A Comparative Study of Two Radiomics-Based Blood Flow Modes with Thyroid Imaging Reporting and Data System in Predicting Malignancy of Thyroid Nodules and Reducing Unnecessary Fine-Needle Aspiration Rate.

RATIONALE AND OBJECTIVES: We aimed to compare superb microvascular imaging (SMI)-based radiomics methods, and contrast-enhanced ultrasound (CEUS)-based radiomics methods to the American College of Radiology Thyroid Imaging Reporting and Data System (ACR TI-RADS) for classifying thyroid nodules (TNs) and reducing unnecessary fine-needle aspiration biopsy (FNAB) rate. MATERIALS AND METHODS: This retrospective study enrolled a dataset of 472 pathologically confirmed TNs. Radiomics characteristics were extracted from B-mode ultrasound (BMUS), SMI, and CEUS images, respectively. After eliminating redundant features, four radiomics scores (Rad-scores) were constructed. Using multivariable logistic regression analysis, four radiomics prediction models incorporating Rad-score and corresponding US features were constructed and validated in terms of discrimination, calibration, decision curve analysis, and unnecessary FNAB rate. RESULTS: The diagnostic performance of the BMUS + SMI radiomics method was better than ACR TI-RADS (area under the curve [AUC]: 0.875 vs. 0.689 for the training cohort, 0.879 vs. 0.728 for the validation cohort) (P < 0.05), and comparable with BMUS + CEUS radiomics method (AUC: 0.875 vs. 0.878 for the training cohort, 0.879 vs. 0.865 for the validation cohort) (P > 0.05). Decision curve analysis showed that the BMUS+SMI radiomics method could achieve higher net benefits than the BMUS radiomics method and ACR TI-RADS when the threshold probability was between 0.13 and 0.88 in the entire cohort. When applying the BMUS+SMI radiomics method, the unnecessary FNAB rate reduced from 43.4% to 13.9% in the training cohort and from 45.6% to 18.0% in the validation cohorts in comparison to ACR TI-RADS. CONCLUSION: The dual-modal SMI-based radiomics method is convenient and economical and can be an alternative to the dual-modal CEUS-based radiomics method in helping radiologists select the optimal clinical strategy for TN management.

Predicting the malignancy of extremity soft-tissue tumors by an ultrasound-based radiomics signature.

BACKGROUND: Accurate differentiation of extremity soft-tissue tumors (ESTTs) is important for treatment planning. PURPOSE: To develop and validate an ultrasound (US) image-based radiomics signature to predict ESTTs malignancy. MATERIAL AND METHODS: A dataset of US images from 108 ESTTs were retrospectively enrolled and divided into the training cohort (78 ESTTs) and validation cohort (30 ESTTs). A total of 1037 radiomics features were extracted from each US image. The most useful predictive radiomics features were selected by the maximum relevance and minimum redundancy method, least absolute shrinkage, and selection operator algorithm in the training cohort. A US-based radiomics signature was built based on these selected radiomics features. In addition, a conventional radiologic model based on the US features from the interpretation of two experienced radiologists was developed by a multivariate logistic regression algorithm. The diagnostic performances of the selected radiomics features, the US-based radiomics signature, and the conventional radiologic model for differentiating ESTTs were evaluated and compared in the validation cohort. RESULTS: In the validation cohort, the area under the curve (AUC), sensitivity, and specificity of the US-based radiomics signature for predicting ESTTs malignancy were 0.866, 84.2%, and 81.8%, respectively. The US-based radiomics signature had better diagnostic predictability for predicting ESTT malignancy than the best single radiomics feature and the conventional radiologic model (AUC = 0.866 vs. 0.719 vs. 0.681 for the validation cohort, all P <0.05). CONCLUSION: The US-based radiomics signature could provide a potential imaging biomarker to accurately predict ESTT malignancy.

Dual-modal radiomics nomogram based on contrast-enhanced ultrasound to improve differential diagnostic accuracy and reduce unnecessary biopsy rate in ACR TI-RADS 4-5 thyroid nodules.

