Figure 1.
T2WI and T1WI MRI slices at the same location in a patient with PAS.
Citation: Pontsho Patricia Twala, Alfred Mitema, Cindy Baburam, Naser Aliye Feto. Breakthroughs in the discovery and use of different peroxidase isoforms of microbial origin[J]. AIMS Microbiology, 2020, 6(3): 330-349. doi: 10.3934/microbiol.2020020
| [1] | Nosheen Malik, Muhammad Shabir, Tareq M. Al-shami, Rizwan Gul, Abdelwaheb Mhemdi . Medical decision-making techniques based on bipolar soft information. AIMS Mathematics, 2023, 8(8): 18185-18205. doi: 10.3934/math.2023924 |
| [2] | Khulud Fahad Bin Muhaya, Kholood Mohammad Alsager . Extending neutrosophic set theory: Cubic bipolar neutrosophic soft sets for decision making. AIMS Mathematics, 2024, 9(10): 27739-27769. doi: 10.3934/math.20241347 |
| [3] | Dhuha Saleh Aldhuhayyan, Kholood Mohammad Alsager . Multi-criteria evaluation of tree species for afforestation in arid regions using a hybrid cubic bipolar fuzzy soft rough set framework. AIMS Mathematics, 2025, 10(5): 11813-11841. doi: 10.3934/math.2025534 |
| [4] | Tahir Mahmood, Azam, Ubaid ur Rehman, Jabbar Ahmmad . Prioritization and selection of operating system by employing geometric aggregation operators based on Aczel-Alsina t-norm and t-conorm in the environment of bipolar complex fuzzy set. AIMS Mathematics, 2023, 8(10): 25220-25248. doi: 10.3934/math.20231286 |
| [5] | Waheed Ahmad Khan, Abdul Rehman, Abdelghani Taouti . Soft near-semirings. AIMS Mathematics, 2020, 5(6): 6464-6478. doi: 10.3934/math.2020417 |
| [6] | Rizwan Gul, Muhammad Shabir, Tareq M. Al-shami, M. Hosny . A Comprehensive study on (α,β)-multi-granulation bipolar fuzzy rough sets under bipolar fuzzy preference relation. AIMS Mathematics, 2023, 8(11): 25888-25921. doi: 10.3934/math.20231320 |
| [7] | Tahir Mahmood, Ubaid Ur Rehman, Muhammad Naeem . A novel approach towards Heronian mean operators in multiple attribute decision making under the environment of bipolar complex fuzzy information. AIMS Mathematics, 2023, 8(1): 1848-1870. doi: 10.3934/math.2023095 |
| [8] | Remala Mounikalakshmi, Tamma Eswarlal, Chiranjibe Jana . Bipolar fuzzy INK-subalgebras of INK-algebras. AIMS Mathematics, 2024, 9(10): 27593-27606. doi: 10.3934/math.20241340 |
| [9] | Erdal Karapınar, Marija Cvetković . An inevitable note on bipolar metric spaces. AIMS Mathematics, 2024, 9(2): 3320-3331. doi: 10.3934/math.2024162 |
| [10] | Saqib Mazher Qurashi, Ferdous Tawfiq, Qin Xin, Rani Sumaira Kanwal, Khushboo Zahra Gilani . Different characterization of soft substructures in quantale modules dependent on soft relations and their approximations. AIMS Mathematics, 2023, 8(5): 11684-11708. doi: 10.3934/math.2023592 |
Placenta accrete spectrum (PAS) disorder is defined as the abnormal invasion of trophoblast cells into the myometrium at different depths of infiltration. It occurs mainly in patients with placenta previa or previous cesarean section [1]. Common complications of PAS include catastrophic perinatal hemorrhage and injury of bladder, rectal and urethral [2]. There are many high-risk factors for PAS, including the history of cesarean section, placenta previa, multiple miscarriages and curettage, history of other uterine-related surgeries such as myomectomy, and advanced maternal age [3,4]. With the increase of various risk factors such as cesarean section and abortion, the incidence of PAS is also increasing year by year [5,6,7,8]. China is a country with a relatively high cesarean section rate [9]. With the implementation of the three-child policy, the number of late marriages and childbearing has increased. It can be speculated that the incidence of PAS in China will further rise. Therefore, the prenatal prediction of PAS is of important practical significance.
The traditional detection methods of PAS based on MRI generally include three consecutive steps: region of interest segmentation, image feature extraction and PAS detection [10]. A recent study showed that experienced radiologists performed significantly better than junior radiologists (90.9% of sensitivity and 75% of specificity for senior attending physicians, 81.8% of sensitivity and 61.8% of specificity for primary attending physicians) [11]. In order to reduce the reliance on the clinical experience of doctors and improve the diagnostic level of PAS, some scoring systems for the diagnosis of placental invasion have been proposed in recent years, which have not been widely tested [12]. Some scholars [13,14] used machine learning methods to detect PAS based on radiomics features and clinical factors (such as whether it was a scarred uterus, whether there was a history of cesarean section, and whether there was a history of miscarriage, etc.). There are also a few studies [15] using deep neural networks to learn powerful visual representations in MR images to predict PAS, but detection of PAS based on MRI is still a challenging task, there are several problems:
(1) Radiomics features are explicitly designed or handcrafted. Although the number of features can reach tens of thousands, these features are shallow and low-level image features. The heterogeneity within the placenta and the relationship between the placenta and adjacent tissues may not be fully characterized, thus limiting the predictive potential of the model.
