Cancer DiagnosisNCT06822413
Raman Spectroscopy-Based Deep Learning Model for Early Pan-Cancer Early Diagnosis
An observational study of Cancer Diagnosis and Liver Cancer, Adult, run by Second Affiliated Hospital, Zhejiang University, School of Medicine at 4 sites in China.
Trial summary
The goal of this observational study is to explore whether a Raman-based, deep learning-assisted approach can be used to develop an effective method for early pan-cancer screening. The study includes healthy individuals, patients at risk of cancer, and patients with diagnosed cancers. Read more about this study
- Who is it for?
- Any ageHealthy volunteers can take part
- Conditions the study is for
- Cancer Diagnosis, Liver Cancer, Adult, Cancer Screening
- How many people
- 600 participants
- Where
- 4 sitesChina
- Study dates
- 1 Sep 2022to 28 Jul 2025
- How long will I take part?
- 1 Year
- Phase
- Observational
- Are there results?
- Not yet: the study is under way
Key requirements
Who can take part, as listed by the sponsor. Only the study team can confirm whether you are eligible, so take this list to your doctor.
- Ages Any age
- All sexes
- Healthy volunteers accepted
- Child, Adult, Older adult
Study population: Pan-cancer patients from Zhejiang, Jiangxi and Shanghai province
Who may be able to join
- Histopathological diagnosis of malignant tumors, including colorectal cancer, gastric cancer, hepatic cancer, pancreatic cancer, and esophageal cancer.
- Patients in normal physiological conditions without any malignant tumors or precancerous lesions.
- Patients with malignant tumor without recieving any interventions, including chemotherapy, surgery, radiotherapy, immunotherapy or other anti-tumor treatments.
- Patients with a histopathological diagnosis of any precancerous lesions or non-malignant disease.
Who cannot join
- Patients with metastatic tumors or in the condition with two or more kinds of malignant tumors at the same time
- Post-cancer treatment patients.
Trial locations and contacts
4 sites in 1 country. Contact the study team or a site near you to ask about taking part.
China4 sites, 4 recruiting
- Recruiting
The Second Affiliated Hospital of Zhejiang University School of Medicine
Hangzhou, Zhejiang, 310009
Kefeng Ding, +86 13906504783, dingkefeng@zju.edu.cn
- Recruiting
The First Affiliated Hospital to Nanchang University
Nanchang, Jiangxi, 330006
Yuhuan Jiang, +86 18720998212, 18166043076@163.com
- Recruiting
The Second Affiliated Hospital to Nanchang University
Nanchang, Jiangxi, 330008
Xiaozhong Wang, +86 0791-86300410, xiaozhongwangncu@163.com
- Recruiting
Huashan Hospital Affiliated to Fudan University
Shanghai, Shanghai Municipality, 200040
Ming Guan, +86 19901643902, guanming88@yahoo.com
About this study
Official title: A Novel Raman Spectroscopy-Based Method for Pan-Cancers Early Diagnosis Supported by Deep Learning: A Prospective, Single-Arm, Multicentre Study
The goal of this observational study is to explore whether a Raman-based, deep learning-assisted approach can be used to develop an effective method for early pan-cancer screening. The study includes healthy individuals, patients at risk of cancer, and patients with diagnosed cancers. The main questions it aims to answer are:
- Evaluating the deep-learning model's accuracy and specificity in identifying cancer-specific features in Raman spectral data and determining whether this method can accurately classify patients based on risk.
- Identifying which model is more adaptable to the Raman spectrum
- Providing an interpretable analysis of the model-generated diagnosis Participants are already being diagnosed and follow-up to determine the type of cancer.
Read the detailed description
This study aims to explore the use of deep learning models for classifying patients based on Raman spectroscopy analysis of blood samples, distinguishing between individuals in physiological conditions and patients with various types of precancerous conditions or malignant tumors. The study is conducted through a multi-center collaboration, where blood samples are collected from both healthy participants and patients with histopathologically diagnosed precancerous conditions or primary malignant tumors.
