In recent years, the deployment of supervised machine learning techniques for segmentation tasks has significantly increased. Nonetheless, the annotation process for extensive datasets remains costly, labor-intensive, and error-prone. While acquiring sufficiently large datasets to train deep learning models is feasible, these datasets often experience a distribution shift relative to the actual test data. This problem is particularly critical in the domain of medical imaging, where it adversely affects the efficacy of automatic segmentation models. In this work, we introduce DiffuSeg, a novel conditional diffusion model developed for medical image data, that exploits any labels to synthesize new images in the target domain. This allows a number of new research directions, including the segmentation task that motivates this work. Our method only requires label maps from any existing datasets and unlabelled images from the target domain for image diffusion. To learn the target domain knowledge, a feature factorization variational autoencoder is proposed to provide conditional information for the diffusion model. Consequently, the segmentation network can be trained with the given labels and the synthetic images, thus avoiding human annotations. Initially, we apply our method to the MNIST dataset and subsequently adapt it for use with medical image segmentation datasets, such as retinal fundus images for vessel segmentation and MRI images for heart segmentation. Our approach exhibits significant improvements over relevant baselines in both image generation and segmentation accuracy, especially in scenarios where annotations for the target dataset are unavailable during training. An open-source implementation of our approach can be released after reviewing..

While multi-task learning (MTL) has been widely developed for natural image analysis, its potential for enhancing performance in medical imaging remains relatively unexplored. Most methods formulate MTL as a multi-objective problem, inherently forcing all tasks to compete with each other during optimization. In this work, we propose a novel approach by formulating MTL as a multi-level optimization problem, in which the features learned from one task are optimized by benefiting from the other tasks. Specifically, we advocate for a cooperative approach where each task considers the features of others, enabling individual performance enhancement without detriment to others. To achieve this objective, we introduce a novel optimization strategy aimed at seeking flat minima for each sub-problem, fostering the learning of robust sub-models resilient to changes in other sub-models. We demonstrate the advantages of our proposed method through comprehensive parameter and comparison studies on the OrganCMNIST dataset. Additionally, we evaluate its efficacy on three eye-related medical image datasets, comparing its performance against other state-of-the-art MTL approaches. The results highlight the superiority of our method over existing approaches, showcasing its potential for training multi-purpose models in medical image analysis.

Improving overall performance is the ultimate goal of any machine learning (ML) algorithm. While it is a trivial task to explore multiple individual validation measurements, evaluating and monitoring overall performance can be complicated due to the highly nonlinear nature of the functions describing the relationships among different validation metrics, such as the Dice Similarity Coefficient (DSC) and Jaccard Index (JI). Therefore, it is naturally desirable to have a reliable validation algorithm or model that can integrate all existing validation metrics into a single value. This consolidated metric would enable straightforward assessment of an ML algorithm’s performance and identify areas for improvement. To deal with such a complex nonlinear problem, this study suggests a novel parameterized model named Adaptive Neuro-Fuzzy Inference Systems (ANFIS), which takes any set of input–output precise-imprecise data and uses a neuro-adaptive learning strategy to tune the parameters of the pre-defined membership functions. Our method can be accepted as an elegant and the state-of-the-art method for the nonlinear function approximation, which could be added directly to any convolutional neural networks (CNN) loss functions as the regularization term to generate a constrained-CNN-FUZZY model optimization. To demonstrate the ability of the purposed method and provide a practical explanation of the capability of ANFIS, we use deep CNN as a testing platform to consider the fact that one of the biggest challenges CNN-developers faced today is to reduce the mismatching between the provided input data and the predicted results monitored by different validation metrics. We first create a toy dataset using MNIST and investigate the properties of the proposed model. We then use a medical dataset to demonstrate our method’s efficacy on brain lesion segmentation. In both datasets, our method shows reliable validation results to guide researchers towards choosing performance metrics in a problem-aware manner, especially when the results of different validation metrics are too similar among models to determine the best one.

