Pattern Recognition or Adnexal MR Scoring System: Which Is More Accurate in Evaluating Adnexal Lesions?

PURPOSE: This study aims to compare the accuracy of the ADNEX MR scoring system and pattern recognition system to evaluate adnexal lesions indeterminate on the US exam. METHODS: In this cross-sectional retrospective study, pelvic DCE-MRI of 245 patients with 340 adnexal masses was studied based on the ADNEX MR scoring system and pattern recognition system. RESULTS: ADNEX MR scoring system with a sensitivity of 96.6% and specificity of 91% has an accuracy of 92.9%. The pattern recognition system's sensitivity, specificity, and accuracy are 95.8%, 93.3%, and 94.7%, respectively. PPV and NPV for the ADNEX MR scoring system were 85.1 and 98.1, respectively. PPV and NPV for the pattern recognition system were 89.7% and 97.7%, respectively. The area under the ROC curve for the ADNEX MR scoring system and pattern recognition system is 0.938 (95% CI, 0.909-0.967) and 0.950 (95% CI, 0.922-0.977). Pairwise comparison of these AUCs showed no significant difference (p = 0.052). CONCLUSION: The pattern recognition system is less sensitive than the ADNEX MR scoring system, yet more specific.

An Improved k-Nearest Neighbor Algorithm for Recognition and Classification of Thyroid Nodules.

OBJECTIVES: To complete the task of automatic recognition and classification of thyroid nodules and solve the problem of high classification error rates when the samples are imbalanced. METHODS: An improved k-nearest neighbor (KNN) algorithm is proposed and a method for automatic thyroid nodule classification based on the improved KNN algorithm is established. In the improved KNN algorithm, we consider not only the number of class labels for various classes of data in KNNs, but also the corresponding weights. And we use the Minkowski distance measure instead of the Euclidean distance measure. RESULTS: A total of 508 ultrasound images of thyroid nodules, including 415 benign nodules and 93 malignant nodules, were used in the paper. Experimental results show the improved KNN has 0.872549 accuracy, 0.867347 precision, 1 recall, and 0.928962 F1-score. At the same time, we also considered the influence of different distance weights, the value of k, different distance measures on the classification results. CONCLUSIONS: A comparison result shows that our method has a better performance than the traditional KNN and other classical machine learning methods.

Not without Context-A Multiple Methods Study on Evaluation and Correction of Automated Brain Tumor Segmentations by Experts.

RATIONALE AND OBJECTIVES: Brain tumor segmentations are integral to the clinical management of patients with glioblastoma, the deadliest primary brain tumor in adults. The manual delineation of tumors is time-consuming and highly provider-dependent. These two problems must be addressed by introducing automated, deep-learning-based segmentation tools. This study aimed to identify criteria experts use to evaluate the quality of automatically generated segmentations and their thought processes as they correct them. MATERIALS AND METHODS: Multiple methods were used to develop a detailed understanding of the complex factors that shape experts' perception of segmentation quality and their thought processes in correcting proposed segmentations. Data from a questionnaire and semistructured interview with neuro-oncologists and neuroradiologists were collected between August and December 2021 and analyzed using a combined deductive and inductive approach. RESULTS: Brain tumors are highly complex and ambiguous segmentation targets. Therefore, physicians rely heavily on the given context related to the patient and clinical context in evaluating the quality and need to correct brain tumor segmentation. Most importantly, the intended clinical application determines the segmentation quality criteria and editing decisions. Physicians' personal beliefs and preferences about the capabilities of AI algorithms and whether questionable areas should not be included are additional criteria influencing the perception of segmentation quality and appearance of an edited segmentation. CONCLUSION: Our findings on experts' perceptions of segmentation quality will allow the design of improved frameworks for expert-centered evaluation of brain tumor segmentation models. In particular, the knowledge presented here can inspire the development of brain tumor-specific metrics for segmentation model training and evaluation.

A Hierarchy-driven Multi-label Network with Label Constraints for Post-operative Complication Prediction of Lung Cancer.

