With the rapid growth of online medical platforms, more and more doctors are willing to manage and communicate with patients via online services. Considering the large volume and various patient conditions, identifying and classifying patients' medical records has become a crucial problem. To efficiently index these records, a common practice is to annotate them with semantically meaningful tags. However, manual labeling tags by doctors is impractical due to the possibility of thousands of tag candidates, which necessitates a tag recommender system. Due to the long tail distribution of tags and the dominance of low-activity doctors, as well as the unique uploaded medical records, this task is rather challenging. This paper proposes an efficient doctor specific tag recommendation framework for improved medical record management without side information. Specifically, we first utilize effective language models to learn the text representation. Then, we construct a doctor embedding learning module to enhance the recommendation quality by integrating implicit information within text representations and considering latent tag correlations to make more accurate predictions. Extensive experiment results demonstrate the effectiveness of our framework from the viewpoints of all doctors (20% improvement) or low-activity doctors (10% improvement).

In clinics, a radiology report is crucial for guiding a patient's treatment. However, writing radiology reports is a heavy burden for radiologists. To this end, we present an automatic, multi-modal approach for report generation from a chest x-ray. Our approach, motivated by the observation that the descriptions in radiology reports are highly correlated with specific information of the x-ray images, features two distinct modules: (i) Learned knowledge base: To absorb the knowledge embedded in the radiology reports, we build a knowledge base that can automatically distill and restore medical knowledge from textual embedding without manual labor; (ii) Multi-modal alignment: to promote the semantic alignment among reports, disease labels, and images, we explicitly utilize textual embedding to guide the learning of the visual feature space. We evaluate the performance of the proposed model using metrics from both natural language generation and clinic efficacy on the public IU-Xray and MIMIC-CXR datasets. Our ablation study shows that each module contributes to improving the quality of generated reports. Furthermore, the assistance of both modules, our approach outperforms state-of-the-art methods over almost all the metrics. Code is available at https://github.com/LX-doctorAI1/M2KT.

Fast screening and diagnosis are critical in COVID-19 patient treatment. In addition to the gold standard RT-PCR, radiological imaging like X-ray and CT also works as an important means in patient screening and follow-up. However, due to the excessive number of patients, writing reports becomes a heavy burden for radiologists. To reduce the workload of radiologists, we propose DeltaNet to generate medical reports automatically. Different from typical image captioning approaches that generate reports with an encoder and a decoder, DeltaNet applies a conditional generation process. In particular, given a medical image, DeltaNet employs three steps to generate a report: 1) first retrieving related medical reports, i.e., the historical reports from the same or similar patients; 2) then comparing retrieved images and current image to find the differences; 3) finally generating a new report to accommodate identified differences based on the conditional report. We evaluate DeltaNet on a COVID-19 dataset, where DeltaNet outperforms state-of-the-art approaches. Besides COVID-19, the proposed DeltaNet can be applied to other diseases as well. We validate its generalization capabilities on the public IU-Xray and MIMIC-CXR datasets for chest-related diseases.

Recently, attention-based models for joint intent detection and slot filling have achieved state-of-the-art performance. However, we think the conventional attention can only capture the first-order feature interaction between two tasks and is insufficient. To address this issue, we propose a unified BiLinear attention block, which leverages bilinear pooling to synchronously explore both the contextual and channel-wise bilinear attention distributions to capture the second-order interactions between the input intent and slot features. Higher-order interactions are constructed by combining many such blocks and exploiting Exponential Linear activations. Furthermore, we present a Higher-order Attention Network (HAN) to jointly model them. The experimental results show that our approach outperforms the state-of-the-art results. We also conduct experiments on the new SLURP dataset, and give a discussion on HAN’s properties, i.e., robustness and generalization.

