Search

Medical imaging is spearheading the AI transformation of healthcare. Performance reporting is key to determine which methods should be translated into clinical practice. Frequently, broad conclusions are simply derived from mean performance values. In this paper, we argue that this common practice is often a misleading simplification as it ignores performance variability. Our contribution is threefold. (1) Analyzing all MICCAI segmentation papers (n = 221) published in 2023, we first observe that more than 50% of papers do not assess performance variability at all. Moreover, only one (0.5%) paper reported confidence intervals (CIs) for model performance. (2) To address the reporting bottleneck, we show that the unreported standard deviation (SD) in segmentation papers can be approximated by a second-order polynomial function of the mean Dice similarity coefficient (DSC). Based on external validation data from 56 previous MICCAI challenges, we demonstrate that this approximation can accurately reconstruct the CI of a method using information provided in publications. (3) Finally, we reconstructed 95% CIs around the mean DSC of MICCAI 2023 segmentation papers. The median CI width was 0.03 which is three times larger than the median performance gap between the first and second ranked method. For more than 60% of papers, the mean performance of the second-ranked method was within the CI of the first-ranked method. We conclude that current publications typically do not provide sufficient evidence to support which models could potentially be translated into clinical practice., Comment: Paper accepted at MICCAI 2024 conference

The influence of bias in datasets on the fairness of model predictions is a topic of ongoing research in various fields. We evaluate the performance of skin lesion classification using ResNet-based CNNs, focusing on patient sex variations in training data and three different learning strategies. We present a linear programming method for generating datasets with varying patient sex and class labels, taking into account the correlations between these variables. We evaluated the model performance using three different learning strategies: a single-task model, a reinforcing multi-task model, and an adversarial learning scheme. Our observations include: 1) sex-specific training data yields better results, 2) single-task models exhibit sex bias, 3) the reinforcement approach does not remove sex bias, 4) the adversarial model eliminates sex bias in cases involving only female patients, and 5) datasets that include male patients enhance model performance for the male subgroup, even when female patients are the majority. To generalise these findings, in future research, we will examine more demographic attributes, like age, and other possibly confounding factors, such as skin colour and artefacts in the skin lesions. We make all data and models available on GitHub., Comment: Submitted to MICCAI 2024

In this paper, we use spectral analysis to investigate transfer learning and study model sensitivity to frequency shortcuts in medical imaging. By analyzing the power spectrum density of both pre-trained and fine-tuned model gradients, as well as artificially generated frequency shortcuts, we observe notable differences in learning priorities between models pre-trained on natural vs medical images, which generally persist during fine-tuning. We find that when a model's learning priority aligns with the power spectrum density of an artifact, it results in overfitting to that artifact. Based on these observations, we show that source data editing can alter the model's resistance to shortcut learning.

Transfer learning has become an essential part of medical imaging classification algorithms, often leveraging ImageNet weights. The domain shift from natural to medical images has prompted alternatives such as RadImageNet, often showing comparable classification performance. However, it remains unclear whether the performance gains from transfer learning stem from improved generalization or shortcut learning. To address this, we conceptualize confounders by introducing the Medical Imaging Contextualized Confounder Taxonomy (MICCAT) and investigate a range of confounders across it -- whether synthetic or sampled from the data -- using two public chest X-ray and CT datasets. We show that ImageNet and RadImageNet achieve comparable classification performance, yet ImageNet is much more prone to overfitting to confounders. We recommend that researchers using ImageNet-pretrained models reexamine their model robustness by conducting similar experiments. Our code and experiments are available at https://github.com/DovileDo/source-matters.

Medical Imaging (MI) datasets are fundamental to artificial intelligence in healthcare. The accuracy, robustness, and fairness of diagnostic algorithms depend on the data (and its quality) used to train and evaluate the models. MI datasets used to be proprietary, but have become increasingly available to the public, including on community-contributed platforms (CCPs) like Kaggle or HuggingFace. While open data is important to enhance the redistribution of data's public value, we find that the current CCP governance model fails to uphold the quality needed and recommended practices for sharing, documenting, and evaluating datasets. In this paper, we conduct an analysis of publicly available machine learning datasets on CCPs, discussing datasets' context, and identifying limitations and gaps in the current CCP landscape. We highlight differences between MI and computer vision datasets, particularly in the potentially harmful downstream effects from poor adoption of recommended dataset management practices. We compare the analyzed datasets across several dimensions, including data sharing, data documentation, and maintenance. We find vague licenses, lack of persistent identifiers and storage, duplicates, and missing metadata, with differences between the platforms. Our research contributes to efforts in responsible data curation and AI algorithms for healthcare., Comment: Manuscript under review

