Dilated Heterogeneous Convolution for Cell Detection and Segmentation Based on Mask R-CNN.

Owing to the variable shapes, large size difference, uneven grayscale, and dense distribution among biological cells in an image, it is very difficult to accurately detect and segment cells. Especially, it is a serious challenge for some microscope imaging devices with limited resources owing to a large number of learning parameters and computational burden when using the standard Mask R-CNN. In this work, we propose a mask R-DHCNN for cell detection and segmentation. More specifically, Dilation Heterogeneous Convolution (DHConv) is proposed by designing a novel convolutional kernel structure (i.e., DHConv), which integrates the strengths of the heterogeneous kernel structure and dilated convolution. Then, the traditional homogeneous convolution structure of the standard Mask R-CNN is replaced with the proposed DHConv module to it adapt to shape and size differences encountered in cell detection and segmentation tasks. Finally, a series of comparison and ablation experiments are conducted on various biological cell datasets (such as U373, GoTW1, SIM+, and T24) to verify the effectiveness of the proposed method. The results show that the proposed method can obtain better performance than some state-of-the-art methods in multiple metrics (including AP, Precision, Recall, Dice, and PQ) while maintaining competitive FLOPs and FPS.

Precise Phase Measurement for Fringe Reflection Technique through Optimized Camera Response.

The Fringe Reflection is a robust and non-contact technique for optical measurement and specular surface characterization. The periodic alternation between dark and light cycles of the fringe patterns encodes the geometric information and provides a non-contact method of spatial measurement through phase extraction. Precisely expressing the positions of the points of the fringe pattern is a fundamental requirement for an accurate fringe reflection measurement. However, the nonlinear processes, both in generating the fringe pattern on a screen and capturing it using pixel values, cause inevitable errors in the phase measurement and eventually reduce the system's precision. Aiming at reducing these nonlinear errors, we focus on constructing a new quantity from the pixel values of the photos of the fringe patterns that could linearly respond to the ideal fringe pattern. To this end, we hypothesize that the process of displaying the fringe pattern on a screen using a control function is similar to the process of capturing the pattern and converting the illuminating information into pixel values, which can be described using the camera's response function. This similarity allows us to build a scaled energy quantity that could have a better linear relation with the control function. We optimize the extracted camera response function using an objective to increase the precision and reduce the quoted error. Experiments designed to determine the positions of points along the quartile lines verify the effectiveness of the proposed method in improving fringe reflection measurement precision.

Online Detection System for Wheat Machine Harvesting Impurity Rate Based on DeepLabV3.

Wheat, one of the most important food crops in the world, is usually harvested mechanically by combine harvesters. The impurity rate is one of the most important indicators of the quality of wheat obtained by mechanized harvesting. To realize the online detection of the impurity rate in the mechanized harvesting process of wheat, a vision system based on the DeepLabV3+ model of deep learning for identifying and segmenting wheat grains and impurities was designed in this study. The DeepLabV3+ model construction considered the four backbones of MobileNetV2, Xception-65, ResNet-50, and ResNet-101 for training. The optimal DeepLabV3+ model was determined through the accuracy rate, comprehensive evaluation index, and average intersection ratio. On this basis, an online detection method of measuring the wheat impurity rate in mechanized harvesting based on image information was constructed. The model realized the online detection of the wheat impurity rate. The test results showed that ResNet-50 had the best recognition and segmentation performance; the accuracy rate of grain identification was 86.86%; the comprehensive evaluation index was 83.63%; the intersection ratio was 0.7186; the accuracy rate of impurity identification was 89.91%; the comprehensive evaluation index was 87.18%; the intersection ratio was 0.7717; and the average intersection ratio was 0.7457. In terms of speed, ResNet-50 had a fast segmentation speed of 256 ms per image. Therefore, in this study, ResNet-50 was selected as the backbone network for DeepLabV3+ to carry out the identification and segmentation of mechanically harvested wheat grains and impurity components. Based on the manual inspection results, the maximum absolute error of the device impurity rate detection in the bench test was 0.2%, and the largest relative error was 17.34%; the maximum absolute error of the device impurity rate detection in the field test was 0.06%; and the largest relative error was 13.78%. This study provides a real-time method for impurity rate measurement in wheat mechanized harvesting.

