Search

IntroductionState-of-the-art multi-modal brain tumor segmentation methods often rely on large quantities of manually annotated data to produce acceptable results. In settings where such labeled data may be scarce, there may be value in exploiting cheaper or more readily available data through clinical trials, such as Response Assessment in Neuro-Oncology (RANO).MethodsThis study demonstrates the utility of such measurements for multi-modal brain tumor segmentation, whereby an encoder network is first trained to regress synthetic “Pseudo-RANO” measurements using a mean squared error loss with cosine similarity penalty to promote orthogonality of the principal axes. Using oriented bounding-boxes to measure overlap with the ground truth, we show that the encoder model can reliably estimate tumor principal axes with good performance. The trained encoder was combined with a randomly initialized decoder for fine-tuning as a U-Net architecture for whole tumor (WT) segmentation.ResultsOur results demonstrate that weakly supervised encoder models converge faster than those trained without pre-training and help minimize the annotation burden when trained to perform segmentation.DiscussionThe use of cheap, low-fidelity labels in the context allows for both faster and more stable training with fewer densely segmented ground truth masks, which has potential uses outside this particular paradigm.

In recent years the healthcare industry has had increased difficulty seeing all low-risk patients, including but not limited to suspected osteoarthritis (OA) patients. To help address the increased waiting lists and shortages of staff, we propose a novel method of automated biomarker identification and quantification for the monitoring of treatment or disease progression through the analysis of clinical motion data captured from a standard RGB video camera. The proposed method allows for the measurement of biomechanics information and analysis of their clinical significance, in both a cheap and sensitive alternative to the traditional motion capture techniques. These methods and results validate the capabilities of standard RGB cameras in clinical environments to capture clinically relevant motion data. Our method focuses on generating 3D human shape and pose from 2D video data via adversarial training in a deep neural network with a self-attention mechanism to encode both spatial and temporal information. Biomarker identification using Principal Component Analysis (PCA) allows the production of representative features from motion data and uses these to generate a clinical report automatically. These new biomarkers can then be used to assess the success of treatment and track the progress of rehabilitation or to monitor the progression of the disease. These methods have been validated with a small clinical study, by administering a local anaesthetic to a small population with knee pain, this allows these new representative biomarkers to be validated as statistically significant (p-value

Besides the complex nature of colonoscopy frames with intrinsic frame formation artefacts such as light reflections and the diversity of polyp types/shapes, the publicly available polyp segmentation training datasets are limited, small and imbalanced. In this case, the automated polyp segmentation using a deep neural network remains an open challenge due to the overfitting of training on small datasets. We proposed a simple yet effective polyp segmentation pipeline that couples the segmentation (FCN) and classification (CNN) tasks. We find the effectiveness of interactive weight transfer between dense and coarse vision tasks that mitigates the overfitting in learning. This motivates us to design a new training scheme within our segmentation pipeline. Our method is evaluated on CVC-EndoSceneStill and Kvasir-SEG datasets. It achieves 4.34% and 5.70% Polyp-IoU improvements compared to the state-of-the-art methods on the EndoSceneStill and Kvasir-SEG datasets, respectively and achieves real-time performance in inference. The model and code are available at https://github.com/MELSunny/Keras-FCN

This paper presents a spatiotemporal deep learning approach for mouse behavioral classification in the home-cage. Using a series of dual-stream architectures with assorted modifications for optimal performance, we introduce a novel feature sharing approach that jointly processes the streams at regular intervals throughout the network. The dataset in focus is an annotated, publicly available dataset of a singly-housed mouse. We achieved even better classification accuracy by ensembling the best performing models; an Inception-based network and an attention-based network, both of which utilize this feature sharing attribute. Furthermore, we demonstrate through ablation studies that for all models, the feature sharing architectures consistently outperform the conventional dual-stream having standalone streams. In particular, the inception-based architectures showed higher feature sharing gains with their increase in accuracy anywhere between 6.59% and 15.19%. The best-performing models were also further evaluated on other mouse behavioral datasets.

