Image Features Research Articles

Region-guided transformer for remote sensing image captioning

ABSTRACT Remote sensing image acquisition is an essential way to obtain information. However, research on remote sensing images mainly focuses on object detection or image classification. The emergence of remote sensing image captioning (RSIC) has enabled understanding and inference of remote sensing images, thus attracting considerable attention. There are still challenges in RSIC: the features used in RSIC are mostly based on grid features, and this form of features makes it difficult for the model to determine the main description targets. Hence, a more effective cross-modal matching method is needed for better text generation. Thus, we propose a region-guided transformer in response to the aforementioned issues. We extracted region features to enhance the ability of the model to focus on the main targets. To address the issue of information loss caused by region feature extraction, we proposed environment features to supplement background information. To improve the matching between text and image features, we propose a region-guided decoder that enhances the model's perception of different features through a weighted cross-attention mechanism. Meanwhile, we introduce region-guided information to guide the text-generation process. The effectiveness and superiority of our model have been demonstrated through extensive experiments.

Estimation of video sequence homography based on a first-order estimation method

As it is a pre-processing task, estimation of video-sequence-based homography requires low computational costs and fast evaluation. However, current algorithms for video sequence tasks are commonly based on image-pair homography and do not consider the inner properties of the video sequences. Therefore they take unnecessary computational resources. In this work, we propose a novel algorithm with a first-order estimation method to fill the gap between estimation of image-pairs and video sequence homography. By considering the continuous movement of the camera, the proposed algorithm adopts a first-order estimation to accelerate the estimation process while maintaining its robustness. Instead of extracting many image features from every frame, we demonstrate that estimating a homography matrix with pixel-based texture patterns is effective and sufficient for video sequences. Experiments show that homography estimation with simple one-dimensional texture vectors, as used in our algorithm, can surpass state-of-the-art feature-based algorithms and deep-learning-based methods. This first-order estimation method was more than 40 times faster and real-time estimation used only the CPU.

A high-efficiency local and global detector for diatom-based drowning diagnosis

Detection and classification of diatoms has been considered as the most effective method for the drowning diagnosis in forensic practice. However, challenges (such as limited samples, complex background interference, and detecting multiple objects) remain during detection and classification. To address these challenges, we propose a MDMS (multi-scale dynamic multi-head self-attention)-based deep learning network for the diatom-based drowning diagnosis. This framework uses TFFT (two-stage full fine-tuning training strategy) to solve the challenges of limited diatom samples and detecting multiple objects, and builds a multi-scale dynamic multi-head self-attention module to extract the local and global features of diatom images. In the meantime, we introduce an online hard example mining strategy to attenuate the complex background interference. The experimental results show that the proposed framework can effectively reduce the missing and false detection rates of diatom objects, with the mAP (mean Average Precision) reaching 92.434%, which is better than the result using the mainstream methods.

An intelligent bone age assessment model incorporating multilayer superimposed texture enhancement and the China-05 attention mechanism

