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.

PROTECTION OF SWEET CORN FROM OSTRINIA NUBILALIS HBN. AND HELICOVERPA ARMIGERA HBN.

O. nubilalis and H. armigera regularly occur and cause significant damages in corn crops in Serbia, particularly under global warming conditions. Several measures are applied against these pests (crop rotation, tolerant and resistant hybrids, monitoring, forecast, chemical measures). Larvae damage stem, panicle and ear, which favour development of saprophytes and secondary infections by mycotoxin producing, pathogenic fungi. The aim of the paper was to test the efficacy of the insecticides azadirachtin and indoxacarb in sweet corn protection against the mentioned pests. The trials were conducted in 2014 at two localities (Becej B. and PoIjanice P.) on sweet corn, hybrid Enterprise according to standard OEPP methods (PP1/13; 1/152; 1/135). Products on the basis of azadirachtin (10 g a.i./I of product) at a rate of 0.4 and 0.5% and indoxacarb (150 g a.i./I of product) at a rate of 0.25 I/ha, were applied. Treatments were conducted on the 5th of August with tractor sprayers (high clearance). The plot size was 5000 m². Three assessments were made. The first one prior to treatment, on 25 randomly selected plants per replicate, and the number of O. nubilalis and H. armigera egg masses and larvae on silk was registered. In the second assessment (18th of August), on 20 randomly selected plants per replicate, the number of damaged plants and the number of vital larvae was registered. In the third assessment, immediately before harvest (28th of August, i.e. 12th of September) on 20 randomly selected plants per replicate, the number of plants broken below ear (fallen on the ground), damaged ears and vital larvae, was determined. Results are presented as means, efficacy (E%) according to Abbott and significance of differences by LSD test (5%). At B locality egg masses of O. nubilalis were registered on ear silk on 13-19% of plants and larvae on 3-7%, and larvae of H. armigera on 2-4%. At P locality egg masses of O. nubilalis were present on 34-40.8% of plants. After 13 days from treatment, at B locality the percentage of damaged plants was 3.8-7.5% and at a significantly lower level compared to control where 40.0% of damaged plants was recorded. Vital larvae of O. nubilalis were present on 1.3-31% of plants, depending on the insecticide and application rate, and in the control on 41.3%. At P locality the percentage of damaged plants per treatment ranged from 20 to 46.3% depending on insecticide and application rate, and in the control 63.8%, and the presence of vital larvae of O. nubilalis on 16.3-21.3% of plants, and in the control on 53.5%. Immediately before harvest, at B locality azadirachtin efficacy, depending on application rate and counted parameters, was 88.5-92.5%; 66.7-72.9% and 69.1-75.2%. Efficacy of indoxacarb in general was 75-100%. At P locality, efficacy of azadirachtin depending on application rate and counted parameters, was 77.8-88.9%; 66.5-83.3% and 44.1-74.6%, while efficacy of this insecticide in general amounted 91.5-100%.

[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.

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.

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.

Eleven densely clustered genes, six of them novel, in 176 kb of mouse t-complex DNA.

Targeted sequencing of the mouse t-complex has started with a 176-kb, gene-rich BAC localized with six PCR-based markers in inversion 2/3 of the highly duplicated region. The sequence contains 11 genes recovered primarily as cDNAs from early embryonic collections, including Igfals (previously placed on chromosome 17), Nubp2 (a fully characterized gene), Jsap1 (a JNK-binding protein), Rsp29 (the mouse homologue of the rat gene), Ndk3 (a nucleoside diphosphate kinase), and six additional putative genes of unknown function. With 50% GC content, 75% of the DNA transcribed, and one gene/16.0 kb (on average), the region may qualify as one of the most gene-dense segments in the mouse genome and provides candidates for dosage-sensitive phenotypes and mouse embryonic lethals mapped to the vicinity.

Genome-wide expression profiling of mid-gestation placenta and embryo using a 15,000 mouse developmental cDNA microarray.

cDNA microarray technology has been increasingly used to monitor global gene expression patterns in various tissues and cell types. However, applications to mammalian development have been hampered by the lack of appropriate cDNA collections, particularly for early developmental stages. To overcome this problem, a PCR-based cDNA library construction method was used to derive 52,374 expressed sequence tags from pre- and peri-implantation embryos, embryonic day (E) 12.5 female gonad/mesonephros, and newborn ovary. From these cDNA collections, a microarray representing 15,264 unique genes (78% novel and 22% known) was assembled. In initial applications, the divergence of placental and embryonic gene expression profiles was assessed. At stage E12.5 of development, based on triplicate experiments, 720 genes (6.5%) displayed statistically significant differences in expression between placenta and embryo. Among 289 more highly expressed in placenta, 61 placenta-specific genes encoded, for example, a novel prolactin-like protein. The number of genes highly expressed (and frequently specific) for placenta has thereby been increased 5-fold over the total previously reported, illustrating the potential of the microarrays for tissue-specific gene discovery and analysis of mammalian developmental programs.

Large-scale cDNA analysis reveals phased gene expression patterns during preimplantation mouse development.

Little is known about gene action in the preimplantation events that initiate mammalian development. Based on cDNA collections made from each stage from egg to blastocyst, 25438 3'-ESTs were derived, and represent 9718 genes, half of them novel. Thus, a considerable fraction of mammalian genes is dedicated to embryonic expression. This study reveals profound changes in gene expression that include the transient induction of transcripts at each stage. These results raise the possibility that development is driven by the action of a series of stage-specific expressed genes. The new genes, 798 of them placed on the mouse genetic map, provide entry points for analyses of human and mouse developmental disorders.

EGFR expression is linked to osteopontin and Nf-kB 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 (AU)