An EEG-Based Transfer Learning Method for Cross-Subject Fatigue Mental State Prediction.

Fatigued driving is one of the main causes of traffic accidents. The electroencephalogram (EEG)-based mental state analysis method is an effective and objective way of detecting fatigue. However, as EEG shows significant differences across subjects, effectively "transfering" the EEG analysis model of the existing subjects to the EEG signals of other subjects is still a challenge. Domain-Adversarial Neural Network (DANN) has excellent performance in transfer learning, especially in the fields of document analysis and image recognition, but has not been applied directly in EEG-based cross-subject fatigue detection. In this paper, we present a DANN-based model, Generative-DANN (GDANN), which combines Generative Adversarial Networks (GAN) to enhance the ability by addressing the issue of different distribution of EEG across subjects. The comparative results show that in the analysis of cross-subject tasks, GDANN has a higher average accuracy of 91.63% in fatigue detection across subjects than those of traditional classification models, which is expected to have much broader application prospects in practical brain-computer interaction (BCI).

InstanceEasyTL: An Improved Transfer-Learning Method for EEG-Based Cross-Subject Fatigue Detection.

Electroencephalogram (EEG) is an effective indicator for the detection of driver fatigue. Due to the significant differences in EEG signals across subjects, and difficulty in collecting sufficient EEG samples for analysis during driving, detecting fatigue across subjects through using EEG signals remains a challenge. EasyTL is a kind of transfer-learning model, which has demonstrated better performance in the field of image recognition, but not yet been applied in cross-subject EEG-based applications. In this paper, we propose an improved EasyTL-based classifier, the InstanceEasyTL, to perform EEG-based analysis for cross-subject fatigue mental-state detection. Experimental results show that InstanceEasyTL not only requires less EEG data, but also obtains better performance in accuracy and robustness than EasyTL, as well as existing machine-learning models such as Support Vector Machine (SVM), Transfer Component Analysis (TCA), Geodesic Flow Kernel (GFK), and Domain-adversarial Neural Networks (DANN), etc.

Co-regulatory Network of Oncosuppressor miRNAs and Transcription Factors for Pathology of Human Hepatic Cancer Stem Cells (HCSC).

Hepatic cancer stem cells (HCSCs) are considered as main players for the hepatocellular carcinoma (HCC) initiation, metastasis, drug resistance and recurrence. There is a growing evidence supporting the down-regulated miRNAs in HCSCs as key suppressors for the stemness traits, but still more details are vague about how these miRNAs modulate the HCC development. To uncover some of these miRNA regulatory aspects in HCSC, we compiled 15 down-regulated miRNA and their validated and predicted up-regulated targets in HCSC. The targets were enriched for several cancer cell stemness hallmarks and CSC pre-metastatic niche, which support these miRNAs role in suppression of HCSCs neoplastic transformation. Further, we constructed miRNA-Transcription factor (TF) regulatory networks, which provided new insights on the role of the proposed miRNA-TF co-regulation in the cancer stemness axis and its cross talk with the surrounding microenvironment. Our analysis revealed HCSC important hubs as candidate regulators for targeting hepatic cancer stemness such as, miR-148a, miR-214, E2F family, MYC and SLC7A5. Finally, we proposed a possible model for miRNA and TF co-regulation of HCSC signaling pathways. Our study identified an HCSC signature and set bridges between the reported results to give guide for future validation of HCC therapeutic strategies avoiding drug resistance.

Gamma Knife Management of Skull Base Chordomas: Is it a Choice?

BACKGROUND: Skull base chordomas are locally invasive tumors which able to extend in different directions with skull base invasion. Although they are histologically benign, they have invasive nature makes total resection virtually impossible to achieve in most cases and this lead to residual tumors after surgery. To decrease postoperative surgical resection morbidity of these tumors, gamma knife radiosurgery (GKRS) was performed as alternative management for these residual chordomas to evaluate its safety and efficacy. MATERIALS AND METHODS: A retrospective study was made on eight residual skull base chordomas treated with GKRS between 2011 and 2015. The mean patient age was 49 years (range 30-73 years). Four patients harboring chordoma were male, and four patients were females with 1:1 ratio. All patients had undergone one prior surgery. Patients were treated with peripheral dose ranged between 12-15 gray (Gy) (mean 13.75 Gy) usually at 35% to 50% isodose curve (mean 38.8%). The maximum dose to the adjacent brain stem area ranged between 10 and 12 Gy. All patients were followed up from 8 to 39 months (mean 18 months). RESULTS: The tumor control rate was 50% and 25% after 18 and 36 months, respectively, but we found that their wasdeclined in the tumor control rate with long follow-up time. Four tumors were stable in their size just for 18 months, and then there two of these tumors were progressed in their size, the other four patients showed progression in their tumors in their 1st year of treatment without sign of central tumor necrosis. CONCLUSION: Skull base chordoma patients complained from symptoms due to tumor mass effect which were not prospected to respond to GKRS alone as the aim of this type of treatment was the local tumor control, the tumor control rate declined with long follow-up time and this correlated with radioresistant nature of skull base chordoma. We advise a gross total resection to decrease the tumor volume, and this making gamma knife a reasonable treatment modality.

