Bostel Issued Patent for Dual Deep Learning Algorithm for Skin Cancer Diagnosis
April 12, 2022 · Atlanta
Bostel Technologies, LLC today announced the issuance by the U.S. Patent and Trademark Office of Bostel’s first and most central patent relating to the diagnosis of cancer using dual deep learning, including sonification.
On April 12, 2022, the USPTO issued patent number 11,298,072, titled, “Dermoscopy Diagnosis of Cancerous Lesions Utilizing Dual Deep Learning Algorithms via Visual and Audio (Sonification) Outputs”. The patent covers Bostel’s novel approach to multimodal deep learning in diagnostic applications.
“Melanoma and other skin cancers can be deadly. Effectively diagnosing problematic lesions as early as possible is critical,” said Dr. Avi Dascalu, Bostel’s Chief Medical Officer who is a dermatologist and the lead inventor named on this patent. Dr. Dascalu highlighted Bostel’s use of both traditional vision-based machine-learning approaches, as well as cutting edge methods that use sonification, or the conversion of data from the image into structured sound. “Our algorithms detect even small cancers, without many false positives,” Dascalu said.
Dr. Bruce N. Walker, President of Bostel Technologies and a world expert in sonfication, pointed out that reliably detecting cancer when it is present, and not classifying safe lesions or moles as dangerous, must both be featured in any effective diagnostic or screening tool. “Success requires both high sensitivity and a solid specificity. Bostel’s dual deep learning method excels at both these metrics.”
The effectiveness of Bostel’s now-patented technologies has been well documented in various peer-reviewed publications. These technologies are also powering products and services that Bostel will soon bring to the market.
More people are diagnosed with skin cancer each year in the U.S. than all other cancers combined. According to the Skin Cancer Foundation, one in five Americans will develop skin cancer by the age of 70. If detected early, the five-year mean survivability rate for melanoma is 99%. If undetected, or if detected to late, the consequences can be severe. Every hour, two people in the U.S. die from skin cancer.
Read more about Bostel Technologies’ publications and technologies.
About Bostel Technologies
Bostel Technologies LLC is a privately-held, Atlanta-headquartered medical technology company that has created a patented diagnostic platform called Melody™ that uses Dual Deep Learning technology to improve the clinical diagnoses of melanoma by applying an additional sonification (data to sound waves conversion) layer on deep learning algorithms.
For more information please visit https://www.BostelTechnologies.com.
Contact: Bruce N. Walker, President: bwalker@bosteltechnologies.com
Bostel Publishes Peer-Reviewed Article in Journal of Cancer Research and Clinical Oncology
September 15, 2021 · Atlanta
Bostel Technologies, LLC today announced the publication of its fourth peer-reviewed journal article about skin cancer diagnosis using Bostel’s proprietary technology.
Appearing in the Journal of Cancer Research and Clinical Oncology, the article “Non‐melanoma skin cancer diagnosis: a comparison between dermoscopic and smartphone images by unified visual and sonification deep learning algorithms” discusses recent findings about Bostel’s technology used with both dermoscopic and non-dermoscopic images, and for non-melanoma skin cancer.
This follows on Bostel’s series of publications relating to diagnosis of skin cancer using novel multimodal deep learning.
More people are diagnosed with skin cancer each year in the U.S. than all other cancers combined. According to the Skin Cancer Foundation, one in five Americans will develop skin cancer by the age of 70. If detected early, the five-year mean survivability rate for melanoma is 99%. If undetected, or if detected to late, the consequences can be severe. Every hour, two people in the U.S. die from skin cancer.
Read More about this new article, with links to download.
About Bostel Technologies
Bostel Technologies LLC is a privately-held, Atlanta-headquartered medical technology company that has created a patented diagnostic platform called Melody™ that uses Dual Deep Learning technology to improve the clinical diagnoses of melanoma by applying an additional sonification (data to sound waves conversion) layer on deep learning algorithms.
For more information please visit https://www.BostelTechnologies.com.
