M2: Mixed Models With Preferences, Popularities and Transitions for Next-Basket Recommendation.

Next-basket recommendation considers the problem of recommending a set of items into the next basket that users will purchase as a whole. In this paper, we develop a novel mixed model with preferences, popularities and transitions (M2) for the next-basket recommendation. This method models three important factors in next-basket generation process: 1) users' general preferences, 2) items' global popularities and 3) transition patterns among items. Unlike existing recurrent neural network-based approaches, M2 does not use the complicated networks to model the transitions among items, or generate embeddings for users. Instead, it has a simple encoder-decoder based approach (ed-Trans) to better model the transition patterns among items. We compared M2 with different combinations of the factors with 5 state-of-the-art next-basket recommendation methods on 4 public benchmark datasets in recommending the first, second and third next basket. Our experimental results demonstrate that M2 significantly outperforms the state-of-the-art methods on all the datasets in all the tasks, with an improvement of up to 22.1%. In addition, our ablation study demonstrates that the ed-Trans is more effective than recurrent neural networks in terms of the recommendation performance. We also have a thorough discussion on various experimental protocols and evaluation metrics for next-basket recommendation evaluation.

U-Net: A valuable encoder-decoder architecture for liver tumors segmentation in CT images.

This study proposes a new predictive segmentation method for liver tumors detection using computed tomography (CT) liver images. In the medical imaging field, the exact localization of metastasis lesions after acquisition faces persistent problems both for diagnostic aid and treatment effectiveness. Therefore, the improvement in the diagnostic process is substantially crucial in order to increase the success chance of the management and the therapeutic follow-up. The proposed procedure highlights a computerized approach based on an encoder-decoder structure in order to provide volumetric analysis of pathologic tumors. Specifically, we developed an automatic algorithm for the liver tumors defect segmentation through the Seg-Net and U-Net architectures from metastasis CT images. In this study, we collected a dataset of 200 pathologically confirmed metastasis cancer cases. A total of 8,297 CT image slices of these cases were used developing and optimizing the proposed segmentation architecture. The model was trained and validated using 170 and 30 cases or 85% and 15% of the CT image data, respectively. Study results demonstrate the strength of the proposed approach that reveals the superlative segmentation performance as evaluated using following indices including F1-score = 0.9573, Recall = 0.9520, IOU = 0.9654, Binary cross entropy = 0.0032 and p-value <0.05, respectively. In comparison to state-of-the-art techniques, the proposed method yields a higher precision rate by specifying metastasis tumor position.

Autosegmentation of Prostate Zones and Cancer Regions from Biparametric Magnetic Resonance Images by Using Deep-Learning-Based Neural Networks.

The accuracy in diagnosing prostate cancer (PCa) has increased with the development of multiparametric magnetic resonance imaging (mpMRI). Biparametric magnetic resonance imaging (bpMRI) was found to have a diagnostic accuracy comparable to mpMRI in detecting PCa. However, prostate MRI assessment relies on human experts and specialized training with considerable inter-reader variability. Deep learning may be a more robust approach for prostate MRI assessment. Here we present a method for autosegmenting the prostate zone and cancer region by using SegNet, a deep convolution neural network (DCNN) model. We used PROSTATEx dataset to train the model and combined different sequences into three channels of a single image. For each subject, all slices that contained the transition zone (TZ), peripheral zone (PZ), and PCa region were selected. The datasets were produced using different combinations of images, including T2-weighted (T2W) images, diffusion-weighted images (DWI) and apparent diffusion coefficient (ADC) images. Among these groups, the T2W + DWI + ADC images exhibited the best performance with a dice similarity coefficient of 90.45% for the TZ, 70.04% for the PZ, and 52.73% for the PCa region. Image sequence analysis with a DCNN model has the potential to assist PCa diagnosis.

Deep Learning-Based Feature Silencing for Accurate Concrete Crack Detection.

