Fully semantic segmentation for rectal cancer based on post-nCRT MRl modality and deep learning framework.

PURPOSE: Rectal tumor segmentation on post neoadjuvant chemoradiotherapy (nCRT) magnetic resonance imaging (MRI) has great significance for tumor measurement, radiomics analysis, treatment planning, and operative strategy. In this study, we developed and evaluated segmentation potential exclusively on post-chemoradiation T2-weighted MRI using convolutional neural networks, with the aim of reducing the detection workload for radiologists and clinicians. METHODS: A total of 372 consecutive patients with LARC were retrospectively enrolled from October 2015 to December 2017. The standard-of-care neoadjuvant process included 22-fraction intensity-modulated radiation therapy and oral capecitabine. Further, 243 patients (3061 slices) were grouped into training and validation datasets with a random 80:20 split, and 41 patients (408 slices) were used as the test dataset. A symmetric eight-layer deep network was developed using the nnU-Net Framework, which outputs the segmentation result with the same size. The trained deep learning (DL) network was examined using fivefold cross-validation and tumor lesions with different TRGs. RESULTS: At the stage of testing, the Dice similarity coefficient (DSC), 95% Hausdorff distance (HD95), and mean surface distance (MSD) were applied to quantitatively evaluate the performance of generalization. Considering the test dataset (41 patients, 408 slices), the average DSC, HD95, and MSD were 0.700 (95% CI: 0.680-0.720), 17.73 mm (95% CI: 16.08-19.39), and 3.11 mm (95% CI: 2.67-3.56), respectively. Eighty-two percent of the MSD values were less than 5 mm, and fifty-five percent were less than 2 mm (median 1.62 mm, minimum 0.07 mm). CONCLUSIONS: The experimental results indicated that the constructed pipeline could achieve relatively high accuracy. Future work will focus on assessing the performances with multicentre external validation.

Optimized tools and timing of response reassessment after neoadjuvant chemoradiation in rectal cancer.

PURPOSE: Reassessment tools of response to long-course neoadjuvant chemoradiation treatment (nCRT) in patients with locally advanced rectal cancer (LARC) are important in predicting complete response (CR) and thus deciding whether a wait-and-watch strategy can be implemented in these patients. Choosing which routine reassessment tools are optimal and when to use them is still unclear and will be researched in the study. METHODS: Altogether, 250 patients with LARC who received nCRT from 2013 to 2021 and were followed up were retrospectively reviewed. Common reassessment tools of response included digital rectal examination (DRE), clinical examination and symptoms, endoscopy, biopsy, magnetic resonance imaging (MRI), and blood biomarkers. RESULTS: Overall, 27.20% (68/250) patients had a complete response and 72.80% (182/250) did not. The combination of MRI, endoscopy, and biopsy showed the best performance in terms of accuracy of 74% and area under the curve (AUC, 0.714, 95% CI 0.546-0.882). Reassessing through DRE and presence of symptoms failed to improve the efficacy of response reassessment. After 100 days, biopsy as an assessment tool would obtain a substantial rise in accuracy from 51.28 to 100% (p = 0.003). CONCLUSION: The combination of MRI, endoscopy, and biopsy is suitable as the reassessment tool of response for applying a wait-and-watch strategy after long-course nCRT in patients with LARC. The accuracy of biopsy as reassessment tools would be improved if they were used over 100 days after nCRT in patients with rectal cancer.

Thermodynamic Optimization of the Ethylene Oligomerization Chemical Process.

The use of olefin oligomerization in the synthesis of liquid fuel has broad application prospects in military and civil fields. Here, based on finite time thermodynamics (FTT), an ethylene oligomerization chemical process (EOCP) model with a constant temperature heat source outside the heat exchanger and reactor pipes was established. The process was first optimized with the minimum specific entropy generation rate (SEGR) as the optimization objective, then multi-objective optimization was further performed by utilizing the NSGA-II algorithm with the minimization of the entropy generation rate (EGR) and the maximization of the C10H20 yield as the optimization objectives. The results showed that the point of the minimum EGR was the same as that of SEGR in the Pareto optimal frontier. The solution obtained using the Shannon entropy decision method had the lowest deviation index, the C10H20 yield was reduced by 49.46% compared with the point of reference and the EGR and SEGR were reduced by 59.01% and 18.88%, respectively.

Ecological Function Analysis and Optimization of a Recompression S-CO2 Cycle for Gas Turbine Waste Heat Recovery.

In this paper, a recompression S-CO2 Brayton cycle model that considers the finite-temperature difference heat transfer between the heat source and the working fluid, irreversible compression, expansion, and other irreversibility is established. First, the ecological function is analyzed. Then the mass flow rate, pressure ratio, diversion coefficient, and the heat conductance distribution ratios (HCDRs) of four heat exchangers (HEXs) are chosen as variables to optimize cycle performance, and the problem of long optimization time is solved by building a neural network prediction model. The results show that when the mass flow rate is small, the pressure ratio, the HCDRs of heater, and high temperature regenerator are the main influencing factors of the ecological function; when the mass flow rate is large, the influences of the re-compressor, the HCDRs of low temperature regenerator, and cooler on the ecological function increase; reasonable adjustment of the HCDRs of four HEXs can make the cycle performance better, but mass flow rate plays a more important role; the ecological function can be increased by 12.13%, 31.52%, 52.2%, 93.26%, and 96.99% compared with the initial design point after one-, two-, three-, four- and five-time optimizations, respectively.

Entropy Generation Minimization for Reverse Water Gas Shift (RWGS) Reactors.

Thermal design and optimization for reverse water gas shift (RWGS) reactors is particularly important to fuel synthesis in naval or commercial scenarios. The RWGS reactor with irreversibilities of heat transfer, chemical reaction and viscous flow is studied based on finite time thermodynamics or entropy generation minimization theory in this paper. The total entropy generation rate (EGR) in the RWGS reactor with different boundary conditions is minimized subject to specific feed compositions and chemical conversion using optimal control theory, and the optimal configurations obtained are compared with three reference reactors with linear, constant reservoir temperature and constant heat flux operations, which are commonly used in engineering. The results show that a drastic EGR reduction of up to 23% can be achieved by optimizing the reservoir temperature profile, the inlet temperature of feed gas and the reactor length simultaneously, compared to that of the reference reactor with the linear reservoir temperature. These optimization efforts are mainly achieved by reducing the irreversibility of heat transfer. Optimal paths have subsections of relatively constant thermal force, chemical force and local EGR. A conceptual optimal design of sandwich structure for the compact modular reactor is proposed, without elaborate control tools or excessive interstage equipment. The results can provide guidelines for designing industrial RWGS reactors in naval or commercial scenarios.