Cytological Images Research Articles

Automated Generation of Lung Cytological Images from Image Findings Using Text-to-Image Technology

Cytology, a type of pathological examination, involves sampling cells from the human body and observing the morphology of the nucleus, cytoplasm, and cell arrangement. In developing classification AI technologies to support cytology, it is essential to collect and utilize a diverse range of images without bias. However, this is often challenging in practice because of the epidemiologic bias of cancer types and cellular characteristics. The main aim of this study was to develop a method to generate cytological diagnostic images from image findings using text-to-image technology in order to generate diverse images. In the proposed method, we collected Papanicolaou-stained specimens derived from the lung cells of 135 lung cancer patients, from which we extracted 472 patch images. Descriptions of the corresponding findings for these patch images were compiled to create a data set. This dataset was then utilized to finetune the Stable Diffusion (SD) v1 and v2 models. The cell images generated by this method closely resemble real images, and both cytotechnologists and cytopathologists provided positive subjective evaluations. Furthermore, SDv2 demonstrated shapes and contours of nuclei and cytoplasm that were more similar to real images compared to SDv1, showing superior performance in quantitative evaluation metrics. When the generated images were utilized in the classification tasks for cytological images, there was an improvement in classification performance. These results indicate that the proposed method may be effective for generating high-quality cytological images, which enables the image classification model to learn diverse features, thereby improving classification performance.

Novelty Classification Model Use in Reinforcement Learning for Cervical Cancer.

Cervical cancer significantly impacts global health, where early detection is piv- otal for improving patient outcomes. This study aims to enhance the accuracy of cervical cancer diagnosis by addressing class imbalance through a novel hybrid deep learning model. The proposed model, RL-CancerNet, integrates EfficientNetV2 and Vision Transformers (ViTs) within a Reinforcement Learning (RL) framework. EfficientNetV2 extracts local features from cervical cytology images to capture fine-grained details, while ViTs analyze these features to recognize global dependencies across image patches. To address class imbalance, an RL agent dynamically adjusts the focus towards minority classes, thus reducing the common bias towards majority classes in medical image classification. Additionally, a Supporter Module incorporating Conv3D and BiLSTM layers with an attention mechanism enhances contextual learning. RL-CancerNet was evaluated on the benchmark cervical cytology datasets Herlev and SipaKMeD, achieving an exceptional accuracy of 99.7%. This performance surpasses several state-of-the-art models, demonstrating the model's effectiveness in identifying subtle diagnostic features in complex backgrounds. The integration of CNNs, ViTs, and RL into RL-CancerNet significantly improves the diagnostic accuracy of cervical cancer screenings. This model not only advances the field of automated medical screening but also provides a scalable framework adaptable to other medical imaging tasks, potentially enhancing diagnostic processes across various medical domains.

An Artificial Intelligence-assisted Diagnostic System Improves Upper Urine Tract Cytology Diagnosis.

To evaluate efficacy of the AIxURO system, a deep learning-based artificial intelligence (AI) tool, in enhancing the accuracy and reliability of urine cytology for diagnosing upper urinary tract cancers. One hundred and eighty-five cytology samples of upper urine tract were collected and categorized according to The Paris System for Reporting Urinary Cytology (TPS), yielding 168 negative for High-Grade Urothelial Carcinoma (NHGUC), 14 atypical urothelial cells (AUC), 2 suspicious for high-grade urothelial carcinoma (SHGUC), and 1 high-grade urothelial carcinoma (HGUC). The AIxURO system, trained on annotated cytology images, was employed to analyze these samples. Independent assessments by a cytotechnologist and a cytopathologist were conducted to validate the initial AIxURO assessment. AIxURO identified discrepancies in 37 of the 185 cases, resulting in a 20% discrepancy rate. The cytotechnologist achieved an accuracy of 85% for NHGUC and 21.4% for AUC, whereas the cytopathologist attained accuracies of 95% for NHGUC and 85.7% for AUC. The cytotechnologist exhibited overcall rates of roughly 15% and undercall rates of greater than 50%, while the cytopathologist showed profoundly lower miscall rates from both undercall and overcall. AIxURO significantly enhanced diagnostic accuracy and consistency, particularly in complex cases involving atypical cells. AIxURO can improve the accuracy and reliability of cytology diagnosis for upper urine tract urothelial carcinomas by providing precise detection on atypical urothelial cells and reducing subjectivity in assessments. The integration of AIxURO into clinical practice can significantly ameliorate diagnostic outcomes, highlighting the synergistic potential of AI technology and human expertise in cytology.