BACKGROUND: American College of Radiology (ACR) Thyroid Imaging Reporting and Data System (TI-RADS, TR) 4 and 5 thyroid nodules (TNs) demonstrate much more complicated and overlapping risk characteristics than TR1-3 and have a rather wide range of malignancy possibilities (> 5%), which may cause overdiagnosis or misdiagnosis. This study was designed to establish and validate a dual-modal ultrasound (US) radiomics nomogram integrating B-mode ultrasound (BMUS) and contrast-enhanced ultrasound (CEUS) imaging to improve differential diagnostic accuracy and reduce unnecessary fine needle aspiration biopsy (FNAB) rates in TR 4-5 TNs. METHODS: A retrospective dataset of 312 pathologically confirmed TR4-5 TNs from 269 patients was collected for our study. Data were randomly divided into a training dataset of 219 TNs and a validation dataset of 93 TNs. Radiomics characteristics were derived from the BMUS and CEUS images. After feature reduction, the BMUS and CEUS radiomics scores (Rad-score) were built. A multivariate logistic regression analysis was conducted incorporating both Rad-scores and clinical/US data, and a radiomics nomogram was subsequently developed. The performance of the radiomics nomogram was evaluated using calibration, discrimination, and clinical usefulness, and the unnecessary FNAB rate was also calculated. RESULTS: BMUS Rad-score, CEUS Rad-score, age, shape, margin, and enhancement direction were significant independent predictors associated with malignant TR4-5 TNs. The radiomics nomogram involving the six variables exhibited excellent calibration and discrimination in the training and validation cohorts, with an AUC of 0.873 (95% CI, 0.821-0.925) and 0.851 (95% CI, 0.764-0.938), respectively. The marked improvements in the net reclassification index and integrated discriminatory improvement suggested that the BMUS and CEUS Rad-scores could be valuable indicators for distinguishing benign from malignant TR4-5 TNs. Decision curve analysis demonstrated that our developed radiomics nomogram was an instrumental tool for clinical decision-making. Using the radiomics nomogram, the unnecessary FNAB rate decreased from 35.3 to 14.5% in the training cohort and from 41.5 to 17.7% in the validation cohorts compared with ACR TI-RADS. CONCLUSION: The dual-modal US radiomics nomogram revealed superior discrimination accuracy and considerably decreased unnecessary FNAB rates in benign and malignant TR4-5 TNs. It could guide further examination or treatment options.

Deep learning predicts cervical lymph node metastasis in clinically node-negative papillary thyroid carcinoma.

OBJECTIVES: Precise determination of cervical lymph node metastasis (CLNM) involvement in patients with early-stage thyroid cancer is fairly significant for identifying appropriate cervical treatment options. However, it is almost impossible to directly judge lymph node metastasis based on the imaging information of early-stage thyroid cancer patients with clinically negative lymph nodes. METHODS: Preoperative US images (BMUS and CDFI) of 1031 clinically node negative PTC patients definitively diagnosed on pathology from two independent hospitals were divided into training set, validation set, internal test set, and external test set. An ensemble deep learning model based on ResNet-50 was built integrating clinical variables, BMUS, and CDFI images using a bagging classifier to predict metastasis of CLN. The final ensemble model performance was compared with expert interpretation. RESULTS: The ensemble deep convolutional neural network (DCNN) achieved high performance in predicting CLNM in the test sets examined, with area under the curve values of 0.86 (95% CI 0.78-0.94) for the internal test set and 0.77 (95% CI 0.68-0.87) for the external test set. Compared to all radiologists averaged, the ensemble DCNN model also exhibited improved performance in making predictions. For the external validation set, accuracy was 0.72 versus 0.59 (p = 0.074), sensitivity was 0.75 versus 0.58 (p = 0.039), and specificity was 0.69 versus 0.60 (p = 0.078). CONCLUSIONS: Deep learning can non-invasive predict CLNM for clinically node-negative PTC using conventional US imaging of thyroid cancer nodules and clinical variables in a multi-institutional dataset with superior accuracy, sensitivity, and specificity comparable to experts. CRITICAL RELEVANCE STATEMENT: Deep learning efficiently predicts CLNM for clinically node-negative PTC based on US images and clinical variables in an advantageous manner. KEY POINTS: • A deep learning-based ensemble algorithm for predicting CLNM in PTC was developed. • Ultrasound AI analysis combined with clinical data has advantages in predicting CLNM. • Compared to all experts averaged, the DCNN model achieved higher test performance.

Ultrasound radiomics based on axillary lymph nodes images for predicting lymph node metastasis in breast cancer.