In the process of intelligent bone age assessment for Chinese ethnicity, generalized convolutional network models are not well targeted in extracting specific features in medical skeletal images and lack specificity in training and predicting skeletal developmental features in different ethnicities. This study aims to propose a hybrid improved deep residual network model, ZH05-DL-ResNet50, focusing on intelligent bone age assessment for Chinese ethnicity. In the process of building the ZH05-DL-ResNet50 model. First, multiple overlapping texture enhancement layers are introduced through combinatorial optimization, which can better characterize the global features of hand bone radiographs while using less texture information, reducing the interference of redundant information and freeing up computational power; second, the China-05′s spatial focusing mechanism is designed so that the model can intelligently focus on the region of interest, efficiently locate and automatically learn key image information; Finally, the model can be used for intelligent bone age assessment of Chinese ethnicity by constructing a 50-layer residual depth network, the superposition enhancement layer and the focusing mechanism are fused to form the ZH05-DL-ResNet50 model, which mitigates the problem of gradient disappearance and explosion caused by the increase of network depth, and reduces the information loss and depletion of the multi-layer texture superposition features in the focus region of interest. The training was performed using the Chinese ethnographic dataset provided and created by Tsinghua Changgeng Hospital, where 10 % of the radiographs were used as the test set and the rest as the training and validation sets. The overall performance of the models was estimated by comparing the average accuracy and loss values of different models, and the overall performance between model training and model design was evaluated using the data distribution (Distribution) and histogram of bias weight distribution (Histogram). The results showed that the average accuracy of the bone age estimation model was 98.1 % and the average error on the test set was 0.312 years. Evaluation of the model visualization and accuracy comparison showed that the model performed well and was more appropriate and accurate than other bone age estimation models. Therefore, the first intelligent bone age assessment model for Chinese ethnicity, ZH05-DL-ResNet50, was created, which differs from the untargeted nature of other intelligent bone age assessment models, and is used to train and predict hand bone radiographs more appropriately and accurately for Chinese ethnicity.

Analysis of thyroid nodule ultrasound images by image feature extraction technique

Analysis of thyroid nodule ultrasound images by image feature extraction technique

BSD: A multi-task framework for pulmonary disease classification using deep learning

The diagnosis of pulmonary diseases using deep learning on chest X-ray images can be affected by the bone structures, the tissue in regions outside the lungs, and the characteristics of the images as burrs, blurring and complex pulmonary structures. To address these issues, a new pulmonary diseases diagnostic framework named BSD is proposed, the innovations of which are: Firstly, three steps of bone suppression, pulmonary parenchyma extraction and pulmonary diseases diagnosis are included. The first two steps can eliminate the influence of bone structures and other tissues. Therefore, better diagnostic results can be obtained based on the extracted boneless pulmonary parenchyma. Secondly, aiming at the characteristics of the chest X-ray image, a new segmentation network named IU-Net is proposed for the pulmonary extraction, in which the original convolution layers of U-Net are replaced by our new designed function modules. Finally, based on the characteristic of boneless pulmonary parenchyma, an enhanced functional module RCA which can better extract the image features is designed, therefore improved the disease diagnosis. In the experiments on the chest X-ray pneumonia datasets, the framework achieved satisfied results in the binary classification with an accuracy and Kappa of 98.73% and 96.80%, respectively. And in the multi-classification task on the COVID-19 radiology database, it achieved an accuracy and Kappa of 95.76% and 95.75%, respectively, which is better than the state-of-the-art. Therefore, BSD framework can better facilitate physicians to diagnose pulmonary disease and increase the diagnostic capabilities.

Lightweight image super-resolution with sliding Proxy Attention Network

Recently, image super-resolution (SR) models using window-based Transformers have demonstrated superior performance compared to SR models based on convolutional neural networks. Nevertheless, Transformer-based SR models often entail high computational demands. This is due to the adoption of shifted window self-attention following the window self-attention layer to model long-range relationships, resulting in additional computational overhead. Moreover, extracting local image features only with the self-attention mechanism is insufficient to reconstruct rich high-frequency image content. To overcome these challenges, we propose the Sliding Proxy Attention Network (SPAN), capable of recovering high-quality High-Resolution (HR) images from Low-Resolution (LR) inputs with substantially fewer model parameters and computational operations. The primary innovation of SPAN lies in the Sliding Proxy Transformer Block (SPTB), integrating the local detail sensitivity of convolution with the long-range dependency modeling of self-attention mechanism. Key components within SPTB include the Enhanced Local Feature Extraction Block (ELFEB) and the Sliding Proxy Attention Block (SPAB). ELFEB is designed to enhance the local receptive field with lightweight parameters for high-frequency details compensation. SPAB optimizes computational efficiency by implementing intra-window and cross-window attention in a single operation through leveraging window overlap. Experimental results demonstrate that SPAN can produce high-quality SR images while effectively managing computational complexity. The code is publicly available at: https://github.com/zononhzy/SPAN.

