Eigenrank by committee: Von-Neumann entropy based data subset selection and failure prediction for deep learning based medical image segmentation

Gaonkar, Bilwaj; Beckett, Joel; Attiah, Mark; Ahn, Christine S.; Edwards, Matthew D.; Wilson, Bayard; Laiwalla, Azim; Salehi, Banafsheh; Yoo, Bryan; Bui, Alex A. T.; Macyszyn, Luke

doi:10.1016/j.media.2020.101834

Cited by 12 publications

(4 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More details on our deep models can be found in our previously published work. 17,18 Procedure Automatic segmentations of spinal canals were then generated using the axial T2 slices of MRI scans from the cohort of 140 patients described above. An example of an automatically obtained spinal canal segmentation is shown in Figure 1.…”

Section: Machine Learning Trainingmentioning

confidence: 99%

Predicting Spinal Surgery Candidacy From Imaging Data Using Machine Learning

et al. 2021

Self Cite

View full text Add to dashboard Cite

BACKGROUND The referral process for consultation with a spine surgeon remains inefficient, given a substantial proportion of referrals to spine surgeons are nonoperative. OBJECTIVE To develop a machine-learning-based algorithm which accurately identifies patients as candidates for consultation with a spine surgeon, using only magnetic resonance imaging (MRI). METHODS We trained a deep U-Net machine learning model to delineate spinal canals on axial slices of 100 normal lumbar MRI scans which were previously delineated by expert radiologists and neurosurgeons. We then tested the model against lumbar MRI scans for 140 patients who had undergone lumbar spine MRI at our institution (60 of whom ultimately underwent surgery, and 80 of whom did not). The model generated automated segmentations of the lumbar spinal canals and calculated a maximum degree of spinal stenosis for each patient, which served as our biomarker for surgical pathology warranting expert consultation. RESULTS The machine learning model correctly predicted surgical candidacy (ie, whether patients ultimately underwent lumbar spinal decompression) with high accuracy (area under the curve = 0.88), using only imaging data from lumbar MRI scans. CONCLUSION Automated interpretation of lumbar MRI scans was sufficient to correctly determine surgical candidacy in nearly 90% of cases. Given that a significant proportion of referrals placed for spine surgery evaluation fail to meet criteria for surgical intervention, our model could serve as a valuable tool for patient triage and thereby address some of the inefficiencies within the outpatient surgical referral process.

show abstract

Section: Machine Learning Trainingmentioning

confidence: 99%

Predicting Spinal Surgery Candidacy From Imaging Data Using Machine Learning

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…The contrast, colors, and brightness depend on the scene's characteristics, the settings of the devices, and the quality of the components [23]. The non-traditional image enhancement techniques are: filtering linear (linear filtering), non-linear contrast adjustments (non-linear contrast adjustments), random-noise reduction, filter models for noise reduction (pattern noise reduction filters), and color processing [24]. Linear filtering techniques, such as sharpening, deblurring (anti-blur), edge enhancement, and deconvolution (correction technique based on an algorithm that allows reconstruction of the missing elements on a statistical basis, remove the disturbing factors and make it possible to create a higher quality image), they are used to increase the contrast of small details in an image [25].…”

Section: Image Improvement Techniquesmentioning

confidence: 99%

Ramifications of incorrect image segmentations; emphasizing on the potential effects on deep learning methods failure

Al-Dmour

2022

J Big Data

View full text Add to dashboard Cite

Introduction Detecting failure cases is critical to ensure a secure self-driving system. Any flaw in the system directly results in an accident. In genuine class, the model’s probability reflects better-reflected model confidence. As a result, the confidence distributions of failed predictions were changed to lower values. In contrast, accurate predictions were remained associated with high values, allowing for considerably more excellent separability between such prediction types. The study investigates the association of ramifications with computational color constancy that can negatively influence CNN’s image classification and semantic segmentation. Methodology Image datasets were used to conduct different scales and complexity experiments. For instance, minimal and straightforward images of digits were comparatively provided through MNIST and SVHN datasets. The dataset’s standard validation set was employed to test and compute additional metrics because ground truth that is not publicly available for some test sets. Results The results depicted that baseline methods were outperformed through the proposed approach with a considerable variant on minimal datasets or models in every context. Therefore, Transmission Control Protocol (TCP) is appropriate in failure prediction, and ConfidNet is competent to be fulfilled as confidence criterion. Further, one of the solutions would be to elevate the validation set size, but this would influence the prediction performance of a failure model. On the contrary, the confidence estimation was based on models with test predictive performance levels, similar to baselines. Conclusions The gap between validation accuracy and training accuracy was significant on CIFAR-100, which indicates the modest enhancement for failure detection via the validation set.

show abstract

“…For a stationary hydrological time series, the methods to detect its short‐term dependence are mainly divided into non‐parametric methods and parametric methods. Typical non‐parametric methods include Spearman rank order serial correlation test (Zar, 1972) and rank von Neumann ratio (Gaonkar et al., 2021). Parametric methods, such as the autocorrelation coefficient test (Fathian et al., 2016), are commonly used for detecting short‐term dependence.…”

Section: Introductionmentioning

confidence: 99%

Correlation Coefficient‐Based Information Criterion for Quantification of Dependence Characteristics in Hydrological Time Series

Xie

Huo

Sang

et al. 2022

Water Resources Research

View full text Add to dashboard Cite

Generally, dependence means that the value of a hydrological variable at a certain time is not random but related to its previous values (Moravej & Khalili, 2015). For example, drought or flood events usually have a propensity to occur in clusters (Moravej & Khalili, 2015;Paschalis et al., 2012;Tan et al., 2017). Determining the dependence characteristics of hydrological processes is necessary to understand their complex variations and for hydrological calculation and design (

show abstract

Eigenrank by committee: Von-Neumann entropy based data subset selection and failure prediction for deep learning based medical image segmentation

Cited by 12 publications

References 13 publications

Predicting Spinal Surgery Candidacy From Imaging Data Using Machine Learning

Predicting Spinal Surgery Candidacy From Imaging Data Using Machine Learning

Ramifications of incorrect image segmentations; emphasizing on the potential effects on deep learning methods failure

Correlation Coefficient‐Based Information Criterion for Quantification of Dependence Characteristics in Hydrological Time Series

Contact Info

Product

Resources

About