Explore the vast range of titles available.

Automatic medical image segmentation plays a critical role in scientific research and medical care. Existing high-performance deep learning methods typically rely on large training datasets with high-quality manual annotations, which are difficult to obtain in many clinical applications. Here, we introduce Annotation-effIcient Deep lEarning (AIDE), an open-source framework to handle imperfect training datasets. Methodological analyses and empirical evaluations are conducted, and we demonstrate that AIDE surpasses conventional fully-supervised models by presenting better performance on open datasets possessing scarce or noisy annotations. We further test AIDE in a real-life case study for breast tumor segmentation. Three datasets containing 11,852 breast images from three medical centers are employed, and AIDE, utilizing 10% training annotations, consistently produces segmentation maps comparable to those generated by fully-supervised counterparts or provided by independent radiologists. The 10-fold enhanced efficiency in utilizing expert labels has the potential to promote a wide range of biomedical applications. Existing high-performance deep learning methods typically rely on large training datasets with high-quality manual annotations, which are difficult to obtain in many clinical applications. Here, the authors introduce an open-source framework to handle imperfect training datasets.

•Self-supervised learning for arbitrary resolution quantitative susceptibility mapping (QSM), trained on one resolution data.•Morphology-based loss to reduce artifacts effectively and save training time efficiently.•Morphological QSM builder for decoupling dependence of the QSM on resolution with apriori information.•Significant changes in magnetic susceptibility in the brain regions of patients in the progression of AD or with PD. Quantitative susceptibility mapping (QSM) has been applied to the measurement of iron deposition and the auxiliary diagnosis of neurodegenerative disease. There still exists a dipole inversion problem in QSM reconstruction. Recently, deep learning approaches have been proposed to resolve this problem. However, most of these approaches are supervised methods that need pairs of the input phase and ground-truth. It remains a challenge to train a model for all resolutions without using the ground-truth and only using one resolution data. To address this, we proposed a self-supervised QSM deep learning method based on morphology. It consists of a morphological QSM builder to decouple the dependency of the QSM on acquisition resolution, and a morphological loss to reduce artifacts effectively and save training time efficiently. The proposed method can reconstruct arbitrary resolution QSM on both human data and animal data, regardless of whether the resolution is higher or lower than that of the training set. Our method outperforms the previous best unsupervised method with a 3.6% higher peak signal-to-noise ratio, 16.2% lower normalized root mean square error, and 22.1% lower high-frequency error norm. The morphological loss reduces training time by 22.1% with respect to the cycle gradient loss used in the previous unsupervised methods. Experimental results show that the proposed method accurately measures QSM with arbitrary resolutions, and achieves state-of-the-art results among unsupervised deep learning methods. Research on applications in neurodegenerative diseases found that our method is robust enough to measure significant increase in striatal magnetic susceptibility in patients during Alzheimer’s disease progression, as well as significant increase in substantia nigra susceptibility in Parkinson’s disease patients, and can be used as an auxiliary differential diagnosis tool for Alzheimer’s disease and Parkinson’s disease.

Congenital aorta–right atrial tunnel (ARAT) is a rare congenital cardiovascular malformation characterized by an abnormal tunnel‐like connection between the aorta and the right atrium. Patients with ARAT frequently have other congenital heart malformations and require diagnosis through a variety of imaging examinations. We report a 1‐month‐old female infant with multiple congenital cardiac malformations who was diagnosed with ARAT using low‐dose multislice spiral computed tomography because echocardiography was unclear. Congenital aorta–right atrial tunnel (ARAT) is a rare congenital cardiovascular malformation characterized by an abnormal tunnel‐like connection between the aorta and the right atrium. Patients with ARAT frequently have other congenital heart malformations and require diagnosis through a variety of imaging examinations. We report a 1‐month‐old female infant with multiple congenital cardiac malformations who was diagnosed with ARAT using low‐dose multislice spiral computed tomography because echocardiography was unclear.

The neutrophil-to-lymphocyte ratio (NLR) may predict outcomes in end-stage liver disease, but its value after transjugular intrahepatic portosystemic shunt (TIPS) is unclear. This study explored the link between NLR and long-term outcomes in decompensated cirrhosis patients post-TIPS. We retrospectively analyzed 184 patients treated between January 2016 and December 2021, noting demographic data, lab results, and follow-up outcomes, including liver transplantation or death. Cox regression, adjusted for various factors, showed that NLR is an independent predictor of post-TIPS progression (HR 1.665; 95% CI 1.149–2.414; P  = 0.007). Patients were divided into tertiles based on NLR. The medium tertile had a 3.51-fold increased risk of progression compared to the lowest (HR 3.510; 95% CI 1.104–11.153, P  = 0.033), and the highest tertile had a 5.112-fold increase (HR 5.112; 95% CI 1.653–15.806, P  = 0.005). This suggests that NLR is a valuable prognostic marker for long-term progression in these patients, highlighting the role of systemic inflammation.

