A deep learning model for drug screening and evaluation in bladder cancer organoids.

Three-dimensional cell tissue culture, which produces biological structures termed organoids, has rapidly promoted the progress of biological research, including basic research, drug discovery, and regenerative medicine. However, due to the lack of algorithms and software, analysis of organoid growth is labor intensive and time-consuming. Currently it requires individual measurements using software such as ImageJ, leading to low screening efficiency when used for a high throughput screen. To solve this problem, we developed a bladder cancer organoid culture system, generated microscopic images, and developed a novel automatic image segmentation model, AU2Net (Attention and Cross U2Net). Using a dataset of two hundred images from growing organoids (day1 to day 7) and organoids with or without drug treatment, our model applies deep learning technology for image segmentation. To further improve the accuracy of model prediction, a variety of methods are integrated to improve the model's specificity, including adding Grouping Cross Merge (GCM) modules at the model's jump joints to strengthen the model's feature information. After feature information acquisition, a residual attentional gate (RAG) is added to suppress unnecessary feature propagation and improve the precision of organoids segmentation by establishing rich context-dependent models for local features. Experimental results show that each optimization scheme can significantly improve model performance. The sensitivity, specificity, and F1-Score of the ACU2Net model reached 94.81%, 88.50%, and 91.54% respectively, which exceed those of U-Net, Attention U-Net, and other available network models. Together, this novel ACU2Net model can provide more accurate segmentation results from organoid images and can improve the efficiency of drug screening evaluation using organoids.

Oncocytic Carcinoma in the Retromolar Trigone: A Case Report.

Oncocytic carcinoma (OC) is a pretty rare malignant neoplasm. Oncocytic carcinomas mainly occur in major salivary glands but infrequently occur in minor salivary glands. We report a case of OC occurring in the retromolar glands involving the ipsilateral tonsil, which has not been reported in the English literature. This case may expand the database of OC, and provide diagnosis and treatment ideas for clinicians.

A novel deep learning segmentation model for organoid-based drug screening.

Organoids are self-organized three-dimensional in vitro cell cultures derived from stem cells. They can recapitulate organ development, tissue regeneration, and disease progression and, hence, have broad applications in drug discovery. However, the lack of effective graphic algorithms for organoid growth analysis has slowed the development of organoid-based drug screening. In this study, we take advantage of a bladder cancer organoid system and develop a deep learning model, the res-double dynamic conv attention U-Net (RDAU-Net) model, to improve the efficiency and accuracy of organoid-based drug screenings. In this RDAU-Net model, the dynamic convolution and attention modules are integrated. The feature-extracting capability of the encoder and the utilization of multi-scale information are substantially enhanced, and the semantic gap caused by skip connections has been filled, which substantially improved its anti-interference ability. A total of 200 images of bladder cancer organoids on culture days 1, 3, 5, and 7, with or without drug treatment, were employed for training and testing. Compared with the other variations of the U-Net model, the segmentation indicators, such as Intersection over Union and dice similarity coefficient, in the RDAU-Net model have been improved. In addition, this algorithm effectively prevented false identification and missing identification, while maintaining a smooth edge contour of segmentation results. In summary, we proposed a novel method based on a deep learning model which could significantly improve the efficiency and accuracy of high-throughput drug screening and evaluation using organoids.

Primary observation of the role of posttranslational modification of dentin sialophosphoprotein (DSPP) on postnatal development of mandibular condyle in mice.

OBJECTIVES: We aimed to observe the posttranslational role of dentin sialophosphoprotein (DSPP) on postnatal development of mandibular condyle in mice. METHODS: To explore the function of full-length DSPP, four groups of mice were employed: (1) wild type (WT) mice; (2)Dspp knockout (Dspp KO) mice; (3) mice expressing the normal DSPP transgene in the Dspp KO background (Dspp KO/normal Tg); (4) mice expressing the uncleavable full-length DSPP in the Dspp KO background (Dspp KO/D452A Tg). Firstly, Plain X-ray Radiography and Micro-computed Tomography were used to observe the condylar morphology changes of Dspp KO/D452A Tg mice in comparison with the other three groups. Then, Hematoxylin & eosin and toluidine blue staining were applied to uncover the histological changes of mandibular condylar cartilage (MCC) of Dspp KO/D452A Tg mice. To explore the function of the NH2-terminal fragments (i.e. DSP/DSP-PG), three groups of mice were employed: (1) WT mice; (2) Dspp KO mice; (3) mice expressing the NH2-terminal fragments of DSPP in the Dspp-null background (Dspp KO/DSP Tg). The former strategies were utilized to examine the differences of condylar morphology and histological structures changes within three groups of mice. RESULTS: Transgenic full-length DSPP partially maintained mandibular condylar morphology and MCC thickness of Dspp KO mice. Transgenic DSP failed to do so, but led to smaller mandibular condyle and disordered cartilage structure. CONCLUSIONS: Our observations provide insight into the role of posttranslational modification of DSPP in the postnatal development of healthy MCC and maintenance of condylar morphology.

Haploinsufficiency of Dspp Gene Causes Dentin Dysplasia Type II in Mice.

Dentin dysplasia (DD) and dentinogenesis imperfecta (DGI) patients have abnormal structure, morphology, and function of dentin. DD-II, DGI-II, and DGI-III are caused by heterozygous mutations in the dentin sialophosphoprotein (DSPP) gene in humans. Evidences have shown that loss of function of DSPP in Dspp knockout mice leads to phenotypes similar to DGI-III, and that the abnormal dentinogenesis is associated with decreased levels of DSPP, indicating that DSPP haploinsufficiency may play a role in dentinogenesis. Thus, to testify the haploinsufficiency of Dspp, we used a Dspp heterozygous mouse model to observe the phenotypes in the teeth and the surrounding tissues. We found that Dspp heterozygous mice displayed dentin phenotypes similar to DD-II at the ages of 12 and 18 months, which was characterized by excessive attrition of the enamel at the occlusal surfaces, thicker floor dentin of the pulp chamber, decreased pulp volume, and compromised mineralization of the dentin. In addition, the periodontium was also affected, exhibiting apical proliferation of the junctional epithelium, decreased height and width of the alveolar bone, and infiltration of the inflammatory cells, leading to the destruction of the periodontium. Both the dental and periodontal phenotypes were age-dependent, which were more severe at 18 months old than those at 12 months old. Our report is the first to claim the haploinsufficiency of Dspp gene and a DD-II mouse model, which can be further used to study the molecular mechanisms of DD-II.