An autonomous concrete crack inspection system is necessary for preventing hazardous incidents arising from deteriorated concrete surfaces. In this paper, we present a concrete crack detection framework to aid the process of automated inspection. The proposed approach employs a deep convolutional neural network architecture for crack segmentation, while addressing the effect of gradient vanishing problem. A feature silencing module is incorporated in the proposed framework, capable of eliminating non-discriminative feature maps from the network to improve performance. Experimental results support the benefit of incorporating feature silencing within a convolutional neural network architecture for improving the network's robustness, sensitivity, and specificity. An added benefit of the proposed architecture is its ability to accommodate for the trade-off between specificity (positive class detection accuracy) and sensitivity (negative class detection accuracy) with respect to the target application. Furthermore, the proposed framework achieves a high precision rate and processing time than the state-of-the-art crack detection architectures.

Coarse-to-Fine Satellite Images Change Detection Framework via Boundary-Aware Attentive Network.

Timely and accurate change detection on satellite images by using computer vision techniques has been attracting lots of research efforts in recent years. Existing approaches based on deep learning frameworks have achieved good performance for the task of change detection on satellite images. However, under the scenario of disjoint changed areas in various shapes on land surface, existing methods still have shortcomings in detecting all changed areas correctly and representing the changed areas boundary. To deal with these problems, we design a coarse-to-fine detection framework via a boundary-aware attentive network with a hybrid loss to detect the change in high resolution satellite images. Specifically, we first perform an attention guided encoder-decoder subnet to obtain the coarse change map of the bi-temporal image pairs, and then apply residual learning to obtain the refined change map. We also propose a hybrid loss to provide the supervision from pixel, patch, and map levels. Comprehensive experiments are conducted on two benchmark datasets: LEBEDEV and SZTAKI to verify the effectiveness of the proposed method and the experimental results show that our model achieves state-of-the-art performance.

Optical Coherence Tomography Vulnerable Plaque Segmentation Based on Deep Residual U-Net.

Automatic and accurate segmentation of intravascular optical coherence tomography imagery is of great importance in computer-aided diagnosis and in treatment of cardiovascular diseases. However, this task has not been well addressed for two reasons. First, because of the difficulty of acquisition, and the laborious labeling from personnel, optical coherence tomography image datasets are usually small. Second, optical coherence tomography images contain a variety of imaging artifacts, which hinder a clear observation of the vascular wall. In order to overcome these limitations, a new method of cardiovascular vulnerable plaque segmentation is proposed. This method constructs a novel Deep Residual U-Net to segment vulnerable plaque regions. Furthermore, in order to overcome the inaccuracy in object boundary segmentation which previous research has shown extensively, a loss function consisting of weighted cross-entropy loss and Dice coefficient is proposed to solve this problem. Thorough experiments and analysis have been carried out to verify the effectiveness and superior performance of the proposed method.

HCS-Net: Multi-level deformation strategy combined with quadruple attention for image registration.

BACKGROUND AND OBJECTIVE: Non-rigid image registration plays a significant role in computer-aided diagnosis and surgical navigation for brain diseases. Registration methods that utilize convolutional neural networks (CNNs) have shown excellent accuracy when applied to brain magnetic resonance images (MRI). However, CNNs have limitations in understanding long-range spatial relationships in images, which makes it challenging to incorporate contextual information. And in intricate image registration tasks, it is difficult to achieve a satisfactory dense prediction field, resulting in poor registration performance. METHODS: This paper proposes a multi-level deformable unsupervised registration model that combines Transformer and CNN to achieve non-rigid registration of brain MRI. Firstly, utilizing a dual encoder structure to establish the dependency relationship between the global features of two images and to merge features of varying scales, as well as to preserve the relative spatial position information of feature maps at different scales. Then the proposed multi-level deformation strategy utilizes different deformable fields of varying resolutions generated by the decoding structure to progressively deform the moving image. Ultimately, the proposed quadruple attention module is incorporated into the decoding structure to merge feature information from various directions and emphasize the spatial features in the dominant channels. RESULTS: The experimental results on multiple brain MR datasets demonstrate that the promising network could provide accurate registration and is comparable to state-of-the-art methods. CONCLUSION: The proposed registration model can generate superior deformable fields and achieve more precise registration effects, enhancing the auxiliary role of medical image registration in various fields and advancing the development of computer-aided diagnosis, surgical navigation, and related domains.

HEDN: multi-oriented hierarchical extraction and dual-frequency decoupling network for 3D medical image segmentation.