Lung cancer is one of the most dangerous cancers all over the world. Surgical resection remains the only potentially curative option for patients with lung cancer. However, this invasive treatment often causes various complications, which seriously endanger patient health. In this study, we proposed a novel multi-label network, namely a hierarchy-driven multi-label network with label constraints (HDMN-LC), to predict the risk of complications of lung cancer patients. In this method, we first divided all complications into pulmonary and cardiovascular complication groups and employed the hierarchical cluster algorithm to analyze the hierarchies between these complications. After that, we employed the hierarchies to drive the network architecture design so that related complications could share more hidden features. And then, we combined all complications and employed an auxiliary task to predict whether any complications would occur to impose the bottom layer to learn general features. Finally, we proposed a regularization term to constrain the relationship between specific and combined complication labels to improve performance. We conducted extensive experiments on real clinical data of 593 patients. Experimental results indicate that the proposed method outperforms the single-label, multi-label baseline methods, with an average AUC value of 0.653. And the results also prove the effectiveness of hierarchy-driven network architecture and label constraints. We conclude that the proposed method can predict complications for lung cancer patients more effectively than the baseline methods.Clinical relevance-This study presents a novel multi-label network that can more accurately predict the risk of specific postoperative complications for lung cancer patients. The method can help clinicians identify high-risk patients more accurately and timely so that interventions can be implemented in advance to ensure patient safety.

Semi-supervised enhanced discriminative local constraint preserving projection for dimensionality reduction of medical hyperspectral images.

Microscopic hyperspectral images has the advantage of containing rich spatial and spectral information. However, the large number of spectral bands provides a significant amount of spectral features, but also leads to data redundancy and noise, which seriously affect the recognition and classification performance of the images, as well as increasing the requirements for computation and storage. To address this issue, we propose a dimensionality reduction algorithm named enhanced discriminant local constraint preserving projection (EDLCPP). Specifically, the global spectral attention mechanism focuses on important bands, the high discriminability sample selection module measures the discriminability of samples using a modified average neighborhood margin, the graph construction module preserves the local geometric relationship and discriminant information, and the graph embedding module embeds the constructed graphs into a low-dimensional space to obtain the projection matrices. Experimental results on eight cholangiocarcinoma (CCA) hyperspectral images, Bloodcell1-3, and Bloodcell2-2 datasets have demonstrated the effectiveness of the proposed method.

Laparoscopic Image-Based Critical Action Recognition and Anticipation With Explainable Features.

Surgical workflow analysis integrates perception, comprehension, and prediction of the surgical workflow, which helps real-time surgical support systems provide proper guidance and assistance for surgeons. This article promotes the idea of critical actions, which refer to the essential surgical actions that progress towards the fulfillment of the operation. Fine-grained workflow analysis involves recognizing current critical actions and previewing the moving tendency of instruments in the early stage of critical actions. Aiming at this, we propose a framework that incorporates operational experience to improve the robustness and interpretability of action recognition in in-vivo situations. High-dimensional images are mapped into an experience-based explainable feature space with low dimensions to achieve critical action recognition through a hierarchical classification structure. To forecast the instrument's motion tendency, we model the motion primitives in the polar coordinate system (PCS) to represent patterns of complex trajectories. Given the laparoscopy variance, the adaptive pattern recognition (APR) method, which adapts to uncertain trajectories by modifying model parameters, is designed to improve prediction accuracy. The in-vivo dataset validations show that our framework fulfilled the surgical awareness tasks with exceptional accuracy and real-time performance.

An efficient multi-level pre-processing algorithm for the enhancement of dermoscopy images in melanoma detection.

In this paper, a multi-level algorithm for pre-processing of dermoscopy images is proposed, which helps in improving the quality of the raw images, making it suitable for skin lesion detection. This multi-level pre-processing method has a positive impact on automated skin lesion segmentation using Regularized Extreme Learning Machine. Raw images are subjected to de-noising, illumination correction, contrast enhancement, sharpening, reflection removal, and virtual shaving before the skin lesion segmentation. The Non-Local Means (NLM) filter with lowest Blind Reference less Image Spatial Quality Evaluator (BRISQUE) score exhibits better de-noising of dermoscopy images. To suppress uneven illumination, gamma correction is subjected to the denoised image. The Robust Image Contrast Enhancement (RICE) algorithm is used for contrast enhancement, and produces enhanced images with better structural preservation and negligible loss of information. Unsharp masking for sharpening exhibits low BRISQUE scores for better sharpening of fine details in an image. Output images produced by the phase congruency-based method in virtual shaving show high similarity with ground truth images as the hair is removed completely from the input images. Obtained scores at each stage of pre-processing framework show that the performance is superior compared to all the existing methods, both qualitatively and quantitatively, in terms of uniform contrast, preservation of information content, removal of undesired information, and elimination of artifacts in melanoma images. The output of the proposed system is assessed qualitatively and quantitatively with and without pre-processing of dermoscopy images. From the overall evaluation results, it is found that the segmentation of skin lesion is more efficient using Regularized Extreme Learning Machine if the multi-level pre-processing steps are used in proper sequence.

