Computer aided diagnosis of parotid gland lesions using ultrasonic multi-feature tissue characterization

Salivary gland pathologies: evolution in classification and association with unique genetic alterations

PURPOSE

The correct classification of salivary gland pathologies is crucial for choosing a treatment method and determining the prognosis. Better outcomes are now achievable thanks to the introduction of new therapy approaches, such as targeted therapies for malignant salivary gland tumors. To apply these in clinical routine, a clear classification of the lesions is required.

METHODS

The following review examines all changes from the first World Health Organization (WHO) Classification of salivary gland pathologies from 1972 to fifth edition from 2022. Possible developments in the diagnosis and classification of salivary gland pathology are also presented.

RESULTS

The current WHO classification is the fifth edition. With the development of new diagnostic methods, based on genetic alterations, it provides insight into the molecular basis of lesions. This has resulted in the evolution of classification, introduction of new entities and reclassification of existing ones.

CONCLUSIONS

Genetic alterations will become increasingly more significant in the identification of salivary gland pathologies in the future. These alterations will be helpful as prognostic and predictive biomarkers, and may also serve as targets for anti-cancer therapies.

Harmonization of robust radiomic features in the submandibular gland using multi-ultrasound systems: a preliminary study

OBJECTIVE

This study aimed to identify robust radiomic features in multiultrasonography of the submandibular gland and normalize the interdevice discrepancies by applying a machine-learning-based harmonization method.

METHODS

Ultrasonographic images of normal submandibular gland of young healthy adults, aged between 20 and 40 years, were selected from two different devices. In a total of 30 images, the region of interest was determined along the border of gland parenchyma, and 103 radiomic features were extracted using A-VIEW. The coefficient of variation (CV) was obtained for individual features, and the features showing CV less than 10% were selected. For the selected features, the interdevice discrepancy was normalized using machine-learning method, called the ComBat harmonization. Median differences of the features between the two scanners, before and after harmonization, were compared using Mann-Whitney U-test; confidence interval of 95%.

RESULTS

Among total 103 radiomic features, 17 features were selected as robust, showing CV less than 10% in both scanners. All values of selected features, except two, showed a statistical difference between the two devices. After applying the ComBat harmonization method, the median and distribution of the 16 features were harmonized to show no significant difference between the two scanners (p > 0.05). One feature remained different (p ≤ 0.05).

CONCLUSION

On ultrasonographic examination, robust radiomic features for normal submandibular gland were obtained and interdevice normalization was efficiently conducted using ComBat harmonization. Our findings would be useful for multidevices or multicenter studies based on clinical ultrasonographic imaging data to improve the accuracy of the overall diagnostic model.

Artificial Intelligence-based methods in head and neck cancer diagnosis: an overview

BACKGROUND

This paper reviews recent literature employing Artificial Intelligence/Machine Learning (AI/ML) methods for diagnostic evaluation of head and neck cancers (HNC) using automated image analysis.

METHODS

Electronic database searches using MEDLINE via OVID, EMBASE and Google Scholar were conducted to retrieve articles using AI/ML for diagnostic evaluation of HNC (2009-2020). No restrictions were placed on the AI/ML method or imaging modality used.

RESULTS

In total, 32 articles were identified. HNC sites included oral cavity (n = 16), nasopharynx (n = 3), oropharynx (n = 3), larynx (n = 2), salivary glands (n = 2), sinonasal (n = 1) and in five studies multiple sites were studied. Imaging modalities included histological (n = 9), radiological (n = 8), hyperspectral (n = 6), endoscopic/clinical (n = 5), infrared thermal (n = 1) and optical (n = 1). Clinicopathologic/genomic data were used in two studies. Traditional ML methods were employed in 22 studies (69%), deep learning (DL) in eight studies (25%) and a combination of these methods in two studies (6%).

CONCLUSIONS

There is an increasing volume of studies exploring the role of AI/ML to aid HNC detection using a range of imaging modalities. These methods can achieve high degrees of accuracy that can exceed the abilities of human judgement in making data predictions. Large-scale multi-centric prospective studies are required to aid deployment into clinical practice.