Enhancing pap smear image classification: integrating transfer learning and attention mechanisms for improved detection of cervical abnormalities

Cervical cancer remains a major global health challenge, accounting for significant morbidity and mortality among women. Early detection through screening, such as Pap smear tests, is crucial for effective treatment and improved patient outcomes. However, traditional manual analysis of Pap smear images is labor-intensive, subject to human error, and requires extensive expertise. To address these challenges, automated approaches using deep learning techniques have been increasingly explored, offering the potential for enhanced diagnostic accuracy and efficiency. This research focuses on improving cervical cancer detection from Pap smear images using advanced deep-learning techniques. Specifically, we aim to enhance classification performance by leveraging Transfer Learning (TL) combined with an attention mechanism, supplemented by effective preprocessing techniques. Our preprocessing pipeline includes image normalization, resizing, and the application of Histogram of Oriented Gradients (HOG), all of which contribute to better feature extraction and improved model performance. The dataset used in this study is the Mendeley Liquid-Based Cytology (LBC) dataset, which provides a comprehensive collection of cervical cytology images annotated by expert cytopathologists. Initial experiments with the ResNet model on raw data yielded an accuracy of 63.95%. However, by applying our preprocessing techniques and integrating an attention mechanism, the accuracy of the ResNet model increased dramatically to 96.74%. Further, the Xception model, known for its superior feature extraction capabilities, achieved the best performance with an accuracy of 98.95%, along with high precision (0.97), recall (0.99), and F1-Score (0.98) on preprocessed data with an attention mechanism. These results underscore the effectiveness of combining preprocessing techniques, TL, and attention mechanisms to significantly enhance the performance of automated cervical cancer detection systems. Our findings demonstrate the potential of these advanced techniques to provide reliable, accurate, and efficient diagnostic tools, which could greatly benefit clinical practice and improve patient outcomes in cervical cancer screening.

Capture of live circulating tumor cells via unique surface charges from cancer patients by a novel nanotechnology

AbstractCirculating tumor cells (CTCs) serve as a pivotal foundation for both fundamental oncological research and the precise evaluation of therapeutic interventions. However, the isolation of CTCs from clinical blood samples presents a multitude of sophisticated challenges, predominantly associated with the specificity of biomarkers and the sensitivity of detection techniques. In our previous study, we proposed a novel detection concept for CTCs based on a signature biophysical feature on the surface of cancer cells: a negative charge regulated by glycolytic processes. In this study, we have conducted experiments to ascertain the efficacy of this proposed method in capturing CTCs from clinical blood samples of individuals afflicted with solid tumors and leukemia. Our findings indicate that the method is capable of isolating tens of thousands of viable cancer cells from various metastatic solid cancers and leukemia using a mere 1 mL of blood. These cells were enumerated using cytological imaging that identified morphological characteristics indicative of malignancy. The outcomes of our study suggest that the negatively charged surface of cancer cells is a ubiquitous trait across both cultured cancer cell lines and fresh blood samples derived from cancer patients. Moreover, the capture technology employed in this study demonstrated superior performance in comparison to antecedent methodologies, enhancing the detection and documentation of CTCs for subsequent verification and analysis. This advancement holds significant promise for the improvement of diagnostic accuracy and the monitoring of therapeutic responses in oncology.