Isolation of protein-free chitin spore coats of Nosema ceranae and its application to screen the interactive spore wall proteins.

Nosema ceranae is the pathogen of nosemosis in the honey bee, which can bring great economic loss to apiculture. Chitin acts as a major component of the endospore of microsporidia and plays an essential role to form the bridges across the endospore. Here, Chitin Spore Coats (CSCs) of N. ceranae were successfully extracted by optimized hot alkaline treatment. SDS-PAGE and Calcofluor White Stain (CWS) staining indicated that the obtained CSCs were protein-free and the transmission electron microscopy analysis showed that CSCs performed the intact and loose chitin spore coats. Western blotting and indirect immunofluorescence analysis (IFA) demonstrated that CSCs could interact with three spore wall proteins (rNcSWP7, rNcSWP8, and rNcSWP12). Our method was effective to extract CSCs of N. ceranae and this could be very useful for screening spore wall proteins involved in endospore composition, which could be helpful to uncover the biological structure and pathogenesis of microsporidia.

Imidacloprid activates ROS and causes mortality in honey bees (Apis mellifera) by inducing iron overload.

Imidacloprid, a neonicotinoid pesticide widely used for insect pest control, has become a potential pollutant to pollinators. Previous reports have demonstrated the toxicity of this drug in activating oxidative stress resulting in high mortality in the honey bee Apis mellifera. However, the mechanisms underlying the toxicity of imidacloprid have not been fully elucidated. In this study, sublethal (36 ng/bee) and median lethal (132 ng/bee) doses of imidacloprid were administered to bees. The results showed dose-dependent increases in reactive oxygen species (ROS), Fe2+, and mortality in bees. Notably, imidacloprid also induced upregulation of the gene encoding ferritin (AmFth), which plays a pivotal role in reducing Fe2+ overload. Upregulation of AmFth has been suggested to be closely related to ROS accumulation and high mortality in bees. To confirm the role played by AmFth in imidacloprid-activated ROS, dsAmFth double-strand was orally administered to bees after exposure to imidacloprid. The results revealed aggravated Fe2+ overload, higher ROS activation, and elevated mortality in the bees, indicating that imidacloprid activated ROS and caused mortality in the bees, probably by inducing iron overload. This study helps to elucidate the molecular mechanisms underlying the toxicity of imidacloprid from the perspective of iron metabolism.

Task-Demand-Dependent Neural Representation of Odor Information in the Olfactory Bulb and Posterior Piriform Cortex.

In awake rodents, the neural representation of olfactory information in the olfactory bulb is largely dependent on brain state and behavioral context. Learning-modified neural plasticity has been observed in mitral/tufted cells, the main output neurons of the olfactory bulb. Here, we propose that the odor information encoded by mitral/tufted cell responses in awake mice is highly dependent on the behavioral task demands. We used fiber photometry to record calcium signals from the mitral/tufted cell population in awake, head-fixed male mice under different task demands. We found that the mitral/tufted cell population showed similar responses to two distinct odors when the odors were presented in the context of a go/go task, in which the mice received a water reward regardless of the identity of the odor presented. However, when the same odors were presented in a go/no-go task, in which one odor was rewarded and the other was not, then the mitral cell population responded very differently to the two odors, characterized by a robust reduction in the response to the nonrewarded odor. Thus, the representation of odors in the mitral/tufted cell population depends on whether the task requires discrimination of the odors. Strikingly, downstream of the olfactory bulb, pyramidal neurons in the posterior piriform cortex also displayed a task-demand-dependent neural representation of odors, but the anterior piriform cortex did not, indicating that these two important higher olfactory centers use different strategies for neural representation.SIGNIFICANCE STATEMENT The most important task of the olfactory system is to generate a precise representation of odor information under different brain states. Whether the representation of odors by neurons in olfactory centers such as the olfactory bulb and the piriform cortex depends on task demands remains elusive. We find that odor representation in the mitral/tufted cells of the olfactory bulb depends on whether the task requires odor discrimination. A similar neural representation is found in the posterior piriform cortex but not the anterior piriform cortex, indicating that these higher olfactory centers use different representational strategies. The task-demand-dependent representational strategy is likely important for facilitating information processing in higher brain centers responsible for decision making and encoding of salience.

