Nonalcoholic fatty liver disease (NAFLD) detection and deep learning in a Chinese community-based population

OBJECTIVES

We aimed to develop and validate a deep learning system (DLS) by using an auxiliary section that extracts and outputs specific ultrasound diagnostic features to improve the explainable, clinical relevant utility of using DLS for detecting NAFLD.

METHODS

In a community-based study of 4144 participants with abdominal ultrasound scan in Hangzhou, China, we sampled 928 (617 [66.5%] females, mean age: 56 years ± 13 [standard deviation]) participants (2 images per participant) to develop and validate DLS, a two-section neural network (2S-NNet). Radiologists' consensus diagnosis classified hepatic steatosis as none steatosis, mild, moderate, and severe. We also explored the NAFLD detection performance of six one-section neural network models and five fatty liver indices on our data set. We further evaluated the influence of participants' characteristics on the correctness of 2S-NNet by logistic regression.

RESULTS

Area under the curve (AUROC) of 2S-NNet for hepatic steatosis was 0.90 for ≥ mild, 0.85 for ≥ moderate, and 0.93 for severe steatosis, and was 0.90 for NAFLD presence, 0.84 for moderate to severe NAFLD, and 0.93 for severe NAFLD. The AUROC of NAFLD severity was 0.88 for 2S-NNet, and 0.79-0.86 for one-section models. The AUROC of NAFLD presence was 0.90 for 2S-NNet, and 0.54-0.82 for fatty liver indices. Age, sex, body mass index, diabetes, fibrosis-4 index, android fat ratio, and skeletal muscle via dual-energy X-ray absorptiometry had no significant impact on the correctness of 2S-NNet (p > 0.05).

CONCLUSIONS

By using two-section design, 2S-NNet had improved the performance for detecting NAFLD with more explainable, clinical relevant utility than using one-section design.

KEY POINTS

• Based on the consensus review derived from radiologists, our DLS (2S-NNet) had an AUROC of 0.88 by using two-section design and yielded better performance for detecting NAFLD than using one-section design with more explainable, clinical relevant utility. • The 2S-NNet outperformed five fatty liver indices with the highest AUROCs (0.84-0.93 vs. 0.54-0.82) for different NAFLD severity screening, indicating screening utility of deep learning-based radiology may perform better than blood biomarker panels in epidemiology. • The correctness of 2S-NNet was not significantly influenced by individual's characteristics, including age, sex, body mass index, diabetes, fibrosis-4 index, android fat ratio, and skeletal muscle via dual-energy X-ray absorptiometry.

Accessory salivary tissue in the mylohyoid boutonnière: a clinical and radiologic pseudolesion of the oral cavity

BACKGROUND AND PURPOSE

Though classically depicted as a continuous muscular barrier between the sublingual and submandibular spaces, the mylohyoid muscle is often discontinuous. These areas of discontinuity may contain fat, blood vessels, salivary tissue, or combinations thereof that may be mistaken both clinically and radiologically for pathologic abnormalities. We sought to demonstrate the prevalence and radiologic appearance of dehiscence of the mylohyoid muscle.

METHODS

One hundred axial, contrast-enhanced CT studies of the neck, obtained over a 10-month period, were retrospectively reviewed. Inclusion criteria included 3-mm-thick slices and absence of pathologic abnormalities or surgical changes in the oral cavity. Scans were assessed for the presence and contents of mylohyoid defects such as accessory salivary tissue, defined as nonlymphoid tissue within defects in the mylohyoid, having attenuation and enhancement characteristics similar to those of orthotopic sublingual and submandibular salivary tissue.

RESULTS

Mylohyoid defects were identified in 77 of 100 individuals. The deficiencies were bilateral in 67% and unilateral in 33%. Accessory salivary tissue was identified in 37 of 100. Fat and blood vessels were commonly identified within the mylohyoid defects. Sixty-one percent of the defects contained only fat. Thirty-five percent of the defects contained blood vessels.

CONCLUSION

Deficiencies in the mylohyoid muscle were visible in 77% of individuals who underwent scanning. The defects may contain fat, blood vessels, salivary tissue, or all three characteristics. Accessory salivary tissue was identified in 37% of individuals who underwent scanning. Recognition of mylohyoid deficiencies and the typical appearance of accessory salivary tissue will allow accurate diagnosis of this benign, anatomic variant.