The classification of stages of epiretinal membrane using convolutional neural network on optical coherence tomography image.

BACKGROUND AND OBJECTIVE: The gold standard for diagnosing epiretinal membranes is to observe the surface of the internal limiting membrane on optical coherence tomography images. The stages of the epiretinal membrane are used to decide the condition of the health of the membrane. The stages are not detected because some of them are similar. To accurately classify the stages, a deep-learning technology can be used to improve the classification accuracy. METHODS: A combinatorial fusion with multiple convolutional neural networks (CNN) algorithms are proposed to enhance the accuracy of a single image classification model. The proposed method was trained using a dataset of 1947 optical coherence tomography images diagnosed with the epiretinal membrane at the Taichung Veterans General Hospital in Taiwan. The images consisted of 4 stages; stages 1, 2, 3, and 4. RESULTS: The overall accuracy of the classification was 84%. The combination of five and six CNN models achieves the highest testing accuracy (85%) among other combinations, respectively. Any combination with a different number of CNN models outperforms any single CNN algorithm working alone. Meanwhile, the accuracy of the proposed method is better than ophthalmologists with years of clinical experience. CONCLUSIONS: We have developed an efficient epiretinal membrane classification method by using combinatorial fusion with CNN models on optical coherence tomography images. The proposed method can be used for screening purposes to facilitate ophthalmologists making the correct diagnoses in general medical practice.

Discovery of novel potent imidazo[1,2-b]pyridazine PDE10a inhibitors.

Design and optimization of a novel series of imidazo[1,2-b]pyridazine PDE10a inhibitors are described. Compound 31 displays excellent pharmacokinetic properties and was also evaluated as an insulin secretagogue in vitro and in vivo.

Developments in factor Xa inhibitors for the treatment of thromboembolic disorders.

Thromboembolic diseases are the leading causes of morbidity and mortality in the developed world. Anticoagulants provide effective treatment for venous or arterial thromboembolism. Two coagulation factors, factor Xa (fXa) and thrombin, are the primary targets under active investigation for anticoagulant therapy. fXa, in contrast to the multifunctional roles of thrombin in the coagulation cascade, converts prothrombin to thrombin collectively at the junction of the intrinsic and extrinsic pathway of coagulation. The effectiveness of fXa inhibitors as antithrombotic agents and their potentially reduced bleeding risks may offer superior therapeutic profiles with respect to thrombin inhibitors. After decades of research, many fXa inhibitors are now in the advanced stages of clinical trials. Unlike most reviews, which only provide incremental updates, this review provides an overview of fXa and the medicinal chemistry of its inhibitors. Overviews on coagulation models, antithrombotic therapy, and fXa will be provided, followed by the evolution of the medicinal chemistry of fXa inhibitors over the past few decades.

7-fluoroindazoles as potent and selective inhibitors of factor Xa.

We have developed a novel series of potent and selective factor Xa inhibitors that employ a key 7-fluoroindazolyl moiety. The 7-fluoro group on the indazole scaffold replaces the carbonyl group of an amide that is found in previously reported factor Xa inhibitors. The structure of a factor Xa cocrystal containing 7-fluoroindazole 51a showed the 7-fluoro atom hydrogen-bonding with the N-H of Gly216 (2.9 A) in the peptide backbone. Thus, the 7-fluoroindazolyl moiety not only occupied the same space as the carbonyl group of an amide found in prior factor Xa inhibitors but also maintained a hydrogen bond interaction with the protein's beta-sheet domain. The structure-activity relationship for this series was consistent with this finding, as the factor Xa inhibitory potencies were about 60-fold greater (DeltaDelta G approximately 2.4 kcal/mol) for the 7-fluoroindazoles 25a and 25c versus the corresponding indazoles 25b and 25d. Highly convergent synthesis of these factor Xa inhibitors is also described.

Benzo[d]imidazole Transient Receptor Potential Vanilloid 1 Antagonists for the Treatment of Pain: Discovery of trans-2-(2-{2-[2-(4-Trifluoromethyl-phenyl)-vinyl]-1H-benzimidazol-5-yl}-phenyl)-propan-2-ol (Mavatrep).

Reported herein is the design, synthesis, and pharmacologic characterization of a class of TRPV1 antagonists constructed on a benzo[d]imidazole platform that evolved from a biaryl amide lead. This design composes three sections: a 2-substituted 5-phenyl headgroup attached to the benzo[d]imidazole platform, which is tethered at the two position to a phenyl tail group. Optimization of this design led to the identification of 4 (mavatrep), comprising a trifluoromethyl-phenyl-vinyl tail. In a TRPV1 functional assay, using cells expressing recombinant human TRPV1 channels, 4 antagonized capsaicin-induced Ca(2+) influx, with an IC50 value of 4.6 nM. In the complete Freund's adjuvant- and carrageenan-induced thermal hypersensitivity models, 4 exhibited full efficacy, with ED80 values of 7.8 and 0.5 mg/kg, respectively, corresponding to plasma levels of 270.8 and 9.2 ng/mL, respectively. On the basis of its superior pharmacologic and safety profile, 4 (mavatrep) was selected for clinical development for the treatment of pain.