All blood samples are obtained from patients' routine clinical blood tests conducted during hospital admission or other necessary medical evaluations. The spectral data undergo a rigorous preprocessing pipeline, which includes alignment resampling to standardize the data, baseline removal to eliminate unwanted variations, and normalization to ensure uniformity across all samples. The data is optimized for deep learning model training.
Various deep-learning models are then employed to analyze the processed Raman spectra and develop a classification system to distinguish between pan-cancer cases and healthy controls. The preprocessed dataset is partitioned into three subsets for model training and performance evaluation: 80% for training, 10% for validation, and 10% for testing. These datasets are used for model training to identify patterns in the spectral data that correlate with the presence of specific cancers or a healthy state, enabling accurate classification.
To enhance the interpretability of deep learning models, Grad-CAM (Gradient-weighted Class Activation Mapping) is used to visualize the models' decision-making processes. This allows the identification of the Raman spectra regions that are more influential in the model's classification decision, providing a transparent understanding of how the model differentiates between the various classes.
Ultimately, this study aims to demonstrate the potential of Raman spectroscopy combined with deep learning techniques as a non-invasive, accurate, and interpretable method for cancer detection and classification, with implications for early diagnosis and personalized treatment strategies.
- Conditions
- Cancer Diagnosis, Liver Cancer, Adult, Cancer Screening, Colorectal Cancer (CRC), Gastric Cancers, Normal Physiology
- Being tested
- No Interventions
- Keywords
- Pan-cancer, Deep Learning Models, Cancer Screening, Raman Spectroscopy, Colorectal Cancer, Pancreatic Cancer, Gastric Cancer, Esophageal Cancer, malignant tumour, Precancerous Condtions, Pancreatitis, Colorectal Adenoma, Gastirc Ulcer, Oesophagitis, Cirrhoses
- Medical subject headings
- Carcinoma, Hepatocellular, Colorectal Neoplasms, Stomach Neoplasms, Pancreatic cancer, adult, Esophageal Neoplasms, Neoplasms, Precancerous Conditions, Pancreatitis
What participants receive
What participants receive. In a randomised study each person is assigned to one group by chance.
No InterventionsOther
All blood samples from participating patients were obtained from routine clinical blood tests conducted during hospital admission or other necessary medical evaluations, followed by serum extraction.
| Study group | Role | What they receive |
|---|---|---|
| Normal Physiology | Patients without cancers or precancerous lesion Receives: Other: No Interventions | |
| Colorectal Cancer | Patients diagnosed with colorectal cancer (Pre-intervention) Receives: Other: No Interventions | |
| Gastric Cancer | Patients diagnosed with gastric cancer (Pre-intervention) Receives: Other: No Interventions | |
| Hepatic Cancer | Patients diagnosed with hepatic cancer (Pre-intervention) Receives: Other: No Interventions | |
| Oesophageal | Patients diagnosed with oesophageal cancer (Pre-intervention) | |
| Pancreatic Cancer | Patients diagnosed with pancreatic cancer (Pre-intervention) Receives: Other: No Interventions | |
| Gastric Ulcer | Patients with gastric ulcers without any cancer Receives: Other: No Interventions | |
| Colorectal Adenoma | Patients with colorectal adenoma without any cancer Receives: Other: No Interventions | |
| Liver Cirrhosis | Patients with liver cirrhosis without any cancer Receives: Other: No Interventions | |
| Pancreatitis | Patients with pancreatitis without any cancer Receives: Other: No Interventions | |
| Oesophagitis | Patients with oesophagitis without any cancer Receives: Other: No Interventions |
What is being measured
The primary outcome is the main question the study is designed to answer.
A Deep Learning Model for High-Accuracy Pan-Cancer Classification
Establish deep learning models with high specificity and sensitivity for pan-cancer classification, capable of distinguishing different pan-cancer types (Distinguish between patients in physiological conditions, precancerous lesion and malignant tumour) based on Raman spectroscopy.
Measured: From patient enrollment to the completion of model construction, expected to be finalized within two months after data collection.
Secondary outcomes (1)
Raman Shift Characteristics for Model Decision Interpretation and Visualization
Performing interpretable analysis of the diagnosis derived from the primary outcome using Grad-CAM to visualize and illustrate the model's decision-making process.