(2) In clinical practice, doctors usually diagnose PAS based on the placental signal reflected by T2WI MR images supplemented by the bleeding conditions reflected by T1WI MR images. Traditional MR image analysis methods are difficult to extract multiple sequences of MR image features at the same time and assign corresponding weights to predict PAS according to their significance. Figure 1 shows T2WI and T1WI MRI slices of a patient with PAS at the same location.
Among them, Figure 1(a) is a sagittal view of T2WI, which shows PAS in the posterior and lower part of placenta (white arrow), and a strip of low signal on T2WI (red arrow) is seen in the placenta; Figure 1(b) is a sagittal view of T1WI, and a mass of hyperintense hemorrhage is seen in the placenta (white arrow).
In order to solve the above problems, we proposed a dual-path neural network fused with a multi-head attention module, which includes a dual-path neural network and a multi-head attention module. Dual-path neural network can extract T2WI and T1WI MR image features. Specifically, the presence of low-intensity bands or small patches in the placenta on T2WI sequences may indicate PAS; Intraplacental hemorrhage is usually seen in the placenta of T1WI MR images with patchy slightly high signal intensity, which may also suggest PAS. The multi-head attention module assigns different weights to the features of different sequences through learning and fuses them to better measure the importance of different sequence features.
The main contributions of this paper are: (1) A dual-path neural network is designed to extract the features of T2WI and T1WI sequences of MR images; (2) A multi-head attention module is proposed to learn the weights of different features to generate final features with stronger discrimination. Experimental results on an independent validation dataset show that the detection accuracy achieved by our method is superior to the methods using only a single sequence of MR images. The comparative experimental results also show the effectiveness of the multi-head attention module proposed in this paper.
In this section, we discuss the work most related to our work: detection of PAS based on MRI. MRI is less affected by intestinal gas and bones, has high tissue resolution and can be imaged at any angle in multiple directions, so it is especially recommended for cases with unclear posterior placenta and ultrasound results and/or high clinical suspicion [16,17,18]. In practice, MR images can provide important information for doctors to predict and diagnose the type of PAS. Recently, there have been many studies with promising performance. These algorithms typically use hand-designed or measured features to detect PAS. For example, Zheng et al. [19] used the observed imaging features on MR images to diagnose PAS, such as whether it is placenta previa, whether the placenta is thickened, etc. However, manually designing and measuring features is time-consuming and labor-intensive. To overcome this difficulty, several radiomics or deep learning-based methods have been proposed to automatically extract MRI features. For example, Romeo et al. [13] used a machine learning algorithm to predict the types of PAS based on radiomics features. Li et al. [15] used an auto-encoding network to extract features of MR images to predict the types of PAS. However, most of the current studies are based on a single sequence of MRI for the detection of PAS. In clinical practice, doctors usually diagnose PAS based on the placental signal reflected by T2WI MR images supplemented by the bleeding conditions reflected by T1WI MR images. Therefore, we propose a dual-path neural network fused with a multi-head attention module to detect PAS. The model first uses a dual-path neural network to extract T2WI and T1WI MR image features separately, and then combines these features. The multi-head attention module learns multiple different attention weights to focus on different aspects of the placental image to generate discriminative final features.
This retrospective study was approved by the Ethics Committee of The Affiliated Hospital of Medical College of Ningbo University, and all patients' identities were de-identified to protect patient privacy. The MR images were collected from The Affiliated Hospital of Medical College of Ningbo University and Ningbo Women & Children's Hospital from January 2018 to May 2021.
All MRI examinations were performed by radiologists with more than 5-year of work experience using 1.5 Tesla units to perform 8 or 16-channel array sensitivity-coded abdominal coil scans. The imaging equipment of The Affliated Hospital of Medical College of Ningbo University is Ge signa twinspeed 1.5T superconducting dual gradient magnetic resonance scanner with 8-channel body phased array coil. The imaging equipment of Ningbo Women & Children's Hospital is Philips Achieva Noval Dual 1.5T superconducting dual gradient magnetic resonance scanner, using a 16-channel body phased array coil. In this study, we chose the supine sagittal image of the conventional T2WI and T1WI sequence (side-lying imaging is prone to curling artifacts due to the bulge of the abdomen) as the experimental sequence.
Inclusion criteria are as follows: (1) Patients who underwent T2WI and T1WI MRI after 30 weeks of gestation; (2) Those with clear placenta invasion or pathological records after cesarean section; (3) Image quality is good. The exclusion criteria are as follows: (1) Patients without T2WI or T1WI MRI data; (2) Patients with mismatched number of T2WI and T1WI MRI slices; (3) Patients without clinical or surgical pathological confirmation; (4) Patients with severe image artifact.
Based on the above criteria, we collected a total of 321 cases, including 142 normal cases and 179 cases of PAS (including accrete, increta and percreta). The degree of invasion in all patients was determined based on surgical findings, intraoperative diagnosis and pathological examinations. Table 1 is the distribution table of our dataset.
| Normal | Accrete | Increta | Percreta | |
| Jan., 2018~Dec., 2019 | 86 | 17 | 114 | 8 |
| Jan., 2020~May, 2021 | 56 | 14 | 22 | 4 |
| Total | 142 | 31 | 136 | 12 |
DownLoad:
CSV
In order to extract the features of dual-sequence MR images, we designed a dual-path neural network to extract T2WI and T1WI MR image features. The dual-path neural network consists of two independent backbone networks, and finally combines the features extracted from the two backbone networks. Taking ResNet-50 as the backbone network as an example [20], the structure of the dual-path neural network is shown in Figure 2.
