AdaCBM: An Adaptive Concept Bottleneck Model for Explainable and Accurate Diagnosis

The integration of vision-language models such as CLIP and Concept Bottleneck Models (CBMs) offers a promising approach to explaining deep neural network (DNN) decisions using concepts understandable by humans, addressing the black-box concern of DNNs. While CLIP provides both explainability and zero-shot classification capability, its pre-training on generic image and text data may limit its classification accuracy and applicability to medical image diagnostic tasks, creating a transfer learning problem. To maintain explainability and address transfer learning needs, CBM methods commonly design post-processing modules after the bottleneck module. However, this way has been ineffective. This paper takes an unconventional approach by re-examining the CBM framework through the lens of its geometrical representation as a simple linear classification system. The analysis uncovers that post-CBM fine-tuning modules merely rescale and shift the classification outcome of the system, failing to fully leverage the system's learning potential. We introduce an adaptive module strategically positioned between CLIP and CBM to bridge the gap between source and downstream domains. This simple yet effective approach enhances classification performance while preserving the explainability afforded by the framework. Our work offers a comprehensive solution that encompasses the entire process, from concept discovery to model training, providing a holistic recipe for leveraging the strengths of GPT, CLIP, and CBM.

Structural Attention: Rethinking Transformer for Unpaired Medical Image Synthesis

Unpaired medical image synthesis aims to provide complementary information for an accurate clinical diagnostics, and address challenges in obtaining aligned multi-modal medical scans. Transformer-based models excel in imaging translation tasks thanks to their ability to capture long-range dependencies. Although effective in supervised training settings, their performance falters in unpaired image synthesis, particularly in synthesizing structural details. This paper empirically demonstrates that, lacking strong inductive biases, Transformer can converge to non-optimal solutions in the absence of paired data. To address this, we introduce UNet Structured Transformer (UNest), a novel architecture incorporating structural inductive biases for unpaired medical image synthesis. We leverage the foundational Segment-Anything Model to precisely extract the foreground structure and perform structural attention within the main anatomy. This guides the model to learn key anatomical regions, thus improving structural synthesis under the lack of supervision in unpaired training. Evaluated on two public datasets, spanning three modalities, i.e., MR, CT, and PET, UNest improves recent methods by up to 19.30% across six medical image synthesis tasks. Our code is released at https://github.com/HieuPhan33/MICCAI2024-UNest.

CAPE: CAM as a Probabilistic Ensemble for Enhanced DNN Interpretation

Deep Neural Networks (DNNs) are widely used for visual classification tasks, but their complex computation process and black-box nature hinder decision transparency and interpretability. Class activation maps (CAMs) and recent variants provide ways to visually explain the DNN decision-making process by displaying 'attention' heatmaps of the DNNs. Nevertheless, the CAM explanation only offers relative attention information, that is, on an attention heatmap, we can interpret which image region is more or less important than the others. However, these regions cannot be meaningfully compared across classes, and the contribution of each region to the model's class prediction is not revealed. To address these challenges that ultimately lead to better DNN Interpretation, in this paper, we propose CAPE, a novel reformulation of CAM that provides a unified and probabilistically meaningful assessment of the contributions of image regions. We quantitatively and qualitatively compare CAPE with state-of-the-art CAM methods on CUB and ImageNet benchmark datasets to demonstrate enhanced interpretability. We also test on a cytology imaging dataset depicting a challenging Chronic Myelomonocytic Leukemia (CMML) diagnosis problem. Code is available at: https://github.com/AIML-MED/CAPE.