Measured: From the end of model construction to the end of model interpretable analysis - expected 2 months after model construction
Timeline
From the start of the study to its completion; the mark is today. Estimated dates are the sponsor’s plan.
- First posted12 Feb 2025
- Study start1 Sep 2022
- Primary completion15 May 2025 (estimated)
- Study completion28 Jul 2025 (estimated)
Resources
- Official record on ClinicalTrials.govThe registry entry this page is built from, with its full change history.
- Other trials for Cancer DiagnosisStudies of the same condition, open and under way.
- What the trial phases meanHow a treatment moves from first tests in people to approval.
More details
For doctors and researchers: how the study is designed, who runs it, and its registry IDs.
Study design
- Study type
- Observational
- Observational model
- Cohort
- Time perspective
- Prospective
- Enrolment
- 600 participants (estimated)
- Target duration
- 1 Year
Sponsor and investigators
- Lead sponsor
- Second Affiliated Hospital, Zhejiang University, School of Medicine
- Sponsor type
- University, hospital or other
- Collaborators
- The First Affiliated Hospital of Nanchang University, Second Affiliated Hospital of Nanchang University, Huashan Hospital
- Responsible party
- Sponsor
- Investigators
- Kefeng Ding, MD, Study chair, Department of Colorectal Surgery, The Second Hospital of Zhejiang University School of Medicine
IDs, dates and publications
- ClinicalTrials.gov ID
- NCT06822413
- Sponsor's protocol ID
- 2024-1060
- Status last verified
- Jan 2025
- First submitted
- 5 Feb 2025
- Last updated
- 24 Apr 2025
- Results posted
- No
- Data monitoring committee
- No
- FDA-regulated drug
- No
- FDA-regulated device
- No
- Individual data sharing
- No
Study at a glance
From the registry record, last updated by the sponsor on 24 Apr 2025. Recruitment status is as the sponsor reported it: confirm with the study team.
- Official title
- A Novel Raman Spectroscopy-Based Method for Pan-Cancers Early Diagnosis Supported by Deep Learning: A Prospective, Single-Arm, Multicentre Study
- ClinicalTrials.gov ID
- NCT06822413
- Acronym / sponsor ID
- 2024-1060
- Conditions
- Cancer Diagnosis, Liver Cancer, Adult, Cancer Screening, Colorectal Cancer (CRC), Gastric Cancers, Normal Physiology
- Keywords
- Pan-cancer, Deep Learning Models, Cancer Screening, Raman Spectroscopy, Colorectal Cancer, Pancreatic Cancer, Gastric Cancer, Esophageal Cancer
- Study type
- Observational
- Recruitment status
- Recruiting
- Enrolment
- 600 participants (estimated)
- Lead sponsor
- Second Affiliated Hospital, Zhejiang University, School of MedicineUniversity, hospital or other
- Collaborators
- The First Affiliated Hospital of Nanchang University, Second Affiliated Hospital of Nanchang University, Huashan Hospital
- Study start
- 1 Sep 2022 (actual)
- Primary completion
- 15 May 2025 (estimated)
- Study completion
- 28 Jul 2025 (estimated)
- First posted
- 12 Feb 2025 (actual)
- Results
- Not posted in the source record
Clinical summary
The research question as the sponsor registered it. This describes what the study plans to test, not what it found.
The goal of this observational study is to explore whether a Raman-based, deep learning-assisted approach can be used to develop an effective method for early pan-cancer screening. The study includes healthy individuals, patients at risk of cancer, and patients with diagnosed cancers. The main questions it aims to answer are:
- Evaluating the deep-learning model's accuracy and specificity in identifying cancer-specific features in Raman spectral data and determining whether this method can accurately classify patients based on risk.
- Identifying which model is more adaptable to the Raman spectrum
- Providing an interpretable analysis of the model-generated diagnosis Participants are already being diagnosed and follow-up to determine the type of cancer.