As shown in Figure 2, the dual-path neural network consists of two independent backbone networks. The backbone network ResNet-50 includes 5 convolution blocks. The last layer of each convolution block outputs a feature map of a specific scale as the input of next convolution block, and the size of the feature map output by the previous convolution block is 1/2 of the size of the feature map output by the next convolution block. The final output of each backbone network is a 128-dimensional feature vector, and the outputs of the two backbone networks are spliced as the extracted combined features.
We obtained the combined features that fused the two sequences of MR images by the dual-path neural network. To assign different weights to different features and perform further fusion, we proposed a multi-head attention module. The output of the attention module usually focuses on a specific part of the image, such as: intraplacental heterogeneity information in T2WI MR images or hemorrhage information in T1WI MR images. A single attention unit can usually only reflect one aspect of an image. However, it may be more effective to have multiple attention units focus on different features in different sequences of images and to describe the images of the entire case together as the MRI data contains multiple sequences. Therefore, to be able to represent multiple aspects of an image, multiple attention units are needed to focus on different aspects of the image. Multiple attention units focus on the same input, but the parameters between multiple units are independent of each other.
Based on the above ideas, this paper proposed a multi-head attention module, which learns multiple sets of parameters to focus on different aspects of the final feature as shown in Figure 3.
Specifically, multiple sets of paired scalars are learned. The first scalar scales the global features linearly, and the second scalar acts as a bias to introduce nonlinear factors. The above process can be expressed as:
| Vi=ωi∗T+bi | (1) |
where ωi and bi represent the scalar parameter pair learned by the ith attention unit. After obtaining the feature Vi output by the attention unit, L2 regularization is performed on it, and the features obtained by all units are spliced together, and after nonlinear transformation, it is used as the output of the multi-head attention module. The process can be expressed as:
| V=Relu(V1⊕V2⊕⋯⊕VN) | (2) |
where V represents the final feature, ⊕ represents the splicing operation, and the nonlinear transformation uses the Relu activation function. In subsequent experimental sections, we will compare the detection accuracy of attention module networks with different head counts.
The dataset we collected included 142 normal cases and 179 cases of PAS (31 accrete, 136 increta and 12 percreta). The number of T2WI and T1WI sequence slices in each case is equal, including 24–48 slices. Both sequences scan the same part of the patient, so the slices of the two sequences can be in one-to-one correspondence. We excluded 5 slices from the head and tail of the two sequences in each case because there was no uterine area in these slices. To expand the dataset, we treat each T2WI image and its corresponding T1WI image as a slice group [21,22].
Background information occupies a large proportion in MR images and has a large impact on subsequent feature extraction and classification [23,24]. We crop the center region of the image, and the cropped size is 256 × 256. We randomly split the dataset into a training set and an independent validation set in a 4:1 ratio. Table 2 is the data set split table.
| Class | Train | Validation |
| Normal | 1886 | 472 |
| PAS | 2451 | 613 |
DownLoad:
CSV
All models are implemented in PyTorch. Batch normalization [25] is used for all models. All networks are trained using one RTX 2080Ti GPU with 50 training epochs for the dual-path neural network and the multi-head attention module. We used the Adam Optimizer with a small learning rate 10−4. In addition, the two backbone networks in the dual-path neural network are separately trained on T2WI and T1WI sequence image data respectively. Based on the trained model, the features are extracted and spliced to obtain the combined features which are used for the training of the multi-head attention module.
Evaluate the performance of classification methods using a confusion matrix. The true positive (TP), true negative (TN), false positive (FP) and false negative (FN) values are obtained from the confusion matrix to calculate four performance evaluation metrics as follows:
| Accuracy=TN+TPTN+TP+FN+FP | (3) |
| Precision=TPTP+FP | (4) |
| Recall=TPTP+FN | (5) |
| F1score=2×Precision×RecallPrecision+Recall | (6) |
Among them, accuracy represents the percentage of samples that exactly match the real situation; precision is the proportion of true positives in samples predicted as positive examples; Recall is the proportion of true positives in true positive examples; F1-score is the harmonic mean of precision and recall. In order to avoid dividing by 0 in the calculation process, when TP is 0, the F1 score is recorded as 0.
In order to prove that the features of dual-sequence MR images are effective for the detection of PAS, we use three machine learning methods to compare the detection accuracy of the three features on an independent validation set. The three machine learning methods are: decision tree (DT), random forest (RF), and support vector machine (SVM); the three features are: features extracted from T2WI MR images, features extracted from T1WI MR images, and combined features obtained by splicing the above two features. Table 3 shows the comparison results.
| Methods | Features | Accuracy | F1 score |
| Decision Tree | T2WI features | 0.857 | 0.870 |
| T1WI features | 0.681 | 0.715 | |
| Combined features | 0.854 | 0.868 | |
| Random Forest | T2WI features | 0.864 | 0.876 |
| T1WI features | 0.709 | 0.733 | |
| Combined features | 0.862 | 0.874 | |
| Support Vector Machine | T2WI features | 0.862 | 0.875 |
| T1WI features | 0.700 | 0.737 | |
| Combined features | 0.869 | 0.882 |
DownLoad:
CSV
It can be seen in Table 3 that the method using SVM achieves the highest accuracy and F1 score on combined features, which are 0.869 and 0.882 respectively, which are higher than the accuracy of the same method on T2WI features and T1WI features. Based on DT and RF, the accuracy and F1 score of T2WI features and combined features are almost equal, and the accuracy and F1 score of T1WI features are lower than those of the above two features. In summary, simply splicing the features of the two sequences can improve the detection accuracy of PAS, but the effect is not obvious. Based on the SVM method, we used T2WI features and combined features to draw receiver operating characteristic (ROC) curves and performed the significance test (DeLong's Test) of the area under the ROC curves (AUC). The experimental results are shown in Table 4.
