Enhancements in Radiological Detection of Metastatic Lymph Nodes Utilizing AI-Assisted Ultrasound Imaging Data and the Lymph Node Reporting and Data System Scale.

The paper presents a novel approach for the automatic detection of neoplastic lesions in lymph nodes (LNs). It leverages the latest advances in machine learning (ML) with the LN Reporting and Data System (LN-RADS) scale. By integrating diverse datasets and network structures, the research investigates the effectiveness of ML algorithms in improving diagnostic accuracy and automation potential. Both Multinominal Logistic Regression (MLR)-integrated and fully connected neuron layers are included in the analysis. The methods were trained using three variants of combinations of histopathological data and LN-RADS scale labels to assess their utility. The findings demonstrate that the LN-RADS scale improves prediction accuracy. MLR integration is shown to achieve higher accuracy, while the fully connected neuron approach excels in AUC performance. All of the above suggests a possibility for significant improvement in the early detection and prognosis of cancer using AI techniques. The study underlines the importance of further exploration into combined datasets and network architectures, which could potentially lead to even greater improvements in the diagnostic process.

Custom Loss Functions in XGBoost Algorithm for Enhanced Critical Error Mitigation in Drill-Wear Analysis of Melamine-Faced Chipboard.

The advancement of machine learning in industrial applications has necessitated the development of tailored solutions to address specific challenges, particularly in multi-class classification tasks. This study delves into the customization of loss functions within the eXtreme Gradient Boosting (XGBoost) algorithm, which is a critical step in enhancing the algorithm's performance for specific applications. Our research is motivated by the need for precision and efficiency in the industrial domain, where the implications of misclassification can be substantial. We focus on the drill-wear analysis of melamine-faced chipboard, a common material in furniture production, to demonstrate the impact of custom loss functions. The paper explores several variants of Weighted Softmax Loss Functions, including Edge Penalty and Adaptive Weighted Softmax Loss, to address the challenges of class imbalance and the heightened importance of accurately classifying edge classes. Our findings reveal that these custom loss functions significantly reduce critical errors in classification without compromising the overall accuracy of the model. This research not only contributes to the field of industrial machine learning by providing a nuanced approach to loss function customization but also underscores the importance of context-specific adaptations in machine learning algorithms. The results showcase the potential of tailored loss functions in balancing precision and efficiency, ensuring reliable and effective machine learning solutions in industrial settings.

Application of Siamese Networks to the Recognition of the Drill Wear State Based on Images of Drilled Holes.

In this article, a Siamese network is applied to the drill wear classification problem. For furniture companies, one of the main problems that occurs during the production process is finding the exact moment when the drill should be replaced. When the drill is not sharp enough, it can result in a poor quality product and therefore generate some financial loss for the company. In various approaches to this problem, usually, three classes are considered: green for a drill that is sharp, red for the opposite, and yellow for a tool that is suspected of being worn out, requiring additional evaluation by a human expert. In the above problem, it is especially important that the green and the red classes not be mistaken, since such errors have the highest probability of generating financial loss for the manufacturer. Most of the solutions analysing this problem are too complex, requiring specialized equipment, high financial investment, or both, without guaranteeing that the obtained results will be satisfactory. In the approach presented in this paper, images of drilled holes are used as the training data for the Siamese network. The presented solution is much simpler in terms of the data collection methodology, does not require a large financial investment for the initial equipment, and can accurately qualify drill wear based on the chosen input. It also takes into consideration additional manufacturer requirements, like no green-red misclassifications, that are usually omitted in existing solutions.

False-positive reduction in computer-aided mass detection using mammographic texture analysis and classification.