Decomposing Disease Descriptions for Enhanced Pathology Detection: A Multi-Aspect Vision-Language Matching Framework

Medical vision language pre-training (VLP) has emerged as a frontier of research, enabling zero-shot pathological recognition by comparing the query image with the textual descriptions for each disease. Due to the complex semantics of biomedical texts, current methods struggle to align medical images with key pathological findings in unstructured reports. This leads to the misalignment with the target disease's textual representation. In this paper, we introduce a novel VLP framework designed to dissect disease descriptions into their fundamental aspects, leveraging prior knowledge about the visual manifestations of pathologies. This is achieved by consulting a large language model and medical experts. Integrating a Transformer module, our approach aligns an input image with the diverse elements of a disease, generating aspect-centric image representations. By consolidating the matches from each aspect, we improve the compatibility between an image and its associated disease. Additionally, capitalizing on the aspect-oriented representations, we present a dual-head Transformer tailored to process known and unknown diseases, optimizing the comprehensive detection efficacy. Conducting experiments on seven downstream datasets, ours outperforms recent methods by up to 8.07% and 11.23% in AUC scores for seen and novel categories, respectively. Our code is released at \href{https://github.com/HieuPhan33/MAVL}{https://github.com/HieuPhan33/MAVL}.

Structure-Preserving Synthesis: MaskGAN for Unpaired MR-CT Translation

Medical image synthesis is a challenging task due to the scarcity of paired data. Several methods have applied CycleGAN to leverage unpaired data, but they often generate inaccurate mappings that shift the anatomy. This problem is further exacerbated when the images from the source and target modalities are heavily misaligned. Recently, current methods have aimed to address this issue by incorporating a supplementary segmentation network. Unfortunately, this strategy requires costly and time-consuming pixel-level annotations. To overcome this problem, this paper proposes MaskGAN, a novel and cost-effective framework that enforces structural consistency by utilizing automatically extracted coarse masks. Our approach employs a mask generator to outline anatomical structures and a content generator to synthesize CT contents that align with these structures. Extensive experiments demonstrate that MaskGAN outperforms state-of-the-art synthesis methods on a challenging pediatric dataset, where MR and CT scans are heavily misaligned due to rapid growth in children. Specifically, MaskGAN excels in preserving anatomical structures without the need for expert annotations. The code for this paper can be found at https://github.com/HieuPhan33/MaskGAN.

CNN Attention Guidance for Improved Orthopedics Radiographic Fracture Classification

Convolutional neural networks (CNNs) have gained significant popularity in orthopedic imaging in recent years due to their ability to solve fracture classification problems. A common criticism of CNNs is their opaque learning and reasoning process, making it difficult to trust machine diagnosis and the subsequent adoption of such algorithms in clinical setting. This is especially true when the CNN is trained with limited amount of medical data, which is a common issue as curating sufficiently large amount of annotated medical imaging data is a long and costly process. While interest has been devoted to explaining CNN learnt knowledge by visualizing network attention, the utilization of the visualized attention to improve network learning has been rarely investigated. This paper explores the effectiveness of regularizing CNN network with human-provided attention guidance on where in the image the network should look for answering clues. On two orthopedics radiographic fracture classification datasets, through extensive experiments we demonstrate that explicit human-guided attention indeed can direct correct network attention and consequently significantly improve classification performance. The development code for the proposed attention guidance is publicly available on GitHub.

Multi-centred Strong Augmentation via Contrastive Learning for Unsupervised Lesion Detection and Segmentation

The scarcity of high quality medical image annotations hinders the implementation of accurate clinical applications for detecting and segmenting abnormal lesions. To mitigate this issue, the scientific community is working on the development of unsupervised anomaly detection (UAD) systems that learn from a training set containing only normal (i.e., healthy) images, where abnormal samples (i.e., unhealthy) are detected and segmented based on how much they deviate from the learned distribution of normal samples. One significant challenge faced by UAD methods is how to learn effective low-dimensional image representations that are sensitive enough to detect and segment abnormal lesions of varying size, appearance and shape. To address this challenge, we propose a novel self-supervised UAD pre-training algorithm, named Multi-centred Strong Augmentation via Contrastive Learning (MSACL). MSACL learns representations by separating several types of strong and weak augmentations of normal image samples, where the weak augmentations represent normal images and strong augmentations denote synthetic abnormal images. To produce such strong augmentations, we introduce MedMix, a novel data augmentation strategy that creates new training images with realistic looking lesions (i.e., anomalies) in normal images. The pre-trained representations from MSACL are generic and can be used to improve the efficacy of different types of off-the-shelf state-of-the-art (SOTA) UAD models. Comprehensive experimental results show that the use of MSACL largely improves these SOTA UAD models on four medical imaging datasets from diverse organs, namely colonoscopy, fundus screening and covid-19 chest-ray datasets.