| T2WI features ~ Combined features | |
| Difference between areas | 0.0236 |
| Standard Error | 0.00362 |
| 95% Confidence Interval | 0.0165 to 0.0307 |
| z statistic | 6.519 |
| Significance level | P < 0.0001 |
DownLoad:
CSV
As can be seen from Table 4, the P-value is less than 0.0001, which indicates that there is a significant difference between the AUCs of the two kinds of features. To further improve model performance, we design a multi-head attention module to pay attention to different features in different sequences of MR images. The multi-head attention module can assign their respective weights according to their importance to improve the detection accuracy.
In order to compare the detection accuracy of attention modules with different numbers of heads in the detection of PAS, we calculated the detection accuracy and F1 score of attention modules with different numbers of heads on the independent validation set. Table 5 shows the comparison results. The case where the number of attention heads is 0 means that the attention mechanism is not used. It only uses one Relu layer and fully connected layers (the output dimension of the fully connected layer is 2, which means normal or invasion respectively) to detect PAS.
| The number of heads | Accuracy | F1 score |
| 0 | 0.857 | 0.873 |
| 2 | 0.859 | 0.874 |
| 4 | 0.874 | 0.888 |
| 8 | 0.886 | 0.899 |
| 16 | 0.861 | 0.876 |
DownLoad:
CSV
As can be seen from Table 5, the detection accuracy and F1 score of using the attention module are improved compared with those without the attention module. The highest accuracy and F1 score were achieved with 8 attention heads, 0.886 and 0.899 respectively. When the number of heads is less than 8, the fitting ability of the model is insufficient due to insufficient parameters. When the number of heads is greater than 8, because the model has too many parameters and the size of the training set is not large, the model is over-fitted, and the accuracy rate decreases to a certain extent. Therefore, an attention module with 8 heads is used in the experiment. To further compare the model performance with and without the attention module, we plot the ROC curves. Figure 4 shows the ROC curves with and without the 8-head attention module.
As shown in Figure 4, the performance of the model with the 8-head attention module is significantly higher than that of the model without the attention module. To compare the performance of the two models more intuitively, we calculated the AUC. The results are shown in Table 6.
| Methods | AUC |
| Attention module not used | 0.930 |
| Eight attention heads module | 0.940 |
DownLoad:
CSV
In order to objectively evaluate the performance of the model and eliminate the impact of data leakage on the experimental results, we select 40 samples that do not appear in the training set from the validation set to form a new test set (20 for normal, 20 for PAS), and verify the performance of the proposed model with 8-head attention module from the accuracy and F1 score. The experimental results show that the model can also achieve ideal results on the test set, reaching an accuracy of 0.825 and an F1 score of 0.837.
This paper proposed a method to detect PAS by extracting and fusing dual sequence placental MR image features using a dual-path neural network. The proposed model mainly includes a dual-path neural network and a multi-head attention module. The dual-path neural network is used to extract the features of the two sequences of MR images and perform feature fusion; the multi-head attention module learns the corresponding weights for different features in different sequences to generate more discriminative final features. Experimental results on an independent validation set demonstrate the effectiveness of each module in our method, with clear advantages over methods that only use a single sequence of MR images. This method may assist physicians in clinical diagnosis, help physicians make perinatal planning and improve maternal outcomes.
This work was supported by the Key Talents of Ningbo City Health Technology under Grant 2020SWSQNGG-06 and Zhejiang Province Medicine and Health Project under Grant 2022KY1149.
The authors declare that there are no conflicts of interest.
