PURPOSE: 
Histological grading is important for the treatment algorithm in pancreatic neuroendocrine neoplasms (PNEN). The present study examined the efficacy of contrast-enhanced harmonic endoscopic ultrasound (CH-EUS) and time-intensity curve (TIC) analysis of PNEN diagnosis and grading. 
METHODS: 
TIC analysis was performed in 30 patients using data obtained from CH-EUS, and a histopathological diagnosis was made via EUS-guided fine-needle aspiration or surgical resection. The TIC parameters were analyzed by dividing them into G1/G2 and G3/NEC groups. Then, patients were classified into non-aggressive and aggressive groups and evaluated. 
RESULTS: 
Twenty-six patients were classified as G1/G2, and four as G3/NEC. From the TIC analysis, five parameters were obtained (I: echo intensity change, II: time for peak enhancement, III: speed of contrast, IV: decrease rate for enhancement, and V: enhancement ratio for node/pancreatic parenchyma). Three of these parameters (I, IV, and V) showed high diagnostic performance. Using the cutoff value obtained from the receiver-operating characteristic (ROC) analysis, the correct diagnostic rates of parameters I, IV, and V were 96.7%, 100%, and 100%, respectively, between G1/G2 and G3/NEC. A total of 21 patients were classified into the non-aggressive group, and nine into the aggressive group. Using the cutoff value obtained from the ROC analysis, the accurate diagnostic rates of I, IV, and V were 86.7%, 86.7%, and 88.5%, respectively, between the non-aggressive and aggressive groups.
 
CONCLUSION: 
CH-EUS and TIC analysis showed high diagnostic accuracy for grade diagnosis of PNEN. Quantitative perfusion analysis is useful to predict PNEN grade diagnosis preoperatively.

/pdf/contrast-enhanced-harmonic-endoscopic-ultrasound-using-time-2mob5l32ii.pdf

Contrast-enhanced harmonic endoscopic ultrasound using time–intensity curve analysis predicts pathological grade of pancreatic neuroendocrine neoplasm

This paper aims to build an artificial intelligence (AI) architecture for automated extraction of learned-from-data image features from contrast-enhanced ultrasound (CEUS) videos and to evaluate the AI architecture for classification between benign and malignant cervical lymph nodes. An AI architecture for CEUS feature extraction and classification was constructed by using the point-wise gated Boltzmann machine (PGBM). The PGBM consisted of task-relevant and task-irrelevant hidden units for both feature learning and feature selection, and the task-relevant units were connected to the support vector machine (SVM) to yield the likelihood for classification. The synthetic minority over-sampling technique was used to improve the classification ability for an unbalanced data set. Experimental evaluation was performed with the five-fold cross validation on a database of 127 lymph nodes (39 benign and 88 malignant) from 88 patients. The SVM likelihood exhibited a significant difference between benign and malignant cervical lymph nodes (0.74 ± 0.21 versus 0.33 ± 0.28, $p ). On the test set, the accuracy, precision, sensitivity, specificity, and Youden’s index of the AI architecture were 82.55%, 89.58%, 84.75%, 77.56%, and 62.32%, respectively. The AI architecture using the PGBM shows promising classification results, and it may be potentially used in clinical diagnosis for cervical lymph node malignancy.

Artificial Intelligence Based Diagnosis for Cervical Lymph Node Malignancy Using the Point-Wise Gated Boltzmann Machine

Four-quadrant fast compressive tracking of breast ultrasound videos for computer-aided response evaluation of neoadjuvant chemotherapy in mice

Objective:Axillary lymph node status assessment has always been an important issue in clinical treatment of breast cancer. However, there has been no effective method to accurately predict the path...

Application of conventional ultrasonography combined with contrast-enhanced ultrasonography in the axillary lymph nodes and evaluation of the efficacy of neoadjuvant chemotherapy in breast cancer patients.

This prospective study was aimed at evaluating the role of automated breast ultrasound (ABUS) and contrast-enhanced ultrasound (CEUS) in the early prediction of treatment response to neoadjuvant chemotherapy (NAC) in patients with breast cancer.Forty-three patients with pathologically confirmed invasive breast cancer treated with NAC were included. The standard for evaluation of response to NAC was based on surgery within 21 d of completing treatment. The patients were classified as having a pathological complete response (pCR) and a non-pCR. All patients underwent CEUS and ABUS 1 wk before receiving NAC and after two treatment cycles. The rising time (RT), time to peak (TTP), peak intensity (PI), wash-in slope (WIS) and wash-in area under the curve (Wi-AUC) were measured on the CEUS images before and after NAC. The maximum tumor diameters in the coronal and sagittal planes were measured on ABUS, and the tumor volume (V) was calculated. The difference (∆) in each parameter between the two treatment time points was compared. Binary logistic regression analysis was used to identify the predictive value of each parameter.∆V, ∆TTP and ∆PI were independent predictors of pCR. The CEUS-ABUS model achieved the highest AUC (0.950), followed by those based on CEUS (0.918) and ABUS (0.891) alone.The CEUS-ABUS model could be used clinically to optimize the treatment of patients with breast cancer. 

Early Prediction of Response to Neoadjuvant Chemotherapy Using Quantitative Parameters on Automated Breast Ultrasound Combined with Contrast-Enhanced Ultrasound in Breast Cancer.

Lei Tang

Papers

Evaluating pathologic response of breast cancer to neoadjuvant chemotherapy with computer-extracted features from contrast-enhanced ultrasound videos.