Previous 3D encoder-decoder segmentation architectures struggled with fine-grained feature decomposition, resulting in unclear feature hierarchies when fused across layers. Furthermore, the blurred nature of contour boundaries in medical imaging limits the focus on high-frequency contour features. To address these challenges, we propose a Multi-oriented Hierarchical Extraction and Dual-frequency Decoupling Network (HEDN), which consists of three modules: Encoder-Decoder Module (E-DM), Multi-oriented Hierarchical Extraction Module (Multi-HEM), and Dual-frequency Decoupling Module (Dual-DM). The E-DM performs the basic encoding and decoding tasks, while Multi-HEM decomposes and fuses spatial and slice-level features in 3D, enriching the feature hierarchy by weighting them through 3D fusion. Dual-DM separates high-frequency features from the reconstructed network using self-supervision. Finally, the self-supervised high-frequency features separated by Dual-DM are inserted into the process following Multi-HEM, enhancing interactions and complementarities between contour features and hierarchical features, thereby mutually reinforcing both aspects. On the Synapse dataset, HEDN outperforms existing methods, boosting Dice Similarity Score (DSC) by 1.38% and decreasing 95% Hausdorff Distance (HD95) by 1.03 mm. Likewise, on the Automatic Cardiac Diagnosis Challenge (ACDC) dataset, HEDN achieves  0.5% performance gains across all categories.

Adaptive Feature Medical Segmentation Network: an adaptable deep learning paradigm for high-performance 3D brain lesion segmentation in medical imaging.

Introduction: In neurological diagnostics, accurate detection and segmentation of brain lesions is crucial. Identifying these lesions is challenging due to its complex morphology, especially when using traditional methods. Conventional methods are either computationally demanding with a marginal impact/enhancement or sacrifice fine details for computational efficiency. Therefore, balancing performance and precision in compute-intensive medical imaging remains a hot research topic. Methods: We introduce a novel encoder-decoder network architecture named the Adaptive Feature Medical Segmentation Network (AFMS-Net) with two encoder variants: the Single Adaptive Encoder Block (SAEB) and the Dual Adaptive Encoder Block (DAEB). A squeeze-and-excite mechanism is employed in SAEB to identify significant data while disregarding peripheral details. This approach is best suited for scenarios requiring quick and efficient segmentation, with an emphasis on identifying key lesion areas. In contrast, the DAEB utilizes an advanced channel spatial attention strategy for fine-grained delineation and multiple-class classifications. Additionally, both architectures incorporate a Segmentation Path (SegPath) module between the encoder and decoder, refining segmentation, enhancing feature extraction, and improving model performance and stability. Results: AFMS-Net demonstrates exceptional performance across several notable datasets, including BRATs 2021, ATLAS 2021, and ISLES 2022. Its design aims to construct a lightweight architecture capable of handling complex segmentation challenges with high precision. Discussion: The proposed AFMS-Net addresses the critical balance issue between performance and computational efficiency in the segmentation of brain lesions. By introducing two tailored encoder variants, the network adapts to varying requirements of speed and feature. This approach not only advances the state-of-the-art in lesion segmentation but also provides a scalable framework for future research in medical image processing.

TLTNet: A novel transscale cascade layered transformer network for enhanced retinal blood vessel segmentation.

Extracting global and local feature information is still challenging due to the problems of retinal blood vessel medical images like fuzzy edge features, noise, difficulty in distinguishing between lesion regions and background information, and loss of low-level feature information, which leads to insufficient extraction of feature information. To better solve these problems and fully extract the global and local feature information of the image, we propose a novel transscale cascade layered transformer network for enhanced retinal blood vessel segmentation, which consists of an encoder and a decoder and is connected between the encoder and decoder by a transscale transformer cascade module. Among them, the encoder consists of a local-global transscale transformer module, a multi-head layered transscale adaptive embedding module, and a local context(LCNet) module. The transscale transformer cascade module learns local and global feature information from the first three layers of the encoder, and multi-scale dependent features, fuses the hierarchical feature information from the skip connection block and the channel-token interaction fusion block, respectively, and inputs it to the decoder. The decoder includes a decoding module for the local context network and a transscale position transformer module to input the local and global feature information extracted from the encoder with retained key position information into the decoding module and the position embedding transformer module for recovery and output of the prediction results that are consistent with the input feature information. In addition, we propose an improved cross-entropy loss function based on the difference between the deterministic observation samples and the prediction results with the deviation distance, which is validated on the DRIVE and STARE datasets combined with the proposed network model based on the dual transformer structure in this paper, and the segmentation accuracies are 97.26% and 97.87%, respectively. Compared with other state-of-the-art networks, the results show that the proposed network model has a significant competitive advantage in improving the segmentation performance of retinal blood vessel images.

