AI for Cancer Diagnosis - General
Artificial intelligence models exist to identify cancer in its development stage. Theyt can speed up the disease diagnosis and fast-track the patient’s condition to provide quick treatments with an early detection process. AI can detect cancer risks when the condition is not fatal and save lives.
CancerAid: Cancer Support and Monitoring
CancerAid’s AI app supports cancer patients by providing personalized information, monitoring symptoms, and offering a virtual support system.
Freenome: Best for Cancer Detection
Freenome is a pioneering AI medical software that focuses on developing high-quality diagnostic tests for the early detection and treatment of diseases, especially cancer, through a simple blood draw. Through their multiomics platform, Freenome’s tests analyze disease-associated patterns in the blood, enabling the identification of suspicious molecular patterns associated with tumors. This breakthrough technology bridges the accessibility gap by offering a standard blood test that can detect cancer at its earliest stages, significantly improving the chances of successful treatment.
Highlights
Multiomics Approach: Combines nucleotide and protein data for a complete view of a patient’s cancer, enabling early detection of pre-cancerous conditions.
Holistic Picture of Cancer: Provides a thorough understanding of a patient’s cancer, allowing for personalized treatment plans.
Wide Application: Has the potential to detect multiple types of cancer, expanding its impact in cancer diagnostics.
Acceptable and Convenient: Uses a blood-based testing approach, offering a non-invasive, patient-friendly alternative to traditional screenings.
High Funding and Collaboration: Backed by substantial funding and collaborations with industry giants like Google, Novartis, and Roche.
Preemptive Cancer Detection: Identifies early cancer signals, allowing for proactive interventions, saving lives, and improving patient outcomes.
ImageDx
Reveal Biosciences, Inc., an established AI data provider, has developed a powerful and dynamic SaaS pathology platform called imageDx™. Equipped with a full service automated laboratory histopathology lab, Reveal is uniquely positioned as a “one stop solution” for generating quantitative data from tissue samples with imageDx™ at its core. The imageDx™ platform provides cloud-based image management and AI-powered digital assays to a wide user base.
imageDx™ is available for small to large teams enterprise wide. To date, imageDx™ has delivered data to over 400 leading bio-pharmaceutical companies globally. This includes 7 out of the top 10 Pharmaceutical Companies.
Users upload images onto the imageDx™ platform for remote collaboration and large scale analysis. Next, an integrated quality control algorithm called imageQC™ is deployed across all images to assess focus, tissue and slide artifacts, and color profile to ensure the accuracy of data generated. Users gain access to a portfolio of digital assays on the platform spanning a wide variety of therapeutic areas to generate standardized data at scale. Data visualization capabilities allow users to view their quantitative data alongside the corresponding whole slide images. As a cloud-based workspace, imageDx™ enables secure user-to-user image and data collaboration, enhanced automated and manual annotations and sophisticated labelling ontologies.
The imageDx™ platform is compatible with all leading pathology image formats including the FDA approved scanners from Leica and Phillips.
The platform provides a powerful pathology solution for both pre-clinical and clinical contexts. With digital assays covering areas such as NASH, Oncology, Neuroscience, Fibrosis and Inflammation, Reveal also develops custom AI models to generate specific data points at speed using a unique proprietary pipeline architecture.
Reveal Biosciences, Inc
Digital Assays
Reveal is developing a pipeline of AI-based digital assays on the imageDx pathology platform for preclinical research, clinical trials, and decision support.
https://www.revealbio.com/digital-assays/
imagedx: IHC
AI-Powered Digital Assays
https://www.revealbio.com/imagedx-ihc/
InnerEye
Doctors at Addenbrooke’s hospital in Cambridge aim to drastically cut cancer waiting times using artificial intelligence (AI) to automate lengthy radiotherapy preparations.
The AI technology, known as InnerEye, is a result of an eight-year collaboration between Cambridge-based Microsoft Research and Addenbrooke’s. Its aim is to save clinicians many hours of time laboriously marking up patient scans prior to radiotherapy.
Now the team have demonstrated how machine learning (ML) models built using the InnerEye open-source technology can cut this preparation time by up to 90% - meaning that waiting times for starting potentially life-saving radiotherapy treatment can be dramatically reduced.
The InnerEye Deep Learning Toolkit has been made freely available as open-source software by Microsoft.
Whilst ML models developed using the tool need to be tested and validated in each individual healthcare setting, doctors at Cambridge University Hospitals (CUH) have demonstrated how the technology can be applied in clinical settings.
Microsoft github.com Repo:
Medical Imaging Deep Learning library to train and deploy 3D segmentation models on Azure Machine Learning
https://github.com/microsoft/InnerEye-DeepLearning
LORIS (Logistic Regression-Based Immunotherapy-Response Score) - AI tool to predict response to cancer therapy
Dr. Eytan Ruppin of NIH’s National Cancer Institute and Dr. Luc Morris of Memorial Sloan Kettering Cancer Center
Scientists developed an AI tool that uses routine clinical data to identify cancer patients most likely to respond to immunotherapy drugs called checkpoint inhibitors. The approach could help guide personalized cancer treatments for patients.
