Prediction of Urban Taxi Travel Demand by Using Hybrid Dynamic Graph Convolutional Network Model.

The efficient and accurate prediction of urban travel demand, which is a hot topic in intelligent transportation research, is challenging due to its complicated spatial-temporal dependencies, dynamic nature, and uneven distribution. Most existing forecasting methods merely considered the static spatial dependencies while ignoring the influence of the diversity of dynamic demand patterns and/or uneven distribution. In this paper, we propose a traffic demand forecasting framework of a hybrid dynamic graph convolutional network (HDGCN) model to deeply capture the characteristics of urban travel demand and improve prediction accuracy. In HDGCN, traffic flow similarity graphs are designed according to the dynamic nature of travel demand, and a dynamic graph sequence is generated according to time sequence. Then, the dynamic graph convolution module and the standard graph convolution module are introduced to extract the spatial features from dynamic graphs and static graphs, respectively. Finally, the spatial features of the two components are fused and combined with the gated recurrent unit (GRU) to learn the temporal features. The efficiency and accuracy of the HDGCN model in predicting urban taxi travel demand are verified by using the taxi data from Manhattan, New York City. The modeling and comparison results demonstrate that the HDGCN model can achieve stable and effective prediction for taxi travel demand compared with the state-of-the-art baseline models. The proposed model could be used for the real-time, accurate, and efficient travel demand prediction of urban taxi and other urban transportation systems.

Extension of the Generalized Hydrodynamics to the Dimensional Crossover Regime.

In an effort to address integrability breaking in cold gas experiments, we extend the integrable hydrodynamics of the Lieb-Liniger model with two additional components representing the population of atoms in the first and second transverse excited states, thus enabling a description of quasi-1D condensates. Collisions between different components are accounted for through the inclusion of a Boltzmann-type collision integral in the hydrodynamic equation. Contrary to standard generalized hydrodynamics, our extended model captures thermalization of the condensate at a rate consistent with experimental observations from a quantum Newton's cradle setup.

The Inability of the Choroid to Revascularize in Oxygen-Induced Retinopathy Results from Increased p53/miR-Let-7b Activity.

Retinopathy of prematurity (ROP) is characterized by an initial retinal avascularization, followed by pathologic neovascularization. Recently, choroidal thinning has also been detected in children formerly diagnosed with ROP; a similar sustained choroidal thinning is observed in ROP models. But the mechanism underlying the lack of choroidal revascularization remains unclear and was investigated in an oxygen-induced retinopathy (OIR) model. In OIR, evidence of senescence was detected, preceded by oxidative stress in the choroid and the retinal pigment epithelium. This was associated with a global reduction of proangiogenic factors, including insulin-like growth factor 1 receptor (Igf1R). Coincidentally, tumor suppressor p53 was highly expressed in the OIR retinae. Curtailing p53 activity resulted in reversal of senescence, normalization of Igf1r expression, and preservation of choroidal integrity. OIR-induced down-regulation of Igf1r was mediated at least partly by miR-let-7b as i) let-7b expression was augmented throughout and beyond the period of oxygen exposure, ii) let-7b directly targeted Igf1r mRNA, and iii) p53 knock-down blunted let-7b expression, restored Igf1r expression, and elicited choroidal revascularization. Finally, restoration of Igf1r expression rescued choroid thickness. Altogether, this study uncovers a significant mechanism for defective choroidal revascularization in OIR, revealing a new role for p53/let-7b/IGF-1R axis in the retina. Future investigations on this (and connected) pathway could further our understanding of other degenerative choroidopathies, such as geographic atrophy.

Overview of the Canadian Clinician Investigator Trainees' research presented at the 2019 CSCI-CITAC Joint Meeting.

