Use of MRI Radiomics Models in Evaluating the Low HER2 Expression in Breast Cancer.

OBJECTIVE: To investigate the magnetic resonance imaging (MRI) radiomics models in evaluating the human epidermal growth factor receptor 2(HER2) expression in breast cancer.

Materials and Methods: The MRI data of 161 patients with invasive ductal carcinoma (non-special type) of breast cancer were retrospectively collected, and the MRI radiomics models were established based on the MRI imaging features of the fat suppression T2 weighted image (T2WI) sequence, dynamic contrast-enhanced (DCE)-T1WIsequence and joint sequences. The T-test and the least absolute shrinkage and selection operator (LASSO) algorithm were used for feature dimensionality reduction and screening, respectively, and the random forest (RF) algorithm was used to construct the classification model.

Results: The model established by the LASSO-RF algorithm was used in the ROC curve analysis. In predicting the low expression state of HER2 in breast cancer, the radiomics models of the fat suppression T2WI sequence, DCE-T1WI sequence, and the combination of the two sequences showed better predictive efficiency. In the receiver operating characteristic (ROC) curve analysis for the verification set of low, negative, and positive HER2 expression, the area under the ROC curve (AUC) value was 0.81, 0.72, and 0.62 for the DCE-T1WI sequence model, 0.79, 0.65 and 0.77 for the T2WI sequence model, and 0.84, 0.73 and 0.66 for the joint sequence model, respectively. The joint sequence model had the highest AUC value.

Conclusions: The MRI radiomics models can be used to effectively predict the HER2 expression in breast cancer and provide a non-invasive and early assistant method for clinicians to formulate individualized and accurate treatment plans.

A study on the application of radiomics based on cardiac MR non-enhanced cine sequence in the early diagnosis of hypertensive heart disease.

BACKGROUND: The prevalence of hypertensive heart disease (HHD) is high and there is currently no easy way to detect early HHD. Explore the application of radiomics using cardiac magnetic resonance (CMR) non-enhanced cine sequences in diagnosing HHD and latent cardiac changes caused by hypertension. METHODS: 132 patients who underwent CMR scanning were divided into groups: HHD (42), hypertension with normal cardiac structure and function (HWN) group (46), and normal control (NOR) group (44). Myocardial regions of the end-diastolic (ED) and end-systolic (ES) phases of the CMR short-axis cine sequence images were segmented into regions of interest (ROI). Three feature subsets (ED, ES, and ED combined with ES) were established after radiomic least absolute shrinkage and selection operator feature selection. Nine radiomic models were built using random forest (RF), support vector machine (SVM), and naive Bayes. Model performance was analyzed using receiver operating characteristic curves, and metrics like accuracy, area under the curve (AUC), precision, recall, and specificity. RESULTS: The feature subsets included first-order, shape, and texture features. SVM of ED combined with ES achieved the highest accuracy (0.833), with a macro-average AUC of 0.941. AUCs for HHD, HWN, and NOR identification were 0.967, 0.876, and 0.963, respectively. Precisions were 0.972, 0.740, and 0.826; recalls were 0.833, 0.804, and 0.863, respectively; and specificities were 0.989, 0.863, and 0.909, respectively. CONCLUSIONS: Radiomics technology using CMR non-enhanced cine sequences can detect early cardiac changes due to hypertension. It holds promise for future use in screening for latent cardiac damage in early HHD.

Predicting Risk Stratification in Early-Stage Endometrial Carcinoma: Significance of Multiparametric MRI Radiomics Model.