A systematic review on deep learning based methods for cervical cell image analysis

Cervical cytology image analysis is indispensable for the detection of abnormal cervical cells. Traditionally, manual screening is time-consuming and labor-intensive. Therefore, a lot of deep learning (DL)-based automatic detection methods have been employed in this field to provide timely, accurate and objective results. In this study, we systematically review the current developments in cervical cell image analysis with DL methods. Specifically, we first present the most popular DL models that are widely applied in cervical cell analysis. Second, we describe the methodology for conducting this review. Third, we provide all publicly available datasets related to cervical cell images to the best of our knowledge. Then, we introduce relevant evaluation metrics and loss functions. Next, we summarize and assort the applications for cervical cell classification and segmentation. Afterwards, we discuss about current challenges and future research directions in this field. Finally, we draw the conclusion of this review.According to the analysis, we conclude that the studies based on DL models have maintained an increasing trend in recent years, which indicates the potential of DL in cervical cell image analysis. In cervical cell image classification, CNN is the most commonly used DL model. Among CNN models, we can find that VGGNet and ResNet are the most popular network architectures for the classification of cervical cells. Transformer is the second commonly used DL model. Moreover, Herlev and SIPaKMeD are the most popular public datasets used for cervical cell classification. In cervical cell segmentation, U-Net and FCN are the two most popular DL architectures. In addition, ISBI2014 and Herlev datasets are the most frequently used among the existing publicly available segmentation datasets. However, there are some issues in this field, such as poor cervical cell classification performance as a result of similar pathological properties between different cell categories. Therefore, it is necessary to develop more effective methods with DL models to improve these issues in the future research.

Artificial Intelligence Recognition Model Using Liquid-Based Cytology Images to Discriminate Malignancy and Histological Types of Non-Small-Cell Lung Cancer

Introduction: Artificial intelligence image recognition has applications in clinical practice. The purpose of this study was to develop an automated image classification model for lung cancer cytology using a deep learning convolutional neural network (DCNN). Methods: Liquid-based cytology samples from 8 normal parenchymal (N), 22 adenocarcinoma (ADC), and 15 squamous cell carcinoma (SQCC) surgical specimens were prepared, and 45 Papanicolaou-stained slides were scanned using whole-slide imaging. The final dataset of 9,141 patches consisted of 2,737 N, 4,756 ADC, and 1,648 SQCC samples. Densenet-121 was used as the DCNN to classify N versus malignant (ADC+SQCC) and ADC versus SQCC images. AdamW optimizer and 5-fold cross-validation were used in the training. Results: For malignancy prediction, the sensitivity, specificity, and accuracy were 0.97, 0.85, and 0.94, respectively, in the patch-level classification, and 0.92, 0.88, and 0.91, respectively, in the case-level classification. For SQCC prediction, the sensitivity, specificity, and accuracy were 0.86, 0.91, and 0.90, respectively, in the patch-level classification and 0.73, 0.82, and 0.78, respectively, in the case-level classification. Conclusion: The DCNN model performed excellently in predicting malignancy and histological types of lung cancer. This model may be useful for predicting cytopathological diagnosis in clinical situations by reinforcing training.

Trans-YOLOv5: a YOLOv5-based prior transformer network model for automated detection of abnormal cells or clumps in cervical cytology images

The development of various models for automated images screening has significantly enhanced the efficiency and accuracy of cervical cytology image analysis. Single-stage target detection models are capable of fast detection of abnormalities in cervical cytology, but an accurate diagnosis of abnormal cells not only relies on identification of a single cell itself, but also involves the comparison with the surrounding cells. Herein we present the Trans-YOLOv5 model, an automated abnormal cell detection model based on the YOLOv5 model incorporating the global-local attention mechanism to allow efficient multiclassification detection of abnormal cells in cervical cytology images. The experimental results using a large cervical cytology image dataset demonstrated the efficiency and accuracy of this model in comparison with the state-of-the-art methods, with a mAP reaching 65.9% and an AR reaching 53.3%, showing a great potential of this model in automated cervical cancer screening based on cervical cytology images.

Fractal Dimension, Circularity, and Solidity of Cell Clusters in Liquid-Based Endometrial Cytology Are Potentially Useful for Endometrial Cancer Detection and Prognosis Prediction.