Detailed description
This study aims to explore the use of deep learning models for classifying patients based on Raman spectroscopy analysis of blood samples, distinguishing between individuals in physiological conditions and patients with various types of precancerous conditions or malignant tumors. The study is conducted through a multi-center collaboration, where blood samples are collected from both healthy participants and patients with histopathologically diagnosed precancerous conditions or primary malignant tumors.
All blood samples are obtained from patients' routine clinical blood tests conducted during hospital admission or other necessary medical evaluations. The spectral data undergo a rigorous preprocessing pipeline, which includes alignment resampling to standardize the data, baseline removal to eliminate unwanted variations, and normalization to ensure uniformity across all samples. The data is optimized for deep learning model training.
Various deep-learning models are then employed to analyze the processed Raman spectra and develop a classification system to distinguish between pan-cancer cases and healthy controls. The preprocessed dataset is partitioned into three subsets for model training and performance evaluation: 80% for training, 10% for validation, and 10% for testing. These datasets are used for model training to identify patterns in the spectral data that correlate with the presence of specific cancers or a healthy state, enabling accurate classification.
To enhance the interpretability of deep learning models, Grad-CAM (Gradient-weighted Class Activation Mapping) is used to visualize the models' decision-making processes. This allows the identification of the Raman spectra regions that are more influential in the model's classification decision, providing a transparent understanding of how the model differentiates between the various classes.
Ultimately, this study aims to demonstrate the potential of Raman spectroscopy combined with deep learning techniques as a non-invasive, accurate, and interpretable method for cancer detection and classification, with implications for early diagnosis and personalized treatment strategies.
Study design
- Observational model
- Cohort
- Time perspective
- Prospective
- Target follow-up
- 1 Year
- Number of arms
- 11
| Arm | Type | Receives |
|---|---|---|
| Normal Physiology | – | Other: No InterventionsPatients without cancers or precancerous lesion |
| Colorectal Cancer | – | Other: No InterventionsPatients diagnosed with colorectal cancer (Pre-intervention) |
| Gastric Cancer | – | Other: No InterventionsPatients diagnosed with gastric cancer (Pre-intervention) |
| Hepatic Cancer | – | Other: No InterventionsPatients diagnosed with hepatic cancer (Pre-intervention) |
| Oesophageal | – | –Patients diagnosed with oesophageal cancer (Pre-intervention) |
| Pancreatic Cancer | – | Other: No InterventionsPatients diagnosed with pancreatic cancer (Pre-intervention) |
| Gastric Ulcer | – | Other: No InterventionsPatients with gastric ulcers without any cancer |
| Colorectal Adenoma | – | Other: No InterventionsPatients with colorectal adenoma without any cancer |
| Liver Cirrhosis | – | Other: No InterventionsPatients with liver cirrhosis without any cancer |
| Pancreatitis | – | Other: No InterventionsPatients with pancreatitis without any cancer |
| Oesophagitis | – | Other: No InterventionsPatients with oesophagitis without any cancer |
Who may qualify
- Sex
- All
- Healthy volunteers
- Accepted
- Age groups
- Child, Adult, Older adult
- Study population
- Pan-cancer patients from Zhejiang, Jiangxi and Shanghai province
Key inclusion criteria (4 listed)
- Histopathological diagnosis of malignant tumors, including colorectal cancer, gastric cancer, hepatic cancer, pancreatic cancer, and esophageal cancer.
- Patients in normal physiological conditions without any malignant tumors or precancerous lesions.
- Patients with malignant tumor without recieving any interventions, including chemotherapy, surgery, radiotherapy, immunotherapy or other anti-tumor treatments.
- Patients with a histopathological diagnosis of any precancerous lesions or non-malignant disease.
Key exclusion criteria (2 listed)
- Patients with metastatic tumors or in the condition with two or more kinds of malignant tumors at the same time
- Post-cancer treatment patients.
Eligibility is decided by the study team after screening; this overview does not establish that a patient qualifies. Full inclusion and exclusion criteria.
