LNAS: a clinically applicable deep-learning system for mediastinal enlarged lymph nodes segmentation and station mapping without regard to the pathogenesis using unenhanced CT images.

BACKGROUND: The accurate identification and evaluation of lymph nodes by CT images is of great significance for disease diagnosis, treatment, and prognosis. PURPOSE: To assess the lymph nodes' segmentation, size, and station by artificial intelligence (AI) for unenhanced chest CT images and evaluate its value in clinical scenarios. MATERIAL AND METHODS: This retrospective study proposed an end-to-end Lymph Nodes Analysis System (LNAS) consisting of three models: the Lymph Node Segmentation model (LNS), the Mediastinal Organ Segmentation model (MOS), and the Lymph Node Station Registration model (LNR). We selected a healthy chest CT image as the template image and annotated 14 lymph node station masks according to the IASLC to build the lymph node station mapping template. The exact contours and stations of the lymph nodes were annotated by two junior radiologists and reviewed by a senior radiologist. Patients aged 18 and above, who had undergone unenhanced chest CT and had at least one suspicious enlarged mediastinal lymph node in imaging reports, were included. Exclusions were patients who had thoracic surgeries in the past 2 weeks or artifacts on CT images affecting lymph node observation by radiologists. The system was trained on 6725 consecutive chest CTs that from Tianjin Medical University General Hospital, among which 6249 patients had suspicious enlarged mediastinal lymph nodes. A total of 519 consecutive chest CTs from Qilu Hospital of Shandong University (Qingdao) were used for external validation. The gold standard for each CT was determined by two radiologists and reviewed by one senior radiologist. RESULTS: The patient-level sensitivity of the LNAS system reached of 93.94% and 92.89% in internal and external test dataset, respectively. And the lesion-level sensitivity (recall) reached 89.48% and 85.97% in internal and external test dataset. For man-machine comparison, AI significantly apparently shortened the average reading time (p < 0.001) and had better lesion-level and patient-level sensitivities. CONCLUSION: AI improved the sensitivity lymph node segmentation by radiologists with an advantage in reading time.

Macrocyclic-Albumin Conjugates for Precise Delivery of Radionuclides and Anticancer Drugs to Tumors.

Precise delivery of radionuclides and anticancer drugs to tumor tissue is crucial to ensuring drug synergism and optimal therapeutic effects in radionuclide-based combination radio-chemotherapy. However, current codelivery vectors often rely on physical embedment/adsorption to load anticancer drugs, which lacks precise mechanisms for drug loading and release, resulting in unpredictable combination effects. Herein, a macrocyclic-albumin conjugate (MAC) that enables precise loading and controlled release of anticancer drugs is presented. By conjugating multiple macrocyclic hosts (sulfonate azocalix[4]arenes, SAC4A) to albumin molecules, the MAC facilitates the precise loading of anticancer drugs through host-guest interactions and site-specific labeling of radionuclides. Furthermore, the MAC degrades under hypoxic conditions, enabling the release of loaded drugs upon reaching tumor tissues. Through precise loading and targeted delivery of radionuclides and anticancer drugs, MAC achieves efficient cancer diagnosis and combined radio-chemotherapy in breast cancer cell (4T1)-bearing mice. Considering that SAC4A can load many anticancer drugs, MAC may provide a promising platform for effective combination radio-chemotherapy.

Sex-specific associations of cardiovascular risk factors and coronary plaque composition for hemodynamically significant coronary artery stenosis: a coronary computed tomography angiography study.

BACKGROUND: It has been reported that there are sex differences in plaque composition and hemodynamically significant stenosis. This study aimed to explore the impact of sex on cardiovascular risk factors for specific plaque compositions and hemodynamically significant stenosis. METHODS: Data regarding demographics and cardiovascular risk factors were collected. Hemodynamically significant stenosis was identified by a computed tomography-derived fractional flow reserve of ≤ 0.8. Associations among cardiovascular risk factors, plaque composition, and hemodynamically significant stenosis were assessed using a multivariate binary logistic regression analysis across sexes. The discriminating capacity of diverse plaque components for hemodynamically significant stenosis was assessed by area under the receiver-operating characteristics curve with 95% confidence intervals. RESULTS: A total of 1164 patients (489 men and 675 women) were included. For men, hyperlipidemia and cigarette smoking were risk factors for each plaque component (all P < 0.05), and diabetes mellitus also predicted fibrotic components (P < 0.05). For women, risk factors for each plaque component were hypertension and diabetes mellitus (all P < 0.01). Nonetheless, hyperlipidemia (P < 0.05) was a specific risk factor for non-calcified components. Calcified components combined with fibrotic components showed superior discrimination of hemodynamically significant stenosis in men and calcified components alone in women (all P < 0.01). Hypertension (P < 0.01) was a risk factor for hemodynamically significant stenosis in women. In contrast, diabetes, hyperlipidemia, and cigarette smoking were risk factors for hemodynamically significant stenosis in men (all P < 0.05). CONCLUSIONS: In men, hemodynamically significant stenosis was predicted by a combination of calcified and fibrotic components with multiple risk factors. In women, hemodynamically significant stenosis was predicted by calcified components caused by a single risk factor. It might be a key point to improve prognosis by more precise risk management between men and women, which needs to be proved by further prospective trials.

Application of tumor pH/hypoxia-responsive nanoparticles for combined photodynamic therapy and hypoxia-activated chemotherapy.

Introduction: Cancer selectivity, including targeted internalization and accelerated drug release in tumor cells, remains a major challenge for designing novel stimuli-responsive nanocarriers to promote therapeutic efficacy. The hypoxic microenvironment created by photodynamic therapy (PDT) is believed to play a critical role in chemoresistance. Methods: We construct dual-responsive carriers (DANPCT) that encapsulate the photosensitizer chlorin e6 (Ce6) and hypoxia-activated prodrug tirapazamine (TPZ) to enable efficient PDT and PDT-boosted hypoxia-activated chemotherapy. Results and discussion: Due to TAT masking, DANPCT prolonged payload circulation in the bloodstream, and selective tumor cell uptake occurred via acidity-triggered TAT presentation. PDT was performed with a spatially controlled 660-nm laser to enable precise cell killing and exacerbate hypoxia. Hypoxia-responsive conversion of the hydrophobic NI moiety led to the disassembly of DANPCT, facilitating TPZ release. TPZ was reduced to cytotoxic radicals under hypoxic conditions, contributing to the chemotherapeutic cascade. This work offers a sophisticated strategy for programmed chemo-PDT.