Objectives: To determine whether ultrasound radiomics can be used to distinguish axillary lymph nodes (ALN) metastases in breast cancer based on ALN imaging. Methods: A total of 147 breast cancer patients with 41 non-metastatic lymph nodes and 109 metastatic lymph nodes were divided into a training set (105 ALN) and a validation set (45 ALN). Radiomics features were extracted from ultrasound images and a radiomics signature (RS) was built. The Intraclass correlation coefficients (ICCs), Spearman correlation analysis, and least absolute shrinkage and selection operator (LASSO) methods were used to select the ALN status-related features. All images were assessed by two radiologists with at least 10 years of experience in ALN ultrasound examination. The performance levels of the model and radiologists in the training and validation subgroups were then evaluated and compared. Result: Radiomics signature accurately predicted the ALN status, achieved an area under the receiver operator characteristic curve of 0.929 (95%CI, 0.881-0.978) and area under curve(AUC) of 0.919 (95%CI, 95%CI, 0.841-0.997) in training and validation cohorts respectively. The radiomics model performed better than two experts' prediction of ALN status in both cohorts (P<0.05). Besides, prediction in subgroups based on baseline clinicopathological information also achieved good discrimination performance, with an AUC of 0.937, 0.918, 0.885, 0.930, and 0.913 in HR+/HER2-, HER2+, triple-negative, tumor sized ≤ 3cm and tumor sized>3 cm, respectively. Conclusion: The radiomics model demonstrated a good ability to predict ALN status in patients with breast cancer, which might provide essential information for decision-making.

A multiparametric clinic-ultrasomics nomogram for predicting extremity soft-tissue tumor malignancy: a combined retrospective and prospective bicentric study.

OBJECTIVE: We aimed at building and testing a multiparametric clinic-ultrasomics nomogram for prediction of malignant extremity soft-tissue tumors (ESTTs). MATERIALS AND METHODS: This combined retrospective and prospective bicentric study assessed the performance of the multiparametric clinic-ultrasomics nomogram to predict the malignancy of ESTTs, when compared with a conventional clinic-radiologic nomogram. A dataset of grayscale ultrasound (US), color Doppler flow imaging (CDFI), and elastography images for 209 ESTTs were retrospectively enrolled from one hospital, and divided into the training and validation cohorts. A multiparametric ultrasomics signature was built based on multimodal ultrasomic features extracted from the grayscale US, CDFI, and elastography images of ESTTs in the training cohort. Another conventional radiologic score was built based on multimodal US features as interpreted by two experienced radiologists. Two nomograms that integrated clinical risk factors and the multiparameter ultrasomics signature or conventional radiologic score were respectively developed. Performance of the two nomograms was validated in the retrospective validation cohort, and tested in a prospective dataset of 51 ESTTs from the second hospital. RESULTS: The multiparametric ultrasomics signature was built based on seven grayscale ultrasomic features, three CDFI ultrasomic features, and one elastography ultrasomic feature. The conventional radiologic score was built based on five multimodal US characteristics. Predictive performance of the multiparametric clinic-ultrasomics nomogram was superior to that of the conventional clinic-radiologic nomogram in the training (area under the receiver operating characteristic curve [AUC] 0.970 vs. 0.890, p = 0.006), validation (AUC: 0.946 vs. 0.828, p = 0.047) and test (AUC: 0.934 vs. 0.842, p = 0.040) cohorts, respectively. Decision curve analysis of combined training, validation and test cohorts revealed that the multiparametric clinic-ultrasomics nomogram had a higher overall net benefit than the conventional clinic-radiologic model. CONCLUSION: The multiparametric clinic-ultrasomics nomogram can accurately predict the malignancy of ESTTs.

Predicting Malignancy of Thyroid Micronodules: Radiomics Analysis Based on Two Types of Ultrasound Elastography Images.

RATIONALE AND OBJECTIVES: To develop a multimodal ultrasound radiomics nomogram for accurate classification of thyroid micronodules. MATERIALS AND METHODS: A retrospective study including 181 thyroid micronodules within 179 patients was conducted. Radiomics features were extracted from strain elastography (SE), shear wave elastography (SWE) and B-mode ultrasound (BMUS) images. Minimum redundancy maximum relevance and least absolute shrinkage and selection operator algorithms were used to select malignancy-related features. BMUS, SE, and SWE radiomics scores (Rad-scores) were then constructed. Multivariable logistic regression was conducted using radiomics signatures along with clinical data, and a nomogram was ultimately established. The calibration, discriminative, and clinical usefulness were considered to evaluate its performance. A clinical prediction model was also built using independent clinical risk factors for comparison. RESULTS: An aspect ratio ≥ 1, mean elasticity index, BMUS Rad-score, SE Rad-score, and SWE Rad-score were identified as the independent predictors for predicting malignancy of thyroid micronodules by multivariable logistic regression. The radiomics nomogram based on these characteristics showed favorable calibration and discriminative capabilities (AUCs: 0.903 and 0.881 for training and validation cohorts, respectively), all outperforming clinical prediction model (AUCs: 0.791 and 0.626, respectively). The decision curve analysis also confirmed clinical usefulness of the nomogram. The significant improvement of net reclassification index and integrated discriminatory improvement indicated that multimodal ultrasound radiomics signatures might work as new imaging markers for classifying thyroid micronodules. CONCLUSION: The nomogram combining multimodal ultrasound radiomics features and clinical factors has the potential to be used for accurate diagnosis of thyroid micronodules in the clinic.