The 2019 Annual General Meeting and Young Investigators' Forum of the Canadian Society for Clinical Investigation / Société Canadienne de Recherche Clinique (CSCI/SCRC) and Clinician Investigator Trainee Association of Canada / Association des Cliniciens-Chercheurs en Formation du Canada (CITAC/ACCFC) was held in Banff, Alberta on November 8-10th, 2019. The theme was "Positioning Early Career Investigators for Success: Strategy and Resilience". Lectures and workshops provided knowledge and tools to facilitate the attendees' development as clinician investigators. Dr. Jason Berman (President of CSCI/SCRC), Elina Cook (President of CITAC/ACCFC) and Drs. Doreen Rabi and Zelma Kiss (University of Calgary Organizing Co-Chairs) gave opening presentations. The keynote speakers were Dr. William Foulkes (McGill University) (Distinguished Scientist Award winner) and Dr. Andrés Finzi (Université de Montréal) (Joe Doupe Young Investigator Award winner). Dr. Robert Bortolussi (Dalhousie University) received the Distinguished Service Award for his work as the Editor-in-Chief of Clinical and Investigative Medicine and for being instrumental in the development of the Canadian Child Health Clinician Scientist Program. This meeting was the first to host a panel discussion with Drs. Stephen Robbins and Marcello Tonelli from the Canadian Institutes of Health Research. Workshops on communication, career planning and work-life balance were hosted by André Picard and Drs. Todd Anderson, Karen Tang, William Ghali, May Lynn Quan, Alicia Polachek and Shannon Ruzycki. The AGM showcased 90 presentations from clinician investigator trainees from across Canada. Most of the abstracts are summarized in this review. Eight outstanding abstracts were selected for oral presentation at the President's Forum.

The Vision Health Research Network and its commitment to the scholarly development of its trainees.

The Vision Health Research Network (VHRN) is a provincial scientific organization that aims to improve the ocular health of patients across Quebec by supporting local research endeavors in vision health. The VHRN Student Committee, composed of 288 trainees with diverse backgrounds, has demonstrated its commitment to the scholarly development of its members by providing leadership opportunities, creating networking events, increasing visibility of researchers-in-training and encouraging professional advancement through educational workshops and funding programs. In this article, we review the contributions of the VHRN Student Committee and discuss its future projects.

High precision calibration of optical lattice depth based on multiple pulses Kapitza-Dirac diffraction.

The precise calibration of optical lattice depth is an important step in the experiments of ultracold atoms in optical lattices. The Raman-Nath diffraction method, as the most commonly used method of calibrating optical lattice depth, has a limited range of validity and the calibration accuracy is not high enough. Based on multiple pulses Kapitza-Dirac diffraction, we propose and demonstrate a new calibration method by measuring the fully transfer fidelity of the first diffraction order. The high sensitivity of the transfer fidelity to the lattice depth ensures the highly precision calibration of the optical lattice depth. For each lattice depth measured, the calibration uncertainty is further reduced to less than 0.6% by applying the Back-Propagation Neural Network Algorithm. The accuracy of this method is almost one order of magnitude higher than that of the Raman-Nath diffraction method, and it has a wide range of validity applicable to both shallow lattices and deep lattices.

Newsletter 2018: Clinician Investigator Trainee Association of Canada (CITAC).

A decade of CITAC Annual General Meetings: 2007-2017 In 2007, the Clinician Investigator Trainee Association of Canada (CITAC) launched its inaugural Annual General Meeting (AGM). The AGM has since become a major annual event, jointly organized by CITAC and leaders from the Canadian Society for Clinical Investigation (CSCI), and continues to provide a forum for clinician investigator (CI) trainees to exchange ideas, advance career prospects and engage with the broader community. Indeed, since its inception, all Canadian institutions with medical doctor and clinician investigator (MD+CI) training programs have participated in the AGM, while more than 1,000 trainees have registered as CITAC members. The 10th CITAC-CSCI AGM was recently held in Toronto (November 20-22, 2017). There were nearly 200 attendees, including CI trainees, faculty member and physician leaders from across Canada (Figure 1A, 1B). Trainees spanning diverse career stages had opportunities to participate in interactive poster sessions, workshops and lectures by leading physician-scientists. These exercises were designed to encourage and enhance networking, career development and mentorship for prospective physician-scientists.

Retinopathy of prematurity: inflammation, choroidal degeneration, and novel promising therapeutic strategies.

Retinopathy of prematurity (ROP) is an important cause of childhood blindness globally, and the incidence is rising. The disease is characterized by initial arrested retinal vascularization followed by neovascularization and ensuing retinal detachment causing permanent visual loss. Although neovascularization can be effectively treated via retinal laser ablation, it is unknown which children are at risk of entering this vision-threatening phase of the disease. Laser ablation may itself induce visual field deficits, and there is therefore a need to identify targets for novel and less destructive treatments of ROP. Inflammation is considered a key contributor to the pathogenesis of ROP. A large proportion of preterm infants with ROP will have residual visual loss linked to loss of photoreceptor (PR) and the integrity of the retinal pigment epithelium (RPE) in the macular region. Recent studies using animal models of ROP suggest that choroidal degeneration may be associated with a loss of integrity of the outer retina, a phenomenon so far largely undescribed in ROP pathogenesis. In this review, we highlight inflammatory and neuron-derived factors related to ROP progression, as well, potential targets for new treatment strategies. We also introduce choroidal degeneration as a significant cause of residual visual loss following ROP. We propose that ROP should no longer be considered an inner retinal vasculopathy only, but also a disease of choroidal degeneration affecting both retinal pigment epithelium and photoreceptor integrity.

