Two-step artificial intelligence algorithm for liver segmentation automates anatomic virtual hepatectomy.

BACKGROUND: Anatomic virtual hepatectomy with precise liver segmentation for hemilivers, sectors, or Couinaud's segments using conventional three-dimensional simulation is not automated and artificial intelligence (AI)-based algorithms have not yet been applied. METHODS: Computed tomography data of 174 living-donor candidates for liver transplantation (training data) were used for developing a new two-step AI algorithm to automate liver segmentation that was validated in another 51 donors (validation data). The Pure-AI (no human intervention) and ground truth (GT, full human intervention) data groups were compared. RESULTS: In the Pure-AI group, the median Dice coefficients of the right and left hemilivers were highly similar, 0.95 and 0.92, respectively; sectors, posterior to lateral: 0.86-0.92, and Couinaud's segments 1-8: 0.71-0.89. Labeling of the first-order branch as hemiliver, right or left portal vein perfectly matched; 92.8% of the second-order (sectors); 91.6% of third-order (segments) matched between the Pure-AI and GT data. CONCLUSIONS: The two-step AI algorithm for liver segmentation automates anatomic virtual hepatectomy. The AI-based algorithm correctly divided all hemilivers, and more than 90% of the sectors and segments.

Artificial intelligence enhances the accuracy of portal and hepatic vein extraction in computed tomography for virtual hepatectomy.

BACKGROUND/PURPOSE: Current conventional algorithms used for 3-dimensional simulation in virtual hepatectomy still have difficulties distinguishing the portal vein (PV) and hepatic vein (HV). The accuracy of these algorithms was compared with a new deep-learning based algorithm (DLA) using artificial intelligence. METHODS: A total of 110 living liver donor candidates until 2017, and 46 donor candidates until 2019 were allocated to the training group and validation groups for the DLA, respectively. All PV or HV branches were labeled based on Couinaud's segment classification and the Brisbane 2000 Terminology by hepato-biliary surgeons. Misclassified and missing branches were compared between a conventional tracking-based algorithm (TA) and DLA in the validation group. RESULTS: The sensitivity, specificity, and Dice coefficient for the PV were 0.58, 0.98, and 0.69 using the TA; and 0.84, 0.97, and 0.90 using the DLA (P < .001, excluding specificity); and for the HV, 0.81, 087, and 0.83 using the TA; and 0.93, 0.94 and 0.94 using the DLA (P < .001 to P = .001). The DLA exhibited greater accuracy than the TA. CONCLUSION: Compared with the TA, artificial intelligence enhanced the accuracy of extraction of the PV and HVs in computed tomography.

Fuzzy logic feedback control for fed-batch enzymatic hydrolysis of lignocellulosic biomass.

A fuzzy logic feedback control system was developed for process monitoring and feeding control in fed-batch enzymatic hydrolysis of a lignocellulosic biomass, dilute acid-pretreated corn stover. Digested glucose from hydrolysis reaction was assigned as input while doser feeding time and speed of pretreated biomass were responses from fuzzy logic control system. Membership functions for these three variables and rule-base were created based on batch hydrolysis data. The system response was first tested in LabVIEW environment then the performance was evaluated through real-time hydrolysis reaction. The feeding operations were determined timely by fuzzy logic control system and efficient responses were shown to plateau phases during hydrolysis. Feeding of proper amount of cellulose and maintaining solids content was well balanced. Fuzzy logic proved to be a robust and effective online feeding control tool for fed-batch enzymatic hydrolysis.

Optimal control strategy for fed-batch enzymatic hydrolysis of lignocellulosic biomass based on epidemic modeling.

A mathematical optimal control strategy for feeding operation was developed for fed-batch enzymatic hydrolysis of dilute acid pretreated lignocellulosic biomass based on a modified epidemic model. Cellulose conversion was maximized and glucose concentration achieved highest possible value over a fixed hydrolysis time. Boundaries of feeding rate and lignin content were set for feasible controls. Using the optimal control feeding strategy, glucose concentration and accumulated cellulose conversion reached up to 77.31 g/L and 72.08% in 100 h, which are 108.76% and 37.50% higher than in batch hydrolysis with same amount of enzyme consumption. Solids content in feeding source has a significant interference on system mass transfer. Optimal control is a useful tool for guiding operations in fed-batch and continuous processes as it enables process optimization through clear objective functions and feasible controls.

Epidemic based modeling of enzymatic hydrolysis of lignocellulosic biomass.

An epidemic based model was developed to describe the enzymatic hydrolysis of a lignocellulosic biomass, dilute sulfuric acid pretreated corn stover. The process of substrate getting adsorbed and digested by enzyme was simulated as susceptibles getting infected by viruses and becoming removed and recovered. This model simplified the dynamic enzyme "infection" process and the catalysis of cellulose into a two-parameter controlled, enzyme behavior guided mechanism. Furthermore, the model incorporates the adsorption block by lignin and inhibition effects on cellulose catalysis. The model satisfactorily predicted the enzyme adsorption and hydrolysis, negative role of lignin, and inhibition effects over hydrolysis for a broad range of substrate and enzyme loadings. Sensitivity analysis was performed to evaluate the incorporation of lignin and other inhibition effects. Our model will be a useful tool for evaluating the effects of parameters during hydrolysis and guide a design strategy for continuous hydrolysis and the associated process control.