Contact: Bruce N. Walker, President: bwalker@bosteltechnologies.com
Bostel Headed to San Francisco in January for Key Industry Meetings
January 21, 2020 · Boston
Bostel Technologies, LLC today announced that it will be at two key conferences in January in San Francisco. Bostel and its representatives will be in San Francisco starting Sunday, January 12, for the 7th Annual Dermatology Summit at the Palace Hotel. Following this meeting the Company will be present for the JP Morgan Healthcare Conference and the associated meetings that week. Parties who are interested in meeting the company can use the information at the bottom of this press release.
Melanoma and nonmelanoma skin cancer are now among the most common types of cancer, worldwide. Non-melanoma skin cancer is the 5th most commonly occurring cancer in men and women with over 1 million diagnoses worldwide in 2018, although this is likely to be an underestimate. Melanoma of the skin is the 19th most commonly occurring cancer in men and women, there were nearly 300,000 new cases in 2018.
More people are diagnosed with skin cancer each year in the U.S. than all other cancers combined. According to the Skin Cancer Foundation, one in five Americans will develop skin cancer by the age of 70. If detected early, the five-year mean survivability rate for melanoma is 99%. If undetected, or if detected to late, the consequences can be severe. Every hour, two people in the U.S. die from skin cancer.
About Bostel Technologies
Bostel Technologies LLC is a privately-held, Atlanta-headquartered medical technology company that has created a patented diagnostic platform called Melody™ that uses Dual Deep Learning technology to improve the clinical diagnoses of melanoma by applying an additional sonification (data to sound waves conversion) layer on deep learning algorithms.
For more information please visit https://www.BostelTechnologies.com.
Contact: Bruce N. Walker, President: bwalker@bosteltechnologies.com
Prospective Clinical Study Using Melody Validates Its Utility as Diagnostic for Melanoma
May 30, 2019 · Boston
Bostel Technologies, LLC today announced that the globally respect medical journal The Lancet published results of a prospective clinical study that showed that Melody™, Bostel’s Dual Deep Learning Technology™, significantly improves the diagnostics accuracy of melanoma.
“We have leveraged sonification and artificial intelligence to create a new diagnostic paradigm with clinically-proven sensitivity and specificity,” commented Harry Keegan, Bostel’s Chief Executive Officer. “This patent protected platform empowers healthcare professionals to efficiently and effectively diagnose melanoma lesions using dermoscopy so they can focus on improving outcomes and helping their patients”.
Experimental studies have indicated a potential diagnostic role for deep learning algorithms in identifying skin cancer at varying sensitivities. Previously, it was demonstrated that diagnostics by dermoscopy are improved by applying an additional sonification (data to sound waves conversion) layer on deep. learning algorithms. The aim of the study was to determine the impact of image quality on accuracy of diagnosis by sonification employing a rudimentary skin magnifier with polarized light.
The publication (The Lancet, EBioMEdicine; May 2019, Volume 43, Pages 107–113) recounted that processing of dermoscopic images followed by sonification resulted in an accurate diagnostic output using skin magnifier with polarized light. This implyied that the quality of the dermoscope is not the major factor influencing DL diagnosis of skin cancer. Thus Melody, Bostels Dual Deep Learning technology platform might have great utility in assisting healthcare providers to better detect melanoma.
Melanoma and nonmelanoma skin cancer are now among the most common types of cancer, worldwide. Non-melanoma skin cancer is the 5th most commonly occurring cancer in men and women, with over 1 million diagnoses worldwide in 2018, although this is likely to be an underestimate. Melanoma of the skin is the 19th most commonly occurring cancer in men and women, there were nearly 300,000 new cases in 2018.
More people are diagnosed with skin cancer each year in the U.S. than all other cancers combined. According to the Skin Cancer Foundation, one in five Americans will develop skin cancer by the age of 70. If detected early, the five-year mean survivability rate for melanoma is 99%. If undetected, or if detected to late, the consequences can be severe. Every hour, two people in the U.S. die from skin cancer.
About Bostel Technologies
Bostel Technologies LLC is a privately-held, Atlanta-headquartered medical technology company that has created a patented diagnostic platform called Melody™ that uses Dual Deep Learning technology to improve the clinical diagnoses of melanoma by applying an additional sonification (data to sound waves conversion) layer on deep learning algorithms.
For more information please visit https://www.BostelTechnologies.com.