Gene Ontology (GO) is the primary gene function knowledge base that enables computational tasks in biomedicine. The basic element of GO is a term, which includes a set of genes with the same function. Existing research efforts of GO mainly focus on predicting gene term associations. Other tasks, such as generating descriptions of new terms, are rarely pursued. In this paper, we propose a novel task: GO term description generation. This task aims to automatically generate a sentence that describes the function of a GO term belonging to one of the three categories, i.e., molecular function, biological process, and cellular component. To address this task, we propose a Graph-in-Graph network that can efficiently leverage the structural information of GO. The proposed network introduces a two-layer graph: the first layer is a graph of GO terms where each node is also a graph (gene graph). Such a Graph-in-Graph network can derive the biological functions of GO terms and generate proper descriptions. To validate the effectiveness of the proposed network, we build three large-scale benchmark datasets. By incorporating the proposed Graph-in-Graph network, the performances of seven different sequence-to-sequence models can be substantially boosted across all evaluation metrics, with up to 34.7%, 14.5%, and 39.1% relative improvements in BLEU, ROUGE-L, and METEOR, respectively.

Most video-and-language representation learning approaches employ contrastive learning, e.g., CLIP, to project the video and text features into a common latent space according to the semantic similarities of text-video pairs. However, such learned shared latent spaces are not often optimal, and the modality gap between visual and textual representation can not be fully eliminated. In this paper, we propose Expectation-Maximization Contrastive Learning (EMCL) to learn compact video-and-language representations. Specifically, we use the Expectation-Maximization algorithm to find a compact set of bases for the latent space, where the features could be concisely represented as the linear combinations of these bases. Such feature decomposition of video-and-language representations reduces the rank of the latent space, resulting in increased representing power for the semantics. Extensive experiments on three benchmark text-video retrieval datasets prove that our EMCL can learn more discriminative video-and-language representations than previous methods, and significantly outperform previous state-of-the-art methods across all metrics. More encouragingly, the proposed method can be applied to boost the performance of existing approaches either as a jointly training layer or an out-of-the-box inference module with no extra training, making it easy to be incorporated into any existing methods.

The "Patient Instruction" (PI), which contains critical instructional information provided both to carers and to the patient at the time of discharge, is essential for the patient to manage their condition outside hospital. An accurate and easy-to-follow PI can improve the self-management of patients which can in turn reduce hospital readmission rates. However, writing an appropriate PI can be extremely time consuming for physicians, and is subject to being incomplete or error-prone for (potentially overworked) physicians. Therefore, we propose a new task that can provide an objective means of avoiding incompleteness, while reducing clinical workload: the automatic generation of the PI, which is imagined as being a document that the clinician can review, modify, and approve as necessary (rather than taking the human "out of the loop"). We build a benchmark clinical dataset and propose the Re$^3$Writer, which imitates the working patterns of physicians to first retrieve related working experience from historical PIs written by physicians, then reason related medical knowledge. Finally, it refines the retrieved working experience and reasoned medical knowledge to extract useful information, which is used to generate the PI for previously-unseen patient according to their health records during hospitalization. Our experiments show that, using our method, the performance of 6 different models can be substantially boosted across all metrics, with up to 20%, 11%, and 19% relative improvements in BLEU-4, ROUGE-L, and METEOR, respectively. Meanwhile, we show results from human evaluations to measure the effectiveness in terms of its usefulness for clinical practice. The code is available at https://github.com/AI-in-Health/Patient-Instructions.

Automatic chest radiology report generation is critical in clinics which can relieve experienced radiologists from the heavy workload and remind inexperienced radiologists of misdiagnosis or missed diagnose. Existing approaches mainly formulate chest radiology report generation as an image captioning task and adopt the encoder-decoder framework. However, in the medical domain, such pure data-driven approaches suffer from the following problems: 1) visual and textual bias problem; 2) lack of expert knowledge. In this paper, we propose a knowledge-enhanced radiology report generation approach introduces two types of medical knowledge: 1) General knowledge, which is input independent and provides the broad knowledge for report generation; 2) Specific knowledge, which is input dependent and provides the fine-grained knowledge for chest X-ray report generation. To fully utilize both the general and specific knowledge, we also propose a knowledge-enhanced multi-head attention mechanism. By merging the visual features of the radiology image with general knowledge and specific knowledge, the proposed model can improve the quality of generated reports. The experimental results on the publicly available IU-Xray dataset show that the proposed knowledge-enhanced approach outperforms state-of-the-art methods in almost all metrics. And the results of MIMIC-CXR dataset show that the proposed knowledge-enhanced approach is on par with state-of-the-art methods. Ablation studies also demonstrate that both general and specific knowledge can help to improve the performance of chest radiology report generation.