Impact of pretreatment with dilute sulfuric acid under moderate temperature on hydrolysis of corn stover with two enzyme systems.

Pretreatment of corn stover with dilute sulfuric acid at moderate temperature was investigated, and glucan digestibility by Cellic CTec2 and Celluclast on the pretreated biomass was compared. Pretreatments were carried out from 60 to 180 min at the temperature from 105 to 135 °C, with acid concentrations ranging from 0.5 to 2% (w/v). Significant portion of xylan was removed during pretreatment, and the glucan digestibility by CTec2 was significantly better than that by Celluclast in all cases. Analysis showed that glucan digestibility by both two enzymes correlated directly with the extent of xylan removal in pretreatment. Confidence interval was built to give a more precise range of glucan conversion and to test the significant difference among pretreatment conditions. Response surface model was built to obtain the optimal pretreatment condition to achieve high glucan conversion after enzymatic hydrolysis. Considering the cost and energy savings, the optimal pretreatment condition of 1.75% acid for 160 min at 135 °C was determined, and glucan conversion can achieve the range from 72.86 to 76.69% at 95% confidence level after enzymatic hydrolysis, making total glucan recovery up to the range from 89.42 to 93.25%.

High temperature dilute acid pretreatment of coastal Bermuda grass for enzymatic hydrolysis.

Dilute sulfuric acid was used to pretreat coastal Bermuda grass at high temperature prior to enzymatic hydrolysis. After both pretreatment and enzymatic hydrolysis processes, the highest yield of total sugars (combined xylose and glucose) was 97% of the theoretical value. The prehydrolyzate liquor was analyzed for inhibitory compounds (furfural, hydroxymethylfurfural (HMF)) in order to assess potential risk for inhibition during the following fermentation. Accounting for the formation of the inhibitory compounds, a pretreatment with 1.2% acid at 140 °C for 30 min with a total sugar yield of 94% of the theoretical value may be more favorable for fermentation. From this study, it can be concluded that dilute sulfuric acid pretreatment can be successfully applied to coastal Bermuda grass to achieve high yields of monomeric glucose and xylose with acceptable levels of inhibitory compound formation.

Sodium hydroxide pretreatment and enzymatic hydrolysis of coastal Bermuda grass.

Coastal Bermuda grass was pretreated with NaOH at concentrations from 0.5% to 3% (w/v) for a residence time from 15 to 90min at 121 degrees C. The pretreatments were evaluated based on total lignin removal and production of total reducing sugars, glucose and xylose from enzymatic hydrolysis of the pretreated biomass. Up to 86% lignin removal was observed. The optimal NaOH pretreatment conditions at 121 degrees C for total reducing sugars production as well as glucose and xylose yields are 15min and 0.75% NaOH. Under these optimal pretreatment conditions, total reducing sugars yield was about 71% of the theoretical maximum, and the overall conversion efficiencies for glucan and xylan were 90.43% and 65.11%, respectively.

Microwave-based alkali pretreatment of switchgrass and coastal bermudagrass for bioethanol production.

Switchgrass and coastal bermudagrass are promising lignocellulosic feedstocks for bioethanol production. However, pretreatment of lignocelluloses is required to improve production of fermentable sugars from enzymatic hydrolysis. Microwave-based alkali pretreatment of switchgrass and coastal bermudagrass was investigated in this study. Pretreatments were carried out by immersing the biomass in dilute alkali reagents and exposing the slurry to microwave radiation at 250 W for residence times ranging from 5 to 20 min. Simons' stain method was used to quantify changes in biomass porosity as a result of the pretreatment. Pretreatments were evaluated based on yields of total reducing sugars, glucose, and xylose. An evaluation of different alkalis identified sodium hydroxide as the most effective alkali reagent for microwave-based pretreatment of switchgrass and coastal bermudagrass. 82% glucose and 63% xylose yields were achieved for switchgrass and 87% glucose and 59% xylose yields were achieved for coastal bermudagrass following enzymatic hydrolysis of biomass pretreated under optimal conditions. Dielectric properties for dilute sodium hydroxide solutions were measured and compared with solid losses, lignin reduction, and reducing sugar levels in hydrolyzates. Results indicate that dielectric loss tangent of alkali solutions is a potential indicator of the severity of microwave-based pretreatments.

Modeling changes in biomass composition during microwave-based alkali pretreatment of switchgrass.

