Machine learning predictive performance evaluation of conventional and fuzzy radiomics in clinical cancer imaging cohorts.

BACKGROUND: Hybrid imaging became an instrumental part of medical imaging, particularly cancer imaging processes in clinical routine. To date, several radiomic and machine learning studies investigated the feasibility of in vivo tumor characterization with variable outcomes. This study aims to investigate the effect of recently proposed fuzzy radiomics and compare its predictive performance to conventional radiomics in cancer imaging cohorts. In addition, lesion vs. lesion+surrounding fuzzy and conventional radiomic analysis was conducted. METHODS: Previously published 11C Methionine (MET) positron emission tomography (PET) glioma, 18F-FDG PET/computed tomography (CT) lung, and 68GA-PSMA-11 PET/magneto-resonance imaging (MRI) prostate cancer retrospective cohorts were included in the analysis to predict their respective clinical endpoints. Four delineation methods including manually defined reference binary (Ref-B), its smoothed, fuzzified version (Ref-F), as well as extended binary (Ext-B) and its fuzzified version (Ext-F) were incorporated to extract imaging biomarker standardization initiative (IBSI)-conform radiomic features from each cohort. Machine learning for the four delineation approaches was performed utilizing a Monte Carlo cross-validation scheme to estimate the predictive performance of the four delineation methods. RESULTS: Reference fuzzy (Ref-F) delineation outperformed its binary delineation (Ref-B) counterpart in all cohorts within a volume range of 938-354987 mm3 with relative cross-validation area under the receiver operator characteristics curve (AUC) of +4.7-10.4. Compared to Ref-B, the highest AUC performance difference was observed by the Ref-F delineation in the glioma cohort (Ref-F: 0.74 vs. Ref-B: 0.70) and in the prostate cohort by Ref-F and Ext-F (Ref-F: 0.84, Ext-F: 0.86 vs. Ref-B: 0.80). In addition, fuzzy radiomics decreased feature redundancy by approx. 20%. CONCLUSIONS: Fuzzy radiomics has the potential to increase predictive performance particularly in small lesion sizes compared to conventional binary radiomics in PET. We hypothesize that this effect is due to the ability of fuzzy radiomics to model partial volume effects and delineation uncertainties at small lesion boundaries. In addition, we consider that the lower redundancy of fuzzy radiomic features supports the identification of imaging biomarkers in future studies. Future studies shall consider systematically analyzing lesions and their surroundings with fuzzy and binary radiomics.

Supervised machine learning enables non-invasive lesion characterization in primary prostate cancer with [68Ga]Ga-PSMA-11 PET/MRI.

PURPOSE: Risk classification of primary prostate cancer in clinical routine is mainly based on prostate-specific antigen (PSA) levels, Gleason scores from biopsy samples, and tumor-nodes-metastasis (TNM) staging. This study aimed to investigate the diagnostic performance of positron emission tomography/magnetic resonance imaging (PET/MRI) in vivo models for predicting low-vs-high lesion risk (LH) as well as biochemical recurrence (BCR) and overall patient risk (OPR) with machine learning. METHODS: Fifty-two patients who underwent multi-parametric dual-tracer [18F]FMC and [68Ga]Ga-PSMA-11 PET/MRI as well as radical prostatectomy between 2014 and 2015 were included as part of a single-center pilot to a randomized prospective trial (NCT02659527). Radiomics in combination with ensemble machine learning was applied including the [68Ga]Ga-PSMA-11 PET, the apparent diffusion coefficient, and the transverse relaxation time-weighted MRI scans of each patient to establish a low-vs-high risk lesion prediction model (MLH). Furthermore, MBCR and MOPR predictive model schemes were built by combining MLH, PSA, and clinical stage values of patients. Performance evaluation of the established models was performed with 1000-fold Monte Carlo (MC) cross-validation. Results were additionally compared to conventional [68Ga]Ga-PSMA-11 standardized uptake value (SUV) analyses. RESULTS: The area under the receiver operator characteristic curve (AUC) of the MLH model (0.86) was higher than the AUC of the [68Ga]Ga-PSMA-11 SUVmax analysis (0.80). MC cross-validation revealed 89% and 91% accuracies with 0.90 and 0.94 AUCs for the MBCR and MOPR models respectively, while standard routine analysis based on PSA, biopsy Gleason score, and TNM staging resulted in 69% and 70% accuracies to predict BCR and OPR respectively. CONCLUSION: Our results demonstrate the potential to enhance risk classification in primary prostate cancer patients built on PET/MRI radiomics and machine learning without biopsy sampling.