Medical imaging papers often focus on methodology, but the quality of the algorithms and the validity of the conclusions are highly dependent on the datasets used. As creating datasets requires a lot of effort, researchers often use publicly available datasets, there is however no adopted standard for citing the datasets used in scientific papers, leading to difficulty in tracking dataset usage. In this work, we present two open-source tools we created that could help with the detection of dataset usage, a pipeline \url{https://github.com/TheoSourget/Public_Medical_Datasets_References} using OpenAlex and full-text analysis, and a PDF annotation software \url{https://github.com/TheoSourget/pdf_annotator} used in our study to manually label the presence of datasets. We applied both tools on a study of the usage of 20 publicly available medical datasets in papers from MICCAI and MIDL. We compute the proportion and the evolution between 2013 and 2023 of 3 types of presence in a paper: cited, mentioned in the full text, cited and mentioned. Our findings demonstrate the concentration of the usage of a limited set of datasets. We also highlight different citing practices, making the automation of tracking difficult., Comment: Accepted at MIDL conference Updated with the revised version after MIDL rebuttal

The advancement of machine learning algorithms in medical image analysis requires the expansion of training datasets. A popular and cost-effective approach is automated annotation extraction from free-text medical reports, primarily due to the high costs associated with expert clinicians annotating chest X-ray images. However, it has been shown that the resulting datasets are susceptible to biases and shortcuts. Another strategy to increase the size of a dataset is crowdsourcing, a widely adopted practice in general computer vision with some success in medical image analysis. In a similar vein to crowdsourcing, we enhance two publicly available chest X-ray datasets by incorporating non-expert annotations. However, instead of using diagnostic labels, we annotate shortcuts in the form of tubes. We collect 3.5k chest drain annotations for CXR14, and 1k annotations for 4 different tube types in PadChest. We train a chest drain detector with the non-expert annotations that generalizes well to expert labels. Moreover, we compare our annotations to those provided by experts and show "moderate" to "almost perfect" agreement. Finally, we present a pathology agreement study to raise awareness about ground truth annotations. We make our annotations and code available.

International benchmarking competitions have become fundamental for the comparative performance assessment of image analysis methods. However, little attention has been given to investigating what can be learnt from these competitions. Do they really generate scientific progress? What are common and successful participation strategies? What makes a solution superior to a competing method? To address this gap in the literature, we performed a multi-center study with all 80 competitions that were conducted in the scope of IEEE ISBI 2021 and MICCAI 2021. Statistical analyses performed based on comprehensive descriptions of the submitted algorithms linked to their rank as well as the underlying participation strategies revealed common characteristics of winning solutions. These typically include the use of multi-task learning (63%) and/or multi-stage pipelines (61%), and a focus on augmentation (100%), image preprocessing (97%), data curation (79%), and postprocessing (66%). The "typical" lead of a winning team is a computer scientist with a doctoral degree, five years of experience in biomedical image analysis, and four years of experience in deep learning. Two core general development strategies stood out for highly-ranked teams: the reflection of the metrics in the method design and the focus on analyzing and handling failure cases. According to the organizers, 43% of the winning algorithms exceeded the state of the art but only 11% completely solved the respective domain problem. The insights of our study could help researchers (1) improve algorithm development strategies when approaching new problems, and (2) focus on open research questions revealed by this work., Comment: accepted to CVPR 2023

While a key component to the success of deep learning is the availability of massive amounts of training data, medical image datasets are often limited in diversity and size. Transfer learning has the potential to bridge the gap between related yet different domains. For medical applications, however, it remains unclear whether it is more beneficial to pre-train on natural or medical images. We aim to shed light on this problem by comparing initialization on ImageNet and RadImageNet on seven medical classification tasks. Our work includes a replication study, which yields results contrary to previously published findings. In our experiments, ResNet50 models pre-trained on ImageNet tend to outperform those trained on RadImageNet. To gain further insights, we investigate the learned representations using Canonical Correlation Analysis (CCA) and compare the predictions of the different models. Our results indicate that, contrary to intuition, ImageNet and RadImageNet may converge to distinct intermediate representations, which appear to diverge further during fine-tuning. Despite these distinct representations, the predictions of the models remain similar. Our findings show that the similarity between networks before and after fine-tuning does not correlate with performance gains, suggesting that the advantages of transfer learning might not solely originate from the reuse of features in the early layers of a convolutional neural network., Comment: Published in TMLR

Validation metrics are key for the reliable tracking of scientific progress and for bridging the current chasm between artificial intelligence (AI) research and its translation into practice. However, increasing evidence shows that particularly in image analysis, metrics are often chosen inadequately in relation to the underlying research problem. This could be attributed to a lack of accessibility of metric-related knowledge: While taking into account the individual strengths, weaknesses, and limitations of validation metrics is a critical prerequisite to making educated choices, the relevant knowledge is currently scattered and poorly accessible to individual researchers. Based on a multi-stage Delphi process conducted by a multidisciplinary expert consortium as well as extensive community feedback, the present work provides the first reliable and comprehensive common point of access to information on pitfalls related to validation metrics in image analysis. Focusing on biomedical image analysis but with the potential of transfer to other fields, the addressed pitfalls generalize across application domains and are categorized according to a newly created, domain-agnostic taxonomy. To facilitate comprehension, illustrations and specific examples accompany each pitfall. As a structured body of information accessible to researchers of all levels of expertise, this work enhances global comprehension of a key topic in image analysis validation., Comment: Shared first authors: Annika Reinke and Minu D. Tizabi; shared senior authors: Lena Maier-Hein and Paul F. J\"ager. Published in Nature Methods. arXiv admin note: text overlap with arXiv:2206.01653

