Explore the vast range of titles available.

This study investigated a series of deep learning (DL) models for the objective assessment of four categories of mammographic breast density (e.g., fatty, scattered, heterogeneously dense, and extremely dense). A retrospective analysis was conducted using data collected from Taizhou Cancer Hospital over a period from January 2015 to December 2020. The dataset included mammograms from 9,621 women, totaling 57,282 images. The dataset was divided into training, validation, and test sets at a ratio of 7:2:1. Four DL models were employed, with Average Precision (AP) served as the primary evaluation metric. Additionally, the diagnostic performance of the DL models was compared with that of radiologists. Finally, we conducted validation of our model using an external test set. Among the DL models studied, InceptionV3 performed best, with AP values of 0.895 for almost entirely fatty, 0.857 for scattered fibroglandular tissue, 0.953 for heterogeneously dense, and 0.952 for extremely dense categories. The InceptionV3 model outperformed radiologists in accuracy and consistency. While radiologists surpassed the InceptionV3 model in fatty and scattered categories, their accuracy dropped significantly in heterogeneously and extremely dense categories. Nevertheless, our study demonstrated that DL can serve as a valuate tool in assisting radiologists with the objective quantification of breast density.

Papillary thyroid cancer (PTC) accounts for more than 80% of thyroid cancers, and ultrasound (US) imaging is the preferred method for the diagnosis of PTC. However, accurate prediction of different patterns of cervical lymph node metastasis (CLNM) in PTC continues to be a challenge. Herein, US images and clinical factors of PTC patients from three hospitals for more than 11 years are collected, and a multimodal deep learning model called DeepThy‐Net is then developed to predict different CLNM patterns. The proposed model not only uses the convolutional features extracted by deep learning but also integrates traditional clinical factors that are highly related to lymph node metastasis. Finally, the model is tested in two independent test sets, and the experimental results show that the area under curve (AUC) is between 0.870 and 0.905, indicating clinical applicability. The proposed method provides an important reference for the treatment and management of PTC. Moreover, for PTC cases involving an active surveillance strategy, the proposed method can serve as an important CLNM early warning tool. A DeepThy‐Net model is built to extract the features of the ultrasound images and predict different cervical lymph node metastasis patterns in papillary thyroid cancer. The clinical factors recorded by doctors are also digitized and input into a fully connected network with the above‐mentioned features, and finally, the prediction results are obtained.

Although using artificial intelligence (AI) to analyze ultrasound images is a promising approach to assessing thyroid nodule risks, traditional AI models lack transparency and interpretability. We developed a multimodal generative pre-trained transformer for thyroid nodules (ThyGPT), aiming to provide a transparent and interpretable AI copilot model for thyroid nodule risk assessment and management. Ultrasound data from 59,406 patients across nine hospitals were retrospectively collected to train and test the model. After training, ThyGPT was found to assist in reducing biopsy rates by more than 40% without increasing missed diagnoses. In addition, it detects errors in ultrasound reports 1,610 times faster than humans. With the assistance of ThyGPT, the area under the curve for radiologists in assessing thyroid nodule risks improved from 0.805 to 0.908 ( p  < 0.001). As an AI-generated content-enhanced computer-aided diagnosis (AIGC-CAD) model, ThyGPT has the potential to revolutionize how radiologists use such tools.

This retrospective study evaluated the efficacy of large language models (LLMs) in improving the accuracy of Chinese ultrasound reports. Data from three hospitals (January-April 2024) including 400 reports with 243 errors across six categories were analyzed. Three GPT versions and Claude 3.5 Sonnet were tested in zero-shot settings, with the top two models further assessed in few-shot scenarios. Six radiologists of varying experience levels performed error detection on a randomly selected test set. In zero-shot setting, Claude 3.5 Sonnet and GPT-4o achieved the highest error detection rates (52.3% and 41.2%, respectively). In few-shot, Claude 3.5 Sonnet outperformed senior and resident radiologists, while GPT-4o excelled in spelling error detection. LLMs processed reports faster than the quickest radiologist (Claude 3.5 Sonnet: 13.2 s, GPT-4o: 15.0 s, radiologist: 42.0 s per report). This study demonstrates the potential of LLMs to enhance ultrasound report accuracy, outperforming human experts in certain aspects.