Endometrial carcinoma (EC) risk stratification prior to surgery is crucial for clinical treatment. In this study, we intend to evaluate the predictive value of radiomics models based on magnetic resonance imaging (MRI) for risk stratification and staging of early-stage EC. The study included 155 patients who underwent MRI examinations prior to surgery and were pathologically diagnosed with early-stage EC between January, 2020, and September, 2022. Three-dimensional radiomics features were extracted from segmented tumor images captured by MRI scans (including T2WI, CE-T1WI delayed phase, and ADC), with 1521 features extracted from each of the three modalities. Then, using five-fold cross-validation and a multilayer perceptron algorithm, these features were filtered using Pearson's correlation coefficient to develop a prediction model for risk stratification and staging of EC. The performance of each model was assessed by analyzing ROC curves and calculating the AUC, accuracy, sensitivity, and specificity. In terms of risk stratification, the CE-T1 sequence demonstrated the highest predictive accuracy of 0.858 ± 0.025 and an AUC of 0.878 ± 0.042 among the three sequences. However, combining all three sequences resulted in enhanced predictive accuracy, reaching 0.881 ± 0.040, with a corresponding increase in the AUC to 0.862 ± 0.069. In the context of staging, the utilization of a combination involving T2WI with CE-T1WI led to a notably elevated predictive accuracy of 0.956 ± 0.020, surpassing the accuracy achieved when employing any singular feature. Correspondingly, the AUC was 0.979 ± 0.022. When incorporating all three sequences concurrently, the predictive accuracy reached 0.956 ± 0.000, accompanied by an AUC of 0.986 ± 0.007. It is noteworthy that this level of accuracy surpassed that of the radiologist, which stood at 0.832. The MRI radiomics model has the potential to accurately predict the risk stratification and early staging of EC.

TBACkp: HER2 expression status classification network focusing on intrinsic subenvironmental characteristics of breast cancer liver metastases.

The HER2 expression status in breast cancer liver metastases is a crucial indicator for the diagnosis, treatment, and prognosis assessment of patients. And typical diagnosis involves assessing the HER2 expression status through invasive procedures like biopsy. However, this method has certain drawbacks, such as being difficult in obtaining tissue samples and requiring long examination periods. To address these limitations, we propose an AI-aided diagnostic model. This model enables rapid diagnosis. It diagnoses a patient's HER2 expression status on the basis of preprocessed images, which is the region of the lesion extracted from a CT image rather than from an actual tissue sample. The algorithm of the model adopts a parallel structure, including a Branch Block and a Trunk Block. The Branch Block is responsible for extracting the gradient characteristics between the tumor sub-environments, and the Trunk Block is for fusing the characteristics extracted by the Branch Block. The Branch Block contains CNN with self-attention, which combines the advantages of CNN and self-attention to extract more meticulous and comprehensive image features. And the Trunk Block is so designed that it fuses the extracted image feature information without affecting the transmission of the original image features. The Conv-Attention is used to calculate the attention in the Trunk Block, which uses kernel dot product and is responsible for providing the weight for the self-attention in the process of using convolution induced deviation calculation. Combined with the structure of the model and the method used, we refer to this model as TBACkp. The dataset comprises the enhanced abdominal CT images of 151 patients with liver metastases from breast cancer, together with the corresponding HER2 expression levels for each patient. The experimental results are as follows: (AUC: 0.915, ACC: 0.854, specificity: 0.809, precision: 0.863, recall: 0.881, F1-score: 0.872). The results demonstrate that this method can accurately assess the HER2 expression status in patients when compared with other advanced deep learning model.

Robust Vascular Segmentation for Raw Complex Images of Laser Speckle Contrast Based on Weakly Supervised Learning.

Laser speckle contrast imaging (LSCI) is widely used for in vivo real-time detection and analysis of local blood flow microcirculation due to its non-invasive ability and excellent spatial and temporal resolution. However, vascular segmentation of LSCI images still faces a lot of difficulties due to numerous specific noises caused by the complexity of blood microcirculation's structure and irregular vascular aberrations in diseased regions. In addition, the difficulties of LSCI image data annotation have hindered the application of deep learning methods based on supervised learning in the field of LSCI image vascular segmentation. To tackle these difficulties, we propose a robust weakly supervised learning method, which selects the threshold combinations and processing flows instead of labor-intensive annotation work to construct the ground truth of the dataset, and design a deep neural network, FURNet, based on UNet++ and ResNeXt. The model obtained from training achieves high-quality vascular segmentation and captures multi-scene vascular features on both constructed and unknown datasets with good generalization. Furthermore, we intravital verified the availability of this method on a tumor before and after embolization treatment. This work provides a new approach for realizing LSCI vascular segmentation and also makes a new application-level advance in the field of artificial intelligence-assisted disease diagnosis.

Radiomics model based on multi-sequence MRI for preoperative prediction of ki-67 expression levels in early endometrial cancer.

