A5007340702- Colorectal Cancer Screening and Detection
- Radiomics and Machine Learning in Medical Imaging
- AI in cancer detection
- Advanced X-ray and CT Imaging
- Gastric Cancer Management and Outcomes
- Radiation Dose and Imaging
- Colorectal Cancer Surgical Treatments
- COVID-19 diagnosis using AI
- Medical Imaging Techniques and Applications
- Image Retrieval and Classification Techniques
- Medical Image Segmentation Techniques
- Generative Adversarial Networks and Image Synthesis
- Lung Cancer Diagnosis and Treatment
- Interstitial Lung Diseases and Idiopathic Pulmonary Fibrosis
- Diverticular Disease and Complications
- Machine Learning in Healthcare
- Digital Radiography and Breast Imaging
- Medical Imaging and Analysis
- Artificial Intelligence in Healthcare and Education
- Pancreatic and Hepatic Oncology Research
- Advanced Image Processing Techniques
- Inflammatory Bowel Disease
- Radiology practices and education
- Dental Radiography and Imaging
- Esophageal and GI Pathology
Massachusetts General Hospital
2015-2024
Harvard University
2015-2024
John Wiley & Sons (United States)
2020
UPMC Health System
2019-2020
Duke Medical Center
2020
Swedish Medical Center
2019-2020
Johns Hopkins University
2020
American Association of Physicists in Medicine
2019-2020
Ashland (United States)
2020
Philips (Finland)
2020
We have developed a three-dimensional (3-D) computer-aided diagnosis scheme for automated detection of colonic polyps in computed tomography (CT) colonographic data sets, and assessed its performance based on colonoscopy as the gold standard. In this scheme, thick region encompassing entire wall is extracted from an isotropic volume reconstructed CT images colonography. Polyp candidates are detected by first computing 3-D geometric features that characterize polyps, folds, walls at each...
Background: Colon screening by optical colonoscopy (OC) or computed tomographic colonography (CTC) requires a laxative bowel preparation, which inhibits participation. Objective: To assess the performance of detecting adenomas 6 mm larger and patient experience laxative-free, computer-aided CTC. Design: Prospective test comparison laxative-free CTC OC. The included electronic cleansing detection. Optical examinations were initially blinded to results, subsequently revealed during colonoscope...
Rapid advances in artificial intelligence (AI) and machine learning, specifically deep learning (DL) techniques, have enabled broad application of these methods health care. The promise the DL approach has spurred further interest computer-aided diagnosis (CAD) development applications using both "traditional" newer DL-based methods. We use term CAD-AI to refer this expanded clinical decision support environment that uses traditional AI Numerous studies been published date on tools for...
Abstract The adoption of artificial intelligence (AI) tools in medicine poses challenges to existing clinical workflows. This commentary discusses the necessity context-specific quality assurance (QA), emphasizing need for robust QA measures with control (QC) procedures that encompass (1) acceptance testing (AT) before use, (2) continuous QC monitoring, and (3) adequate user training. discussion also covers essential components AT QA, illustrated real-world examples. We highlight what we see...
Colon cancer is one of the leading causes deaths in United States. However, most colon cancers can be prevented if precursor colonic polyps are detected and removed. An advanced computer-aided diagnosis (CAD) scheme was developed for automated detection at computed tomographic (CT) colonography. A region encompassing wall extracted from an isotropic volume data set obtained by interpolating CT colonographic scans along axial direction. Polyp candidates with computation three-dimensional (3D)...
One of the limitations current computer‐aided detection (CAD) polyps in CT colonography (CTC) is a relatively large number false‐positive (FP) detections. Rectal tubes (RTs) are one typical sources FPs because portion RT, especially bulbous tip, often exhibits cap‐like shape that closely mimics appearance small polyp. Radiologists can easily recognize and dismiss RT‐induced FPs; thus, they may lose their confidence CAD as an effective tool if scheme generates such “obvious” due to RTs...
One of the major challenges in computer-aided detection (CAD) polyps CT colonography (CTC) is reduction false-positive detections (FPs) without a concomitant sensitivity. A large number FPs likely to confound radiologist's task image interpretation, lower efficiency, and cause radiologists lose their confidence CAD as useful tool. Major sources generated by schemes include haustral folds, residual stool, rectal tubes, ileocecal valve, extra-colonic structures such small bowel stomach. Our...
We evaluated the effect of our novel technique feature-guided analysis polyps on reduction false-positive (FP) findings generated by computer-aided diagnosis (CAD) scheme for detection from computed tomography colonographic data sets. The performance obtained use in segmentation and feature polyp candidates was compared with that previously employed fuzzy clustering technique. also a called modified gradient concentration (MGC) performance. A total 144 sets, representing prone supine views...
The objective of this study was to assess prospectively the diagnostic accuracy computer-assisted computed tomographic colonography (CTC) in detection polypoid (pedunculated or sessile) and nonpolypoid neoplasms compare between gastroenterologists radiologists.This nationwide multicenter prospective controlled trial recruited 1,257 participants with average high risk colorectal cancer at 14 Japanese institutions. Participants had CTC colonoscopy on same day. images were interpreted...
Electronic cleansing (EC) is an emerging method for segmentation of fecal material in CT colonography (CTC) that used reducing or eliminating the requirement cathartic bowel preparation and hence improving patients' adherence to recommendations colon cancer screening. In EC, feces tagged by x-ray-opaque oral contrast agent are removed from CTC images, effectively after image acquisition. Existing EC approaches tend suffer following artifacts: degradation soft-tissue structures because...
Proper training of deep convolutional neural networks (DCNNs) requires large annotated image databases that are currently not available in CT colonography (CTC). In this study, we employed a transfer learning (DETALE) scheme to circumvent problem automated polyp detection for CTC. our method, DCNN had been pre-trained with millions non-medical images was adapted identify polyps using virtual endoluminal the candidates prompted by computer-aided (CADe) system. For evaluation, 154 CTC cases...
Purpose We have developed a novel automated technique for segmenting colonic walls the application of computer-aided polyp detection in CT colonography. In particular, was designed to minimize presence extracolonic components, such as small bowel, segmented colon. Methods The segmentation combines an improved version our previously reported anatomy-oriented colon with colon-based analysis step that performs self-adjusting volume-growing within lumen. Extracolonic components are eliminated by...
In recent years, several computer‐aided detection (CAD) schemes have been developed for the of polyps in CT colonography (CTC). However, few studies addressed problem computerized colorectal masses CTC. This is mostly because are considered to be well visualized by a radiologist their size and invasiveness. Nevertheless, automated would naturally complement CTC produce more comprehensive computer aid radiologists. Therefore, this study, we identified some problems involved with masses,...
Three-dimensional (3D) convolutional neural networks (CNNs) can process volumetric medical imaging data in their native input form. However, there is little information about the comparative performance of such models general and CT colonography (CTC) particular. We compared a 3D densely connected CNN (3D-DenseNet) with those popular residual (3D-ResNet) Visual Geometry Group (3D-VGG) reduction false-positive detections (FPs) computer-aided detection (CADe) polyps CTC. VGG earliest design...