The pandemic of coronavirus disease (COVID-19) caused the world to face an existential health crisis. COVID-19 lesions segmentation from CT images is nowadays an essential step to assess the severity of the disease and the amount of damage to the lungs. Deep learning has brought about a breakthrough in medical image segmentation where U-Net is the most prominent deep network. However, in this study, we argue that its architecture still lacks in certain aspects. First, there is an incompatibility in the U-Net skip connection between the encoder and decoder features which adversely affects the final prediction. Second, it lacks capturing multiscale context information and ignores the contribution of all semantic information through the segmentation process. Therefore, we propose a model named MCA-Unet, a novel multiscale deep learning segmentation model, which proposes some modifications to improve upon the U-Net model. MCA-Unet is integrated with a multiscale context aggregation module which is constituted of two blocks; a context embedding block (CEB) and a cascaded dilated convolution block (CDCB). The CEB aims at reducing the semantic gap between the concatenated features along the U-Net skip connections, it enriches the low-level encoder features with rich semantics inherited from the subsequent higher-level features, to reduce the semantic gap between the low-processed encoder features and the highly-processed decoder features, thus ensuring effectual concatenation. The CDCB is integrated to address the variability in shape and size of the COVID-19 lesions, it captures global context information by gradually expanding the receptive field, then operates reversely to capture the small fine details that might be scattered by enlarging the receptive field. To validate the robustness of our model, we tested it on a publicly available dataset of 1705 axial CT images with different types of COVID-19 infection. Experimental results show that MCA-Unet has attained a remarkable gain in performance in comparison with the basic U-Net and its variant. It achieved high performance using different evaluation metrics showing 88.6% Dice similarity coefficient, 85.4% Jaccard index, and 93.5% F-score measure. This outperformance shows great potential to help physicians during their examination and improve the clinical workflow.

Segmentation of echocardiographic images is an essential step for assessing the cardiac functionality, as indicative clinical measures can be obtained from the delineation of the left ventricle chamber and all further heart analysis relies on the accuracy of this process. However, the fuzzy nature of echocardiographic images degraded by distortion and speckle noise poses some challenges on the manual segmentation task. In this paper, we propose a fully automated left ventricle segmentation method that can overcome those challenges. Our method performs accurate delineation for the ventricle boundaries despite the ill-defined borders and shape variability of the left ventricle. The well-known deep learning segmentation model, known as the U-net, has addressed some of these challenges with outstanding performance. However, it still ignores the contribution of all semantic information through the segmentation process. Here we propose a novel deep learning segmentation method based on U-net, named ResDUnet. It incorporates feature extraction at different scales through the integration of cascaded dilated convolution. To ease the training process, residual blocks are deployed instead of the basic U-net blocks. Each residual block is enriched with a squeeze and excitation unit for channel-wise attention and adaptive feature re-calibration. The performance of the method is evaluated on a dataset of 2000 images acquired from 500 patients with large variability in quality and patient pathology. ResDUnet outperforms state-of-the-art methods with a Dice similarity increase of 8.4% and 1.2% compared to deeplabv3 and U-net, respectively. Furthermore, to demonstrate the impact of each proposed sub-module, several experiments have been carried out with different designs and variations of the integrated sub-modules. We also describe and discuss all technical elements of a deep-learning model via a step-by-step explanation of parameters and methods, while using our left ventricle segmentation as a case study, to explain the application of AI to echocardiographic imaging.

The annotation of the tumour from medical scans is a crucial step in nephroblastoma treatment. Therefore, an accurate and reliable segmentation method is needed to facilitate the evaluation and the treatments of the tumour. The proposed method serves this purpose by performing the segmentation of nephroblastoma in MRI scans. The segmentation is performed by adapting and a 2D free hand drawing tool to select a region of interest in the scan slices. Results from 24 patients show a mean root-mean-square error of 0.0481 ± 0.0309, an average Dice coefficient of 0.9060 ± 0.0549 and an average accuracy of 99.59% ± 0.0039. Thus the proposed method demonstrated an effective agreement with manual annotations.

Early detection of esophageal abnormalities can help in preventing the progression of the disease into later stages. During esophagus examination, abnormalities are often overlooked due to the irregular shape, variable size, and the complex surrounding area which requires a significant effort and experience. In this paper, a novel deep learning model which is based on faster region-based convolutional neural network (Faster R-CNN) is presented to automatically detect abnormalities in the esophagus from endoscopic images. The proposed detection system is based on a combination of Gabor handcrafted features with the CNN features. The densely connected convolutional networks (DenseNets) architecture is embraced to extract the CNN features providing a strengthened feature propagation between the layers and alleviate the vanishing gradient problem. To address the challenges of detecting abnormal complex regions, we propose fusing extracted Gabor features with the CNN features through concatenation to enhance texture details in the detection stage. Our newly designed architecture is validated on two datasets (Kvasir and MICCAI 2015). Regarding the Kvasir, the results show an outstanding performance with a recall of 90.2% and a precision of 92.1% with a mean of average precision (mAP) of 75.9%. While for the MICCAI 2015 dataset, the model is able to surpass the state-of-the-art performance with 95% recall and 91% precision with mAP value of 84%. The experimental results demonstrate that the system is able to detect abnormalities in endoscopic images with good performance without any human intervention.