Prognostic value of TOP2A in bladder urothelial carcinoma and potential molecular mechanisms.

BACKGROUND: The prognosis of bladder urothelial carcinoma (BLCA) varies greatly among patients, and conventional pathological predictors are generally inadequate and often inaccurate to predict the heterogeneous behavior of BLCA. This study aims to investigate the prognostic value and function of TOP2A in BLCA. METHODS: TOP2A expression level was examined by RNA-sequencing, quantitative real time polymerase chain reaction and immunohistochemistry from 10, 40 and 209 BLCA samples, respectively. Public databases were analyzed for validation. Cell proliferation, migration, invasion assays were performed to explore potential functions of TOP2A in BLCA. Flow cytometry was performed for cell cycle and apoptosis analysis. Univariable and multivariable Cox regression models were performed to identify independent risk factors for the prognosis of BLCA. RESULTS: We found TOP2A was significantly upregulated in BLCA samples, especially for high-grade and advanced stage tumors, compared with matched normal epithelial tissue. Univariable COX regression analysis revealed high TOP2A expression was significantly associated with poorer cancer-specific, progression-free and recurrence-free survival, but not independently of clinical characteristics in the multivariable models. Knockdown of TOP2A remarkably inhibited the proliferation of BLCA cells and non-cancerous urothelial cells. Furthermore, migration and invasion capacity of BLCA cells were strongly suppressed after TOP2A knockdown. Moreover, flow cytometry suggested TOP2A had anti-apoptotic function, and knockdown of TOP2A could induce resistance to doxorubicin in J82 cells. CONCLUSIONS: In our study, TOP2A was overexpressed in BLCA and could serve as a prognostic biomarker for BLCA. Moreover, TOP2A is functionally important for the proliferation, invasion and survival of BLCA cells.

Physiochemical properties and paclitaxel release behaviors of dual-stimuli responsive copolymer-magnetite superparamagnetic nanocomposites.

Magnetically driven drug delivery systems of superparamagnetic iron oxide nanoparticles have a considerable potential as candidates to overcome the present obstacles of drug delivery in anti-tumor therapy owing to its remote controllability by external magnetic fields and other unique properties. In this work, a biodegradable anionic copolymer with side carboxylic groups named methoxy-poly (ethylene glycol)-block-poly(α-carboxyl-ε-caprolactone) was synthesized to complex iron oxide magnetic nanoparticles and load paclitaxel (PTX) to form dual-stimuli responsive copolymer-magnetite superparamagnetic nanocomposites with an elastic core and carboxylic groups on the surface in a very easy way. The physiochemical properties of these nanocomposites were measured. High PTX loading content and high saturation magnetization were obtained. Being proved to be stable at a wide pH range and low cytotoxic in vitro, these nanocomposites presented faster PTX release in vitro at pH 6.5 than at pH 7.4 and obviously reduced burst release.

Suppression of parasitic interference in a fiber-tip Fabry-Perot interferometer for high-pressure measurements.

We demonstrate a novel design and fabrication process for fiber-tip Fabry-Perot interferometric (FTFPI) pressure sensors which eliminates fringe envelopes in the reflection spectrum. The outer facet reflectivity and thickness of the FTFPI silica diaphragm were reduced through orthogonal rough-polishing of the fiber end facet. A silica FTFPI sample with a diaphragm thickness of ~10.7 µm was produced and tested under hydraulic pressures ranging from 0 to 30 MPa. The proposed sensor achieved a pressure sensitivity of -284 pm/MPa at 1555 nm and could be a valuable new tool for high pressure measurements.