Training supervised video captioning model requires coupled video-caption pairs. However, for many targeted languages, sufficient paired data are not available. To this end, we introduce the unpaired video captioning task aiming to train models without coupled video-caption pairs in target language. To solve the task, a natural choice is to employ a two-step pipeline system: first utilizing video-to-pivot captioning model to generate captions in pivot language and then utilizing pivot-to-target translation model to translate the pivot captions to the target language. However, in such a pipeline system, 1) visual information cannot reach the translation model, generating visual irrelevant target captions; 2) the errors in the generated pivot captions will be propagated to the translation model, resulting in disfluent target captions. To address these problems, we propose the Unpaired Video Captioning with Visual Injection system (UVC-VI). UVC-VI first introduces the Visual Injection Module (VIM), which aligns source visual and target language domains to inject the source visual information into the target language domain. Meanwhile, VIM directly connects the encoder of the video-to-pivot model and the decoder of the pivot-to-target model, allowing end-to-end inference by completely skipping the generation of pivot captions. To enhance the cross-modality injection of the VIM, UVC-VI further introduces a pluggable video encoder, i.e., Multimodal Collaborative Encoder (MCE). The experiments show that UVC-VI outperforms pipeline systems and exceeds several supervised systems. Furthermore, equipping existing supervised systems with our MCE can achieve 4% and 7% relative margins on the CIDEr scores to current state-of-the-art models on the benchmark MSVD and MSR-VTT datasets, respectively.

Vision-and-language (V-L) tasks require the system to understand both vision content and natural language, thus learning fine-grained joint representations of vision and language (a.k.a. V-L representations) is of paramount importance. Recently, various pre-trained V-L models are proposed to learn V-L representations and achieve improved results in many tasks. However, the mainstream models process both vision and language inputs with the same set of attention matrices. As a result, the generated V-L representations are entangled in one common latent space . To tackle this problem, we propose DiMBERT (short for Di sentangled M ultimodal-Attention BERT ), which is a novel framework that applies separated attention spaces for vision and language, and the representations of multi-modalities can thus be disentangled explicitly. To enhance the correlation between vision and language in disentangled spaces, we introduce the visual concepts to DiMBERT which represent visual information in textual format. In this manner, visual concepts help to bridge the gap between the two modalities. We pre-train DiMBERT on a large amount of image–sentence pairs on two tasks: bidirectional language modeling and sequence-to-sequence language modeling. After pre-train, DiMBERT is further fine-tuned for the downstream tasks. Experiments show that DiMBERT sets new state-of-the-art performance on three tasks (over four datasets), including both generation tasks (image captioning and visual storytelling) and classification tasks (referring expressions). The proposed DiM (short for Di sentangled M ultimodal-Attention) module can be easily incorporated into existing pre-trained V-L models to boost their performance, up to a 5% increase on the representative task. Finally, we conduct a systematic analysis and demonstrate the effectiveness of our DiM and the introduced visual concepts.

While Machine Comprehension (MC) has attracted extensive research interests in recent years, existing approaches mainly belong to the category of Machine Reading Comprehension task which mines textual inputs (paragraphs and questions) to predict the answers (choices or text spans). However, there are a lot of MC tasks that accept audio input in addition to the textual input, e.g. English listening comprehension test. In this paper, we target the problem of Audio-Oriented Multimodal Machine Comprehension, and its goal is to answer questions based on the given audio and textual information. To solve this problem, we propose a Dynamic Inter- and Intra-modality Attention (DIIA) model to effectively fuse the two modalities (audio and textual). DIIA can work as an independent component and thus be easily integrated into existing MC models. Moreover, we further develop a Multimodal Knowledge Distillation (MKD) module to enable our multimodal MC model to accurately predict the answers based only on either the text or the audio. As a result, the proposed approach can handle various tasks including: Audio-Oriented Multimodal Machine Comprehension, Machine Reading Comprehension and Machine Listening Comprehension, in a single model, making fair comparisons possible between our model and the existing unimodal MC models. Experimental results and analysis prove the effectiveness of the proposed approaches. First, the proposed DIIA boosts the baseline models by up to 21.08% in terms of accuracy; Second, under the unimodal scenarios, the MKD module allows our multimodal MC model to significantly outperform the unimodal models by up to 18.87%, which are trained and tested with only audio or textual data.

