Deep Learning of Multimodal Ultrasound: Stratifying the Response to Neoadjuvant Chemotherapy in Breast Cancer Before Treatment.

BACKGROUND: Not only should resistance to neoadjuvant chemotherapy (NAC) be considered in patients with breast cancer but also the possibility of achieving a pathologic complete response (PCR) after NAC. Our study aims to develop 2 multimodal ultrasound deep learning (DL) models to noninvasively predict resistance and PCR to NAC before treatment. METHODS: From January 2017 to July 2022, a total of 170 patients with breast cancer were prospectively enrolled. All patients underwent multimodal ultrasound examination (grayscale 2D ultrasound and ultrasound elastography) before NAC. We combined clinicopathological information to develop 2 DL models, DL_Clinical_resistance and DL_Clinical_PCR, for predicting resistance and PCR to NAC, respectively. In addition, these 2 models were combined to stratify the prediction of response to NAC. RESULTS: In the test cohort, DL_Clinical_resistance had an AUC of 0.911 (95%CI, 0.814-0.979) with a sensitivity of 0.905 (95%CI, 0.765-1.000) and an NPV of 0.882 (95%CI, 0.708-1.000). Meanwhile, DL_Clinical_PCR achieved an AUC of 0.880 (95%CI, 0.751-0.973) and sensitivity and NPV of 0.875 (95%CI, 0.688-1.000) and 0.895 (95%CI, 0.739-1.000), respectively. By combining DL_Clinical_resistance and DL_Clinical_PCR, 37.1% of patients with resistance and 25.7% of patients with PCR were successfully identified by the combined model, suggesting that these patients could benefit by an early change of treatment strategy or by implementing an organ preservation strategy after NAC. CONCLUSIONS: The proposed DL_Clinical_resistance and DL_Clinical_PCR models and combined strategy have the potential to predict resistance and PCR to NAC before treatment and allow stratified prediction of NAC response.

Image-Guided Thermal Ablation for Hepatic Epithelioid Hemangioendothelioma: A Multicenter Experience.

PURPOSE: To investigate the feasibility, safety, and clinical outcomes of image-guided thermal ablation in patients with hepatic epithelioid hemangioendothelioma (HEHE). MATERIALS AND METHODS: This was a multicenter retrospective investigation of 18 patients (43.9 years [SD ± 14.8]; 6 men) who underwent image-guided thermal ablation for HEHE between January 2013 and February 2023. A total of 31 ablation sessions (24 involving microwave ablation and 7 involving radiofrequency ablation) were evaluated. The rates of technical success, adverse events, and outcomes were assessed. The Kaplan‒Meier method was used to estimate progression-free survival (PFS) and overall survival (OS) rates. The risk factors affecting PFS were investigated using Cox proportional hazard regression analysis. RESULTS: The technical success rate was 93.5% (29/31). No major adverse events occurred. Local tumor progression occurred after 2 sessions (6.5%, 2/31), and intrahepatic distant metastasis occurred after 16 sessions (51.6%, 16/31). During the medium follow-up time of 37.2 months (range, 3-117 months), the OS and PFS rates were 87.6% and 62.2%, respectively, at 1 year; 75.5% and 37.4%, respectively, at 3 years; and 75.5% and 37.4%, respectively, at 5 years. The median OS and PFS were 90.5 months (95% CI: 68.1-112.8) and 23.8 months (95% CI: 15.4-32.2), respectively. According to the multivariate analysis, a larger tumor size (P = .026) was associated with shorter PFS. CONCLUSIONS: Image-guided thermal ablation is a feasible and safe treatment option for patients with HEHE that resulted in local tumor control and a favorable long-term prognosis.

Prospective assessment of pancreatic ductal adenocarcinoma diagnosis from endoscopic ultrasonography images with the assistance of deep learning.

BACKGROUND: Endosonographers are highly dependent on the diagnosis of pancreatic ductal adenocarcinoma (PDAC). The objectives of this study were to develop a deep-learning radiomics (DLR) model based on endoscopic ultrasonography (EUS) images for identifying PDAC and to explore its true clinical benefit. METHODS: A retrospective data set of EUS images that included PDAC and benign lesions was used as a training cohort (N = 368 patients) to develop the DLR model, and a prospective data set was used as a test cohort (N = 123 patients) to validate the effectiveness of the DLR model. In addition, seven endosonographers performed two rounds of reader studies on the test cohort with or without DLR assistance to further assess the clinical applicability and true benefits of the DLR model. RESULTS: In the prospective test cohort, DLR exhibited an area under the receiver operating characteristic curves of 0.936 (95% confidence interval [CI], 0.889-0.976) with a sensitivity of 0.831 (95% CI, 0.746-0.913) and 0.904 (95% CI, 0.820-0.980), respectively. With DLR assistance, the overall diagnostic performance of the seven endosonographers improved: one endosonographer achieved a significant expansion of specificity (p = .035,) and another achieved a significant increase in sensitivity (p = .038). In the junior endosonographer group, the diagnostic performance with the help of the DLR was higher than or comparable to that of the senior endosonographer group without DLR assistance. CONCLUSIONS: A prospective test cohort validated that the DLR model based on EUS images effectively identified PDAC. With the assistance of this model, the gap between endosonographers at different levels of experience narrowed, and the accuracy of endosonographers expanded.