Long period fiber grating based on periodically screw-type distortions for torsion sensing.

A novel long-period fiber grating (LPFG), fabricated by periodically cascading a series of screw-type distortions, is proposed and experimentally demonstrated. These screw-type distortions are induced by twisting the fiber during CO2 laser beam exposure. The resulting LPFG will either be left- or right-hand helical, depending on the twist rate and direction used during fabrication, with a certain frozen shear strain. Due to the independence between grating pitch and twist rate, this type of LPFG could be more flexible than the helical- or chiral-fiber gratings reported previously. During LPFG twisting, the device displays good directional dependence and an enhanced torsion sensitivity of 0.1604 nm/(rad/m), which implies the structure could be an excellent candidate for torsion sensors.

Bacterium-Expressed dsRNA Downregulates Microsporidia Nosema bombycis Gene Expression.

The microsporidia Nosema bombycis is the insect pathogen of pebrine disease severely destructive to sericulture production. Here, we describe the use of Escherichia coli HT115 strain (DE3) to express double-strand RNAs targeting the gene encoding ADP/ATP protein in N. bombycis. The results showed that dsRNAs deferentially suppressed the gene expression during N. bombycis infection in the silkworm, and the effect waned gradually. Our results, for the first time, provide a tool to utilize the dsRNA expressed by recombinant E. coli to control the pebrine disease of the domestic silkworm.

Epidemic spreading between two coupled subpopulations with inner structures.

The structure of underlying contact network and the mobility of agents are two decisive factors for epidemic spreading in reality. Here, we study a model consisting of two coupled subpopulations with intra-structures that emphasizes both the contact structure and the recurrent mobility pattern of individuals simultaneously. We show that the coupling of the two subpopulations (via interconnections between them and round trips of individuals) makes the epidemic threshold in each subnetwork to be the same. Moreover, we find that the interconnection probability between two subpopulations and the travel rate are important factors for spreading dynamics. In particular, as a function of interconnection probability, the epidemic threshold in each subpopulation decreases monotonously, which enhances the risks of an epidemic. While the epidemic threshold displays a non-monotonic variation as travel rate increases. Moreover, the asymptotic infected density as a function of travel rate in each subpopulation behaves differently depending on the interconnection probability.

Complete genome sequences from three genetically distinct strains reveal high intraspecies genetic diversity in the microsporidian Encephalitozoon cuniculi.

Microsporidia from the Encephalitozoonidae are obligate intracellular parasites with highly conserved and compacted nuclear genomes: they have few introns, short intergenic regions, and almost identical gene complements and chromosome arrangements. Comparative genomics of Encephalitozoon and microsporidia in general have focused largely on the genomic diversity between different species, and we know very little about the levels of genetic diversity within species. Polymorphism studies with Encephalitozoon are so far restricted to a small number of genes, and a few genetically distinct strains have been identified; most notably, three genotypes (ECI, ECII, and ECIII) of the model species E. cuniculi have been identified based on variable repeats in the rRNA internal transcribed spacer (ITS). To determine if E. cuniculi genotypes are genetically distinct lineages across the entire genome and at the same time to examine the question of intraspecies genetic diversity in microsporidia in general, we sequenced de novo genomes from each of the three genotypes and analyzed patterns of single nucleotide polymorphisms (SNPs) and insertions/deletions across the genomes. Although the strains have almost identical gene contents, they harbor large numbers of SNPs, including numerous nonsynonymous changes, indicating massive intraspecies variation within the Encephalitozoonidae. Based on this diversity, we conclude that the recognized genotypes are genetically distinct and propose new molecular markers for microsporidian genotyping.

A dataset of the quality of soybean harvested by mechanization for deep-learning-based monitoring and analysis.