Surgical Instrument Signaling Gesture Recognition Using Surface Electromyography Signals.

Surgical Instrument Signaling (SIS) is compounded by specific hand gestures used by the communication between the surgeon and surgical instrumentator. With SIS, the surgeon executes signals representing determined instruments in order to avoid error and communication failures. This work presented the feasibility of an SIS gesture recognition system using surface electromyographic (sEMG) signals acquired from the Myo armband, aiming to build a processing routine that aids telesurgery or robotic surgery applications. Unlike other works that use up to 10 gestures to represent and classify SIS gestures, a database with 14 selected gestures for SIS was recorded from 10 volunteers, with 30 repetitions per user. Segmentation, feature extraction, feature selection, and classification were performed, and several parameters were evaluated. These steps were performed by taking into account a wearable application, for which the complexity of pattern recognition algorithms is crucial. The system was tested offline and verified as to its contribution for all databases and each volunteer individually. An automatic segmentation algorithm was applied to identify the muscle activation; thus, 13 feature sets and 6 classifiers were tested. Moreover, 2 ensemble techniques aided in separating the sEMG signals into the 14 SIS gestures. Accuracy of 76% was obtained for the Support Vector Machine classifier for all databases and 88% for analyzing the volunteers individually. The system was demonstrated to be suitable for SIS gesture recognition using sEMG signals for wearable applications.

High-Order Correlation-Guided Slide-Level Histology Retrieval With Self-Supervised Hashing.

Histopathological Whole Slide Images (WSIs) play a crucial role in cancer diagnosis. It is of significant importance for pathologists to search for images sharing similar content with the query WSI, especially in the case-based diagnosis. While slide-level retrieval could be more intuitive and practical in clinical applications, most methods are designed for patch-level retrieval. A few recently unsupervised slide-level methods only focus on integrating patch features directly, without perceiving slide-level information, and thus severely limits the performance of WSI retrieval. To tackle the issue, we propose a High-Order Correlation-Guided Self-Supervised Hashing-Encoding Retrieval (HSHR) method. Specifically, we train an attention-based hash encoder with slide-level representation in a self-supervised manner, enabling it to generate more representative slide-level hash codes of cluster centers and assign weights for each. These optimized and weighted codes are leveraged to establish a similarity-based hypergraph, in which a hypergraph-guided retrieval module is adopted to explore high-order correlations in the multi-pairwise manifold to conduct WSI retrieval. Extensive experiments on multiple TCGA datasets with over 24,000 WSIs spanning 30 cancer subtypes demonstrate that HSHR achieves state-of-the-art performance compared with other unsupervised histology WSI retrieval methods.

SVM classifier of cervical histopathology images based on texture and morphological features.

BACKGROUND: Cervical histopathology image classification is a crucial indicator in cervical biopsy results. OBJECTIVE: The objective of this study is to identify histopathology images of cervical cancer at an early stage by extracting texture and morphological features for the Support Vector Machine (SVM) classifier. METHODS: We extract three different texture features and one morphological feature of cervical histopathology images: first-order histogram, K-means clustering, Gray Level Co-occurrence Matrix (GLCM) and nucleus feature. The original dataset used in our experiment is obtained from 20 patients diagnosed with cervical cancer, including 135 whole slide images (WSIs). Given an entire WSI, the patches on its tissue region are extracted randomly. RESULTS: We finally obtain 3,000 patches, including 1,000 normal, 1,000 hysteromyoma and 1,000 cancer images. Among them, 80% of the entire data set is randomly selected as training set and the remaining 20% as test set. The accuracy of SVM classification using first-order histogram, K-means clustering, GLAM and nucleus feature for extracting features are respectively 87.4%, 90.6%, 91.6% and 93.5%. CONCLUSIONS: The classification accuracy of the SVM combining the four features is 96.8%, and the proposed nucleus feature plays a key role in the SVM classification of cervical histopathology images.

