Pulmonary nodules are the principal lung cancer indicator, whose malignancy is mainly related to their size, morphological and textural features. Computational deep representations are today the most common tool to characterize lung nodules but remain limited to capturing nodule variability. In consequence, nodule malignancy classification from CT observations remains an open problem. This work introduces a multi-head attention network that takes advantage of volumetric nodule observations and robustly represents textural and geometrical patterns, learned from a discriminative task. The proposed approach starts by computing 3D convolutions, exploiting textural patterns of volumetric nodules. Such convolutional representation is enriched from a multi-scale projection using receptive field blocks, followed by multiple volumetric attentions that exploit non-local nodule relationships. These attentions are fused to enhance the representation and achieve more robust malignancy discrimination. The proposed approach was validated on the public LIDC-IDRI dataset, achieving a 91.82% in F1-score, 91.19% in sensitivity, and 92.43% in AUC for binary classification. The reported results outperform the state-of-the-art strategy with 3D nodule representations.
Detection, characterization and counting of mitosis is a main biomarker in cancer, allowing diagnosis, histological grading and prognosis. Nonetheless, mitosis identification remains as a challenging task (inter-observer variability up to 20%). Even, the computational support strategies remain limited to include wide visual variability of mitotic patterns, with an inherent bias because labeled observations. This work introduces a semi-supervised scheme that learns to identify mitotic cells from an initial limited amount of labeled data. Then, the initial trained backbone is used to propagate pseudo-labels into training samples. The most challenging samples, i.e., false positive and false negative pseudo-labeled samples, are included in further batches to re-train the model. At each iteration, a set of complementary non-mitotic patches are generated from an auxiliary net. The proposed approach was validated with the public ICPR dataset, achieving competitive results of 0.74 accuracy and 0.78 sensitivity. In addition, the proposed approach achieves an average inference time of 5.21 seconds (on a batch of 240 candidate patches).
Computed tomography (CT) is the first-line imaging modality for evaluation of patients suspected of stroke. Specially, such modality is key as screening test between ischemia and hemorrhage strokes. Despite remarkable support of encoder-decoder architectures, the delineation of ischemic lesions remains challenging on CT studies, reporting poor sensitivity, especially in the acute stage. Among others, these nets are affected because of the low scan quality, the challenging stroke geometry, and the variable textural representation. This work introduces a boundary-focused attention U-Net that takes advantage of cross-attention mechanism, that along multiple levels allows to recover stroke segmentation on CT scans. The proposed architecture is enriched with skip connections, that help in the recovering of saliency lesion maps and motivated the preservation of morphology. Besides, an auxiliary class is herein introduced with a weighted special loss function that remark lesion tissue, alleviating the negative impact of class unbalance. The proposed approach was validated on the public ISLES2018 dataset achieving an average dice score of 0.42 and a precision of 0.48.
KEYWORDS: Visualization, Statistical modeling, Cancer, Visual process modeling, Solid state lighting, Data modeling, Tissues, Solids, Prostate cancer, Imaging systems
Gleason Score (GS) is the principal histological grading system to support the quantification of cancer aggressiveness. This analysis is carried out by expert pathologists but with reported evidence of moderate agreement among pathologists (kappa values less than 0.5). This fact can be prone to errors that directly affect the diagnosis and subsequent treatment. Current deep learning approaches have been proposed to support such visual pattern quantification but there exist a remarked on expert annotations that overfit representations. Besides, the supervised representation is limited to model the high reported visual variability intra Gleason grades. This work introduces a semi-Supervised Learning (SSL) approach that initially uses a reduced set of annotated visual patterns to built several GS deep representations. Then, the set of deep models automatically propagates annotations to unlabeled patches. The most confident predicted samples are used to retrain the ensemble deep representation. Over a patch-based framework with a total of 26259 samples, coded from 886 tissue microarrays, the proposed approach achieved remarkable results between grades three and four. Interestingly, the proposed SSL with only the 10% of samples achieves more general representation, achieving averages scores of ~75.93% and ∼ 71.88% concerning two expert pathologists
Parkinson’s disease is a neurodegenerative disease that affects more than 6.1 million people worldwide. In the clinical routine, the main tool to diagnose and monitor disease progression is based on motor impairments, such as postural instability, bradykinesia, tremor, among others. Besides, new biomarkers based on motion patterns have emerged to describe disease findings. Nonetheless, this motor characterization has low sensitivity, especially at early stages, and is largely expert-dependent, because protocols are mainly based on visual observations. However, most of these analyses require complex and some invasive systems that additionally only bring global information of complete recordings. This work introduces a multimodal approach that integrates gait and eye motion videos to quantify and predict patient stage on-the-fly. This method starts by computing dense apparent velocity maps that represent the local displacement of the person seen from the gait in a sagittal plane and as micro-movements during the fixation experiment. Then, each frame is described as a covariance descriptor of deep feature activation maps computed over the motion field at each video time. Then, the covariance video manifold is mapped to a recurrent LSTM network to learn higher non-local dependencies and quantify a motion descriptor. Also, an end-to-end scheme allows to lately fuse both modalities (gait and fixational eye) to obtain a more sensitive Parkinson disease descriptor. In a study with 25 subjects, the proposed approach reaches an average F1-score of 0.83 with an average recall of 0.78. In a temporal prediction analysis, the approach reports major correlations with the disease considering swing phase.
