1
|
Wang Z, Luo S, Chen J, Jiao Y, Cui C, Shi S, Yang Y, Zhao J, Jiang Y, Zhang Y, Xu F, Xu J, Lin Q, Dong F. Multi-modality deep learning model reaches high prediction accuracy in the diagnosis of ovarian cancer. iScience 2024; 27:109403. [PMID: 38523785 PMCID: PMC10959660 DOI: 10.1016/j.isci.2024.109403] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/20/2023] [Revised: 12/29/2023] [Accepted: 02/28/2024] [Indexed: 03/26/2024] Open
Abstract
We evaluated the diagnostic performance of a multimodal deep-learning (DL) model for ovarian mass differential diagnosis. This single-center retrospective study included 1,054 ultrasound (US)-detected ovarian tumors (699 benign and 355 malignant). Patients were randomly divided into training (n = 675), validation (n = 169), and testing (n = 210) sets. The model was developed using ResNet-50. Three DL-based models were proposed for benign-malignant classification of these lesions: single-modality model that only utilized US images; dual-modality model that used US images and menopausal status as inputs; and multi-modality model that integrated US images, menopausal status, and serum indicators. After 5-fold cross-validation, 210 lesions were tested. We evaluated the three models using the area under the curve (AUC), accuracy, sensitivity, and specificity. The multimodal model outperformed the single- and dual-modality models with 93.80% accuracy and 0.983 AUC. The Multimodal ResNet-50 DL model outperformed the single- and dual-modality models in identifying benign and malignant ovarian tumors.
Collapse
Affiliation(s)
- Zimo Wang
- Second Clinical College of Jinan University, Department of Ultrasound, Shenzhen People’s Hospital, First Affiliated Hospital of Southern University of Science and Technology, Shenzhen Medical Ultrasound Engineering Center. Shenzhen, Guangdong 518020, China
| | - Shuyu Luo
- Second Clinical College of Jinan University, Department of Ultrasound, Shenzhen People’s Hospital, First Affiliated Hospital of Southern University of Science and Technology, Shenzhen Medical Ultrasound Engineering Center. Shenzhen, Guangdong 518020, China
| | - Jing Chen
- Second Clinical College of Jinan University, Department of Ultrasound, Shenzhen People’s Hospital, First Affiliated Hospital of Southern University of Science and Technology, Shenzhen Medical Ultrasound Engineering Center. Shenzhen, Guangdong 518020, China
| | - Yang Jiao
- Second Clinical College of Jinan University, Department of Ultrasound, Shenzhen People’s Hospital, First Affiliated Hospital of Southern University of Science and Technology, Shenzhen Medical Ultrasound Engineering Center. Shenzhen, Guangdong 518020, China
| | - Chen Cui
- Illuminate, LLC, 6B, Building 5, Tianyu Xiangshan Garden, No. 33, Nongxuan Road, Futian District, Donghai Community, Xiangmihu Street, Futian District, Shenzhen 518000, China
- Microport Prophecy, 1601 ZhangDong Road, ZJHi-Tech Park, Shanghai 201203, China
| | - Siyuan Shi
- Illuminate, LLC, 6B, Building 5, Tianyu Xiangshan Garden, No. 33, Nongxuan Road, Futian District, Donghai Community, Xiangmihu Street, Futian District, Shenzhen 518000, China
- Microport Prophecy, 1601 ZhangDong Road, ZJHi-Tech Park, Shanghai 201203, China
| | - Yang Yang
- Illuminate, LLC, 6B, Building 5, Tianyu Xiangshan Garden, No. 33, Nongxuan Road, Futian District, Donghai Community, Xiangmihu Street, Futian District, Shenzhen 518000, China
- Microport Prophecy, 1601 ZhangDong Road, ZJHi-Tech Park, Shanghai 201203, China
| | - Junyi Zhao
- University of Shanghai for Science and Technology, Shanghai 201203, China
| | - Yitao Jiang
- Illuminate, LLC, 6B, Building 5, Tianyu Xiangshan Garden, No. 33, Nongxuan Road, Futian District, Donghai Community, Xiangmihu Street, Futian District, Shenzhen 518000, China
- Microport Prophecy, 1601 ZhangDong Road, ZJHi-Tech Park, Shanghai 201203, China
| | - Yujuan Zhang
- Second Clinical College of Jinan University, Department of Ultrasound, Shenzhen People’s Hospital, First Affiliated Hospital of Southern University of Science and Technology, Shenzhen Medical Ultrasound Engineering Center. Shenzhen, Guangdong 518020, China
| | - Fanhua Xu
- Second Clinical College of Jinan University, Department of Ultrasound, Shenzhen People’s Hospital, First Affiliated Hospital of Southern University of Science and Technology, Shenzhen Medical Ultrasound Engineering Center. Shenzhen, Guangdong 518020, China
| | - Jinfeng Xu
- Second Clinical College of Jinan University, Department of Ultrasound, Shenzhen People’s Hospital, First Affiliated Hospital of Southern University of Science and Technology, Shenzhen Medical Ultrasound Engineering Center. Shenzhen, Guangdong 518020, China
| | - Qi Lin
- Second Clinical College of Jinan University, Department of Ultrasound, Shenzhen People’s Hospital, First Affiliated Hospital of Southern University of Science and Technology, Shenzhen Medical Ultrasound Engineering Center. Shenzhen, Guangdong 518020, China
| | - Fajin Dong
- Second Clinical College of Jinan University, Department of Ultrasound, Shenzhen People’s Hospital, First Affiliated Hospital of Southern University of Science and Technology, Shenzhen Medical Ultrasound Engineering Center. Shenzhen, Guangdong 518020, China
| |
Collapse
|
2
|
Liu J, Wen C, Hu M, Long J, Zhang J, Li M, Lin XC. Metabolomics analysis of MnO 2 nanosheets CDT for breast cancer cells and mechanism of cytotoxic action. RSC Adv 2023; 13:26630-26639. [PMID: 37681048 PMCID: PMC10481133 DOI: 10.1039/d3ra03992g] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/14/2023] [Accepted: 08/30/2023] [Indexed: 09/09/2023] Open
Abstract
Chemodynamic therapy (CDT) has received more and more attention as an emerging therapeutic strategy, especially transition metals with Fenton or Fenton-like activity have good effects in CDT research, manganese dioxide nanosheets (MnO2 NSs) and their complexes have become one of the most favored nanomaterials in CDT of tumors. CDT is mainly based on the role of reactive oxygen species (ROS) in tumor treatment, which have clear chemical properties and produce clear chemical reactions. However, their mechanism of interaction with cells has not been fully elucidated. Here, we performed CDT on mouse breast cancer cells (4T1) based on MnO2 NSs, extracted the metabolites from the 4T1 cells during the treatment, and analyzed the differences in metabolites by using high-resolution liquid chromatography-mass spectrometry (LC-MS). Untargeted metabolomics studies were conducted using the relevant data. This study mainly explored the changes in MnO2 NSs on the metabolite profile of 4T1 cells and their potential impact on tumor therapy, in order to determine the mechanism of action of MnO2 NSs in the treatment of breast cancer. The results of the study showed the presence of 11 different metabolites in MnO2 NSs CDT for 4T1 tumor cells, including phosphoserine, sphingine, phosphocholine, and stearoylcarnitine. These findings provide a deeper understanding of breast cancer treatment, and are beneficial for the further research and clinical application of CDT.
