70. Computer aided detection system for the automated classification of clustered microcalcifications in digital mammograms

2018 ◽  
Vol 56 ◽  
pp. 106-107
Author(s):  
R. Massafra ◽  
A. Fanizzi ◽  
T. Basile ◽  
R. Bellotti ◽  
R. Carbonara ◽  
...  
Author(s):  
Shruti Jain

: Lung carcinoma is most commonly occurring death through cancer across the world that mainly occurs due to Smoking. Small cell lung cancer and Non small cell lung cancer (NSCLC) are the two different types of Lung cancer. For the detection and classification of lung cancer, there are different techniques in the literature. This paper emphasis on the three class classification of the Adenocarcinomas, Squamous cell carcinomas, and large cell carcinomas of NSCLC . For precise and superior results, Computer Aided Detection (CADe) system is designed so that the radiologist can diagnose the carcinoma in the ultrasonic images comfortably. CADe analyses the quality of the images, select region of interest, preprocess the data, extract the features and classify the cancer. After exhaustive literature survey, Laws’ mask and SVM classifier with Gaussian RBF kernels is used in this paper. The experimentations were performed on 92 images using 50% - 50% training and testing criteria. The comparative study reveals that our system for separating three class lung cancer provides 95.65% average accuracy for Laws' mask 3 dimensions using SVM classifier that is maximum among the existing methods reported in the literature using the same dataset.


Radiology ◽  
2005 ◽  
Vol 235 (2) ◽  
pp. 385-390 ◽  
Author(s):  
Jay A. Baker ◽  
Eric L. Rosen ◽  
Michele M. Crockett ◽  
Joseph Y. Lo

Author(s):  
Wei Yan Peh ◽  
John Thomas ◽  
Elham Bagheri ◽  
Rima Chaudhari ◽  
Sagar Karia ◽  
...  

Pathological slowing in the electroencephalogram (EEG) is widely investigated for the diagnosis of neurological disorders. Currently, the gold standard for slowing detection is the visual inspection of the EEG by experts, which is time-consuming and subjective. To address those issues, we propose three automated approaches to detect slowing in EEG: Threshold-based Detection System (TDS), Shallow Learning-based Detection System (SLDS), and Deep Learning-based Detection System (DLDS). These systems are evaluated on channel-, segment-, and EEG-level. The three systems perform prediction via detecting slowing at individual channels, and those detections are arranged in histograms for detection of slowing at the segment- and EEG-level. We evaluate the systems through Leave-One-Subject-Out (LOSO) cross-validation (CV) and Leave-One-Institution-Out (LOIO) CV on four datasets from the US, Singapore, and India. The DLDS achieved the best overall results: LOIO CV mean balanced accuracy (BAC) of 71.9%, 75.5%, and 82.0% at channel-, segment- and EEG-level, and LOSO CV mean BAC of 73.6%, 77.2%, and 81.8% at channel-, segment-, and EEG-level. The channel- and segment-level performance is comparable to the intra-rater agreement (IRA) of an expert of 72.4% and 82%. The DLDS can process a 30 min EEG in 4 s and can be deployed to assist clinicians in interpreting EEGs.


2020 ◽  
Vol 11 ◽  
Author(s):  
Yaoxian Jiang ◽  
Guangyao Yang ◽  
Yuan Liang ◽  
Qin Shi ◽  
Boqi Cui ◽  
...  

PurposeA computer-aided system was used to semiautomatically measure Tönnis angle, Sharp angle, and center-edge (CE) angle using contours of the hip bones to establish an auxiliary measurement model for developmental screening or diagnosis of hip joint disorders.MethodsWe retrospectively analyzed bilateral hip x-rays for 124 patients (41 men and 83 women aged 20–70 years) who presented at the Affiliated Zhongshan Hospital of Dalian University in 2017 and 2018. All images were imported into a computer-aided detection system. After manually outlining hip bone contours, Tönnis angle, Sharp angle, and CE angle marker lines were automatically extracted, and the angles were measured and recorded. An imaging physician also manually measured all angles and recorded hip development, and Pearson correlation coefficients were used to compare computer-aided system measurements with imaging physician measurements. Accuracy for different angles was calculated, and the area under the receiver operating characteristic (AUROC) curve was used to represent the diagnostic efficiency of the computer-aided system.ResultsFor Tönnis angle, Sharp angle, and CE angle, correlation coefficients were 0.902, 0.887, and 0.902, respectively; the accuracies of the computer-aided detection system were 89.1, 93.1, and 82.3%; and the AUROC curve values were 0.940, 0.956, and 0.948.ConclusionThe measurements of Tönnis angle, Sharp angle, and CE angle using the semiautomatic system were highly correlated with the measurements of the imaging physician and can be used to assess hip joint development with high accuracy and diagnostic efficiency.


Sign in / Sign up

Export Citation Format

Share Document