The number of international benchmarking competitions is steadily increasing in various fields of machine learning (ML) research and practice. So far, however, little is known about the common practice as well as bottlenecks faced by the community in tackling the research questions posed. To shed light on the status quo of algorithm development in the specific field of biomedical imaging analysis, we designed an international survey that was issued to all participants of challenges conducted in conjunction with the IEEE ISBI 2021 and MICCAI 2021 conferences (80 competitions in total). The survey covered participants' expertise and working environments, their chosen strategies, as well as algorithm characteristics. A median of 72% challenge participants took part in the survey. According to our results, knowledge exchange was the primary incentive (70%) for participation, while the reception of prize money played only a minor role (16%). While a median of 80 working hours was spent on method development, a large portion of participants stated that they did not have enough time for method development (32%). 25% perceived the infrastructure to be a bottleneck. Overall, 94% of all solutions were deep learning-based. Of these, 84% were based on standard architectures. 43% of the respondents reported that the data samples (e.g., images) were too large to be processed at once. This was most commonly addressed by patch-based training (69%), downsampling (37%), and solving 3D analysis tasks as a series of 2D tasks. K-fold cross-validation on the training set was performed by only 37% of the participants and only 50% of the participants performed ensembling based on multiple identical models (61%) or heterogeneous models (39%). 48% of the respondents applied postprocessing steps.

The availability of large public datasets and the increased amount of computing power have shifted the interest of the medical community to high-performance algorithms. However, little attention is paid to the quality of the data and their annotations. High performance on benchmark datasets may be reported without considering possible shortcuts or artifacts in the data, besides, models are not tested on subpopulation groups. With this work, we aim to raise awareness about shortcuts problems. We validate previous findings, and present a case study on chest X-rays using two publicly available datasets. We share annotations for a subset of pneumothorax images with drains. We conclude with general recommendations for medical image classification., Comment: Submitted to ISBI 2023

Furigana are pronunciation notes used in Japanese writing. Being able to detect these can help improve optical character recognition (OCR) performance or make more accurate digital copies of Japanese written media by correctly displaying furigana. This project focuses on detecting furigana in Japanese books and comics. While there has been research into the detection of Japanese text in general, there are currently no proposed methods for detecting furigana. We construct a new dataset containing Japanese written media and annotations of furigana. We propose an evaluation metric for such data which is similar to the evaluation protocols used in object detection except that it allows groups of objects to be labeled by one annotation. We propose a method for detection of furigana that is based on mathematical morphology and connected component analysis. We evaluate the detections of the dataset and compare different methods for text extraction. We also evaluate different types of images such as books and comics individually and discuss the challenges of each type of image. The proposed method reaches an F1-score of 76\% on the dataset. The method performs well on regular books, but less so on comics, and books of irregular format. Finally, we show that the proposed method can improve the performance of OCR by 5\% on the manga109 dataset. Source code is available via \texttt{\url{https://github.com/nikolajkb/FuriganaDetection}}, Comment: This project was originally submitted by NKB in fulfillment of the 30 ECTS MSc thesis at the IT University of Copenhagen

Increasing evidence shows that flaws in machine learning (ML) algorithm validation are an underestimated global problem. Particularly in automatic biomedical image analysis, chosen performance metrics often do not reflect the domain interest, thus failing to adequately measure scientific progress and hindering translation of ML techniques into practice. To overcome this, our large international expert consortium created Metrics Reloaded, a comprehensive framework guiding researchers in the problem-aware selection of metrics. Following the convergence of ML methodology across application domains, Metrics Reloaded fosters the convergence of validation methodology. The framework was developed in a multi-stage Delphi process and is based on the novel concept of a problem fingerprint - a structured representation of the given problem that captures all aspects that are relevant for metric selection, from the domain interest to the properties of the target structure(s), data set and algorithm output. Based on the problem fingerprint, users are guided through the process of choosing and applying appropriate validation metrics while being made aware of potential pitfalls. Metrics Reloaded targets image analysis problems that can be interpreted as a classification task at image, object or pixel level, namely image-level classification, object detection, semantic segmentation, and instance segmentation tasks. To improve the user experience, we implemented the framework in the Metrics Reloaded online tool, which also provides a point of access to explore weaknesses, strengths and specific recommendations for the most common validation metrics. The broad applicability of our framework across domains is demonstrated by an instantiation for various biological and medical image analysis use cases., Comment: Shared first authors: Lena Maier-Hein, Annika Reinke. arXiv admin note: substantial text overlap with arXiv:2104.05642 Published in Nature Methods