To validate a radiomics model based on multi-sequence magnetic resonance imaging (MRI) in predicting the ki-67 expression levels in early-stage endometrial cancer, 131 patients with early endometrial cancer who had undergone pathological examination and preoperative MRI scan were retrospectively enrolled and divided into two groups based on the ki-67 expression levels. The radiomics features were extracted from the T2 weighted imaging (T2WI), dynamic contrast enhanced T1 weighted imaging (DCE-T1WI), and apparent diffusion coefficient (ADC) map and screened using the Pearson correlation coefficients (PCC). A multi-layer perceptual machine and fivefold cross-validation were used to construct the radiomics model. The receiver operating characteristic (ROC) curves analysis, calibration curves, and decision curve analysis (DCA) were used to assess the models. The combined multi-sequence radiomics model of T2WI, DCE-T1WI, and ADC map showed better discriminatory powers than those using only one sequence. The combined radiomics models with multi-sequence fusions achieved the highest area under the ROC curve (AUC). The AUC value of the validation set was 0.852, with an accuracy of 0.827, sensitivity of 0.844, specificity of 0.773, and precision of 0.799. In conclusion, the combined multi-sequence MRI based radiomics model enables preoperative noninvasive prediction of the ki-67 expression levels in early endometrial cancer. This provides an objective imaging basis for clinical diagnosis and treatment.

Using machine learning-based radiomics to differentiate between glioma and solitary brain metastasis from lung cancer and its subtypes.

OBJECTIVE: To establish a machine learning-based radiomics model to differentiate between glioma and solitary brain metastasis from lung cancer and its subtypes, thereby achieving accurate preoperative classification. MATERIALS AND METHODS: A retrospective analysis was conducted on MRI T1WI-enhanced images of 105 patients with glioma and 172 patients with solitary brain metastasis from lung cancer, which were confirmed pathologically. The patients were divided into the training group and validation group in an 8:2 ratio for image segmentation, extraction, and filtering; multiple layer perceptron (MLP), support vector machine (SVM), random forest (RF), and logistic regression (LR) were used for modeling; fivefold cross-validation was used to train the model; the validation group was used to evaluate and assess the predictive performance of the model, ROC curve was used to calculate the accuracy, sensitivity, and specificity of the model, and the area under curve (AUC) was used to assess the predictive performance of the model. RESULTS: The accuracy and AUC of the MLP differentiation model for high-grade glioma and solitary brain metastasis in the validation group was 0.992, 1.000, respectively, while the sensitivity and specificity were 1.000, 0.968, respectively. The accuracy and AUC for the MLP and SVM differentiation model for high-grade glioma and small cell lung cancer brain metastasis in the validation group was 0.966, 1.000, respectively, while the sensitivity and specificity were 1.000, 0.929, respectively. The accuracy and AUC for the MLP differentiation model for high-grade glioma and non-small cell lung cancer brain metastasis in the validation group was 0.982, 0.999, respectively, while the sensitivity and specificity were 0.958, 1.000, respectively. CONCLUSION: The application of machine learning-based radiomics has a certain clinical value in differentiating glioma from solitary brain metastasis from lung cancer and its subtypes. In the HGG/SBM and HGG/NSCLC SBM validation groups, the MLP model had the best diagnostic performance, while in the HGG/SCLC SBM validation group, the MLP and SVM models had the best diagnostic performance.

Osteoporosis prediction in lumbar spine X-ray images using the multi-scale weighted fusion contextual transformer network.

