{"id":555952,"date":"2023-04-19T17:10:01","date_gmt":"2023-04-19T21:10:01","guid":{"rendered":"https:\/\/www.rochester.edu\/newscenter\/?p=555952"},"modified":"2023-04-19T18:35:04","modified_gmt":"2023-04-19T22:35:04","slug":"breast-cancer-diagnosis-machine-learning-ultrasound-555952","status":"publish","type":"post","link":"https:\/\/www.rochester.edu\/newscenter\/breast-cancer-diagnosis-machine-learning-ultrasound-555952\/","title":{"rendered":"Better breast cancer diagnosis through machine-learning ultrasound"},"content":{"rendered":"

Early results show 98 percent accuracy in predicting malignant tissue.<\/h2>\n

Mammography is the gold standard for breast cancer diagnosis, but it\u2019s not reliably accurate in all cases, especially in people with dense breasts. At the University of Rochester<\/a>, Avice O\u2019Connell<\/a> \u201977M (Res) a professor of imaging sciences at the Medical Center<\/a>, and Kevin Parker<\/a>, a professor of electrical and computer engineering at the Hajim School of Engineering & Applied Sciences<\/a>,\u00a0wanted to do better. Along with Jihye Baek, a PhD student in electrical and computer engineering<\/a>, they launched a research project incorporating ultrasound with machine learning for previously detected masses. The end result: nearly 98 percent accuracy in predicting breast cancer in these masses.<\/p>\n

The sensitivity of mammography can range from 40 percent for dense breast tissue to a high of just above 90 percent. \u201cWhile 90 percent sounds good, a higher accuracy rate means we can help many more women,\u201d says Parker.<\/p>\n

The findings were published last November in the journal Machine Learning: Science and Technology<\/a><\/em>. Parker\u2019s team combined ultrasound with a feature-based machine-learning method for breast cancer detection, adding a color overlay map showing the probability of malignancy.<\/p>\n

Mammography versus breast ultrasound<\/strong><\/h3>\n

Mammography and ultrasound are the two main methods of breast cancer diagnosis. Mammography relies on an x-ray system to take an image of breast tissue. Breast ultrasound, as the name suggests, produces an image of breast tissue\u2014a sonogram\u2014from sound waves. A handheld wand called a transducer scans the breast with sound waves, and the resulting sound echoes create the image.<\/p>\n

As the researchers point out in their paper, ultrasound is less expensive than mammography, portable, and radiation-free, making it a desirable tool, especially in developing countries. But at present, ultrasound is used only as a complement to standard mammography. That\u2019s because, as O\u2019Connell explains, ultrasound finds many masses within a breast, most of which are not cancer. \u201cBreast imagers need new ways to reduce the number of false positive biopsies,\u201d she says.<\/p>\n

\"Side-by-side
INTERDISCIPLINARY PARTNERSHIP:<\/strong> Kevin Parker (left), a professor of electrical and computer engineering, and Avice O’Connell, a professor of imaging sciences, are working to improve breast cancer diagnostics.<\/figcaption><\/figure>\n

Ultrasound better than mammography at imaging dense breast tissue<\/strong><\/h3>\n

Improving breast cancer screening and diagnosis is an active area of research locally and nationally. At the Medical Center and its Wilmot Cancer Institute<\/a>, for example, a unique 3D ultrasound system has been developed separately for patient care and continues to be evaluated.<\/p>\n

Improved ultrasound diagnostics are especially important for women with dense fibroglandular tissue. According to the National Cancer Institute, that includes nearly half of all women age 40 and older who get mammograms. \u201cFor them, the sensitivity is as low as 50 percent with mammograms,\u201d says Parker. \u201cWith advanced ultrasound, we may be able to get into the upper 90 percentiles of accuracy.\u201d<\/p>\n

Parker believes their system also has unique features in that it simplifies the process. While some researchers are looking at many features in the breast\u2014some as many as 30\u2014the Rochester team focuses on five key biophysical features involving the distribution of cells, blood vessels, and proteins.<\/p>\n

Machine-learning ultrasound: a promising new means to improve diagnosis, reduce false positives<\/strong><\/h3>\n

The team\u2019s approach involves machine learning, which is a type of artificial intelligence, or AI. From the data the researchers input, the computers develop algorithms that enable them to learn patterns and better recognize cancerous tissue. The new image that is produced by the algorithm shows the probability of malignancy within lesions, using a color overlay with blue and green corresponding to benign tissue and red corresponding to a high probably of malignancy.<\/p>\n