Automatically Diagnosing Skin Cancers From Multimodality Images Using Two-Stage Genetic Programming.

Developing a computer-aided diagnostic system for detecting various skin malignancies from images has attracted many researchers. Unlike many machine-learning approaches, such as artificial neural networks, genetic programming (GP) automatically evolves models with flexible representation. GP successfully provides effective solutions using its intrinsic ability to select prominent features (i.e., feature selection) and build new features (i.e., feature construction). Existing approaches have utilized GP to construct new features from the complete set of original features and the set of operators. However, the complete set of features may contain redundant or irrelevant features that do not provide useful information for classification. This study aims to develop a two-stage GP method, where the first stage selects prominent features, and the second stage constructs new features from these selected features and operators, such as multiplication in a wrapper approach to improve the classification performance. To include local, global, texture, color, and multiscale image properties of skin images, GP selects and constructs features extracted from local binary patterns and pyramid-structured wavelet decomposition. The accuracy of this GP method is assessed using two real-world skin image datasets captured from the standard camera and specialized instruments, and compared with commonly used classification algorithms, three state of the art, and an existing embedded GP method. The results reveal that this new approach of feature selection and feature construction effectively helps improve the performance of the machine-learning classification algorithms. Unlike other black-box models, the evolved models by GP are interpretable; therefore, the proposed method can assist dermatologists to identify prominent features, which has been shown by further analysis on the evolved models.

Classifying neovascular age-related macular degeneration with a deep convolutional neural network based on optical coherence tomography images.

Neovascular age-related macular degeneration (nAMD) is among the main causes of visual impairment worldwide. We built a deep learning model to distinguish the subtypes of nAMD using spectral domain optical coherence tomography (SD-OCT) images. Data from SD-OCT images of nAMD (polypoidal choroidal vasculopathy, retinal angiomatous proliferation, and typical nAMD) and normal healthy patients were analyzed using a convolutional neural network (CNN). The model was trained and validated based on 4749 SD-OCT images from 347 patients and 50 healthy controls. To adopt an accurate and robust image classification architecture, we evaluated three well-known CNN structures (VGG-16, VGG-19, and ResNet) and two customized classification layers (fully connected layer with dropout vs. global average pooling). Following the test set performance, the model with the highest classification accuracy was used. Transfer learning and data augmentation were applied to improve the robustness and accuracy of the model. Our proposed model showed an accuracy of 87.4% on the test data (920 images), scoring higher than ten ophthalmologists, for the same data. Additionally, the part that our model judged to be important in classification was confirmed through Grad-CAM images, and consequently, it has a similar judgment criteria to that of ophthalmologists. Thus, we believe that our model can be used as an auxiliary tool in clinical practice.

Segmentation of HE-stained meningioma pathological images based on pseudo-labels.

Biomedical research is inseparable from the analysis of various histopathological images, and hematoxylin-eosin (HE)-stained images are one of the most basic and widely used types. However, at present, machine learning based approaches of the analysis of this kind of images are highly relied on manual labeling of images for training. Fully automated processing of HE-stained images remains a challenging task due to the high degree of color intensity, size and shape uncertainty of the stained cells. For this problem, we propose a fully automatic pixel-wise semantic segmentation method based on pseudo-labels, which concerns to significantly reduce the manual cell sketching and labeling work before machine learning, and guarantees the accuracy of segmentation. First, we collect reliable training samples in a unsupervised manner based on K-means clustering results; second, we use full mixup strategy to enhance the training images and to obtain the U-Net model for the nuclei segmentation from the background. The experimental results based on the meningioma pathology image dataset show that the proposed method has good performance and the pathological features obtained statistically based on the segmentation results can be used to assist in the clinical grading of meningiomas. Compared with other machine learning strategies, it can provide a reliable reference for clinical research more effectively.

Extraction of artefactual MRS patterns from a large database using non-negative matrix factorization.