Learning From Human Attention for Attribute-Assisted Visual Recognition.

With prior knowledge of seen objects, humans have a remarkable ability to recognize novel objects using shared and distinct local attributes. This is significant for the challenging tasks of zero-shot learning (ZSL) and fine-grained visual classification (FGVC), where the discriminative attributes of objects have played an important role. Inspired by human visual attention, neural networks have widely exploited the attention mechanism to learn the locally discriminative attributes for challenging tasks. Though greatly promoted the development of these fields, existing works mainly focus on learning the region embeddings of different attribute features and neglect the importance of discriminative attribute localization. It is also unclear whether the learned attention truly matches the real human attention. To tackle this problem, this paper proposes to employ real human gaze data for visual recognition networks to learn from human attention. Specifically, we design a unified Attribute Attention Network (A 2 Net) that learns from human attention for both ZSL and FGVC tasks. The overall model consists of an attribute attention branch and a baseline classification network. On top of the image feature maps provided by the baseline classification network, the attribute attention branch employs attribute prototypes to produce attribute attention maps and attribute features. The attribute attention maps are converted to gaze-like attentions to be aligned with real human gaze attention. To guarantee the effectiveness of attribute feature learning, we further align the extracted attribute features with attribute-defined class embeddings. To facilitate learning from human gaze attention for the visual recognition problems, we design a bird classification game to collect real human gaze data using the CUB dataset via an eye-tracker device. Experiments on ZSL and FGVC tasks without/with real human gaze data validate the benefits and accuracy of our proposed model. This work supports the promising benefits of collecting human gaze datasets and automatic gaze estimation algorithms learning from human attention for high-level computer vision tasks.

A Novel Network for Low-Dose CT Denoising Based on Dual-Branch Structure and Multi-Scale Residual Attention.

Deep learning-based denoising of low-dose medical CT images has received great attention both from academic researchers and physicians in recent years, and has shown important application value in clinical practice. In this work, a novel two-branch and multi-scale residual attention-based network for low-dose CT image denoising is proposed. It adopts a two-branch framework structure, to extract and fuse image features at shallow and deep levels respectively, to recover image texture and structure information as much as possible. We propose the adaptive dynamic convolution block (ADCB) in the local information extraction layer. It can effectively extract the detailed information of low-dose CT denoising and enables the network to better capture the local details and texture features of the image, thereby improving the denoising effect and image quality. Multi-scale edge enhancement attention block (MEAB) is proposed in the global information extraction layer, to perform feature fusion through dilated convolution and a multi-dimensional attention mechanism. A multi-scale residual convolution block (MRCB) is proposed to integrate feature information and improve the robustness and generalization of the network. To demonstrate the effectiveness of our method, extensive comparison experiments are conducted and the performances evaluated on two publicly available datasets. Our model achieves 29.3004 PSNR, 0.8659 SSIM, and 14.0284 RMSE on the AAPM-Mayo dataset. It is evaluated by adding four different noise levels σ = 15, 30, 45, and 60 on the Qin_LUNG_CT dataset and achieves the best results. Ablation studies show that the proposed ADCB, MEAB, and MRCB modules improve the denoising performances significantly. The source code is available at https://github.com/Ye111-cmd/LDMANet .

