Mass detection on mammograms: influence of signal shape uncertainty on human and model observers

Castella, Cyril; Eckstein, Miguel P.; Abbey, Craig K.; Kinkel, Karen; Verdun, Francis R.; Saunders, R. S.; Samei, Ehsan; Bochud, François

doi:10.1364/josaa.26.000425

Cited by 31 publications

(39 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However. prior work suggests that there is little difference in human observer performance between SKE and SKS tasks [3].…”

Section: Resultsmentioning

confidence: 99%

“…Such studies may be used to determine, for example, detection limits under controlled conditions such as threshold size or contrast, without requiring image search. Such an approach can be used to compare detection performances of different breast imaging modalities in radiological studies or virtual clinical trials (VCTs) [3,4]. The principal advantage of a model observer (MO) is the ability to reliably, and tirelessly, undertake evaluations of sets of images without recourse to the variables introduced by using groups of human observers.…”

Section: Introductionmentioning

confidence: 99%

“…The principal advantage of a model observer (MO) is the ability to reliably, and tirelessly, undertake evaluations of sets of images without recourse to the variables introduced by using groups of human observers. This approach is routed in statistical decision theory and linear discriminant analysis and has been an active area of research for many years [2,3,5].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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

“…However. prior work suggests that there is little difference in human observer performance between SKE and SKS tasks [3].…”

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

“…Moreover, for pathologies with multiple lesions, the signal parameters differ for each lesion depending on the stage of the lesion, the background tissue characteristics, etc. Several signal-known-statistically (SKS) experiments (where the signal attributes are known statistically) showed that the uncertainty and variability in signal parameters can significantly influence human performance [15], [41], [42]. This suggests that the SKS MOs may have a great potential to be closer to human observers and they have begun to draw more attention in the last decade.…”

Section: B Existing Numerical Observersmentioning

confidence: 99%

“…In order to represent the routine diagnostic process more realistically, we propose a novel nonlinear numerical observer -PCJO for the detection-localization of multiple parametric signals with random amplitude, orientation, size and location. The only known signal parameter for the PCJO is the signal shape, bearing in mind that Castella [42] reported that uncertainty and variability in signal shape do not influence human performance significantly. The PCJO also involves the perception stage to some extent.…”

Section: B Existing Numerical Observersmentioning

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

Low‐dose CT denoising via convolutional neural network with an observer loss function

2021

View full text Add to dashboard Cite

Convolutional neural network (CNN)-based denoising is an effective method for reducing complex computed tomography (CT) noise. However, the image blur induced by denoising processes is a major concern.The main source of image blur is the pixel-level loss (e.g., mean squared error [MSE] and mean absolute error [MAE]) used to train a CNN denoiser. To reduce the image blur, feature-level loss is utilized to train a CNN denoiser. A CNN denoiser trained using visual geometry group (VGG) loss can preserve the small structures, edges, and texture of the image.However, VGG loss, derived from an ImageNetpretrained image classifier, is not optimal for training a CNN denoiser for CT images. ImageNet contains natural RGB images, so the features extracted by the ImageNet-pretrained model cannot represent the characteristics of CT images that are highly correlated with diagnosis. Furthermore, a CNN denoiser trained with VGG loss causes bias in CT number. Therefore, we propose to use a binary classification network trained using CT images as a feature extractor and newly define the feature-level loss as observer loss. Methods: As obtaining labeled CT images for training classification network is difficult, we create labels by inserting simulated lesions. We conduct two separate classification tasks, signal-known-exactly (SKE) and signal-knownstatistically (SKS), and define the corresponding feature-level losses as SKE loss and SKS loss, respectively. We use SKE loss and SKS loss to train CNN denoiser. Results: Compared to pixel-level losses, a CNN denoiser trained using observer loss (i.e., SKE loss and SKS loss) is effective in preserving structure, edge, and texture. Observer loss also resolves the bias in CT number, which is a problem of VGG loss. Comparing observer losses using SKE and SKS tasks, SKS yields images having a more similar noise structure to reference images. Conclusions: Using observer loss for training CNN denoiser is effective to preserve structure, edge, and texture in denoised images and prevent the CT number bias. In particular, when using SKS loss, denoised images having a similar noise structure to reference images are generated.

show abstract

Mass detection on mammograms: influence of signal shape uncertainty on human and model observers

Cited by 31 publications

References 43 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

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

Low‐dose CT denoising via convolutional neural network with an observer loss function

Contact Info

Product

Resources

About