| [1] |
Karigar CS, Rao SS (2011) Role of microbial enzymes in the bioremediation of pollutants: A review. Enzyme Res 2011: 805187. doi: 10.4061/2011/805187
|
| [2] | Chandrasekaran M, Kumar SR (2010) Marine microbial enzymes. Biotechnology 9: 1-15. |
| [3] | Opwis K, Kiehl K, Gutmann JS (2016) Immobilization of peroxidases on textile carrier materials and thier use in bleaching processes. Chem Eng Trans 49: 67-72. |
| [4] |
Casciello C, Tonin F, Berini F, et al. (2017) A valuable peroxidase activity from the novel species Nonomuraea gerenzanensis growing on alkali lignin. Biotechnol Rep 13: 49-57. doi: 10.1016/j.btre.2016.12.005
|
| [5] |
Madhu A, Chakraborty JN (2017) Developments in application of enzymes for textile processing. J Cleaner Prod 145: 114-133. doi: 10.1016/j.jclepro.2017.01.013
|
| [6] |
Bansal N, Kanwar SS (2013) Peroxidase(s) in environment protection. Sci World J 2013: 714639. doi: 10.1155/2013/714639
|
| [7] |
Choi J, Detry N, Kim KT, et al. (2014) fPoxDB: fungal peroxidase database for comparative genomics. BMC Microbiol 14: 117. doi: 10.1186/1471-2180-14-117
|
| [8] |
Colpa DI, Fraaije MW, Bloois EV (2014) DyP-type peroxidase: a promising versatile class of enzymes. J Ind Microbiol Biotechnol 41: 1-7. doi: 10.1007/s10295-013-1371-6
|
| [9] |
Kolhe P, Ingle S, Wagh N (2015) Degradation of phenol containing wastewater by advance catalysis system–a review. Annu Res Rev Biol 8: 1-15. doi: 10.9734/ARRB/2015/19936
|
| [10] |
Lončar N, Colpa DI, Fraaije MW (2016) Exploring the biocatalytic potential of a DyP-type peroxidase by profiling the substrate acceptance of Thermobifida fusca DyP peroxidase. Tetrahedrom 72: 7276-7281. doi: 10.1016/j.tet.2015.12.078
|
| [11] |
Pandey VP, Bhagat PK, Prajapati R, et al. (2016) A defense associated peroxidase from lemon having dye decolorizing ability and offering resistance to heat, heavy metals and organic solvents. Biochem Anal Biochem 5: 291. doi: 10.4172/2161-1009.1000291
|
| [12] |
Passardi F, Theiler G, Zamocky M, et al. (2007) PeroxiBase: the peroxidase database. Phytochemistry 68: 1605-1611. doi: 10.1016/j.phytochem.2007.04.005
|
| [13] | Rajkumar R, Yaakob Z, Takriff MS, et al. (2013) Optimization of medium composition for the production of peroxidase by Bacillus sp. Der Pharma Chemica 5: 167-174. |
| [14] |
Zhang Z, Lai J, Wu K, et al. (2018) Peroxidase-catalyzed chemiluminescence system and its application in immunoassay. Talanta 180: 260-270. doi: 10.1016/j.talanta.2017.12.024
|
| [15] | Patil SR (2014) Production and purification of lignin peroxidase from Bacillus megaterium and its application in bioremediation. CIBTech J Microbiol 3: 22-28. |
| [16] |
Adewale IO, Adekunle AT (2018) Biochemical properties of peroxidase from white and red cultivars of Kola nut (Cola nitida). Biocatal Agric Biotechnol 14: 1-9. doi: 10.1016/j.bcab.2018.01.013
|
| [17] |
Cesarino I, Araujo P, Sampaio Mayer JL, et al. (2012) Enzymatic activity and proteomic profile of class III peroxidases during sugarcane stem development. Plant Physiol Biochem 55: 66-76. doi: 10.1016/j.plaphy.2012.03.014
|
| [18] |
Li J, Liu C, Li B (2015) Identification and molecular characterization of a novel DyP-type peroxidase from Pseudomonas aeruginosa PKE117. Appl Biochem Biotechnol 166: 774-85. doi: 10.1007/s12010-011-9466-x
|
| [19] | Ganesh P, Dineshraj D, Yoganathan K (2017) Production and screening of depolymerising enymes by potential bacteria and fungi isolated from plastic waste dump yard sites. Int J Appl Res 3: 693-695. |
| [20] |
Khelil O, Choubane S, Cheba BA (2015) Co-production of cellulases and manganese peroxidases by Bacillus sp. R2 and Bacillus Cereus 11778 on waste newspaper: application in dyes decolourization. Procedia Technol 19: 980-987. doi: 10.1016/j.protcy.2015.02.140
|
| [21] |
Pandey VP, Awasthi M, Singh S, et al. (2017) A comprehensive review on function and application of plant peroxidases. Biochem Anal Biochem 6: 1. doi: 10.4172/2161-1009.1000308
|
| [22] |
Pathak VM, Navneet (2017) Review on the current status of polymer degradation: a microbial approach. Bioresources Bioprocessing 4: 15. doi: 10.1186/s40643-017-0145-9
|
| [23] |
Wei R, Zimmermann W (2017) Microbial enzymes for the recycling of recalcitrant petroleum-based plastics: how far are we? Microb Biotechnol 10: 1308-1322. doi: 10.1111/1751-7915.12710
|
| [24] |
Zahmatkesh M, Spanjers H, van Lier JB, et al. (2017) Fungal treatment of humic-rich industrial wastewater: application of white rot fungi in remediation of food-processing wastewater. Environ Technol 38: 2752-2762. doi: 10.1080/09593330.2016.1276969
|
| [25] |
