Artificial neural network detection of pancreatic cancer from proton (1H) magnetic resonance spectroscopy patterns of plasma metabolites
Abstract Background Routine screening to detect silent but deadly cancers such as pancreatic ductal adenocarcinoma (PDAC) can significantly improve survival, creating an important need for a convenient screening test. High-resolution proton (1H) magnetic resonance spectroscopy (MRS) of plasma identi...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Communications Medicine |
| Online Access: | https://doi.org/10.1038/s43856-024-00727-0 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832585445273239552 |
|---|---|
| author | Meiyappan Solaiyappan Santosh Kumar Bharti Raj Kumar Sharma Mohamad Dbouk Wasay Nizam Malcolm V. Brock Michael G. Goggins Zaver M. Bhujwalla |
| author_facet | Meiyappan Solaiyappan Santosh Kumar Bharti Raj Kumar Sharma Mohamad Dbouk Wasay Nizam Malcolm V. Brock Michael G. Goggins Zaver M. Bhujwalla |
| author_sort | Meiyappan Solaiyappan |
| collection | DOAJ |
| description | Abstract Background Routine screening to detect silent but deadly cancers such as pancreatic ductal adenocarcinoma (PDAC) can significantly improve survival, creating an important need for a convenient screening test. High-resolution proton (1H) magnetic resonance spectroscopy (MRS) of plasma identifies circulating metabolites that can allow detection of cancers such as PDAC that have highly dysregulated metabolism. Methods We first acquired 1H MR spectra of human plasma samples classified as normal, benign pancreatic disease and malignant (PDAC). We next trained a system of artificial neural networks (ANNs) to process and discriminate these three classes using the full spectrum range and resolution of the acquired spectral data. We then identified and ranked spectral regions that played a salient role in the discrimination to provide interpretability of the results. We tested the accuracy of the ANN performance using blinded plasma samples. Results We show that our ANN approach yields, in a cross validation-based training of 170 samples, a sensitivity and a specificity of 100% for malignant versus non-malignant (normal and disease combined) discrimination. The trained ANNs achieve a sensitivity and specificity of 87.5% and 93.1% respectively (AUC: ROC = 0.931, P-R = 0.854), with 45 blinded plasma samples. Further, we show that the salient spectral regions of the ANN discrimination correspond to metabolites of known importance for their role in cancers. Conclusions Our results demonstrate that the ANN approach presented here can identify PDAC from 1H MR plasma spectra to provide a convenient plasma-based assay for population-level screening of PDAC. The ANN approach can be suitably expanded to detect other cancers with metabolic dysregulation. |
| format | Article |
| id | doaj-art-a6a043f360ac40249d56d6e9afddffee |
| institution | Kabale University |
| issn | 2730-664X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Communications Medicine |
| spelling | doaj-art-a6a043f360ac40249d56d6e9afddffee2025-01-26T12:49:59ZengNature PortfolioCommunications Medicine2730-664X2025-01-015111010.1038/s43856-024-00727-0Artificial neural network detection of pancreatic cancer from proton (1H) magnetic resonance spectroscopy patterns of plasma metabolitesMeiyappan Solaiyappan0Santosh Kumar Bharti1Raj Kumar Sharma2Mohamad Dbouk3Wasay Nizam4Malcolm V. Brock5Michael G. Goggins6Zaver M. Bhujwalla7Department of Radiology, The Johns Hopkins University School of MedicineDepartment of Radiology, The Johns Hopkins University School of MedicineDepartment of Radiology, The Johns Hopkins University School of MedicineDepartment of Pathology, The Johns Hopkins University School of MedicineDepartment of Surgery, The Johns Hopkins University School of MedicineDepartment of Surgery, The Johns Hopkins University School of MedicineDepartment of Pathology, The Johns Hopkins University School of MedicineDepartment of Radiology, The Johns Hopkins University School of MedicineAbstract Background Routine screening to detect silent but deadly cancers such as pancreatic ductal