BACKGROUND AND OBJECTIVE: The aim of computer-aided-detection (CAD) systems for mammograms is to assist radiologists by marking region of interest (ROIs) depicting abnormalities. However, the confusing appearance of some normal tissues that visually look like masses results in a large proportion of marked ROIs with normal tissues. This paper copes with this problem and proposes a framework to reduce false positive masses detected by CAD. METHODS: To avoid the error induced by the segmentation step, we proposed a segmentation-free framework with particular attention to improve feature extraction and classification steps. We investigated for the first time in mammogram analysis, Hilbert's image representation, Kolmogorov-Smirnov distance and maximum subregion descriptors. Then, a feature selection step is performed to select the most discriminative features. Moreover, we considered several classifiers such as Random Forest, Support Vector Machine and Decision Tree to distinguish between normal tissues and masses. Our experiments were carried out on a large dataset of 10168 ROIs (8254 normal tissues and 1914 masses) constructed from the Digital Database for Screening Mammography (DDSM). To simulate practical scenario, our normal regions are false positives asserted by a CAD system from healthy cases. RESULTS: The combination of all the descriptors yields better results than each feature set used alone, and the difference is statistically significant. Besides, the feature selection steps yields a statistically significant increase in the accuracy values for the three classifiers. Finally, the random forest achieves the highest accuracy (81.09%), outperforming the SVM classifier (80.01%)) and decision tree (79.12%), but the difference is not statistically significant. CONCLUSIONS: The accuracy of discrimination between normal and abnormal ROIs in mammograms obtained with the proposed gray level texture features sets are encouraging and comparable to these obtained with multiresolution features. Combination of several features as well as feature selection steps improve the results. To improve false positives reduction in CAD systems for breast cancer diagnosis, these features could be combined with multiresolution features.

System for automatic heart rate calculation in epileptic seizures.

This article presents a comprehensive system for automatic heart rate (HR) detection. The system is robust and resistant to disturbances (noise, interferences, artifacts) occurring mainly during epileptic seizures. ECG signal filtration (IIR) and normalization due to skewness and standard deviation were used as preprocessing steps. A key element of the system is a reference QRS complex pattern calculated individually for each ECG recording. Next, a cross-correlation of the reference QRS pattern with short, normalized ECG windows is calculated and the maxima of the correlation are found (R-wave locations). Determination of the RR intervals makes possible calculation of heart rate changes and also heart rate variability (HRV). The algorithm was tested using a simulation in which a noise of an amplitude several times higher than ECG standard deviation levels was added. The proposed algorithm is characterized by high QRS detection accuracy, and high sensitivity and specificity. The algorithm proved to be useful in clinical practice, where it was used to automatically determine HR for ECG signals recorded before and during 58 focal seizures in 56 adult patients with intractable temporal lobe epilepsy.

Computer approach to recognition of Fuhrman grade of cells in clear-cell renal cell carcinoma.

OBJECTIVE: To present a computerized system for recognition of Fuhrman grade of cells in clear-cell renal cell carcinoma on the basis of microscopic images of the neoplasm cells in application of hematoxylin and eosin staining. STUDY DESIGN: The applied methods use combined gradient and mathematical morphology to obtain nuclei and classifiers in the form of support vector machine to estimate their Fuhrman grade. The starting point is a microscopic kidney image, which is subject to the advanced methods of preprocessing, leading finally to estimation of Fuhrman grade of cells and the whole analyzed image. RESULTS: The results of the numerical experiments have shown that the proposed nuclei descriptors based on different principles of generation are well connected with the Fuhrman grade. These descriptors have been used as the diagnostic features forming the inputs to the classifier, which performs the final recognition of the cells. The average discrepancy rate between the score of our system and the human expert results, estimated on the basis of over 3,000 nuclei, is below 10%. CONCLUSION: The obtained results have shown that the system is able to recognize 4 Fuhrman grades of the cells with high statistical accuracy and agreement with different expert scores. This result gives a good perspective to apply the system for supporting and accelerating the research of kidney cancer.

Nucleolus detection in the Fuhrman grading system for application in CCRC.

The paper presents a method for nucleolus detection in images of nuclei in clear-cell renal carcinoma (CCRC). The method is based on the similarity of the nuclei image and the two-dimensional paraboloidal window function. The results of numerical experiments performed on almost 2600 images of CCRC nuclei have confirmed the good accuracy of the method. The developed algorithm will be used to accelerate further research in computer-assisted diagnosis of CCRC.