Parker and O\u2019Connell are pleased with the 98-percent accuracy rate, but they note it was accomplished with only 121 scans of suspicious breast lesions from patients at the University of Rochester Medical Center.<\/p>\n

\u201cIn the next stage of our research, we\u2019ll be working with much larger sets of data,\u201d says Parker.<\/p>\n

Given the need for more data, it\u2019s difficult to say how quickly their framework for computer-assisted ultrasound can be put into practice. O\u2019Connell says, \u201cMore research is needed on many more patients for this to be widely adopted.\u201d<\/p>\n

But that\u2019s how any task based on machine learning works. Computers get \u201csmarter\u201d with more data, producing more precise algorithms, translating into better diagnostics, and in the case of breast cancer screening, more lives saved.<\/p>\n

Improving diagnostics in developing countries<\/strong><\/h3>\n

Because ultrasound is portable and less expensive than mammography, it\u2019s a desirable tool in developing countries. But it still requires an experienced sonographer.<\/p>\n

In a separate research paper published in PLOS Digital Health<\/a>, by Tom Marini<\/a>\u00a0\u201917M (MD), a clinical instructor in the Medical Center’s Department of Imaging Sciences<\/a>, along with Parker, O\u2019Connell and their collaborators, the authors describe the possibility of combining a type of ultrasound\u2014called volume sweep imaging (VSI)\u2014with artificial intelligence to provide an automatic and inexpensive form of breast mass diagnosis. Since VSI does not require an experienced sonographer, they hope this approach can make a difference in low- and middle-income countries, where access to breast cancer diagnosis and care poses a challenge.<\/p>\n

\n

Read more<\/strong><\/h3>\n
\n
\n

\"ThreeNew imaging technology could buy time for pancreatic cancer patients<\/strong><\/a><\/p>\n

Tumor shrinkage is one sign of cancer treatment\u2019s efficacy\u2014but Rochester scientists are exploring elasticity and permeability as well.<\/span><\/p>\n<\/div>\n

\n

\"ColorBreakthrough adds new color to ultrasound.<\/strong><\/a><\/p>\n

Rochester engineering professor Kevin Parker has devised a way to differentiate fine details in medical ultrasound images that currently appear as indistinguishable objects in shades of gray.<\/span><\/p>\n<\/div>\n

\n

\"Close-upNovel imaging system could mean near-instant biopsy results<\/strong><\/a><\/p>\n

The new imaging system developed by Michael Giacomelli, an assistant professor of biomedical engineering and of optics, uses two-photon fluorescence microscopy (TPFM).<\/span><\/p>\n<\/div>\n<\/div>\n

 <\/p>\n","protected":false},"excerpt":{"rendered":"

