Neoplasms

All Conditions

Nervous System Diseases

Gland and Hormone Related Diseases

Adenoma

Pituitary Diseases

Pituitary Neoplasms

Neoplasms, Glandular and Epithelial

Neoplasms by Histologic Type

Hypothalamic Diseases

Brain Diseases

Central Nervous System Diseases

Endocrine System Diseases

Endocrine Gland Neoplasms

Hypothalamic Neoplasms

Supratentorial Neoplasms

Brain Neoplasms

Central Nervous System Neoplasms

Nervous System Neoplasms

Results of artificial intelligence model will be compared with the gold standard

Artificial intelligence model

Yao Zhao

Refractory pituitary adenoma is characterized by invasive tumor growth, continuous growth and/or hormone hypersecretion in spite of standardized multi-modal treatment such as surgeries, medications or radiations. Quality of life or even lives are threatened by these tumors. According to the 2017 World Health Organization's new classification guideline of pituitary adenoma, patients have to suffer from symptoms or complications caused by these tumors, to bear a heavy financial burden, and to accept additional therapeutic side effects when the diagnosis of "refractory pituitary adenoma" is made. If refractory pituitary adenoma could be predicted at early stage, these patients would be able to have a more frequent clinical follow-up, receive multiple effective treatment as early as possible, or even be enrolled in clinical trials of investigational medications, so as to prevent or delay the recurrence or persistent of the tumor growth. Therefore, the unmet clinical need falls into an early prediction system for refractory pituitary adenomas, which could provide accurate guidance for subsequent treatment in the early stage. The investigators have constructed a pituitary adenoma database including clinical data, radiological images, pathological images and genetic information. The investigators are proposing a study using machine learning to extract features from these multi-dimensional, multi-omics data, which could be further used to train a prediction model for the risk of refractory pituitary adenoma. The proposed model would also be validated in another prospectively collected database. The established model would be able to identify potential medication targets and provide guidance for personalized therapy of refractory pituitary adenoma.

Radiomic and Pathomic Study of Pituitary Adenoma Using Machine Learning

Machine Learning Modeling the Risk of Refractory Pituitary Adenoma Using Radiomic and Pathomic Data

Predicting the development of refractory pituitary adenoma after the first surgery

Predicting endocrine remission after Gamma Knife surgery in Growth Hormone secreting pituitary adenoma

Predicting immunostaining in patients with non-functioning pituitary adenoma using H\&E stained images

Predicting relapse or regrowth of a non-functioning pituitary adenoma after the first surgery

Predicting endocrinopathy which warrant replacement after pituitary adenoma resection

Predicting surgical difficulty and complications using pre-surgical radiomic features

Huashan Hospital

Clinical Professor

Symptoms and General Pathology

Digestive System Diseases

Pathologic Complete Response

Rectal Neoplasms

Colorectal Neoplasms

Intestinal Neoplasms

Gastrointestinal Neoplasms

Digestive System Neoplasms

Gastrointestinal Diseases

Intestinal Diseases

Rectal Diseases

Disease Progression

Disease Attributes

the patients with locally advanced rectal cancer (LARC) finished the neoadjuvant treatment, and not yet receive total mesorectum excision (TME) surgery will be enrolled. The post-neoadjuvant treatment MRI images features of each enrolled patients will be captured by the artificial intelligence system, and evaluated by experienced radiologists as well. Blind to the pathologic report of TME specimen, both approaches further respectively yield a predicted pathologic response to neoadjuvant treatment for each enrolled patient, shown as pCR or non-pCR.

The tumor ROI in the post- neoadjuvant treatment MRI images will be manually delineated, and further subjected to the AI prediction system arm to verify the predictive accuracy of this AI prediction system in identifying the pCR individuals from non-pCR patients with LARC.

artificial intelligence prediction system

The enrolled patients will be assigned to the trained experienced radiologists to evaluate their predictive accuracy in identifying the pCR individuals from non-pCR patients

the radiologists

Xiangbo Wan, MD, PhD

Xinjuan Fan, MD, PhD

Zhenhui Li, MD

Weidong Han, MD, PhD

In this study, investigators seek for a better way to identify the potential pathologic complete response (pCR) patients form non-pCR patients with locally advanced rectal cancer (LARC), based on their post-neoadjuvant treatment Magnetic Resonance Imaging (MRI) data.

Previously, a post neoadjuvant treatment MRI based radiomics AI model had been constructed and trained. Here, the predictive power of this artificial intelligence system and expert radiologist to identify pCR patients from non-pCR LARC patients will be compared in this prospective, multicenter, back-to-back clinical study

This is a multicenter, prospective, observational clinical study for seeking out a better way to predict the pathologic complete response (pCR) in patients with locally advanced rectal cancer (LARC) based on the post-neoadjuvant treatment Magnetic Resonance Imaging (MRI) data. Patients who have been pathologically diagnosed as rectal adenocarcinoma and defined as clinical II-III stage will be enrolled from the Sixth Affiliated Hospital of Sun Yat-sen University, Sir Run Run Shaw Hospital and the Third Affiliated Hospital of Kunming Medical College. All participants should follow a standard treatment protocol, including neoadjuvant treatment, total mesorectum excision (TME) surgery. Patients with LARC who received neoadjuvant treatment will be enrolled and their post-neoadjuvant treatment MRI images will be used to predict their pathologic response (pCR vs. non-pCR). The artificial intelligence prediction system and the expert radiologist will define the pathologic response as pCR or non-pCR, respectively. The pathologist will provide the final pathology report of TME surgery specimen (pCR or non-pCR) as a standard. The predictive efficacy of these two back-to-back approaches generated will be compared in this multicenter, prospective clinical study.

Post-Neoadjuvant Treatment MRI Based AI System to Predict pCR for Rectal Cancer

A Post-Neoadjuvant Treatment MRI Based AI System to Predict Pathologic Complete Response for Patients With Rectal Cancer: A Multicenter, Prospective Clinical Study

The area under curve (AUC) of Receiver Operating Characteristic (ROC) curves of AI prediction system and expert radiologists in identifying the pCR candidates from non-pCR individuals among neoadjuvant chemotherapy or chemoradiotherapy treated LARC patients will be calculated respectively.

The specificity of AI prediction system and expert radiologists in identifying the pCR candidates from non-pCR individuals among neoadjuvant chemotherapy or chemoradiotherapy treated LARC patients will be calculated respectively.

The sensitivity of AI prediction system and expert radiologists in identifying the pCR candidates from non-pCR individuals among neoadjuvant chemotherapy or chemoradiotherapy treated LARC patients will be calculated respectively.

Study title	NCT ID	Conditions	Interventions	Eligibility	Organization	Link
Radiomic and Pathomic Study of Pituitary Adenoma Using Machine Learning	NCT05108064	Pituitary Neopl...	Artificial inte...	18 Years -	Huashan Hospital
Post-Neoadjuvant Treatment MRI Based AI System to Predict pCR for Rectal Cancer	NCT04278274	Rectal Cancer	artificial inte... the radiologist...	18 Years - 75 Years	Sixth Affiliated Hospital, Sun Yat-sen University

Spots Global Cancer Trial Database for artificial intelligence model