The advanced development of deep learning methods has recently made significant improvements in medical image segmentation. Encoder–decoder networks, such as U-Net, have addressed some of the challenges in medical image segmentation with an outstanding performance, which has promoted them to be the most dominating deep learning architecture in this domain. Despite their outstanding performance, we argue that they still lack some aspects. First, there is incompatibility in U-Net’s skip connection between the encoder and decoder features due to the semantic gap between low-processed encoder features and highly processed decoder features, which adversely affects the final prediction. Second, it lacks capturing multi-scale context information and ignores the contribution of all semantic information through the segmentation process. Therefore, we propose a model named MDA-Unet, a novel multi-scale deep learning segmentation model. MDA-Unet improves upon U-Net and enhances its performance in segmenting medical images with variability in the shape and size of the region of interest. The model is integrated with a multi-scale spatial attention module, where spatial attention maps are derived from a hybrid hierarchical dilated convolution module that captures multi-scale context information. To ease the training process and reduce the gradient vanishing problem, residual blocks are deployed instead of the basic U-net blocks. Through a channel attention mechanism, the high-level decoder features are used to guide the low-level encoder features to promote the selection of meaningful context information, thus ensuring effective fusion. We evaluated our model on 2 different datasets: a lung dataset of 2628 axial CT images and an echocardiographic dataset of 2000 images, each with its own challenges. Our model has achieved a significant gain in performance with a slight increase in the number of trainable parameters in comparison with the basic U-Net model, providing a dice score of 98.3% on the lung dataset and 96.7% on the echocardiographic dataset, where the basic U-Net has achieved 94.2% on the lung dataset and 93.9% on the echocardiographic dataset.

Purpose: To develop a statistical method of combining multimodal MRI (mMRI) of adult glial brain tumours to generate tissue heterogeneity maps that indicate tumour grade and infiltration margins. Materials and methods: We performed a retrospective analysis of mMRI from patients with histological diagnosis of glioma (n = 25). 1H Magnetic Resonance Spectroscopic Imaging (MRSI) was used to label regions of “pure” low- or high-grade tumour across image types. Normal brain and oedema characteristics were defined from healthy controls (n = 10) and brain metastasis patients (n = 10) respectively. Probability density distributions (PDD) for each tissue type were extracted from intensity normalised proton density and T2-weighted images, and p and q diffusion maps. Superpixel segmentation and Bayesian inference was used to produce whole-brain tissue-type maps. Results: Total lesion volumes derived automatically from tissue-type maps correlated with those from manual delineation (p 2 years (Mann Witney p = 0.0001). Regions classified from mMRI as oedema had non-tumour-like 1H MRS characteristics. Conclusions: 1H MRSI can label tumour tissue types to enable development of a mMRI tissue type mapping algorithm, with potential to aid management of patients with glial tumours. Keywords: Magnetic resonance spectroscopy (MRS), Multimodal MRI, Glioma, Nosologic imaging, Pattern recognition

Background and study aims Video-colonoscopy, despite being the gold-standard for diagnosis of colorectal lesions, has limitations including patient discomfort and risk of complications. This study assessed training characteristics and acceptability in operators of a new robotic colonoscope (RC). Materials and methods Participants (n = 9) with varying degrees of skill and background knowledge in colonoscopy performed colonoscopies with a RC on a simulation-based training model. Quantitative procedure-related and qualitative operator-related parameters were recorded. Results Polyp detection rate was highest in the novice group (91.67 %) followed by experts (86.11 %), then equally, trainees and video gamers (79.17 %). Four participants repeated the procedure at a follow-up session. Each participant improved cecal intubation time and had the same or higher polyp detection rate. The potential role for RC was identified for an out-of-hospital environment and as a novel diagnostic tool. Conclusions Results from this pilot suggest that operators at all skill levels found the RC acceptable and potentially useful as a diagnostic tool. Acquisition of skills with RC seems to improve rapidly to a clinically relevant level with simulation-based training