Deep learning radiomics of ultrasonography for comprehensively predicting tumor and axillary lymph node status after neoadjuvant chemotherapy in breast cancer patients: A multicenter study.

BACKGROUND: Neoadjuvant chemotherapy (NAC) can downstage tumors and axillary lymph nodes in breast cancer (BC) patients. However, tumors and axillary response to NAC are not parallel and vary among patients. This study aims to explore the feasibility of deep learning radiomics nomogram (DLRN) for independently predicting the status of tumors and lymph node metastasis (LNM) after NAC. METHODS: In total, 484 BC patients who completed NAC from two hospitals (H1: 297 patients in the training cohort and 99 patients in the validation cohort; H2: 88 patients in the test cohort) were retrospectively enrolled. The authors developed two deep learning radiomics (DLR) models for personalized prediction of the tumor pathologic complete response (PCR) to NAC (DLR-PCR) and the LNM status (DLR-LNM) after NAC based on pre-NAC and after-NAC ultrasonography images. Furthermore, they proposed two DLRNs (DLRN-PCR and DLRN-LNM) for two different tasks based on the clinical characteristics and DLR scores, which were generated from both DLR-PCR and DLR-LNM. RESULTS: In the validation and test cohorts, DLRN-PCR exhibited areas under the receiver operating characteristic curves (AUCs) of 0.903 and 0.896 with sensitivities of 91.2% and 75.0%, respectively. DLRN-LNM achieved AUCs of 0.853 and 0.863, specificities of 82.0% and 81.8%, and negative predictive values of 81.3% and 87.2% in the validation and test cohorts, respectively. The two DLRN models achieved satisfactory predictive performance based on different BC subtypes. CONCLUSIONS: The proposed DLRN models have the potential to accurately predict the tumor PCR and LNM status after NAC. PLAIN LANGUAGE SUMMARY: In this study, we proposed two deep learning radiomics nomogram models based on pre-neoadjuvant chemotherapy (NAC) and preoperative ultrasonography images for independently predicting the status of tumor and axillary lymph node (ALN) after NAC. A more comprehensive assessment of the patient's condition after NAC can be achieved by predicting the status of the tumor and ALN separately. Our model can potentially provide a noninvasive and personalized method to offer decision support for organ preservation and avoidance of excessive surgery.

Radical Resection Combined With Intestinal Autotransplantation for Locally Advanced Pancreatic Cancer After Neoadjuvant Therapy: A Report of 36 Consecutive Cases.

OBJECTIVE: To achieve radical resection of locally advanced pancreatic ductal adenocarcinoma (PDAC), and tested the safety and benefits of intestinal autotransplantation in pancreatic surgery. BACKGROUND: PDAC has an extremely dismal prognosis. Radical resection was proved to improve the prognosis of patients with PDAC; however, the locally advanced disease had a very low resection rate currently. We explored and evaluated whether the combination of modern advances in systemic treatment and this macroinvasive surgery was feasible in clinical practice. METHODS: Patients diagnosed as PDAC with superior mesenteric artery involvement and with or without celiac trunk involvement were included. Patients were treated with modified-FOLFIRINOX chemotherapy with or without anti-PD-1 antibodies and were applied to tumor resection combined with intestinal autotransplantation. Data on operative parameters, pathologic results, mortality, morbidity, and survival were analyzed. RESULTS: A total of 36 consecutive cases were applied to this strategy and underwent radical resection combined with intestinal autotransplantation. Among these patients, 24 of them received the Whipple procedure, 11 patients received total pancreatectomy, and the other 1 patient received distal pancreatectomy. The median operation time was 539 minutes. Postoperative pathology showed an R0 resection rate of 94.4%, and tumor invasion of a superior mesenteric artery or superior mesenteric vein was confirmed in 32 patients. The median number of dissected lymph nodes was 43, and 25 patients were positive for lymph node metastasis. The median time of intensive care unit stay was 4 days. Two patients died within 30 days after surgery due to multiorgan failure. The severe postoperative adverse events (equal to or higher than grade 3) were observed in 12 out of 36 patients, and diarrhea, gastroparesis, and abdominal infection were the most frequent adverse events. Postoperative hospital stay was averagely of 34 days. The recurrence-free survival is 13.6 months. The median overall survival of patients after diagnosis and after surgery was 21.4 months and 14.5 months, respectively. CONCLUSIONS: Our attempt suggests the safety of this modality and may be clinically beneficial for highly selected patients with PDAC. However, the experience in multidisciplinary pancreatic cancer care and intestinal transplantation is warranted.