Radiomic Model for Determining the Value of Elasticity and Grayscale Ultrasound Diagnoses for Predicting BRAFV600E Mutations in Papillary Thyroid Carcinoma.

BRAFV600E is the most common mutated gene in thyroid cancer and is most closely related to papillary thyroid carcinoma(PTC). We investigated the value of elasticity and grayscale ultrasonography for predicting BRAFV600E mutations in PTC. Methods: 138 patients with PTC who underwent preoperative ultrasound between January 2014 and 2021 were retrospectively examined. Patients were divided into BRAFV600E mutation-free group (n=75) and BRAFV600E mutation group (n=63). Patients were randomly divided into training (n=96) and test (n=42) groups. A total of 479 radiomic features were extracted from the grayscale and elasticity ultra-sonograms. Regression analysis was done to select the features that provided the most information. Then, 10-fold cross-validation was used to compare the performance of different classification algorithms. Logistic regression was used to predict BRAFV600E mutations. Results: Eight radiomics features were extracted from the grayscale ultrasonogram, and five radiomics features were extracted from the elasticity ultrasonogram. Three models were developed using these radiomic features. The models were derived from elasticity ultrasound, grayscale ultrasound, and a combination of grayscale and elasticity ultrasound, with areas under the curve (AUC) 0.952 [95% confidence interval (CI), 0.914-0.990], AUC 0.792 [95% CI, 0.703-0.882], and AUC 0.985 [95% CI, 0.965-1.000] in the training dataset, AUC 0.931 [95% CI, 0.841-1.000], AUC 0. 725 [95% CI, 0.569-0.880], and AUC 0.938 [95% CI, 0.851-1.000] in the test dataset, respectively. Conclusion: The radiomic model based on grayscale and elasticity ultrasound had a good predictive value for BRAFV600E gene mutations in patients with PTC.

Relation of Carotid Plaque Features Detected with Ultrasonography-Based Radiomics to Clinical Symptoms.

Carotid plaque is one of the predominant causes of stroke. We sought to build a nomogram using ultrasonography (US)-based radiomics and clinical features for identification of symptomatic carotid plaques. We prospectively enrolled 548 patients (mean age ± standard deviation, 63 ± 10 years; 373 men) were randomly divided into training and test cohorts. Clinical and conventional US features of carotid plaques were used to generate a clinical and conventional US model. US-based radiomics model was constructed by extracting radiomics features from grayscale and strain elasticity images. Multivariate logistic regression was performed using the radiomics scores together with clinical and conventional US data, and a final nomogram was subsequently developed. The performance of the final nomogram was assessed with respect to discrimination and clinical usefulness in the training of the test cohorts and contrast-enhanced US test cohort. All the radiomics scores were significantly higher in patients with symptomatic carotid plaques. The US-based radiomics model [area under the curve (AUC) = 0.930 and 0.922 for training and test cohorts, respectively] and final nomogram (AUC = 0.927 and 0.919, respectively) outperformed the clinical and conventional US model (AUC = 0.723 and 0.580, respectively). The decision curve analysis indicated that the final nomogram was clinically useful. In patients undergoing the contrast-enhanced US, the prevalence of plaque enhancement was higher in high-risk patients than in low-risk patients based on the final nomogram-score (P = 0.008). Nomogram has a high diagnostic performance for identification of symptomatic carotid plaques.

Radiomics model based on shear-wave elastography in the assessment of axillary lymph node status in early-stage breast cancer.