Deep learning and machine vision technology are widely applied to detect the quality of mechanized soybean harvesting. A clean dataset is the foundation for constructing an online detection learning model for the quality of mechanized harvested soybeans. In pursuit of this objective, we established an image dataset for mechanized harvesting of soybeans. The photos were taken on October 9, 2018, at a soybean experimental field of Liangfeng Grain and Cotton Planting Professional Cooperative in Guanyi District, Liangshan, Shandong, China. The dataset contains 40 soybean images of different qualities. By scaling, rotating, flipping, filtering, and adding noise to enhance the data, we expanded the dataset to 800 frames. The dataset consists of three folders, which store images, label maps, and record files for partitioning the dataset into training, validation, and testing sets. In the initial stages, the author devised an online detection model for soybean crushing rate and impurity rate based on machine vision, and research outcomes affirm the efficacy of this dataset. The dataset can help researchers construct a quality prediction model for mechanized harvested soybeans using deep learning techniques.

Clinical characteristics and surgical outcomes of low-grade epilepsy-associated brain tumors.

Background: Low-grade epilepsy-associated brain tumors (LEATs) are found to be the second most common lesion-related epilepsy. Malignant potential of LEATs is very low and the overall survival is good, so the focus of treatment is focused more on seizure outcome rather than oncological prognosis. Objectives: This study was conducted to evaluate the risk factors of seizure outcomes after resection in patients with LEATs. Design: A retrospective study. Methods: A retrospective analysis of patients with LEATs who underwent resective surgery in our three epilepsy centers between October 2010 and April 2023 with a minimum follow-up of 1 year. Demography, clinical characters, neurophysiology, and molecular neuropathology were assessed for association with postoperative seizure outcomes at 1-, 2-, and 5-year follow-up. Synthetic minority oversampling technique (SMOTE) algorithm model was performed to handle the imbalance of data distribution. Gaussian Naïve Bayes (GNB) algorithms were created as a basis for classifying outcomes according to observation indicators. Results: A total of 111 patients were enrolled in the cohort. The most common pathology was ganglioglioma (n = 37, 33.3%). The percentage of patients with seizure freedom was 91.0% (101/111) at 1-year follow-up, 87.5% (77/88) at 2-year follow-up, and 79.1% (53/67) at 5-year follow-up. Partial resection had a significantly poor seizure outcome compared to total resection and supratotal resection (p < 0.05). The epileptiform discharge on post-resective intraoperative electrocorticography (ECoG) or postoperative scalp electroencephalography (EEG) were negative factors on postoperative seizure freedom at 1-, 2-, or 5-year follow-ups (p < 0.05). The area under the receiver-operating characteristic curve value of the GNB-SMOTE model was 0.95 (95% CI, 0.876-1.000), 0.892 (95% CI, 0.656-0.934), and 0.786 (95% CI, 0.491-0.937) at 1-, 2-, and 5-year follow-up, respectively. Conclusion: The partial resection, post-resective intraoperative ECoG, and postoperative scalp EEG were valuable indicators of poor seizure outcomes. The utilization of post-resective intraoperative ECoG is beneficial to improve seizure outcomes. Based on the data diversity and completeness of three medical centers, a multivariate correlation analysis model was established based on GNB algorithm.

Efficacy of deep brain stimulation for Tourette syndrome and its comorbidities: A meta-analysis.

