A rare case of highly differentiated follicular carcinoma in ovary with FGFR4 Gly388Arg polymorphism: a case report and literature review.

BACKGROUND: Highly differentiated follicular carcinoma (HDFCO) is a rare form of struma-derived thyroid-type carcinoma in ovary, defined as ovarian struma spreading beyond ovary but consisting of benign thyroid tissues. No more than 30 cases of HDFCO have been reported since it was first recognized in 2008. The clinicopathologic and molecular features of HDFCO remain unclear up till now. CASE PRESENTATION: A 38-year-old, para 1 gravida 5 woman has a long history of recurrent right ovarian cysts. Histological evaluation showed the tumor progressed from ovarian mature cystic teratoma (OMCT) to highly differentiated follicular carcinoma (HDFCO) during three relapses. Whole-exome sequencing revealed the germline FGFR4 Gly388Arg polymorphism. Repeated operations were performed to remove lesions for the first two relapses. On the third recurrence, the patient received radical surgery with subsequent thyroidectomy and radioactive iodine ablation. No evidence of disease was observed by February 2022 (8 months). CONCLUSIONS: The germline FGFR4 Gly388Arg polymorphism may accelerate the malignant transformation of HDFCO, probably by working as a second hit in the developing spectrum.

Tensor-Factorized Neural Networks.

The growing interests in multiway data analysis and deep learning have drawn tensor factorization (TF) and neural network (NN) as the crucial topics. Conventionally, the NN model is estimated from a set of one-way observations. Such a vectorized NN is not generalized for learning the representation from multiway observations. The classification performance using vectorized NN is constrained, because the temporal or spatial information in neighboring ways is disregarded. More parameters are required to learn the complicated data structure. This paper presents a new tensor-factorized NN (TFNN), which tightly integrates TF and NN for multiway feature extraction and classification under a unified discriminative objective. This TFNN is seen as a generalized NN, where the affine transformation in an NN is replaced by the multilinear and multiway factorization for tensor-based NN. The multiway information is preserved through layerwise factorization. Tucker decomposition and nonlinear activation are performed in each hidden layer. The tensor-factorized error backpropagation is developed to train TFNN with the limited parameter size and computation time. This TFNN can be further extended to realize the convolutional TFNN (CTFNN) by looking at small subtensors through the factorized convolution. Experiments on real-world classification tasks demonstrate that TFNN and CTFNN attain substantial improvement when compared with an NN and a convolutional NN, respectively.