Fenglin Liu, Shen Ge, Xian Wu. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

Automatically generating radiology reports can improve current clinical practice in diagnostic radiology. On one hand, it can relieve radiologists from the heavy burden of report writing; On the other hand, it can remind radiologists of abnormalities and avoid the misdiagnosis and missed diagnosis. Yet, this task remains a challenging job for data-driven neural networks, due to the serious visual and textual data biases. To this end, we propose a Posterior-and-Prior Knowledge Exploring-and-Distilling approach (PPKED) to imitate the working patterns of radiologists, who will first examine the abnormal regions and assign the disease topic tags to the abnormal regions, and then rely on the years of prior medical knowledge and prior working experience accumulations to write reports. Thus, the PPKED includes three modules: Posterior Knowledge Explorer (PoKE), Prior Knowledge Explorer (PrKE) and Multi-domain Knowledge Distiller (MKD). In detail, PoKE explores the posterior knowledge, which provides explicit abnormal visual regions to alleviate visual data bias; PrKE explores the prior knowledge from the prior medical knowledge graph (medical knowledge) and prior radiology reports (working experience) to alleviate textual data bias. The explored knowledge is distilled by the MKD to generate the final reports. Evaluated on MIMIC-CXR and IU-Xray datasets, our method is able to outperform previous state-of-the-art models on these two datasets.

Medical report generation, which aims to automatically generate a long and coherent report of a given medical image, has been receiving growing research interests. Existing approaches mainly adopt a supervised manner and heavily rely on coupled image-report pairs. However, in the medical domain, building a large-scale image-report paired dataset is both time-consuming and expensive. To relax the dependency on paired data, we propose an unsupervised model Knowledge Graph Auto-Encoder (KGAE) which accepts independent sets of images and reports in training. KGAE consists of a pre-constructed knowledge graph, a knowledge-driven encoder and a knowledge-driven decoder. The knowledge graph works as the shared latent space to bridge the visual and textual domains; The knowledge-driven encoder projects medical images and reports to the corresponding coordinates in this latent space and the knowledge-driven decoder generates a medical report given a coordinate in this space. Since the knowledge-driven encoder and decoder can be trained with independent sets of images and reports, KGAE is unsupervised. The experiments show that the unsupervised KGAE generates desirable medical reports without using any image-report training pairs. Moreover, KGAE can also work in both semi-supervised and supervised settings, and accept paired images and reports in training. By further fine-tuning with image-report pairs, KGAE consistently outperforms the current state-of-the-art models on two datasets.

Psoriasis is a chronic skin disease which affects hundreds of millions of people around the world. This disease cannot be fully cured and requires lifelong caring. If the deterioration of Psoriasis is not detected and properly treated in time, it could cause serious complications or even lead to a life threat. Therefore, a quantitative measurement that can track the Psoriasis severity is necessary. Currently, PASI (Psoriasis Area and Severity Index) is the most frequently used measurement in clinical practices. However, PASI has the following disadvantages: (1) Time consuming: calculating PASI usually takes more than 30 minutes which poses a heavy burden on dermatologists; and (2) Inconsistency: due to the complexity of PASI calculation, different or even the same dermatologist could give different scores for the same case. To overcome these drawbacks, we propose PSENet which applies deep neural networks to estimate Psoriasis severity based on skin lesion images. Different from typical deep learning frameworks for image processing, PSENet has the following characteristics: (1) PSENet introduces a score refine module which is able to capture the visual features of skin at both coarse and fine-grained granularities; (2) PSENet uses siamese structure in training and accepts pairwise inputs, which reduces the dependency on large amount of training data; and (3) PSENet can not only estimate the severity, but also locate the skin lesion regions from the input image. To train and evaluate PSENet, we work with professional dermatologists from a top hospital and spend years in building a golden dataset. The experimental results show that PSENet can achieve the mean absolute error of 2.21 and the accuracy of 77.87% in pair comparison, outperforming baseline methods. Overall, PSENet not only relieves dermatologists from the dull PASI calculation but also enables patients to track Psoriasis severity in a much more convenient manner.