An image caption model based on attention mechanism and deep reinforcement learning.

Image caption technology aims to convert visual features of images, extracted by computers, into meaningful semantic information. Therefore, the computers can generate text descriptions that resemble human perception, enabling tasks such as image classification, retrieval, and analysis. In recent years, the performance of image caption has been significantly enhanced with the introduction of encoder-decoder architecture in machine translation and the utilization of deep neural networks. However, several challenges still persist in this domain. Therefore, this paper proposes a novel method to address the issue of visual information loss and non-dynamic adjustment of input images during decoding. We introduce a guided decoding network that establishes a connection between the encoding and decoding parts. Through this connection, encoding information can provide guidance to the decoding process, facilitating automatic adjustment of the decoding information. In addition, Dense Convolutional Network (DenseNet) and Multiple Instance Learning (MIL) are adopted in the image encoder, and Nested Long Short-Term Memory (NLSTM) is utilized as the decoder to enhance the extraction and parsing capability of image information during the encoding and decoding process. In order to further improve the performance of our image caption model, this study incorporates an attention mechanism to focus details and constructs a double-layer decoding structure, which facilitates the enhancement of the model in terms of providing more detailed descriptions and enriched semantic information. Furthermore, the Deep Reinforcement Learning (DRL) method is employed to train the model by directly optimizing the identical set of evaluation indexes, which solves the problem of inconsistent training and evaluation standards. Finally, the model is trained and tested on MS COCO and Flickr 30 k datasets, and the results show that the model has improved compared with commonly used models in the evaluation indicators such as BLEU, METEOR and CIDEr.

GNet: An integrated context-aware neural framework for transcription factor binding signal at single nucleotide resolution prediction.

Transcription factors (TFs) are important factors that regulate gene expression. Revealing the mechanism affecting the binding specificity of TFs is the key to understanding gene regulation. Most of the previous studies focus on TF-DNA binding sites at the sequence level, and they seldom utilize the contextual features of DNA sequences. In this paper, we develop an integrated spatiotemporal context-aware neural network framework, named GNet, for predicting TF-DNA binding signal at single nucleotide resolution by achieving three tasks: single nucleotide resolution signal prediction, identification of binding regions at the sequence level, and TF-DNA binding motif prediction. GNet extracts implicit spatial contextual information with a gated highway neural mechanism, which captures large context multi-level patterns using linear shortcut connections, and the idea of it permeates the encoder and decoder parts of GNet. The improved dual external attention mechanism, which learns implicit relationships both within and among samples, and improves the performance of the model. Experimental results on 53 human TF ChIP-seq datasets and 6 chromatin accessibility ATAC-seq datasets shows that GNet outperforms the state-of-the-art methods in the three tasks, and the results of cross-species studies on 15 human and 18 mouse TF datasets of the corresponding TF families indicate that GNet also shows the best performance in cross-species prediction over the competitive methods.

NAG-Net: Nested attention-guided learning for segmentation of carotid lumen-intima interface and media-adventitia interface.

Cardiovascular diseases (CVD), as the leading cause of death in the world, poses a serious threat to human health. The segmentation of carotid Lumen-intima interface (LII) and Media-adventitia interface (MAI) is a prerequisite for measuring intima-media thickness (IMT), which is of great significance for early screening and prevention of CVD. Despite recent advances, existing methods still fail to incorporate task-related clinical domain knowledge and require complex post-processing steps to obtain fine contours of LII and MAI. In this paper, a nested attention-guided deep learning model (named NAG-Net) is proposed for accurate segmentation of LII and MAI. The NAG-Net consists of two nested sub-networks, the Intima-Media Region Segmentation Network (IMRSN) and the LII and MAI Segmentation Network (LII-MAISN). It innovatively incorporates task-related clinical domain knowledge through the visual attention map generated by IMRSN, enabling LII-MAISN to focus more on the clinician's visual focus region under the same task during segmentation. Moreover, the segmentation results can directly obtain fine contours of LII and MAI through simple refinement without complicated post-processing steps. To further improve the feature extraction ability of the model and reduce the impact of data scarcity, the strategy of transfer learning is also adopted to apply the pretrained weights of VGG-16. In addition, a channel attention-based encoder feature fusion block (EFFB-ATT) is specially designed to achieve efficient representation of useful features extracted by two parallel encoders in LII-MAISN. Extensive experimental results have demonstrated that our proposed NAG-Net outperformed other state-of-the-art methods and achieved the highest performance on all evaluation metrics.

