Diagnosing acute promyelocytic leukemia by using convolutional neural network.

PURPOSE: To evaluate the efficacy of diagnosis systems based upon instance segmentation with convolutional neural networks (CNNs) for diagnosing acute promyelocytic leukemia (APL) in bone marrow smear images. MATERIALS AND METHODS: A self-established dataset was used in this study that was exempted from review by the institution review board, which consisted of 13,504 bone marrow smear images. One subset of the dataset with 12,215 labeled images was split into training (80%) and validation (20%), another with 1289 labeled images was used to test, in which each test entry consists of about 130 images. An instance segmentation method named Mask R-CNN was used to detect and classify the nucleated cells. Here, we train a trained neural network from scratch; for comparison, we also use a network pre-trained on MS COCO (common objects in context, a data set provided by Microsoft which can be used for image recognition, the images in MS coco dataset are divided into training, validation and test sets) and fine-tuned with our dataset and both were trained with same data augmentation scheme. Diagnosis systems based on trained models and "FAB Classification" (French-American-British classification systems, a series of diagnostic criteria for acute leukemia, which was first proposed in 1976) were developed for diagnosing the test entry as APL or as not. Average precision (AP) and average recall (AR) were used to evaluate model performance. RESULTS: The best-performing model had an average precision of 62.5%, which was the augmented pre-trained Mask R-CNN with average recall 84.1%. The average precision of the pre-trained model was greater than that of the model trained from scratch (P < 0.05). Augmenting the dataset further increased accuracy (P < 0 0.03). CONCLUSION: Deep learning technology such as instance segmentation with Mask R-CNN may accurately diagnose APL in bone marrow smear images with an average precision of 62.5% when 0.5 as IoU thresholds. A data augmentation and pre-trained approach further improved accuracy.

Composition, distribution and risk of total fluorine, extractable organofluorine and perfluorinated compounds in Chinese teas.

To explore the residual characteristics of fluorine and perfluorinated compounds (PFCs) in tea, the total fluorine (TF), extractable organofluorine (EOF) and PFCs in 19 Chinese commercial teas of five categories were measured using cyclic neutron activation analysis combined with HPLC-MS/MS. The results showed that fluorine mainly existed as inorganic fluorine in teas, and identified fluorine (∑PFCs quantified as F) only accounted for 0.023-0.41% of EOF, indicating that most EOF in tea were still unknown. 50-99% of ∑PFCs in tea were short-chain (C⩽6), while perfluorooctanoic acid was the typical PFCs residual species. Less fermented teas contained significantly higher PFCs (mean, 20ng/g) than more fermented teas (3.0ng/g, p<0.01), suggesting that microbe may degrade PFCs during fermentation. The highest TF content was discovered in Hubei brick tea, which poses risk of fluorosis, whereas PFCs residues in teas caused no immediate harm.

Evolution of microbial community along with increasing solid concentration during high-solids anaerobic digestion of sewage sludge.

High-solids anaerobic digestion (HSAD), a promising method with smaller reactor and less heating energy consumption, showed relatively lower digestion efficiency sometimes and higher tolerance to some inhibitors. To investigate the phenomena, the archaeal and bacterial communities in four anaerobic digesters treating sewage sludge with total solids (TS) of 10-19% were investigated. Although acetoclastic methanogenesis conducted mainly by genus Methanosarcina was still the main pathway producing methane, the total ratio of acetoclastic methanogens decreased along with the increased TS. In contrary, the relative abundance of hydrogenotrophic methanogens increased from 6.8% at TS 10% to 22.3% at TS 19%, and methylotrophic methanogens from 10.4% to 20.9%. The bacterial community was dominated by five phyla. Acidogenic and acetogenic bacteria affiliated to Firmicutes decreased following the increase of TS; while the proteolysis phylum Bacteroidetes increased, with a tolerant family ST-12K33 notably existing in the digesters at TS 17% and 19%.

[Influence of tap water treatment on perfluorinated compounds residue in the dissolved phase].

To study the perfluorinated compounds (PFCs) residues through water treatments including flocculation, sedimentation, sand filtration, ozonation with activated carbon and chlorination, as well as the seasonal variation of PFCs in the raw water of waterworks, 13 PFCs species in the dissolved phase of raw water, finished water, as well as the water samples after flocculation, sedimentation, sand filtration, and ozonation with activated carbon filtration were measured by the high performance liquid chromatography-tandem mass spectrometry combined with solid phase extraction. Results indicated that sigma PFCs residue in water was higher in spring and summer than that in fall and winter. The vast majority of PFCs in samples were of short and medium chains (C < or = 10), and perfluorooctane sulfonate was the most typical residue species. Among the five water treatment stages, sedimentation, sand filtration and ozonation with activated carbon filtration can remove PFCs, while flocculation and chlorination significantly raise the levels of short- (C < or = 6) and medium-chain (10 > or = C > or = 7) PFCs, respectively, causing sigma PFCs increase in finished water by 10%-44% compared to raw water. However, the PFCs residues in finished water are still far below their limit values, posing no threat against human health.

[Residue characteristics and distributions of perfluorinated compounds in surface seawater along Shenzhen coastline].

In order to explore the residue characteristics and distributions of 15 perfluorinated compounds (PFCs) in 18 surface seawater samples along Shenzhen coastline, high performance liquid chromatography-tandem mass spectrometry (HPLC-MS/MS) combined with solid phase extraction enrichment was applied in this research. The results indicated that residue level of PFCs in coastal surface seawater samples was significantly affected by human activities. Sigma PFCs residue levels in surface seawater from Shenzhen west coast, which locates below the estuary of Pearl River and Donghao River, are much higher than those from the east coast, which has low development and sparse population (P<0.05). Under natural conditions, sigma PFCs residue levels in coastal surface seawater samples from Shenzhen Bays are higher than those out of bays. The major residue species in surface seawater samples along Shenzhen coast were medium- and short-chain PFCs, including perfluorooctane sulfonate (PFOS), perfluorooctanoic acid (PFOA), perfluorohexanoic acid and perfluoropentanoic acid. Their similar environmental behavior (P<0.05, P<0.01) is likely associated with the production process of PFCs-related products. Furthermore, cluster analysis results show that PFOS (R2 = 0.4092) level can be used as a representative parameter for evaluating PFCs contamination status in surface seawater along Shenzhen coast.

4-Methyl-N-[(2-oxo-1,3-thia-zolidin-3-yl)carbon-yl]benzene-sulfonamide.

The asymmetric unit of the title compound, C(11)H(12)N(2)O(4)S(2), contains two independent mol-ecules with similar dihedral angles of 76.7 (1) and 77.3 (1)° between the mean planes of the five- and six-membered rings. In both mol-ecules, the amino groups are involved in intra-molecular N-H⋯O hydrogen bonds. In the crystal structure, weak inter-molecular C-H⋯O hydrogen bonds link mol-ecules into ribbons extended along the a axis.

Research on the rheological properties of pesticide suspension concentrate.

This study reports research on pesticide suspension rheology and a new rheological parameter, the relative value of approach, which has great advantage for judging the physical stability of a pesticide suspension concentrate. Experiments showed that the system can form stable dispersions when the value of the relative value of approach (S(r)) is less than 0.1.