Xie X, Chen M, Aiyi Z (2017) Identification and characterization of two selenium-dependent glutathione proxidase 1 isoforms from Larimichthys crocea. Fish Shellfish Immunol 71: 411-422. doi: 10.1016/j.fsi.2017.09.067
|
| [26] |
Yoshida T, Sugano Y (2015) A structural and functional perspective of DyP-type peroxidase family. Arch Biochem Biophys 574: 49-55. doi: 10.1016/j.abb.2015.01.022
|
| [27] |
Datta R, Kelkar A, Baraniya D, et al. (2017) Enzymatic degradation of lignin in soil: a review. Sustainability 9: 1163. doi: 10.3390/su9071163
|
| [28] |
Min K, Gong G, Woo H, et al. (2015) A dye-decolorizing peroxidase from Bacillus subtilis exhibiting subtrate-dependent optimum temperature for dyes and beta-ether lignin dimer. Sci Rep 5: 8245. doi: 10.1038/srep08245
|
| [29] | Bholay AD, Borkhataria BV, Jadhav PU, et al. (2012) Bacterial lignin peroxidase: a tool for biobleaching and biodegradation of industrial effluents. Universal J Environ Res Technol 2: 58-64. |
| [30] | Guisado G, Lopez MJ, Vargas-Garcia MC, et al. (2012) Pseudallescheria angusta, A lingninolytic microorganisms for wood fibres biomodification. Bioresources 7: 464-474. |
| [31] | Niladevi KN (2009) Lignolytic enzymes. Biotechnol Agro-Ind Residues Util 4: 397-414. |
| [32] |
Osuji AC, Osayi EE, Eze SOO, et al. (2014) Biobleaching of industrial important dyes with peroxidase partially purified from garlic. Scientific World J 2014: 183163. doi: 10.1155/2014/183163
|
| [33] |
Baysal O, Yildiz A (2017) Bacillus subtilis: An industrially important microbe for enzyme production. EC Microbiol 5: 148-156. doi: 10.1186/s40168-017-0368-1
|
| [34] |
Dragana R, Nikola G, Željko D, et al. (2017) Separation of peroxidases from Miscanthus x giganteus, their partial characterisation and application for degradation of dyes. Plant Physiol Biochem 120: 179-185. doi: 10.1016/j.plaphy.2017.10.009
|
| [35] |
Chanwun T, Muhamad N, Chirapongsatonkul N, et al. (2013) Hecea brasiliensis cell suspension peroxidase: purification, chracterization and application for dye decolorization. AMB Express 3: 14. doi: 10.1186/2191-0855-3-14
|
| [36] |
van Bloois E, Torres Pazmino DE, Winter RT, et al. (2010) A robust and extracellular heme-containing peroxidase from Thermobifida fusca as prototype of a bacterial peroxidase superfamily. Appl Microbiol Biotechnol 86: 1419-1430. doi: 10.1007/s00253-009-2369-x
|
| [37] |
Shigeto J, Tsutsumi Y (2016) Diverse functions and reactions of class III peroxidases. New Phytol 209: 1395-1402. doi: 10.1111/nph.13738
|
| [38] |
Veitch NC (2004) Horseradish peroxidase: a modern view of a classic enzyme. Phytochemistry 65: 249-259. doi: 10.1016/j.phytochem.2003.10.022
|
| [39] |
Petrić M, Subotić A, Jevremović S, et al. (2015) Esterase and peroxidase isoforms in different stages of morphogenesis in Fritillaria meleagris L. in bulb-scale culture. Comptes Rendus Biologies 338: 793-802. doi: 10.1016/j.crvi.2015.08.002
|
| [40] |
Racz A, Hideg E, Czegeny G (2018) Selective responses of class III plant peroxidase isoforms to environmentally relevant UV-B doses. J Plant Physiol 221: 101-106. doi: 10.1016/j.jplph.2017.12.010
|
| [41] | Kanwar SS, Bansal N (2014) Decolorization of industrial dyes by an extracellular peroxidase from Bacillus sp. F31. JAM 1: 252-265. |
| [42] | Gholami-Borujeni F, Mahvi AH, Naseri S, et al. (2011) Application of immobilized horseradish peroxidase for removal and detoxification of azo dye from aqueous solution. Res J Chem Environ 15: 217-221. |
| [43] |
Shafi J, Tian H, Ji M (2017) Bacillus species as versatile weapons for plant pathogens a review. Biotechnol Biotechnol Equipment 31: 446-459. doi: 10.1080/13102818.2017.1286950
|
| [44] |
Matamoros MA, Saiz A, Penuelas M, et al. (2015) Function of glutathion peroxidase in legume root nodules. J Exp Bot 66: 2979-2990. doi: 10.1093/jxb/erv066
|
| [45] |
Silva MC, Torres JA, Corrêa AD, et al. (2012) Obtention of plant peroxidase and its potential for the decolorization of the reactive dye Remazol Turquoise G133%. Water Sci Technol 65: 669-675. doi: 10.2166/wst.2012.892
|
| [46] | Singh R, Kumar M, Mittal A, et al. (2016) Microbial enzymes: industrial progress in 21st century. Biotechnology 6: 174. |
| [47] |
Ruiz-Dueñas F, Fernández E, Martínez MJ, et al. (2011) Pleurotus ostreatus heme peroxidases: An in silico analysis from the genome sequence to the enzyme molecular strucuture. C R Biol 334: 795-805. doi: 10.1016/j.crvi.2011.06.004
|
| [48] | Malomo SO, Adeoye RL, Babatunde L, et al. (2011) Suicide inactivation of horseradish peroxidase by excess hydrogen peroxide: the effects of reaction pH, buffer ion concentration, and redoz mediation. Biokemistri 23: 124-128. |
| [49] |
