Deep learning-based diagnosis of feline hypertrophic cardiomyopathy.

Feline hypertrophic cardiomyopathy (HCM) is a common heart disease affecting 10-15% of all cats. Cats with HCM exhibit breathing difficulties, lethargy, and heart murmur; furthermore, feline HCM can also result in sudden death. Among various methods and indices, radiography and ultrasound are the gold standards in the diagnosis of feline HCM. However, only 75% accuracy has been achieved using radiography alone. Therefore, we trained five residual architectures (ResNet50V2, ResNet152, InceptionResNetV2, MobileNetV2, and Xception) using 231 ventrodorsal radiographic images of cats (143 HCM and 88 normal) and investigated the optimal architecture for diagnosing feline HCM through radiography. To ensure the generalizability of the data, the x-ray images were obtained from 5 independent institutions. In addition, 42 images were used in the test. The test data were divided into two; 22 radiographic images were used in prediction analysis and 20 radiographic images of cats were used in the evaluation of the peeking phenomenon and the voting strategy. As a result, all models showed > 90% accuracy; Resnet50V2: 95.45%; Resnet152: 95.45; InceptionResNetV2: 95.45%; MobileNetV2: 95.45% and Xception: 95.45. In addition, two voting strategies were applied to the five CNN models; softmax and majority voting. As a result, the softmax voting strategy achieved 95% accuracy in combined test data. Our findings demonstrate that an automated deep-learning system using a residual architecture can assist veterinary radiologists in screening HCM.

Chiral environment of catalytic sites in the chiral metal-organic frameworks.

Chiral metal-organic frameworks are considered a useful platform in heterogeneous catalysis for enantioselective chemical transformations. However, it has been observed that the enantioselectivity is sensitive to the site at which the reaction takes place, even in a single crystal, since the chiral environment of the catalytic site varies according to its location, e.g., that of the surface is anisotropic, whereas that of the interior is isotropic.

Assessing the guest-accessible volume in MOFs using two-photon fluorescence microscopy.

The assessment of guest-accessible volume in MOFs can be reliably done by using two-photon confocal fluorescence microscopy (TPM) with a tool-box of dyes with a wide range of sizes. It would be applicable to any porous materials, whose single-crystal structures are not available, or non-crystalline materials.

Homochiral 3D metal-organic frameworks from chiral 1D rods: 6-way helical packing.

The chiral 3D MOFs resulted from the packing of chiral 1D SBBs were studied. It was demonstrated that the final packing pattern is sensitively dependent on the dimension of SBBs. In addition, we were able to identify a new plywood-like network from ligand 2H(2) exhibiting an unprecedented six-way chiral helical packing motif, which extends the list of invariant rod packings.