Microwave ablation versus laparoscopic resection as first-line therapy for solitary 3-5-cm HCC.

BACKGROUND AND AIMS: The study objective was to compare the effectiveness of microwave ablation (MWA) and laparoscopic liver resection (LLR) on solitary 3-5-cm HCC over time. APPROACH AND RESULTS: From 2008 to 2019, 1289 patients from 12 hospitals were enrolled in this retrospective study. Diagnosis of all lesions were based on histopathology. Propensity score matching was used to balance all baseline variables between the two groups in 2008-2019 (n = 335 in each group) and 2014-2019 (n = 257 in each group) cohorts, respectively. For cohort 2008-2019, during a median follow-up of 35.8 months, there were no differences in overall survival (OS) between MWA and LLR (HR: 0.88, 95% CI 0.65-1.19, p = 0.420), and MWA was inferior to LLR regarding disease-free survival (DFS) (HR 1.36, 95% CI 1.05-1.75, p = 0.017). For cohort 2014-2019, there was comparable OS (HR 0.85, 95% CI 0.56-1.30, p = 0.460) and approached statistical significance for DFS (HR 1.33, 95% CI 0.98-1.82, p = 0.071) between MWA and LLR. Subgroup analyses showed comparable OS in 3.1-4.0-cm HCCs (HR 0.88, 95% CI 0.53-1.47, p = 0.630) and 4.1-5.0-cm HCCs (HR 0.77, 95% CI 0.37-1.60, p = 0.483) between two modalities. For both cohorts, MWA shared comparable major complications (both p > 0.05), shorter hospitalization, and lower cost to LLR (all p < 0.001). CONCLUSIONS: MWA might be a first-line alternative to LLR for solitary 3-5-cm HCC in selected patients with technical advances, especially for patients unsuitable for LLR.

Safety and efficacy of microwave ablation for the treatment of low-risk papillary thyroid microcarcinoma: a prospective multicenter study.

OBJECTIVES: To assess the safety and efficacy of ultrasound-guided thermal ablation for low-risk papillary thyroid microcarcinoma (PTMC) via a prospective multicenter study. METHODS: From January 2017 through June 2021, low-risk PTMC patients were screened. The management details of active surveillance (AS), surgery, and thermal ablation were discussed. Among patients who accepted thermal ablation, microwave ablation (MWA) was performed. The main outcome was disease-free survival (DFS). The secondary outcomes were tumor size and volume changes, local tumor progression (LTP), lymph node metastasis (LNM), and complication rate. RESULTS: A total of 1278 patients were included in the study. The operation time of ablation was 30.21 ± 5.14 min with local anesthesia. The mean follow-up time was 34.57 ± 28.98 months. Six patients exhibited LTP at 36 months, of whom 5 patients underwent a second ablation, and 1 patient received surgery. The central LNM rate was 0.39% at 6 months, 0.63% at 12 months, and 0.78% at 36 months. Of the 10 patients with central LNM at 36 months, 5 patients chose ablation, 3 patients chose surgery and the other 2 patients chose AS. The overall complication rate was 1.41%, and 1.10% of patients developed hoarseness of the voice. All of the patients recovered within 6 months. CONCLUSIONS: Thermal ablation of low-risk PTMC was observed to be safe and efficacious with few minor complications. This technique may help to bridge the gap between surgery and AS as treatment options for patients wishing to have their PTMC managed in a minimally invasive manner. CLINICAL RELEVANCE STATEMENT: This study proved that microwave ablation is a safe and effective treatment method for papillary thyroid microcarcinoma. KEY POINTS: Percutaneous US-guided microwave ablation of papillary thyroid microcarcinoma is a very minimally invasive treatment under local anesthesia during a short time period. The local tumor progression and complication rate of microwave ablation in the treatment of papillary thyroid microcarcinoma are very low.

Long-term outcomes of endoscopic ultrasound-guided laser ablation for liver tumors in the caudate lobe: 5 years of experience.

