Search

Abstract Background Complete resection of malignant gliomas is hampered by the difficulty in distinguishing tumor cells at the infiltration zone. Fluorescence guidance with 5-ALA assists in reaching this goal. Using hyperspectral imaging, previous work characterized five fluorophores’ emission spectra in most human brain tumors. Methods In this paper, the effectiveness of these five spectra was explored for different tumor and tissue classification tasks in 184 patients (891 hyperspectral measurements) harboring low- (n = 30) and high-grade gliomas (n = 115), non-glial primary brain tumors (n = 19), radiation necrosis (n = 2), miscellaneous (n = 10) and metastases (n = 8). Four machine-learning models were trained to classify tumor type, grade, glioma margins, and IDH mutation. Results Using random forests and multilayer perceptrons, the classifiers achieve average test accuracies of 84–87%, 96.1%, 86%, and 91% respectively. All five fluorophore abundances vary between tumor margin types and tumor grades (p

In semi-supervised learning (SSL) for medical image classification, model performance is often hindered by the scarcity of labeled data and the complexity of unlabeled data. This paper proposes an enhanced SSL approach to address these challenges by effectively utilizing unlabeled data through a combination of pseudo-labeling and contrastive learning. The key contribution of our method is the introduction of a Dynamic Sample Reweighting strategy to select reliable unlabeled samples, thereby improving the model’s utilization of unlabeled data. Additionally, we incorporate multiple data augmentation strategies based on the Mean Teacher (MT) model to ensure consistent outputs across different perturbations. To better capture and integrate multi-scale features, we propose a novel feature fusion network, the Medical Multi-scale Feature Fusion Network (MedFuseNet), which enhances the model’s ability to classify complex medical images. Finally, we introduce a pseudo-label guided contrastive learning (PGC) loss function that improves intra-class compactness and inter-class separability of the model’s feature representations. Extensive experiments on three public medical image datasets demonstrate that our method outperforms existing SSL approaches, achieving 93.16% accuracy on the ISIC2018 dataset using only 20% labeled data, highlighting the potential of our approach to advance medical image classification under limited supervision.

The development of medical image classification models necessitates a substantial number of labeled images for model training. In real-world scenarios, sample sizes are typically limited and labeled samples often constitute only a small portion of the dataset. This paper aims to investigate a collaborative similarity learning strategy that optimizes pseudo-labels to enhance model accuracy and expedite its convergence, known as the joint similarity learning framework. By integrating semantic similarity and instance similarity, the pseudo-labels are mutually refined to ensure their quality during initial training. Furthermore, the similarity score is utilized as a weight to guide samples away from misclassification predictions during the classification process. To enhance the model’s generalization ability, an adaptive consistency constraint is introduced into the loss function to improve performance on untrained datasets. The model achieved a satisfactory accuracy of 93.65% at 80% labeling ratio, comparable to supervised learning methods’ performance. Even with very low labeling ratio (e.g., 5%), the model still attained an accuracy of 74.28%. Comparison with other techniques such as Mean Teacher and FixMatch revealed that our approach significantly outperforms them in medical image classification tasks through improving accuracy by approximately 2%, demonstrating this framework’s leadership in medical image classification.

Abstract Histopathological analysis requires a lot of clinical experience and time for pathologists. Artificial intelligence (AI) may have an important role in assisting pathologists and leading to more efficient and effective histopathological diagnoses. To address the challenge of requiring a large number of labelled images to train deep learning models in breast cancer histopathological image classification, a self‐training semi‐supervised learning method consisting three components is proposed: Firstly, a pre‐trained ResNet‐18 was used to extract features and generate pseudo‐labels for unlabelled data; secondly, a relational weight network based on the squeeze‐and‐excitation network (SENet) was trained to calculate the non‐linear distance metrices between labelled and unlabelled samples, in order to improve the accuracy of pseudo‐labelling; lastly, a consistency loss—maximum mean difference (MMD)—was added into the model to minimize the divergence between distributions of unlabelled and labelled samples. Extensive experiments were conducted on the open access BreakHis dataset. The proposed method outperformed the state‐of‐the‐art semi‐supervised methods at all tested annotated percentages (10–70%), and also achieved comparable performance with supervised methods at higher annotated percentages (50%, 70%).

Deep learning has substantially improved the state-of-the-art in object detection and image classification. Deep learning usually requires large-scale labelled datasets to train the models; however, due to the restrictions in medical data sharing and accessibility and the expensive labelling cost, the application of deep learning in medical image classification has been dramatically hindered. In this study, we propose a novel method that leverages semi-supervised adversarial learning and pseudo-labelling to incorporate the unlabelled images in model learning. We validate the proposed method on two public databases, including ChestX-ray14 for lung disease classification and BreakHis for breast cancer histopathological image diagnosis. The results show that our method achieved highly effective performance with an accuracy of 93.15% while using only 30% of the labelled samples, which is comparable to the state-of-the-art accuracy for chest X-ray classification; it also outperformed the current methods in multi-class breast cancer histopathological image classification with a high accuracy of 96.87%.