Endometrial cancer (EC) in women is increasing globally, necessitating improved diagnostic methods and prognosis prediction. While endometrial histology is the conventional approach, liquid-based endometrial cytology may benefit from novel analytical techniques for cell clusters. A clinical study was conducted at the University of Fukui Hospital from 2012 to 2018, involving 210 patients with endometrial cytology. The liquid-based cytology images were analyzed using cell cluster analysis with Image J software. Logistic regression, ROC analysis, and survival analysis were employed to assess the diagnostic accuracy and prognosis between cell cluster analysis and EC/atypical endometrial hyperplasia (AEH). Circularity and fractal dimension demonstrated significant associations with EC and AEH, regardless of age and cytology results. The ROC analysis revealed improved diagnostic accuracy when combining fractal dimension with cytology, particularly in menopausal age groups. Lower circularity and solidity were independently associated with poor overall survival, while higher fractal dimension values correlated with poorer overall survival in Grades 2 and 3 endometrial cancers. The combination of circularity and fractal dimension with cytology improved diagnostic accuracy for both EC and AEH. Moreover, circularity, solidity, and fractal dimension may serve as prognostic indicators for endometrial cancer, contributing to the development of more refined screening and diagnostic strategies.

Detection of Cervical Lesion Cell/Clumps Based on Adaptive Feature Extraction.

Automated detection of cervical lesion cell/clumps in cervical cytological images is essential for computer-aided diagnosis. In this task, the shape and size of the lesion cell/clumps appeared to vary considerably, reducing the detection performance of cervical lesion cell/clumps. To address the issue, we propose an adaptive feature extraction network for cervical lesion cell/clumps detection, called AFE-Net. Specifically, we propose the adaptive module to acquire the features of cervical lesion cell/clumps, while introducing the global bias mechanism to acquire the global average information, aiming at combining the adaptive features with the global information to improve the representation of the target features in the model, and thus enhance the detection performance of the model. Furthermore, we analyze the results of the popular bounding box loss on the model and propose the new bounding box loss tendency-IoU (TIoU). Finally, the network achieves the mean Average Precision (mAP) of 64.8% on the CDetector dataset, with 30.7 million parameters. Compared with YOLOv7 of 62.6% and 34.8M, the model improved mAP by 2.2% and reduced the number of parameters by 11.8%.

Background removal for debiasing computer-aided cytological diagnosis.

To address the background-bias problem in computer-aided cytology caused by microscopic slide deterioration, this article proposes a deep learning approach for cell segmentation and background removal without requiring cell annotation. A U-Net-based model was trained to separate cells from the background in an unsupervised manner by leveraging the redundancy of the background and the sparsity of cells in liquid-based cytology (LBC) images. The experimental results demonstrate that the U-Net-based model trained on a small set of cytology images can exclude background features and accurately segment cells. This capability is beneficial for debiasing in the detection and classification of the cells of interest in oral LBC. Slide deterioration can significantly affect deep learning-based cell classification. Our proposed method effectively removes background features at no cost of cell annotation, thereby enabling accurate cytological diagnosis through the deep learning of microscopic slide images.

TshFNA-Examiner: A Nuclei Segmentation and Cancer Assessment Framework for Thyroid Cytology Image

TshFNA-Examiner: A Nuclei Segmentation and Cancer Assessment Framework for Thyroid Cytology Image

