CMC-Net: 3D calf muscle compartment segmentation with sparse annotation

Accurate 3D segmentation of calf muscle compartments in volumetric MR images is essential to diagnose as well as assess progression of muscular diseases. Recently, good segmentation performance was achieved using state-of-the-art deep learning approaches, which, however, require large amounts of annotated data for training. Considering that obtaining sufficiently large medical image annotation datasets is often difficult, time-consuming, and requires expert knowledge, minimizing the necessary sizes of expert-annotated training datasets is of great importance. This paper reports CMC-Net, a new deep learning framework for calf muscle compartment segmentation in 3D MR images that selects an effective small subset of 2D slices from the 3D images to be labelled, while also utilizing unannotated slices to facilitate proper generalization of the subsequent training steps. Our model consists of three parts: (1) an unsupervised method to select the most representative 2D slices on which expert annotation is performed; (2) ensemble model training employing these annotated as well as additional unannotated 2D slices; (3) a model-tuning method using pseudo-labels generated by the ensemble model that results in a trained deep network capable of accurate 3D segmentations. Experiments on segmentation of calf muscle compartments in 3D MR images show that our new approach achieves good performance with very small annotation ratios, and when utilizing full annotation, it outperforms state-of-the-art full annotation segmentation methods. Additional experiments on a 3D MR thigh dataset further verify the ability of our method in segmenting leg muscle groups with sparse annotation.     

Beyond fine-tuning: Classifying high resolution mammograms using function-preserving transformations

The task of classifying mammograms is very challenging because the lesion is usually small in the high resolution image. The current state-of-the-art approaches for medical image classification rely on using the de-facto method for convolutional neural networks-fine-tuning. However, there are fundamental differences between natural images and medical images, which based on existing evidence from the literature, limits the overall performance gain when designed with algorithmic approaches. In this paper, we propose to go beyond fine-tuning by introducing a novel framework called MorphHR, in which we highlight a new transfer learning scheme. The idea behind the proposed framework is to integrate function-preserving transformations, for any continuous non-linear activation neurons, to internally regularise the network for improving mammograms classification. The proposed solution offers two major advantages over the existing techniques. Firstly and unlike fine-tuning, the proposed approach allows for modifying not only the last few layers but also several of the first ones on a deep ConvNet. By doing this, we can design the network front to be suitable for learning domain specific features. Secondly, the proposed scheme is scalable to hardware. Therefore, one can fit high resolution images on standard GPU memory. We show that by using high resolution images, one prevents losing relevant information. We demonstrate, through numerical and visual experiments, that the proposed approach yields to a significant improvement in the classification performance over state-of-the-art techniques, and is indeed on a par with radiology experts. Moreover and for generalisation purposes, we show the effectiveness of the proposed learning scheme on another large dataset, the ChestX-ray14, surpassing current state-of-the-art techniques.     

Information bottleneck-based interpretable multitask network for breast cancer classification and segmentation

Breast cancer is one of the most common causes of death among women worldwide. Early signs of breast cancer can be an abnormality depicted on breast images (e.g., mammography or breast ultrasonography). However, reliable interpretation of breast images requires intensive labor and physicians with extensive experience. Deep learning is evolving breast imaging diagnosis by introducing a second opinion to physicians. However, most deep learning-based breast cancer analysis algorithms lack interpretability because of their black box nature, which means that domain experts cannot understand why the algorithms predict a label. In addition, most deep learning algorithms are formulated as a single-task-based model that ignores correlations between different tasks (e.g., tumor classification and segmentation). In this paper, we propose an interpretable multitask information bottleneck network (MIB-Net) to accomplish simultaneous breast tumor classification and segmentation. MIB-Net maximizes the mutual information between the latent representations and class labels while minimizing information shared by the latent representations and inputs. In contrast from existing models, our MIB-Net generates a contribution score map that offers an interpretable aid for physicians to understand the model’s decision-making process. In addition, MIB-Net implements multitask learning and further proposes a dual prior knowledge guidance strategy to enhance deep task correlation. Our evaluations are carried out on three breast image datasets in different modalities. Our results show that the proposed framework is not only able to help physicians better understand the model’s decisions but also improve breast tumor classification and segmentation accuracy over representative state-of-the-art models. Our code is available at https://github.com/jxw0810/MIB-Net.     