Background/Aims: Pancreatic cancer (PC) is an aggressive malignancy with a poor survival rate. Despite advances in the treatment of PC, the efficacy of therapy is limited by the development of chemoresistance. Here, we examined the role of microRNA-29c (miR-29c) and the involvement of autophagy and apoptosis in the chemoresistance of PC cells in vivo and in vitro. Methods: We employed qRT-PCR, western blot and immunofluorescence to examine the expression level of miR-29c, USP22 and autophagy relative protein. In addition, we used MTT assay to detect cell proliferation and transwell assay to measure migration and invasiveness. The apoptosis was determined using annexin V-FITC/PI apoptosis detection kit by flow cytometry. Luciferase reporter assays confirmed the relationship between USP22 and miR-29c. Results: miR-29c overexpression in the PC cell line PANC-1 enhanced the effect of gemcitabine on decreasing cell viability and inducing apoptosis and inhibited autophagy, as shown by western blotting, immunofluorescence staining, colony formation assays, and flow cytometry. Ubiquitin specific peptidase (USP)-22, a deubiquitinating enzyme known to induce autophagy and promote PC cell survival, was identified as a direct target of miR-29c. USP22 knockdown experiments indicated that USP22 suppresses gemcitabine-induced apoptosis by promoting autophagy, thereby increasing the chemoresistance of PC cells. Luciferase reporter assays confirmed that USP22 is a direct target of miR-29c. A xenograft mouse model demonstrated that miR-29c increases the chemosensitivity of PC in vivo by downregulating USP22, leading to the inhibition of autophagy and induction of apoptosis. Conclusions: Taken together, these findings reveal a potential mechanism underlying the chemoresistance of PC cells mediated by the regulation of USP22-mediated autophagy by miR-29c, suggesting potential targets and therapeutic strategies in PC.

Objective To explore the potential of using the extracellular volume fraction (ECV), measured through enhanced computed tomography (CT), as a tool for determining the pathological grade of clear cell renal cell carcinoma (ccRCC). Methods This retrospective study, approved by the institutional review board, included 65 patients (median age: 58.40 ± 10.84 years) who were diagnosed with ccRCC based on the nucleolar grading of the International Society of Urological Pathology (ISUP). All patients underwent preoperative abdominal enhanced CT between January 2022 and August 2024. CT features from the unenhanced, corticomedullary, nephrographic, and delayed phases were analyzed, and the extracellular volume fraction (ECV) of ccRCC was calculated by measuring CT values from regions of interest in both the unenhanced and nephrographic phases. Statistical significance was evaluated for differences in these parameters across the four ISUP grades. Additionally, diagnostic efficiency was assessed using receiver operating characteristic (ROC) curve analysis. Results The ECV showed significant differences across the four ISUP grades of ccRCC, its potential as an important predictor of high-grade ccRCC ( P  = 0.035). The ROC curve analysis indicated that ECV exhibited the highest diagnostic efficacy for assessing the lower- and higher- pathological grade of ccRCC, with an area under the ROC curve of 0.976. The optimal diagnostic threshold for ECV was determined to be 41.64%, with a sensitivity of 91.31% and a specificity of 97.62%. Conclusions ECV derived from enhanced CT has the potential to function as an in vivo biomarker for distinguishing between lower- and higher-grade ccRCC. This quantitative measure provides diagnostic value that extends beyond traditional qualitative CT features, offering a more precise and objective assessment of tumor grade.

Background Accurate preoperative T and TNM staging of clear cell renal cell carcinoma (ccRCC) is crucial for diagnosis and treatment, but these assessments often depend on subjective radiologist judgment, leading to interobserver variability. This study aims to design and validate two CT-based deep learning models and evaluate their clinical utility for the preoperative T and TNM staging of ccRCC. Methods Data from 1,148 ccRCC patients across five medical centers were retrospectively collected. Specifically, data from two centers were merged and randomly divided into a training set (80%) and a testing (20%) set. Data from two additional centers comprised external validation set 1, and data from the remaining independent center comprised external validation set 2. Two 3D deep learning models based on a Transformer-ResNet (TR-Net) architecture were developed to predict T staging (T1, T2, T3 + T4) and TNM staging (I, II, III, IV) using corticomedullary phase CT images. Gradient-weighted Class Activation Mapping (Grad-CAM) was used to generate heatmaps for improved model interpretability, and a human-machine collaboration experiment was conducted to evaluate clinical utility. Models’ performance was evaluated using micro-average AUC (micro-AUC), macro-average AUC (macro-AUC), and accuracy (ACC). Results Across the two external validation sets, the T staging model achieved micro-AUCs of 0.939 and 0.954, macro-AUCs of 0.857 and 0.894, and ACCs of 0.843 and 0.869, while the TNM staging model achieved micro-AUCs of 0.935 and 0.924, macro-AUCs of 0.817 and 0.888, and ACCs of 0.856 and 0.807. While the models demonstrated acceptable overall performance in preoperative ccRCC staging, performance was moderate for advanced subclasses (T3 + T4 AUC: 0.769 and 0.795; TNM III AUC: 0.669 and 0.801). Grad-CAM heatmaps highlighted key tumor regions, improving interpretability. The human-machine collaboration demonstrated improved diagnostic accuracy with model assistance. Conclusion The CT-based 3D TR-Net models showed acceptable overall performance with moderate results in advanced subclasses in preoperative ccRCC staging, with interpretable outputs and collaborative benefits, making them potentially useful decision-support tools.