PATH-05. MACHINE LEARNING-BASED CYTOLOGICAL ANALYSIS OF CEREBROSPINAL FLUID IN MEDULLOBLASTOMA

Abstract BACKGROUND Metastatic dissemination occurring via the cerebrospinal fluid contributes to the poor prognosis in many medulloblastoma patients. It has high prognostic relevance, and its accurate detection is critical for adequate therapy stratification. However, cytological examination is a difficult, time-consuming task and frequently unreliable. We, therefore, propose a machine-learning pipeline to solve this diagnostic challenge. METHODS A dataset of 303 digitized images of cerebrospinal fluid preparations from 81 medulloblastoma patients was assembled. Based on these data, over 50000 digitized objects, including more than 5000 patches with tumor cells, were classified by experts into 13 clinically relevant diagnostic categories and used for training. The classification was performed using convolutional neural networks, trained with nested-cross validation and different transfer learning strategies. RESULTS The classification into the 13 diagnostic categories was feasible, with an overall accuracy of 75% on the test set and a tumor-specific F1 score of 89%. Most misclassifications occurred between morphologically similar cell types, mainly lymphocytes and activated lymphocytes, monocytes and activated monocytes, as well as tumor cells and atypical cells with borderline cytomorphology. Grouping these cytologically and/or biologically closely related groups increased the overall accuracy to 91%. Pretraining on published cytological datasets of cerebrospinal fluid and bone marrow further increased classification accuracy. CONCLUSIONS Deep learning can reliably detect tumor cells in digitized cytological images from cerebrospinal fluid preparations in medulloblastoma. Implementing explanation methods, an easy-to-use user interface and validation on additional cohorts will further strengthen the robustness of the presented approach.

Machine learning for determining the stage of the estrous cycle in bitches

Reproductive biotechnologies, such as artificial insemination, are important tools in the reproduction of female dogs. Accurate determination of the specific stage of the estrous cycle is crucial for the successful application of these technologies.Vaginal cytology serves as a cost-effective and rapid diagnostic solution. However, itrelies on the analyzer’s expertise, making itsubject to human errors. Additionally, it may involve a prolonged duration between sample collection and result analysis.To minimize these limitations and streamline the diagnostic process,this studydeveloped software to automate the identification of the main phases of the estrous cycle that are important for artificial insemination. Eighteen vaginal cytology images were used, withsix images representing each of the phases studied (proestrus, estrus, and diestrus).Imageswere analyzed using the open source CellProfiller software, with subsequentclassification of the images using theTanagra software. Sensitivity and specificity valueswere determined for the proestrus, estrus, and diestrus phases, yielding results of 0.99, 0.86, 0.95, and 1, 0.95, 0.82, respectively.These findingsdemonstrate the model’scapacityfor correctly identifyingdifferent phases of the estrous cycle. The proposed model proved effective for the study’sobjective, and the authors suggest that it may be applicable to other economically important species.

Toward Interpretable Cell Image Representation and Abnormality Scoring for Cervical Cancer Screening Using Pap Smears.

Screening is critical for prevention and early detection of cervical cancer but it is time-consuming and laborious. Supervised deep convolutional neural networks have been developed to automate pap smear screening and the results are promising. However, the interest in using only normal samples to train deep neural networks has increased owing to the class imbalance problems and high-labeling costs that are both prevalent in healthcare. In this study, we introduce a method to learn explainable deep cervical cell representations for pap smear cytology images based on one-class classification using variational autoencoders. Findings demonstrate that a score can be calculated for cell abnormality without training models with abnormal samples, and we localize abnormality to interpret our results with a novel metric based on absolute difference in cross-entropy in agglomerative clustering. The best model that discriminates squamous cell carcinoma (SCC) from normals gives 0.908±0.003 area under operating characteristic curve (AUC) and one that discriminates high-grade epithelial lesion (HSIL) 0.920±0.002 AUC. Compared to other clustering methods, our method enhances the V-measure and yields higher homogeneity scores, which more effectively isolate different abnormality regions, aiding in the interpretation of our results. Evaluation using an external dataset shows that our model can discriminate abnormality without the need for additional training of deep models.

SCAC: A Semi-Supervised Learning Approach for Cervical Abnormal Cell Detection.

