Awards
 | This section of a biography of a living person does not include any references or sources .(April 2021) |
- Presidential Early Career Award for Scientists and Engineers, 1999
- NIH Director's Award, 2012
Ronald M. Summers | |
|---|---|
| Citizenship | USA |
| Alma mater | University of Pennsylvania |
| Known for | CT Colonography, deep learning in radiology |
| Scientific career | |
| Institutions | NIH |
Ronald Marc Summers is an American radiologist and senior investigator at the Diagnostic Radiology Department at the NIH Clinical Center in Bethesda, Maryland. He is chief of the Clinical Image Processing Service and directs the Imaging Biomarkers and Computer-Aided Diagnosis (CAD) Laboratory. A researcher in the field of radiology and computer-aided diagnosis, he has co-authored over 500 journal articles and conference proceedings papers and is a coinventor on 12 patents. [1] His lab has conducted research applying artificial intelligence and deep learning to radiology. [2] [3] [4]
Summers received his B.A. degree in physics from the University of Pennsylvania in 1981, where he also obtained his M.D. and Ph.D. degrees in Medicine/Anatomy & Cell Biology in 1988. [5] He completed a medical internship at the Penn Presbyterian Medical Center in Philadelphia, Pennsylvania, a radiology residency at the University of Michigan, Ann Arbor, MI (1989–1993) and an MRI fellowship at Duke University, Durham, NC (1993–1994). [6]
Summers' lab is known for developing software for "virtual colonoscopy" and computer aided detection (CAD) algorithms which assist in the detection of colon polyps. [7] His lab is also known for multi-organ multi-atlas registration and the development of large radiologic image databases. Summers is also a practicing clinician – his clinical areas of specialty are thoracic and gastrointestinal radiology and body cross-sectional imaging. [6]
Summers' lab is known for pioneering work in the application of deep learning to problems in medical imaging such as computer aided detection, classification, and segmentation. A February 2016 paper from his lab exploring convolutional neural network architectures and transfer learning for lymph node detection and interstitial lung disease classification had over 1,000 citations as of early 2019. [8] In 2018 he was the keynote speaker at the inaugural Medical Imaging and Deep Learning (MIDL) conference. [9]
In September 2017 his lab released 100,000 anonymized chest x-ray images from 30,000 patients, including many with advanced lung disease. [10] [11]
In July 2018, his lab released DeepLesion, a dataset of 32,000 annotated lesions identified on CT images spread over 4,400 patients. [12] [13] [14] [15] At the 2019 IEEE Symposium on Biomedical Imaging (ISBI) Youbao Tang, a postdoc in Summers' lab, unveiled a universal lesion detector (nicknamed "ULDor") which uses a mask R-CNN architecture to detect many types of lesions throughout the body with high precision. [16]
In 2019 his lab has demonstrated how to generate weak labels from clinically generated medical reports using deep learning and natural language processing techniques, thus greatly reducing the need for burdensome hand annotation of datasets. [17]
Summers and collaborators have also developed a tool for opportunistic fully automated bone mineral density (BMD) measurement in CT scans which has been used to track BMD changes in large longitudinal cohorts. [18] [19] Together with Perry Pickhardt and collaborators, the tool was used to track bone mineral density changes in 20,000 subjects. [20] [21] Summers' lab has also demonstrated the utility of deep learning for performing automated measurement of muscle, [22] liver fat, [23] vertebral levels, [24] and plaque in large datasets. [25] A 2022 paper from Summers' lab published in Radiology showed how computed tomography (CT) biomarkers are associated with diabetes and pre-diabetes. [26] [27]
Summers has served as a member of the editorial boards of the journals Radiology: Artificial Intelligence, Journal of Medical Imaging, and Academic Radiology and is a Fellow of the Society of Abdominal Radiologists and the American Institute for Medical and Biological Engineering (AIMBE). [6]
| This section of a biography of a living person does not include any references or sources .(April 2021) |
A computed tomography scan is a medical imaging technique used to obtain detailed internal images of the body. The personnel that perform CT scans are called radiographers or radiology technologists.
Appendicitis is inflammation of the appendix. Symptoms commonly include right lower abdominal pain, nausea, vomiting, and decreased appetite. However, approximately 40% of people do not have these typical symptoms. Severe complications of a ruptured appendix include widespread, painful inflammation of the inner lining of the abdominal wall and sepsis.
Radiology is the medical specialty that uses medical imaging to diagnose diseases and guide their treatment, within the bodies of humans and other animals. It began with radiography, but today it includes all imaging modalities, including those that use no ionizing electromagnetic radiation, as well as others that do, such as computed tomography (CT), fluoroscopy, and nuclear medicine including positron emission tomography (PET). Interventional radiology is the performance of usually minimally invasive medical procedures with the guidance of imaging technologies such as those mentioned above.
Bowel obstruction, also known as intestinal obstruction, is a mechanical or functional obstruction of the intestines which prevents the normal movement of the products of digestion. Either the small bowel or large bowel may be affected. Signs and symptoms include abdominal pain, vomiting, bloating and not passing gas. Mechanical obstruction is the cause of about 5 to 15% of cases of severe abdominal pain of sudden onset requiring admission to hospital.
In medical or research imaging, an incidental imaging finding is an unanticipated finding which is not related to the original diagnostic inquiry. As with other types of incidental medical findings, they may represent a diagnostic, ethical, and philosophical dilemma because their significance is unclear. While some coincidental findings may lead to beneficial diagnoses, others may lead to overdiagnosis that results in unnecessary testing and treatment, sometimes called the "cascade effect".