In the pharmaceutical industry, the maintenance of production machines must be audited by the regulator. In this context, the problem of predictive maintenance is not when to maintain a machine, but what parts to maintain at a given point in time. The focus shifts from the entire machine to its component parts and prediction becomes a classification problem. In this paper, we focus on rolling-elements bearings and we propose a framework for predicting their degradation stages automatically. Our main contribution is a k-means bearing lifetime segmentation method based on high-frequency bearing vibration signal embedded in a latent low-dimensional subspace using an AutoEncoder. Given high-frequency vibration data, our framework generates a labeled dataset that is used to train a supervised model for bearing degradation stage detection. Our experimental results, based on the FEMTO Bearing dataset, show that our framework is scalable and that it provides reliable and actionable predictions for a range of different bearings., Comment: Submitted to the KDD Applied Data Science track

Today, deep convolutional neural networks (CNNs) have demonstrated state-of-the-art performance for medical image segmentation, on various imaging modalities and tasks. Despite early success, segmentation networks may still generate anatomically aberrant segmentations, with holes or inaccuracies near the object boundaries. To enforce anatomical plausibility, recent research studies have focused on incorporating prior knowledge such as object shape or boundary, as constraints in the loss function. Prior integrated could be low-level referring to reformulated representations extracted from the ground-truth segmentations, or high-level representing external medical information such as the organ's shape or size. Over the past few years, prior-based losses exhibited a rising interest in the research field since they allow integration of expert knowledge while still being architecture-agnostic. However, given the diversity of prior-based losses on different medical imaging challenges and tasks, it has become hard to identify what loss works best for which dataset. In this paper, we establish a benchmark of recent prior-based losses for medical image segmentation. The main objective is to provide intuition onto which losses to choose given a particular task or dataset. To this end, four low-level and high-level prior-based losses are selected. The considered losses are validated on 8 different datasets from a variety of medical image segmentation challenges including the Decathlon, the ISLES and the WMH challenge. Results show that whereas low-level prior-based losses can guarantee an increase in performance over the Dice loss baseline regardless of the dataset characteristics, high-level prior-based losses can increase anatomical plausibility as per data characteristics., Comment: To be submitted to SPIE: Journal of Medical Imaging

We present ENHANCE, an open dataset with multiple annotations to complement the existing ISIC and PH2 skin lesion classification datasets. This dataset contains annotations of visual ABC (asymmetry, border, colour) features from non-expert annotation sources: undergraduate students, crowd workers from Amazon MTurk and classic image processing algorithms. In this paper we first analyse the correlations between the annotations and the diagnostic label of the lesion, as well as study the agreement between different annotation sources. Overall we find weak correlations of non-expert annotations with the diagnostic label, and low agreement between different annotation sources. We then study multi-task learning (MTL) with the annotations as additional labels, and show that non-expert annotations can improve (ensembles of) state-of-the-art convolutional neural networks via MTL. We hope that our dataset can be used in further research into multiple annotations and/or MTL. All data and models are available on Github: https://github.com/raumannsr/ENHANCE., Comment: Accepted for publication at the Journal of Machine Learning for Biomedical Imaging (MELBA) https://www.melba-journal.org

Transfer learning is a commonly used strategy for medical image classification, especially via pretraining on source data and fine-tuning on target data. There is currently no consensus on how to choose appropriate source data, and in the literature we can find both evidence of favoring large natural image datasets such as ImageNet, and evidence of favoring more specialized medical datasets. In this paper we perform a systematic study with nine source datasets with natural or medical images, and three target medical datasets, all with 2D images. We find that ImageNet is the source leading to the highest performances, but also that larger datasets are not necessarily better. We also study different definitions of data similarity. We show that common intuitions about similarity may be inaccurate, and therefore not sufficient to predict an appropriate source a priori. Finally, we discuss several steps needed for further research in this field, especially with regard to other types (for example 3D) medical images. Our experiments and pretrained models are available via \url{https://www.github.com/vcheplygina/cats-scans}

While the importance of automatic image analysis is continuously increasing, recent meta-research revealed major flaws with respect to algorithm validation. Performance metrics are particularly key for meaningful, objective, and transparent performance assessment and validation of the used automatic algorithms, but relatively little attention has been given to the practical pitfalls when using specific metrics for a given image analysis task. These are typically related to (1) the disregard of inherent metric properties, such as the behaviour in the presence of class imbalance or small target structures, (2) the disregard of inherent data set properties, such as the non-independence of the test cases, and (3) the disregard of the actual biomedical domain interest that the metrics should reflect. This living dynamically document has the purpose to illustrate important limitations of performance metrics commonly applied in the field of image analysis. In this context, it focuses on biomedical image analysis problems that can be phrased as image-level classification, semantic segmentation, instance segmentation, or object detection task. The current version is based on a Delphi process on metrics conducted by an international consortium of image analysis experts from more than 60 institutions worldwide., Comment: Shared first authors: Annika Reinke and Minu D. Tizabi. This is a dynamic paper on limitations of commonly used metrics. It discusses metrics for image-level classification, semantic and instance segmentation, and object detection. For missing use cases, comments or questions, please contact a.reinke@dkfz.de. Substantial contributions to this document will be acknowledged with a co-authorship