Falade A, Mabinya L, Okoh A, et al. (2019) Studies on peroxidase productin and detection of Sporotrichum thermophile-like catalase-peroxidase gene in a Bacillus species isolated from Hogsback forest reserve, South Africa. Heliyon 5: e03012. doi: 10.1016/j.heliyon.2019.e03012
|
| [50] | Simo C, Djocgoue PF, Minyaka E, et al. (2018) Guaicol proxidase heritability in tolerance of cocoa (Theobroma cacao L.) to Phytophthora megakarya, agent of cocoa black pod disease. Int J Agric Policy Res 6: 7-20. |
| [51] |
Shahin SA, Jonathan S, Lary DJ, et al. (2017) Phytophthora megakarya and Phytophthora palmivora, closely related casual agents of cacao balsk pod rot, underwent increases in genome sizes and gene numbers by differnt mechanisms. Genome Biol Evol 9: 536-557. doi: 10.1093/gbe/evx021
|
| [52] | Shahin SA, Jonathan S, Lary DJ, et al. (2017) Phytothora megakarya and P. palmivora, casual agents of black pod rot, induce similar plant defense responses late during infection of susceptible cacoa pods. Fontiers Plant Sci 18: 1-18. |
| [53] |
Falade A, Mabinya L, Okoh A, et al. (2018) Peroxidases produced by new ligninolytic Bacillus strains isolated form marsh and grassland decolourized anthraquinone and azo dyes. Pol J Environ Stud 28: 3163-3172. doi: 10.15244/pjoes/92520
|
| [54] |
Husain Q (2010) Peroxidase mediated decolorizatio and remediation of wastewar containing industrial dyes: a review. Rev Environ Sci Biotechnol 9: 117-140. doi: 10.1007/s11157-009-9184-9
|
| [55] |
Karn SK, Fang G, Duan J (2017) Bacillus sp. acting as dual role for corrosion induction and corrosion inhibition with carbon steel (CS). Front Microbiol 8: 2038. doi: 10.3389/fmicb.2017.02038
|
| [56] |
Nayanashree G, Thippeswamy B (2015) Natural rubber degradation by laccase and manganese peroxidase enzymes of Penicillium chrysogenum. Int J Environ Sci Technol 12: 2665-2672. doi: 10.1007/s13762-014-0636-6
|
| [57] | Nayanashree G, Thippeswamy B, Krishnappa M., et al. (2014) Enzymatic studies on Natural rubber biodegradation by Bacillus pumilus. Int J Biological Res 2: 44-47. |
| [58] | Gopi V, Upgade A, Soundararajan N (2012) Bioremediation potential of individual and consortium Non-adapted fungal strains on Azo dye containing textile effluent. Adv Appl Sci Res 3: 303-311. |
| [59] |
Ong ST, Keng PS, Lee WN, et al. (2011) Dye waste treatment. Water 3: 157-176. doi: 10.3390/w3010157
|
| [60] | Ratanapongleka K, Phetsom J (2014) Decolorization of synthetic dyes by crude laccase from Lentinus polychrous Lev. Int J Chem Eng Appli 5: 26-30. |
| [61] |
Bikovens O, Dizhbite T, Telysheva G (2012) Characterisation of humin substances formed during co-compositing of grass and wood wastes with animal grease. Environ Technol 33: 1427-1433. doi: 10.1080/09593330.2011.632652
|
| [62] |
Grinhut T, Hadar Y, Chen Y (2007) Degradation and transformation of humic substances by saprotrophic fungi: processes and mechanisms. Fungal Biol Rev 21: 179-189. doi: 10.1016/j.fbr.2007.09.003
|
| [63] | Mojsov K (2011) Application of enzymes in the textile industry: a review. II International Congress "engineering 230–239. |
| [64] | Gomathi VC, Ramanathan B, Sivaramaiah N, et al. (2012) Decolourization of paper mill effluent by immobilized cells of Phanerochaete chrysosporium. Int J Plant Anim Environ Sci 2: 141-146. |
| [65] |
Jadhav UP, Bholay AD, Shindikar M, et al. (2016) Bacterial lignin peroxidase mediated biobleaching and biodegradation of paper and pulp mill effluent. IOSR J Environ Sci Toxicol Food Technol 10: 31-36. doi: 10.9790/2402-1009023136
|
| [66] |
Andrady AL (2011) Microplastics in the marine environment. Mar Pollut Bull 62: 1596-1605. doi: 10.1016/j.marpolbul.2011.05.030
|
| [67] | Sowmya HV, Ramalingappa, Krishnappa M, et al. (2014) Biodegradation of polyethylene by Bacillus cereus. Adv Polymer Sci Technol Int J 4: 28-32. |
| [68] |
Wilkes RA, Aristilde L (2017) Degradation and metabolism of synthetic plastics and associated products by Pseudomonas sp.: capabilities and challenges. J Appl Microbiol 123: 582-593. doi: 10.1111/jam.13472
|
| [69] |
Roohi, Kulsoom B, Mohammed K, et al. (2017) Microbial enzymatic degradation of biodegradable plastics. Curr Pharm Biotechnol 18. doi: 10.2174/1389201018666170523165742
|
| [70] | Sharma M, Sharma P, Sharma A, et al. (2015) Microbial degradation of plastic-a brief review. CIBTech J Microbiol 4: 85-89. |
| [71] | Sowmya HV, Ramlingappa B, Krishnappa M, et al. (2014) Low density polyethylene degrading fungi isolated from local dumpsite of shivamogga district. Int J Biol Res 2: 39-43. |
| [72] |
Sowmya HV, Ramalingappa, Krishnappa M, et al. (2014) Degradation of polyethylene by Trichoderma harzianum--SEM, FTIR, and NMR analyses. Environ Monit Assess 186: 6577-6586. doi: 10.1007/s10661-014-3875-6