OBJECTIVES: To develop and validate an ultrasound elastography radiomics nomogram for preoperative evaluation of the axillary lymph node (ALN) burden in early-stage breast cancer. METHODS: Data of 303 patients from hospital #1 (training cohort) and 130 cases from hospital #2 (external validation cohort) between Jun 2016 and May 2019 were enrolled. Radiomics features were extracted from shear-wave elastography (SWE) and corresponding B-mode ultrasound (BMUS) images. The minimum redundancy maximum relevance and least absolute shrinkage and selection operator algorithms were used to select ALN status-related features. Proportional odds ordinal logistic regression was performed using the radiomics signature together with clinical data, and an ordinal nomogram was subsequently developed. We evaluated its performance using C-index and calibration. RESULTS: SWE signature, US-reported LN status, and molecular subtype were independent risk factors associated with ALN status. The nomogram based on these variables showed good discrimination in the training (overall C-index: 0.842; 95%CI, 0.773-0.879) and the validation set (overall C-index: 0.822; 95%CI, 0.765-0.838). For discriminating between disease-free axilla (N0) and any axillary metastasis (N + (≥ 1)), it achieved a C-index of 0.845 (95%CI, 0.777-0.914) for the training cohort and 0.817 (95%CI, 0.769-0.865) for the validation cohort. The tool could also discriminate between low (N + (1-2)) and heavy metastatic ALN burden (N + (≥ 3)), with a C-index of 0.827 (95%CI, 0.742-0.913) in the training cohort and 0.810 (95%CI, 0.755-0.864) in the validation cohort. CONCLUSION: The radiomics model shows favourable predictive ability for ALN staging in patients with early-stage breast cancer, which could provide incremental information for decision-making. KEY POINTS: • Radiomics analysis helps radiologists to evaluate the axillary lymph node status of breast cancer with accuracy. • This multicentre retrospective study showed that radiomics nomogram based on shear-wave elastography provides incremental information for risk stratification. • Treatment can be given with more precision based on the model.

The Added Value of a Computer-Aided Diagnosis System in Differential Diagnosis of Breast Lesions by Radiologists With Different Experience.

OBJECTIVES: To evaluate the value of the computer-aided diagnosis system, S-Detect (based on deep learning algorithm), in distinguishing benign and malignant breast masses and reducing unnecessary biopsy based on the experience of radiologists. METHODS: From February 2018 to March 2019, 266 breast masses in 192 women were included in our study. Ultrasound (US) examination, including S-Detect technique, was performed by the radiologist with about 10 years of clinical experience in breast US imaging. US images were analyzed by four other radiologists with different experience in breast imaging (radiologists 1, 2, 3, and 4 with 1, 4, 9, and 20 years, respectively) according to their clinical experience (with and without the results of S-Detect). Diagnostic capabilities and unnecessary biopsy of radiologists and radiologists combined with S-Detect were compared and analyzed. RESULTS: After referring to the results of S-Detect, the changes made by less experienced radiologists were greater than experienced radiologists (benign or malignant, 44 vs 22 vs 14 vs 2; unnecessary biopsy, 34 vs 25 vs 10 vs 5). When combined with S-Detect, less experienced radiologists showed significant improvement in accuracy, specificity, positive predictive value, negative predictive value, and area under curve (P < .05), but not for experienced radiologists (P > .05). Similarly, the unnecessary biopsy rate of less experienced radiologists decreased significantly (44.4% vs 32.7%, P = .006; 36.8% vs 28.2%, P = .033), but not for experienced radiologists (P > .05). CONCLUSIONS: Less experienced radiologists rely more on S-Detect software. And S-Detect can be an effective decision-making tool for breast US, especially for less experienced radiologists.

Preoperative Prediction of Microvascular Invasion in Patients With Hepatocellular Carcinoma Based on Radiomics Nomogram Using Contrast-Enhanced Ultrasound.

PURPOSE: This study aimed to develop a radiomics nomogram based on contrast-enhanced ultrasound (CEUS) for preoperatively assessing microvascular invasion (MVI) in hepatocellular carcinoma (HCC) patients. METHODS: A retrospective dataset of 313 HCC patients who underwent CEUS between September 20, 2016 and March 20, 2020 was enrolled in our study. The study population was randomly grouped as a primary dataset of 192 patients and a validation dataset of 121 patients. Radiomics features were extracted from the B-mode (BM), artery phase (AP), portal venous phase (PVP), and delay phase (DP) images of preoperatively acquired CEUS of each patient. After feature selection, the BM, AP, PVP, and DP radiomics scores (Rad-score) were constructed from the primary dataset. The four radiomics scores and clinical factors were used for multivariate logistic regression analysis, and a radiomics nomogram was then developed. We also built a preoperative clinical prediction model for comparison. The performance of the radiomics nomogram was evaluated via calibration, discrimination, and clinical usefulness. RESULTS: Multivariate analysis indicated that the PVP and DP Rad-score, tumor size, and AFP (alpha-fetoprotein) level were independent risk predictors associated with MVI. The radiomics nomogram incorporating these four predictors revealed a superior discrimination to the clinical model (based on tumor size and AFP level) in the primary dataset (AUC: 0.849 vs. 0.690; p < 0.001) and validation dataset (AUC: 0.788 vs. 0.661; p = 0.008), with a good calibration. Decision curve analysis also confirmed that the radiomics nomogram was clinically useful. Furthermore, the significant improvement of net reclassification index (NRI) and integrated discriminatory improvement (IDI) implied that the PVP and DP radiomics signatures may be very useful biomarkers for MVI prediction in HCC. CONCLUSION: The CEUS-based radiomics nomogram showed a favorable predictive value for the preoperative identification of MVI in HCC patients and could guide a more appropriate surgical planning.