Implementing Peer Learning in Clinical Education: A Framework to Address Challenges In the “Real World”

Phenomenon: Peer learning has many benefits and can assist students in gaining the educational skills required in future years when they become teachers themselves. Peer learning may be particularly useful in clinical learning environments, where students report feeling marginalized, overwhelmed, and unsupported. Educational interventions often fail in the workplace environment, as they are often conceived in the “ideal” rather than the complex, messy real world. This work sought to explore barriers and facilitators to implementing peer learning activities in a clinical curriculum. Approach: Previous peer learning research results and a matrix of empirically derived peer learning activities were presented to local clinical education experts to generate discussion around the realities of implementing such activities. Potential barriers and limitations of and strategies for implementing peer learning in clinical education were the focus of the individual interviews. Findings: Thematic analysis of the data identified three key considerations for real-world implementation of peer learning: culture, epistemic authority, and the primacy of patient-centered care. Strategies for peer learning implementation were also developed from themes within the data, focusing on developing a culture of safety in which peer learning could be undertaken, engaging both educators and students, and establishing expectations for the use of peer learning. Insights: This study identified considerations and strategies for the implementation of peer learning activities, which took into account both educator and student roles. Reported challenges were reflective of those identified within the literature. The resultant framework may aid others in anticipating implementation challenges. Further work is required to test the framework's application in other contexts and its effect on learner outcomes.     

Four challenges in medical image analysis from an industrial perspective

Today’s medical imaging systems produce a huge amount of images containing a wealth of information. However, the information is hidden in the data and image analysis algorithms are needed to extract it, to make it readily available for medical decisions and to enable an efficient work flow. Advances in medical image analysis over the past 20 years mean there are now many algorithms and ideas available that allow to address medical image analysis tasks in commercial solutions with sufficient performance in terms of accuracy, reliability and speed. At the same time new challenges have arisen. Firstly, there is a need for more generic image analysis technologies that can be efficiently adapted for a specific clinical task. Secondly, efficient approaches for ground truth generation are needed to match the increasing demands regarding validation and machine learning. Thirdly, algorithms for analyzing heterogeneous image data are needed. Finally, anatomical and organ models play a crucial role in many applications, and algorithms to construct patient-specific models from medical images with a minimum of user interaction are needed. These challenges are complementary to the on-going need for more accurate, more reliable and faster algorithms, and dedicated algorithmic solutions for specific applications.     

CNN-based lung CT registration with multiple anatomical constraints

Deep-learning-based registration methods emerged as a fast alternative to conventional registration methods. However, these methods often still cannot achieve the same performance as conventional registration methods because they are either limited to small deformation or they fail to handle a superposition of large and small deformations without producing implausible deformation fields with foldings inside.In this paper, we identify important strategies of conventional registration methods for lung registration and successfully developed the deep-learning counterpart. We employ a Gaussian-pyramid-based multilevel framework that can solve the image registration optimization in a coarse-to-fine fashion. Furthermore, we prevent foldings of the deformation field and restrict the determinant of the Jacobian to physiologically meaningful values by combining a volume change penalty with a curvature regularizer in the loss function. Keypoint correspondences are integrated to focus on the alignment of smaller structures.We perform an extensive evaluation to assess the accuracy, the robustness, the plausibility of the estimated deformation fields, and the transferability of our registration approach. We show that it achieves state-of-the-art results on the COPDGene dataset compared to conventional registration method with much shorter execution time. In our experiments on the DIRLab exhale to inhale lung registration, we demonstrate substantial improvements (TRE below 1.2 mm) over other deep learning methods. Our algorithm is publicly available at https://grand-challenge.org/algorithms/deep-learning-based-ct-lung-registration/.     

