Multi-View Stereo Vision Patchmatch Algorithm Based on Data Augmentation.

In this paper, a multi-view stereo vision patchmatch algorithm based on data augmentation is proposed. Compared to other works, this algorithm can reduce runtime and save computational memory through efficient cascading of modules; therefore, it can process higher-resolution images. Compared with algorithms utilizing 3D cost volume regularization, this algorithm can be applied on resource-constrained platforms. This paper applies the data augmentation module to an end-to-end multi-scale patchmatch algorithm and adopts adaptive evaluation propagation, avoiding the substantial memory resource consumption characterizing traditional region matching algorithms. Extensive experiments on the DTU and Tanks and Temples datasets show that our algorithm is very competitive in completeness, speed and memory.

Unsupervised domain adaptive tumor region recognition for Ki67 automated assisted quantification.

PURPOSE: Ki67 is a protein associated with tumor proliferation and metastasis in breast cancer and acts as an essential prognostic factor. Clinical work requires recognizing tumor regions on Ki67-stained whole-slide images (WSIs) before quantitation. Deep learning has the potential to provide assistance but largely relies on massive annotations and consumes a huge amount of time and energy. Hence, a novel tumor region recognition approach is proposed for more precise Ki67 quantification. METHODS: An unsupervised domain adaptive method is proposed, which combines adversarial and self-training. The model trained on labeled hematoxylin and eosin (H&E) data and unlabeled Ki67 data can recognize tumor regions in Ki67 WSIs. Based on the UDA method, a Ki67 automated assisted quantification system is developed, which contains foreground segmentation, tumor region recognition, cell counting, and WSI-level score calculation. RESULTS: The proposed UDA method achieves high performance in tumor region recognition and Ki67 quantification. The AUC reached 0.9915, 0.9352, and 0.9689 on the validation set and internal and external test sets, respectively, substantially exceeding baseline (0.9334, 0.9167, 0.9408) and rivaling the fully supervised method (0.9950, 0.9284, 0.9652). The evaluation of automated quantification on 148 WSIs illustrated statistical agreement with pathological reports. CONCLUSION: The model trained by the proposed method is capable of accurately recognizing Ki67 tumor regions. The proposed UDA method can be readily extended to other types of immunohistochemical staining images. The results of automated assisted quantification are accurate and interpretable to provide assistance to both junior and senior pathologists in their interpretation.

Learning policy scheduling for text augmentation.

When training deep learning models, data augmentation is an important technique to improve the performance and alleviate overfitting. In natural language processing (NLP), existing augmentation methods often use fixed strategies. However, it might be preferred to use different augmentation policies in different stage of training, and different datasets may require different augmentation policies. In this paper, we take dynamic policy scheduling into consideration. We design a search space over augmentation policies by integrating several common augmentation operations. Then, we adopt a population based training method to search the best augmentation schedule. We conduct extensive experiments on five text classification and two machine translation tasks. The results show that the optimized dynamic augmentation schedules achieve significant improvements against previous methods.

Are Surgeons Working Smarter or Harder? A Systematic Review Comparing the Physical and Mental Demands of Robotic and Laparoscopic or Open Surgery.

BACKGROUND: Minimally invasive surgical techniques such as robotic surgical platforms have provided favourable outcomes for patients, but the impact on surgeons is not well described. This systematic review aims to synthesize and evaluate the physical and mental impact of robotic surgery on surgeons compared to standard laparoscopic or open surgery. METHODS: A search strategy was developed to identify peer-reviewed English articles published from inception to end of December 2019 on the following databases: MEDLINE, PubMed, PsycINFO and Embase. The articles were assessed using a modified Newcastle-Ottawa tool. RESULTS: Of the 6563 papers identified, 30 studies were included in the qualitative synthesis of this review. Most of the included studies presented a high risk of bias. A total of 13 and 21 different physical and mental tools, respectively, were used to examine the impact on surgeons. The most common tool used to measure physical and mental demand were surface electromyography (N = 9) and the NASA Task Load Index (NASA-TLX; N = 8), respectively. Majority of studies showed mixed results for physical (N = 10) and mental impact (N = 7). This was followed by eight and six studies favouring RS over other surgical modalities for physical and mental impact, respectively. CONCLUSION: Most studies showed mixed physical and mental outcomes between the three surgical modalities. There was a high risk of bias and methodological heterogeneity. Future studies need to correlate mental and physical stress with long-term impact on the surgeons.

MiR-210 expression reverses radioresistance of stem-like cells of oesophageal squamous cell carcinoma.

AIM: To investigate the expression of miR-210 and the role it plays in the cell cycle to regulate radioresistance in oesophageal squamous cell carcinoma (ESCC). METHODS: MiR-210 expression was evaluated in 37 pairs of ESCC tissues and matched para-tumorous normal oesophageal tissues from surgical patients who had not received neoadjuvant therapy, and in the cells of two novel radioresistant cell lines, TE-1R and Eca-109R, using quantitative reverse transcription-polymerase chain reaction (qRT-PCR). The transient up-regulation of miR-210 expression in TE-1R and Eca-109R cells was studied using liposomes and was confirmed using qRT-PCR. The rate of cell survival after a series of radio-treatment doses was evaluated using the clone formation assay. Flow cytometry was used to detect the changes to the cell cycle patterns due to radiation treatment. RT-PCR and Western blot were used to detect the expression of ataxia telangiectasia mutated (ATM) and DNA dependent protein kinase (DNA-PKcs) after irradiation, and the cell sphere formation assay was used to evaluate the proliferative ability of the cancer stem-like cells. RESULTS: The level of miR-210 expression was significantly decreased, by 21.3% to 97.2%, with the average being 39.2% ± 16.1%, in the ESCC tissues of most patients (81.1%, 30 of 37 vs patients with high miR-210 expression, P < 0.05). A low level of expression of miR-210 was correlated with a poorly differentiated pathological type (P < 0.01) but was not correlated with the T-stage or lymph node infiltration (both P > 0.05). Early local recurrences (< 18 mo, n = 19) after radiotherapy were significantly related with low miR-210 expression (n = 13, P < 0.05). The level of miR-210 was decreased by approximately 73% (vs TE-1, 0.27 ± 0.10, P < 0.01) in the established radioresistant TE-IR cell line and by 52% (vs Eca-109, 0.48 ± 0.17, P < 0.05) in the corresponding Eca-109R line. Transient transfection with a miR-210 precursor increased the level of miR-210 expression, leading to a significant increase in cell survival after radiotherapy (P < 0.05). Twenty-four hours after radiation, the proportion of pmiR-210 cells in S phase was increased (vs control cells, 30.4% ± 0.4%, and vs untreated TE-1R cells, 23.3% ± 0.7%, P < 0.05 for both). The levels of DNA-PKcs (0.21 ± 0.07) and ATM (0.12 ± 0.03, P < 0.05) proteins were significantly lower in the PmiR-210 cells than in control cells, but no differences were found in the levels of the corresponding mRNAs in the two cell types (P > 0.05 for all). Exogenous miR-210 expression decreased the diameter of pmiR-210 cell spheres (vs control cells, 0.60 ± 0.14, P < 0.05). CONCLUSION: MiR-210 expression is negatively correlated with the pathological type and the local survival rate after radiotherapy, and high expression of miR-210 may reverse the radioresistance of ESCC stem-like cells.