TATL: Task agnostic transfer learning for skin attributes detection.

Existing skin attributes detection methods usually initialize with a pre-trained Imagenet network and then fine-tune on a medical target task. However, we argue that such approaches are suboptimal because medical datasets are largely different from ImageNet and often contain limited training samples. In this work, we propose Task Agnostic Transfer Learning (TATL), a novel framework motivated by dermatologists' behaviors in the skincare context. TATL learns an attribute-agnostic segmenter that detects lesion skin regions and then transfers this knowledge to a set of attribute-specific classifiers to detect each particular attribute. Since TATL's attribute-agnostic segmenter only detects skin attribute regions, it enjoys ample data from all attributes, allows transferring knowledge among features, and compensates for the lack of training data from rare attributes. We conduct extensive experiments to evaluate the proposed TATL transfer learning mechanism with various neural network architectures on two popular skin attributes detection benchmarks. The empirical results show that TATL not only works well with multiple architectures but also can achieve state-of-the-art performances, while enjoying minimal model and computational complexities. We also provide theoretical insights and explanations for why our transfer learning framework performs well in practice.

Hierarchical 3D Feature Learning for Pancreas Segmentation.

We propose a novel 3D fully convolutional deep network for automated pancreas segmentation from both MRI and CT scans. More specifically, the proposed model consists of a 3D encoder that learns to extract volume features at different scales; features taken at different points of the encoder hierarchy are then sent to multiple 3D decoders that individually predict intermediate segmentation maps. Finally, all segmentation maps are combined to obtain a unique detailed segmentation mask. We test our model on both CT and MRI imaging data: the publicly available NIH Pancreas-CT dataset (consisting of 82 contrast-enhanced CTs) and a private MRI dataset (consisting of 40 MRI scans). Experimental results show that our model outperforms existing methods on CT pancreas segmentation, obtaining an average Dice score of about 88%, and yields promising segmentation performance on a very challenging MRI data set (average Dice score is about 77%). Additional control experiments demonstrate that the achieved performance is due to the combination of our 3D fully-convolutional deep network and the hierarchical representation decoding, thus substantiating our architectural design.

DAM: Hierarchical Adaptive Feature Selection Using Convolution Encoder Decoder Network for Strawberry Segmentation.

Autonomous harvesters can be used for the timely cultivation of high-value crops such as strawberries, where the robots have the capability to identify ripe and unripe crops. However, the real-time segmentation of strawberries in an unbridled farming environment is a challenging task due to fruit occlusion by multiple trusses, stems, and leaves. In this work, we propose a possible solution by constructing a dynamic feature selection mechanism for convolutional neural networks (CNN). The proposed building block namely a dense attention module (DAM) controls the flow of information between the convolutional encoder and decoder. DAM enables hierarchical adaptive feature fusion by exploiting both inter-channel and intra-channel relationships and can be easily integrated into any existing CNN to obtain category-specific feature maps. We validate our attention module through extensive ablation experiments. In addition, a dataset is collected from different strawberry farms and divided into four classes corresponding to different maturity levels of fruits and one is devoted to background. Quantitative analysis of the proposed method showed a 4.1% and 2.32% increase in mean intersection over union, over existing state-of-the-art semantic segmentation models and other attention modules respectively, while simultaneously retaining a processing speed of 53 frames per second.

Deep Convolutional Encoder-Decoder algorithm for MRI brain reconstruction.