A reinforcement learning approach for VQA validation: An application to diabetic macular edema grading

Recent advances in machine learning models have greatly increased the performance of automated methods in medical image analysis. However, the internal functioning of such models is largely hidden, which hinders their integration in clinical practice. Explainability and trust are viewed as important aspects of modern methods, for the latter’s widespread use in clinical communities. As such, validation of machine learning models represents an important aspect and yet, most methods are only validated in a limited way. In this work, we focus on providing a richer and more appropriate validation approach for highly powerful Visual Question Answering (VQA) algorithms. To better understand the performance of these methods, which answer arbitrary questions related to images, this work focuses on an automatic visual Turing test (VTT). That is, we propose an automatic adaptive questioning method, that aims to expose the reasoning behavior of a VQA algorithm. Specifically, we introduce a reinforcement learning (RL) agent that observes the history of previously asked questions, and uses it to select the next question to pose. We demonstrate our approach in the context of evaluating algorithms that automatically answer questions related to diabetic macular edema (DME) grading. The experiments show that such an agent has similar behavior to a clinician, whereby asking questions that are relevant to key clinical concepts.     

Holistic multitask regression network for multiapplication shape regression segmentation

A holistic multitask regression approach was implemented to tackle the limitations of clinical image analysis. Standard practice requires identifying multiple anatomic structures in multiple planes from multiple anatomic regions using multiple modalities. The proposed novel holistic multitask regression network (HMR-Net) formulates organ segmentation as a multitask learning problem. Multitask learning leverages the strength of joint task problem solving from capturing task correlations. HMR-Net performs multitask regression by estimating an organ’s class, regional location, and precise contour coordinates. The estimation of each coordinate point also corresponds to another regression task. HMR-Net leverages hierarchical multiscale and fused organ features to handle nonlinear relationships between image appearance and distinct organ properties. Simultaneously, holistic shape information is captured by encoding coordinate correlations. The multitask pipeline enables the capturing of holistic organ information (e.g. class, location, shape) to perform shape regression for medical image segmentation. HMR-Net was validated on eight representative datasets obtained from a total of 222 subjects. A mean average precision and dice score reaching up to 0.81 and 0.93, respectively, was achieved on the representative multiapplication database. The generalized model demonstrates comparable or superior performance compared to state-of-the-art algorithms. The high-performance accuracy demonstrates our model as an effective general framework to perform organ shape regression in multiple applications. This method was proven to provide high-contrast sensitivity to delineate even the smallest and oddly shaped organs. HMR-Net’s flexible framework holds great potential in providing a fully automatic preliminary analysis for multiple types of medical images.     

Weakly supervised histopathology image segmentation with self-attention

Accurate segmentation in histopathology images at pixel-level plays a critical role in the digital pathology workflow. The development of weakly supervised methods for histopathology image segmentation liberates pathologists from time-consuming and labor-intensive works, opening up possibilities of further automated quantitative analysis of whole-slide histopathology images. As an effective subgroup of weakly supervised methods, multiple instance learning (MIL) has achieved great success in histopathology images. In this paper, we specially treat pixels as instances so that the histopathology image segmentation task is transformed into an instance prediction task in MIL. However, the lack of relations between instances in MIL limits the further improvement of segmentation performance. Therefore, we propose a novel weakly supervised method called SA-MIL for pixel-level segmentation in histopathology images. SA-MIL introduces a self-attention mechanism into the MIL framework, which captures global correlation among all instances. In addition, we use deep supervision to make the best use of information from limited annotations in the weakly supervised method. Our approach makes up for the shortcoming that instances are independent of each other in MIL by aggregating global contextual information. We demonstrate state-of-the-art results compared to other weakly supervised methods on two histopathology image datasets. It is evident that our approach has generalization ability for the high performance on both tissue and cell histopathology datasets. There is potential in our approach for various applications in medical images.     