XRT separation equipment is attracting much attention as the mining industry increasingly uses pre-sorting technology. Its sorting accuracy is affected by differences in ore shape and particle size during operation. This paper, in which numerical simulations are conducted to investigate the resistance of ores under various situations, including varying blowing distances, cross-sections, and practical sizes, Additionally, this paper conducts validation tests. The test results indicate that within the 0.1-0.25 m section from the nozzle exit, there is a rapid decrease in velocity, accompanied by a significant change in ore resistance. Beyond the 0.25 m mark, the velocity reduction slows down, while the ore resistance becomes smaller. There exists a notable disparity in the resistance of ores with varying cross-sectional geometries. The size of the jet velocity surface caused by blowing distance significantly influences the resistance of ore with varying particle sizes. Furthermore, the resistance of the ore remains constant subsequent to the impact surface of the ore surpassing the surface of the jet velocity. Consequently, appropriately modifying the blowing distance, inlet pressure, and jet speed in accordance with the cross-sectional area and particle size of the majority of the ores stream can enhance the precision of the sorting process. [ABSTRACT FROM AUTHOR]

Recent studies matching eye gaze patterns with those of others contain research that is heavily reliant on string editing methods borrowed from early work in bioinformatics. Previous studies have shown string editing methods to be susceptible to false negative results when matching mutated genes or unordered regions of interest in scanpaths. Even as new methods have emerged for matching amino acids using novel combinatorial techniques, scanpath matching is still limited by a traditional collinear approach. This approach reduces the ability to discriminate between free viewing scanpaths of two people looking at the same stimulus due to the heavy weight placed on linearity. To overcome this limitation, we here introduce a new method called SoftMatch to compare pairs of scanpaths. SoftMatch diverges from traditional scanpath matching in two different ways: firstly, by preserving locality using fractal curves to reduce dimensionality from 2D Cartesian (x,y) coordinates into 1D (h) Hilbert distances, and secondly by taking a combinatorial approach to fixation matching using discrete Fréchet distance measurements between segments of scanpath fixation sequences. These matching “sequences of fixations over time” are a loose acronym for SoftMatch. Results indicate high degrees of statistical and substantive significance when scoring matches between scanpaths made during free-form viewing of unfamiliar stimuli. Applications of this method can be used to better understand bottom up perceptual processes extending to scanpath outlier detection, expertise analysis, pathological screening, and salience prediction.

Deep learning algorithms have been increasingly used in ship image detection and classification. To improve the ship detection and classification in photoelectric images, an improved recurrent attention convolutional neural network is proposed. The proposed network has a multi-scale architecture and consists of three cascading sub-networks, each with a VGG19 network for image feature extraction and an attention proposal network for locating feature area. A scale-dependent pooling algorithm is designed to select an appropriate convolution in the VGG19 network for classification, and a multi-feature mechanism is introduced in attention proposal network to describe the feature regions. The VGG19 and attention proposal network are cross-trained to accelerate convergence and to improve detection accuracy. The proposed method is trained and validated on a self-built ship database and effectively improve the detection accuracy to 86.7% outperforming the baseline VGG19 and recurrent attention convolutional neural network methods.

Objective: Using diffusion tensor imaging (DTI), we examined chronic stable MS lesions, peri-lesional white matter (PLWM) and normal appearing white matter (NAWM) in patients with relapsing-remitting multiple sclerosis (RRMS) for evidence of progressive tissue destruction and evaluated whether diffusivity change is associated with conventional MRI parameters and clinical findings. Method: Pre- and post-gadolinium T1, T2 and DTI images were acquired from 55 consecutive RRMS patients at baseline and 42.3±9.7months later. Chronic stable T2 lesions of sufficient size were identified in 43 patients (total of 134 lesions). Diffusivity parameters such as axial diffusivity (AD), radial diffusivity (RD), mean diffusivity (MD) and fractional anisotropy (FA) were compared at baseline and follow-up. MRI was also performed in 20 normal subjects of similar age and gender. Results: Within the core of chronic MS lesions the diffusion of water molecules significantly increased over the follow-up period, while in NAWM all diffusivity indices remained stable. Since increase of AD and RD in lesional core was highly concordant, indicating isotropic nature of diffusivity change, and considering potential effect of crossing fibers on directionally-selective indices, only MD, a directionally-independent measure, was used for further analysis. The significant increase of MD in the lesion core during the follow-up period (1.29±0.19μm2/ms and 1.34±0.20μm2/ms at baseline and follow-up respectively, P

Automatic severity assessment and progression prediction can facilitate admission, triage, and referral of COVID-19 patients. This study aims to explore the potential use of lung lesion features in the management of COVID-19, based on the assumption that lesion features may carry important diagnostic and prognostic information for quantifying infection severity and forecasting disease progression. A novel LesionEncoder framework is proposed to detect lesions in chest CT scans and to encode lesion features for automatic severity assessment and progression prediction. The LesionEncoder framework consists of a U-Net module for detecting lesions and extracting features from individual CT slices, and a recurrent neural network (RNN) module for learning the relationship between feature vectors and collectively classifying the sequence of feature vectors. Chest CT scans of two cohorts of COVID-19 patients from two hospitals in China were used for training and testing the proposed framework. When applied to assessing severity, this framework outperformed baseline methods achieving a sensitivity of 0.818, specificity of 0.952, accuracy of 0.940, and AUC of 0.903. It also outperformed the other tested methods in disease progression prediction with a sensitivity of 0.667, specificity of 0.838, accuracy of 0.829, and AUC of 0.736. The LesionEncoder framework demonstrates a strong potential for clinical application in current COVID-19 management, particularly in automatic severity assessment of COVID-19 patients. This framework also has a potential for other lesion-focused medical image analyses.