OBJECTIVES: Liver tumor in the caudate lobe is challenging to treat, partly due to its deep location. Endoscopic ultrasound-guided laser ablation (EUS-LA) is a new attractive option for tumors in high-risk or difficult-to-reach locations. This prospective study investigated the long-term efficacy of EUS-LA for tumors in the caudate lobe, and factors that predict outcomes. METHODS: From June 2016 to July 2021, twenty consecutive patients (aged 56.95 ± 10.06 years) with 25 caudate lobe tumors (15.64 ± 6.37 mm) underwent EUS-LA. Treatment outcomes were assessed and predictive factors were calculated via univariate and multivariate analyses. RESULTS: Twenty-five tumors achieved complete ablation after the first or second session of EUS-LA. The treatment effectiveness was 100%. During a median follow up of 27 months (3-60), four tumors (16%) developed local tumor progression and 15 patients (75%) experienced intrahepatic distant recurrence. According to univariate and multivariate analyses, the significant prognostic factor of local tumor progression was tumor size >2 cm (p = 0.047). Significant prognostic factors of intrahepatic distant recurrence were: tumor number, alpha-fetoprotein level, and total bilirubin level (p = 0.020, 0.019, 0.010, respectively). No adverse events related to EUS-LA were observed. CONCLUSION: EUS-LA is a viable, safe, and effective treatment option for patients with liver tumor in the caudate lobe. Tumor size >2 cm increases the risk of post-procedural local tumor progression. Intrahepatic tumor number, and pretreatment alpha-fetoprotein level and total bilirubin level are associated with intrahepatic distant recurrence. REGISTRATION: Clinicaltrials.gov, ID: NCT02816944(June 29, 2016).

Diagnostic Value of Qualitative and Quantitative Contrast-Enhanced Ultrasound for Pathological Subtypes of Small Solid Renal Masses.

OBJECTIVES: To assess the diagnostic value of qualitative and quantitative contrast-enhanced ultrasound (CEUS) for pathological subtypes of small solid renal masses (sSRMs). METHODS: Patients with sSRMs confirmed by surgical pathology from January 2019 to November 2021 were retrospectively identified. All patients were divided into 3 groups: clear cell renal cell carcinoma (ccRCC) group, none-ccRCC group (renal cell carcinoma other than ccRCC), and angiomyolipoma (AML) group. The mass position, size, echogenicity and blood flow signals were compared. The speed of wash-in, wash-out, the degree of peak enhancement and the homogeneity at peak enhancement, the presence of pseudocapsule sign in CEUS imaging were qualitatively evaluated. Peak enhancement, wash-in area under the curve (WiAUC), rise time, time to peak, wash-in rate (WiR), wash-in perfusion index (WiPI) and tumor-to-cortex enhancement ratio of the above parameters in CEUS imaging were quantitatively evaluated. RESULTS: Of 105 patients, 105 sSRMs (66 ccRCC, 18 none-ccRCC, 21 AML) were enrolled in this study. No significant differences were found on location, size and echogenicity among 3 groups (all P > .05). The proportion of fast-washout and hypo-enhancement were highest in none-ccRCC group. Heterogeneous enhancement was detected in 87.88% in ccRCC group which is significantly higher than other 2 groups. Hundred percent of the AML showed no pseudocapsule sign, which is the highest among the 3 groups. Peak enhancement, WiAUC, WiR, WiPI of ccRCC group were the highest among the 3 groups. CONCLUSIONS: Qualitative and quantitative CEUS not only has the diagnostic value in distinguishing AML from malignant sSRMs, but also helps to differentiate the pathological subtypes of sSRMs.

On-Site Diagnostic Ability of CEUS/CT/MRI for Hepatocellular Carcinoma (2019-2022): A Multicenter Study.

OBJECTIVES: To compare the on-site diagnostic performance of contrast-enhanced ultrasound (CEUS), computed tomography (CECT), and magnetic resonance imaging (CEMRI) for hepatocellular carcinoma (HCC) across diverse practice settings. METHODS: Between May 2019 and April 2022, a total of 2085 patients with 2320 pathologically confirmed focal liver lesions (FLLs) were enrolled. Imaging reports were compared with results from pathology analysis. Diagnostic performance was analyzed in defined size, high-risk factors for HCC, and hospital volume categories. RESULTS: Three images achieved similar diagnostic performance in classifying HCC from 16 types of FLLs, including HCC ≤2.0 cm. For HCC diagnosis at low-volume hospitals and HCC with high-risk factors, the accuracy and specificity of CEUS were comparable to CECT and CEMRI, while the sensitivity of CEUS (77.4 and 89.5%, respectively) was inferior to CEMRI (87.0 and 92.8%, respectively). The diagnostic accuracy of CEUS + CEMRI and CEUS + CECT increased by 7.8 and 6.2% for HCC ≤2.0 cm, 8.0 and 5.0% for HCC with high-risk factors, and 7.4 and 5.5% for HCC at low-volume hospitals, respectively, compared with CEMRI/CECT alone. CONCLUSIONS: Compared with CECT and CEMRI, CEUS provides adequate diagnostic performance in clinical first-line applications at high-volume hospitals. Moreover, a higher diagnostic performance for HCC is achieved by combining CEUS with CECT/CEMRI compared with any single imaging technique.