Tourette Syndrome (TS) is a neurodevelopmental disorder characterized by multiple motor and vocal tics, often accompanied by comorbid disorders. Optional treatments for patients with TS include behavioral therapy, pharmacotherapy, and neurostimulation techniques. Deep brain stimulation (DBS) has been considered a therapeutic approach for refractory TS and its comorbid symptoms. However, systematic comparison is necessary to understand the therapeutic effect of DBS among patients with TS with various comorbid symptoms, demographic characteristics, or stimulation targets. Consequently, our research aimed to assess the clinical efficacy of DBS in alleviating the symptoms of TS and its comorbidities. A systematic literature search was conducted across five databases: PubMed, Web of Science, MEDLINE, Embase, and PsycINFO. The primary outcome was the mean change in the global score of the Yale Global Tic Severity Scale (YGTSS), which assesses the severity of tics. The secondary outcomes included mean improvement of comorbid symptoms, such as obsessive-compulsive behaviors (OCB), depression symptoms and anxiety symptoms. In total, 51 studies with 673 participants were included in this meta-analysis. Overall, the DBS led to a significant improvement in tic symptoms (p â€‹< â€‹0.001), as well as the comorbid obsessive-compulsive, depression, and anxiety symptoms with effect sizes of 1.88, 0.88, 1.04, and 0.76 accordingly. In the subgroup analysis, we found that striatum stimulation led to a more significant improvement in OCB in patients with TS compared to that observed with thalamic stimulation (p â€‹= â€‹0.017). The relationship between sex, age, and target with the improvement of tics, depression, and anxiety was not statistically significant (p â€‹= â€‹0.923, 0.438, 0.591 for different male proportions; p â€‹= â€‹0.463, 0.425, 0.105 for different age groups; p â€‹= â€‹0.619, 0.113, 0.053 for different targets). In conclusion, DBS is an efficient treatment option for TS, as well as the comorbid OCB, depression symptoms, and anxiety symptoms. It is important to highlight that stimulating the striatum is more effective in managing obsessive-compulsive symptoms compared to stimulating the thalamus.

Comparative genomics of parasitic silkworm microsporidia reveal an association between genome expansion and host adaptation.

BACKGROUND: Microsporidian Nosema bombycis has received much attention because the pébrine disease of domesticated silkworms results in great economic losses in the silkworm industry. So far, no effective treatment could be found for pébrine. Compared to other known Nosema parasites, N. bombycis can unusually parasitize a broad range of hosts. To gain some insights into the underlying genetic mechanism of pathological ability and host range expansion in this parasite, a comparative genomic approach is conducted. The genome of two Nosema parasites, N. bombycis and N. antheraeae (an obligatory parasite to undomesticated silkworms Antheraea pernyi), were sequenced and compared with their distantly related species, N. ceranae (an obligatory parasite to honey bees). RESULTS: Our comparative genomics analysis show that the N. bombycis genome has greatly expanded due to the following three molecular mechanisms: 1) the proliferation of host-derived transposable elements, 2) the acquisition of many horizontally transferred genes from bacteria, and 3) the production of abundnant gene duplications. To our knowledge, duplicated genes derived not only from small-scale events (e.g., tandem duplications) but also from large-scale events (e.g., segmental duplications) have never been seen so abundant in any reported microsporidia genomes. Our relative dating analysis further indicated that these duplication events have arisen recently over very short evolutionary time. Furthermore, several duplicated genes involving in the cytotoxic metabolic pathway were found to undergo positive selection, suggestive of the role of duplicated genes on the adaptive evolution of pathogenic ability. CONCLUSIONS: Genome expansion is rarely considered as the evolutionary outcome acting on those highly reduced and compact parasitic microsporidian genomes. This study, for the first time, demonstrates that the parasitic genomes can expand, instead of shrink, through several common molecular mechanisms such as gene duplication, horizontal gene transfer, and transposable element expansion. We also showed that the duplicated genes can serve as raw materials for evolutionary innovations possibly contributing to the increase of pathologenic ability. Based on our research, we propose that duplicated genes of N. bombycis should be treated as primary targets for treatment designs against pébrine. The genome data and annotation information of N. bombycis and N.antheraeae were submitted to GenBank (Accession numbers ACJZ01000001 -ACJZ01003558).

Adaptive Diffusion Pairwise Fused Lasso LMS Algorithm Over Networks.