Deep learning segmentation of Primary Sjögren's syndrome affected salivary glands from ultrasonography images

Salivary gland ultrasonography (SGUS) has proven to be a promising tool for diagnosing various diseases manifesting with abnormalities in salivary glands (SGs), including primary Sjögren's syndrome (pSS). At present, the major obstacle for establishing SUGS as a standardized tool for pSS diagnosis is its low inter/intra observer reliability. The aim of this study was to address this problem by proposing a robust deep learning-based solution for the automated segmentation of SGUS images. For these purposes, four architectures were considered: a fully convolutional neural network, fully convolutional "DenseNets" (FCN-DenseNet) network, U-Net, and LinkNet. During the course of the study, the growing HarmonicSS cohort included 1184 annotated SGUS images. Accordingly, the algorithms were trained using a transfer learning approach. With regard to the intersection-over-union (IoU), the top-performing FCN-DenseNet (IoU = 0.85) network showed a considerable margin above the inter-observer agreement (IoU = 0.76) and slightly above the intra-observer agreement (IoU = 0.84) between clinical experts. Considering its accuracy and speed (24.5 frames per second), it was concluded that the FCN-DenseNet could have wider applications in clinical practice. Further work on the topic will consider the integration of methods for pSS scoring, with the end goal of establishing SGUS as an effective noninvasive pSS diagnostic tool. To aid this progress, we created inference (frozen models) files for the developed models, and made them publicly available.

Diagnostic accuracy of deep-learning with anomaly detection for a small amount of imbalanced data: discriminating malignant parotid tumors in MRI

We hypothesized that, in discrimination between benign and malignant parotid gland tumors, high diagnostic accuracy could be obtained with a small amount of imbalanced data when anomaly detection (AD) was combined with deep leaning (DL) model and the L₂-constrained softmax loss. The purpose of this study was to evaluate whether the proposed method was more accurate than other commonly used DL or AD methods. Magnetic resonance (MR) images of 245 parotid tumors (22.5% malignant) were retrospectively collected. We evaluated the diagnostic accuracy of the proposed method (VGG16-based DL and AD) and that of classification models using conventional DL and AD methods. A radiologist also evaluated the MR images. ROC and precision-recall (PR) analyses were performed, and the area under the curve (AUC) was calculated. In terms of diagnostic performance, the VGG16-based model with the L₂-constrained softmax loss and AD (local outlier factor) outperformed conventional DL and AD methods and a radiologist (ROC-AUC = 0.86 and PR-ROC = 0.77). The proposed method could discriminate between benign and malignant parotid tumors in MR images even when only a small amount of data with imbalanced distribution is available.

Radiomics-Based Assessment of Primary Sjögren's Syndrome From Salivary Gland Ultrasonography Images

Salivary gland ultrasonography (SGUS) has shown good potential in the diagnosis of primary Sjögren's syndrome (pSS). However, a series of international studies have reported needs for improvements of the existing pSS scoring procedures in terms of inter/intra observer reliability before being established as standardized diagnostic tools. The present study aims to solve this problem by employing radiomics features and artificial intelligence (AI) algorithms to make the pSS scoring more objective and faster compared to human expert scoring. The assessment of AI algorithms was performed on a two-centric cohort, which included 600 SGUS images (150 patients) annotated using the original SGUS scoring system proposed in 1992 for pSS. For each image, we extracted 907 histogram-based and descriptive statistics features from segmented salivary glands. Optimal feature subsets were found using the genetic algorithm based wrapper approach. Among the considered algorithms (seven classifiers and five regressors), the best preforming was the multilayer perceptron (MLP) classifier (κ = 0.7). The MLP over-performed average score achieved by the clinicians (κ = 0.67) by the considerable margin, whereas its reliability was on the level of human intra-observer variability (κ = 0.71). The presented findings indicate that the continuously increasing HarmonicSS cohort will enable further advancements in AI-based pSS scoring methods by SGUS. In turn, this may establish SGUS as an effective noninvasive pSS diagnostic tool, with the final goal to supplement current diagnostic tests.

