Multi-Instance Learning for Vocal Fold Leukoplakia Diagnosis Using White Light and Narrow-Band Imaging: A Multicenter Study.

OBJECTIVES: Vocal fold leukoplakia (VFL) is a precancerous lesion of laryngeal cancer, and its endoscopic diagnosis poses challenges. We aim to develop an artificial intelligence (AI) model using white light imaging (WLI) and narrow-band imaging (NBI) to distinguish benign from malignant VFL. METHODS: A total of 7057 images from 426 patients were used for model development and internal validation. Additionally, 1617 images from two other hospitals were used for model external validation. Modeling learning based on WLI and NBI modalities was conducted using deep learning combined with a multi-instance learning approach (MIL). Furthermore, 50 prospectively collected videos were used to evaluate real-time model performance. A human-machine comparison involving 100 patients and 12 laryngologists assessed the real-world effectiveness of the model. RESULTS: The model achieved the highest area under the receiver operating characteristic curve (AUC) values of 0.868 and 0.884 in the internal and external validation sets, respectively. AUC in the video validation set was 0.825 (95% CI: 0.704-0.946). In the human-machine comparison, AI significantly improved AUC and accuracy for all laryngologists (p < 0.05). With the assistance of AI, the diagnostic abilities and consistency of all laryngologists improved. CONCLUSIONS: Our multicenter study developed an effective AI model using MIL and fusion of WLI and NBI images for VFL diagnosis, particularly aiding junior laryngologists. However, further optimization and validation are necessary to fully assess its potential impact in clinical settings. LEVEL OF EVIDENCE: 3 Laryngoscope, 2024.

Revealing molecular and cellular heterogeneity in hypopharyngeal carcinogenesis through single-cell RNA and TCR/BCR sequencing.

Introduction: Hypopharyngeal squamous cell carcinoma (HSCC) is one of the malignant tumors with the worst prognosis in head and neck cancers. The transformation from normal tissue through low-grade and high-grade intraepithelial neoplasia to cancerous tissue in HSCC is typically viewed as a progressive pathological sequence typical of tumorigenesis. Nonetheless, the alterations in diverse cell clusters within the tissue microenvironment (TME) throughout tumorigenesis and their impact on the development of HSCC are yet to be fully understood. Methods: We employed single-cell RNA sequencing and TCR/BCR sequencing to sequence 60,854 cells from nine tissue samples representing different stages during the progression of HSCC. This allowed us to construct dynamic transcriptomic maps of cells in diverse TME across various disease stages, and experimentally validated the key molecules within it. Results: We delineated the heterogeneity among tumor cells, immune cells (including T cells, B cells, and myeloid cells), and stromal cells (such as fibroblasts and endothelial cells) during the tumorigenesis of HSCC. We uncovered the alterations in function and state of distinct cell clusters at different stages of tumor development and identified specific clusters closely associated with the tumorigenesis of HSCC. Consequently, we discovered molecules like MAGEA3 and MMP3, pivotal for the diagnosis and treatment of HSCC. Discussion: Our research sheds light on the dynamic alterations within the TME during the tumorigenesis of HSCC, which will help to understand its mechanism of canceration, identify early diagnostic markers, and discover new therapeutic targets.

Multi-instance learning based artificial intelligence model to assist vocal fold leukoplakia diagnosis: A multicentre diagnostic study.

OBJECTIVE: To develop a multi-instance learning (MIL) based artificial intelligence (AI)-assisted diagnosis models by using laryngoscopic images to differentiate benign and malignant vocal fold leukoplakia (VFL). METHODS: The AI system was developed, trained and validated on 5362 images of 551 patients from three hospitals. Automated regions of interest (ROI) segmentation algorithm was utilized to construct image-level features. MIL was used to fusion image level results to patient level features, then the extracted features were modeled by seven machine learning algorithms. Finally, we evaluated the image level and patient level results. Additionally, 50 videos of VFL were prospectively gathered to assess the system's real-time diagnostic capabilities. A human-machine comparison database was also constructed to compare the diagnostic performance of otolaryngologists with and without AI assistance. RESULTS: In internal and external validation sets, the maximum area under the curve (AUC) for image level segmentation models was 0.775 (95 % CI 0.740-0.811) and 0.720 (95 % CI 0.684-0.756), respectively. Utilizing a MIL-based fusion strategy, the AUC at the patient level increased to 0.869 (95 % CI 0.798-0.940) and 0.851 (95 % CI 0.756-0.945). For real-time video diagnosis, the maximum AUC at the patient level reached 0.850 (95 % CI, 0.743-0.957). With AI assistance, the AUC improved from 0.720 (95 % CI 0.682-0.755) to 0.808 (95 % CI 0.775-0.839) for senior otolaryngologists and from 0.647 (95 % CI 0.608-0.686) to 0.807 (95 % CI 0.773-0.837) for junior otolaryngologists. CONCLUSIONS: The MIL based AI-assisted diagnosis system can significantly improve the diagnostic performance of otolaryngologists for VFL and help to make proper clinical decisions.

