Appendiceal tumor incidence and an in-depth look at appendiceal neuroendocrine neoplasm in a cohort of 8,162 appendectomies: Full dataset

AbstractPrimary ovarian neuroendocrine neoplasms (Ov-NENs) are infrequent and mainly represented by well-differentiated forms (neuroendocrine tumors — NETs — or carcinoids). Poorly differentiated neuroendocrine carcinomas (Ov-NECs) are exceedingly rare and only few cases have been reported in the literature. A subset of Ov-NECs are admixed with non-neuroendocrine carcinomas, as it occurs in other female genital organs, as well (mostly endometrium and uterine cervix), and may be assimilated to mixed neuroendocrine/non-neuroendocrine neoplasms (MiNENs) described in digestive and extra-digestive sites. Here, we present a case of large cell Ov-NEC admixed with an endometrioid carcinoma of the ovary, arising in the context of ovarian endometriosis, associated with a uterine endometrial atypical hyperplasia (EAH). We performed targeted next-generation sequencing analysis, along with a comprehensive immunohistochemical study and FISH analysis for TP53 locus, separately on the four morphologically distinct lesions (Ov-NEC, endometrioid carcinoma, endometriosis, and EAH). The results of our study identified molecular alterations of cancer-related genes (PIK3CA, CTNNB1, TP53, RB1, ARID1A, and p16), which were present with an increasing gradient from preneoplastic lesions to malignant proliferations, both neuroendocrine and non-neuroendocrine components. In conclusion, our findings underscored that the two neoplastic components of this Ov-MiNEN share a substantially identical molecular profile and they progress from a preexisting ovarian endometriotic lesion, in a patient with a coexisting preneoplastic proliferation of the endometrium, genotypically and phenotypically related to the ovarian neoplasm. Moreover, this study supports the inclusion of MiNEN in the spectrum ovarian and, possibly, of all gynecological NENs, among which they are currently not classified.

Download Full-text

Improving Semi-Supervised Learning for Audio Classification with FixMatch

Electronics ◽

10.3390/electronics10151807 ◽

2021 ◽

Vol 10 (15) ◽

pp. 1807

Author(s):

Sascha Grollmisch ◽

Estefanía Cano

Keyword(s):

Neural Networks ◽

Supervised Learning ◽

Transfer Learning ◽

Data Transfer ◽

State Of The Art ◽

Training Data ◽

Audio Classification ◽

Image Domain ◽

Full Dataset ◽

Audio Data

Including unlabeled data in the training process of neural networks using Semi-Supervised Learning (SSL) has shown impressive results in the image domain, where state-of-the-art results were obtained with only a fraction of the labeled data. The commonality between recent SSL methods is that they strongly rely on the augmentation of unannotated data. This is vastly unexplored for audio data. In this work, SSL using the state-of-the-art FixMatch approach is evaluated on three audio classification tasks, including music, industrial sounds, and acoustic scenes. The performance of FixMatch is compared to Convolutional Neural Networks (CNN) trained from scratch, Transfer Learning, and SSL using the Mean Teacher approach. Additionally, a simple yet effective approach for selecting suitable augmentation methods for FixMatch is introduced. FixMatch with the proposed modifications always outperformed Mean Teacher and the CNNs trained from scratch. For the industrial sounds and music datasets, the CNN baseline performance using the full dataset was reached with less than 5% of the initial training data, demonstrating the potential of recent SSL methods for audio data. Transfer Learning outperformed FixMatch only for the most challenging dataset from acoustic scene classification, showing that there is still room for improvement.

Download Full-text