Choroidal Involution Is Associated with a Progressive Degeneration of the Outer Retinal Function in a Model of Retinopathy of Prematurity: Early Role for IL-1ß.

Retinopathy of prematurity (ROP), the most common cause of blindness in premature infants, has long been associated with inner retinal alterations. However, recent studies reveal outer retinal dysfunctions in patients formerly afflicted with ROP. We have recently demonstrated that choroidal involution occurs early in retinopathy. Herein, we investigated the mechanisms underlying the choroidal involution and its long-term impact on retinal function. An oxygen-induced retinopathy (OIR) model was used. In vitro and ex vivo assays were applied to evaluate cytotoxic effects of IL-1ß on choroidal endothelium. Electroretinogram was used to evaluate visual function. We found that proinflammatory IL-1ß was markedly increased in retinal pigment epithelium (RPE)/choroid and positively correlated with choroidal degeneration in the early stages of retinopathy. IL-1ß was found to be cytotoxic to choroid in vitro, ex vivo, and in vivo. Long-term effects on choroidal involution included a hypoxic outer neuroretina, associated with a progressive loss of RPE and photoreceptors, and visual deterioration. Early inhibition of IL-1ß receptor preserved choroid, decreased subretinal hypoxia, and prevented RPE/photoreceptor death, resulting in life-long improved visual function in IL-1 receptor antagonist-treated OIR animals. Together, these findings suggest a critical role for IL-1ß-induced choroidal degeneration in outer retinal dysfunction. Neonatal therapy using IL-1 receptor antagonist preserves choroid and prevents protracted outer neuroretinal anomalies in OIR, suggesting IL-1ß as a potential therapeutic target in ROP.

Training the next generation of Canadian Clinician-Scientists: charting a path to success.

Clinician-scientists are physicians with training in both clinical medicine and research that enables them to occupy a unique niche as specialists in basic and translational biomedical research. While there is widespread acknowledgement of the importance of clinician-scientists in today's landscape of evidence-based medical practice, training of clinician-scientists in Canada has been on the decline, with fewer opportunities to obtain funding. With the increasing length of training and lower financial compensation, fewer medical graduates are choosing to pursue such a career. MD-PhD programs, in which trainees receive both medical and research training, have the potential to be an important tool in training the next generation of clinician-scientists; however, MD-PhD trainees in Canada face barriers that include an increase in medical school tuition and a decrease in the amount of financial support. We examined the available data on MD-PhD training in Canada and identified a lack of oversight, a lack of funding and poor mentorship as barriers experienced by MD-PhD trainees. Specific recommendations are provided to begin the process of addressing these challenges, starting with the establishment of an overseeing national body that would track long-term outcome data for MD-PhD trainees. This national body could then function to implement best practices from individual programs across the country and to provide further mentorship and support for early-career physician-scientists. MD-PhD programs have the potential to address Canada's growing shortage of clinician-scientists, and strengthening MD-PhD programs will help to effect positive change.

Scientific Overview on CSCI-CITAC Annual General Meeting and 2016 Young Investigators' Forum.

The 2016 Annual General Meeting of the Canadian Society of Clinician Investigators (CSCI) and Clinician Investigator Trainee Association of Canada/Association des Cliniciens-Chercheurs en Formation du Canada (CITAC/ACCFC) was a national conference held in Toronto November 21-23, 2016, in conjunction with The University of Toronto Clinician Investigator Program Research Day. The theme for this year's meeting was "Mapping Your Career as a Clinician-Scientist"; emphasizing essential skills for developing a fruitful career as clinician-scientist. The meeting featured an opening presentation by Dr. Alan Underhill, Dr. Nicola Jones and Alexandra Kuzyk. The keynote speakers were Dr. Nada Jabado (McGill University), who discussed the association between cancer and histones, Dr. Norman Rosenblum (University of Toronto), who addressed the career path and the "calling" of the Clinician Scientist, Dr. Martin Schmeing (McGill University), who was the 2016 Joe Doupe Award recipient, and Dr. Linda Rabeneck (Cancer Care Ontario and University of Toronto), who received the Friends of CIHR lectureship. The workshops, focusing on career development for clinician scientists, were hosted by Drs. Alan Underhill, Nicola Jones, Lynn Raymond, Michael Schlossmacher and Norman Rosenblum, as well as University of Toronto communication specialists, Caitlin Johannesson and Suzanne Gold. In addition, the Young Investigators' Forum included presentations from clinician investigator trainees from across the country. The research topics were diverse and comprehensive: from basic sciences to clinical practice; from epidemiology to medical engineering. All scientific abstracts are summarized in this review. Over 70 abstracts were showcased at this year's meeting during two poster sessions, with six outstanding abstracts selected for oral presentations during the President's Forum.