Recently, vision-and-language grounding problems, e.g., image captioning and visual question answering (VQA), has attracted extensive interests from both academic and industrial worlds. However, given the similarity of these tasks, the efforts to obtain better results by combining the merits of their algorithms are not well studied. Inspired by the recent success of federated learning, we propose a federated learning framework to obtain various types of image representations from different tasks, which are then fused together to form fine-grained image representations. The representations merge useful features from different vision-and-language grounding problems, and are thus much more powerful than the original representations alone in individual tasks. To learn such image representations, we propose the Aligning, Integrating and Mapping Network (aimNet). The aimNet is validated on three federated learning settings, which include horizontal federated learning, vertical federated learning, and federated transfer learning. Experiments of aimNet-based federated learning framework on two representative tasks, i.e., image captioning and VQA, demonstrate the effective and universal improvements of all metrics over the baselines. In image captioning, we are able to get 14% and 13% relative gain on the task-specific metrics CIDEr and SPICE, respectively. In VQA, we could also boost the performance of strong baselines by up to 3%.

Question answering (QA) has achieved promising progress recently. However, answering a question in real-world scenarios like the medical domain is still challenging, due to the requirement of external knowledge and the insufficient quantity of high-quality training data. In the light of these challenges, we study the task of generating medical QA pairs in this paper. With the insight that each medical question can be considered as a sample from the latent distribution of questions given answers, we propose an automated medical QA pair generation framework, consisting of an unsupervised key phrase detector that explores unstructured material for validity, and a generator that involves a multi-pass decoder to integrate structural knowledge for diversity. A series of experiments have been conducted on a real-world dataset collected from the National Medical Licensing Examination of China. Both automatic evaluation and human annotation demonstrate the effectiveness of the proposed method. Further investigation shows that, by incorporating the generated QA pairs for training, significant improvement in terms of accuracy can be achieved for the examination QA system. 1

Deep convolutional neural networks (CNNs) have recalibrated the state-of-the-art for a plethora of applications in medical image analyzing such as segmentation and classification. Large receptive field is crucial for modeling long-range spatial dependency in medical images. In this paper, we propose a novel architectural network design for accomplishing a full-image global receptive field, which we call spectral residual block (SRB). Specifically, we propose to utilize a unitary transform that essentially conducts a local-to-global transform. All elements are mapped to spectral domain and thus globally depend on each other. A variety of global operators are carefully devised and efficiently enforce a full-image receptive field, including spectral ReLU for frequency-sensitive filtering and spectral convolutions. The output in spectral domain is eventually converted back global-to-local via a reverse unitary transform. The proposed framework is generic and flexible, and could be applied to various network structures and tasks. Comprehensive evaluations on skin lesion segmentation and Chest X-Ray classification show that our method achieves the state-of-the-art performance, demonstrating both effectiveness and efficiency.

Image captioning has attracted extensive research interests in recent years. Due to the great disparities between vision and language, an important goal of image captioning is to link the information in visual domain to textual domain. However, many approaches conduct this process only in the decoder, making it hard to understand the images and generate captions effectively. In this paper, we propose to bridge the gap between the vision and language domains in the encoder, by enriching visual information with textual concepts, to achieve deep image understandings. To this end, we propose to explore the textual-enriched image features. Specifically, we introduce two modules, namely Textual Distilling Module and Textual Association Module. The former distills relevant textual concepts from image features, while the latter further associates extracted concepts according to their semantics. In this manner, we acquire textual-enriched image features, which provide clear textual representations of image under no explicit supervision. The proposed approach can be used as a plugin and easily embedded into a wide range of existing image captioning systems. We conduct the extensive experiments on two benchmark image captioning datasets, i.e., MSCOCO and Flickr30k. The experimental results and analysis show that, by incorporating the proposed approach, all baseline models receive consistent improvements over all metrics, with the most significant improvement up to 10% and 9%, in terms of the task-specific metrics CIDEr and SPICE, respectively. The results demonstrate that our approach is effective and generalizes well to a wide range of models for image captioning.

