (99m) Tc and its bio-evaluation as an infection imaging agent.

Differentiation of bacterial and sterile inflammation will have a significant impact on the current clinical practice. Ceftriaxone (CTRX) was labelled with (99m) Tc and assessed for its ability to depict infection on scintigraphy. Stoichiometry was performed to optimize labelling parameters. Stability and bacterial binding was verified and biodistribution pattern was seen in normal, infected/inflamed animal models. (99m) Tc-CTRX prepared at pH 7 with stannous chloride of 50 µg, ligand of 30 mg, and boiling for 10 min gave labelling yield of 96.2 ± 0.2% with good stability. In vitro binding was higher for Escherichia coli than Staphylococcus aureus. Biodistribution in normal rats showed high uptake in hepatobiliary system, gut and urinary system. In animal models induced with infection or inflammation, lesion to normal ratios at 4 h were 2.36 ± 0.21, 12.66 ± 1.44 and 1.40 ± 0.01 with S. aureus infection, E. coli infection and turpentine oil inflammation, respectively. Infection specificity especially for E. coli was also confirmed on scintigraphic findings. Ceftriaxone can be labelled with (99m) Tc with high labelling yield at pH compatible with that of blood. Our preparation has shown stability in vitro and in human serum, and binds preferentially with bacteria. (99m) Tc-CTRX scintigraphy can be used to delineate sites of active infection and to differentiate infection and inflammation.