Contact: Bruce N. Walker, President: bwalker@bosteltechnologies.com
May is Skin Cancer Awareness Month – Bostel Urges You to Act
May 01, 2019 · Boston
Bostel Technologies, LLC today recognized the May is Skin Cancer Awareness month and urged people to act now to make changes to minimize the risk of this growing issue.
“At Bostel we are focused on developing Melody, a new technology platform that healthcare providers can use to better detect melanoma,” commented Harry Keegan, Bostel’s Chief Executive Officer. “While we are encouraged by the clinical results we have seen and this gives us hope, making the right behavioral choices today can help ensure that people minimize their risk”.
According to the Skin Cancer Foundation, over 5 million cases of skin cancer are diagnosed each year, making it the most common cancer in the United States. Fortunately, skin cancer is also one of the most preventable forms of cancer. About 90 percent of nonmelanoma skin cancers and 85 percent of melanoma cases are associated with exposure to ultraviolet radiation from the sun. By raising awareness of the dangers of unprotected exposure and encouraging sun-safe habits, we can change behaviors and save lives.
More people are diagnosed with skin cancer each year in the U.S. than all other cancers combined. According to the Skin Cancer Foundation, one in five Americans will develop skin cancer by the age of 70. If detected early, the five-year mean survivability rate for melanoma is 99%. If undetected, or if detected to late, the consequences can be severe. Every hour, two people in the U.S. die from skin cancer.
We encourage people to log on the the Skin Cancer Foundation website to learn what you can do to get involved: https://www.skincancer.org/get-involved/skin-cancer-awareness-month/
About Bostel Technologies
Bostel Technologies LLC is a privately-held, Atlanta-headquartered medical technology company that has created a patented diagnostic platform called Melody™ that uses Dual Deep Learning technology to improve the clinical diagnoses of melanoma by applying an additional sonification (data to sound waves conversion) layer on deep learning algorithms.
For more information please visit https://www.BostelTechnologies.com.
Contact: Bruce N. Walker, President: bwalker@bosteltechnologies.com
Bostel Dual Deep Learning Technology Significantly Improves Diagnostic Accuracy of Melanoma
February 15, 2019 · Boston
Bostel Technologies, LLC today announced that the globally respect medical journal The Lancet published results of a retrospective study that showed that Melody™, Bostel’s Dual Deep Learning Technology™, significantly improves the diagnostics accuracy of melanoma.
“We have leveraged sonification and artificial intelligence to create a new diagnostic paradigm with clinically-proven sensitivity and specificity,” commented Harry Keegan, Bostel’s Chief Executive Officer. “This patent protected platform empowers healthcare professionals to efficiently and effectively diagnose melanoma lesions using dermoscopy so they can focus on improving outcomes and helping their patients”.
The publication (The Lancet, EBioMEdicine; February 2019, volume 40, pages 176–183) details the results from two parallel studies that were conducted: a laboratory retrospective study (LABS, n = 482 biopsies) and a non-interventional prospective observational study (OBS, n = 63 biopsies). Using Melody’s Dual Deep Learning Technology, which leverages dermoscopy and adds a second stage of processing that includes a deep learning algorithm of sonification and heuristic inspection with machine learning, significantly improves diagnostic accuracy.
Melanoma and nonmelanoma skin cancer are now among the most common types of cancer, worldwide. Non-melanoma skin cancer is the 5th most commonly occurring cancer in men and women,with over 1 million diagnoses worldwide in 2018, although this is likely to be an underestimate. Melanoma of the skin is the 19th most commonly occurring cancer in men and women, there were nearly 300,000 new cases in 2018.
More people are diagnosed with skin cancer each year in the U.S. than all other cancers combined. According to the Skin Cancer Foundation, one in five Americans will develop skin cancer by the age of 70. If detected early, the five-year mean survivability rate for melanoma is 99%. If undetected, or if detected to late, the consequences can be severe. Every hour, two people in the U.S. die from skin cancer.
About Bostel Technologies
Bostel Technologies LLC is a privately-held, Atlanta-headquartered medical technology company that has created a patented diagnostic platform called Melody™ that uses Dual Deep Learning technology to improve the clinical diagnoses of melanoma by applying an additional sonification (data to sound waves conversion) layer on deep learning algorithms.
For more information please visit https://www.BostelTechnologies.com.
Contact: Bruce N. Walker, President: bwalker@bosteltechnologies.com