Percutaneous ultrasound and endoscopic ultrasound-guided biopsy of solid pancreatic lesions: An analysis of 1074 lesions.

BACKGROUNDS: Percutaneous ultrasound (US) and endoscopic ultrasound (EUS)-guided pancreatic biopsies are widely accepted in the diagnosis of pancreatic diseases. Studies comparing the diagnostic performance of US- and EUS-guided pancreatic biopsies are lacking. This study aimed to evaluate and compare the diagnostic yields of US- and EUS-guided pancreatic biopsies and identify the risk factors for inconclusive biopsies. METHODS: Of the 1074 solid pancreatic lesions diagnosed from January 2017 to February 2021 in our center, 275 underwent EUS-guided fine needle aspiration (EUS-FNA), and 799 underwent US-guided core needle biopsy (US-CNB/FNA). The outcomes were inconclusive pathological biopsy, diagnostic accuracy and the need for repeat biopsy. All of the included factors and diagnostic performances of both US-CNB/FNA and EUS-FNA were compared, and the independent predictors for the study outcomes were identified. RESULTS: The diagnostic accuracy was 89.8% for EUS-FNA and 95.2% for US-CNB/FNA (P = 0.001). Biopsy under EUS guidance [odds ratio (OR) = 1.808, 95% confidence interval (CI): 1.083-3.019; P = 0.024], lesion size < 2 cm (OR = 2.069, 95% CI: 1.145-3.737; P = 0.016), hypoechoic appearance (OR = 0.274, 95% CI: 0.097-0.775; P = 0.015) and non-pancreatic ductal adenocarcinoma carcinoma (PDAC) diagnosis (OR = 2.637, 95% CI: 1.563-4.449; P < 0.001) were identified as factors associated with inconclusive pathological biopsy. Hypoechoic appearance (OR = 0.236, 95% CI: 0.064-0.869; P = 0.030), lesions in the uncinate process of the pancreas (OR = 3.506, 95% CI: 1.831-6.713; P < 0.001) and non-PDAC diagnosis (OR = 2.622, 95% CI: 1.278-5.377; P = 0.009) were independent predictors for repeat biopsy. Biopsy under EUS guidance (OR = 2.024, 95% CI: 1.195-3.429; P = 0.009), lesions in the uncinate process of the pancreas (OR = 1.776, 95% CI: 1.014-3.108; P = 0.044) and hypoechoic appearance (OR = 0.127, 95% CI: 0.047-0.347; P < 0.001) were associated with diagnostic accuracy. CONCLUSIONS: In conclusion, both percutaneous US- and EUS-guided biopsies of solid pancreatic lesions are safe and effective; though the diagnostic accuracy of EUS-FNA is inferior to US-CNB/FNA. A tailored pancreatic biopsy should be considered a part of the management algorithm for the diagnosis of solid pancreatic disease.

Deep learning radiomics based on contrast-enhanced ultrasound images for assisted diagnosis of pancreatic ductal adenocarcinoma and chronic pancreatitis.

BACKGROUND: Accurate and non-invasive diagnosis of pancreatic ductal adenocarcinoma (PDAC) and chronic pancreatitis (CP) can avoid unnecessary puncture and surgery. This study aimed to develop a deep learning radiomics (DLR) model based on contrast-enhanced ultrasound (CEUS) images to assist radiologists in identifying PDAC and CP. METHODS: Patients with PDAC or CP were retrospectively enrolled from three hospitals. Detailed clinicopathological data were collected for each patient. Diagnoses were confirmed pathologically using biopsy or surgery in all patients. We developed an end-to-end DLR model for diagnosing PDAC and CP using CEUS images. To verify the clinical application value of the DLR model, two rounds of reader studies were performed. RESULTS: A total of 558 patients with pancreatic lesions were enrolled and were split into the training cohort (n=351), internal validation cohort (n=109), and external validation cohorts 1 (n=50) and 2 (n=48). The DLR model achieved an area under curve (AUC) of 0.986 (95% CI 0.975-0.994), 0.978 (95% CI 0.950-0.996), 0.967 (95% CI 0.917-1.000), and 0.953 (95% CI 0.877-1.000) in the training, internal validation, and external validation cohorts 1 and 2, respectively. The sensitivity and specificity of the DLR model were higher than or comparable to the diagnoses of the five radiologists in the three validation cohorts. With the aid of the DLR model, the diagnostic sensitivity of all radiologists was further improved at the expense of a small or no decrease in specificity in the three validation cohorts. CONCLUSIONS: The findings of this study suggest that our DLR model can be used as an effective tool to assist radiologists in the diagnosis of PDAC and CP.