Lymphadenopathy or adenopathy is a disease of the lymph nodes, in which they are abnormal in size or consistency. Lymphadenopathy of an inflammatory type is lymphadenitis, producing swollen or enlarged lymph nodes. In clinical practice, the distinction between lymphadenopathy and lymphadenitis is rarely made and the words are usually treated as synonymous. Inflammation of the lymphatic vessels is known as lymphangitis. Infectious lymphadenitis affecting lymph nodes in the neck is often called scrofula.
Virtual colonoscopy is the use of CT scanning or magnetic resonance imaging (MRI) to produce two- and three-dimensional images of the colon, from the lowest part, the rectum, to the lower end of the small intestine, and to display the images on an electronic display device. The procedure is used to screen for colon cancer and polyps, and may detect diverticulosis. A virtual colonoscopy can provide 3D reconstructed endoluminal views of the bowel. VC provides a secondary benefit of revealing diseases or abnormalities outside the colon.
Dermatoscopy, also known as dermoscopy or epiluminescence microscopy, is the examination of skin lesions with a dermatoscope. It is a tool similar to a camera to allow for inspection of skin lesions unobstructed by skin surface reflections. The dermatoscope consists of a magnifier, a light source, a transparent plate and sometimes a liquid medium between the instrument and the skin. The dermatoscope is often handheld, although there are stationary cameras allowing the capture of whole body images in a single shot. When the images or video clips are digitally captured or processed, the instrument can be referred to as a digital epiluminescence dermatoscope. The image is then analyzed automatically and given a score indicating how dangerous it is. This technique is useful to dermatologists and skin cancer practitioners in distinguishing benign from malignant (cancerous) lesions, especially in the diagnosis of melanoma.
Angiomyolipomas are the most common benign tumour of the kidney. Although regarded as benign, angiomyolipomas may grow such that kidney function is impaired or the blood vessels may dilate and burst, leading to bleeding.
Quantitative computed tomography (QCT) is a medical technique that measures bone mineral density (BMD) using a standard X-ray computed tomography (CT) scanner with a calibration standard to convert Hounsfield units (HU) of the CT image to bone mineral density values. Quantitative CT scans are primarily used to evaluate bone mineral density at the lumbar spine and hip.
Computer-aided detection (CADe), also called computer-aided diagnosis (CADx), are systems that assist doctors in the interpretation of medical images. Imaging techniques in X-ray, MRI, Endoscopy, and ultrasound diagnostics yield a great deal of information that the radiologist or other medical professional has to analyze and evaluate comprehensively in a short time. CAD systems process digital images or videos for typical appearances and to highlight conspicuous sections, such as possible diseases, in order to offer input to support a decision taken by the professional.
A coronary CT calcium scan is a computed tomography (CT) scan of the heart for the assessment of severity of coronary artery disease. Specifically, it looks for calcium deposits in atherosclerotic plaques in the coronary arteries that can narrow arteries and increase the risk of heart attack. These plaques are the cause of most heart attacks, and become calcified as they develop.
A renal cyst is a fluid collection in or on the kidney. There are several types based on the Bosniak classification. The majority are benign, simple cysts that can be monitored and not intervened upon. However, some are cancerous or are suspicious for cancer and are commonly removed in a surgical procedure called nephrectomy.
Magnetic resonance imaging of the brain uses magnetic resonance imaging (MRI) to produce high quality two-dimensional or three-dimensional images of the brain and brainstem as well as the cerebellum without the use of ionizing radiation (X-rays) or radioactive tracers.
Computed tomography of the abdomen and pelvis is an application of computed tomography (CT) and is a sensitive method for diagnosis of abdominal diseases. It is used frequently to determine stage of cancer and to follow progress. It is also a useful test to investigate acute abdominal pain. Renal stones, appendicitis, pancreatitis, diverticulitis, abdominal aortic aneurysm, and bowel obstruction are conditions that are readily diagnosed and assessed with CT. CT is also the first line for detecting solid organ injury after trauma.
Computed tomography of the head uses a series of X-rays in a CT scan of the head taken from many different directions; the resulting data is transformed into a series of cross sections of the brain using a computer program. CT images of the head are used to investigate and diagnose brain injuries and other neurological conditions, as well as other conditions involving the skull or sinuses; it used to guide some brain surgery procedures as well. CT scans expose the person getting them to ionizing radiation which has a risk of eventually causing cancer; some people have allergic reactions to contrast agents that are used in some CT procedures.
A lymphocele is a collection of lymphatic fluid within the body not bordered by epithelial lining. It is usually a surgical complication seen after extensive pelvic surgery and is most commonly found in the retroperitoneal space. Spontaneous development is rare.
In the field of medicine, radiomics is a method that extracts a large number of features from medical images using data-characterisation algorithms. These features, termed radiomic features, have the potential to uncover tumoral patterns and characteristics that fail to be appreciated by the naked eye. The hypothesis of radiomics is that the distinctive imaging features between disease forms may be useful for predicting prognosis and therapeutic response for various cancer types, thus providing valuable information for personalized therapy. Radiomics emerged from the medical fields of radiology and oncology and is the most advanced in applications within these fields. However, the technique can be applied to any medical study where a pathological process can be imaged.
Aidoc Medical is an Israeli technology company that develops computer-aided simple triage and notification systems. Aidoc has obtained FDA and CE mark approval for its stroke, pulmonary embolism, cervical fracture, intracranial hemorrhage, intra-abdominal free gas, and incidental pulmonary embolism algorithms.
Emilio Quaia is an Italian radiologist, academic, and author. He is a professor of Radiology and the Director of the Radiology Department at the University of Padova.
This article incorporates text from this source, which is in the public domain .{{cite journal}}: Cite journal requires |journal= (help){{cite journal}}: Cite journal requires |journal= (help){{cite journal}}: Cite journal requires |journal= (help){{cite book}}: |website= ignored (help)| International | |
|---|---|
| National | |
| Academics | |