Cervical abnormal cell detection plays a crucial role in the early screening of cervical cancer. In recent years, some deep learning-based methods have been proposed. However, these methods rely heavily on large amounts of annotated images, which are time-consuming and labor-intensive to acquire, thus limiting the detection performance. In this paper, we present a novel Semi-supervised Cervical Abnormal Cell detector (SCAC), which effectively utilizes the abundant unlabeled data. We utilize Transformer as the backbone of SCAC to capture long-range dependencies to mimic the diagnostic process of pathologists. In addition, in SCAC, we design a Unified Strong and Weak Augment strategy (USWA) that unifies two data augmentation pipelines, implementing consistent regularization in semi-supervised learning and enhancing the diversity of the training data. We also develop a Global Attention Feature Pyramid Network (GAFPN), which utilizes the attention mechanism to better extract multi-scale features from cervical cytology images. Notably, we have created an unlabeled cervical cytology image dataset, which can be leveraged by semi-supervised learning to enhance detection accuracy. To the best of our knowledge, this is the first publicly available large unlabeled cervical cytology image dataset. By combining this dataset with two publicly available annotated datasets, we demonstrate that SCAC outperforms other existing methods, achieving state-of-the-art performance. Additionally, comprehensive ablation studies are conducted to validate the effectiveness of USWA and GAFPN. These promising results highlight the capability of SCAC to achieve high diagnostic accuracy and extensive clinical applications.

Clinical experience of using a high-intensity erbium laser for the treatment of chronic wounds

Chronic wounds are a common surgical pathology. Some types of laser radiation allow for eff ective debridement of wounds and stimulation of healing processes. High-intensity erbium laser can comprehensively aff ect tissues in all phases of the wound process, leading to accelerated healing of chronic wounds. The aim of the study was to evaluate the eff ectiveness of using high-intensity erbium laser for treating patients with chronic wounds of various origins compared to traditional treatment. Material and methods: An analysis of the treatment of 144 patients with chronic wounds was conducted in two groups. In the 1st group (n = 71), a high-intensity erbium laser and dressings with water-soluble ointments were used. In the 2nd group (n = 73), standard surgical treatment with similar dressings was performed. Results were evaluated using visual assessment of wound defects, planimetry, bacteriological and cytological studies, assessment of procedure tolerability, and pain intensity before and after treatment. Results: рatients in the 1st group showed signs of healing signifi cantly earlier and more frequently achieved complete epithelialization of wounds. Laser treatment contributed to more effective decontamination of wound defects, and signs of tissue regeneration were more frequently observed in cytological images. Patients tolerated erbium laser treatment better than surgical treatment, although pain intensity after treatment did not differ between groups. Conclusion: The study confi rmed the effectiveness of using high-intensity erbium laser for treating chronic wounds. This method can be recommended for use in surgical practice alongside other technical and pharmacological tools.

Prediction of tumor origin in cancers of unknown primary origin with cytology-based deep learning.

Cancer of unknown primary (CUP) site poses diagnostic challenges due to its elusive nature. Many cases of CUP manifest as pleural and peritoneal serous effusions. Leveraging cytological images from 57,220 cases at four tertiary hospitals, we developed a deep-learning method for tumor origin differentiation using cytological histology (TORCH) that can identify malignancy and predict tumor origin in both hydrothorax and ascites. We examined its performance on three internal (n = 12,799) and two external (n = 14,538) testing sets. In both internal and external testing sets, TORCH achieved area under the receiver operating curve values ranging from 0.953 to 0.991 for cancer diagnosis and 0.953 to 0.979 for tumor origin localization. TORCH accurately predicted primary tumor origins, with a top-1 accuracy of 82.6% and top-3 accuracy of 98.9%. Compared with results derived from pathologists, TORCH showed better prediction efficacy (1.677 versus 1.265, P < 0.001), enhancing junior pathologists' diagnostic scores significantly (1.326 versus 1.101, P < 0.001). Patients with CUP whose initial treatment protocol was concordant with TORCH-predicted origins had better overall survival than those who were administrated discordant treatment (27 versus 17 months, P = 0.006). Our study underscores the potential of TORCH as a valuable ancillary tool in clinical practice, although further validation in randomized trials is warranted.