Scientific Overview: CSCI-CITAC Annual General Meeting and Young Investigators' Forum 2015.

The 2015 Annual General Meeting of The Canadian Society of Clinician Investigators (CSCI) and Clinician Investigator Trainee Association of Canada/Association des Cliniciens-Chercheurs en Formation du Canada (CITAC/ACCFC) was held in Toronto November 23-25, 2015, in conjunction with The University of Toronto Clinician Investigator Program Research Day. The theme for this year's meeting was "It takes a village" and the focus was the various support systems necessary to train a successful clinician scientist. The meeting featured an opening presentation by Dr. Vincent Dumez and workshops by Dr. Peter Nickerson, Dr. Jane Aubin, Dr. Kelly Warmington and Dr. Norman Rosenblum, and MD/PhD trainees Nardin Samuel, Kevin Wang and Kirill Zaslavsky. The keynote speakers were Dr. David Malkin (Hospital for Sick Children) who received the CSCI-RCPSC Henry Friesen Award, Dr. Brent Richards (McGill University) who received the Joe Doupe Award and Ernesto Shiffrin (Lady Davis Institute) who received the Distinguished Scientist Award. As always, the conference showcased outstanding scientific presentations from clinician investigator trainees from across the country at the Young Investigators' Forum. The research topics, which ranged from basic sciences to clinical medicine and translational work, are summarized in this review. Over 90 abstracts were presented at this year's meeting during two poster sessions, with several of the outstanding abstracts selected for oral presentations.

Review of the mechanisms and therapeutic avenues for retinal and choroidal vascular dysfunctions in retinopathy of prematurity.

Retinopathy of prematurity (ROP) is a multifactorial disease and the main cause of visual impairment and blindness in premature neonates. The inner retina has been considered the primary region affected in ROP, but choroidal vascular degeneration and progressive outer retinal dysfunctions have also been observed. This review focuses on observations regarding neurovascular dysfunctions in both the inner and outer immature retina, the mechanisms and the neuronal-derived factors implicated in the development of ROP, as well potential therapeutic avenues for this disorder. CONCLUSION: Alterations in the neurovascular integrity of the inner and outer retina contribute to the development of ROP.

G-protein-coupled receptor 91 and succinate are key contributors in neonatal postcerebral hypoxia-ischemia recovery.

OBJECTIVE: Prompt post-hypoxia-ischemia (HI) revascularization has been suggested to improve outcome in adults and newborn subjects. Other than hypoxia-inducible factor, sensors of metabolic demand remain largely unknown. During HI, anaerobic respiration is arrested resulting in accumulation of carbohydrate metabolic intermediates. As such succinate readily increases, exerting its biological effects via a specific receptor, G-protein-coupled receptor (GPR) 91. We postulate that succinate/GPR91 enhances post-HI vascularization and reduces infarct size in a model of newborn HI brain injury. APPROACH AND RESULTS: The Rice-Vannucci model of neonatal HI was used. Succinate was measured by mass spectrometry, and microvascular density was evaluated by quantification of lectin-stained cryosection. Gene expression was evaluated by real-time polymerase chain reaction. Succinate levels rapidly increased in the penumbral region of brain infarcts. GPR91 was foremost localized not only in neurons but also in astrocytes. Microvascular density increased at 96 hours after injury in wild-type animals; it was diminished in GPR91-null mice leading to an increased infarct size. Stimulation with succinate led to an increase in growth factors implicated in angiogenesis only in wild-type mice. To explain the mode of action of succinate/GPR91, we investigated the role of prostaglandin E2-prostaglandin E receptor 4, previously proposed in neural angiogenesis. Succinate-induced vascular endothelial growth factor expression was abrogated by a cyclooxygenase inhibitor and a selective prostaglandin E receptor 4 antagonist. This antagonist also abolished succinate-induced neovascularization. CONCLUSIONS: We uncover a dominant metabolic sensor responsible for post-HI neurovascular adaptation, notably succinate/GPR91, acting via prostaglandin E2-prostaglandin E receptor 4 to govern expression of major angiogenic factors. We propose that pharmacological intervention targeting GPR91 could improve post-HI brain recovery.

