A Multi-Task Feature Fusion Model for Cervical Cell Classification.

Cervical cell classification is a crucial technique for automatic screening of cervical cancer. Although deep learning has greatly improved the accuracy of cell classification, the performance still cannot meet the needs of practical applications. To solve this problem, we propose a multi-task feature fusion model that consists of one auxiliary task of manual feature fitting and two main classification tasks. The auxiliary task enhances the main tasks in a manner of low-layer feature fusion. The main tasks, i.e., a 2-class classification task and a 5-class classification task, are learned together to realize their mutual reinforcement and alleviate the influence of unreliable labels. In addition, a label smoothing method based on cell category similarity is designed to bring inter-cell class information into the label. Comparative experimental results with other state-of-the-art models on the HUSTC and SIPaKMeD datasets prove the effectiveness of the proposed method. With a high sensitivity of 99.82% and a specificity of 98.12% for the 2-class classification task on the HUSTC dataset, our method shows potential to reduce cytologist workload.

Spatiotemporal dynamics of different growth-diffusion systems on a percolation lattice.

To investigate the proliferation and invasion of a tumor within an inhomogeneous matrix, we studied the spatiotemporal dynamics of two types of growth-diffusion systems (GDSs) with logistic or Allee growth occurring on a two-dimensional square site percolation lattice via numerical computation and finite-size scaling approaches. A critical percolation threshold exists in the two systems, but becomes obscure with an increasing Allee effect in Allee growth. The two systems evidently differ in their short-time spatiotemporal patterns: The tumor number density in the logistic model grows and spreads continuously and subdiffusively or weakly superdiffusively while that in the Allee model does so discretely and strongly superdiffusively. This difference is attributed to a lack of cooperation between sites for growth and diffusion in the logistic model as compared to its Allee counterpart. The Allee growth pattern is characterized by a rougher border and more inhomogeneous interior than its logistic counterpart. Judging from their growth-diffusion feature in combination with a clinical image analysis, we conclude that Allee growth is more suitable for modeling the proliferation and invasion of an early-stage malignant tumor than is logistic growth. A phase diagram that correlates a tumor's growth and diffusion on a percolation lattice with a site occupation fraction and Allee effect was established to reveal the sensitivity on proliferation and spreading of a tumor towards the above parameters. The Allee effect was also found to induce diverse dynamic features on its short-time growth and diffusion in the GDS, which brings in an opposite trend toward a tumor's growth and diffusion.

The value of detailed MR imaging report of primary tumor and lymph nodes on prognostic nomograms for nasopharyngeal carcinoma after intensity-modulated radiotherapy.

PURPOSE: To establish effective prognostic nomograms using clinical features and detailed magnetic resonance imaging (MRI) findings for primary tumor and regional lymph nodes after intensity-modulated radiotherapy (IMRT) in patients with nasopharyngeal carcinoma. METHOD: The nomogram for overall survival (OS) was based on a retrospective study of 595 patients who underwent IMRT at Sun Yat-sen University Cancer Center from 2010 to 2012. The predictive accuracy and discriminative ability of our nomogram models were determined by concordance index and calibration curve, and were compared with the nomogram models combining clinical features with tumor-node-metastasis (TNM) classification. The results were validated using bootstrap resampling and a cohort study of 241 patients. The same data cohort was used to predict the progress-free survival (PFS) of nasopharyngeal carcinoma with 3:1 training cohort (N = 558) and validation cohort (N = 278). RESULTS: The following factors were assembled into our prognostic survival nomogram models: Age, Epstein-Barr virus DNA copy number before treatment (EBV_DNA_CN), tensor veli palatini (TVP) involvement, musculus pterygoideus lateralis (MPL) involvement, prestyloid space (PS) involvement, prevertebral space (PVS) involvement, base of sphenoid bone (BOSB) involvement, paranasal sinus (PNS) involvement, the laterality of Ⅱ (Ⅱ_laterality), the laterality of retropharyngeal lymph node (RPLN_laterality), nodal grouping (NG), extranodal neoplastic spread (ENS), contrast-enhancing rim (CER) and Nodal_number. The calibration curves showed good agreement between nomogram-predicted and actual survival. Our nomogram models for OS and PFS, provided better results than the nomogram models combining clinical features with TNM classification. Results were further confirmed in the validation set. CONCLUSION: Detailed MRI findings of primary tumor and regional lymph nodes can improve the performance of prognostic nomograms for patients with nasopharyngeal carcinoma.