Etiology, case fatality, recurrence, and severity in pediatric acute pancreatitis: a meta-analysis of 48 studies.

For children, there are very few published reviews focusing on severe acute pancreatitis (AP). PubMed, EMBASE, Web of Science, Scopus, Chinese National Knowledge Infrastructure (CNKI), Wanfang data, EBSCO, and Cochrane Library were searched from inception until March 2020. Meta-regression analyses were used to estimate the etiology, case fatality, recurrence, and severity of pediatric AP in different regions (North America, Asia, South America, Europe, and Oceania). Pooled data from 47 papers (48 studies) found that main causes of pediatric AP were gallstones in Asia; trauma in Oceania; and idiopathic in Europe, North America, and South America. The case-fatality rate (CFR) of pediatric AP is 4.7% (North America), 6.2% (Europe), 2.4% (Asia), 3.1% (South America), and 7.4% (Oceania). The incidence rates of recurrent acute pancreatitis (RAP) in children who have had an episode of acute pancreatitis in North American, Asia, and Europe were 15.3, 13.1, and 13.8%, respectively. The incidence of severe acute pancreatitis (SAP) in different regions was 30.3% (Oceania), 29.2% (South America), 20.8% (Europe), 15.8% (Asia), and 13.7% (North America). It suggests that physicians should notice the etiology of pediatric AP for the initial assessment, diagnosis, prediction of relapse, and appropriate treatment at a later stage. IMPACT: It indicates the etiology of pediatric acute pancreatitis for the initial assessment, diagnosis, and prediction of relapse. Main causes of pediatric AP were gallstones in Asia; trauma in Oceania; and idiopathic in Europe, North America, and South America. The case-fatality rate of pediatric AP is diverse worldwide. It suggests that physicians noticed the etiology of pediatric AP for the initial assessment, diagnosis, prediction of relapse, and appropriate treatment at a later stage.

Deep learning radiomics of ultrasonography can predict response to neoadjuvant chemotherapy in breast cancer at an early stage of treatment: a prospective study.

OBJECTIVES: Breast cancer (BC) is the most common cancer in women worldwide, and neoadjuvant chemotherapy (NAC) is considered the standard of treatment for most patients with BC. However, response rates to NAC vary among patients, which leads to delays in appropriate treatment and affects the prognosis for patients who ineffectively respond to NAC. This study aimed to investigate the feasibility of deep learning radiomics (DLR) in the prediction of NAC response at an early stage. METHODS: In total, 168 patients with clinicopathologically confirmed BC were enrolled in this prospective study, from March 2016 to December 2020. All patients completed NAC treatment and underwent ultrasonography (US) at three time points (before NAC, after the second course, and after the fourth course). We developed two DLR models, DLR-2 and DLR-4, for predicting responses after the second and fourth courses of NAC. Furthermore, a novel deep learning radiomics pipeline (DLRP) was proposed for stepwise prediction of response at different time points of NAC administration. RESULTS: In the validation cohort, DLR-2 achieved an AUC of 0.812 (95% CI: 0.770-0.851) with an NPV of 83.3% (95% CI: 76.5-89.6). DLR-4 achieved an AUC of 0.937 (95% CI: 0.913-0.955) with a specificity of 90.5% (95% CI: 86.3-94.2). Moreover, 19 of 21 non-response patients were successfully identified by DLRP, suggesting that they could benefit from treatment strategy adjustment at an early stage of NAC. CONCLUSIONS: The proposed DLRP strategy holds promise for effectively predicting NAC response at its early stage for BC patients. KEY POINTS: • We proposed two novel deep learning radiomics (DLR) models to predict response to neoadjuvant chemotherapy (NAC) in breast cancer (BC) patients based on US images at different NAC time points. • Combining two DLR models, a deep learning radiomics pipeline (DLRP) was proposed for stepwise prediction of response to NAC. • The DLRP may provide BC patients and physicians with an effective and feasible tool to predict response to NAC at an early stage and to determine further personalized treatment options.

High-Frequency Ultrasonography Evaluation of Acne by Thickness and Power Doppler Vascular Analysis.

