Starting from the resurgence of deep learning, vision-language models (VLMs) benefiting from large language models (LLMs) have never been so popular. However, while LLMs can utilize extensive background knowledge and task information with in-context learning, most VLMs still struggle with understanding complex multi-modal prompts with multiple images. The issue can traced back to the architectural design of VLMs or pre-training data. Specifically, the current VLMs primarily emphasize utilizing multi-modal data with a single image some, rather than multi-modal prompts with interleaved multiple images and text. Even though some newly proposed VLMs could handle user prompts with multiple images, pre-training data does not provide more sophisticated multi-modal prompts than interleaved image and text crawled from the web. We propose MMICL to address the issue by considering both the model and data perspectives. We introduce a well-designed architecture capable of seamlessly integrating visual and textual context in an interleaved manner and MIC dataset to reduce the gap between the training data and the complex user prompts in real-world applications, including: 1) multi-modal context with interleaved images and text, 2) textual references for each image, and 3) multi-image data with spatial, logical, or temporal relationships. Our experiments confirm that MMICL achieves new stat-of-the-art zero-shot and few-shot performance on a wide range of general vision-language tasks, especially for complex reasoning benchmarks including MME and MMBench. Our analysis demonstrates that MMICL effectively deals with the challenge of complex multi-modal prompt understanding. The experiments on ScienceQA-IMG also show that MMICL successfully alleviates the issue of language bias in VLMs, which we believe is the reason behind the advanced performance of MMICL.
Accurate automatic segmentation of medical images typically requires large datasets with high-quality annotations, making it less applicable in clinical settings due to limited training data. One-shot segmentation based on learned transformations (OSSLT) has shown promise when labeled data is extremely limited, typically including unsupervised deformable registration, data augmentation with learned registration, and segmentation learned from augmented data. However, current one-shot segmentation methods are challenged by limited data diversity during augmentation, and potential label errors caused by imperfect registration. To address these issues, we propose a novel one-shot medical image segmentation method with adversarial training and label error rectification (AdLER), with the aim of improving the diversity of generated data and correcting label errors to enhance segmentation performance. Specifically, we implement a novel dual consistency constraint to ensure anatomy-aligned registration that lessens registration errors. Furthermore, we develop an adversarial training strategy to augment the atlas image, which ensures both generation diversity and segmentation robustness. We also propose to rectify potential label errors in the augmented atlas images by estimating segmentation uncertainty, which can compensate for the imperfect nature of deformable registration and improve segmentation authenticity. Experiments on the CANDI and ABIDE datasets demonstrate that the proposed AdLER outperforms previous state-of-the-art methods by 0.7% (CANDI), 3.6% (ABIDE "seen"), and 4.9% (ABIDE "unseen") in segmentation based on Dice scores, respectively. The source code will be available at https://github.com/hsiangyuzhao/AdLER.
The rise of large language models (LLMs) has marked a pivotal shift in the field of natural language processing (NLP). LLMs have revolutionized a multitude of domains, and they have made a significant impact in the medical field. Large language models are now more abundant than ever, and many of these models exhibit bilingual capabilities, proficient in both English and Chinese. However, a comprehensive evaluation of these models remains to be conducted. This lack of assessment is especially apparent within the context of radiology NLP. This study seeks to bridge this gap by critically evaluating thirty two LLMs in interpreting radiology reports, a crucial component of radiology NLP. Specifically, the ability to derive impressions from radiologic findings is assessed. The outcomes of this evaluation provide key insights into the performance, strengths, and weaknesses of these LLMs, informing their practical applications within the medical domain.
Automatic examination of thin-prep cytologic test (TCT) slides can assist pathologists in finding cervical abnormality for accurate and efficient cancer screening. Current solutions mostly need to localize suspicious cells and classify abnormality based on local patches, concerning the fact that whole slide images of TCT are extremely large. It thus requires many annotations of normal and abnormal cervical cells, to supervise the training of the patch-level classifier for promising performance. In this paper, we propose CellGAN to synthesize cytopathological images of various cervical cell types for augmenting patch-level cell classification. Built upon a lightweight backbone, CellGAN is equipped with a non-linear class mapping network to effectively incorporate cell type information into image generation. We also propose the Skip-layer Global Context module to model the complex spatial relationship of the cells, and attain high fidelity of the synthesized images through adversarial learning. Our experiments demonstrate that CellGAN can produce visually plausible TCT cytopathological images for different cell types. We also validate the effectiveness of using CellGAN to greatly augment patch-level cell classification performance.
Model pre-training on large text corpora has been demonstrated effective for various downstream applications in the NLP domain. In the graph mining domain, a similar analogy can be drawn for pre-training graph models on large graphs in the hope of benefiting downstream graph applications, which has also been explored by several recent studies. However, no existing study has ever investigated the pre-training of text plus graph models on large heterogeneous graphs with abundant textual information (a.k.a. large graph corpora) and then fine-tuning the model on different related downstream applications with different graph schemas. To address this problem, we propose a framework of graph-aware language model pre-training (GALM) on a large graph corpus, which incorporates large language models and graph neural networks, and a variety of fine-tuning methods on downstream applications. We conduct extensive experiments on Amazon's real internal datasets and large public datasets. Comprehensive empirical results and in-depth analysis demonstrate the effectiveness of our proposed methods along with lessons learned.