Image corruptions are common in the real world, for example images in the wild may come with unknown blur, bias field, noise, or other kinds of non-linear distributional shifts, thus hampering encoding methods and rendering downstream task unreliable. Image upgradation requires a complicated balance between high-level contextualised information and spatial specific details. Existing approaches to solving the problems are designed to focus on single corruption, which unavoidably results in poor performance when the acquisitions suffer from multiple degradations. In this study, we investigate the possibility of handling multiple degradations and enhancing the quality of images via deblurring, bias field correction, and denoising. To tackle the problems with propagating errors caused by independent learning, we propose a unified and scalable framework, which consists of three special decoders. Two decoders learn artifact attention from provided images thereby generating realistic individual artifact and multiple artifacts on single image; the third decoder is trained towards removing artifact on the synthetic image with multiple corruptions thereby generating high quality image. We additionally provide improvements over previous image degradation synthesis approaches by modelling multiple image degradations directly from data observations. We first create a toy MNIST dataset and investigate the properties of the proposed algorithm. We then use brain MRI datasets to demonstrate our method’s robustness, including both simulated (where necessary) and real-world artifacts. In addition, our method can be used for single/or multiple degradation(s) synthesis by implementing the learned degradation operators in a new domain from a given dataset. The code will be released upon acceptance of the paper.

Supervised machine learning methods have been widely developed for segmentation tasks in recent years. However, the quality of labels has high impact on the predictive performance of these algorithms. This issue is particularly acute in the medical image domain, where both the cost of annotation and the inter-observer variability are high. Different human experts contribute estimates of the "actual" segmentation labels in a typical label acquisition process, influenced by their personal biases and competency levels. The performance of automatic segmentation algorithms is limited when these noisy labels are used as the expert consensus label. In this work, we use two coupled CNNs to jointly learn, from purely noisy observations alone, the reliability of individual annotators and the expert consensus label distributions. The separation of the two is achieved by maximally describing the annotator's "unreliable behavior" (we call it "maximally unreliable") while achieving high fidelity with the noisy training data. We first create a toy segmentation dataset using MNIST and investigate the properties of the proposed algorithm. We then use three public medical imaging segmentation datasets to demonstrate our method's efficacy, including both simulated (where necessary) and real-world annotations: 1) ISBI2015 (multiple-sclerosis lesions); 2) BraTS (brain tumors); 3) LIDC-IDRI (lung abnormalities). Finally, we create a real-world multiple sclerosis lesion dataset (QSMSC at UCL: Queen Square Multiple Sclerosis Center at UCL, UK) with manual segmentations from 4 different annotators (3 radiologists with different level skills and 1 expert to generate the expert consensus label). In all datasets, our method consistently outperforms competing methods and relevant baselines, especially when the number of annotations is small and the amount of disagreement is large. The studies also reveal that the system is capable of capturing the complicated spatial characteristics of annotators' mistakes.

Recent years have seen increasing use of supervised learning methods for segmentation tasks. However, the predictive performance of these algorithms depends on the quality of labels. This problem is particularly pertinent in the medical image domain, where both the annotation cost and inter-observer variability are high. In a typical label acquisition process, different human experts provide their estimates of the ``true'' segmentation labels under the influence of their own biases and competence levels. Treating these noisy labels blindly as the ground truth limits the performance that automatic segmentation algorithms can achieve. In this work, we present a method for jointly learning, from purely noisy observations alone, the reliability of individual annotators and the true segmentation label distributions, using two coupled CNNs. The separation of the two is achieved by encouraging the estimated annotators to be maximally unreliable while achieving high fidelity with the noisy training data. We first define a toy segmentation dataset based on MNIST and study the properties of the proposed algorithm. We then demonstrate the utility of the method on three public medical imaging segmentation datasets with simulated (when necessary) and real diverse annotations: 1) MSLSC (multiple-sclerosis lesions); 2) BraTS (brain tumours); 3) LIDC-IDRI (lung abnormalities). In all cases, our method outperforms competing methods and relevant baselines particularly in cases where the number of annotations is small and the amount of disagreement is large. The experiments also show strong ability to capture the complex spatial characteristics of annotators' mistakes. Our code is available at \url{https://github.com/moucheng2017/LearnNoisyLabelsMedicalImages}.