AI Tool Beats Expert Pathologists in Predicting Breast Cancer Outcomes
|
By LabMedica International staff writers Posted on 11 Dec 2023 |
|
Pathologists traditionally assess cancerous tissues in patients to guide treatment strategies. This evaluation, known as grading, examines the appearance of cancer cells and is crucial in determining a patient's treatment plan. This grading process, focused on the morphology of cancer cells, has been a standard practice for many years. Now, a study has found that a new artificial intelligence (AI) tool outperforms expert pathologists in predicting the progression of a patient's disease based on tissue evaluations.
Developed by researchers at Northwestern University (Evanston, IL, USA), this AI tool offers the potential to significantly alter the treatment path for breast cancer patients. The tool's ability to more accurately identify those patients currently categorized as high or intermediate risk but who will have a favorable long-term prognosis could lead to less aggressive chemotherapy treatments. This advancement is particularly significant given the adverse side effects associated with chemotherapy, such as nausea and potential heart damage. Previous studies have highlighted the role of non-cancerous cells, including immune cells and structural tissue cells, in cancer progression. This AI tool is pioneering in its comprehensive assessment of both cancerous and non-cancerous elements in invasive breast cancer.
To train this AI model, the researchers utilized a large-scale, international collaboration of medical students and pathologists. This network provided extensive human-generated annotations of cells and tissue structures within digital images of breast cancer tissues, collected through a website over several years. The AI system evaluates 26 different aspects of breast tissue, producing an overall prognostic score. The system also generates individual scores for the cancer, immune and stromal cells to explain the overall score to the pathologist. For example, in some patients, a favorable prognosis score may be due to properties of their immune cells, where for others it may be due to properties of their cancer cells. This information could be used by a patient’s care team in creating an individualized treatment plan.
Adoption of the new model could provide patients diagnosed with breast cancer with a more accurate estimate of the risk associated with their disease, empowering them to make informed decisions about their clinical care, according to the researchers. Additionally, this model may help in assessing therapeutic response, allowing treatment to be escalated or de-escalated depending on how the microscopic appearance of the tissue changes over time. For example, the tool may be able to recognize the effectiveness of a patient’s immune system in targeting cancer during chemotherapy, which could be used to reduce the duration or intensity of chemotherapy. Next, the scientists will evaluate this model prospectively to validate it for clinical use. The scientists also are working to develop models for more specific types of breast cancers like triple-negative or HER2-positive. Invasive breast cancer encompasses several different categories, and the important tissue patterns may vary across these categories.
“Our study demonstrates the importance of non-cancer components in determining a patient’s outcome,” said corresponding study author Lee Cooper, associate professor of pathology at Northwestern University Feinberg School of Medicine. “The importance of these elements was known from biological studies, but this knowledge has not been effectively translated to clinical use.”
“These patterns are challenging for a pathologist to evaluate as they can be difficult for the human eye to categorize reliably,” said Cooper, also a member of the Robert H. Lurie Comprehensive Cancer Center of Northwestern University. “The AI model measures these patterns and presents information to the pathologist in a way that makes the AI decision-making process clear to the pathologist.”
Related Links:
Northwestern University
Latest Pathology News
- AI-Based Model Predicts Kidney Cancer Therapy Response
- Sensitive and Specific DUB Enzyme Assay Kits Require Minimal Setup Without Substrate Preparation
- World’s First AI Model for Thyroid Cancer Diagnosis Achieves Over 90% Accuracy
- Breakthrough Diagnostic Approach to Significantly Improve TB Detection
- Rapid, Ultra-Sensitive, PCR-Free Detection Method Makes Genetic Analysis More Accessible
- Spit Test More Accurate at Identifying Future Prostate Cancer Risk
- DNA Nanotechnology Boosts Sensitivity of Test Strips
- Novel UV and Machine Learning-Aided Method Detects Microbial Contamination in Cell Cultures
- New Error-Corrected Method to Help Detect Cancer from Blood Samples Alone
- "Metal Detector" Algorithm Hunts Down Vulnerable Tumors
- Novel Technique Uses ‘Sugar’ Signatures to Identify and Classify Pancreatic Cancer Cell Subtypes
- Advanced Imaging Reveals Mechanisms Causing Autoimmune Disease
- AI Model Effectively Predicts Patient Outcomes in Common Lung Cancer Type
- AI Model Predicts Patient Response to Bladder Cancer Treatment
- New Laser-Based Method to Accelerate Cancer Diagnosis
- New AI Model Predicts Gene Variants’ Effects on Specific Diseases
Channels
Clinical Chemistry
view channel
Mass Spectrometry-Based Monitoring Technique to Predict and Identify Early Myeloma Relapse
Myeloma, a type of cancer that affects the bone marrow, is currently incurable, though many patients can live for over 10 years after diagnosis. However, around 1 in 5 individuals with myeloma have a high-risk... Read more