OBJECTIVES: To assess acne vulgaris quantitatively using high-frequency ultrasonography (HF-USG) and power Doppler (PD), and investigate the feasibility and application value of HF-USG and PD in acne vulgaris. METHODS: A total of 105 patients with the diagnosis of acne vulgaris in the face referred by a dermatologist were studied prospectively. All the acne patients enrolled were clinically classified by two attending dermatologists independently using three degrees with four levels of classification evaluating only the severest lesion. Gray-scale ultrasound was used to assess the thickness of the lesion, and the thickness ratio was calculated. PD equipped with Qpack semi-quantitative analysis software was used to assess blood signals of the lesion, and Qpack ratio, Qpack peak were calculated. Ten level-4 acne patients were re-evaluated after 2 weeks' treatment, and the results were compared with those before treatment. RESULTS: A total of 105 patients were categorized into four groups by dermatologists, 23 cases were comedones, 33 were papules, 26 were pustules, and 23 were nodules/cysts. There were significant differences in thickness ratio (P < .001), Qpack ratio (P < .001), and Qpack peak (P < .001) among the four groups. For the 10 level-4 acne patients treated 2 weeks by the dermatologist, the difference in thickness ratio between pre-treatment and post-treatment showed no significance (P = .06). However, Qpack ratio and Qpack peak were significantly decreased between pre-treatment and post-treatment (both P = .01). CONCLUSIONS: HF-USG and PD equipped with semi-quantitative analysis software can assess acne vulgaris quantitatively, which provides a good basis for the classification and treatment of acne. Their features include thickness ratio, Qpack ratio, and Qpack peak, with Qpack ratio and Qpack peak being the sensitive features for the early efficacy evaluation.

Conditional standards for the quantification of foetal growth in an ethnic Chinese population: a longitudinal study.

This was an observational study of low-risk singleton pregnancies in an ethnic Chinese population. Foetal biometric variables which included biparietal diameter (BPD), head circumference (HC), abdominal circumference (AC) and femur length (FL) were measured repeatedly. The standard views for measurement were obtained according to INTERGROWTH-21st criteria. A linear mixed model with fractional polynomial regression was used to describe the longitudinal design. The study included 1289 foetuses and a total of 5125 ultrasound scans, of which each foetus was scanned at least three times, the intervals between scans being at least two weeks. The parameters of the linear mixed models were estimated by Stata v.16 (College Station, TX). Using these parameters, the equations of the mean and variance for BPD, HC, AC and FL were constructed. The conditional percentiles or Z scores could be calculated based on the above equations and previous measurements of the same foetus. A spreadsheet was provided for implementation.Impact StatementWhat is already known on this subject? Longitudinal data derived from serial measurements are therefore appropriate for assessing both foetal size and foetal growth. At present, most reference charts of ethnic Chinese foetal biometry are derived from cross-sectional data, which can only assess foetal size.What do the results of this study add? In this study, we have constructed conditional standards for foetal biometry in an ethnic Chinese population and provided a spreadsheet for querying.What are the implications of these findings for clinical practice and/or further research? The conditional standards can be used to assess foetal growth in clinical practice. In the future, we hope that these foetal growth standards can be applied to determine whether abnormal growth increases the risk of adverse outcomes.

Fusion imaging-guided radiofrequency ablation for residual hepatocellular carcinoma invisible on ultrasound after transcatheter arterial chemoembolization.

PURPOSE: This study aimed to investigate the technical efficiency and therapeutic response of fusion imaging (considered as virtual navigation) between contrast-enhanced ultrasound (CEUS) and contrast-enhanced computed tomography/magnetic resonance imaging (CECT/CEMRI) for the guidance of radiofrequency ablation (RFA) in patients with residual hepatocellular carcinoma (HCC) after transcatheter arterial chemoembolization (TACE). METHODS: For this prospective study, 98 patients with residual HCC lesions after TACE treatment were enrolled between June 2017 and December 2020. All the lesions were invisible on conventional ultrasound scans. Percutaneous RFA was performed using either CEUS (CEUS group, 52 lesions) or virtual navigation (VN group, 46 lesions) guidance. The lesion display rate, disease-free survival rate, local recurrence rate, overall survival rate and complication incidence were calculated and compared. RESULTS: Fusion imaging had a significant impact on the RFA outcomes (hazard ratio, 2.629; 95% confidence interval, 1.256-5.505; p = .01). The median disease-free survival time of the VN group was significantly higher than that of the CEUS group (10.9 vs. 8.8 months; p = .007). The local recurrence rates after 3, 6 and 12 months in the VN group were significantly lower than those in the CEUS group (p = .014, .002 and .011). The minor complication rate was not significantly different between the two groups. CONCLUSIONS: CEUS-CECT/CEMRI fusion imaging for guiding RFA enables an efficient and useful therapy of inconspicuous HCC lesions after TACE. The novel solution prolongs the disease-free survival time and reduces the long-term local recurrence of residual lesions treated when using virtual-navigation (VN)-guided RFA.