Artificial Intelligence in Medical Imaging of the Breast.

Artificial intelligence (AI) has invaded our daily lives, and in the last decade, there have been very promising applications of AI in the field of medicine, including medical imaging, in vitro diagnosis, intelligent rehabilitation, and prognosis. Breast cancer is one of the common malignant tumors in women and seriously threatens women's physical and mental health. Early screening for breast cancer via mammography, ultrasound and magnetic resonance imaging (MRI) can significantly improve the prognosis of patients. AI has shown excellent performance in image recognition tasks and has been widely studied in breast cancer screening. This paper introduces the background of AI and its application in breast medical imaging (mammography, ultrasound and MRI), such as in the identification, segmentation and classification of lesions; breast density assessment; and breast cancer risk assessment. In addition, we also discuss the challenges and future perspectives of the application of AI in medical imaging of the breast.

Deep Learning Based on ACR TI-RADS Can Improve the Differential Diagnosis of Thyroid Nodules.

OBJECTIVE: The purpose of this study was to improve the differentiation between malignant and benign thyroid nodules using deep learning (DL) in category 4 and 5 based on the Thyroid Imaging Reporting and Data System (TI-RADS, TR) from the American College of Radiology (ACR). DESIGN AND METHODS: From June 2, 2017 to April 23, 2019, 2082 thyroid ultrasound images from 1396 consecutive patients with confirmed pathology were retrospectively collected, of which 1289 nodules were category 4 (TR4) and 793 nodules were category 5 (TR5). Ninety percent of the B-mode ultrasound images were applied for training and validation, and the residual 10% and an independent external dataset for testing purpose by three different deep learning algorithms. RESULTS: In the independent test set, the DL algorithm of best performance got an AUC of 0.904, 0.845, 0.829 in TR4, TR5, and TR4&5, respectively. The sensitivity and specificity of the optimal model was 0.829, 0.831 on TR4, 0.846, 0.778 on TR5, 0.790, 0.779 on TR4&5, versus the radiologists of 0.686 (P=0.108), 0.766 (P=0.101), 0.677 (P=0.211), 0.750 (P=0.128), and 0.680 (P=0.023), 0.761 (P=0.530), respectively. CONCLUSIONS: The study demonstrated that DL could improve the differentiation of malignant from benign thyroid nodules and had significant potential for clinical application on TR4 and TR5.

Management of breast lesions seen on US images: dual-model radiomics including shear-wave elastography may match performance of expert radiologists.

PURPOSE: To develop a nomogram incorporating B-mode ultrasound (BMUS) and shear-wave elastography (SWE) radiomics to predict malignant status of breast lesions seen on US non-invasively. METHODS: Data on 278 consecutive patients from Hospital #1 (training cohort) and 123 cases from Hospital #2 (external validation cohort) referred for breast US with subsequent histopathologic analysis between May 2017 and October 2019 were retrospectively collected. Using their BMUS and SWE images, we built a radiomics nomogram to improve radiology workflow for management of breast lesions. The performance of the algorithm was compared with a consensus of three ACR BI-RADS committee experts and four individual radiologists, all of whom interpreted breast US images in clinical practice. RESULTS: Twelve features from BMUS and three from SWE were selected finally to construct the respective radiomic signature. The nomogram based on the dual-modal US radiomics achieved good diagnostic performance in the training (AUC 0.96; 95% confidence intervals [CI], 0.94-0.98) and the validation set (AUC 0.92; 95% CI, 0.87-0.97). For the 123 test lesions, the algorithm achieved 105 of 123 (85%) accuracy, comparable to the expert consensus (104 of 123 [85%], P =  0.86) and four individual radiologists (93, 99, 95 and 97 of 123, with P value of 0.05, 0.31, 0.10 and 0.18 respectively). Furthermore, the model also performed well in the BI-RADS 4 and 5 categories. CONCLUSIONS: Performance of a dual-model US radiomics nomogram based on SWE for breast lesion classification may comparable to that of expert radiologists who used ACR BI-RADS guideline.