Osteoporosis is a bone-related disease characterized by decreased bone density and mass, leading to brittle fractures. Osteoporosis assessment from radiographs using a deep learning algorithm has proven a low-cost alternative to the golden standard DXA. Due to the considerable noise and low contrast, automated diagnosis of osteoporosis in X-ray images still poses a significant challenge for traditional diagnostic methods. In this paper, an end-to-end transformer-style network was proposed, termed FCoTNet, to overcome the shortcoming of insufficient fusion of texture information and local features in the traditional CoTNet. To extract complementary geometric representations at each scale of the transformer module, we integrated parallel multi-scale feature extraction architectures in each unit layer of FCoTNet to utilize convolution to aggregate features from different receptive fields. Moreover, in order to extract small-scale texture features which were more critical to the diagnosis of osteoporosis in radiographs, larger fusion weights were assigned to the feature maps with small-size receptive fields. Afterward, the multi-scale global modeling was conducted by self-attention mechanism. The proposed model was first investigated on a private lumbar spine X-ray dataset with the 5-fold cross-validation strategy, obtaining an average accuracy of 78.29 ± 0.93 %, an average sensitivity of 69.72 ± 2.35 %, and an average specificity of 88.92 ± 0.67 % for the multi-classification of normal, osteopenia, and osteoporosis categories. We then conducted a controlled trial with five orthopedic clinicians to evaluate the clinical value of the model. The average clinician's accuracy improved from 61.50 ± 10.79 % unaided to 80.00 ± 5.92 % aided (18.50 % improvement), sensitivity improved from 64.38 ± 8.07 % unaided to 83.31 ± 5.43 % aided (18.93 % improvement), and specificity improved from 80.11 ± 4.72 % unaided to 89.94 ± 3.82 % aided (9.83 % improvement). Meanwhile, the prediction consistency among clinicians significantly improved with the assistance of FCoTNet. Furthermore, the proposed model showed good robustness on an external test dataset. These investigations indicate that the proposed deep learning model achieves state-of-the-art performance for osteoporosis prediction, which substantially improves osteoporosis screening and reduced osteoporosis fractures.

URNet: System for recommending referrals for community screening of diabetic retinopathy based on deep learning.

Diabetic retinopathy (DR) will cause blindness if the detection and treatment are not carried out in the early stages. To create an effective treatment strategy, the severity of the disease must first be divided into referral-warranted diabetic retinopathy (RWDR) and non-referral diabetic retinopathy (NRDR). However, there are usually no sufficient fundus examinations due to lack of professional service in the communities, particularly in the developing countries. In this study, we introduce UGAN_Resnet_CBAM (URNet; UGAN is a generative adversarial network that uses Unet for feature extraction), a two-stage end-to-end deep learning technique for the automatic detection of diabetic retinopathy. The characteristics of DDR fundus data set were used to design an adaptive image preprocessing module in the first stage. Gradient-weighted Class Activation Mapping (Grad-CAM) and t-distribution and stochastic neighbor embedding (t-SNE) were used as the evaluation indices to analyze the preprocessing results. In the second stage, we enhanced the performance of the Resnet50 network by integrating the convolutional block attention module (CBAM). The outcomes demonstrate that our proposed solution outperformed other current structures, achieving 94.5% and 94.4% precisions, and 96.2% and 91.9% recall for NRDR and RWDR, respectively.

Robust vessel segmentation in laser speckle contrast images based on semi-weakly supervised learning.

Objective.The goal of this study is to develop a robust semi-weakly supervised learning strategy for vessel segmentation in laser speckle contrast imaging (LSCI), addressing the challenges associated with the low signal-to-noise ratio, small vessel size, and irregular vascular aberration in diseased regions, while improving the performance and robustness of the segmentation method.Approach.For the training dataset, the healthy vascular images denoted as normal-vessel samples were manually labeled, while the diseased LSCI images involving tumor or embolism were denoted as abnormal-vessel samples and annotated as pseudo labels by the traditional semantic segmentation methods. In the training phase, the pseudo labels were constantly updated to improve the segmentation accuracy based on DeepLabv3+. Objective evaluation was conducted on the normal-vessel test set, while subjective evaluation was performed on the abnormal-vessel test set.Main results.The proposed method achieved an IOU of 0.8671, a Dice of 0.9288, and a mean relative percentage difference (mRPD) with supervised learning of 0.5% in the objective evaluation. In the subjective evaluation, our method significantly outperformed other methods in main vessel segmentation, tiny vessel segmentation, and blood vessel connection. Additionally, our method exhibited robustness when abnormal-vessel style noise was added to normal-vessel samples using a style translation network.Significance.The proposed semi-weakly supervised learning strategy demonstrates high efficiency and excellent robustness for vascular segmentation in LSCI, providing a potential tool for assessing the morphological and structural features of vessels in clinical applications.

Deep Learning Based on Enhanced MRI T1 Imaging to Differentiate Small-cell and Non-small-cell Primary Lung Cancers in Patients with Brain Metastases.