Chemotherapy, radiation, and surgical removal of tumors have long been the standard approaches for treating different types of cancer. But in recent decades, different immunotherapies have become available. These rely on the body’s immune system to find and destroy cancer cells. One type of immunotherapy, called checkpoint inhibition, has greatly improved the treatment of many types of cancer. Immune checkpoint inhibiting drugs can make cancer cells more vulnerable to immune system attack. But they don’t work for everyone.
Scientists have been looking for better ways to identify patients most likely to respond to these drugs. People who probably wouldn’t benefit from them could avoid unnecessary treatments and side effects and be given different treatments. To date, two biomarkers have been approved by the U.S. Food and Drug Administration to identify patients most likely to benefit from these medications. One measures tumor mutational burden, which is the number of DNA mutations in cancer cells. But results of these tests are not always accurate. Other predictive tests depend on tumor molecular data that are costly to obtain and not routinely collected.
A research team led by Dr. Eytan Ruppin of NIH’s National Cancer Institute and Dr. Luc Morris of Memorial Sloan Kettering Cancer Center set out to create a more accurate predictive tool based on readily available biomarkers. To do this, they first analyzed a large data set that included information on more than 2,880 cancer patients with 18 different types of solid tumors. All had been treated with immune checkpoint inhibitors.
The team assessed over 20 different clinical, pathologic, and genomic features. They also examined patient outcomes, such as response to therapy and survival. Using machine learning, they tried to identify which combination of features could best predict a patient’s response to immune checkpoint inhibitors. Results were published on June 3, 2024, in Nature Cancer.
After developing and testing different machine learning models, the team created a new type of AI scoring system, termed LORIS (logistic regression-based immunotherapy-response score). It is based on the tumor mutational burden along with five clinical features that are routinely collected from patients. These include the patient’s age, cancer type, history of cancer therapy, blood albumin (a protein made by the liver), and blood NLR (a measure of inflammation).
Further testing showed that LORIS was better than other methods at predicting a patient’s chance of responding to immune checkpoint inhibitors. This included predictive models based on many more clinical features. LORIS could also consistently predict short-term and long-term survival after immunotherapy. The scientists note that this approach could help guide treatment decisions and maximize benefits to patients. But larger studies are needed to evaluate the tool in clinical settings.
“We were able to develop a new predictive model for immunotherapy response across many different cancer types using only six simple variables,” Morris says. “In contrast to prior models, some of which are very complex, this model is very accessible to clinicians.”
Ruppin adds, “this study provides another example for the importance and benefit of building collaborations between clinicians and data scientists across different centers in our nation to collect and analyze large patient data cohorts to advance patient care.”
The LORIS tool is publicly available at https://loris.ccr.cancer.gov.
OncoNPC
Researchers at Dana-Farber Cancer Institute have developed an artificial intelligence (AI) program that may help trace cancers of unknown primary origin back to their sources.
Cancers of unknown primary origin make up about 3% to 5% cases of metastatic disease; they are cancers that have spread from a separate and unknown place in the body onLoad="get_data()" that cannot be determined through conventional imaging scans, biopsies, or pathology reports.
The AI program, OncoNPC, short for Oncology NGS-based Primary cancer type Classifier, uses sequencing data from tumor DNA to determine where the tumor came from. The machine-learning classifier was developed with targeted next-generation sequencing (NGS) data from 36,445 tumors across 22 cancer types and medical records from the patients.
In results from a study published recently in Nature, OncoNPC was able to accurately predict the origin of about 80% of the tumors tested, including metastatic disease. Furthermore, OncoNPC correctly identified about 95% of the findings that the model considered high-confidence predictions—65% of the samples used for validation.
Cancers of unknown primary origin are particularly hard to treat, as most therapies are targeted at specific types of tumors; the researchers aim to mitigate that with OncoNPC. Determining the origin and type of tumors gives patients better options for treatment, leading to better outcomes.
The researchers plan to refine OncoNPC’s performance through the addition of other types of information, such as pathology reports, as well as exploring how the model may complement other diagnostic techniques in the community cancer treatment setting.
Sources from the original inventors and developers:
OncoNPC, Clinical sequencing-based primary site classifier
https://github.com/itmoon7/onconpc
R-CANCER
Imperial College London
R-CANCER will improve the quality of decisions made by doctors when deciding how best to detect and diagnose cancer, by intelligently collating, analysing and interpreting new data on cancer from academic and open data sources.
Tempus: Precision Cancer Care
Tempus employs AI to analyze clinical and molecular data, aiding oncologists in making informed decisions for personalized cancer treatment.