Collapse
Affiliation(s)
- Jian Liu
- Guangxi Key Laboratory of Information Materials, School of Materials Science and Engineering, Guilin University of Electronic Technology Guilin 541004 China
| | - Changchun Wen
- State Key Laboratory for Chemistry and Molecular Engineering of Medicinal Resources, School of Chemistry and Pharmaceutical Science, Guangxi Normal University Guilin 541004 China +86-773-2535678
| | - Miaomiao Hu
- Guangxi Key Laboratory of Information Materials, School of Materials Science and Engineering, Guilin University of Electronic Technology Guilin 541004 China
| | - Juan Long
- Guangxi Key Laboratory of Information Materials, School of Materials Science and Engineering, Guilin University of Electronic Technology Guilin 541004 China
| | - Jing Zhang
- Guangxi Key Laboratory of Information Materials, School of Materials Science and Engineering, Guilin University of Electronic Technology Guilin 541004 China
| | - Minzhe Li
- Guangxi Key Laboratory of Information Materials, School of Materials Science and Engineering, Guilin University of Electronic Technology Guilin 541004 China
| | - Xiang-Cheng Lin
- Guangxi Key Laboratory of Information Materials, School of Materials Science and Engineering, Guilin University of Electronic Technology Guilin 541004 China
| |
Collapse
|
3
|
Multiblock metabolomics: An approach to elucidate whole-body metabolism with multiblock principal component analysis. Comput Struct Biotechnol J 2021; 19:1956-1965. [PMID: 33995897 PMCID: PMC8086023 DOI: 10.1016/j.csbj.2021.04.015] [Citation(s) in RCA: 7] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Key Words] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/09/2021] [Revised: 03/20/2021] [Accepted: 04/04/2021] [Indexed: 12/16/2022] Open
Abstract
“Multiblock metabolomics” elucidates the global metabolic network in a whole body. “Multiblock metabolomics” combines LC/MS-based metabolomics with multiblock PCA. “Multiblock metabolomics” highlights and elicits organ-specific metabolism. TGs with less unsaturated fatty acids were highly accumulated in the diabetic liver.
Principal component analysis (PCA) is a useful tool for omics analysis to identify underlying factors and visualize relationships between biomarkers. However, this approach is limited in addressing life complexity and further improvement is required. This study aimed to develop a new approach that combines mass spectrometry-based metabolomics with multiblock PCA to elucidate the whole-body global metabolic network, thereby generating comparable metabolite maps to clarify the metabolic relationships among several organs. To evaluate the newly developed method, Zucker diabetic fatty (ZDF) rats (n = 6) were used as type 2 diabetic models and Sprague Dawley (SD) rats (n = 6) as controls. Metabolites in the heart, kidney, and liver were analyzed by capillary electrophoresis and liquid chromatography mass spectrometry, respectively, and the detected metabolites were analyzed by multiblock PCA. More than 300 metabolites were detected in the heart, kidney, and liver. When the metabolites obtained from the three organs were analyzed with multiblock PCA, the score and loading maps obtained were highly synchronized and their metabolism patterns were visually comparable. A significant finding in this study was the different expression patterns in lipid metabolism among the three organs; notably triacylglycerols with polyunsaturated fatty acids or less unsaturated fatty acids showed specific accumulation patterns depending on the organs.
Collapse
Key Words
- AMP, adenosine monophosphate
- Biomarkers
- CE/MS, capillary electrophoresis mass spectrometry
- CV, coefficient of variation
- ESI, electrospray ionization
- FABP, fatty acid-binding protein
- GC/MS, gas chromatography mass spectrometry
- LC/MS, liquid chromatography mass spectrometry
- Mass spectrometry
- Metabolomics
- Multiblock PCA
- PCA, principal component analysis
- PPAR, peroxisome proliferator-activated receptor
- QC, quality control
- SD, Sprague Dawley
- TCA, tricarboxylic acid. CoA, coenzyme A
- TG, triacylglycerol
- Type 2 Diabetes
- UPLC, ultra-performance liquid chromatography
- ZDF, Zucker diabetic fatty
Collapse
|