OBJECTIVES: To differentiate the primary small-cell lung cancer (SCLC) and non-small-cell lung cancer (NSCLC) for patients with brain metastases (BMs) based on a deep learning (DL) model using contrast-enhanced magnetic resonance imaging (MRI) T1 weighted (T1CE) images. METHODS: Out of 711 patients with BMs of lung cancer origin (SCLC 232, NSCLC 479), the MRI datasets of 192 patients (lesions' widths and heights > 30 pixels) with BMs from lung cancer (73 SCLC and 119 NSCLC) confirmed pathologically were enrolled, retrospectively. A typical convolutional neural network ResNet18 was applied for the automatic classification of BMs lesions from lung cancer based on T1CE images, with training and testing groups randomized per patient to eliminate learning bias. A 5-fold cross-validation was performed to evaluate the classification of the model. The receiver operating characteristic (ROC) curve, accuracy, precision, recall and f1 score were calculated. RESULTS: For a 5-fold cross-validation test, the DL model achieved AUCs of 0.8019 and 0.8024 for SCLC and NSCLC patients with BMs, respectively, and a mean overall accuracy of 0.7515±0.04. The DL model performed well in differentiating the primary SCLC and NSCLC with BMs. CONCLUSION: The proposed DL model is feasible and effective in differentiating the pathological subtypes of SCLC and NSCLC causing BMs, which may be used as a new tool for oncologists to diagnose noninvasively BMs and guide therapy based on the imaging structure of tumors.

[Research status and prospect of artificial intelligence technology in the diagnosis of urinary system tumors].

With the rapid development of artificial intelligence technology, researchers have applied it to the diagnosis of various tumors in the urinary system in recent years, and have obtained many valuable research results. The article sorted the research status of artificial intelligence technology in the fields of renal tumors, bladder tumors and prostate tumors from three aspects: the number of papers, image data, and clinical tasks. The purpose is to summarize and analyze the research status and find new valuable research ideas in the future. The results show that the artificial intelligence model based on medical data such as digital imaging and pathological images is effective in completing basic diagnosis of urinary system tumors, image segmentation of tumor infiltration areas or specific organs, gene mutation prediction and prognostic effect prediction, but most of the models for the requirement of clinical application still need to be improved. On the one hand, it is necessary to further improve the detection, classification, segmentation and other performance of the core algorithm. On the other hand, it is necessary to integrate more standardized medical databases to effectively improve the diagnostic accuracy of artificial intelligence models and make it play greater clinical value.

Automatic detection and segmentation of adenomatous colorectal polyps during colonoscopy using Mask R-CNN.

Colorectal cancer (CRC) is one of the main alimentary tract system malignancies affecting people worldwide. Adenomatous polyps are precursors of CRC, and therefore, preventing the development of these lesions may also prevent subsequent malignancy. However, the adenoma detection rate (ADR), a measure of the ability of a colonoscopist to identify and remove precancerous colorectal polyps, varies significantly among endoscopists. Here, we attempt to use a convolutional neural network (CNN) to generate a unique computer-aided diagnosis (CAD) system by exploring in detail the multiple-scale performance of deep neural networks. We applied this system to 3,375 hand-labeled images from the screening colonoscopies of 1,197 patients; of whom, 3,045 were assigned to the training dataset and 330 to the testing dataset. The images were diagnosed simply as either an adenomatous or non-adenomatous polyp. When applied to the testing dataset, our CNN-CAD system achieved a mean average precision of 89.5%. We conclude that the proposed framework could increase the ADR and decrease the incidence of interval CRCs, although further validation through large multicenter trials is required.

Feature-based attention elicited by precueing in an orientation discrimination task.