Added value of contrast-enhanced ultrasound (CEUS) in the diagnosis of primary retroperitoneal serous adenocarcinoma: a case report.

BACKGROUND: Primary retroperitoneal serous adenocarcinoma (PRSA) is a rare malignant disease. Given the rarity of the disease, the imaging features of PRSA are unclear. Contrast-enhanced ultrasound (CEUS) also plays an important role in the evaluation of the differential diagnosis of retroperitoneal lesions. CASE PRESENTATION: We report the case of a 62-year-old woman of with increased CA125 levels for 1 year who was referred to our hospital. After conducting contrast-enhanced computed tomography and magnetic resonance imaging, the mass was misdiagnosed as a chocolate cyst. After transvaginal ultrasound (TUS) combined with CEUS, cystadenocarcinoma was considered as the initial diagnosis. Pathology results confirmed PRSA as the final diagnosis. CONCLUSIONS: CEUS features of PRSA are reported for the first time based on this case, potentially aiding in the differential diagnosis of this rare entity before surgery.

Comparison Between SonoVue and Sonazoid Contrast-Enhanced Ultrasound in Characterization of Focal Nodular Hyperplasia Smaller Than 3 cm.

OBJECTIVES: This study aimed to compare the diagnostic efficacy of contrast-enhanced ultrasound (CEUS), including SonoVue (SV; sulfur hexafluoride; Bracco SpA, Milan, Italy) and Sonazoid (SZ; perflubutane; GE Healthcare, Oslo, Norway), and explore the differences between them in the characterization of CEUS features in focal nodular hyperplasia (FNH) smaller than 3 cm. METHODS: This retrospective study included 31 lesions smaller than 3 cm diagnosed as FNH by CEUS between April 2019 and November 2019. Nine patients underwent SZ CEUS examinations, and 22 patients underwent SV CEUS examinations; all of them were confirmed by pathologic examinations or 2 other kinds of CEUS methods. We compared the CEUS features between SZ and SV in different phases, including arterial, portal venous, delayed, and Kupffer (SZ) phases. RESULTS: Twenty-eight lesions were eventually diagnosed as FNH; 3 were misdiagnosed as FNH by SV CEUS. The overall diagnostic accuracy of CEUS including SZ and SV was 90.3% (28 of 31). No significant difference was found (P > .05) for the positive predictive value. Likewise, no significant difference in depicting centrifugal filling (9 of 9 versus 19 of 19), spoke wheel artery (6 of 9 versus 8 of 19), or feeding artery (2 of 9 versus 10 of 19) features was found between the contrast agents; However, SZ was significantly better at depicting the presence of a central scar than SV (5 of 9 versus 3 of 19; P = .030). Misdiagnosed cases are discussed in detail. CONCLUSIONS: Contrast-enhanced ultrasound enables an accurate diagnosis in FNH smaller than 3 cm. Sonazoid CEUS and SV CEUS were comparable in diagnosing small FNH, and both agents were highly capable of depicting the centrifugal filling dynamic process of FNH smaller than 3 cm. Sonazoid CEUS might be better than SV CEUS at depicting a central scar.

Uterine mass after caesarean section: a report of two cases.

BACKGROUND: Caesarean scar pregnancy (CSP) is a rare complication of caesarean delivery and a special type of ectopic pregnancy. Gestational trophoblastic neoplasia (GTN) is an uncommon complication of pregnancy. Early diagnosis of the two diseases is crucial because a delay or misdiagnosis can lead to increased maternal morbidity and mortality. CASE PRESENTATION: We report two cases of uterine isthmus lesions with a previous caesarean section (CS). Two patients were misdiagnosed based on the first ultrasound exam. The first case of trophoblastic tumour was initially diagnosed as CSP, while the second case, which had a scar pregnancy, was misdiagnosed as GTN. The misdiagnoses were due to the particularity of the locations of the lesions in the two patients, complicating the ultrasound-based diagnosis and hindering early clinical diagnosis and treatment. CONCLUSIONS: A medical history, ß-hCG measurements and transvaginal ultrasound are necessary to diagnose lesions in the lower anterior wall of the uterus early. However, when the location cannot be determined, magnetic resonance imaging (MRI) can be further performed to determine whether the lesion is located at the uterine scar. Combined with the degree of increased ß-hCG, differentiate CSP, myometrial GTN or caesarean scar GTN is helpful.