METHOD OF GENERATIVE-ADVERSARIAL NETWORKS SEARCHING ARCHITECTURES FOR BIOMEDICAL IMAGES SYNTHESIS

Context. The article examines the problem of automatic design of architectures of generative-adversarial networks. Generativeadversarial networks are used for image synthesis. This is especially true for the synthesis of biomedical images – cytological and histological, which are used to make a diagnosis in oncology. The synthesized images are used to train convolutional neural networks. Convolutional neural networks are currently among the most accurate classifiers of biomedical images.&#x0D; Objective. The aim of the work is to develop an automatic method for searching for architectures of generative-adversarial networks based on a genetic algorithm.&#x0D; Method. The developed method consists of the stage of searching for the architecture of the generator with a fixed discriminator and the stage of searching for the architecture of the discriminator with the best generator.&#x0D; At the first stage, a fixed discriminator architecture is defined and a generator is searched for. Accordingly, after the first step, the architecture of the best generator is obtained, i.e. the model with the lowest FID value.&#x0D; At the second stage, the best generator architecture was used and a search for the discriminator architecture was carried out. At each cycle of the optimization algorithm, a population of discriminators is created. After the second step, the architecture of the generative-adversarial network is obtained.&#x0D; Results. Cytological images of breast cancer on the Zenodo platform were used to conduct the experiments. As a result of the study, an automatic method for searching for architectures of generatively adversarial networks has been developed. On the basis of computer experiments, the architecture of a generative adversarial network for the synthesis of cytological images was obtained. The total time of the experiment was ~39.5 GPU hours. As a result, 16,000 images were synthesized (4000 for each class). To assess the quality of synthesized images, the FID metric was used.The results of the experiments showed that the developed architecture is the best. The network’s FID value is 3.39. This result is the best compared to well-known generative adversarial networks.&#x0D; Conclusions. The article develops a method for searching for architectures of generative-adversarial networks for the problems of synthesis of biomedical images. In addition, a software module for the synthesis of biomedical images has been developed, which can be used to train CNN.

Development and validation of an artificial intelligence-based model for detecting urothelial carcinoma using urine cytology images: a multicentre, diagnostic study with prospective validation

Urine cytology is an important non-invasive examination for urothelial carcinoma (UC) diagnosis and follow-up. We aimed to explore whether artificial intelligence (AI) can enhance the sensitivity of urine cytology and help avoid unnecessary endoscopy. In this multicentre diagnostic study, consecutive patients who underwent liquid-based urine cytology examinations at four hospitals in China were included for model development and validation. Patients who declined surgery and lacked associated histopathology results, those diagnosed with rare subtype tumours of the urinary tract, or had low-quality images were excluded from the study. All liquid-based cytology slides were scanned into whole-slide images (WSIs) at 40×magnification and the WSI-labels were derived from the corresponding histopathology results. The Precision Urine Cytology AI Solution (PUCAS) was composed of three distinct stages (patch extraction, features extraction, and classification diagnosis) and was trained to identify important WSI features associated with UC diagnosis. The diagnostic sensitivity was mainly used to validate the performance of PUCAS in retrospective and prospective validation cohorts. This study is registered with the ChiCTR, ChiCTR2300073192. Between January 1, 2018 and October 31, 2022, 2641 patients were retrospectively recruited in the training cohort, and 2335 in retrospective validation cohorts; 400 eligible patients were enrolled in the prospective validation cohort between July 7, 2023 and September 15, 2023. The sensitivity of PUCAS ranged from 0.922 (95% CI: 0.811-0.978) to 1.000 (0.782-1.000) in retrospective validation cohorts, and was 0.896 (0.837-0.939) in prospective validation cohort. The PUCAS model also exhibited a good performance in detecting malignancy within atypical urothelial cells cases, with a sensitivity of over 0.84. In the recurrence detection scenario, PUCAS could reduce 57.5% of endoscopy use with a negative predictive value of 96.4%. PUCAS may help to improve the sensitivity of urine cytology, reduce misdiagnoses of UC, avoid unnecessary endoscopy, and reduce the clinical burden in resource-limited areas. The further validation in other countries is needed. National Natural Science Foundation of China; Key Program of the National Natural Science Foundation of China; the National Science Foundation for Distinguished Young Scholars; the Science and Technology Planning Project of Guangdong Province; the National Key Research and Development Programme of China; Guangdong Provincial Clinical Research Centre for Urological Diseases.