Compressed Sensing Magnetic Resonance Imaging (CS-MRI) could be considered a challenged task since it could be designed as an efficient technique for fast MRI acquisition which could be highly beneficial for several clinical routines. In fact, it could grant better scan quality by reducing motion artifacts amount as well as the contrast washout effect. It offers also the possibility to reduce the exploration cost and the patient's anxiety. Recently, Deep Learning Neuronal Network (DL) has been suggested in order to reconstruct MRI scans with conserving the structural details and improving parallel imaging-based fast MRI. In this paper, we propose Deep Convolutional Encoder-Decoder architecture for CS-MRI reconstruction. Such architecture bridges the gap between the non-learning techniques, using data from only one image, and approaches using large training data. The proposed approach is based on autoencoder architecture divided into two parts: an encoder and a decoder. The encoder as well as the decoder has essentially three convolutional blocks. The proposed architecture has been evaluated through two databases: Hammersmith dataset (for the normal scans) and MICCAI 2018 (for pathological MRI). Moreover, we extend our model to cope with noisy pathological MRI scans. The normalized mean square error (NMSE), the peak-to-noise ratio (PSNR), and the structural similarity index (SSIM) have been adopted as evaluation metrics in order to evaluate the proposed architecture performance and to make a comparative study with the state-of-the-art reconstruction algorithms. The higher PSNR and SSIM values as well as the lowest NMSE values could attest that the proposed architecture offers better reconstruction and preserves textural image details. Furthermore, the running time is about 0.8 s, which is suitable for real-time processing. Such results could encourage the neurologist to adopt it in their clinical routines. Graphical abstract.

An efficient encoder-decoder model for portrait depth estimation from single images trained on pixel-accurate synthetic data.

Depth estimation from a single image frame is a fundamental challenge in computer vision, with many applications such as augmented reality, action recognition, image understanding, and autonomous driving. Large and diverse training sets are required for accurate depth estimation from a single image frame. Due to challenges in obtaining dense ground-truth depth, a new 3D pipeline of 100 synthetic virtual human models is presented to generate multiple 2D facial images and corresponding ground truth depth data, allowing complete control over image variations. To validate the synthetic facial depth data, we propose an evaluation of state-of-the-art depth estimation algorithms based on single image frames on the generated synthetic dataset. Furthermore, an improved encoder-decoder based neural network is presented. This network is computationally efficient and shows better performance than current state-of-the-art when tested and evaluated across 4 public datasets. Our training methodology relies on the use of synthetic data samples which provides a more reliable ground truth for depth estimation. Additionally, using a combination of appropriate loss functions leads to improved performance than the current state-of-the-art network performances. Our approach clearly outperforms competing methods across different test datasets, setting a new state-of-the-art for facial depth estimation from synthetic data.

Self-co-attention neural network for anatomy segmentation in whole breast ultrasound.

The automated whole breast ultrasound (AWBUS) is a new breast imaging technique that can depict the whole breast anatomy. To facilitate the reading of AWBUS images and support the breast density estimation, an automatic breast anatomy segmentation method for AWBUS images is proposed in this study. The problem at hand is quite challenging as it needs to address issues of low image quality, ill-defined boundary, large anatomical variation, etc. To address these issues, a new deep learning encoder-decoder segmentation method based on a self-co-attention mechanism is developed. The self-attention mechanism is comprised of spatial and channel attention module (SC) and embedded in the ResNeXt (i.e., Res-SC) block in the encoder path. A non-local context block (NCB) is further incorporated to augment the learning of high-level contextual cues. The decoder path of the proposed method is equipped with the weighted up-sampling block (WUB) to attain class-specific better up-sampling effect. Meanwhile, the co-attention mechanism is also developed to improve the segmentation coherence among two consecutive slices. Extensive experiments are conducted with comparison to several the state-of-the-art deep learning segmentation methods. The experimental results corroborate the effectiveness of the proposed method on the difficult breast anatomy segmentation problem on AWBUS images.

A novel fully convolutional network for visual saliency prediction.

A human Visual System (HVS) has the ability to pay visual attention, which is one of the many functions of the HVS. Despite the many advancements being made in visual saliency prediction, there continues to be room for improvement. Deep learning has recently been used to deal with this task. This study proposes a novel deep learning model based on a Fully Convolutional Network (FCN) architecture. The proposed model is trained in an end-to-end style and designed to predict visual saliency. The entire proposed model is fully training style from scratch to extract distinguishing features. The proposed model is evaluated using several benchmark datasets, such as MIT300, MIT1003, TORONTO, and DUT-OMRON. The quantitative and qualitative experiment analyses demonstrate that the proposed model achieves superior performance for predicting visual saliency.