The topic of identification for sparse vector in a distributed way has triggered great interest in the area of adaptive filtering. Grouping components in the sparse vector has been validated to be an efficient way for enhancing identification performance for sparse parameter. The technique of pairwise fused lasso, which can promote similarity between each possible pair of nonnegligible components in the sparse vector, does not require that the nonnegligible components have to be distributed in one or multiple clusters. In other words, the nonnegligible components may be randomly scattered in the unknown sparse vector. In this article, based on the technique of pairwise fused lasso, we propose the novel pairwise fused lasso diffusion least mean-square (PFL-DLMS) algorithm, to identify sparse vector. The objective function we construct consists of three terms, i.e., the mean-square error (MSE) term, the regularizing term promoting the sparsity of all components, and the regularizing term promoting the sparsity of difference between each pair of components in the unknown sparse vector. After investigating mean stability condition of mean-square behavior in theoretical analysis, we propose the strategy of variable regularizing coefficients to overcome the difficulty that the optimal regularizing coefficients are usually unknown. Finally, numerical experiments are conducted to verify the effectiveness of the PFL-DLMS algorithm in identifying and tracking sparse parameter vector.

CASF-Net: Cross-attention and cross-scale fusion network for medical image segmentation.

BACKGROUND: Automatic segmentation of medical images has progressed greatly owing to the development of convolutional neural networks (CNNs). However, there are two uncertainties with current approaches based on convolutional operations: (1) how to eliminate the general limitations that CNNs lack the ability of modeling long-range dependencies and global contextual interactions, and (2) how to efficiently discover and integrate global and local features that are implied in the image. Notably, these two problems are interconnected, yet previous approaches mainly focus on the first problem and ignore the importance of information integration. METHODS: In this paper, we propose a novel cross-attention and cross-scale fusion network (CASF-Net), which aims to explicitly tap the potential of dual-branch networks and fully integrate the coarse and fine-grained feature representations. Specifically, the well-designed dual-branch encoder hammers at modeling non-local dependencies and multi-scale contexts, significantly improving the quality of semantic segmentation. Moreover, the proposed cross-attention and cross-scale module efficiently perform multi-scale information fusion, being capable of further exploring the long-range contextual information. RESULTS: Extensive experiments conducted on three different types of medical image segmentation tasks demonstrate the state-of-the-art performance of our proposed method both visually and numerically. CONCLUSIONS: This paper assembles the feature representation capabilities of CNN and transformer and proposes cross-attention and cross-scale fusion algorithms. The promising results show new possibilities of using cross-fusion mechanisms in more downstream medical image tasks.

The natural course of bacillus Calmette-Guérin induced bladder lesions: A long-term follow-up study and systematic review.

Objective: Bacillus Calmette-Guérin (BCG) instillation is the standard adjuvant treatment for intermediate- and high-risk non-muscle-invasive bladder cancer after transurethral resection. Nevertheless, its toxicity often causes bladder complications. On follow-up cystoscopy, post-BCG bladder lesions can be pathologically benign, urothelial carcinoma recurrence, or other types of bladder malignancy. Only a small number of case reports have been published on post-BCG bladder lesions. Their clinical features, natural course, and management remain unknown. Methods: We retrospectively studied cystoscopic videos and medical records of BCG-treated bladder cancer patients at our center. During a long-term follow-up, we took biopsies on tumor-like lesions and described their changes. In addition, we summarized previous studies on post-BCG bladder lesions by systematic literature searching and review. Results: We described a series of three cases with post-BCG bladder lesions mimicking tumor recurrence from a total of 38 cases with follow-up data for more than 5 years. Those lesions could last, grow, or disappear spontaneously, and remain pathological benign for years. In systematic review, we identified and analyzed a total of 15 cases with post-BCG bladder lesions with detailed clinical information. Eleven of the 15 were benign and have a good prognosis with nephrogenic adenoma being the most common pathological type. Conclusion: Based on previous studies and our experience, benign lesions after BCG instillation cannot distinguish with cancer recurrence by cystoscopy alone, even under narrow band imaging mode. Nonetheless, given most of them have a good prognosis, random biopsy or transurethral resection might be spared in the patients with long-term negative biopsy and urine cytology.