Outcome of Early versus Delayed Evacuation of Spontaneous Lobar Hematomas in Unconscious Adults.

OBJECTIVE: To explore the difference in outcomes of medium-sized lobar hematomas evacuated in early versus delayed fashion among unconscious noncomatose individuals. METHODS: A retrospective analysis of demographic, clinical, and radiological data of unconscious patients admitted with lobar hematomas during 18 years was performed. Time to surgery was compared in various patient variables and characteristics. Outcome groups (favorable and poor) were also compared to find out any association with surgery timing, as well as potential indicators of outcome and mortality. RESULTS: The mean follow-up period in this study was 7.5 months after discharge. Two-thirds of the patients carried favorable prognosis at final follow-up with mortality (7.3%) included among poor cases. Time to surgery was not associated to any of the patient characteristics, except for international normalized ratio and associated chest problems which represented the main indicators of delayed surgery. Rebleeding after evacuation was associated with shorter time to surgery in clots ≤35 cc but not in the whole group. Poor outcome was significantly associated with higher basal glucose levels, bigger hematomas, rebleeding after surgery, and delayed evacuation of clots >35 cc. The presence of mild intraventricular hemorrhage (IVH) per se was not associated with increased mortality or poor outcome; however, its volume was. CONCLUSION: Smaller lobar hematomas (≤35 cc) in unconscious adults (Glasgow Coma Scale 8-13) may be managed with initial conservative treatment, while larger hematomas (>35 cc) are better evacuated as early as possible. Basal glucose levels and volume of mild IVH should be considered in the future management planes.

PMCR-Miner: parallel maximal confident association rules miner algorithm for microarray data set.

The MCR-Miner algorithm is aimed to mine all maximal high confident association rules form the microarray up/down-expressed genes data set. This paper introduces two new algorithms: IMCR-Miner and PMCR-Miner. The IMCR-Miner algorithm is an extension of the MCR-Miner algorithm with some improvements. These improvements implement a novel way to store the samples of each gene into a list of unsigned integers in order to benefit using the bitwise operations. In addition, the IMCR-Miner algorithm overcomes the drawbacks faced by the MCR-Miner algorithm by setting some restrictions to ignore repeated comparisons. The PMCR-Miner algorithm is a parallel version of the new proposed IMCR-Miner algorithm. The PMCR-Miner algorithm is based on shared-memory systems and task parallelism, where no time is needed in the process of sharing and combining data between processors. The experimental results on real microarray data sets show that the PMCR-Miner algorithm is more efficient and scalable than the counterparts.

Anaplastic thyroid carcinoma arising in long-standing multinodular goiter following radioactive iodine therapy: report of a case diagnosed by fine needle aspiration.

BACKGROUND: Anaplastic thyroid carcinoma (ATC) is a highly aggressive, undifferentiated carcinoma that may arise on top of normal or abnormal thyroid. Making the diagnosis by fine needle aspiration (FNA) of the thyroid with a long-standing history of multinodular goiter (MNG) is not uncommon. We report a case discussing the cytopathologic findings and the relationship with long-standing goiter and thyroid exposure to radioactive iodine treatment. CASE: A 90-year-old male patient presented with a > 45-year history of MNG that was associated with thyrotoxicosis and multiple courses of radioiodine (I-131) treatment. He developed recent symptoms of dyspnea, dysphagia, neck welling and uniintentional weight loss. Computed tomography of the neck was done revealing a large MNG with retrosternal extension and calcifications. FNA was performed revealing highly anaplastic cells with a colloid background and presence of neutrophils. The diagnosis of ATC was made. The patient refused any kind of management and was discharged upon his request. He died 2 days after the procedure, and no autopsy was performed. CONCLUSION: ATC is an aggressive, undifferentiated thyroid carcinoma that can be diagnosed by FNA and save the patient a surgical intervention. A background of MNG and history of radioactive iodine therapy is not uncommon.