Fabrication of a Coculture Organoid Model in the Biomimetic Matrix of Alginate to Investigate Breast Cancer Progression in a TAMs-Leading Immune Microenvironment.

The current research models of breast cancer are usually limited in their capacity to recapitulate the tumor microenvironment in vitro. The lack of an extracellular matrix (ECM) oversimplifies cell-cell or cell-ECM cross-talks. Moreover, the lack of tumor-associated macrophages (TAMs), that can comprise up to 50% of some solid neoplasms, poses a major problem for recognizing various hallmarks of cancer. To address these concerns, a type of direct breast cancer cells (BCCs)-TAMs coculture organoid model was well developed by a sequential culture method in this study. Alginate cryogels were fabricated with appropriate physical and mechanical properties to serve as an alternative ECM. Then, our previous experience was leveraged to polarize TAMs inside of the cryogels for creating an in vitro immune microenvironment. The direct coculture significantly enhanced BCCs organoid growth and cancer aggressive phenotypes, including the stemness, migration, ECM remodeling, and cytokine secretion. Furthermore, transcriptomic analysis and protein-protein interaction networks implied certain pathways (PI3K-Akt pathway, MAPK signaling pathway, etc.) and targets (TNF, PPARG, TLR2, etc.) during breast cancer progression in a TAM-leading immune microenvironment. Future studies to advance treatment strategies for BCC patients may benefit from using this facile model to reveal and target the interactions between cancer signaling and the immune microenvironment.

Comparison of two single-pill dual combination antihypertensive therapies in Chinese patients: a randomized, controlled trial.

BACKGROUND: Current hypertension guidelines recommend combination of an angiotensin-converting enzyme inhibitor or angiotensin-receptor blocker with a calcium-channel blocker or thiazide diuretic as initial antihypertensive therapy in patients with monotherapy uncontrolled hypertension. However, to what extent these two different combinations are comparable in blood pressure (BP)-lowering efficacy and safety remains under investigation, especially in the Chinese population. We investigated the BP-lowering efficacy and safety of the amlodipine/benazepril and benazepril/hydrochlorothiazide dual therapies in Chinese patients. METHODS: In a multi-center, randomized, actively controlled, parallel-group trial, we enrolled patients with stage 1 or 2 hypertension from July 2018 to June 2021 in 20 hospitals and community health centers across China. Of the 894 screened patients, 560 eligible patients were randomly assigned to amlodipine/benazepril 5/10 mg (n = 282) or benazepril/hydrochlorothiazide 10/12.5 mg (n = 278), with 213 and 212 patients, respectively, who completed the study and had a valid repeat ambulatory BP recording during follow-up and were included in the efficacy analysis. The primary outcome was the change from baseline to 24 weeks of treatment in 24-h ambulatory systolic BP. Adverse events including symptoms and clinically significant changes in physical examinations and laboratory findings were recorded for safety analysis. RESULTS: In the efficacy analysis (n = 425), the primary outcome, 24-h ambulatory systolic BP reduction, was - 13.8 ± 1.2 mmHg in the amlodipine/benazepril group and - 12.3 ± 1.2 mmHg in the benazepril/hydrochlorothiazide group, with a between-group difference of - 1.51 (p = 0.36) mmHg. The between-group differences for major secondary outcomes were - 1.47 (p = 0.18) in 24-h diastolic BP, - 2.86 (p = 0.13) and - 2.74 (p = 0.03) in daytime systolic and diastolic BP, and - 0.45 (p = 0.82) and - 0.93 (p = 0.44) in nighttime systolic and diastolic BP. In the safety analysis (n = 560), the incidence rate of dry cough was significantly lower in the amlodipine/benazepril group than in the benazepril/hydrochlorothiazide group (5.3% vs 10.1%, p = 0.04). CONCLUSIONS: The amlodipine/benazepril and benazepril/hydrochlorothiazide dual therapies were comparable in ambulatory systolic BP lowering. The former combination, compared with the latter, had a greater BP-lowering effect in the daytime and a lower incidence rate of dry cough. TRIAL REGISTRATION: ClinicalTrials.gov, NCT03682692. Registered on 18 September 2018.