Paired multi-modality medical images, can provide complementary information to help physicians make more reasonable decisions than single modality medical images. But they are difficult to generate due to multiple factors in practice (e.g., time, cost, radiation dose). To address these problems, multi-modality medical image translation has aroused increasing research interest recently. However, the existing works mainly focus on translation effect of a whole image instead of a critical target area or Region of Interest (ROI), e.g., organ and so on. This leads to poor-quality translation of the localized target area which becomes blurry, deformed or even with extra unreasonable textures. In this paper, we propose a novel target-aware generative adversarial network called TarGAN, which is a generic multi-modality medical image translation model capable of (1) learning multi-modality medical image translation without relying on paired data, (2) enhancing quality of target area generation with the help of target area labels. The generator of TarGAN jointly learns mapping at two levels simultaneously - whole image translation mapping and target area translation mapping. These two mappings are interrelated through a proposed crossing loss. The experiments on both quantitative measures and qualitative evaluations demonstrate that TarGAN outperforms the state-of-the-art methods in all cases. Subsequent segmentation task is conducted to demonstrate effectiveness of synthetic images generated by TarGAN in a real-world application. Our code is available at https://github.com/2165998/TarGAN.
Abstract An iron‐tungsten oxide catalyst was developed for selective catalytic reduction of NO with NH 3 (NH 3 ‐SCR) by supporting Fe 2 O 3 nanoparticles onto hexagonal WO 3 nanorods. The Fe 2 O 3 /WO 3 catalyst showed much higher catalytic activity than Fe 2 O 3 and WO 3 , as explained by the synergistic effects caused by acid sites (provided by WO 3 ) and redox sites (provided by Fe 2 O 3 ). X‐ray diffraction and transmission electron microscopy techniques revealed that the crystal structures and morphologies of Fe 2 O 3 and WO 3 kept unchanged during the preparation of Fe 2 O 3 /WO 3 . NH 3 adsorption curves, NH 3 temperature programmed desorption, and temperature programmed surface reaction of NO demonstrated that WO 3 possessed strong acidity but poor redox ability, whereas Fe 2 O 3 had high redox ability but inadequate acidic property. Therefore, the enhancement in catalytic activity (when using Fe 2 O 3 /WO 3 as a catalyst) should originate from the redox‐acid synergy, as further evidenced by the low SCR activity of pure Fe 2 O 3 and Fe 2 O 3 /TiO 2 with low capacity for adsorbing NH 3 . In addition, Fe 2 O 3 /WO 3 showed high activity and stability in the presence of K + , SO 2 , and H 2 O, demonstrating its potential in practical applications.
To develop an end-to-end convolutional neural network model for analyzing hematoxylin and eosin(H&E)-stained histological images, enhancing the performance and efficiency of nuclear segmentation and classification within the digital pathology workflow. We propose a dual-mechanism feature pyramid fusion technique that integrates nuclear segmentation and classification tasks to construct the HistoNeXt network model. HistoNeXt utilizes an encoder-decoder architecture, where the encoder, based on the advanced ConvNeXt convolutional framework, efficiently and accurately extracts multi-level abstract features from tissue images. These features are subsequently shared with the decoder. The decoder employs a dual-mechanism architecture: The first branch of the mechanism splits into two parallel paths for nuclear segmentation, producing nuclear pixel (NP) and horizontal and vertical distance (HV) predictions, while the second mechanism branch focuses on type prediction (TP). The NP and HV branches leverage densely connected blocks to facilitate layer-by-layer feature transmission and reuse, while the TP branch employs channel attention to adaptively focus on critical features. Comprehensive data augmentation including morphology-preserving geometric transformations and adaptive H&E channel adjustments was applied. To address class imbalance, type-aware sampling was applied. The model was evaluated on public tissue image datasets including CONSEP, PanNuke, CPM17, and KUMAR. The performance in nuclear segmentation was evaluated using the Dice Similarity Coefficient (DICE), the Aggregated Jaccard Index (AJI) and Panoptic Quality (PQ), and the classification performance was evaluated using F1 scores and category-specific F1 scores. In addition, computational complexity, measured in Giga Floating Point Operations Per Second (GFLOPS), was used as an indicator of resource consumption. HistoNeXt demonstrated competitive performance across multiple datasets: achieving a DICE score of 0.874, an AJI of 0.722, and a PQ of 0.689 on the CPM17 dataset; a DICE score of 0.826, an AJI of 0.625, and a PQ of 0.565 on KUMAR; and performance comparable to Transformer-based models, such as CellViT-SAM-H, on PanNuke, with a binary PQ of 0.6794, a multi-class PQ of 0.4940, and an overall F1 score of 0.82. On the CONSEP dataset, it achieved a DICE score of 0.843, an AJI of 0.592, a PQ of 0.532, and an overall classification F1 score of 0.773. Specific F1 scores for various cell types were as follows: 0.653 for malignant or dysplastic epithelial cells, 0.516 for normal epithelial cells, 0.659 for inflammatory cells, and 0.587 for spindle cells. The tiny model's complexity was 33.7 GFLOPS. By integrating novel convolutional technology and employing a pyramid fusion of dual-mechanism characteristics, HistoNeXt enhances both the precision and efficiency of nuclear segmentation and classification. Its low computational complexity makes the model well suited for local deployment in resource-constrained environments, thereby supporting a broad spectrum of clinical and research applications. This represents a significant advance in the application of convolutional neural networks in digital pathology analysis.
Environmentally benign cerium-based catalysts are promising alternatives to toxic vanadium-based catalysts for controlling NOx emissions via selective catalytic reduction (SCR), but conventional cerium-based catalysts unavoidably suffer from SO2 poisoning in low-temperature SCR. We develop a strongly sulfur-resistant Ce1+1/TiO2 catalyst by spatially confining Ce atom pairs to different anchoring sites of anatase TiO2(001) surfaces. Experimental results combined with theoretical calculations demonstrate that strong electronic interactions between the paired Ce atoms upshift the lowest unoccupied states to an energy level higher than the highest occupied molecular orbital (HOMO) of SO2 so as to be catalytically inert in SO2 oxidation but slightly lower than HOMO of NH3 so that Ce1+1/TiO2 has desired ability toward NH3 activation required for SCR. Hence, Ce1+1/TiO2 shows higher SCR activity and excellent stability in the presence of SO2 at low temperatures with respect to supported single Ce atoms. This work provides a general strategy to develop sulfur-resistant catalysts by tuning the electronic states of active sites for low-temperature SCR, which has implications for practical applications with energy-saving requirements.
To investigate the clinical effect of modified Koyanagi technique with coverage by tunica vaginalis of testis in severe hypospadias.49 cases with severe hypospadias treated from Jan. 2009 to Sep. 2011 were retrospectively studied. 25 patients underwent Koyanagi technique with coverage by tunica vaginalis of testis. 24 cases underwent one-stage Duplay + Duckett technique in the same term. The patients were followed up for 7-24 months.Among the 25 children treated with Koyanagi procedure, 20 cases were cured, 5 patients had postoperative complications, including urethral fistula in 3 cases,urethral stenosis in 2 cases. At the same time, in the Duplay + Duckett group, 17 cases were cured, 7 children had postoperative complications, including urethral fistula in 4 cases, and urethral stenosis in 3 cases. All the patients with urethral fistula were repaired successfully 6 months after the first surgery; The urethral stenosis were cured by dilatation within 1 to 3 months. The successful rate in the 2 groups had no significant difference(P >0.05).Koyanagi technique with coverage by tunica vaginalis of testis is relatively simple with similar effect as Duplay + Duckett technique for severe hypospadias.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)