Despite the success of automated pattern recognition methods in problems of human brain tumor diagnostic classification, limited attention has been paid to the issue of automated data quality assessment in the field of MRS for neuro-oncology. Beyond some early attempts to address this issue, the current standard in practice is MRS quality control through human (expert-based) assessment. One aspect of automatic quality control is the problem of detecting artefacts in MRS data. Artefacts, whose variety has already been reviewed in some detail and some of which may even escape human quality control, have a negative influence in pattern recognition methods attempting to assist tumor characterization. The automatic detection of MRS artefacts should be beneficial for radiology as it guarantees more reliable tumor characterizations, as well as the development of more robust pattern recognition-based tumor classifiers and more trustable MRS data processing and analysis pipelines. Feature extraction methods have previously been used to help distinguishing between good and bad quality spectra to apply subsequent supervised pattern recognition techniques. In this study, we apply feature extraction differently and use a variant of a method for blind source separation, namely Convex Non-Negative Matrix Factorization, to unveil MRS signal sources in a completely unsupervised way. We hypothesize that, while most sources will correspond to the different tumor patterns, some of them will reflect signal artefacts. The experimental work reported in this paper, analyzing a combined short and long echo time 1 H-MRS database of more than 2000 spectra acquired at 1.5T and corresponding to different tumor types and other anomalous masses, provides a first proof of concept that points to the possible validity of this approach.

Feasibility of ABUS as an Alternative to Handheld Ultrasound for Response Control in Neoadjuvant Breast Cancer Treatment.

INTRODUCTION: The Invenia Automated Breast Ultrasound Screening (ABUS) is indicated as an adjunct to mammography for breast cancer screening in asymptomatic women with high-density breast tissue. ABUS provides time-efficient evaluation of the 3-dimensional recordings within 3 to 6 minutes. The role and advantages of ABUS in everyday clinical practice, especially in routine examination during neoadjuvant chemotherapy (NACT), is not clear. The aim of this monocentric, noninterventional retrospective study is to evaluate the use of ABUS in patients who are under NACT treatment for response control. METHODS: Regular sonographic response check with handheld ultrasound (HHUS) examination and with ABUS were conducted in 83 women who underwent NACT. The response controls were conducted every 3 to 6 weeks during NACT. The handheld sonography was performed with GE Voluson S8. Handheld sonographic measurements and ABUS measurements were compared with the final pathologic tumor size. RESULTS: There was no statistical difference between the measurements with HHUS examination or ABUS compared with final pathologic tumor size (P = .47). The average difference from ABUS measured tumor size to final pathologic tumor size was 9.8 mm. The average difference from handheld measured tumor size to final pathologic tumor size was 9/3 mm. Both the specificity of ABUS and HHUS examination in predicting pathologic complete remission was 100%. CONCLUSION: ABUS seems to be a suitable method to conduct response control in neoadjuvant breast cancer treatment. ABUS may facilitate preoperative planning and offers remarkable time saving for physicians compared with HHUS examination and thus should be considered for clinical practice.

COMBING: Clustering in Oncology for Mathematical and Biological Identification of Novel Gene Signatures.

Precision medicine is a paradigm shift in healthcare relying heavily on genomics data. However, the complexity of biological interactions, the large number of genes as well as the lack of comparisons on the analysis of data, remain a tremendous bottleneck regarding clinical adoption. In this paper, we introduce a novel, automatic and unsupervised framework to discover low-dimensional gene biomarkers. Our method is based on the LP-Stability algorithm, a high dimensional center-based unsupervised clustering algorithm. It offers modularity as concerns metric functions and scalability, while being able to automatically determine the best number of clusters. Our evaluation includes both mathematical and biological criteria to define a quantitative metric. The recovered signature is applied to a variety of biological tasks, including screening of biological pathways and functions, and characterization relevance on tumor types and subtypes. Quantitative comparisons among different distance metrics, commonly used clustering methods and a referential gene signature used in the literature, confirm state of the art performance of our approach. In particular, our signature, based on 27 genes, reports at least 30 times better mathematical significance (average Dunn's Index) and 25% better biological significance (average Enrichment in Protein-Protein Interaction) than those produced by other referential clustering methods. Finally, our signature reports promising results on distinguishing immune inflammatory and immune desert tumors, while reporting a high balanced accuracy of 92% on tumor types classification and averaged balanced accuracy of 68% on tumor subtypes classification, which represents, respectively 7% and 9% higher performance compared to the referential signature.