Prediction of H3K27M alteration in midline gliomas of brain using radiomics- A multi-institute study

Abstract Background Non-invasive prediction of H3K27M-altered Diffuse midline gliomas is important because of the involvement of deep locations and proximity to eloquent structures. We aim to predict H3K27M alteration in midline gliomas using radiomics features of T2W images. Methods Radiomics features extracted from 124 subjects (69 H3K27M-altered/55 H3K27M-wildtype). T2W-images were resampled to 1x1x1mm voxel-size, pre-processed, and normalized for artefact correction, intensity variations. Feature-set was normalized, subjected to reduction by variance thresholding, correlation coefficient thresholding, and sequential feature selector. Adaptive synthesis oversampling technique was used to over-sample the training data. Random forest classifier (RFC), Decision tree classifier (DTC) and K-nearest neighbors classifier (KNN) were trained over the training dataset and the performance was assessed over the internal test dataset and external test data set (52 subjects: 33 H3K27M-altered/19-H3K27M-wildtype). Results DTC achieved validation score of 77.33% (5-fold cross-validation) and accuracy of 80.64%, 75% on internal and external test dataset. RFC achieved validation score of 80.7% (5-fold cross-validation) and accuracy of 80.6%, 73% on internal and external test dataset. DTC achieved validation score of 78.67% (5-fold cross-validation) and accuracy of 80.64%, 61.53% on internal and external test dataset. Accuracy score of DTC, RFC, and KNN on internal test dataset was approximately 80% while on the external test dataset, DTC achieved 75% accuracy, RFC achieved 73% accuracy and KNN achieved 65.1% accuracy. Conclusion H3K27M alteration is a potential immunotherapeutic marker and is associated with poor prognosis and radiomics features extracted from conventional T2W-images can help in identifying H3K27M-altered cases non-invasively with high precision.

Deep learning Radiomics Based on Two-Dimensional Ultrasound for Predicting the Efficacy of Neoadjuvant Chemotherapy in Breast Cancer.

We investigate the predictive value of a comprehensive model based on preoperative ultrasound radiomics, deep learning, and clinical features for pathological complete response (pCR) after neoadjuvant chemotherapy (NAC) for the breast cancer. We enrolled 155 patients with pathologically confirmed breast cancer who underwent NAC. The patients were randomly divided into the training set and the validation set in the ratio of 7:3. The deep learning and radiomics features of pre-treatment ultrasound images were extracted, and the random forest recursive elimination algorithm and the least absolute shrinkage and selection operator were used for feature screening and DL-Score and Rad-Score construction. According to multifactorial logistic regression, independent clinical predictors, DL-Score, and Rad-Score were selected to construct the comprehensive prediction model DLRC. The performance of the model was evaluated in terms of its predictive effect, and clinical practicability. Compared to the clinical, radiomics (Rad-Score), and deep learning (DL-Score) models, the DLRC accurately predicted the pCR status, with an area under the curve (AUC) of 0.937 (95%CI: 0.895-0.970) in the training set and 0.914 (95%CI: 0.838-0.973) in the validation set. Moreover, decision curve analysis confirmed that the DLRC had the highest clinical value among all models. The comprehensive model DLRC based on ultrasound radiomics, deep learning, and clinical features can effectively and accurately predict the pCR status of breast cancer after NAC, which is conducive to assisting clinical personalized diagnosis and treatment plan.

The analysis of art design under improved convolutional neural network based on the Internet of Things technology

This work aims to explore the application of an improved convolutional neural network (CNN) combined with Internet of Things (IoT) technology in art design education and teaching. The development of IoT technology has created new opportunities for art design education, while deep learning and improved CNN models can provide more accurate and effective tools for image processing and analysis. In order to enhance the effectiveness of art design teaching and students’ creative expression, this work proposes an improved CNN model. In model construction, it increases the number of convolutional layers and neurons, and incorporates the batch normalization layer and dropout layer to enhance feature extraction capabilities and reduce overfitting. Besides, this work creates an experimental environment using IoT technology, capturing art image samples and environmental data using cameras, sensors, and other devices. In the model application phase, image samples undergo preprocessing and are input into the CNN for feature extraction. Sensor data are concatenated with image feature vectors and input into the fully connected layers to comprehensively understand the artwork. Finally, this work trains the model using techniques such as cross-entropy loss functions and L2 regularization and adjusts hyperparameters to optimize model performance. The results indicate that the improved CNN model can effectively acquire art sample data and student creative expression data, providing accurate and timely feedback and guidance for art design education and teaching, with promising applications. This work offers new insights and methods for the development of art design education.