Medical imaging is an important research field with many opportunities for improving patients' health. However, there are a number of challenges that are slowing down the progress of the field as a whole, such optimizing for publication. In this paper we reviewed several problems related to choosing datasets, methods, evaluation metrics, and publication strategies. With a review of literature and our own analysis, we show that at every step, potential biases can creep in. On a positive note, we also see that initiatives to counteract these problems are already being started. Finally we provide a broad range of recommendations on how to further these address problems in the future. For reproducibility, data and code for our analyses are available on \url{https://github.com/GaelVaroquaux/ml_med_imaging_failures}

Despite the successes of deep learning techniques at detecting objects in medical images, false positive detections occur which may hinder an accurate diagnosis. We propose a technique to reduce false positive detections made by a neural network using an SVM classifier trained with features derived from the uncertainty map of the neural network prediction. We demonstrate the effectiveness of this method for the detection of liver lesions on a dataset of abdominal MR images. We find that the use of a dropout rate of 0.5 produces the least number of false positives in the neural network predictions and the trained classifier filters out approximately 90% of these false positives detections in the test-set., Comment: Accepted at IEEE ISBI 2021

Measuring airways in chest computed tomography (CT) scans is important for characterizing diseases such as cystic fibrosis, yet very time-consuming to perform manually. Machine learning algorithms offer an alternative, but need large sets of annotated scans for good performance. We investigate whether crowdsourcing can be used to gather airway annotations. We generate image slices at known locations of airways in 24 subjects and request the crowd workers to outline the airway lumen and airway wall. After combining multiple crowd workers, we compare the measurements to those made by the experts in the original scans. Similar to our preliminary study, a large portion of the annotations were excluded, possibly due to workers misunderstanding the instructions. After excluding such annotations, moderate to strong correlations with the expert can be observed, although these correlations are slightly lower than inter-expert correlations. Furthermore, the results across subjects in this study are quite variable. Although the crowd has potential in annotating airways, further development is needed for it to be robust enough for gathering annotations in practice. For reproducibility, data and code are available online: \url{http://github.com/adriapr/crowdairway.git}.

Today, deep convolutional neural networks (CNNs) have demonstrated state of the art performance for supervised medical image segmentation, across various imaging modalities and tasks. Despite early success, segmentation networks may still generate anatomically aberrant segmentations, with holes or inaccuracies near the object boundaries. To mitigate this effect, recent research works have focused on incorporating spatial information or prior knowledge to enforce anatomically plausible segmentation. If the integration of prior knowledge in image segmentation is not a new topic in classical optimization approaches, it is today an increasing trend in CNN based image segmentation, as shown by the growing literature on the topic. In this survey, we focus on high level prior, embedded at the loss function level. We categorize the articles according to the nature of the prior: the object shape, size, topology, and the inter-regions constraints. We highlight strengths and limitations of current approaches, discuss the challenge related to the design and the integration of prior-based losses, and the optimization strategies, and draw future research directions.

Early detection of lung cancer has been proven to decrease mortality significantly. A recent development in computed tomography (CT), spectral CT, can potentially improve diagnostic accuracy, as it yields more information per scan than regular CT. However, the shear workload involved with analyzing a large number of scans drives the need for automated diagnosis methods. Therefore, we propose a detection and classification system for lung nodules in CT scans. Furthermore, we want to observe whether spectral images can increase classifier performance. For the detection of nodules we trained a VGG-like 3D convolutional neural net (CNN). To obtain a primary tumor classifier for our dataset we pre-trained a 3D CNN with similar architecture on nodule malignancies of a large publicly available dataset, the LIDC-IDRI dataset. Subsequently we used this pre-trained network as feature extractor for the nodules in our dataset. The resulting feature vectors were classified into two (benign/malignant) and three (benign/primary lung cancer/metastases) classes using support vector machine (SVM). This classification was performed both on nodule- and scan-level. We obtained state-of-the art performance for detection and malignancy regression on the LIDC-IDRI database. Classification performance on our own dataset was higher for scan- than for nodule-level predictions. For the three-class scan-level classification we obtained an accuracy of 78\%. Spectral features did increase classifier performance, but not significantly. Our work suggests that a pre-trained feature extractor can be used as primary tumor origin classifier for lung nodules, eliminating the need for elaborate fine-tuning of a new network and large datasets. Code is available at \url{https://github.com/tueimage/lung-nodule-msc-2018}., Comment: MSc thesis Linde Hesse

One of the critical challenges in machine learning applications is to have fair predictions. There are numerous recent examples in various domains that convincingly show that algorithms trained with biased datasets can easily lead to erroneous or discriminatory conclusions. This is even more crucial in clinical applications where the predictive algorithms are designed mainly based on a limited or given set of medical images and demographic variables such as age, sex and race are not taken into account. In this work, we conduct a survey of the MICCAI 2018 proceedings to investigate the common practice in medical image analysis applications. Surprisingly, we found that papers focusing on diagnosis rarely describe the demographics of the datasets used, and the diagnosis is purely based on images. In order to highlight the importance of considering the demographics in diagnosis tasks, we used a publicly available dataset of skin lesions. We then demonstrate that a classifier with an overall area under the curve (AUC) of 0.83 has variable performance between 0.76 and 0.91 on subgroups based on age and sex, even though the training set was relatively balanced. Moreover, we show that it is possible to learn unbiased features by explicitly using demographic variables in an adversarial training setup, which leads to balanced scores per subgroups. Finally, we discuss the implications of these results and provide recommendations for further research.