Contour tracking in echocardiographic sequences via sparse representation and dictionary learning

This paper presents a dynamical appearance model based on sparse representation and dictionary learning for tracking both endocardial and epicardial contours of the left ventricle in echocardiographic sequences. Instead of learning offline spatiotemporal priors from databases, we exploit the inherent spatiotemporal coherence of individual data to constraint cardiac contour estimation. The contour tracker is initialized with a manual tracing of the first frame. It employs multiscale sparse representation of local image appearance and learns online multiscale appearance dictionaries in a boosting framework as the image sequence is segmented frame-by-frame sequentially. The weights of multiscale appearance dictionaries are optimized automatically. Our region-based level set segmentation integrates a spectrum of complementary multilevel information including intensity, multiscale local appearance, and dynamical shape prediction. The approach is validated on twenty-six 4D canine echocardiographic images acquired from both healthy and post-infarct canines. The segmentation results agree well with expert manual tracings. The ejection fraction estimates also show good agreement with manual results. Advantages of our approach are demonstrated by comparisons with a conventional pure intensity model, a registration-based contour tracker, and a state-of-the-art database-dependent offline dynamical shape model. We also demonstrate the feasibility of clinical application by applying the method to four 4D human data sets.     

Parallel non-Cartesian spatial-temporal dictionary learning neural networks (stDLNN) for accelerating 4D-MRI

Dynamic magnetic resonance imaging (MRI) acquisitions are relatively slow due to physical and physiological limitations. The spatial-temporal dictionary learning (DL) approach accelerates dynamic MRI by learning spatial-temporal correlations, but the regularization parameters need to be manually adjusted, the performance at high acceleration rate is limited, and the reconstruction can be time-consuming. Deep learning techniques have shown good performance in accelerating MRI due to the powerful representational capabilities of neural networks. In this work, we propose a parallel non-Cartesian spatial-temporal dictionary learning neural networks (stDLNN) framework that combines dictionary learning with deep learning algorithms and utilizes the spatial-temporal prior information of dynamic MRI data to achieve better reconstruction quality and efficiency. The coefficient estimation modules (CEM) are designed in the framework to adaptively adjust the regularization coefficients. Experimental results show that combining dictionary learning with deep neural networks and using spatial-temporal dictionaries can obviously improve the image quality and computational efficiency compared with the state-of-the-art non-Cartesian imaging methods for accelerating the 4D-MRI especially at high acceleration rate.     

Comparative validation of multi-instance instrument segmentation in endoscopy: Results of the ROBUST-MIS 2019 challenge

Intraoperative tracking of laparoscopic instruments is often a prerequisite for computer and robotic-assisted interventions. While numerous methods for detecting, segmenting and tracking of medical instruments based on endoscopic video images have been proposed in the literature, key limitations remain to be addressed: Firstly, robustness, that is, the reliable performance of state-of-the-art methods when run on challenging images (e.g. in the presence of blood, smoke or motion artifacts). Secondly, generalization; algorithms trained for a specific intervention in a specific hospital should generalize to other interventions or institutions.In an effort to promote solutions for these limitations, we organized the Robust Medical Instrument Segmentation (ROBUST-MIS) challenge as an international benchmarking competition with a specific focus on the robustness and generalization capabilities of algorithms. For the first time in the field of endoscopic image processing, our challenge included a task on binary segmentation and also addressed multi-instance detection and segmentation. The challenge was based on a surgical data set comprising 10,040 annotated images acquired from a total of 30 surgical procedures from three different types of surgery. The validation of the competing methods for the three tasks (binary segmentation, multi-instance detection and multi-instance segmentation) was performed in three different stages with an increasing domain gap between the training and the test data. The results confirm the initial hypothesis, namely that algorithm performance degrades with an increasing domain gap. While the average detection and segmentation quality of the best-performing algorithms is high, future research should concentrate on detection and segmentation of small, crossing, moving and transparent instrument(s) (parts).     