Microglia and interleukin-1ß in ischemic retinopathy elicit microvascular degeneration through neuronal semaphorin-3A.

OBJECTIVE: Proinflammatory cytokines contribute to the development of retinal vasculopathies. However, the role of these factors and the mechanisms by which they elicit their effects in retina are not known. We investigated whether activated microglia during early stages of ischemic retinopathy produces excessive interleukin-1ß (IL-1ß), which elicits retinal microvascular degeneration not directly but rather by triggering the release of the proapoptotic/repulsive factor semaphorin-3A (Sema3A) from neurons. APPROACH AND RESULTS: Sprague Dawley rats subjected to retinopathy induced by hyperoxia (80% O2; O2-induced retinopathy) exhibited retinal vaso-obliteration associated with microglial activation, NLRP3 upregulation, and IL-1ß and Sema3A release; IL-1ß was mostly generated by microglia. Intraperitoneal administration of IL-1 receptor antagonists (Kineret, or rytvela [101.10]) decreased these effects and enhanced retinal revascularization; knockdown of Sema3A resulted in microvessel preservation and, conversely, administration of IL-1ß caused vaso-obliteration. In vitro, IL-1ß derived from activated primary microglial cells, cultured under hyperoxia, stimulated the release of Sema3A in retinal ganglion cells-5, which in turn induced apoptosis of microvascular endothelium; antagonism of IL-1 receptor decreased microglial activation and on retinal ganglion cells-5 abolished the release of Sema3A inhibiting ensuing endothelial cell apoptosis. IL-1ß was not directly cytotoxic to endothelial cells. CONCLUSIONS: Our findings suggest that in the early stages of O2-induced retinopathy, retinal microglia are activated to produce IL-1ß, which sustains the activation of microglia and induces microvascular injury through the release of Sema3A from adjacent neurons. Interference with IL-1 receptor or Sema3A actions preserves the microvascular bed in ischemic retinopathies and, consequently, decreases ensued pathological preretinal neovascularization.

Subjective and Objective Quality Assessment of Colonoscopy Videos.

Captured colonoscopy videos usually suffer from multiple real-world distortions, such as motion blur, low brightness, abnormal exposure, and object occlusion, which impede visual interpretation. However, existing works mainly investigate the impacts of synthesized distortions, which differ from real-world distortions greatly. This research aims to carry out an in-depth study for colonoscopy Video Quality Assessment (VQA). In this study, we advance this topic by establishing both subjective and objective solutions. Firstly, we collect 1,000 colonoscopy videos with typical visual quality degradation conditions in practice and construct a multi-attribute VQA database. The quality of each video is annotated by subjective experiments from five distortion attributes (i.e., temporal-spatial visibility, brightness, specular reflection, stability, and utility), as well as an overall perspective. Secondly, we propose a Distortion Attribute Reasoning Network (DARNet) for automatic VQA. DARNet includes two streams to extract features related to spatial and temporal distortions, respectively. It adaptively aggregates the attribute-related features through a multi-attribute association module to predict the quality score of each distortion attribute. Motivated by the observation that the rating behaviors for all attributes are different, a behavior guided reasoning module is further used to fuse the attribute-aware features, resulting in the overall quality. Experimental results on the constructed database show that our DARNet correlates well with subjective ratings and is superior nine state-of-the-art methods.

Boundary uncertainty aware network for automated polyp segmentation.

Recently, leveraging deep neural networks for automated colorectal polyp segmentation has emerged as a hot topic due to the favored advantages in evading the limitations of visual inspection, e.g., overwork and subjectivity. However, most existing methods do not pay enough attention to the uncertain areas of colonoscopy images and often provide unsatisfactory segmentation performance. In this paper, we propose a novel boundary uncertainty aware network (BUNet) for precise and robust colorectal polyp segmentation. Specifically, considering that polyps vary greatly in size and shape, we first adopt a pyramid vision transformer encoder to learn multi-scale feature representations. Then, a simple yet effective boundary exploration module (BEM) is proposed to explore boundary cues from the low-level features. To make the network focus on the ambiguous area where the prediction score is biased to neither the foreground nor the background, we further introduce a boundary uncertainty aware module (BUM) that explores error-prone regions from the high-level features with the assistance of boundary cues provided by the BEM. Through the top-down hybrid deep supervision, our BUNet implements coarse-to-fine polyp segmentation and finally localizes polyp regions precisely. Extensive experiments on five public datasets show that BUNet is superior to thirteen competing methods in terms of both effectiveness and generalization ability.

