Learning a Channelized Observer for Image Quality Assessment

Brankov, Jovan G.; Yang, Yongyi; Wei, Liyang; Naqa, Issam El; Wernick, Miles N.

doi:10.1109/tmi.2008.2008956

Cited by 51 publications

(70 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such approaches have routinely beaten state-of-the-art pattern recognition methods, as well as humans in some selected areas. In SPECT, supervised learning and Convolutional Neural Networks (CNNs) with three layers have shown promising MO results with simulated data [7,8].…”

Section: Introductionmentioning

confidence: 99%

A deep learning model observer for use in alterative forced choice virtual clinical trials

Alnowami

Mills

Awis

et al. 2018

Medical Imaging 2018: Image Perception, Observer Performance, and Technology Assessment

View full text Add to dashboard Cite

Virtual clinical trials (VCTs) represent an alternative assessment paradigm that overcomes issues of dose, high cost and delay encountered in conventional clinical trials for breast cancer screening. However, to fully utilize the potential benefits of VCTs requires a machine-based observer that can rapidly and realistically process large numbers of experimental conditions. To address this, a Deep Learning Model Observer (DLMO) was developed and trained to identify lesion targets from normal tissue in small (200 x 200 pixel) image segments, as used in Alternative Forced Choice (AFC) studies. The proposed network consists of 5 convolutional layers with 2x2 kernels and ReLU (Rectified Linear Unit) activations, followed by max pooling with size equal to the size of the final feature maps and three dense layers. The class outputs weights from the final fully connected dense layer are used to consider sets of n images in an n-AFC paradigm to determine the image most likely to contain a target. To examine the DLMO performance on clinical data, a training set of 2814 normal and 2814 biopsy-confirmed malignant mass targets were used. This produced a sensitivity of 0.90 and a specificity of 0.92 when presented with a test data set of 800 previously unseen clinical images. To examine the DLMOs minimum detectable contrast, a second dataset of 630 simulated backgrounds and 630 images with simulated lesion and spherical targets (4mm and 6mm diameter), produced contrast thresholds equivalent to/better than human observer performance for spherical targets, and comparable (12 % difference) for lesion targets.

show abstract

Section: Introductionmentioning

confidence: 99%

A deep learning model observer for use in alterative forced choice virtual clinical trials

Alnowami

Mills

Awis

et al. 2018

Medical Imaging 2018: Image Perception, Observer Performance, and Technology Assessment

View full text Add to dashboard Cite

show abstract

“…Task-based image quality assessment approaches [1,2] characterize the image quality by measuring the performance of an observer, most oftenly a human observer, in completing a specific diagnostic task. Model observers (MOs) [3] have been proposed as surrogates for human observers to avoid the costly and time-consuming procedure involving human observers.…”

Section: Introductionmentioning

confidence: 99%

Channelized model observer for the detection and estimation of signals with unknown amplitude, orientation, and size

et al. 2013

View full text Add to dashboard Cite

As a task-based approach for medical image quality assessment, model observers (MOs) have been proposed as surrogates for human observers. While most MOs treat only signal-known-exactly (SKE) tasks, there are few studies on the signal-known-statistically (SKS) MOs, which are more clinically relevant. In this paper, we present a new SKS MO named Channelized Joint detection and estimation Observer (CJO), capable of detecting and estimating signals with unknown amplitude, orientation and size. We evaluate its estimation and detection performances using both synthesized (correlated Gaussian) backgrounds and real clinical (MR) backgrounds. The results suggest that the CJO has good performances in the SKS detection-estimation task.

show abstract

“…Since the ultimate goal of medical images is to aid clinicians in rendering a diagnosis, it is widely accepted that in order to optimize diagnostic decisions image quality should be as good as possible. Additionally, image quality should be assessed in the context of a specific diagnostic task, the so-called taskbased approach [2], [3]. During the assessment process, one or more diagnostic tasks could be performed by either human observers (radiologists) or numerical observers (mathematical models).…”

Section: Introductionmentioning

confidence: 99%

“…Thus, it has been argued that numerical observers are useful for medical image quality assessment in place of human observers [2], [6]. However, in most cases, the task performance of human observers is the ultimate test of image quality and is needed for the validation of a numerical observer [3].…”

Section: Introductionmentioning

confidence: 99%

A Perceptually Relevant Channelized Joint Observer (PCJO) for the Detection-Localization of Parametric Signals

Zhang

Cavaro‐Ménard

Callet

et al. 2012

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

Abstract-Many numerical observers have been proposed in the framework of task-based approach for medical image quality assessment. However, the existing numerical observers are still limited in diagnostic tasks: the detection task has been largely studied, while the localization task concerning one signal has been little studied and the localization of multiple signals has not been studied yet. In addition, most existing numerical observers need a priori knowledge about all the parameters of the underdetection signals, while only a few of them need at least two signal parameters. In this paper, we propose a novel numerical observer called the Perceptually relevant Channelized Joint Observer (PCJO), which cannot only detect but also localize multiple signals with unknown amplitude, orientation, size and location. We validated the PCJO for predicting human observer task performance by conducting a clinically relevant free-response subjective experiment in which six radiologists (including two experts) had to detect and localize Multiple Sclerosis (MS) lesions on Magnetic Resonance (MR) images. By using the jackknife alternative free-response operating characteristic (JAFROC) as the figure of merit (FOM), the detection-localization task performance of the PCJO was evaluated and then compared to that of the radiologists and two other numerical observersChannelized Hotelling Observer (CHO) and Goossenss CHO for detecting asymmetrical signals with random orientations. Overall, the results show that the PCJO performance was closer to that of the experts than to that of the other radiologists. The JAFROC1 FOMs of the PCJO (around 0.75) are not significantly different from those of the two experts (0.7672 and 0.7110), while the JAFROC1 FOMs of the numerical observers mentioned above (always over 0.84) outperform those of the experts. This indicates that the PCJO is a promising method for predicting radiologists' performance in the joint detection-localization task.

show abstract

Learning a Channelized Observer for Image Quality Assessment

Cited by 51 publications

References 27 publications

A deep learning model observer for use in alterative forced choice virtual clinical trials

A deep learning model observer for use in alterative forced choice virtual clinical trials

Channelized model observer for the detection and estimation of signals with unknown amplitude, orientation, and size

A Perceptually Relevant Channelized Joint Observer (PCJO) for the Detection-Localization of Parametric Signals

Contact Info

Product

Resources

About