Data Augmentation in Histopathological Classification: An Analysis Exploring GANs with XAI and Vision Transformers

Generative adversarial networks (GANs) create images by pitting a generator (G) against a discriminator (D) network, aiming to find a balance between the networks. However, achieving this balance is difficult because G is trained based on just one value representing D’s prediction, and only D can access image features. We introduce a novel approach for training GANs using explainable artificial intelligence (XAI) to enhance the quality and diversity of generated images in histopathological datasets. We leverage XAI to extract feature information from D and incorporate it into G via the loss function, a unique strategy not previously explored in this context. We demonstrate that this approach enriches the training with relevant information and promotes improved quality and more variability in the artificial images, decreasing the FID by up to 32.7% compared to traditional methods. In the data augmentation task, these images improve the classification accuracy of Transformer models by up to 3.81% compared to models without data augmentation and up to 3.01% compared to traditional GAN data augmentation. The Saliency method provides G with the most informative feature information. Overall, our work highlights the potential of XAI for enhancing GAN training and suggests avenues for further exploration in this field.

Hierarchical Progressive Image Forgery Detection and Localization Method Based on UNet

The rapid development of generative technologies has made the production of forged products easier, and AI-generated forged images are increasingly difficult to accurately detect, posing serious privacy risks and cognitive obstacles to individuals and society. Therefore, constructing an effective method that can accurately detect and locate forged regions has become an important task. This paper proposes a hierarchical and progressive forged image detection and localization method called HPUNet. This method assigns more reasonable hierarchical multi-level labels to the dataset as supervisory information at different levels, following cognitive laws. Secondly, multiple types of features are extracted from AI-generated images for detection and localization, and the detection and localization results are combined to enhance the task-relevant features. Subsequently, HPUNet expands the obtained image features into four different resolutions and performs detection and localization at different levels in a coarse-to-fine cognitive order. To address the limited feature field of view caused by inconsistent forgery sizes, we employ three sets of densely cross-connected hierarchical networks for sufficient interaction between feature images at different resolutions. Finally, a UNet network with a soft-threshold-constrained feature enhancement module is used to achieve detection and localization at different scales, and the reliance on a progressive mechanism establishes relationships between different branches. We use ACC and F1 as evaluation metrics, and extensive experiments on our method and the baseline methods demonstrate the effectiveness of our approach.

Dual-stage semantic segmentation of endoscopic surgical instruments.

Endoscopic instrument segmentation is essential for ensuring the safety of robotic-assisted spinal endoscopic surgeries. However, due to the narrow operative region, intricate surrounding tissues, and limited visibility, achieving instrument segmentation within the endoscopic view remainschallenging. This work aims to devise a method to segment surgical instruments in endoscopic video. By designing an endoscopic image classification model, features of frames before and after the video are extracted to achieve continuous and precise segmentation of instruments in endoscopicvideos. Deep learning techniques serve as the algorithmic core for constructing the convolutional neural network proposed in this study. The method comprises dual stages: image classification and instrument segmentation. MobileViT is employed for image classification, enabling the extraction of key features of different instruments and generating classification results. DeepLabv3+ is utilized for instrument segmentation. By training on distinct instruments separately, corresponding model parameters are obtained. Lastly, a flag caching mechanism along with a blur detection module is designed to effectively utilize the image features in consecutive frames. By incorporating specific parameters into the segmentation model, better segmentation of surgical instruments can be achieved in endoscopicvideos. The classification and segmentation models are evaluated on an endoscopic image dataset. In the dataset used for instrument segmentation, the training set consists of 7456 images, the validation set consists of 829 images, and the test set consists of 921 images. In the dataset used for image classification, the training set consists of 2400 images and the validation set consists of 600 images. The image classification model achieves an accuracy of 70% on the validation set. For the segmentation model, experiments are conducted on two common surgical instruments, and the mean Intersection over Union (mIoU) exceeds 98%. Furthermore, the proposed video segmentation method is tested using videos collected during surgeries, validating the effectiveness of the flag caching mechanism and blur detection module. Experimental results on the dataset demonstrate that the dual-stage video processing method excels in performing instrument segmentation tasks under endoscopic conditions. This advancement is significant for enhancing the intelligence level of robotic-assisted spinal endoscopic surgeries.