Background Pregnancy begins with a fertilized ovum that normally attaches to the uterine endometrium. However, an ectopic pregnancy can occur when a fertilized egg implants and grows outside the uterine cavity. Tubal ectopic pregnancy is the most common type (over 95%), with ovarian, abdominal, cervical, broad ligament, and uterine cornual pregnancy being less common. As more cases of ectopic pregnancy are diagnosed and treated in the early stages, the survival rate and fertility retention significantly improve. However, complications of abdominal pregnancy can sometimes be life-threatening and have severe consequences. Case presentation We present a case of intraperitoneal ectopic pregnancy with fetal survival. Ultrasound and magnetic resonance imaging showed a right cornual pregnancy with a secondary abdominal pregnancy. In September 2021, we performed an emergency laparotomy, along with additional procedures such as transurethral ureteroscopy, double J-stent placement, abdominal fetal removal, placentectomy, repair of the right uterine horn, and pelvic adhesiolysis, in the 29th week of pregnancy. During laparotomy, we diagnosed abdominal pregnancy secondary to a rudimentary uterine horn. The mother and her baby were discharged eight days and 41 days, respectively, after surgery. Conclusions Abdominal pregnancy is a rare condition. The variable nature of ectopic pregnancy can cause delays in timely diagnosis, resulting in increased morbidity and mortality, especially in areas with inadequate medical and social services. A high index of suspicion, coupled with appropriate imaging studies, can help facilitate its diagnosis in any suspected case.

Objective To investigate the potential of a hybrid multi-instance learning model (TGMIL) combining Transformer and graph attention networks for classifying gastric adenocarcinoma differentiation on whole-slide images (WSIs) without manual annotation. Methods and materials A hybrid multi-instance learning model is proposed based on the Transformer and the graph attention network, called TGMIL, to classify the differentiation of gastric adenocarcinoma. A total of 613 WSIs from patients with gastric adenocarcinoma were retrospectively collected from two different hospitals. According to the differentiation of gastric adenocarcinoma, the data were divided into four groups: normal group (n = 254), well differentiation group (n = 166), moderately differentiation group (n = 75), and poorly differentiation group (n = 118). The gold standard of differentiation classification was blindly established by two gastrointestinal pathologists. The WSIs were randomly split into a training dataset consisting of 494 images and a testing dataset consisting of 119 images. Within the training set, the WSI count of the normal, well, moderately, and poorly differential groups was 203, 131, 62, and 98 individuals, respectively. Within the test set, the corresponding WSI count was 51, 35, 13, and 20 individuals. Results The TGMIL model developed for the differential prediction task exhibited remarkable efficiency when considering sensitivity, specificity, and the area under the curve (AUC) values. We also conducted a comparative analysis to assess the efficiency of five other models, namely MIL, CLAM_SB, CLAM_MB, DSMIL, and TransMIL, in classifying the differentiation of gastric cancer. The TGMIL model achieved a sensitivity of 73.33% and a specificity of 91.11%, with an AUC value of 0.86. Conclusions The hybrid multi-instance learning model TGMIL could accurately classify the differentiation of gastric adenocarcinoma using WSI without the need for labor-intensive and time-consuming manual annotations, which will improve the efficiency and objectivity of diagnosis.

Statistical analyses, including multivariate Cox regression, prediction error curves over time, and time-dependent receiver operating characteristic (ROC) analysis, were conducted to evaluate the model’s performance, compare it against unimodal approaches, and confirm the independent prognostic value of the integrated risk score. The model was evaluated on the basis of its concordance index (C-index), hazard ratio (HR) from Cox regression analysis, and area under the receiver operating characteristic curve (AUC), among other metrics. Multivariate Cox regression analyses revealed the strong predictive power of the integrated risk score for CRPC progression, with HRs indicating a high level of statistical significance: HR = 11.109, with a 95% confidence interval (CI) of 3.342–36.933 in the IVC; HR = 33.075 (95% CI: 6.556–166.852) in the external testing cohort 1; and HR = 21.236 (CI: 5.103–88.602) in the external testing cohort 2. [...]the study has been