An observational study in Cancer Diagnosis, Liver Cancer, Adult and Cancer Screening, sponsored by Second Affiliated Hospital, School of Medicine, Zhejiang University. Recruiting at 4 sites in China. Per ClinicalTrials.gov, last updated 2025-04-24.
Sponsored by Second Affiliated Hospital, School of Medicine, Zhejiang University · Observational
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:
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.
3,648 studies on the registry are indexed under Carcinoma, Hepatocellular; 1,061 are open to participants now.
This study's planned enrollment of 600 is above the median of 200 across 850 observational studies indexed under Carcinoma, Hepatocellular.
Browse Carcinoma, Hepatocellular studies →Second Affiliated Hospital, School of Medicine, Zhejiang University is the lead sponsor of 1,047 studies on the registry; 502 are open to participants now.
Counted across the registry records on this site, refreshed daily.
Pan-cancer patients from Zhejiang, Jiangxi and Shanghai province
Go through the criteria one by one — yes, no or not sure — and take the list to your doctor or the study team. Kept in this browser only.
Exclusion Criteria:
Underlined terms in the criteria open these too. Explained by clinicaltrials.gg, not part of the registry record. The study team decides who can take part.
Cancer that has spread from where it began to other parts of the body. “Metastatic” cancer is cancer that has spread this way.
Metastases
Cancer that has spread from where it began to other parts of the body. “Metastatic” cancer is cancer that has spread this way.
Explained by clinicaltrials.gg, not part of the registry record. The study team decides who can take part.
Patients without cancers or precancerous lesion
Other: No Interventions
Patients diagnosed with colorectal cancer (Pre-intervention)
Other: No Interventions
Patients diagnosed with gastric cancer (Pre-intervention)
Other: No Interventions
Patients diagnosed with hepatic cancer (Pre-intervention)
Other: No Interventions
Patients diagnosed with oesophageal cancer (Pre-intervention)
Patients diagnosed with pancreatic cancer (Pre-intervention)
Other: No Interventions
Patients with gastric ulcers without any cancer
Other: No Interventions
Patients with colorectal adenoma without any cancer
Other: No Interventions
Patients with liver cirrhosis without any cancer
Other: No Interventions
Patients with pancreatitis without any cancer
Other: No Interventions
Patients with oesophagitis without any cancer
Other: No Interventions
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.
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.
Time frame: From patient enrollment to the completion of model construction, expected to be finalized within two months after data collection.
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.
Time frame: From the end of model construction to the end of model interpretable analysis - expected 2 months after model construction
Plan to share: No
No publications or documents are linked to this record.
Started Sep 2022 (actual). Primary completion is estimated for May 2025, 32 months after the start.
Of 302 non-industry observational studies under Carcinoma, Hepatocellular, half reached primary completion within 54 months of starting (the median), counting those still running; a quarter within 35 and three quarters within 114. This study's planned 32 months is below that.
Counting every sponsor, half of 351 studies reached it within 51 months; a quarter within 32 and three quarters within 108.
How these figures are worked out, and which studies are left out of them.
Eligibility is decided by the study team. Share this record with your doctor or contact the team directly.
Contact study teamGet an email when the registry record changes — status, dates, results — or when someone posts here.
Sign in to followQuestions and observations about this study, from anyone following it. Not medical advice, and not a channel to the study team — their contact details are on the registry record.
Sign in to join the discussion. Reading takes no account; posting does. You choose a display name, and a pseudonym is the default.
Nothing here yet. If you are running this trial, taking part in it, or weighing whether to, this is the place to say so.
Second Affiliated Hospital, School of Medicine, Zhejiang University →