Quantification of heterogeneity as a biomarker in tumor imaging: a systematic review

BACKGROUND

Many techniques are proposed for the quantification of tumor heterogeneity as an imaging biomarker for differentiation between tumor types, tumor grading, response monitoring and outcome prediction. However, in clinical practice these methods are barely used. This study evaluates the reported performance of the described methods and identifies barriers to their implementation in clinical practice.

METHODOLOGY

The Ovid, Embase, and Cochrane Central databases were searched up to 20 September 2013. Heterogeneity analysis methods were classified into four categories, i.e., non-spatial methods (NSM), spatial grey level methods (SGLM), fractal analysis (FA) methods, and filters and transforms (F&T). The performance of the different methods was compared.

PRINCIPAL FINDINGS

Of the 7351 potentially relevant publications, 209 were included. Of these studies, 58% reported the use of NSM, 49% SGLM, 10% FA, and 28% F&T. Differentiation between tumor types, tumor grading and/or outcome prediction was the goal in 87% of the studies. Overall, the reported area under the curve (AUC) ranged from 0.5 to 1 (median 0.87). No relation was found between the performance and the quantification methods used, or between the performance and the imaging modality. A negative correlation was found between the tumor-feature ratio and the AUC, which is presumably caused by overfitting in small datasets. Cross-validation was reported in 63% of the classification studies. Retrospective analyses were conducted in 57% of the studies without a clear description.

CONCLUSIONS

In a research setting, heterogeneity quantification methods can differentiate between tumor types, grade tumors, and predict outcome and monitor treatment effects. To translate these methods to clinical practice, more prospective studies are required that use external datasets for validation: these datasets should be made available to the community to facilitate the development of new and improved methods.

Clinical value of radiofrequency ultrasonic local estimators in classifying breast lesions

OBJECTIVES

We sought to summarize the features of radiofrequency ultrasonic local estimator (RULES) images of benign and malignant masses and to explore the diagnostic value of RULES scores to identify breast lumps.

METHODS

A total of 81 women with a mean age ± SD of 41.33 ± 12.03 years (range, 19-68 years) with 82 lesions seen at our hospital were included in this study. Inclusion criteria were Breast Imaging Reporting and Data System grade 2 to 5 breast lesions, preoperative 2-dimensional (2D) ultrasound (US) examinations and RULES image acquisition, no treatment before the US examinations, surgical resection in our hospital, and histopathologic results. Each RULES characteristic was scored on the basis of expected values for malignant characteristics, and this RULES scoring system was assessed by a receiver operating characteristic curve.

RESULTS

Of the 82 lesions, 45 were benign, and 37 were malignant. Malignancy was associated with multiple colors, red as the main color, colors distributed in 3 or more locations, aggregated colors, and more than half of the area filled with colors. A RULES score of 7 had the highest sum of sensitivity (67.6%) and specificity (95.6%) and the highest accuracy (82.9%) for diagnosis of malignancy. When 2D US imaging a Breast Imaging Reporting and Data System category of 4 was combined with a RULES score of 4 to detect breast cancer, the sensitivity was 83.8%; the specificity was 93.3%; and the accuracy increased to 89.0%.

CONCLUSIONS

The use of RULES images and characteristics is helpful in differentiating benign and malignant breast lesions. Diagnostic accuracy can be improved by combining 2D US imaging and RULES.

Probabilistic inverse problem to characterize tissue-equivalent material mechanical properties

The understanding of internal processes that affect the changes of consistency of soft tissue is a challenging problem. An ultrasound-monitoring Petri dish has been designed to monitor the evolution of relevant mechanical parameters during engineered tissue formation processes in real time. A better understanding of the measured ultrasonic signals required the use of numerical models of the ultrasound-tissue interactions. The extraction of relevant data and its evolution with sufficient sensitivity and accuracy is addressed by applying well-known signal processing techniques to both the experimental and numerically predicted measurements. In addition, a stochastic model-class selection formulation is used to rank which of the proposed interaction models are more plausible. The sensitivity of the system is verified by monitoring a gelation process.