Specific visual features can be attended to and processed with a higher priority by our brain, termed feature-based attention (FBA). Two potential mechanisms for FBA have been suggested: goal-driven attentional mediating and stimulus-driven feature priming. Some researchers argued that several reported top-down FBA effects might also involve the influence of feature priming. To clarify this confusion, we used an orientation discrimination task in which the target was tilted randomly from the horizontal or vertical axis and presented at one of four iso-eccentric positions. The target's orientation was precued from trial to trial by an oriented line (Experiment 1) or by a symbolic arrow presented peripherally (Experiment 2) or centrally (Experiments 3/4). The cue could be either valid or invalid according to the congruency of its indicating orientation with the target's nearest cardinal axis. Our results demonstrate that the discrimination speed was significantly faster following a valid than an invalid cue (validity effect) in the session with 80% cue validity when both response accuracy and speed were emphasized. Moreover, this validity effect could also be observed in the session with 50% cue validity using the line cue (Experiment 1), even though its magnitude was significantly reduced, which illustrates the impact of feature priming. However, we did not find the validity effect in the session with 50% cue validity using the symbolic cue (Experiments 2/3). These modulations on the magnitude of the validity effect should be ascribed to top-down attentional mediating that is independent of spatial attention (illustrated by Experiment 3). Importantly, when response accuracy was stressed over speed in Experiment 4, the accuracy was significantly higher following a valid than an invalid cue in the session with 80% cue validity but not in the session with 50% cue validity. Our findings indicate that both top-down attentional mediating and feature priming are important mechanisms for FBA.

Dynamic modulation of the perceptual load on microsaccades during a selective spatial attention task.

Selective spatial attention enhances task performance at restricted regions within the visual field. The magnitude of this effect depends on the level of attentional load, which determines the efficiency of distractor rejection. Mechanisms of attentional load include perceptual selection and/or cognitive control involving working memory. Recent studies have provided evidence that microsaccades are influenced by spatial attention. Therefore, microsaccade activities may be exploited to help understand the dynamic control of selective attention under different load levels. However, previous reports in humans on the effect of attentional load on microsaccades are inconsistent, and it is not clear to what extent these results and the dynamic changes of microsaccade activities are similar in monkeys. We trained monkeys to perform a color detection task in which the perceptual load was manipulated by task difficulty with limited involvement of working memory. Our results indicate that during the task with high perceptual load, the rate and amplitude of microsaccades immediately before the target color change were significantly suppressed. We also found that the occurrence of microsaccades before the monkeys' detection response deteriorated their performance, especially in the hard task. We propose that the activity of microsaccades might be an efficacious indicator of the perceptual load.

The time course of attention modulation elicited by spatial uncertainty.

Uncertainty regarding the target location is an influential factor for spatial attention. Modulation in spatial uncertainty can lead to adjustments in attention scope and variations in attention effects. Hence, investigating spatial uncertainty modulation is important for understanding the underlying mechanism of spatial attention. However, the temporal dynamics of this modulation remains unclear. To evaluate the time course of spatial uncertainty modulation, we adopted a Posner-like attention orienting paradigm with central or peripheral cues. Different numbers of cues were used to indicate the potential locations of the target and thereby manipulate the spatial uncertainty level. The time interval between the onsets of the cue and the target (stimulus onset asynchrony, SOA) varied from 50 to 2000ms. We found that under central cueing, the effect of spatial uncertainty modulation could be detected from 200 to 2000ms after the presence of the cues. Under peripheral cueing, the effect of spatial uncertainty modulation was observed from 50 to 2000ms after cueing. Our results demonstrate that spatial uncertainty modulation produces robust and sustained effects on target detection speed. The time course of this modulation is influenced by the cueing method, which suggests that discrepant processing procedures are involved under different cueing conditions.

Using spatial uncertainty to manipulate the size of the attention focus.

Preferentially processing behaviorally relevant information is vital for primate survival. In visuospatial attention studies, manipulating the spatial extent of attention focus is an important question. Although many studies have claimed to successfully adjust attention field size by either varying the uncertainty about the target location (spatial uncertainty) or adjusting the size of the cue orienting the attention focus, no systematic studies have assessed and compared the effectiveness of these methods. We used a multiple cue paradigm with 2.5° and 7.5° rings centered around a target position to measure the cue size effect, while the spatial uncertainty levels were manipulated by changing the number of cueing positions. We found that spatial uncertainty had a significant impact on reaction time during target detection, while the cue size effect was less robust. We also carefully varied the spatial scope of potential target locations within a small or large region and found that this amount of variation in spatial uncertainty can also significantly influence target detection speed. Our results indicate that adjusting spatial uncertainty is more effective than varying cue size when manipulating attention field size.