Objective Thyroid capsule invasion (TCI) predicts early progression in papillary thyroid microcarcinoma (PTMC). This study aimed to develop an integrated model that combines handcrafted peri-tumoral radiomics features with deep learning (DL)-derived intra-tumoral features for accurate early prediction of TCI, to support clinical decision-making. Materials and methods Retrospective data from 964 patients with 964 pathologically confirmed PTMC lesions across three centers were collected. Radiomics features were extracted from multiple peri-tumoral regions, and the optimal peri-tumor region with the best radiomics features was selected using a support vector machine (SVM). The selected radiomics features were then combined with intra-tumoral DL features extracted from the tumors before being fed into four different DL models for training and validation. Performance was validated on the internal ( n  = 177) and external ( n  = 84) test sets. Six radiologists (senior/attending/junior) assessed TCI with/without DL assistance. Results The radiomics features, which achieved the best diagnostic performance with an AUC of 0.795 using SVM, were extracted from the peri-tumor region with 30% expansion from the original tumor. By further combining these radiomics features with intra-tumoral DL features, four different DL models were established to identify TCI in PTMC. Swin-Transformer achieved superior performance (internal AUC: 0.923; external AUC: 0.892). With DL model assistance, the AUCs of six radiologists significantly improved, for example, from 0.720 to 0.796 and from 0.725 to 0.790 for senior radiologists, and similar gains were observed for attending and junior radiologists. Conclusions As an effective clinical assistive tool,  this integrated model can provide TCI identification with high level of accuracy. With its ability to enhance radiologists’ diagnostic performance, it supports early PTMC risk stratification and personalized intervention. Critical relevance statement This retrospective multicenter study establishes an integrated model for identifying TCI in PTMC. The model significantly enhances radiologists’ diagnostic precision across multiple experience levels, supporting early clinical decision-making for optimized intervention strategies. Key Points Accurate prediction of TCI facilitates early assessment of PTMC progression and guides subsequent individualized clinical management. DL significantly improves the predictive performance for TCI. DL effectively assists radiologists in TCI diagnosis. Graphical Abstract

The subtle imaging features of thymic epithelial tumors (TETs), which comprise multiple pathological subtypes of thymoma and thymic carcinoma, are of great significance for the identification of high-risk patients. Finding the radiomics features related to the immunohistochemical markers of TETs may provide a non-invasive method for the construction of a prediction model. This retrospective study analyzed non-enhanced computed tomography (NECT) images of 307 patients with TETs from two institutions. The radiomic features were extracted, clustered, and used to develop the models with machine learning algorithms. In general, the radiomics of TET patients were profiled and clustered into three clusters, which showed differences in correlation between clinicopathological characteristics, including histological type, Masaoka stage, and immunohistochemical results. Moreover, the “original-shape-flatness” and “wavelet-LHL-first-order-Median” were the most strongly correlated with CD117 and TDT expression, and the combined model of the two demonstrated predictive efficacy for CD117/TDT expression and risk groups in training and validation cohorts. This study highlights that radiomics and biomarker-associated features can serve as a non-invasive predictive biomarker for TET patients.

Recognizing the limitations of computer-assisted tools for thyroid nodule diagnosis using static ultrasound images, this study developed a diagnostic tool utilizing dynamic ultrasound video, namely Thyroid Nodules Visualization (TNVis), by leveraging a two-stage deep learning framework that involved three-dimensional (3D) visualization. In this multicenter study, 4569 cases were included for framework development, and data from seven hospitals were employed for diagnostic validation. TNVis achieved a Dice similarity coefficient of 0.90 after internal testing. For the external validation, TNVis significantly improved radiologists’ performance, reaching an AUC of 0.79, compared to their diagnostic performance without the use of TNVis (AUC: 0.66; p  < 0.001) and those with partial assistance (AUC: 0.72; p  < 0.001). In conclusion, the TNVis-assisted diagnostic strategy not only significantly improves the diagnostic ability of radiologists but also closely imitates their clinical diagnostic procedures and provides them with an objective 3D representation of the nodules for precise and personalized diagnosis and treatment planning.