This study used two different approaches to model changes in biomass composition during microwave-based pretreatment of switchgrass: kinetic modeling using a time-dependent rate coefficient, and a Mamdani-type fuzzy inference system. In both modeling approaches, the dielectric loss tangent of the alkali reagent and pretreatment time were used as predictors for changes in amounts of lignin, cellulose, and xylan during the pretreatment. Training and testing data sets for development and validation of the models were obtained from pretreatment experiments conducted using 1-3% w/v NaOH (sodium hydroxide) and pretreatment times ranging from 5 to 20 min. The kinetic modeling approach for lignin and xylan gave comparable results for training and testing data sets, and the differences between the predictions and experimental values were within 2%. The kinetic modeling approach for cellulose was not as effective, and the differences were within 5-7%. The time-dependent rate coefficients of the kinetic models estimated from experimental data were consistent with the heterogeneity of individual biomass components. The Mamdani-type fuzzy inference was shown to be an effective approach to model the pretreatment process and yielded predictions with less than 2% deviation from the experimental values for lignin and with less than 3% deviation from the experimental values for cellulose and xylan. The entropies of the fuzzy outputs from the Mamdani-type fuzzy inference system were calculated to quantify the uncertainty associated with the predictions. Results indicate that there is no significant difference between the entropies associated with the predictions for lignin, cellulose, and xylan. It is anticipated that these models could be used in process simulations of bioethanol production from lignocellulosic materials.

Switchgrass for bioethanol and other value-added applications: a review.

Switchgrass is a promising feedstock for value-added applications due to its high productivity, potentially low requirements for agricultural inputs and positive environmental impacts. The objective of this paper is to review published research on the conversion of switchgrass into bioethanol and other value-added products. Environmental benefits associated with switchgrass include the potential for carbon sequestration, nutrient recovery from runoff, soil remediation and provision of habitats for grassland birds. Pretreatment of switchgrass is required to improve the yields of fermentable sugars. Based on the type of pretreatment, glucose yields range from 70% to 90% and xylose yields range from 70% to 100% after hydrolysis. Following pretreatment and hydrolysis, ethanol yields range from 72% to 92% of the theoretical maximum. Other value-added uses of switchgrass include gasification, bio-oil production, newsprint production and fiber reinforcement in thermoplastic composites. Future prospects for research include increased biomass yields, optimization of feedstock composition for bioenergy applications, and efficient pentose fermentation to improve ethanol yields.

Potential of agricultural residues and hay for bioethanol production.

Production of bioethanol from agricultural residues and hays (wheat, barley, and triticale straws, and barley, triticale, pearl millet, and sweet sorghum hays) through a series of chemical pretreatment, enzymatic hydrolysis, and fermentation processes was investigated in this study. Composition analysis suggested that the agricultural straws and hays studied contained approximately 28.62-38.58% glucan, 11.19-20.78% xylan, and 22.01-27.57% lignin, making them good candidates for bioethanol production. Chemical pretreatment with sulfuric acid or sodium hydroxide at concentrations of 0.5, 1.0, and 2.0% indicated that concentration and treatment agent play a significant role during pretreatment. After 2.0% sulfuric acid pretreatment at 121 degrees C/15 psi for 60 min, 78.10-81.27% of the xylan in untreated feedstocks was solubilized, while 75.09-84.52% of the lignin was reduced after 2.0% sodium hydroxide pretreatment under similar conditions. Enzymatic hydrolysis of chemically pretreated (2.0% NaOH or H2SO4) solids with Celluclast 1.5 L-Novozym 188 (cellobiase) enzyme combination resulted in equal or higher glucan and xylan conversion than with Spezyme(R) CP- xylanase combination. The glucan and xylan conversions during hydrolysis with Celluclast 1.5 L-cellobiase at 40 FPU/g glucan were 78.09 to 100.36% and 74.03 to 84.89%, respectively. Increasing the enzyme loading from 40 to 60 FPU/g glucan did not significantly increase sugar yield. The ethanol yield after fermentation of the hydrolyzate from different feedstocks with Saccharomyces cerevisiae ranged from 0.27 to 0.34 g/g glucose or 52.00-65.82% of the theoretical maximum ethanol yield.

Review: Takagi-Sugeno fuzzy modeling of skin permeability.

The skin is a major exposure route for many potentially toxic chemicals. It is, therefore, important to be able to predict the permeability of compounds through skin under a variety of conditions. Available skin permeability databases are often limited in scope and not conducive to developing effective models. This sparseness and ambiguity of available data prompted the use of fuzzy set theory to model and predict skin permeability. Using a previously published database containing 140 compounds, a rule-based Takagi-Sugeno fuzzy model is shown to predict skin permeability of compounds using octanol-water partition coefficient, molecular weight, and temperature as inputs. Model performance was estimated using a cross-validation approach. In addition, 10 data points were removed prior to model development for additional testing with new data. The fuzzy model is compared to a regression model for the same inputs using both R2 and root mean square error measures. The quality of the fuzzy model is also compared with previously published models. The statistical analysis demonstrates that the fuzzy model performs better than the regression model with identical data and validation protocols. The prediction quality for this model is similar to others that were published. The fuzzy model provides insights on the relationships between lipophilicity, molecular weight, and temperature on percutaneous penetration. This model can be used as a tool for rapid determination of initial estimates of skin permeability.