Category Archives: Cancer

AI detects bowel cancer in less than 1 second in small study

FacebooktwitterlinkedinFacebooktwitterlinkedin

Yuichi Mori and Showa University colleagues haved used AI to identify bowel cancer by analyzing colonoscopy derived polyps in less than a second.

The  system compares a magnified view of a colorectal polyp with 30,000 endocytoscopic images. The researchers claimed  86% accuracy, based on a study of 300 polyps.

While further testing the technology, Mori said that the team will focus on creating a system that can automatically detect polyps.

Click to view Endoscopy Thieme video


Join ApplySci at Wearable Tech + Digital Health + Neurotech Silicon Valley on February 26-27, 2018 at Stanford University. Speakers include:  Vinod Khosla – Justin Sanchez – Brian Otis – Bryan Johnson – Zhenan Bao – Nathan Intrator – Carla Pugh – Jamshid Ghajar – Mark Kendall – Robert Greenberg – Darin Okuda – Jason Heikenfeld – Bob Knight – Phillip Alvelda

Machine learning improves breast cancer detection

FacebooktwitterlinkedinFacebooktwitterlinkedin

MIT’s Regina Barzilay has used AI to improve breast cancer detection and diagnosis. Machine learning tools predict if a high-risk lesion identified on needle biopsy after a mammogram will upgrade to cancer at surgery, potentially eliminating unnecessary procedures.

In current practice, when a mammogram detects a suspicious lesion, a needle biopsy is performed to determine if it is cancer. Approximately 70 percent of the lesions are benign, 20 percent are malignant, and 10 percent are high-risk.

Using a method known as a “random-forest classifier,” the AI model resulted in 30 per cent fewer  surgeries, compared to the strategy of always doing surgery, while diagnosing more cancerous lesions (97 per cent vs 79 per cent) than the strategy of only doing surgery on traditional “high-risk lesions.”

Trained on information about 600 high-risk lesions, the technology looks for data patterns that include demographics, family history, past biopsies, and pathology reports.

MGH radiologists will begin incorporating the method into their clinical practice over the next year.


Join ApplySci at Wearable Tech + Digital Health + Neurotech Silicon Valley on February 26-27, 2018 at Stanford University, featuring:  Vinod KhoslaJustin SanchezBrian OtisBryan JohnsonZhenan BaoNathan IntratorCarla PughJamshid Ghajar – Mark Kendall – Robert Greenberg Darin Okuda Jason Heikenfeld

CRISPR platform targets RNA and DNA to detect cancer, Zika

FacebooktwitterlinkedinFacebooktwitterlinkedin

Broad and Wyss scientists have used an RNA-targeting CRISPR enzyme to detect  the presence of as little as a single target molecule. SHERLOCK (Specific High Sensitivity Enzymatic Reporter UnLOCKing) could one day be used to respond to viral and bacterial outbreaks, monitor antibiotic resistance, and detect cancer.

Demonstrated applications included:

  • Detecting the presence of Zika virus in patient blood or urine samples within hours;
  • Distinguishing between the genetic sequences of African and American strains of Zika virus;
  • Discriminating specific types of bacteria, such as E. coli;
  • Detecting antibiotic resistance genes;
  • Identifying cancerous mutations in simulated cell-free DNA fragments; and
  • Rapidly reading human genetic information, such as risk of heart disease, from a saliva sample.

The tool can be paper-based, not requiring refrigeration, and suited for fast deployment at field hospitals or rural clinics.


Join ApplySci at Wearable Tech + Digital Health + NeuroTech Boston – Featuring: Joi Ito, Ed Boyden, Roz Picard, George Church, Tom Insel, John Rogers, Jamshid Ghajar, Phillip Alvelda and Nathan Intrator – September 19, 2017 at the MIT Media Lab

Nanorobots optimize cancer drug delivery, preserve surrounding tissues

FacebooktwitterlinkedinFacebooktwitterlinkedin

Sylvain Martel and Polytechnique Montréal and McGill University colleagues have developed nanorobotic agents that can specifically target active cancerous cells of tumors.  Optimal targeting  could help preserve surrounding organs and healthy tissues, and allow reduced dosage.

The nanorobotic agents can autonomously detect oxygen-depleted tumour areas, and deliver the drug to them. These “hypoxic” zones are often resistant to therapies.

According to professor Martel:  “This innovative use of nanotransporters will have an impact not only on creating more advanced engineering concepts and original intervention methods, but it also throws the door wide open to the synthesis of new vehicles for therapeutic, imaging and diagnostic agents. Chemotherapy, which is so toxic for the entire human body, could make use of these natural nanorobots to move drugs directly to the targeted area, eliminating the harmful side effects while also boosting its therapeutic effectiveness.”


Wearable Tech + Digital Health + NeuroTech Silicon Valley – February 7-8, 2017 @ Stanford University

AI identifies cancer after doctor misdiagnosis, used to personalize care

FacebooktwitterlinkedinFacebooktwitterlinkedin

IBM Watson detected a rare form of leukemia in a patient in Japan, after comparing genetic changes with a database of 20 million research papers. She had been misdiagnosed by doctors for months, and received the wrong treatment for her cancer type.

Watson has created partnerships with 16 US health systems and imaging firms to identify cancer, diabetes and heart disease.  It has just announced a similar partnership with 21 hospitals in China.

While AI systems still occasionally make mistakes, the trend of using the technology for diagnosis, and  personalized treatment, with suggested therapies based on assumptions of success,  is growing rapidly.