Ultrasound based radiomics model for assessment of placental function in pregnancies with preeclampsia

The goal of our research is to elucidate and better assess placental function in rats with preeclampsia through an innovative application of ultrasound-based radiomics. Using a rat model induced with L-NAME, we carefully investigated placental dysfunction via microstructural analysis and immunoprotein level assessment. Employing the Boruta feature selection method on ultrasound images facilitated the identification of crucial features, consequently enabling the development of a robust model for classifying placental dysfunction. Our study included 12 pregnant rats, and thorough placental evaluations were conducted on 160 fetal rats. Distinct alterations in placental microstructure and angiogenic factor expression were evident in rats with preeclampsia. Leveraging high-throughput mining of quantitative image features, we extracted 558 radiomic features, which were subsequently used to construct an impressive evaluation model with an area under the receiver operating curve (AUC) of 0.95. This model also exhibited a remarkable sensitivity, specificity, accuracy, positive predictive value, and negative predictive value of 88.7%, 91.5%, 90.2%, 90.4%, and 90.0%, respectively. Our findings highlight the ability of ultrasound-based radiomics to detect abnormal placental features, demonstrating its potential for evaluating both normative and impaired placental function with high precision and reliability.

Detection of bone cancer based on a four-phase framework generative deep belief neural network in deep learning

The medical image processing plays an important role in analyzing and detecting tumors and detecting cancer cells in their early stages. Microscopic images were used as a deep learning approach to recognize bone features. These images were acquired using microscopy, a time-consuming and labor-intensive process that required repeating. Cancer cells cannot be identified by conventional techniques because of the noise in the images. To address these challenges, this paper introduces the Gated Convolutional Neural Network (GCNN) techniques used to identify multiclass bone cancer, including non-tumor, non-viable, and viable tumors. As a first stage, the most basic part of image Preprocessing is to deposing without interrupting the diagnostics information during the removal of noise. The second stage is edge detection, used for image brightness discontinuity detection based on Scaled Region Edge Detector (SRED). It is used for image segmentation and data extraction within regions based on the Screen Cluster Area Segmentation (SCAS) to segment the Region of Interest (RoI) based on Relative Scalar Color Histogram (RSCH). The fourth step is Feature extraction is to find out the features and match the image feature from the Bone Cancer Detection object based on the maximum threshold weights using GCNN with Maximum Standard External Regions (MSER) used for features extracting applied to improve feature quality analysis and Feature support rate. This results in higher classification accuracy, Precision, recall under F-measure, and lower error rates. This enables a more achieved classification than other existing methods.

The relationship between lung CT features and serum cryptococcal antigen titers in localized pulmonary cryptococcosis patients

