- Browse by Subject
Browsing by Subject "Lesions"
Now showing 1 - 4 of 4
Results Per Page
Sort Options
Item Automated Microaneurysms Detection in Retinal Images Using Radon Transform and Supervised Learning: Application to Mass Screening of Diabetic Retinopathy(IEEE, 2021) Tavakoli, Meysam; Mehdizadeh, Alireza; Aghayan, Afshin; Shahri, Reza Pourreza; Ellis, Tim; Dehmeshki, Jamshid; Physics, School of ScienceDetection of red lesions in color retinal images is a critical step to prevent the development of vision loss and blindness associated with diabetic retinopathy (DR). Microaneurysms (MAs) are the most frequently observed and are usually the first lesions to appear as a consequence of DR. Therefore, their detection is necessary for mass screening of DR. However, detecting these lesions is a challenging task because of the low image contrast, and the wide variation of imaging conditions. Recently, the emergence of computer-aided diagnosis systems offers promising approaches to detect these lesions for diagnostic purposes. In this paper we focus on developing unsupervised and supervised techniques to cope intelligently with the MAs detection problem. In the first step, the retinal images are preprocessed to remove background variation in order to achieve a high level of accuracy in the detection. In the main processing step, important landmarks such as the optic nerve head and retinal vessels are detected and masked using the Radon transform (RT) and multi-overlapping windows. Finally, the MAs are detected and numbered by using a combination of RT and a supervised support vector machine classifier. The method was tested on three publicly available datasets and a local database comprising a total of 749 images. Detection performance was evaluated using sensitivity, specificity, and FROC analysis. From the image analysis viewpoint, DR was detected with a sensitivity of 100% and a specificity of 93% on average across all of these databases. Moreover, from lesion-based analysis the proposed approach detected the MAs with sensitivity of 95.7% with an average of 7 false positives per image. These results compare favourably with the best of the published results to date.Item Chronic Posttraumatic Epilepsy following Neocortical Undercut Lesion in Mice(Public Library of Science (PLoS), 2016) Ping, Xingjie; Jin, Xiaoming; Department of Anatomy & Cell Biology, IU School of MedicinePosttraumatic epilepsy (PTE) usually develops in a small percentage of patients of traumatic brain injury after a varying latent period. Modeling this chronic neurological condition in rodents is time consuming and inefficient, which constitutes a significant obstacle in studying its mechanism and discovering novel therapeutics for its prevention and treatment. Partially isolated neocortex, or undercut, is known to induce cortical hyperexcitability and epileptiform activity in vitro, and has been used extensively for studying the neurophysiological mechanism of posttraumatic epileptogenesis. However, whether the undercut lesion in rodents causes chronic epileptic seizures has not been systematically characterized. Here we used a miniature telemetry system to continuously monitor electroencephalography (EEG) in adult C57BL mice for up to 3 months after undercut surgery. We found that 50% of animals developed spontaneous seizures between 16-50 days after injury. The mean seizure duration was 8.9±3.6 seconds, and the average seizure frequency was 0.17±0.17 times per day. There was no progression in seizure frequency and duration over the recording period. Video monitoring revealed behavioral arrests and clonic limb movement during seizure attacks. A pentylenetetrazol (PTZ) test further showed increased seizure susceptibility in the undercut mice. We conclude that undercut lesion in mice is a model of chronic PTE that involves spontaneous epileptic seizures.Item Obscure Overt Gastrointestinal Bleeding Due To Isolated Small Bowel Angiomatosis(American College of Gastroenterology, 2016-04) El Hajj, Ihab I.; Martinez, Melissa; Chiorean, Michael V.; Cote, Gregory A.; Department of Medicine, IU School of MedicineIsolated small bowel angiomatosis is a rare entity with a distinctive endoscopic appearance. A multidisciplinary approach is often required to diagnose and treat these complex lesions. We present 2 cases of isolated small bowel angiomatosis, and illustrate the endoscopic findings that may guide similar diagnoses.Item Weakly-Supervised Cross-Domain Adaptation for Endoscopic Lesions Segmentation(IEEE, 2021) Dong, Jiahua; Cong, Yang; Sun, Gan; Yang, Yunsheng; Xu, Xiaowei; Ding, Zhengming; Computer Information and Graphics Technology, School of Engineering and TechnologyWeakly-supervised learning has attracted growing research attention on medical lesions segmentation due to significant saving in pixel-level annotation cost. However, 1) most existing methods require effective prior and constraints to explore the intrinsic lesions characterization, which only generates incorrect and rough prediction; 2) they neglect the underlying semantic dependencies among weakly-labeled target enteroscopy diseases and fully-annotated source gastroscope lesions, while forcefully utilizing untransferable dependencies leads to the negative performance. To tackle above issues, we propose a new weakly-supervised lesions transfer framework, which can not only explore transferable domain-invariant knowledge across different datasets, but also prevent the negative transfer of untransferable representations. Specifically, a Wasserstein quantified transferability framework is developed to highlight wide-range transferable contextual dependencies, while neglecting the irrelevant semantic characterizations. Moreover, a novel self-supervised pseudo label generator is designed to equally provide confident pseudo pixel labels for both hard-to-transfer and easy-to-transfer target samples. It inhibits the enormous deviation of false pseudo pixel labels under the self-supervision manner. Afterwards, dynamically-searched feature centroids are aligned to narrow category-wise distribution shift. Comprehensive theoretical analysis and experiments show the superiority of our model on the endoscopic dataset and several public datasets.