Semisupervised learning (SSL) techniques explore the progressive discovery of the hidden latent data structure by propagating supervised information on unlabeled data, which are thereafter used to reinforce learning. These schemes are beneficial in remote sensing, where thousands of new images are added every day, and manual labeling results are prohibitive. Our work introduces an ensemble-based semisupervised deep learning approach that initially takes a subset of labeled data Dl, which represents the latent structure of the data and progressively propagates labels automatically from an expanding set of unlabeled data Du. The ensemble is a set of classifiers whose predictions are collated to derive a consolidated prediction. Only those data having a high-confidence prediction are considered as newly generated labels. The proposed approach was exhaustively validated on four public datasets, achieving appreciable results compared to the state-of-the-art methods in most of the evaluated configurations. For all datasets, the proposed approach achieved a classification F1-score and recall of up to 90%, on average. The SSL and recursive scheme also demonstrated an average gain of ∼2 % at the last training stage in such large datasets.
Histopathological tissue analysis is the most effective and definitive method to prognosis cancer and stratify the aggressiveness of the disease. The Gleason Score (GS) is the most powerful grading system based on architectural tumor pattern quantification. This score characterizes cancer tumor tissue, such as the level of cell differentiation on histopathological images. The reported GS is described as the sum of two principal grades present in a particular image, and ranged from 6 (cancer grow slowly) to 10 (cancer cells spread more rapidly). A main drawback of GS is the pathological dependency on histopathological region stratification, which strongly impacts the clinical procedure to treat the disease. The agreement among experts has been quantified with a kappa index of: ~0.71. Even worse, a higher uncertainty is reported for intermediate grade stratification. This work presents a like-inception deep architecture that is able to differentiate between intermediate and close GS grades. Each image herein evaluated was split-up into regional patches that correspond to a single GS grade. A set of training patches were augmented according to appearance image variations of each grade. Then, a transfer learning scheme was implemented to adapt a bi-Gleason tumor patterns prediction among close levels. The proposed approach was evaluated on public set of 886 tissue H&E stained images with different GS grades, achieving an average accuracy of 0.73% between grades three and four.
Magnetic resonance imaging (MRI) plays a valuable role in many task related with characterization of prostate cancer lesions. Recently, the DCE-MRI (Dynamic contrast Enhanced) has allowed to visualize and localize potential tumor regions. Specifically, Ktrans, from DCR-MRI, has shown to be a powerful pharmacokinetic parameter that allows to characterize tumor biology and to detect treatment responses from reconstructed coefficient maps of capillary permeability. Nevertheless, even expert-based analysis of Ktrans sequences are subject to a large false positive findings (FPF). In much of such cases, the prostate angiogenesis, or benign prostatic hyperplasia (BPH) regions are misclassified as cancer findings. This work introduces a robust deep convolutional strategy that characterizes Ktrans regions and allows an automatic prediction of cancer findings. The proposed strategy was validated over the SPIE-AAPM-NCI PROSTATEx public dataset with 320 multimodal images on peripheral, transitional and anterior fibromuscular stroma regions. The best configuration of proposal strategy achieved an area under the ROC curve (AUC) of 0.74. Additionally, the proposed strategy achieved a proper characterization by using mainly Ktrans information that together with T2-MRI-transaxial overcome baseline strategies that use additional modalities of MRI.
Parkinson’s disease (PD) is a neurodegenerative disorder characterized by a set of progressive motor disabilities knows as shuffling gait patterns. The diagnosis and treatment of parkinsonian patients at different stages is typically supported by a Kinematic analysis. In clinical routine, such analysis is related with the quantitative and qualitative description of body segment displacements, computed from a reduced set of markers. Nevertheless, classical markers-based analysis has strong limitations to capture local and regional dynamic relationships associated with shuffling gait patterns. Particularly, the sparse set of markers lost sensitivity to detect progression of disease and commonly this kinematic characterization is restricted only to advanced stages. This work introduces a new hierarchical parkinsonian gait descriptor that coded kinematics at local and regional levels. At local level, a Spatial Kinematic Pattern (SKP) is computed as circular binary occurrence vectors, along trajectories. Regionally, such local vectors are grouped to describe body segments motions. Each of these regions coarsely correspond to the head, trunk and limbs. From each independent region is possible to describe kinematic patterns associated with the disease. The proposed approach was validated into a classification scheme to differentiate among regional parkinsonian patterns w.r.t to control patterns. Hence, each coding region descriptor was mapped to a support vector machine model. The proposed method was evaluated from a set of 84 gait videos of control and parkinsonian patients, achieving an average accuracy of 84, 52%.
Resting hand tremor is one of the most important biomarkers in Parkinson’s disease (PD). This indicator is mainly described as periodic oscillatory movements when hands are completely supported, i.e., without voluntary muscle contraction. Such characterization is however very difficult to observe in standard clinical analysis, due to the imperceptible low tremor amplitude. Furthermore, in early stages of PD those motions are commonly misclassified as control patterns. Common clinical practice often suggests a physical tremor magnification by forcing postural hand configurations, dealing with natural strain motions that might disturb tremor behavior. In this work was introduced a video characterization that highlights hand tremor patterns from resting and postural setups. Initially, each of videos are represented as a bank of spatial and temporal filters. Then, specific spatio-temporal bands are amplified to stand out tremor patterns. A set of anatomical points of interest was fixed to be quantitatively assessed along the magnified sequence. Temporal variance of these points were associated with tremor recorded in videos. The proposed approach was evaluated in a total of 80 videos recording hands in resting and postural configurations. Variance analysis was performed to measure temporal amplitude differences of tremor in PD and control videos. In resting validation, a gain of 7.76 dB was achieved in parkinsonian and control comparison by using amplified videos. While physical magnification obtains a F-test of 5.19, the proposed optical magnification yields a F-test of 8.19, allowing a better quantification of the disease.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.