Deep learning has led to state-of-the-art results for many medical imaging tasks, such as segmentation of different anatomical structures. With the increased numbers of deep learning publications and openly available code, the approach to choosing a model for a new task becomes more complicated, while time and (computational) resources are limited. A possible solution to choosing a model efficiently is meta-learning, a learning method in which prior performance of a model is used to predict the performance for new tasks. We investigate meta-learning for segmentation across ten datasets of different organs and modalities. We propose four ways to represent each dataset by meta-features: one based on statistical features of the images and three are based on deep learning features. We use support vector regression and deep neural networks to learn the relationship between the meta-features and prior model performance. On three external test datasets these methods give Dice scores within 0.10 of the true performance. These results demonstrate the potential of meta-learning in medical imaging.

Machine learning has a recognised need for large amounts of annotated data. Due to the high cost of expert annotations, crowdsourcing, where non-experts are asked to label or outline images, has been proposed as an alternative. Although many promising results are reported, the quality of diagnostic crowdsourced labels is still unclear. We propose to address this by instead asking the crowd about visual features of the images, which can be provided more intuitively, and by using these features in a multi-task learning framework through ensemble strategies. We compare our proposed approach to a baseline model with a set of 2000 skin lesions from the ISIC 2017 challenge dataset. The baseline model only predicts a binary label from the skin lesion image, while our multi-task model also predicts one of the following features: asymmetry of the lesion, border irregularity and color. We show that multi-task models with individual crowdsourced features have limited effect on the model, but when combined in an ensembles, leads to improved generalisation. The area under the receiver operating characteristic curve is 0.794 for the baseline model and 0.811 and 0.808 for multi-task ensembles respectively. Finally, we discuss the findings, identify some limitations and recommend directions for further research. The code of the models is available at https://github.com/raumannsr/hints_crowd.

Rapid advances in image processing capabilities have been seen across many domains, fostered by the application of machine learning algorithms to "big-data". However, within the realm of medical image analysis, advances have been curtailed, in part, due to the limited availability of large-scale, well-annotated datasets. One of the main reasons for this is the high cost often associated with producing large amounts of high-quality meta-data. Recently, there has been growing interest in the application of crowdsourcing for this purpose; a technique that has proven effective for creating large-scale datasets across a range of disciplines, from computer vision to astrophysics. Despite the growing popularity of this approach, there has not yet been a comprehensive literature review to provide guidance to researchers considering using crowdsourcing methodologies in their own medical imaging analysis. In this survey, we review studies applying crowdsourcing to the analysis of medical images, published prior to July 2018. We identify common approaches, challenges and considerations, providing guidance of utility to researchers adopting this approach. Finally, we discuss future opportunities for development within this emerging domain., Comment: Submitted to Human Computation

Transfer learning is a widely used strategy in medical image analysis. Instead of only training a network with a limited amount of data from the target task of interest, we can first train the network with other, potentially larger source datasets, creating a more robust model. The source datasets do not have to be related to the target task. For a classification task in lung CT images, we could use both head CT images, or images of cats, as the source. While head CT images appear more similar to lung CT images, the number and diversity of cat images might lead to a better model overall. In this survey we review a number of papers that have performed similar comparisons. Although the answer to which strategy is best seems to be "it depends", we discuss a number of research directions we need to take as a community, to gain more understanding of this topic., Comment: Accepted to Current Opinion in Biomedical Engineering

In many pattern recognition problems, a single feature vector is not sufficient to describe an object. In multiple instance learning (MIL), objects are represented by sets (\emph{bags}) of feature vectors (\emph{instances}). This requires an adaptation of standard supervised classifiers in order to train and evaluate on these bags of instances. Like for supervised classification, several benchmark datasets and numerous classifiers are available for MIL. When performing a comparison of different MIL classifiers, it is important to understand the differences of the datasets, used in the comparison. Seemingly different (based on factors such as dimensionality) datasets may elicit very similar behaviour in classifiers, and vice versa. This has implications for what kind of conclusions may be drawn from the comparison results. We aim to give an overview of the variability of available benchmark datasets and some popular MIL classifiers. We use a dataset dissimilarity measure, based on the differences between the ROC-curves obtained by different classifiers, and embed this dataset dissimilarity matrix into a low-dimensional space. Our results show that conceptually similar datasets can behave very differently. We therefore recommend examining such dataset characteristics when making comparisons between existing and new MIL classifiers. The datasets are available via Figshare at \url{https://bit.ly/2K9iTja}., Comment: Published at SIMBAD 2015 workshop