EGFR expression is linked to osteopontin and Nf-κB signaling in clear cell renal cell carcinoma.

AIM AND BACKGROUND: Epidermal growth factor receptor (EGFR) is a receptor tyrosine kinase involved in many important aspects of cell biology that are related to tumorigenesis. There are opposite evidences of the role of EGFR in renal cancer and the outcome of EGFR-targeted therapies, suggesting the complexity of EGFR signaling pathways. In vitro, osteopontin (OPN) and nuclear factor kappa B (NF-κB) are thought to be involved in specific ligand-independent EGFR activation that could have a role in resistance to EGFR mAb therapy. Aim of this study was to analyze the relationship between EGFR and OPN at the protein and mRNA level, as well as their relation to NF-κB in clear cell renal cell carcinoma (CCRCC). MATERIALS AND METHODS: Expression of EGFR, OPN, and p65 NF-κB protein was analyzed using immunohistochemistry and compared mutually in 88 CCRCC samples. Expression of EGFR and OPN mRNAs was analyzed using quantitative Real-time PCR in 22 CCRCC samples and compared mutually and with NF-κB protein expression. RESULTS: Epidermal growth factor receptor mRNA level was higher in CCRCC samples in comparison with normal renal tissue (p = 0.012) and was associated with high OPN mRNA level, and with NF-κB activation (p < 0.001 and p = 0.045, respectively). Immunohistochemical staining showed the inverse association; high EGFR protein expression was related with low OPN and NF-κB protein expression (p < 0.001 and p = 0.047, respectively). CONCLUSION: Epidermal growth factor receptor gene is upregulated in CRCC and associated with OPN gene expression and NF-kB signaling. The inverse relation between OPN and EGFR at the protein level could probably reflect dynamic changes that EGFR undergoes following activation.

[Paraneoplastic palmoplantar hyperkeratosis. Minor form of acrokeratosis neoplastica Bazex?]. / Paraneoplastische palmoplantare Hyperkeratose. Minorform der Acrokeratosis paraneoplastica Bazex?

Acrokeratosis paraneoplastica Bazex is a rare, obligate paraneoplasia initially presenting with palmoplantar hyperkeratosis. Later stages show acral psoriasiform lesions on other parts of the body. Common associated malignancies are laryngeal cancer and other tumors of the head or neck region or neck lymph node metastases. A 49-year-old woman presented with palmoplantar hyperkeratoses for 4 months; in addition she had a squamous cell carcinoma of the larynx. We diagnosed a minor form of acrokeratosis paraneoplastica Bazex. Some authors consider this as a separate entity, but the well- known course argues against this hypothesis. We report a case and review the literature.

Two novel mouse genes--Nubp2, mapped to the t-complex on chromosome 17, and Nubp1, mapped to chromosome 16--establish a new gene family of nucleotide-binding proteins in eukaryotes.

Two novel mouse genes and one novel human gene that define distinctive eukaryotic nucleotide-binding proteins (NUBP) and are related to the mrp gene of prokaryotes are characterized. Phylogenetic analyses of the genes, encoding a short form (Nubp2) and a long form (Nubp1) of NUBP, clearly establish them as a new NUBP/MRP gene family that is well conserved throughout phylogeny. In addition to conserved ATP/GTP-binding motifs A (P-loop) and A', members of this family share at least two highly conserved sequence motifs, NUBP/MRP motifs alpha and beta. Only one type of NUBP/MRP gene has been observed thus far in prokaryotes, but there are two types in eukaryotes. One group includes mouse Nubp1, human NBP, yeast NBP35, and Caenorhabditis elegans F10G8.6 and is characterized by a unique N-terminal sequence with four cysteine residues that is lacking in the other group, which includes mouse Nubp2, human NUBP2, and yeast YIA3w. Northern blot analyses of the two mouse genes show distinctive patterns consistent with this classification. Mouse Nubp2 is mapped to the t-complex region of mouse Chromosome 17, whereas Nubp1 is mapped to the proximal region of mouse Chromosome 16. Interestingly, both regions are syntenic with human chromosome 16p13.1-p13.3, suggesting that a chromosomal breakage between Nubp2 and Nubp1 probably occurred during the evolution of mouse chromosomes.