This study presents a unified low-parameter approach to multi-class classification of microorganisms (micrococci, diplococci, streptococci, and bacilli) based on automated machine learning. The method is designed to produce interpretable taxonomic descriptors through analysis of the external geometric characteristics of microorganisms, including cell shape, colony organization, and dynamic behavior in unfixed microscopic scenes. A key advantage of the proposed approach is its lightweight nature: the resulting models have significantly fewer parameters than deep learning-based alternatives, enabling fast inference even on standard CPU hardware. An annotated dataset containing images of four bacterial types obtained under conditions simulating real clinical trials has been developed and published to validate the method. The results (Precision = 0.910, Recall = 0.901, and F1-score = 0.905) confirm the effectiveness of the proposed method for biomedical diagnostic tasks, especially in settings with limited computational resources and a need for feature interpretability. Our approach demonstrates performance comparable to state-of-the-art methods while offering superior efficiency and lightweight design due to its significantly reduced number of parameters.
1 December 2024 in Pattern Recognition and Image Analysis
This paper presents a study aimed at improving the detection quality of small-sized microorganisms under challenging microscopic conditions through the application of a lightweight combined image preprocessing model. We focused on the task of detecting diplococci in images obtained through dynamic sample microscopy. The proposed approach employs predefined filters for image preprocessing, combined with the prediction of their applicability. This enables the elimination of artifacts such as blurred boundaries and indistinct edges, which are often encountered when working with small-sized objects in nonfixed scenes. The application of the proposed model has significantly improved detection quality compared to traditional methods.
β-glucans are biologically active biopolymers that influence metabolic activity and possess immunomodulatory, antitumor, anti-inflammatory, and wound-healing properties. The biological activity of β-glucans is influenced by both their primary structure and spatial conformation, which, in turn, depend on the natural source of the polysaccharides and their extraction methods. In this study, the water-soluble fraction of β-(1→3,1→6)-D-glucan, isolated from non-irradiated and irradiated Pleurotus ostreatus cryopowder pre-treated with alcohol, was investigated. Increasing the irradiation dose was found to increase the yield of the water-soluble glucan fraction. Furthermore, irradiation increased the solubility of glucans in water and reduced their bulk density and moisture content, which may be due to partial degradation of the biopolymer. According to FTIR and NMR spectroscopy, water-soluble glucan samples isolated from both irradiated and non-irradiated samples consist predominantly of β-(1→3,1→6)-D-glucan, protein, and a small amount of (1→3)-α-glucan. It was found that the triple-helix conformation of glucans in solution, assessed using Congo red analysis, did not change upon irradiation. Irradiation resulted in a dose-dependent increase in the antiradical activity of the glucans against the stable DPPH radical. Addition of irradiated glucans to sugar syrup used as a feed supplement for bee feeding resulted in a significant increase in the proline content of honey. Thus, electron irradiation is a promising method for obtaining β-glucans with high water solubility and contributes to enhancing their biological activity.
Timely identification and accurate delineation of ultra-early ischemic stroke lesions in non-contrast computed tomography (CT) scans of the human brain are of paramount importance for prompt medical intervention and improved patient outcomes. In this study, we propose a deep learning-driven methodology specifically designed for segmenting ultra-early ischemic regions, with a particular emphasis on both the ischemic core and the surrounding penumbra during the initial stages of stroke progression. We introduce a lightweight preprocessing model based on convolutional filtering techniques, which enhances image clarity while preserving the structural integrity of medical scans, a critical factor when detecting subtle signs of ultra-early ischemic strokes. Unlike conventional preprocessing methods that directly modify the image and may introduce artifacts or distortions, our approach ensures the absence of neural network-induced artifacts, which is especially crucial for accurate diagnosis and segmentation of ultra-early ischemic lesions. The model employs predefined differentiable filters with trainable parameters, allowing for artifact-free and precision-enhanced image refinement tailored to the challenges of ultra-early stroke detection. In addition, we incorporated into the combined preprocessing pipeline a newly proposed trainable linear combination of pretrained image filters, a concept first introduced in this study. For model training and evaluation, we utilize a publicly available dataset of acute ischemic stroke cases, focusing on the subset relevant to ultra-early stroke manifestations, which contains annotated non-contrast CT brain scans from 112 patients. The proposed model demonstrates high segmentation accuracy for ultra-early ischemic regions, surpassing existing methodologies across key performance metrics. The results have been rigorously validated on test subsets from the dataset, confirming the effectiveness of our approach in supporting the early-stage diagnosis and treatment planning for ultra-early ischemic strokes.
This paper presents a novel approach to classification in biomedical imaging, specifically targeting polyp recognition in video endoscopy snapshots. Our method leverages specialized image descriptors to enhance the accuracy and robustness of polyp recognition. By employing these specialized descriptors, we address the challenges inherent in analyzing biomedical images from open datasets. Our approach not only improves classification performance but also offers a comparative efficiency compared to the existing heavyweight deep neural network model baseline. These results are confirmed by the following metric values: precision 0.983, recall 0.969, and F1-score 0.976. The proposed method demonstrates significant potential for advancing diagnostic capabilities in medical imaging and contributes to the ongoing efforts to develop more effective tools for automated medical analysis without significant computational resource requirements.