The potential of integrating Computer-Assisted Diagnosis (CAD) with Large Language Models (LLMs) in clinical applications, particularly in digital family doctor and clinic assistant roles, shows promise. However, existing works have limitations in terms of reliability, effectiveness, and their narrow applicability to specific image domains, which restricts their overall processing capabilities. Moreover, the mismatch in writing style between LLMs and radiologists undermines their practical utility. To address these challenges, we present ChatCAD+, an interactive CAD system that is universal, reliable, and capable of handling medical images from diverse domains. ChatCAD+ utilizes current information obtained from reputable medical websites to offer precise medical advice. Additionally, it incorporates a template retrieval system that emulates real-world diagnostic reporting, thereby improving its seamless integration into existing clinical workflows. The source code is available at https://github.com/zhaozh10/ChatCAD. The online demo will be available soon.
Recent self-supervised contrastive learning methods greatly benefit from the Siamese structure that aims to minimizing distances between positive pairs. These methods usually apply random data augmentation to input images, expecting the augmented views of the same images to be similar and positively paired. However, random augmentation may overlook image semantic information and degrade the quality of augmented views in contrastive learning. This issue becomes more challenging in medical images since the abnormalities related to diseases can be tiny, and are easy to be corrupted (e.g., being cropped out) in the current scheme of random augmentation. In this work, we first demonstrate that, for widely-used X-ray images, the conventional augmentation prevalent in contrastive pre-training can affect the performance of the downstream diagnosis or classification tasks. Then, we propose a novel augmentation method, i.e., FocusContrast, to learn from radiologists' gaze in diagnosis and generate contrastive views for medical images with guidance from radiologists' visual attention. Specifically, we track the gaze movement of radiologists and model their visual attention when reading to diagnose X-ray images. The learned model can predict visual attention of the radiologists given a new input image, and further guide the attention-aware augmentation that hardly neglects the disease-related abnormalities. As a plug-and-play and framework-agnostic module, FocusContrast consistently improves state-of-the-art contrastive learning methods of SimCLR, MoCo, and BYOL by 4.0~7.0% in classification accuracy on a knee X-ray dataset.
When communicating with elders with cognitive impairment, cognitive stimulation (CS) help to maintain the cognitive health of elders. Data sparsity is the main challenge in building CS-based dialogue systems, particularly in the Chinese language. To fill this gap, we construct a Chinese CS conversation (CSConv) dataset, which contains about 2.6K groups of dialogues with CS principles and emotional support strategy labels. Making chit chat while providing emotional support is overlooked by the majority of existing cognitive dialogue systems. In this paper, we propose a multi-source knowledge fusion method for CS dialogue (CSD), to generate open-ended responses guided by the CS principle and emotional support strategy. We first use a progressive mask method based on external knowledge to learn encoders as effective classifiers, which is the prerequisite to predict the CS principle and emotional support strategy of the target response. Then a decoder interacts with the perceived CS principle and emotional support strategy to generate responses. Extensive experiments conducted on the CSConv dataset demonstrate the effectiveness of the proposed method, while there is still a large space for improvement compared to human performance.
Mammographic image analysis is a fundamental problem in the computer-aided diagnosis scheme, which has recently made remarkable progress with the advance of deep learning. However, the construction of a deep learning model requires training data that are large and sufficiently diverse in terms of image style and quality. In particular, the diversity of image style may be majorly attributed to the vendor factor. However, mammogram collection from vendors as many as possible is very expensive and sometimes impractical for laboratory-scale studies. Accordingly, to further augment the generalization capability of deep learning models to various vendors with limited resources, a new contrastive learning scheme is developed. Specifically, the backbone network is firstly trained with a multi-style and multi-view unsupervised self-learning scheme for the embedding of invariant features to various vendor styles. Afterward, the backbone network is then recalibrated to the downstream tasks of mass detection, multi-view mass matching, BI-RADS classification and breast density classification with specific supervised learning. The proposed method is evaluated with mammograms from four vendors and two unseen public datasets. The experimental results suggest that our approach can effectively improve analysis performance on both seen and unseen domains, and outperforms many state-of-the-art (SOTA) generalization methods.
Magnetic resonance (MR) images collected in 2D scanning protocols typically have large inter-slice spacing, resulting in high in-plane resolution but reduced through-plane resolution. Super-resolution techniques can reduce the inter-slice spacing of 2D scanned MR images, facilitating the downstream visual experience and computer-aided diagnosis. However, most existing super-resolution methods are trained at a fixed scaling ratio, which is inconvenient in clinical settings where MR scanning may have varying inter-slice spacings. To solve this issue, we propose Hierarchical Feature Conditional Diffusion (HiFi-Diff)} for arbitrary reduction of MR inter-slice spacing. Given two adjacent MR slices and the relative positional offset, HiFi-Diff can iteratively convert a Gaussian noise map into any desired in-between MR slice. Furthermore, to enable fine-grained conditioning, the Hierarchical Feature Extraction (HiFE) module is proposed to hierarchically extract conditional features and conduct element-wise modulation. Our experimental results on the publicly available HCP-1200 dataset demonstrate the high-fidelity super-resolution capability of HiFi-Diff and its efficacy in enhancing downstream segmentation performance.