BackgroundTo explore the associations of computed tomography (CT) image features with the serum cryptococcal antigen (CrAg) titers measured by the lateral flow assay (LFA) in localized pulmonary cryptococcosis patients.MethodsA retrospective analysis of patients with pathologically confirmed pulmonary cryptococcosis admitted to the First Affiliated Hospital of Xiamen University from January 2016 to December 2022 was performed. Clinical data, CT results, serum CrAg-LFA test results, and follow-up data were collected and analyzed.ResultsA total of 107 patients with localized pulmonary cryptococcosis were included, of which 31 had a single lesion in chest CT and the other 76 had multiple lesions. The positivity rate was (94.74% vs 64.52%) and titers of serum CrAg-LFA (1.77 ± 0.87 vs 0.91 ± 0.98) in the multiple lesion group were higher than those in the single lesion group, respectively. Multivariate linear regression analysis showed that the serum CrAg titers were positively associated with the number of lesions (β, 0.08; 95% CI, 0.05 to 0.12) and the lesion size (β, 0.40; 95% CI, 0.31 to 0.50) after adjusting other covariates. The serum CrAg-LFA titers of 60 pulmonary cryptococcosis patients showed a decreasing trend with the reduction in pulmonary lesion size after effective therapy.ConclusionIn pulmonary cryptococcosis patients, the number and size of lung lesions are positively correlated with the titers of the serum CrAg-LFA test. The CrAg-LFA test could be a useful tool for the diagnosis, severity assessment, and therapeutic monitoring of localized pulmonary cryptococcosis patients.

RvXmBlendNet: A Multi-architecture Hybrid Model for Improved Skin Cancer Detection

AbstractSkin cancer, one of the most dangerous cancers, poses a significant global threat. While early detection can substantially improve survival rates, traditional dermatologists often face challenges in accurate diagnosis, leading to delays in treatment and avoidable fatalities. Deep learning models like CNN and transfer learning have enhanced diagnosis from dermoscopic images, providing precise and timely detection. However, despite the progress made with hybrid models, many existing approaches still face challenges, such as limited generalization across diverse datasets, vulnerability to overfitting, and difficulty in capturing complex patterns. As a result, there is a growing need for more robust and effective hybrid models that integrate multiple architectures and advanced mechanisms to address these challenges. Therefore, this study aims to introduce a novel multi-architecture hybrid deep learning model called "RvXmBlendNet," which combines the strengths of four individual models: ResNet50 (R), VGG19 (v), Xception (X), and MobileNet (m), followed by "BlendNet" to signify their fusion into a unified architecture. The integration of these models is achieved through a synergistic combination of architectures, incorporating self-attention mechanisms using attention layers and adaptive content blocks. This study used the HAM10000 dataset to refine dermoscopic image preprocessing and enhance deep learning model accuracy. Techniques like OpenCV-based hair removal, min–max scaling, and adaptive histogram equalization were employed to improve image quality and feature extraction. A comparative study between the proposed hybrid "RvXmBlendNet" and individual models (CNN, ResNet50, VGG19, Xception, and MobileNet) demonstrated that "RvXmBlendNet" achieved the highest accuracy of 98.26%, surpassing other models. These results suggest that the system can facilitate earlier interventions, improve patient outcomes, and potentially lower healthcare costs by reducing the need for invasive diagnostic procedures.

Optimization of whole slide imaging scan settings for computer vision using human lung cancer tissue.

Digital pathology has become increasingly popular for research and clinical applications. Using high-quality microscopes to produce Whole Slide Images of tumor tissue enables the discovery of insights into biological aspects invisible to the human eye. These are acquired through downstream analyses using spatial statistics and artificial intelligence. Determination of the quality and consistency of these images is needed to ensure accurate outcomes when identifying clinical and subclinical image features. Additionally, the time-intensive process of generating high-volume images results in a trade-off that needs to be carefully balanced. This study aims to determine optimal instrument settings to generate representative images of pathological tissue using digital microscopy. Using various settings, an H&E stained sample was scanned using the ZEISS Axio Scan.Z1. Next, nucleus segmentation was performed on resulting images using StarDist. Subsequently, detections were compared between scans using a matching algorithm. Finally, nucleus-level information was compared between scans. Results indicated that while general matching percentages were high, similarity between information from replicates was relatively low. Additionally, settings resulting in longer scanning times and increased data volume did not increase similarity between replicates. In conclusion, the scan setting ultimately deemed optimal combined consistent and qualitative performance with low throughput time.