Dataset Information

Improving B-mode ultrasound diagnostic performance for focal liver lesions using deep learning: A multicentre study.

ABSTRACT:

Background

The diagnosis performance of B-mode ultrasound (US) for focal liver lesions (FLLs) is relatively limited. We aimed to develop a deep convolutional neural network of US (DCNN-US) for aiding radiologists in classification of malignant from benign FLLs.

Materials and methods

This study was conducted in 13 hospitals and finally 2143 patients with 24,343 US images were enrolled. Patients who had non-cystic FLLs with pathological results were enrolled. The FLLs from 11 hospitals were randomly divided into training and internal validations (IV) cohorts with a 4:1 ratio for developing and evaluating DCNN-US. Diagnostic performance of the model was verified using external validation (EV) cohort from another two hospitals. The diagnosis value of DCNN-US was compared with that of contrast enhanced computed tomography (CT)/magnetic resonance image (MRI) and 236 radiologists, respectively.

Findings

The AUC of Model^LBC for FLLs was 0.924 (95% CI: 0.889-0.959) in the EV cohort. The diagnostic sensitivity and specificity of Model^LBC were superior to 15-year skilled radiologists (86.5% vs 76.1%, p = 0.0084 and 85.5% vs 76.9%, p = 0.0051, respectively). Accuracy of Model^LBC was comparable to that of contrast enhanced CT (both 84.7%) but inferior to contrast enhanced MRI (87.9%) for lesions detected by US.

Interpretation

DCNN-US with high sensitivity and specificity in diagnosing FLLs shows its potential to assist less-experienced radiologists in improving their performance and lowering their dependence on sectional imaging in liver cancer diagnosis.

SUBMITTER: Yang Q

PROVIDER: S-EPMC7262550 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundThe UK's National Institute for Health and Care Excellence (NICE) has recommended contrast-enhanced ultrasound (CEUS) for the characterisation of focal liver lesions where the results of standard unenhanced ultrasound are inconclusive. A further recommendation is for CEUS to replace other imaging modalities. However, little is currently known about the diagnostic pathways in the National Health Service (NHS) followed by patients with potential liver lesions. The aim of this study was to identify the diagnostic pathways for a number of representative hospital trusts and record the clinicians' views on patient experiences of these processes through a series of semi-structured interviews with UK clinicians (radiologists and sonographers) (N = 7). This study was undertaken in the broader context of a larger research project where the overarching research question is focused on patient preferences for CEUS and other imaging modalities, and how these impact on patient quality of life (QOL).ResultsThe results from the semi-structured interviews with UK clinicians revealed that there is a great deal of heterogeneity in diagnostic pathways followed by patients with potential liver lesions which differ both within and between hospitals. In terms of the patient experience, the clinicians believed that a combination of the more patient-friendly ultrasound process, and the fact that scan results are given to patients in 80-90% of cases on the day, as well as the problems inherent to other scan modalities (claustrophobia, anxiety) would lead to patients preferring ultrasound compared with other imaging modalities (CT or MR). However, current clinical practice means that patient choice is virtually non-existent.ConclusionsThe significant variation in diagnostic pathways across the NHS will require further standardisation through local agreements if contrast-enhanced ultrasound is to replace other imaging modalities in characterising focal liver lesions in line with NICE Diagnostics Guidance. The gradual development of patient choice of modalities may necessitate a change of practice in radiology processes.

Project description:ObjectiveTo evaluate the diagnostic performance and image quality of 1.5-mm slice thickness MRI with deep learning-based image reconstruction (1.5-mm MRI + DLR) compared to routine 3-mm slice thickness MRI (routine MRI) and 1.5-mm slice thickness MRI without DLR (1.5-mm MRI without DLR) for evaluating temporal lobe epilepsy (TLE).Materials and methodsThis retrospective study included 117 MR image sets comprising 1.5-mm MRI + DLR, 1.5-mm MRI without DLR, and routine MRI from 117 consecutive patients (mean age, 41 years; 61 female; 34 patients with TLE and 83 without TLE). Two neuroradiologists evaluated the presence of hippocampal or temporal lobe lesions, volume loss, signal abnormalities, loss of internal structure of the hippocampus, and lesion conspicuity in the temporal lobe. Reference standards for TLE were independently constructed by neurologists using clinical and radiological findings. Subjective image quality, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) were analyzed. Performance in diagnosing TLE, lesion findings, and image quality were compared among the three protocols.ResultsThe pooled sensitivity of 1.5-mm MRI + DLR (91.2%) for diagnosing TLE was higher than that of routine MRI (72.1%, P < 0.001). In the subgroup analysis, 1.5-mm MRI + DLR showed higher sensitivity for hippocampal lesions than routine MRI (92.7% vs. 75.0%, P = 0.001), with improved depiction of hippocampal T2 high signal intensity change (P = 0.016) and loss of internal structure (P < 0.001). However, the pooled specificity of 1.5-mm MRI + DLR (76.5%) was lower than that of routine MRI (89.2%, P = 0.004). Compared with 1.5-mm MRI without DLR, 1.5-mm MRI + DLR resulted in significantly improved pooled accuracy (91.2% vs. 73.1%, P = 0.010), image quality, SNR, and CNR (all, P < 0.001).ConclusionThe use of 1.5-mm MRI + DLR enhanced the performance of MRI in diagnosing TLE, particularly in hippocampal evaluation, because of improved depiction of hippocampal abnormalities and enhanced image quality.

Project description:BackgroundThe incidence rate of thyroid nodules has reached 65%, but only 5-15% of these modules are malignant. Therefore, accurately determining the benign and malignant nature of thyroid nodules can prevent unnecessary treatment. We aimed to develop a deep-learning (DL) radiomics model based on ultrasound (US), explore its diagnostic efficacy for benign and malignant thyroid nodules, and verify whether it improved the diagnostic level of physicians.MethodsWe retrospectively included 1,076 thyroid nodules from 817 patients at three institutions. The radiomics and DL features of the US images were extracted and used to construct radiomics signature (Rad_sig) and deep-learning signature (DL_sig). A Pearson correlation analysis and least absolute shrinkage and selection operator (LASSO) regression analysis were used for feature selection. Clinical US semantic signature (C_US_sig) was constructed based on clinical information and US semantic features. Next, a combined model was constructed based on the above three signatures in the form of a nomogram. The model was constructed using a development set (institution 1: 719 nodules), and the model was evaluated using two external validation sets (institution 2: 74 nodules, and institution 3: 283 nodules). The performance of the model was assessed using decision curve analysis (DCA) and calibration curves. Furthermore, the C_US_sigs of junior physicians, senior physicians, and expers were constructed. The DL radiomics model was used to assist the physicians with different levels of experience in the interpretation of thyroid nodules.ResultsIn the development and validation sets, the combined model showed the highest performance, with areas under the curve (AUCs) of 0.947, 0.917, and 0.929, respectively. The DCA results showed that the comprehensive nomogram had the best clinical utility. The calibration curves indicated good calibration for all models. The AUCs for distinguishing between benign and malignant thyroid nodules by junior physicians, senior physicians, and experts were 0.714-0.752, 0.740-0.824, and 0.891-0.908, respectively; however, with the assistance of DL radiomics, the AUCs reached 0.858-0.923, 0.888-0.944, and 0.912-0.919, respectively.ConclusionsThe nomogram based on DL radiomics had high diagnostic efficacy for thyroid nodules, and DL radiomics could assist physicians with different levels of experience to improve their diagnostic level.