Deep learning-based prediction of mandibular growth trend in children with anterior crossbite using cephalometric radiographs.

BACKGROUND: It is difficult for orthodontists to accurately predict the growth trend of the mandible in children with anterior crossbite. This study aims to develop a deep learning model to automatically predict the mandibular growth result into normal or overdeveloped using cephalometric radiographs. METHODS: A deep convolutional neural network (CNN) model was constructed based on the algorithm ResNet50 and trained on the basis of 256 cephalometric radiographs. The prediction behavior of the model was tested on 40 cephalograms and visualized by equipped with Grad-CAM. The prediction performance of the CNN model was compared with that of three junior orthodontists. RESULTS: The deep-learning model showed a good prediction accuracy about 85%, much higher when compared with the 54.2% of the junior orthodontists. The sensitivity and specificity of the model was 0.95 and 0.75 respectively, higher than that of the junior orthodontists (0.62 and 0.47 respectively). The area under the curve value of the deep-learning model was 0.9775. Visual inspection showed that the model mainly focused on the characteristics of special regions including chin, lower edge of the mandible, incisor teeth, airway and condyle to conduct the prediction. CONCLUSIONS: The deep-learning CNN model could predict the growth trend of the mandible in anterior crossbite children with relatively high accuracy using cephalometric images. The deep learning model made the prediction decision mainly by identifying the characteristics of the regions of chin, lower edge of the mandible, incisor teeth area, airway and condyle in cephalometric images.

Comparison of the effects of rapid maxillary expansion versus Twin Block appliance on mandibular growth in skeletal Class II patients.

BACKGROUND: This is a retrospective study that compares mandibular growth changes in skeletal Class II patients treated by rapid maxillary expansion (RME) and following fixed appliance with those patients treated by Twin-Block (TB) and following fixed appliance. METHODS: Fourteen patients treated by RME and following fixed appliance were included into the RME group. Fifteen patients treated by Twin-Block and following fixed appliance were included into the TB group. Lateral cephalometric radiographs taken before treatment and immediately after fixed appliance treatment were used to evaluate mandibular growth effects. RESULTS: The starting forms of the patients in the two groups were examined to be of good comparability. The mandibular length increased significantly in both groups as measured by Co-Gn, Go-Gn and Ar-Gn, but the TB group didn't show more mandibular growth than the RME group (P > 0.05). Skeletal changes of the mandible in vertical dimension were different in the two groups. The change in FMA was 0.35° in the RME group, while the change was 2.65° in the TB group (P < 0.001). The change in LAFH was 5.14 mm in the RME group, significantly smaller than the change of 10.19 mm in the TB group (P < 0.001). CONCLUSION: The investigated Phase I treatment with RME followed by Phase II treatment of fixed appliance achieved the same increases in sagittal mandibular growth and facial profile improvements as the Twin-Block therapy. The treatment with RME followed by fixed appliance was better for vertical control, while the treatment with Twin-Block followed by fixed appliance significantly increased the mandibular plane angle.

A new natural hybrid of Iris (Iridaceae) from Chongqing, China.

A newly discovered natural hybrid, Iris×ampliflora Y.E. Xiao, F.Y. Yu & X.F. Chen (Iridaceae: subgenus LimnirissectionLophiris) from Chongqing, China, is described and illustrated. This hybrid is morphologically similar to I.japonica Thunb. and I.wattii Baker, but can be distinguished by its giant leaves and large purple flowers. Phylogenetic trees based on cpDNA data support the separation of I.×ampliflora from other closely related species in the section Lophiris. According to its morphological features, molecular systematic evidence and chromosome data, we speculate that I.×ampliflora [31 chromosomes] likely is a new hybrid between I.japonica [2n = 32] and I.wattii [2n = 30].

Bis(2-methyl-1H-imidazole-κN)silver(I) nitrate dihydrate.

The Ag(I) atom in the salt, [Ag(C(4)H(6)N(2))(2)]NO(3)·2H(2)O, shows a nearly linear coordination [N-Ag-N = 178.26 (7)°]. The cation, anion and water mol-ecules are linked by N-H⋯O and O-H⋯O hydrogen bonds into a layer motif extending parallel to (101).

Poly[aqua-bis(µ(4)-naphthalene-1,4-di-carboxyl-ato)(1,10-phenanthroline-5,6-dione)dimanganese(II)].

The three-dimensional coordination polymer, [Mn(2)(C(12)H(6)O(4))(2)(C(12)H(6)N(2)O(2))(H(2)O)](n), features a water-coord-inated Mn(II) ion and an N-heterocycle-chelated Mn(II) ion, both in six-coordinate octa-hedral geometries. Of the two rigid dianions, one is bonded to four Mn(II) ions, with each of the O atoms being connected to a different metal ion. The other dianion uses one carboxyl-ate group to chelate to one Mn(II) ion and its other carboxyl-ate group to bind to two Mn(II) ions.

catena-Poly[[(1,10-phenanthroline-5,6-dione-κN,N')lead(II)]-µ-terephthalato-κO:O].

The Pb(II) atom in the polymeric title compound, [Pb(C(8)H(4)O(4))(C(12)H(6)N(2)O(2))](n), is chelated by the N-heterocycle, and adjacent atoms are bridged by rigid terephthalate dianions into a linear chain. The Pb(II) atom is stereochemically active in a ψ-square-pyramidal coordination geometry in which the lone-pair electrons occupy a basal site. When three other weaker Pb⋯O inter-actions are considered, the geometry is a ψ-dodeca-hedron.