Constrained Contrastive Distribution Learning for Unsupervised Anomaly Detection and Localisation in Medical Images

Unsupervised anomaly detection (UAD) learns one-class classifiers exclusively with normal (i.e., healthy) images to detect any abnormal (i.e., unhealthy) samples that do not conform to the expected normal patterns. UAD has two main advantages over its fully supervised counterpart. Firstly, it is able to directly leverage large datasets available from health screening programs that contain mostly normal image samples, avoiding the costly manual labelling of abnormal samples and the subsequent issues involved in training with extremely class-imbalanced data. Further, UAD approaches can potentially detect and localise any type of lesions that deviate from the normal patterns. One significant challenge faced by UAD methods is how to learn effective low-dimensional image representations to detect and localise subtle abnormalities, generally consisting of small lesions. To address this challenge, we propose a novel self-supervised representation learning method, called Constrained Contrastive Distribution learning for anomaly detection (CCD), which learns fine-grained feature representations by simultaneously predicting the distribution of augmented data and image contexts using contrastive learning with pretext constraints. The learned representations can be leveraged to train more anomaly-sensitive detection models. Extensive experiment results show that our method outperforms current state-of-the-art UAD approaches on three different colonoscopy and fundus screening datasets. Our code is available at https://github.com/tianyu0207/CCD.

Weakly-supervised Video Anomaly Detection with Contrastive Learning of Long and Short-range Temporal Features

In this paper, we address the problem of weakly-supervised video anomaly detection, in which given video-level labels for training, we aim to identify in test videos, the snippets containing abnormal events. Although current methods based on multiple instance learning (MIL) show effective detection performance, they ignore important video temporal dependencies. Also, the number of abnormal snippets can vary per anomaly video, which complicates the training process of MIL-based methods because they tend to focus on the most abnormal snippet -- this can cause it to mistakenly select a normal snippet instead of an abnormal snippet, and also to fail to select all abnormal snippets available. We propose a novel method, named Multi-scale Temporal Network trained with top-K Contrastive Multiple Instance Learning (MTN-KMIL), to address the issues above. The main contributions of MTN-KMIL are: 1) a novel synthesis of a pyramid of dilated convolutions and a self-attention mechanism, with the former capturing the multi-scale short-range temporal dependencies between snippets and the latter capturing long-range temporal dependencies; and 2) a novel contrastive MIL learning method that enforces large margins between the top-K normal and abnormal video snippets at the feature representation level and anomaly score level, resulting in accurate anomaly discrimination. Extensive experiments show that our method outperforms several state-of-the-art methods by a large margin on three benchmark data sets (ShanghaiTech, UCF-Crime and XD-Violence). The code is available at https://github.com/tianyu0207/MTN-KMIL

Detecting, Localising and Classifying Polyps from Colonoscopy Videos using Deep Learning

In this paper, we propose and analyse a system that can automatically detect, localise and classify polyps from colonoscopy videos. The detection of frames with polyps is formulated as a few-shot anomaly classification problem, where the training set is highly imbalanced with the large majority of frames consisting of normal images and a small minority comprising frames with polyps. Colonoscopy videos may contain blurry images and frames displaying feces and water jet sprays to clean the colon -- such frames can mistakenly be detected as anomalies, so we have implemented a classifier to reject these two types of frames before polyp detection takes place. Next, given a frame containing a polyp, our method localises (with a bounding box around the polyp) and classifies it into five different classes. Furthermore, we study a method to improve the reliability and interpretability of the classification result using uncertainty estimation and classification calibration. Classification uncertainty and calibration not only help improve classification accuracy by rejecting low-confidence and high-uncertain results, but can be used by doctors to decide how to decide on the classification of a polyp. All the proposed detection, localisation and classification methods are tested using large data sets and compared with relevant baseline approaches.