Ultrasound-based deep learning radiomics in the assessment of pathological complete response to neoadjuvant chemotherapy in locally advanced breast cancer.

PURPOSE: The aim of the study was to develop and validate a deep learning radiomic nomogram (DLRN) for preoperatively assessing breast cancer pathological complete response (pCR) after neoadjuvant chemotherapy (NAC) based on the pre- and post-treatment ultrasound. METHODS: Patients with locally advanced breast cancer (LABC) proved by biopsy who proceeded to undergo preoperative NAC were enrolled from hospital #1 (training cohort, 356 cases) and hospital #2 (independent external validation cohort, 236 cases). Deep learning and handcrafted radiomic features reflecting the phenotypes of the pre-treatment (radiomic signature [RS] 1) and post-treatment tumour (RS2) were extracted. The minimum redundancy maximum relevance algorithm and the least absolute shrinkage and selection operator regression were used for feature selection and RS construction. A DLRN was then developed based on the RSs and independent clinicopathological risk factors. The performance of the model was assessed with regard to calibration, discrimination and clinical usefulness. RESULTS: The DLRN predicted the pCR status with accuracy, yielded an area under the receiver operator characteristic curve of 0.94 (95% confidence interval, 0.91-0.97) in the validation cohort, with good calibration. The DLRN outperformed the clinical model and single RS within both cohorts (P < 0.05, as per the DeLong test) and performed better than two experts' prediction of pCR (both P < 0.01 for comparison of total accuracy). Besides, prediction within the hormone receptor-positive/human epidermal growth factor receptor 2 (HER2)-negative, HER2+ and triple-negative subgroups also achieved good discrimination performance, with an AUC of 0.90, 0.95 and 0.93, respectively, in the external validation cohort. Decision curve analysis confirmed that the model was clinically useful. CONCLUSION: A deep learning-based radiomic nomogram had good predictive value for pCR in LABC, which could provide valuable information for individual treatment.

Deep learning with convolutional neural network in the assessment of breast cancer molecular subtypes based on US images: a multicenter retrospective study.

OBJECTIVES: To evaluate the prediction performance of deep convolutional neural network (DCNN) based on ultrasound (US) images for the assessment of breast cancer molecular subtypes. METHODS: A dataset of 4828 US images from 1275 patients with primary breast cancer were used as the training samples. DCNN models were constructed primarily to predict the four St. Gallen molecular subtypes and secondarily to identify luminal disease from non-luminal disease based on the ground truth from immunohistochemical of whole tumor surgical specimen. US images from two other institutions were retained as independent test sets to validate the system. The models' performance was analyzed using per-class accuracy, positive predictive value (PPV), and Matthews correlation coefficient (MCC). RESULTS: The model achieved good performance in identifying the four breast cancer molecular subtypes in the two test sets, with accuracy ranging from 80.07% (95% CI, 76.49-83.23%) to 97.02% (95% CI, 95.22-98.16%) and 87.94% (95% CI, 85.08-90.31%) to 98.83% (95% CI, 97.60-99.43) for the two test cohorts for each sub-category, respectively. In terms of 4-class weighted average MCC, the model achieved 0.59 for test cohort A and 0.79 for test cohort B. Specifically, the DCNN also yielded good diagnostic performance in discriminating luminal disease from non-luminal disease, with a PPV of 93.29% (95% CI, 90.63-95.23%) and 88.21% (95% CI, 85.12-90.73%) for the two test cohorts, respectively. CONCLUSION: Using pretreatment US images of the breast cancer, deep learning model enables the assessment of molecular subtypes with high diagnostic accuracy. TRIAL REGISTRATION: Clinical trial number: ChiCTR1900027676 KEY POINTS: • Deep convolutional neural network (DCNN) helps clinicians assess tumor features with accuracy. • Multicenter retrospective study shows that DCNN derived from pretreatment ultrasound imagine improves the prediction of breast cancer molecular subtypes. • Management of patients becomes more precise based on the DCNN model.

Study Processes and Applications of Ultrasomics in Precision Medicine.

Ultrasomics is the science of transforming digitally encrypted medical ultrasound images that hold information related to tumor pathophysiology into mineable high-dimensional data. Ultrasomics data have the potential to uncover disease characteristics that are not found with the naked eye. The task of ultrasomics is to quantify the state of diseases using distinctive imaging algorithms and thereby provide valuable information for personalized medicine. Ultrasomics is a powerful tool in oncology but can also be applied to other medical problems for which a disease is imaged. To date there is no comprehensive review focusing on ultrasomics. Here, we describe how ultrasomics works and its capability in diagnosing disease in different organs, including breast, liver, and thyroid. Its pitfalls, challenges and opportunities are also discussed.