Recently, attention based models have been used extensively in many sequence-to-sequence learning systems. Especially for image captioning, the attention based models are expected to ground correct image regions with proper generated words. However, for each time step in the decoding process, the attention based models usually use the hidden state of the current input to attend to the image regions. Under this setting, these attention models have a deviated focus'' problem that they calculate the attention weights based on previous words instead of the one to be generated, impairing the performance of both grounding and captioning. In this paper, we propose the Prophet Attention, similar to the form of self-supervision. In the training stage, this module utilizes the future information to calculate theideal'' attention weights towards image regions. These calculated ideal'' weights are further used to regularize thedeviated'' attention. In this manner, image regions are grounded with the correct words. The proposed Prophet Attention can be easily incorporated into existing image captioning models to improve their performance of both grounding and captioning. The experiments on the Flickr30k Entities and the MSCOCO datasets show that the proposed Prophet Attention consistently outperforms baselines in both automatic metrics and human evaluations. It is worth noticing that we set new state-of-the-arts on the two benchmark datasets and achieve the 1st place on the leaderboard of the online MSCOCO benchmark in terms of the default ranking score, i.e., CIDEr-c40.

Diagnosis prediction aims to forecast diseases that a patient might have in his next hospital visit, which is critical in Clinical Decision Supporting System (CDSS). Existing approaches mainly formulate diagnosis prediction as a multi-label classification problem and use discrete medical codes as major features. While the structural information among medical codes and time series data in clinical data are generally neglected. In this paper, we propose Multi-modal Clinical Data based Hierarchical Multi-label model (MHM) to integrate discrete medical codes, structural information and time series data into the same framework for diagnosis prediction task. Experimental results on two real world datasets demonstrate the superiority of proposed MHM over state-of-the-art approaches.

Diagnosis prediction plays a key role in clinical decision supporting process, which attracted extensive research attention recently. Existing studies mainly utilize discrete medical codes (e.g., the ICD codes and procedure codes) as the primary features in prediction. However, in real clinical settings, such medical codes could be either incomplete or erroneous. For example, missed diagnosis will neglect some codes which should be included, mis-diagnosis will generate incorrect medical codes. To increase the robustness towards noisy data, we introduce textual clinical notes in addition to medical codes. Combining information from both sides will lead to improved understanding towards clinical health conditions. To accommodate both the textual notes and discrete medical codes in the same framework, we propose Multimodal Attentional Neural Networks (MNN), which integrates multi-modal data in a collaborative manner. Experimental results on real world EHR datasets demonstrate the advantages of MNN in terms of both robustness and accuracy.

Given a set of objects P and a set of ranking functions F over P, an interesting problem is to compute the top ranked objects for all functions. Evaluation of multiple top-k queries finds application in systems, where there is a heavy workload of ranking queries (e.g., online search engines and product recommendation systems). The simple solution of evaluating the top-k queries one-by-one does not scale well; instead, the system can make use of the fact that similar queries share common results to accelerate search. This paper is the first, to our knowledge, thorough study of this problem. We propose methods that compute all top-k queries in batch. Our first solution applies the block indexed nested loops paradigm, while our second technique is a view-based algorithm. We propose appropriate optimization techniques for the two approaches and demonstrate experimentally that the second approach is consistently the best. Our approach facilitates evaluation of other complex queries that depend on the computation of multiple top-k queries, such as reverse top-k and top-m influential queries. We show that our batch processing technique for these complex queries outperform the state-of-the-art by orders of magnitude.

Given a collection of objects that carry both spatial and textual information, a spatio-textual similarity join retrieves the pairs of objects that are spatially close and textually similar. As an example, consider a social network with spatially and textually tagged persons (i.e., their locations and profiles). A useful task (for friendship recommendation) would be to find pairs of persons that are spatially close and their profiles have a large overlap (i.e., they have common interests). Another application is data de-duplication (e.g., finding photographs which are spatially close to each other and high overlap in their descriptive tags). Despite the importance of this operation, there is very little previous work that studies its efficient evaluation and in fact under a different definition; only the best match for each object is identified. In this paper, we combine ideas from state-of-the-art spatial distance join and set similarity join methods and propose efficient algorithms that take into account both spatial and textual constraints. Besides, we propose a batch processing technique which boosts the performance of our approaches. An experimental evaluation using real and synthetic datasets shows that our optimized techniques are orders of magnitude faster than base-line solutions.