Objectives This study aimed to propose a deep learning (DL)–based framework for identifying the composition of thyroid nodules and assessing their malignancy risk. Methods We conducted a retrospective multicenter study using ultrasound images from four hospitals. Convolutional neural network (CNN) models were constructed to classify ultrasound images of thyroid nodules into solid and non-solid, as well as benign and malignant. A total of 11,201 images of 6784 nodules were used for training, validation, and testing. The area under the receiver-operating characteristic curve (AUC) was employed as the primary evaluation index. Results The models had AUCs higher than 0.91 in the benign and malignant grading of solid thyroid nodules, with the Inception-ResNet AUC being the highest at 0.94. In the test set, the best algorithm for identifying benign and malignant thyroid nodules had a sensitivity of 0.88, and a specificity of 0.86. In the human vs. DL test set, the best algorithm had a sensitivity of 0.93, and a specificity of 0.86. The Inception-ResNet model performed better than the senior physicians ( p  < 0.001). The sensitivity and specificity of the optimal model based on the external test set were 0.90 and 0.75, respectively. Conclusions This research demonstrates that CNNs can assist thyroid nodule diagnosis and reduce the rate of unnecessary fine-needle aspiration (FNA). Clinical relevance statement High-resolution ultrasound has led to increased detection of thyroid nodules. This results in unnecessary fine-needle aspiration and anxiety for patients whose nodules are benign. Deep learning can solve these problems to some extent. Key Points • Thyroid solid nodules have a high probability of malignancy . • Our models can improve the differentiation between benign and malignant solid thyroid nodules . • The differential performance of one model was superior to that of senior radiologists. Applying this could reduce the rate of unnecessary fine-needle aspiration of solid thyroid nodules .

Mitochondrial malic enzyme 2 (ME2), which catalyzes the conversion of malate to pyruvate, is frequently upregulated during tumorigenesis and is a potential target for cancer therapy. However, the regulatory mechanism underlying ME2 activity is largely unknown. In this study, we demonstrate that ME2 is highly expressed in human colorectal cancer (CRC) tissues, and that ME2 knockdown inhibits the proliferation of CRC cells. Furthermore, we reveal that ME2 is succinylated and identify Sirtuins 5 (SIRT5) as an ME2 desuccinylase. Glutamine deprivation directly enhances the interaction of SIRT5 with ME2 and thus promotes SIRT5-mediated desuccinylation of ME2 at lysine 346, activating ME2 enzymatic activity. Activated ME2 significantly enhances mitochondrial respiration, thereby counteracting the effects of glutamine deprivation and supporting cell proliferation and tumorigenesis. Additionally, the levels of succinylated ME2 at K346 and SIRT5 in CRC tissues, which are negatively correlated, are associated with patient prognosis. These observations suggest that SIRT5-catalyzed ME2 desuccinylation is a key signaling event through which cancer cells maintain mitochondrial respiration and promote CRC progression under glutamine deficiency conditions, offering the possibility of targeting SIRT5-mediated ME2 desuccinylation for CRC treatment.

Background The confused taxonomic classification of Crucigenia is mainly inferred through morphological evidence and few nuclear genes and chloroplast genomic fragments. The phylogenetic status of C. quadrata, as the type species of Crucigenia , remains considerably controversial. Additionally, there are currently no reports on the chloroplast genome of Crucigenia . Results In this study, we utilize molecular phylogenetics and comparative genomics to show that C. quadrata belongs to Chlorophyceae rather than Trebouxiophyceae. The Bayesian and maximum likelihood (ML) phylogenetic trees support a monophyletic group of C. quadrata and Scenedesmaceae (Chlorophyceae) species. Our study presents the first complete chloroplast genome of C. quadrata, which is 197,184 bp in length and has a GC content of 31%. It has a typical quadripartite structure, and the chloroplast genome codons exhibit usage bias. Nucleotide diversity analysis highlights six genes ( ccsA , psbF , chlN , cemA , rps3 , rps18 ) as hotspots for genetic variation. Coding gene sequence divergence analyses indicate that four genes ( cemA , clpP , psaA , rps3 ) are subject to positive selection. Conclusions The determination of the phylogenetic status and the comparative chloroplast genomic analyses of C. quadrata will not only be useful in enhancing our understanding of the intricacy of Crucigenia taxonomy but also provide the important basis for studying the evolution of the incertae sedis taxa within Trebouxiophyceae.