ABSTRACT
This work demonstrates that automated mine countermeasure (MCM) tasks are greatly facilitated by characterizing the seafloor environment in which the sensors operate as a first step within a comprehensive strategy for how to exploit information from available sensors, multiple detector types, measured features, and target classifiers, depending on the specific seabed characteristics present within the high-frequency synthetic aperture sonar (SAS) imagery used to perform MCM tasks. This approach is able to adapt as environmental characteristics change and includes the ability to recognize novel seabed types. Classifiers are then adaptively retrained through active learning in these unfamiliar seabed types, resulting in improved mitigation of challenging environmental clutter as it is encountered. Further, a segmentation constrained network algorithm is introduced to enable enhanced generalization abilities for recognizing mine-like objects from underrepresented environments within the training data. Additionally, a fusion approach is presented that allows the combination of multiple detectors, feature types spanning both measured expert features and deep learning, and an ensemble of classifiers for the particular seabed mixture proportions measured around each detected target. The environmentally adaptive approach is demonstrated to provide the best overall performance for automated mine-like object recognition.
ABSTRACT
Previously, we demonstrated potent antineoplastic activity of a distinctive histone deacetylase inhibitor (HDACI), AR42, against chemoresistant CP70 ovarian cancer cells in vitro and in vivo. Here, in follow-up to that work, we explored AR42 global mechanisms-of-action by examining drug-associated, genome-wide microRNA and mRNA expression profiles, which differed from those of the well-studied HDACI vorinostat. Expression of microRNA genes in negative correlation with their "target" coding gene (mRNA) transcripts, and transcription factor genes with expression positively correlated with coding genes having their cognate binding sites, were identified and subjected to gene ontology analyses. Those evaluations showed AR42 gene expression patterns to negatively correlate with Wnt signaling (> 18-fold induction of SFRP1), the epithelial-to-mesenchymal transition (40% decreased ATF1), and cell cycle progression (33-fold increased 14-3-3σ). By contrast, AR42 transcriptome alterations correlated positively with extrinsic ("death receptor") apoptosis (> 2.3-fold upregulated DAPK) and favorable ovarian cancer histopathology and prognosis. Inhibition of Wnt signaling was experimentally validated by: (1) > 2.6-fold reduced Wnt reporter activity; and (2) 36% reduction in nuclear, activated ß-catenin. Likely AR42 induction of multiple (type I or type II autophagic) cell death cascades was further supported by 57% decreased reliance upon reactive oxygen, increased mitochondrial membrane disruption, and caspase independence, as compared with vorinostat. Taken together, we demonstrate distinct antineoplastic pathway alterations, in aggressive ovarian cancer cells, following treatment with a promising HDACI, AR42. These combined computational and experimental approaches may also represent a straightforward means for mechanistic studies of other promising antineoplastics, and/or the identification of agents that may complement epigenetic therapies.