Early results in a study by faculty at the Medical Center and the Hajim School show 98 percent accuracy in predicting malignant tissue.<\/p>\n","protected":false},"author":16,"featured_media":555972,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[116],"tags":[19382,18632,22532,111,18572],"class_list":["post-555952","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-sci-tech","tag-department-of-electrical-and-computer-engineering","tag-hajim-school-of-engineering-and-applied-sciences","tag-kevin-parker","tag-medical-center","tag-research-finding"],"acf":[],"yoast_head":"\nBetter breast cancer diagnosis through machine-learning ultrasound<\/title>\n<meta name=\"description\" content=\"Incorporating machine learning into ultrasound, University of Rochester researchers show promising improvements in breast cancer diagnosis.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.rochester.edu\/newscenter\/breast-cancer-diagnosis-machine-learning-ultrasound-555952\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Better breast cancer diagnosis through machine-learning ultrasound\" \/>\n<meta property=\"og:description\" content=\"Incorporating machine learning into ultrasound, University of Rochester researchers show promising improvements in breast cancer diagnosis.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.rochester.edu\/newscenter\/breast-cancer-diagnosis-machine-learning-ultrasound-555952\/\" \/>\n<meta property=\"og:site_name\" content=\"News Center\" \/>\n<meta property=\"article:published_time\" content=\"2023-04-19T21:10:01+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2023-04-19T22:35:04+00:00\" \/>\n<meta property=\"og:image\" content=\"http:\/\/www.rochester.edu\/newscenter\/wp-content\/uploads\/2023\/04\/fea-breast-cancer-diagnosis-machine-learning-ultrasound.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1000\" \/>\n\t<meta property=\"og:image:height\" content=\"600\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Peter Iglinski\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@PiDaddy\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Peter Iglinski\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"6 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.rochester.edu\/newscenter\/breast-cancer-diagnosis-machine-learning-ultrasound-555952\/\",\"url\":\"https:\/\/www.rochester.edu\/newscenter\/breast-cancer-diagnosis-machine-learning-ultrasound-555952\/\",\"name\":\"Better breast cancer diagnosis through machine-learning ultrasound\",\"isPartOf\":{\"@id\":\"https:\/\/www.rochester.edu\/newscenter\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/www.rochester.edu\/newscenter\/breast-cancer-diagnosis-machine-learning-ultrasound-555952\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/www.rochester.edu\/newscenter\/breast-cancer-diagnosis-machine-learning-ultrasound-555952\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/www.rochester.edu\/newscenter\/wp-content\/uploads\/2023\/04\/fea-breast-cancer-diagnosis-machine-learning-ultrasound.jpg\",\"datePublished\":\"2023-04-19T21:10:01+00:00\",\"dateModified\":\"2023-04-19T22:35:04+00:00\",\"author\":{\"@id\":\"https:\/\/www.rochester.edu\/newscenter\/#\/schema\/person\/f7a217a901be900507c6e137448f5d5a\"},\"description\":\"Incorporating machine learning into ultrasound, University of Rochester researchers show promising improvements in breast cancer diagnosis.\",\"breadcrumb\":{\"@id\":\"https:\/\/www.rochester.edu\/newscenter\/breast-cancer-diagnosis-machine-learning-ultrasound-555952\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.rochester.edu\/newscenter\/breast-cancer-diagnosis-machine-learning-ultrasound-555952\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.rochester.edu\/newscenter\/breast-cancer-diagnosis-machine-learning-ultrasound-555952\/#primaryimage\",\"url\":\"https:\/\/www.rochester.edu\/newscenter\/wp-content\/uploads\/2023\/04\/fea-breast-cancer-diagnosis-machine-learning-ultrasound.jpg\",\"contentUrl\":\"https:\/\/www.rochester.edu\/newscenter\/wp-content\/uploads\/2023\/04\/fea-breast-cancer-diagnosis-machine-learning-ultrasound.jpg\",\"width\":1000,\"height\":600,\"caption\":\"University of Rochester researchers in imaging sciences and electrical and computer engineering have partnered to develop machine-learning ultrasound to detect malignant breast tissue. (Getty Images)\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.rochester.edu\/newscenter\/breast-cancer-diagnosis-machine-learning-ultrasound-555952\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/www.rochester.edu\/newscenter\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Better breast cancer diagnosis through machine-learning ultrasound\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.rochester.edu\/newscenter\/#website\",\"url\":\"https:\/\/www.rochester.edu\/newscenter\/\",\"name\":\"News Center\",\"description\":\"University of Rochester\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.rochester.edu\/newscenter\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.rochester.edu\/newscenter\/#\/schema\/person\/f7a217a901be900507c6e137448f5d5a\",\"name\":\"Peter Iglinski\",\"sameAs\":[\"https:\/\/x.com\/PiDaddy\"],\"url\":\"https:\/\/www.rochester.edu\/newscenter\/author\/peter-iglinski\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Better breast cancer diagnosis through machine-learning ultrasound","description":"Incorporating machine learning into ultrasound, University of Rochester researchers show promising improvements in breast cancer diagnosis.