Individual pig detection and tracking is an important requirement in many video-based pig monitoring applications. However, it still remains a challenging task in complex scenes, due to problems of light fluctuation, similar appearances of pigs, shape deformations, and occlusions. In order to tackle these problems, we propose a robust on-line multiple pig detection and tracking method which does not require manual marking or physical identification of the pigs and works under both daylight and infrared (nighttime) light conditions. Our method couples a CNN-based detector and a correlation filter-based tracker via a novel hierarchical data association algorithm. In our method, the detector gains the best accuracy/speed trade-off by using the features derived from multiple layers at different scales in a one-stage prediction network. We define a tag-box for each pig as the tracking target, from which features with a more local scope are extracted for learning, and the multiple object tracking is conducted in a key-points tracking manner using learned correlation filters. Under challenging conditions, the tracking failures are modelled based on the relations between responses of the detector and tracker, and the data association algorithm allows the detection hypotheses to be refined; meanwhile the drifted tracks can be corrected by probing the tracking failures followed by the re-initialization of tracking. As a result, the optimal tracklets can sequentially grow with on-line refined detections, and tracking fragments are correctly integrated into respective tracks while keeping the original identifications. Experiments with a dataset captured from a commercial farm show that our method can robustly detect and track multiple pigs under challenging conditions. The promising performance of the proposed method also demonstrates the feasibility of long-term individual pig tracking in a complex environment and thus promises commercial potential.

We present a complete, end-to-end computer-aided detection (CAD) system for identifying lesions in the colon, imaged with computed tomography (CT). This system includes facilities for colon segmentation, candidate generation, feature analysis, and classification. The algorithms have been designed to offer robust performance to variation in image data and patient preparation. By utilizing efficient 2D and 3D processing, software optimizations, multi-threading, feature selection, and an optimized cascade classifier, the CAD system quickly determines a set of detection marks. The colon CAD system has been validated on the largest set of data to date, and demonstrates excellent performance, in terms of its high sensitivity, low false positive rate, and computational efficiency.

This paper presents a new, automatic method of accurately extracting lesions from CT data. It first determines, at each voxel, a five-dimensional (5D) feature vector that contains intensity, shape index, and 3D spatial location. Then, nonparametric mean shift clustering forms superpixels from these 5D features, resulting in an oversegmentation of the image. Finally, a graph cut algorithm groups the superpixels using a novel energy formulation that incorporates shape, intensity, and spatial features. The mean shift superpixels increase the robustness of the result while reducing the computation time. We assume that the lesion is part spherical, resulting in high shape index values in a part of the lesion. From these spherical subregions, foreground and background seeds for the graph cut segmentation can be automatically obtained. The proposed method has been evaluated on a clinical CT dataset. Visual inspection on different types of lesions (lung nodules and colonic polyps), as well as a quantitative evaluation on 101 solid and 80 GGO nodules, both demonstrate the potential of the proposed method. The joint spatial-intensity-shape features provide a powerful cue for successful segmentation of lesions adjacent to structures of similar intensity but different shape, as well as lesions exhibiting partial volume effect.

In recent years the healthcare industry has had increased difficulty seeing all low-risk patients, including but not limited to suspected osteoarthritis (OA) patients. To help address the increased waiting lists and shortages of staff, we propose a novel method of automated biomarker identification and quantification for the monitoring of treatment or disease progression through the analysis of clinical motion data captured from a standard RGB video camera. The proposed method allows for the measurement of biomechanics information and analysis of their clinical significance, in both a cheap and sensitive alternative to the traditional motion capture techniques. These methods and results validate the capabilities of standard RGB cameras in clinical environments to capture clinically relevant motion data. Our method focuses on generating 3D human shape and pose from 2D video data via adversarial training in a deep neural network with a self-attention mechanism to encode both spatial and temporal information. Biomarker identification using Principal Component Analysis (PCA) allows the production of representative features from motion data and uses these to generate a clinical report automatically. These new biomarkers can then be used to assess the success of treatment and track the progress of rehabilitation or to monitor the progression of the disease. These methods have been validated with a small clinical study, by administering a local anaesthetic to a small population with knee pain, this allows these new representative biomarkers to be validated as statistically significant (p-value, 0.05). These significant biomarkers include the cumulative acceleration of elbow flexion/extension in a sit-to-stand, as well as the smoothness of the knee and elbow flexion/extension in both a squat and sit-to-stand. [ABSTRACT FROM AUTHOR]