Degenerative adversarial neuroimage nets for brain scan simulations: Application in ageing and dementia

Accurate and realistic simulation of high-dimensional medical images has become an important research area relevant to many AI-enabled healthcare applications. However, current state-of-the-art approaches lack the ability to produce satisfactory high-resolution and accurate subject-specific images. In this work, we present a deep learning framework, namely 4D-Degenerative Adversarial NeuroImage Net (4D-DANI-Net), to generate high-resolution, longitudinal MRI scans that mimic subject-specific neurodegeneration in ageing and dementia. 4D-DANI-Net is a modular framework based on adversarial training and a set of novel spatiotemporal, biologically-informed constraints. To ensure efficient training and overcome memory limitations affecting such high-dimensional problems, we rely on three key technological advances: i) a new 3D training consistency mechanism called Profile Weight Functions (PWFs), ii) a 3D super-resolution module and iii) a transfer learning strategy to fine-tune the system for a given individual. To evaluate our approach, we trained the framework on 9852 T1-weighted MRI scans from 876 participants in the Alzheimer’s Disease Neuroimaging Initiative dataset and held out a separate test set of 1283 MRI scans from 170 participants for quantitative and qualitative assessment of the personalised time series of synthetic images. We performed three evaluations: i) image quality assessment; ii) quantifying the accuracy of regional brain volumes over and above benchmark models; and iii) quantifying visual perception of the synthetic images by medical experts. Overall, both quantitative and qualitative results show that 4D-DANI-Net produces realistic, low-artefact, personalised time series of synthetic T1 MRI that outperforms benchmark models.     

Aircraft detection in remote sensing images using centre-based proposal regions and invariant features

ABSTRACT

Aircraft detection in remote sensing imagery has drawn much attention in recent years, which plays an important role in various military and civil applications. While many advanced works have been developed with powerful learning algorithms in natural images, there still lacks an effective one to detect aircraft precisely in remote sensing images, especially in some complicated conditions. In this paper, a novel method is designed to detect aircraft precisely, named aircraft detection using Centre-based Proposal regions and Invariant Features (CPIF), which can handle some difficult image deformations, especially rotations. Our framework mainly contains three steps. Firstly, we propose an algorithm to extract proposal regions from remote sensing imagery. Secondly, an ensemble learning classifier with the rotation-invariant HOG is trained for aircraft classification. Lastly, we detect aircraft in remote sensing images by combining the products of the above steps. The proposed method is evaluated on a public dataset RSOD and the results are performed to demonstrate the superiority and effectiveness in comparison with the state-of-the-art methods.     

Reducing annotation effort in digital pathology: A Co-Representation learning framework for classification tasks

Classification of digital pathology images is imperative in cancer diagnosis and prognosis. Recent advancements in deep learning and computer vision have greatly benefited the pathology workflow by developing automated solutions for classification tasks. However, the cost and time for acquiring high quality task-specific large annotated training data are subject to intra- and inter-observer variability, thus challenging the adoption of such tools. To address these challenges, we propose a classification framework via co-representation learning to maximize the learning capability of deep neural networks while using a reduced amount of training data. The framework captures the class-label information and the local spatial distribution information by jointly optimizing a categorical cross-entropy objective and a deep metric learning objective respectively. A deep metric learning objective is incorporated to enhance the classification, especially in the low training data regime. Further, a neighborhood-aware multiple similarity sampling strategy, and a soft-multi-pair objective that optimizes interactions between multiple informative sample pairs, is proposed to accelerate deep metric learning. We evaluate the proposed framework on five benchmark datasets from three digital pathology tasks, i.e., nuclei classification, mitosis detection, and tissue type classification. For all the datasets, our framework achieves state-of-the-art performance when using approximately only 50% of the training data. On using complete training data, the proposed framework outperforms the state-of-the-art on all the five datasets.     

