Explainable Image Quality Assessments in Teledermatological Photography.

Background and Objectives: Image quality is a crucial factor in the effectiveness and efficiency of teledermatological consultations. However, up to 50% of images sent by patients have quality issues, thus increasing the time to diagnosis and treatment. An automated, easily deployable, explainable method for assessing image quality is necessary to improve the current teledermatological consultation flow. We introduce ImageQX, a convolutional neural network for image quality assessment with a learning mechanism for identifying the most common poor image quality explanations: bad framing, bad lighting, blur, low resolution, and distance issues. Methods: ImageQX was trained on 26,635 photographs and validated on 9,874 photographs, each annotated with image quality labels and poor image quality explanations by up to 12 board-certified dermatologists. The photographic images were taken between 2017 and 2019 using a mobile skin disease tracking application accessible worldwide. Results: Our method achieves expert-level performance for both image quality assessment and poor image quality explanation. For image quality assessment, ImageQX obtains a macro F1-score of 0.73 ± 0.01, which places it within standard deviation of the pairwise inter-rater F1-score of 0.77 ± 0.07. For poor image quality explanations, our method obtains F1-scores of between 0.37 ± 0.01 and 0.70 ± 0.01, similar to the inter-rater pairwise F1-score of between 0.24 ± 0.15 and 0.83 ± 0.06. Moreover, with a size of only 15 MB, ImageQX is easily deployable on mobile devices. Conclusion: With an image quality detection performance similar to that of dermatologists, incorporating ImageQX into the teledermatology flow can enable a better, faster flow for remote consultations.

Toward Reduction in False-Positive Thyroid Nodule Biopsies with a Deep Learning-based Risk Stratification System Using US Cine-Clip Images.

Purpose: To develop a deep learning-based risk stratification system for thyroid nodules using US cine images. Materials and Methods: In this retrospective study, 192 biopsy-confirmed thyroid nodules (175 benign, 17 malignant) in 167 unique patients (mean age, 56 years ± 16 [SD], 137 women) undergoing cine US between April 2017 and May 2018 with American College of Radiology (ACR) Thyroid Imaging Reporting and Data System (TI-RADS)-structured radiology reports were evaluated. A deep learning-based system that exploits the cine images obtained during three-dimensional volumetric thyroid scans and outputs malignancy risk was developed and compared, using fivefold cross-validation, against a two-dimensional (2D) deep learning-based model (Static-2DCNN), a radiomics-based model using cine images (Cine-Radiomics), and the ACR TI-RADS level, with histopathologic diagnosis as ground truth. The system was used to revise the ACR TI-RADS recommendation, and its diagnostic performance was compared against the original ACR TI-RADS. Results: The system achieved higher average area under the receiver operating characteristic curve (AUC, 0.88) than Static-2DCNN (0.72, P = .03) and tended toward higher average AUC than Cine-Radiomics (0.78, P = .16) and ACR TI-RADS level (0.80, P = .21). The system downgraded recommendations for 92 benign and two malignant nodules and upgraded none. The revised recommendation achieved higher specificity (139 of 175, 79.4%) than the original ACR TI-RADS (47 of 175, 26.9%; P < .001), with no difference in sensitivity (12 of 17, 71% and 14 of 17, 82%, respectively; P = .63). Conclusion: The risk stratification system using US cine images had higher diagnostic performance than prior models and improved specificity of ACR TI-RADS when used to revise ACR TI-RADS recommendation.Keywords: Neural Networks, US, Abdomen/GI, Head/Neck, Thyroid, Computer Applications-3D, Oncology, Diagnosis, Supervised Learning, Transfer Learning, Convolutional Neural Network (CNN) Supplemental material is available for this article. © RSNA, 2022.

Quantitative Framework for Risk Stratification of Thyroid Nodules With Ultrasound: A Step Toward Automated Triage of Thyroid Cancer.

OBJECTIVE. The purpose of this study was to explore whether a quantitative framework can be used to sonographically differentiate benign and malignant thyroid nodules at a level comparable to that of experts. MATERIALS AND METHODS. A dataset of ultrasound images of 92 biopsy-confirmed nodules was collected retrospectively. The nodules were delineated and annotated by two expert radiologists using the standardized Thyroid Imaging Reporting and Data System lexicon of the American College of Radiology. In the framework studied, quantitative features of echogenicity, texture, edge sharpness, and margin curvature properties of thyroid nodules were analyzed in a regularized logistic regression model to predict malignancy of a nodule. The framework was validated by leave-one-out cross-validation technique, and ROC AUC, sensitivity, and specificity were used to compare with those obtained with six expert annotation-based classifiers. RESULTS. The AUC of the proposed method was 0.828 (95% CI, 0.715-0.942), which was greater than or comparable to that of the expert classifiers, for which the AUC values ranged from 0.299 to 0.829 (p = 0.99). Use of the proposed framework could have avoided biopsy of 20 of 46 benign nodules in a curative strategy (at sensitivity of 1, statistically significantly higher than three expert classifiers) or helped identify 10 of 46 malignancies in a conservative strategy (at specificity of 1, statistically significantly higher than five expert classifiers). CONCLUSION. When the proposed quantitative framework was used, thyroid nodule malignancy was predicted at the level of expert classifiers. Such a framework may ultimately prove useful as the basis for a fully automated system of thyroid nodule triage.

Toward Automated Pre-Biopsy Thyroid Cancer Risk Estimation in Ultrasound.

We propose a computational framework for automated cancer risk estimation of thyroid nodules visualized in ultrasound (US) images. Our framework estimates the probability of nodule malignancy using random forests on a rich set of computational features. An expert radiologist annotated thyroid nodules in 93 biopsy-confirmed patients using semantic image descriptors derived from standardized lexicon. On our dataset, the AUC of the proposed method was 0.70, which was comparable to five baseline expert annotation-based classifiers with AUC values from 0.72 to 0.81. Moreover, the use of the framework for decision making on nodule biopsy could have spared five out of 46 benign nodule biopsies at no cost to the health of patients with malignancies. Our results confirm the feasibility of computer-aided tools for noninvasive malignancy risk estimation in patients with thyroid nodules that could help to decrease the number of unnecessary biopsies and surgeries.

Robust estimation of unbalanced mixture models on samples with outliers.

Mixture models are often used to compactly represent samples from heterogeneous sources. However, in real world, the samples generally contain an unknown fraction of outliers and the sources generate different or unbalanced numbers of observations. Such unbalanced and contaminated samples may, for instance, be obtained by high density data sensors such as imaging devices. Estimation of unbalanced mixture models from samples with outliers requires robust estimation methods. In this paper, we propose a novel robust mixture estimator incorporating trimming of the outliers based on component-wise confidence level ordering of observations. The proposed method is validated and compared to the state-of-the-art FAST-TLE method on two data sets, one consisting of synthetic samples with a varying fraction of outliers and a varying balance between mixture weights, while the other data set contained structural magnetic resonance images of the brain with tumors of varying volumes. The results on both data sets clearly indicate that the proposed method is capable to robustly estimate unbalanced mixtures over a broad range of outlier fractions. As such, it is applicable to real-world samples, in which the outlier fraction cannot be estimated in advance.