Wearable Tech + Digital Health + NeuroTech Silicon Valley – February 7-8, 2017 @ Stanford University

Preparation free, ingestible colorectal screening device

FacebooktwitterlinkedinFacebooktwitterlinkedin

Check-Cap is developing a swallowable imaging capsule that screens for colorectal cancer with out requiring  bowel-cleansing preparation.

The ingestible capsule transmits X-rays to the intestinal wall and back, creating 3D images of the colon’s internal surface and enabling detection of clinically significant polyps.  Given Imaging,  also based in Israel, used light based (vs. X ray) imaging in its similar PillCam capsule. (Which was acquired by Covidien and then Medtronic.)

Data is transmitted to a wearable device that stores the information for offline analysis.  Users are notified when the capsule has passed through his/her system.   In the next phase, physicians will be able to view the images on any device at any time.

The hope is that with out requiring uncomfortable preparation, more people will participate in colorectal screening, and disease will be discovered early.


Wearable Tech + Digital Health + NeuroTech Silicon Valley – February 7-8, 2017 @ Stanford University

Non-invasive electric field treatment for glioblastoma

FacebooktwitterlinkedinFacebooktwitterlinkedin

Optune by Novocure  uses targeted electric fields to disrupt cancer cell division and cause cancer cell death.  500 hospitals globally can prescribe the FDA approved treatment to glioblastoma patients.

“Tumor Treating Fields” are low intensity, alternating electric fields within the intermediate frequency range. TTFields disrupt cell division through physical interactions with key molecules during mitosis. The non-invasive treatment targets solid tumors.

Company founder Yoram Palti said that trials in other tumors will have results starting this year, and he “believes that we will change the way we treat cancer. There are other growths that are more sensitive to our approach than brain cancer. A pilot of 40 lung cancer patients had exciting results in a treatment where the electrodes are only worn 12 hours a day and not 24.”

Click to view Optune US video


Wearable Tech + Digital Health NYC – June 7, 2016 @ the New York Academy of Sciences

NeuroTech NYC – June 8, 2016 @ the New York Academy of Sciences

Optical sensor could detect cancer, other diseases, earlier

FacebooktwitterlinkedinFacebooktwitterlinkedin

Guiseppe Strangi and Case Western colleagues have developed a highly sensitive optical sensor, based on nanostructured metamaterials.  The researchers claim that is is 1 million times more sensitive than current sensors, and capable of identifying a single lightweight molecule in a highly dilute solution.  This could dramatically improve the detection of cancer and other diseases.

If doctors could detect a single molecule of an enzyme produced by circulating cancer cells, significantly earlier diagnosis is possible, which could dramatically improve one’s prognosis.

According to Strangi:”Very early, most circulating tumor cells express proteins of a very low molecular weight, less than 500 Daltons. These proteins are usually too small and in too low a concentration to detect with current test methods, yielding false negative results. With this platform, we’ve detected proteins of 244 Daltons, which should enable doctors to detect cancers earlier–we don’t know how much earlier yet.”


Wearable Tech + Digital Health San Francisco – April 5, 2016 @ the Mission Bay Conference Center

NeuroTech San Francisco – April 6, 2016 @ the Mission Bay Conference Center

Wearable Tech + Digital Health NYC – June 7, 2016 @ the New York Academy of Sciences

NeuroTech San Francisco – June 8, 2016 @ the New York Academy of Sciences

 

Machine learning analysis of doctor notes predicts cancer progression

FacebooktwitterlinkedinFacebooktwitterlinkedin

Gunnar Rätsch and Memorial Sloan Kettering colleagues are using AI to find similarities between cancer cases.  Ratsch’s algorithm has analyzed 100 million sentences taken from clinical notes of about 200,000 cancer patients to predict disease progression.

In a recent study, machine learning was used to classify  patient symptoms, medical histories and doctors’ observations into 10,000 clusters. Each cluster represented a common observation in medical records, including recommended treatments and typical symptoms. Connections between clusters were mapped to  show inter-relationships. In another study, algorithms were used to  find hidden associations between written notes and patients’ gene and blood sequencing.


Wearable Tech + Digital Health San Francisco – April 5, 2016 @ the Mission Bay Conference Center

NeuroTech San Francisco – April 6, 2016 @ the Mission Bay Conference Center

Wearable Tech + Digital Health NYC – June 7, 2016 @ the New York Academy of Sciences

NeuroTech NYC – June 8, 2016 @ the New York Academy of Sciences

 

 

Sensor + algorithm detect prostate cancer in urine

FacebooktwitterlinkedinFacebooktwitterlinkedin

Chris Probert and University of Liverpool and UWE Bristol colleagues are creating a test that uses gas chromatography to “smell” prostrate cancer in urine.  If proven accurate, the test might be able to be used instead of current invasive diagnostic procedures, at an earlier stage.

155 men were tested. 58 were diagnosed with prostate cancer, 24 with bladder cancer and 73 with hematuria or poor stream without cancer.  The sensor successfully identified patterns of volatile compounds that allow classification of urine in patients with urological cancers.

Urine samples are inserted into the  “Odoreader” and measured using algorithms.  A 30 meter column enables the urine compounds to travel through it at different rate. The algorithm detects cancer by reading the patterns.


Wearable Tech + Digital Health San Francisco – April 5, 2016 @ the Mission Bay Conference Center

NeuroTech San Francisco – April 6, 2016 @ the Mission Bay Conference Center

Wearable Tech + Digital Health NYC -June 7, 2016 @ the New York Academy of Sciences

NeuroTech NYC – June 8, 2016 @ the New York Academy of Sciences