A Master-Slave Binary Grey Wolf Optimizer for Optimal Feature Selection in Biomedical Data Classification.

A new master-slave binary grey wolf optimizer (MSBGWO) is introduced. A master-slave learning scheme is introduced to the grey wolf optimizer (GWO) to improve its ability to explore and get better solutions in a search space. Five high-dimensional biomedical datasets are used to test the ability of MSBGWO in feature selection. The experimental results of MSBGWO are superior in terms of classification accuracy, precision, recall, F-measure, and number of features selected when compared to those of the binary grey wolf optimizer version 2 (BGWO2), binary genetic algorithm (BGA), binary particle swarm optimization (BPSO), differential evolution (DE) algorithm, and sine-cosine algorithm (SCA).

Automated segmentation by deep learning of loose connective tissue fibers to define safe dissection planes in robot-assisted gastrectomy.

The prediction of anatomical structures within the surgical field by artificial intelligence (AI) is expected to support surgeons' experience and cognitive skills. We aimed to develop a deep-learning model to automatically segment loose connective tissue fibers (LCTFs) that define a safe dissection plane. The annotation was performed on video frames capturing a robot-assisted gastrectomy performed by trained surgeons. A deep-learning model based on U-net was developed to output segmentation results. Twenty randomly sampled frames were provided to evaluate model performance by comparing Recall and F1/Dice scores with a ground truth and with a two-item questionnaire on sensitivity and misrecognition that was completed by 20 surgeons. The model produced high Recall scores (mean 0.606, maximum 0.861). Mean F1/Dice scores reached 0.549 (range 0.335-0.691), showing acceptable spatial overlap of the objects. Surgeon evaluators gave a mean sensitivity score of 3.52 (with 88.0% assigning the highest score of 4; range 2.45-3.95). The mean misrecognition score was a low 0.14 (range 0-0.7), indicating very few acknowledged over-detection failures. Thus, AI can be trained to predict fine, difficult-to-discern anatomical structures at a level convincing to expert surgeons. This technology may help reduce adverse events by determining safe dissection planes.

An Optimized Method for Skin Cancer Diagnosis Using Modified Thermal Exchange Optimization Algorithm.

Skin cancer is the most common cancer of the body. It is estimated that more than one million people worldwide develop skin cancer each year. Early detection of this cancer has a high effect on the disease treatment. In this paper, a new optimal and automatic pipeline approach has been proposed for the diagnosis of this disease from dermoscopy images. The proposed method includes a noise reduction process before processing for eliminating the noises. Then, the Otsu method as one of the widely used thresholding method is used to characterize the region of interest. Afterward, 20 different features are extracted from the image. To reduce the method complexity, a new modified version of the Thermal Exchange Optimization Algorithm is performed to the features. This improves the method precision and consistency. To validate the proposed method's efficiency, it is implemented to the American Cancer Society database, its results are compared with some state-of-the-art methods, and the final results showed the superiority of the proposed method against the others.

CRDet: Improving Signet Ring Cell Detection by Reinforcing the Classification Branch.

Detecting signet ring cells on histopathologic images is a critical computer-aided diagnostic task that is highly relevant to cancer grading and patients' survival rates. However, the cells are densely distributed and exhibit diverse and complex visual patterns in the image, together with the commonly observed incomplete annotation issue, posing a significant barrier to accurate detection. In this article, we propose to mitigate the detection difficulty from a model reinforcement point of view. Specifically, we devise a Classification Reinforcement Detection Network (CRDet). It is featured by adding a dedicated Classification Reinforcement Branch (CRB) on top of the architecture of Cascade RCNN. The proposed CRB consists of a context pooling module to perform a more robust feature representation by fully making use of context information, and a feature enhancement classifier to generate a superior feature by leveraging the deconvolution and attention mechanism. With the enhanced feature, the small-sized cell can be better characterized and CRDet enjoys a more accurate signet ring cell identification. We validate our proposal on a large-scale real clinical signet ring cell data set. It is shown that CRDet outperforms several popular convolutional neural network-based object detection models on this particular task.