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.rochester.edu\/newscenter\/breast-cancer-diagnosis-machine-learning-ultrasound-555952\/","og_locale":"en_US","og_type":"article","og_title":"Better breast cancer diagnosis through machine-learning ultrasound","og_description":"Incorporating machine learning into ultrasound, University of Rochester researchers show promising improvements in breast cancer diagnosis.","og_url":"https:\/\/www.rochester.edu\/newscenter\/breast-cancer-diagnosis-machine-learning-ultrasound-555952\/","og_site_name":"News Center","article_published_time":"2023-04-19T21:10:01+00:00","article_modified_time":"2023-04-19T22:35:04+00:00","og_image":[{"url":"http:\/\/www.rochester.edu\/newscenter\/wp-content\/uploads\/2023\/04\/fea-breast-cancer-diagnosis-machine-learning-ultrasound.jpg","width":1000,"height":600,"type":"image\/jpeg"}],"author":"Peter Iglinski","twitter_card":"summary_large_image","twitter_creator":"@PiDaddy","twitter_misc":{"Written by":"Peter Iglinski","Est. reading time":"6 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.rochester.edu\/newscenter\/breast-cancer-diagnosis-machine-learning-ultrasound-555952\/","url":"https:\/\/www.rochester.edu\/newscenter\/breast-cancer-diagnosis-machine-learning-ultrasound-555952\/","name":"Better breast cancer diagnosis through machine-learning ultrasound","isPartOf":{"@id":"https:\/\/www.rochester.edu\/newscenter\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.rochester.edu\/newscenter\/breast-cancer-diagnosis-machine-learning-ultrasound-555952\/#primaryimage"},"image":{"@id":"https:\/\/www.rochester.edu\/newscenter\/breast-cancer-diagnosis-machine-learning-ultrasound-555952\/#primaryimage"},"thumbnailUrl":"https:\/\/www.rochester.edu\/newscenter\/wp-content\/uploads\/2023\/04\/fea-breast-cancer-diagnosis-machine-learning-ultrasound.jpg","datePublished":"2023-04-19T21:10:01+00:00","dateModified":"2023-04-19T22:35:04+00:00","author":{"@id":"https:\/\/www.rochester.edu\/newscenter\/#\/schema\/person\/f7a217a901be900507c6e137448f5d5a"},"description":"Incorporating machine learning into ultrasound, University of Rochester researchers show promising improvements in breast cancer diagnosis.","breadcrumb":{"@id":"https:\/\/www.rochester.edu\/newscenter\/breast-cancer-diagnosis-machine-learning-ultrasound-555952\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.rochester.edu\/newscenter\/breast-cancer-diagnosis-machine-learning-ultrasound-555952\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.rochester.edu\/newscenter\/breast-cancer-diagnosis-machine-learning-ultrasound-555952\/#primaryimage","url":"https:\/\/www.rochester.edu\/newscenter\/wp-content\/uploads\/2023\/04\/fea-breast-cancer-diagnosis-machine-learning-ultrasound.jpg","contentUrl":"https:\/\/www.rochester.edu\/newscenter\/wp-content\/uploads\/2023\/04\/fea-breast-cancer-diagnosis-machine-learning-ultrasound.jpg","width":1000,"height":600,"caption":"University of Rochester researchers in imaging sciences and electrical and computer engineering have partnered to develop machine-learning ultrasound to detect malignant breast tissue. (Getty Images)"},{"@type":"BreadcrumbList","@id":"https:\/\/www.rochester.edu\/newscenter\/breast-cancer-diagnosis-machine-learning-ultrasound-555952\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.rochester.edu\/newscenter\/"},{"@type":"ListItem","position":2,"name":"Better breast cancer diagnosis through machine-learning ultrasound"}]},{"@type":"WebSite","@id":"https:\/\/www.rochester.edu\/newscenter\/#website","url":"https:\/\/www.rochester.edu\/newscenter\/","name":"News Center","description":"University of Rochester","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.rochester.edu\/newscenter\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Person","@id":"https:\/\/www.rochester.edu\/newscenter\/#\/schema\/person\/f7a217a901be900507c6e137448f5d5a","name":"Peter Iglinski","sameAs":["https:\/\/x.com\/PiDaddy"],"url":"https:\/\/www.rochester.edu\/newscenter\/author\/peter-iglinski\/"}]}},"_links":{"self":[{"href":"https:\/\/www.rochester.edu\/newscenter\/wp-json\/wp\/v2\/posts\/555952","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.rochester.edu\/newscenter\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.rochester.edu\/newscenter\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.rochester.edu\/newscenter\/wp-json\/wp\/v2\/users\/16"}],"replies":[{"embeddable":true,"href":"https:\/\/www.rochester.edu\/newscenter\/wp-json\/wp\/v2\/comments?post=555952"}],"version-history":[{"count":16,"href":"https:\/\/www.rochester.edu\/newscenter\/wp-json\/wp\/v2\/posts\/555952\/revisions"}],"predecessor-version":[{"id":556612,"href":"https:\/\/www.rochester.edu\/newscenter\/wp-json\/wp\/v2\/posts\/555952\/revisions\/556612"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.rochester.edu\/newscenter\/wp-json\/wp\/v2\/media\/555972"}],"wp:attachment":[{"href":"https:\/\/www.rochester.edu\/newscenter\/wp-json\/wp\/v2\/media?parent=555952"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.rochester.edu\/newscenter\/wp-json\/wp\/v2\/categories?post=555952"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.rochester.edu\/newscenter\/wp-json\/wp\/v2\/tags?post=555952"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}