adenocarcinoma (PDAC) can significantly improve survival, creating an important need for a convenient screening test. High-resolution proton (1H) magnetic resonance spectroscopy (MRS) of plasma identifies circulating metabolites that can allow detection of cancers such as PDAC that have highly dysregulated metabolism. Methods We first acquired 1H MR spectra of human plasma samples classified as normal, benign pancreatic disease and malignant (PDAC). We next trained a system of artificial neural networks (ANNs) to process and discriminate these three classes using the full spectrum range and resolution of the acquired spectral data. We then identified and ranked spectral regions that played a salient role in the discrimination to provide interpretability of the results. We tested the accuracy of the ANN performance using blinded plasma samples. Results We show that our ANN approach yields, in a cross validation-based training of 170 samples, a sensitivity and a specificity of 100% for malignant versus non-malignant (normal and disease combined) discrimination. The trained ANNs achieve a sensitivity and specificity of 87.5% and 93.1% respectively (AUC: ROC = 0.931, P-R = 0.854), with 45 blinded plasma samples. Further, we show that the salient spectral regions of the ANN discrimination correspond to metabolites of known importance for their role in cancers. Conclusions Our results demonstrate that the ANN approach presented here can identify PDAC from 1H MR plasma spectra to provide a convenient plasma-based assay for population-level screening of PDAC. The ANN approach can be suitably expanded to detect other cancers with metabolic dysregulation.https://doi.org/10.1038/s43856-024-00727-0 |
| spellingShingle | Meiyappan Solaiyappan Santosh Kumar Bharti Raj Kumar Sharma Mohamad Dbouk Wasay Nizam Malcolm V. Brock Michael G. Goggins Zaver M. Bhujwalla Artificial neural network detection of pancreatic cancer from proton (1H) magnetic resonance spectroscopy patterns of plasma metabolites Communications Medicine |
| title | Artificial neural network detection of pancreatic cancer from proton (1H) magnetic resonance spectroscopy patterns of plasma metabolites |
| title_full | Artificial neural network detection of pancreatic cancer from proton (1H) magnetic resonance spectroscopy patterns of plasma metabolites |
| title_fullStr | Artificial neural network detection of pancreatic cancer from proton (1H) magnetic resonance spectroscopy patterns of plasma metabolites |
| title_full_unstemmed | Artificial neural network detection of pancreatic cancer from proton (1H) magnetic resonance spectroscopy patterns of plasma metabolites |
| title_short | Artificial neural network detection of pancreatic cancer from proton (1H) magnetic resonance spectroscopy patterns of plasma metabolites |
| title_sort | artificial neural network detection of pancreatic cancer from proton 1h magnetic resonance spectroscopy patterns of plasma metabolites |
| url | https://doi.org/10.1038/s43856-024-00727-0 |
| work_keys_str_mv | AT meiyappansolaiyappan artificialneuralnetworkdetectionofpancreaticcancerfromproton1hmagneticresonancespectroscopypatternsofplasmametabolites AT santoshkumarbharti artificialneuralnetworkdetectionofpancreaticcancerfromproton1hmagneticresonancespectroscopypatternsofplasmametabolites AT rajkumarsharma artificialneuralnetworkdetectionofpancreaticcancerfromproton1hmagneticresonancespectroscopypatternsofplasmametabolites AT mohamaddbouk artificialneuralnetworkdetectionofpancreaticcancerfromproton1hmagneticresonancespectroscopypatternsofplasmametabolites AT wasaynizam artificialneuralnetworkdetectionofpancreaticcancerfromproton1hmagneticresonancespectroscopypatternsofplasmametabolites AT malcolmvbrock artificialneuralnetworkdetectionofpancreaticcancerfromproton1hmagneticresonancespectroscopypatternsofplasmametabolites AT michaelggoggins artificialneuralnetworkdetectionofpancreaticcancerfromproton1hmagneticresonancespectroscopypatternsofplasmametabolites AT zavermbhujwalla artificialneuralnetworkdetectionofpancreaticcancerfromproton1hmagneticresonancespectroscopypatternsofplasmametabolites |