Detection of Polycystic Ovary Syndrome from Ultrasound Images Using SIFT Descriptors

2019 ◽  
Vol 9 (2) ◽  
pp. 26-30 ◽  
Author(s):  
Gopalakrishnan C ◽  
Iyapparaja M
Keyword(s):  
Polycystic Ovary Syndrome ◽  
Polycystic Ovary ◽  
Ultrasound Images ◽  
Ovary Syndrome

scholarly journals Data mining polycystic ovary morphology in electronic medical record ultrasound reports

2019 ◽  
Vol 5 (1) ◽  
Author(s):  
Jay Jojo Cheng ◽  
Shruthi Mahalingaiah
Keyword(s):  
Polycystic Ovary Syndrome ◽  
Large Scale ◽  
Polycystic Ovary ◽  
Medical Center ◽  
Ultrasound Images ◽  
Dominant Follicle ◽  
Ovary Syndrome ◽  
Test Set ◽  
Report Text

Abstract Background Polycystic ovary syndrome (PCOS) is characterized by hyperandrogenemia, oligo-anovulation, and numerous ovarian cysts. Hospital electronic medical records provide an avenue for investigating polycystic ovary morphology commonly seen in PCOS at a large scale. The purpose of this study was to develop and evaluate the performance of two machine learning text algorithms, for classification of polycystic ovary morphology (PCOM) in pelvic ultrasounds. Methods Pelvic ultrasound reports from patients at Boston Medical Center between October 1, 2003 and December 12, 2016 were included for analysis, which resulted in 39,093 ultrasound reports from 25,535 unique women. Following the 2003 Rotterdam Consensus Criteria for polycystic ovary syndrome, 2000 randomly selected ultrasounds were expert labeled for PCOM status as present, absent, or unidentifiable (not able to be determined from text alone). An ovary was marked as having PCOM if there was mention of numerous peripheral follicles or if the volume was greater than 10 ml in the absence of a dominant follicle or other confounding pathology. Half of the labeled data was used to develop and refine the algorithms, and the other half was used as a test set for evaluating its accuracy. Results On the evaluation set of 1000 random US reports, the accuracy of the classifiers were 97.6% (95% CI: 96.5, 98.5%) and 96.1% (94.7, 97.2%). Both models were more adept at identifying PCOM-absent ultrasounds than either PCOM-unidentifiable or PCOM-present ultrasounds. The two classifiers estimated prevalence of PCOM within the whole set of 39,093 ultrasounds to be 44% PCOM-absent, 32% PCOM-unidentifiable, and 24% PCOM-present. Conclusions Although accuracy measured on the test set and inter-rater agreement between the two classifiers (Cohen’s Kappa = 0.988) was high, a major limitation of our approach is that it uses the ultrasound report text as a proxy and does not directly count follicles from the ultrasound images themselves.

scholarly journals Predicting & Identifying Risk of Polycystic Ovary Syndrome (Pcos)

2020 ◽  
Vol 9 (4) ◽  
pp. 1805-1808
Keyword(s):  
Genetic Algorithm ◽  
Polycystic Ovary Syndrome ◽  
Polycystic Ovary ◽  
Back Propagation ◽  
Machine Learning Algorithms ◽  
Main Concern ◽  
Ultrasound Images ◽  
Back Propagation Algorithm ◽  
Ovary Syndrome ◽  
Propagation Algorithm

Polycystic Ovary syndrome is a disorder that many women faces during their reproductive age, due to this they suffer from diabetes, infertility and high blood pressure. Diagnosis of this disorder is mainly done through various types of screenings like ultrasound images. Imaging is the most important factor in the diagnosis, through ultrasound images the follicles generated and cysts formed are easily affected. Although, this is the best method for diagnosis, the main concern is the symptoms shown by this disorder are many times ignored because symptoms like acne, hair loss, and weight gain can also be the causes of some other problem and this leads to the PCOS getting more severe. This paper can be said as a prevention measure or as an alert that one needs to visit hospital for screening. It will help female to recognize the symptoms at early age so that they can take required steps toward the cure. The proposed work is based on the images obtained after ultrasound and how the noises that occur in them can be removed by various methods like data mining, machine learning algorithms. This paper will provide the overview of predicting the disorder using symptoms as parameters through genetic algorithm and back propagation algorithm in neural network. Since, genetic algorithm and back propagation algorithm is known for their accuracy can produce better results

Polycystic Ovary Syndrome

2014 ◽  
Author(s):  
Lubna Pal ◽  
Kimberly Keefe
Keyword(s):  
Polycystic Ovary Syndrome ◽  
Depressive Disorders ◽  
Polycystic Ovary ◽  
Transvaginal Ultrasound ◽  
Oral Glucose ◽  
Ultrasound Images ◽  
Ovary Syndrome ◽  
The Metabolic Syndrome ◽  
Obstructive Sleep ◽  
Increased Risk

Polycystic ovary syndrome (PCOS) is a commonly encountered endocrine disorder that is characterized by a combination of hyperandrogenism, menstrual disturbances (predominantly oligomenorrhea), and a classic sonographic polycystic ovarian morphology. Additional sequelae associated with PCOS include infertility and enhanced risk of developing type 2 diabetes mellitus and cardiovascular disease. The prevalence of depressive disorders and obstructive sleep apnea is disproportionately higher in women with PCOS, and this population is at increased risk for endometrial hyperplasia and endometrial cancer. This chapter reviews the definition, epidemiology, etiology and genetics, pathophysiology, diagnosis (including history, physical examination, and laboratory tests), differential diagnosis, and management of PCOS. Syndromes and diseases associated with PCOS are discussed. Tables describe the three approaches to PCOS, conditions mimicking PCOS, diagnosis of the metabolic syndrome in women using the National Cholesterol Education Program criteria, workup for PCOS, comprehensive care for PCOS patients, and the multistep approach to treatment of PCOS-related anovulatory infertility. Figures include transvaginal ultrasound images of a normal ovary and a multifollicular ovary in a woman with PCOS, the Ferriman-Gallwey scoring system for quantifying hirsutism, acanthosis nigrans on the neck of a woman with PCOS and insulin resistance, the relationship between body mass index and basal luteinizing hormone levels, oral glucose challenge results in nonobese women with PCOS, and an algorithm for treatment decision making. This review contains 6 highly rendered figures, 6 tables, and 120 references.

Sign in / Sign up

Export Citation Format

Share Document