The value of S-Detect in improving the diagnostic performance of radiologists for the differential diagnosis of thyroid nodules.

AIMS: To compare the diagnostic value of S-Detect (a computer aided diagnosis system using deep learning) in differentiating thyroid nodules in radiologists with different experience and to assess if S-Detect can improve the diagnostic performance of radiologists. MATERIALS AND METHODS: Between February 2018 and October 2019, 204 thyroid nodules in 181 patients were included. An experienced radiologist performed ultrasound for thyroid nodules and obtained the result of S-Detect. Four radiologists with different experience on thyroid ultrasound (Radiologist 1, 2, 3, 4 with 1, 4, 9, 20 years, respectively) analyzed the conventional ultrasound images of each thyroid nodule and made a diagnosis of "benign" or "malignant" based on the TI-RADS category. After referring to S-Detect results, they re-evaluated the diagnoses. The diagnostic performance of radiologists was analyzed before and after referring to the results of S-Detect. RESULTS: The accuracy, sensitivity, specificity, positive predictive value and negative predictive value of S-Detect were 77.0, 91.3, 65.2, 68.3 and 90.1%, respectively. In comparison with the less experienced radiologists (radiologist 1 and 2), S-Detect had a higher area under receiver operating characteristic curve (AUC), accuracy and specificity (p <0.05). In comparison with the most experienced radiologist, the diagnostic accuracy and AUC were lower (p<0.05). In the less experienced radiologists, the diagnostic accuracy, specificity and AUC were significantly improved when combined with S-Detect (p<0.05), but not for experienced radiologists (radiologist 3 and 4) (p>0.05). CONCLUSIONS: S-Detect may become an additional diagnostic method for the diagnosis of thyroid nodules and improve the diagnostic performance of less experienced radiologists.

Nomogram for predicting transmural bowel infarction in patients with acute superior mesenteric venous thrombosis.

BACKGROUND: The prognosis of acute mesenteric ischemia (AMI) caused by superior mesenteric venous thrombosis (SMVT) remains undetermined and early detection of transmural bowel infarction (TBI) is crucial. The predisposition to develop TBI is of clinical concern, which can lead to fatal sepsis with hemodynamic instability and multi-organ failure. Early resection of necrotic bowel could improve the prognosis of AMI, however, accurate prediction of TBI remains a challenge for clinicians. When determining the eligibility for explorative laparotomy, the underlying risk factors for bowel infarction should be fully evaluated. AIM: To develop and externally validate a nomogram for prediction of TBI in patients with acute SMVT. METHODS: Consecutive data from 207 acute SMVT patients at the Wuhan Tongji Hospital and 89 patients at the Guangzhou Nanfang Hospital between July 2005 and December 2018 were included in this study. They were grouped as training and external validation cohort. The 207 cases (training cohort) from Tongji Hospital were divided into TBI and reversible intestinal ischemia groups based on the final therapeutic outcomes. Univariate and multivariate logistic regression analyses were conducted to identify independent risk factors for TBI using the training data, and a nomogram was subsequently developed. The performance of the nomogram was evaluated with respect to discrimination, calibration, and clinical usefulness in the training and external validation cohort. RESULTS: Univariate and multivariate logistic regression analyses identified the following independent prognostic factors associated with TBI in the training cohort: The decreased bowel wall enhancement (OR = 6.37, P < 0.001), rebound tenderness (OR = 7.14, P < 0.001), serum lactate levels > 2 mmol/L (OR = 3.14, P = 0.009) and previous history of deep venous thrombosis (OR = 6.37, P < 0.001). Incorporating these four factors, the nomogram achieved good calibration in the training set [area under the receiver operator characteristic curve (AUC) 0.860; 95%CI: 0.771-0.925] and the external validation set (AUC 0.851; 95%CI: 0.796-0.897). The positive and negative predictive values (95%CIs) of the nomogram were calculated, resulting in positive predictive values of 54.55% (40.07%-68.29%) and 53.85% (43.66%-63.72%) and negative predictive values of 93.33% (82.14%-97.71%) and 92.24% (85.91%-95.86%) for the training and validation cohorts, respectively. Based on the nomogram, patients who had a Nomo-score of more than 90 were considered to have high risk for TBI. Decision curve analysis indicated that the nomogram was clinically useful. CONCLUSION: The nomogram achieved an optimal prediction of TBI in patients with AMI. Using the model, the risk for an individual patient inclined to TBI can be assessed, thus providing a rational therapeutic choice.