Histological changes in retinal detachment: A systematic review for the clinician.

Although there have been numerous innovations in the management of retinal detachment (RD) over the past decades, there is still limited understanding of the pathophysiological processes that take place before and after repair. Summarizing key concepts using animal studies may allow for a better assessment of common pre- and postoperative microstructural abnormalities in RD. We performed a systematic literature review on Ovid MEDLINE, EMBASE, and Cochrane Controlled Register of Trials from January 1968 to January 2022, searching animal or human studies reporting retinal histologic changes following primary or induced RD. Thirty-two studies were included. Main cellular events were summarized: photoceptor apoptosis occurs as early as 12 hours after RD and, although most cells survive, there is extensive remodeling. Outer segments progressively degenerate, while inner segments are reorganized. Rod and cone opsins are redistributed, and rod axons retract while cones undergo changes in shape. Second- and third-order neurons rearrange their dendritic processes, and Müller cells become hypertrophic, growing into the subretinal space. Finally, retinal pigment epithelium cells undergo a change in their morphology. Acknowledging critical morphologic changes following RD is crucial in understanding why anatomical and functional outcomes can vary. Insights from histological studies, together with high-resolution imaging, may be key in identifying novel biomarkers in RD.

Toward Multicenter Skin Lesion Classification Using Deep Neural Network With Adaptively Weighted Balance Loss.

Recently, deep neural network-based methods have shown promising advantages in accurately recognizing skin lesions from dermoscopic images. However, most existing works focus more on improving the network framework for better feature representation but ignore the data imbalance issue, limiting their flexibility and accuracy across multiple scenarios in multi-center clinics. Generally, different clinical centers have different data distributions, which presents challenging requirements for the network's flexibility and accuracy. In this paper, we divert the attention from framework improvement to the data imbalance issue and propose a new solution for multi-center skin lesion classification by introducing a novel adaptively weighted balance (AWB) loss to the conventional classification network. Benefiting from AWB, the proposed solution has the following advantages: 1) it is easy to satisfy different practical requirements by only changing the backbone; 2) it is user-friendly with no tuning on hyperparameters; and 3) it adaptively enables small intraclass compactness and pays more attention to the minority class. Extensive experiments demonstrate that, compared with solutions equipped with state-of-the-art loss functions, the proposed solution is more flexible and more competent for tackling the multi-center imbalanced skin lesion classification task with considerable performance on two benchmark datasets. In addition, the proposed solution is proved to be effective in handling the imbalanced gastrointestinal disease classification task and the imbalanced DR grading task. Code is available at https://github.com/Weipeishan2021.

Adaptive Cross-Feature Fusion Network With Inconsistency Guidance for Multi-Modal Brain Tumor Segmentation.

In the context of contemporary artificial intelligence, increasing deep learning (DL) based segmentation methods have been recently proposed for brain tumor segmentation (BraTS) via analysis of multi-modal MRI. However, known DL-based works usually directly fuse the information of different modalities at multiple stages without considering the gap between modalities, leaving much room for performance improvement. In this paper, we introduce a novel deep neural network, termed ACFNet, for accurately segmenting brain tumor in multi-modal MRI. Specifically, ACFNet has a parallel structure with three encoder-decoder streams. The upper and lower streams generate coarse predictions from individual modality, while the middle stream integrates the complementary knowledge of different modalities and bridges the gap between them to yield fine prediction. To effectively integrate the complementary information, we propose an adaptive cross-feature fusion (ACF) module at the encoder that first explores the correlation information between the feature representations from upper and lower streams and then refines the fused correlation information. To bridge the gap between the information from multi-modal data, we propose a prediction inconsistency guidance (PIG) module at the decoder that helps the network focus more on error-prone regions through a guidance strategy when incorporating the features from the encoder. The guidance is obtained by calculating the prediction inconsistency between upper and lower streams and highlights the gap between multi-modal data. Extensive experiments on the BraTS 2020 dataset show that ACFNet is competent for the BraTS task with promising results and outperforms six mainstream competing methods.