Siam-U-Net: encoder-decoder siamese network for knee cartilage tracking in ultrasound images

The tracking of the knee femoral condyle cartilage during ultrasound-guided minimally invasive procedures is important to avoid damaging this structure during such interventions. In this study, we propose a new deep learning method to track, accurately and efficiently, the femoral condyle cartilage in ultrasound sequences, which were acquired under several clinical conditions, mimicking realistic surgical setups. Our solution, that we name Siam-U-Net, requires minimal user initialization and combines a deep learning segmentation method with a siamese framework for tracking the cartilage in temporal and spatio-temporal sequences of 2D ultrasound images. Through extensive performance validation given by the Dice Similarity Coefficient, we demonstrate that our algorithm is able to track the femoral condyle cartilage with an accuracy which is comparable to experienced surgeons. It is additionally shown that the proposed method outperforms state-of-the-art segmentation models and trackers in the localization of the cartilage. We claim that the proposed solution has the potential for ultrasound guidance in minimally invasive knee procedures.     

Weakly supervised classification of time-series of very high resolution remote sensing images by transfer learning

In multi-temporal remotely sensed data analysis, labeling samples from each image is often a required process, this is however very tedious and time-consuming. In many cases the ground objects do not change significantly through time, and one can reuse some of the labels with appropriate consistency verification. In this letter, a novel weakly supervised transfer learning framework is proposed to classify multi-temporal remote-sensing images with only one labeled image. By utilizing the consistency of time-series images and a domain adaptation method, our framework is able to classify all the other multi-temporal images chronologically without any labeling effort for these images. Our framework achieves a similar level of classification accuracy as if it were through supervised learning. Our framework is shown to be effective for processing multi-temporal remote-sensing images when training samples are only available for one temporal dataset.     

Surgical scene generation and adversarial networks for physics-based iOCT synthesis

The development and integration of intraoperative optical coherence tomography (iOCT) into modern operating rooms has motivated novel procedures directed at improving the outcome of ophthalmic surgeries. Although computer-assisted algorithms could further advance such interventions, the limited availability and accessibility of iOCT systems constrains the generation of dedicated data sets. This paper introduces a novel framework combining a virtual setup and deep learning algorithms to generate synthetic iOCT data in a simulated environment. The virtual setup reproduces the geometry of retinal layers extracted from real data and allows the integration of virtual microsurgical instrument models. Our scene rendering approach extracts information from the environment and considers iOCT typical imaging artifacts to generate cross-sectional label maps, which in turn are used to synthesize iOCT B-scans via a generative adversarial network. In our experiments we investigate the similarity between real and synthetic images, show the relevance of using the generated data for image-guided interventions and demonstrate the potential of 3D iOCT data synthesis.     

Exploiting the potential of unlabeled endoscopic video data with self-supervised learning

Purpose

Surgical data science is a new research field that aims to observe all aspects of the patient treatment process in order to provide the right assistance at the right time. Due to the breakthrough successes of deep learning-based solutions for automatic image annotation, the availability of reference annotations for algorithm training is becoming a major bottleneck in the field. The purpose of this paper was to investigate the concept of self-supervised learning to address this issue.

Methods

Our approach is guided by the hypothesis that unlabeled video data can be used to learn a representation of the target domain that boosts the performance of state-of-the-art machine learning algorithms when used for pre-training. Core of the method is an auxiliary task based on raw endoscopic video data of the target domain that is used to initialize the convolutional neural network (CNN) for the target task. In this paper, we propose the re-colorization of medical images with a conditional generative adversarial network (cGAN)-based architecture as auxiliary task. A variant of the method involves a second pre-training step based on labeled data for the target task from a related domain. We validate both variants using medical instrument segmentation as target task.

Results

The proposed approach can be used to radically reduce the manual annotation effort involved in training CNNs. Compared to the baseline approach of generating annotated data from scratch, our method decreases exploratively the number of labeled images by up to 75% without sacrificing performance. Our method also outperforms alternative methods for CNN pre-training, such as pre-training on publicly available non-medical (COCO) or medical data (MICCAI EndoVis2017 challenge) using the target task (in this instance: segmentation).

Conclusion

As it makes efficient use of available (non-)public and (un-)labeled data, the approach has the potential to become a valuable tool for CNN (pre-)training.