Classifiers for medical image analysis are often trained with a single consensus label, based on combining labels given by experts or crowds. However, disagreement between annotators may be informative, and thus removing it may not be the best strategy. As a proof of concept, we predict whether a skin lesion from the ISIC 2017 dataset is a melanoma or not, based on crowd annotations of visual characteristics of that lesion. We compare using the mean annotations, illustrating consensus, to standard deviations and other distribution moments, illustrating disagreement. We show that the mean annotations perform best, but that the disagreement measures are still informative. We also make the crowd annotations used in this paper available at \url{https://figshare.com/s/5cbbce14647b66286544}., Comment: Accepted for publication at MICCAI LABELS 2018

Supervised feature learning using convolutional neural networks (CNNs) can provide concise and disease relevant representations of medical images. However, training CNNs requires annotated image data. Annotating medical images can be a time-consuming task and even expert annotations are subject to substantial inter- and intra-rater variability. Assessing visual similarity of images instead of indicating specific pathologies or estimating disease severity could allow non-experts to participate, help uncover new patterns, and possibly reduce rater variability. We consider the task of assessing emphysema extent in chest CT scans. We derive visual similarity triplets from visually assessed emphysema extent and learn a low dimensional embedding using CNNs. We evaluate the networks on 973 images, and show that the CNNs can learn disease relevant feature representations from derived similarity triplets. To our knowledge this is the first medical image application where similarity triplets has been used to learn a feature representation that can be used for embedding unseen test images, Comment: 10 pages. Submitted to LABELS2018 - MICCAI Workshop on Large-scale Annotation of Biomedical data and Expert Label Synthesis

Machine learning (ML) algorithms have made a tremendous impact in the field of medical imaging. While medical imaging datasets have been growing in size, a challenge for supervised ML algorithms that is frequently mentioned is the lack of annotated data. As a result, various methods which can learn with less/other types of supervision, have been proposed. We review semi-supervised, multiple instance, and transfer learning in medical imaging, both in diagnosis/detection or segmentation tasks. We also discuss connections between these learning scenarios, and opportunities for future research., Comment: Submitted to Medical Image Analysis

Supervised learning is ubiquitous in medical image analysis. In this paper we consider the problem of meta-learning -- predicting which methods will perform well in an unseen classification problem, given previous experience with other classification problems. We investigate the first step of such an approach: how to quantify the similarity of different classification problems. We characterize datasets sampled from six classification problems by performance ranks of simple classifiers, and define the similarity by the inverse of Euclidean distance in this meta-feature space. We visualize the similarities in a 2D space, where meaningful clusters start to emerge, and show that the proposed representation can be used to classify datasets according to their origin with 89.3\% accuracy. These findings, together with the observations of recent trends in machine learning, suggest that meta-learning could be a valuable tool for the medical imaging community.

Measuring airways in chest computed tomography (CT) images is important for characterizing diseases such as cystic fibrosis, yet very time-consuming to perform manually. Machine learning algorithms offer an alternative, but need large sets of annotated data to perform well. We investigate whether crowdsourcing can be used to gather airway annotations which can serve directly for measuring the airways, or as training data for the algorithms. We generate image slices at known locations of airways and request untrained crowd workers to outline the airway lumen and airway wall. Our results show that the workers are able to interpret the images, but that the instructions are too complex, leading to many unusable annotations. After excluding unusable annotations, quantitative results show medium to high correlations with expert measurements of the airways. Based on this positive experience, we describe a number of further research directions and provide insight into the challenges of crowdsourcing in medical images from the perspective of first-time users.

A method for automatically quantifying emphysema regions using High-Resolution Computed Tomography (HRCT) scans of patients with chronic obstructive pulmonary disease (COPD) that does not require manually annotated scans for training is presented. HRCT scans of controls and of COPD patients with diverse disease severity are acquired at two different centers. Textural features from co-occurrence matrices and Gaussian filter banks are used to characterize the lung parenchyma in the scans. Two robust versions of multiple instance learning (MIL) classifiers, miSVM and MILES, are investigated. The classifiers are trained with the weak labels extracted from the forced expiratory volume in one minute (FEV$_1$) and diffusing capacity of the lungs for carbon monoxide (DLCO). At test time, the classifiers output a patient label indicating overall COPD diagnosis and local labels indicating the presence of emphysema. The classifier performance is compared with manual annotations by two radiologists, a classical density based method, and pulmonary function tests (PFTs). The miSVM classifier performed better than MILES on both patient and emphysema classification. The classifier has a stronger correlation with PFT than the density based method, the percentage of emphysema in the intersection of annotations from both radiologists, and the percentage of emphysema annotated by one of the radiologists. The correlation between the classifier and the PFT is only outperformed by the second radiologist. The method is therefore promising for facilitating assessment of emphysema and reducing inter-observer variability., Comment: Accepted at PLoS ONE