Interventions
| Intervention | Type | Arms |
|---|---|---|
| No InterventionsAll blood samples from participating patients were obtained from routine clinical blood tests conducted during hospital admission or other necessary medical evaluations, followed by serum extraction. | Other | Colorectal Adenoma, Colorectal Cancer, Gastric Cancer, Gastric Ulcer, Hepatic Cancer, Liver Cirrhosis, Normal Physiology, Oesophagitis, Pancreatic Cancer, Pancreatitis |
Primary outcome
A Deep Learning Model for High-Accuracy Pan-Cancer Classification
Time frame: From patient enrollment to the completion of model construction, expected to be finalized within two months after data collection.
Establish deep learning models with high specificity and sensitivity for pan-cancer classification, capable of distinguishing different pan-cancer types (Distinguish between patients in physiological conditions, precancerous lesion and malignant tumour) based on Raman spectroscopy.
1 secondary outcome
Raman Shift Characteristics for Model Decision Interpretation and Visualization
Time frame: From the end of model construction to the end of model interpretable analysis - expected 2 months after model construction
Results and safety
This study is still under way. Results are not available in the source record yet.
Research links
- Official record on ClinicalTrials.govLast updated by the sponsor 24 Apr 2025.
- Individual participant dataSharing planned: No
Related trials for Cancer Diagnosis
RecruitingObservational study
International PPB/DICER1 Registry
Pleuropulmonary Blastoma, Sertoli-Leydig Cell Tumor
Recruiting
68Ga-XMFH01 PET/Fluorescence Imaging in Prostate Cancer
Prostate Cancer (Diagnosis), ACP3
Recruiting
MRD Monitoring in Colorectal Cancer Using ctDNA
Colorectal Neoplasms, Colorectal Cancer (Diagnosis)
Not yet recruitingObservational study
Investigation of an Intelligent Centre-adaptive Multi-modal Fusion Framework (Cad- MMFF) to Overcome Unnecessary Prostate Biopsies and Optimize MRI Utilization
Prostate Cancer (Diagnosis)
RecruitingPhase 2
Analgesic Efficacy and Safety of Topical VMD-3866 Gel in Management of Pain Induced by Chemotherapy (CIPN)
Chemotherapy-induced Peripheral Neuropathy, Chemotherapy-induced Neuropathic Pain
Referral and contact
AzTrials does not enrol participants or take referrals. Contact the study team or a site listed below; they decide who can take part.
Kefeng Ding, MD study chair
Department of Colorectal Surgery, The Second Hospital of Zhejiang University School of Medicine
4 sites in 1 country: see every site and its status.
Questions about this trial
What is this clinical trial studying?
An observational study of Cancer Diagnosis and Liver Cancer, Adult, run by Second Affiliated Hospital, Zhejiang University, School of Medicine at 4 sites in China.
The full registered description is in the About this study section and the official record.
Who may be eligible to take part?
The sponsor lists 4 inclusion and 2 exclusion criteria. Eligibility is decided by the study team after screening, so read the full criteria and contact a listed site.
Is this clinical trial currently recruiting?
The record says: looking for participants now, as of the sponsor's last update on 24 Apr 2025. Status can change between updates, so confirm with the study contact before making plans.
Where is the study taking place?
The record lists 4 sites in China. Whether a site is taking part right now should be confirmed with that site. See every site.
What are the possible benefits and risks?
They depend on the study and the treatment, and no study can promise a benefit. The study team explains the known risks during informed consent, before anyone joins; the record itself does not list them.
Are results available for this study?
This study is still under way. Results are not available in the source record yet.
How can a doctor refer a patient or contact the research team?
Contact Jiasheng Xu, MD (+86 18720996980, 1821286450@qq.com), or a site near the patient. AzTrials does not enrol participants or take referrals.
What does the primary outcome measure?
A Deep Learning Model for High-Accuracy Pan-Cancer Classification (time frame: From patient enrollment to the completion of model construction, expected to be finalized within two months after data collection.). It is what the study was designed to measure, not a finding.
Where can I read the original study information?
Does a listing mean the treatment is approved or proven to work?
No. A listing means the study is registered. It does not show that the treatment is safe, works, or is approved by a regulator.
How often is this information updated?
AzTrials copies changed records from ClinicalTrials.gov every night and reloads the whole registry every week. The sponsor last updated this record on 24 Apr 2025; AzTrials last refreshed its copy on 26 Oct 2026.