‘Brilliantly Luminous’ Nanoscale Chemical Tool to Improve Disease Detection
Thousands of commercially available glowing molecules known as fluorophores are commonly used in medical imaging, disease detection, biomarker tagging, and chemical analysis. They are also integral in... Read more
Low-Cost Portable Screening Test to Transform Kidney Disease Detection
Millions of individuals suffer from kidney disease, which often remains undiagnosed until it has reached a critical stage. This silent epidemic not only diminishes the quality of life for those affected... Read more
New Method Uses Pulsed Infrared Light to Find Cancer's 'Fingerprints' In Blood Plasma
Cancer diagnoses have traditionally relied on invasive or time-consuming procedures like tissue biopsies. Now, new research published in ACS Central Science introduces a method that utilizes pulsed infrared... Read moreMolecular Diagnostics
view channel
New Genetic Tool Analyzes Umbilical Cord Blood to Predict Future Disease
Children are experiencing metabolic problems at increasingly younger ages, placing them at higher risk for serious health issues later in life. There is a growing need to identify this risk from birth... Read more
Spinal Fluid Biomarker for Parkinson’s Disease Offers Early and Accurate Diagnosis
Parkinson’s disease is a neurodegenerative condition typically diagnosed at an advanced stage based on clinical symptoms, primarily motor disorders. However, by this time, the brain has already undergone... Read more
Hematology
view channel
New Scoring System Predicts Risk of Developing Cancer from Common Blood Disorder
Clonal cytopenia of undetermined significance (CCUS) is a blood disorder commonly found in older adults, characterized by mutations in blood cells and a low blood count, but without any obvious cause or... Read more
Non-Invasive Prenatal Test for Fetal RhD Status Demonstrates 100% Accuracy
In the United States, approximately 15% of pregnant individuals are RhD-negative. However, in about 40% of these cases, the fetus is also RhD-negative, making the administration of RhoGAM unnecessary.... Read more
Immunology
view channel
Stem Cell Test Predicts Treatment Outcome for Patients with Platinum-Resistant Ovarian Cancer
Epithelial ovarian cancer frequently responds to chemotherapy initially, but eventually, the tumor develops resistance to the therapy, leading to regrowth. This resistance is partially due to the activation... Read more
Machine Learning-Enabled Blood Test Predicts Immunotherapy Response in Lymphoma Patients
Chimeric antigen receptor (CAR) T-cell therapy has emerged as one of the most promising recent developments in the treatment of blood cancers. However, over half of non-Hodgkin lymphoma (NHL) patients... Read more
Microbiology
view channel
New Test Diagnoses Bacterial Meningitis Quickly and Accurately
Bacterial meningitis is a potentially fatal condition, with one in six patients dying and half of the survivors experiencing lasting symptoms. Therefore, rapid diagnosis and treatment are critical.... Read more
Handheld Device Delivers Low-Cost TB Results in Less Than One Hour
Tuberculosis (TB) remains the deadliest infectious disease globally, affecting an estimated 10 million people annually. In 2021, about 4.2 million TB cases went undiagnosed or unreported, mainly due to... Read more
New AI-Based Method Improves Diagnosis of Drug-Resistant Infections
Drug-resistant infections, particularly those caused by deadly bacteria like tuberculosis and staphylococcus, are rapidly emerging as a global health emergency. These infections are more difficult to treat,... Read more
Breakthrough Diagnostic Technology Identifies Bacterial Infections with Almost 100% Accuracy within Three Hours
Rapid and precise identification of pathogenic microbes in patient samples is essential for the effective treatment of acute infectious diseases, such as sepsis. The fluorescence in situ hybridization... Read moreTechnology
view channel
Disposable Microchip Technology Could Selectively Detect HIV in Whole Blood Samples
As of the end of 2023, approximately 40 million people globally were living with HIV, and around 630,000 individuals died from AIDS-related illnesses that same year. Despite a substantial decline in deaths... Read more
Pain-On-A-Chip Microfluidic Device Determines Types of Chronic Pain from Blood Samples
Chronic pain is a widespread condition that remains difficult to manage, and existing clinical methods for its treatment rely largely on self-reporting, which can be subjective and especially problematic... Read more
Innovative, Label-Free Ratiometric Fluorosensor Enables More Sensitive Viral RNA Detection
Viruses present a major global health risk, as demonstrated by recent pandemics, making early detection and identification essential for preventing new outbreaks. While traditional detection methods are... Read more
Industry
view channel
Cepheid and Oxford Nanopore Technologies Partner on Advancing Automated Sequencing-Based Solutions
Cepheid (Sunnyvale, CA, USA), a leading molecular diagnostics company, and Oxford Nanopore Technologies (Oxford, UK), the company behind a new generation of sequencing-based molecular analysis technologies,... Read more
Grifols and Tecan’s IBL Collaborate on Advanced Biomarker Panels
Grifols (Barcelona, Spain), one of the world’s leading producers of plasma-derived medicines and innovative diagnostic solutions, is expanding its offer in clinical diagnostics through a strategic partnership... Read more