We address the problem of \emph{instance label stability} in multiple instance learning (MIL) classifiers. These classifiers are trained only on globally annotated images (bags), but often can provide fine-grained annotations for image pixels or patches (instances). This is interesting for computer aided diagnosis (CAD) and other medical image analysis tasks for which only a coarse labeling is provided. Unfortunately, the instance labels may be unstable. This means that a slight change in training data could potentially lead to abnormalities being detected in different parts of the image, which is undesirable from a CAD point of view. Despite MIL gaining popularity in the CAD literature, this issue has not yet been addressed. We investigate the stability of instance labels provided by several MIL classifiers on 5 different datasets, of which 3 are medical image datasets (breast histopathology, diabetic retinopathy and computed tomography lung images). We propose an unsupervised measure to evaluate instance stability, and demonstrate that a performance-stability trade-off can be made when comparing MIL classifiers., Comment: Published at MICCAI 2015

Chronic obstructive pulmonary disease (COPD) is a lung disease where early detection benefits the survival rate. COPD can be quantified by classifying patches of computed tomography images, and combining patch labels into an overall diagnosis for the image. As labeled patches are often not available, image labels are propagated to the patches, incorrectly labeling healthy patches in COPD patients as being affected by the disease. We approach quantification of COPD from lung images as a multiple instance learning (MIL) problem, which is more suitable for such weakly labeled data. We investigate various MIL assumptions in the context of COPD and show that although a concept region with COPD-related disease patterns is present, considering the whole distribution of lung tissue patches improves the performance. The best method is based on averaging instances and obtains an AUC of 0.742, which is higher than the previously reported best of 0.713 on the same dataset. Using the full training set further increases performance to 0.776, which is significantly higher (DeLong test) than previous results., Comment: Published at International Conference on Pattern Recognition (ICPR) 2014

Supervised learning has been very successful for automatic segmentation of images from a single scanner. However, several papers report deteriorated performances when using classifiers trained on images from one scanner to segment images from other scanners. We propose a transfer learning classifier that adapts to differences between training and test images. This method uses a weighted ensemble of classifiers trained on individual images. The weight of each classifier is determined by the similarity between its training image and the test image. We examine three unsupervised similarity measures, which can be used in scenarios where no labeled data from a newly introduced scanner or scanning protocol is available. The measures are based on a divergence, a bag distance, and on estimating the labels with a clustering procedure. These measures are asymmetric. We study whether the asymmetry can improve classification. Out of the three similarity measures, the bag similarity measure is the most robust across different studies and achieves excellent results on four brain tissue segmentation datasets and three white matter lesion segmentation datasets, acquired at different centers and with different scanners and scanning protocols. We show that the asymmetry can indeed be informative, and that computing the similarity from the test image to the training images is more appropriate than the opposite direction.

Chronic obstructive pulmonary disease (COPD) is a lung disease which can be quantified using chest computed tomography (CT) scans. Recent studies have shown that COPD can be automatically diagnosed using weakly supervised learning of intensity and texture distributions. However, up till now such classifiers have only been evaluated on scans from a single domain, and it is unclear whether they would generalize across domains, such as different scanners or scanning protocols. To address this problem, we investigate classification of COPD in a multi-center dataset with a total of 803 scans from three different centers, four different scanners, with heterogenous subject distributions. Our method is based on Gaussian texture features, and a weighted logistic classifier, which increases the weights of samples similar to the test data. We show that Gaussian texture features outperform intensity features previously used in multi-center classification tasks. We also show that a weighting strategy based on a classifier that is trained to discriminate between scans from different domains, can further improve the results. To encourage further research into transfer learning methods for classification of COPD, upon acceptance of the paper we will release two feature datasets used in this study on http://bigr.nl/research/projects/copd, Comment: Accepted at Journal of Biomedical and Health Informatics

Multiple instance learning (MIL) is a form of weakly supervised learning where training instances are arranged in sets, called bags, and a label is provided for the entire bag. This formulation is gaining interest because it naturally fits various problems and allows to leverage weakly labeled data. Consequently, it has been used in diverse application fields such as computer vision and document classification. However, learning from bags raises important challenges that are unique to MIL. This paper provides a comprehensive survey of the characteristics which define and differentiate the types of MIL problems. Until now, these problem characteristics have not been formally identified and described. As a result, the variations in performance of MIL algorithms from one data set to another are difficult to explain. In this paper, MIL problem characteristics are grouped into four broad categories: the composition of the bags, the types of data distribution, the ambiguity of instance labels, and the task to be performed. Methods specialized to address each category are reviewed. Then, the extent to which these characteristics manifest themselves in key MIL application areas are described. Finally, experiments are conducted to compare the performance of 16 state-of-the-art MIL methods on selected problem characteristics. This paper provides insight on how the problem characteristics affect MIL algorithms, recommendations for future benchmarking and promising avenues for research.

Many classification problems can be difficult to formulate directly in terms of the traditional supervised setting, where both training and test samples are individual feature vectors. There are cases in which samples are better described by sets of feature vectors, that labels are only available for sets rather than individual samples, or, if individual labels are available, that these are not independent. To better deal with such problems, several extensions of supervised learning have been proposed, where either training and/or test objects are sets of feature vectors. However, having been proposed rather independently of each other, their mutual similarities and differences have hitherto not been mapped out. In this work, we provide an overview of such learning scenarios, propose a taxonomy to illustrate the relationships between them, and discuss directions for further research in these areas.