|
| [73] | Khatoon N, Jamal A, Ali MI (2018) Lignin peroxidase isoenzyme: a novel approach to biodegrade the toxic synthetic polymer waste. Environ Technol 40: 1-10. |
| [74] | Sowmya HV, Ramalingappa B, Nayanashree G, et al. (2015) Polyethylene degradation by fungal consortium. Int J Environ Sci Technol 9: 823-830. |
| [75] |
Krueger M, Harms H, Schlosser D (2015) Prospects for microbiological solution to environmental pollution with plastics. Appl Microbiol Biotechnol 99: 8857-8574. doi: 10.1007/s00253-015-6879-4
|
| [76] |
Dang T, Nguyen D, Thai H, et al. (2018) Plastic degradation by thermophilic Bacillus sp. BCBT21 isolated from composting agricultural residual in Vietnam. Adv Nat Sci Nanosci Nanotechnol 9: 015014. doi: 10.1088/2043-6254/aaabaf
|
| [77] | Gore S, Khotha A, Nevgi D, et al. (2017) The use of horse radish peroxidase, an eco-friendly method for removal of phenol from industrial effluent. J Environ Sci Toxicol Food Technol 11: 7-13. |
| [78] |
Shekoohiya S, Moussavi G, Naddafi K (2016) The peroxidase-mediated biodegradation of petroleum hydrocarbons in a H2O2-induced SBR using in-situ production of peroxidase: Biodegradation experiments and bacterial identification. J Hazard Mater 313: 170-178. doi: 10.1016/j.jhazmat.2016.03.081
|
| 1. | Baravan A. Asaad, Sagvan Y. Musa, A novel class of bipolar soft separation axioms concerning crisp points, 2023, 56, 2391-4661, 10.1515/dema-2022-0189 | |
| 2. | Sagvan Y. Musa, Baravan A. Asaad, Carmelo Antonio Finocchiaro, Topological Structures via Bipolar Hypersoft Sets, 2022, 2022, 2314-4785, 1, 10.1155/2022/2896053 | |
| 3. | Çiğdem GÜNDÜZ, Can METİN, BIPOLAR SOFT CONTINUITY ON BIPOLAR SOFT TOPOLOGICAL SPACES, 2023, 5, 2667-7660, 11, 10.47087/mjm.1314428 | |
| 4. | Hind Y. Saleh, Baravan A. Asaad, Ramadhan A. Mohammed, Novel Classes of Bipolar Soft Generalized Topological Structures: Compactness and Homeomorphisms, 2024, 16, 1616-8658, 49, 10.26599/FIE.2023.9270031 |
Figures(3) / Tables(1)
Pontsho Patricia Twala, Alfred Mitema, Cindy Baburam, Naser Aliye Feto. Breakthroughs in the discovery and use of different peroxidase isoforms of microbial origin[J]. AIMS Microbiology, 2020, 6(3): 330-349. doi: 10.3934/microbiol.2020020
| Normal | Accrete | Increta | Percreta | |
| Jan., 2018~Dec., 2019 | 86 | 17 | 114 | 8 |
| Jan., 2020~May, 2021 | 56 | 14 | 22 | 4 |
| Total | 142 | 31 | 136 | 12 |
DownLoad:
CSV
| Class | Train | Validation |
| Normal | 1886 | 472 |
| PAS | 2451 | 613 |
DownLoad:
CSV
| Methods | Features | Accuracy | F1 score |
| Decision Tree | T2WI features | 0.857 | 0.870 |
| T1WI features | 0.681 | 0.715 | |
| Combined features | 0.854 | 0.868 | |
| Random Forest | T2WI features | 0.864 | 0.876 |
| T1WI features | 0.709 | 0.733 | |
| Combined features | 0.862 | 0.874 | |
| Support Vector Machine | T2WI features | 0.862 | 0.875 |
| T1WI features | 0.700 | 0.737 | |
| Combined features | 0.869 | 0.882 |
DownLoad:
CSV
| T2WI features ~ Combined features | |
| Difference between areas | 0.0236 |
| Standard Error | 0.00362 |
| 95% Confidence Interval | 0.0165 to 0.0307 |
| z statistic | 6.519 |
| Significance level | P < 0.0001 |
DownLoad:
CSV
| The number of heads | Accuracy | F1 score |
| 0 | 0.857 | 0.873 |
| 2 | 0.859 | 0.874 |
| 4 | 0.874 | 0.888 |
| 8 | 0.886 | 0.899 |
| 16 | 0.861 | 0.876 |
DownLoad:
CSV
| Methods | AUC |
| Attention module not used | 0.930 |
| Eight attention heads module | 0.940 |
DownLoad:
CSV
| Normal | Accrete | Increta | Percreta | |
| Jan., 2018~Dec., 2019 | 86 | 17 | 114 | 8 |
| Jan., 2020~May, 2021 | 56 | 14 | 22 | 4 |
| Total | 142 | 31 | 136 | 12 |
| Class | Train | Validation |
| Normal | 1886 | 472 |
| PAS | 2451 | 613 |
| Methods | Features | Accuracy | F1 score |
| Decision Tree | T2WI features | 0.857 | 0.870 |
| T1WI features | 0.681 | 0.715 | |
| Combined features | 0.854 | 0.868 | |
| Random Forest | T2WI features | 0.864 | 0.876 |
| T1WI features | 0.709 | 0.733 | |
| Combined features | 0.862 | 0.874 | |
| Support Vector Machine | T2WI features | 0.862 | 0.875 |
| T1WI features | 0.700 | 0.737 | |
| Combined features | 0.869 | 0.882 |
| T2WI features ~ Combined features | |
| Difference between areas | 0.0236 |
| Standard Error | 0.00362 |
| 95% Confidence Interval | 0.0165 to 0.0307 |
| z statistic | 6.519 |
| Significance level | P < 0.0001 |
| The number of heads | Accuracy | F1 score |
| 0 | 0.857 | 0.873 |
| 2 | 0.859 | 0.874 |
| 4 | 0.874 | 0.888 |
| 8 | 0.886 | 0.899 |
| 16 | 0.861 | 0.876 |
| Methods | AUC |
| Attention module not used | 0.930 |
| Eight attention heads module | 0.940 |
