A deep learning fusion network trained with clinical and high-frequency ultrasound images in the multi-classification of skin diseases in comparison with dermatologists: a prospective and multicenter study.

Background: Clinical appearance and high-frequency ultrasound (HFUS) are indispensable for diagnosing skin diseases by providing internal and external information. However, their complex combination brings challenges for primary care physicians and dermatologists. Thus, we developed a deep multimodal fusion network (DMFN) model combining analysis of clinical close-up and HFUS images for binary and multiclass classification in skin diseases. Methods: Between Jan 10, 2017, and Dec 31, 2020, the DMFN model was trained and validated using 1269 close-ups and 11,852 HFUS images from 1351 skin lesions. The monomodal convolutional neural network (CNN) model was trained and validated with the same close-up images for comparison. Subsequently, we did a prospective and multicenter study in China. Both CNN models were tested prospectively on 422 cases from 4 hospitals and compared with the results from human raters (general practitioners, general dermatologists, and dermatologists specialized in HFUS). The performance of binary classification (benign vs. malignant) and multiclass classification (the specific diagnoses of 17 types of skin diseases) measured by the area under the receiver operating characteristic curve (AUC) were evaluated. This study is registered with www.chictr.org.cn (ChiCTR2300074765). Findings: The performance of the DMFN model (AUC, 0.876) was superior to that of the monomodal CNN model (AUC, 0.697) in the binary classification (P = 0.0063), which was also better than that of the general practitioner (AUC, 0.651, P = 0.0025) and general dermatologists (AUC, 0.838; P = 0.0038). By integrating close-up and HFUS images, the DMFN model attained an almost identical performance in comparison to dermatologists (AUC, 0.876 vs. AUC, 0.891; P = 0.0080). For the multiclass classification, the DMFN model (AUC, 0.707) exhibited superior prediction performance compared with general dermatologists (AUC, 0.514; P = 0.0043) and dermatologists specialized in HFUS (AUC, 0.640; P = 0.0083), respectively. Compared to dermatologists specialized in HFUS, the DMFN model showed better or comparable performance in diagnosing 9 of the 17 skin diseases. Interpretation: The DMFN model combining analysis of clinical close-up and HFUS images exhibited satisfactory performance in the binary and multiclass classification compared with the dermatologists. It may be a valuable tool for general dermatologists and primary care providers. Funding: This work was supported in part by the National Natural Science Foundation of China and the Clinical research project of Shanghai Skin Disease Hospital.

Decoding the molecular subtypes of breast cancer seen on multimodal ultrasound images using an assembled convolutional neural network model: A prospective and multicentre study.

BACKGROUND: Preoperative determination of breast cancer molecular subtypes facilitates individualized treatment plan-making and improves patient prognosis. We aimed to develop an assembled convolutional neural network (ACNN) model for the preoperative prediction of molecular subtypes using multimodal ultrasound (US) images. METHODS: This multicentre study prospectively evaluated a dataset of greyscale US, colour Doppler flow imaging (CDFI), and shear-wave elastography (SWE) images in 807 patients with 818 breast cancers from November 2016 to February 2021. The St. Gallen molecular subtypes of breast cancer were confirmed by postoperative immunohistochemical examination. The monomodal ACNN model based on greyscale US images, the dual-modal ACNN model based on greyscale US and CDFI images, and the multimodal ACNN model based on greyscale US and CDFI as well as SWE images were constructed in the training cohort. The performances of three ACNN models in predicting four- and five-classification molecular subtypes and identifying triple negative from non-triple negative subtypes were assessed and compared. The performance of the multimodal ACNN was also compared with preoperative core needle biopsy (CNB). FINDING: The performance of the multimodal ACNN model (macroaverage area under the curve [AUC]: 0.89-0.96) was superior to that of the dual-modal ACNN model (macroaverage AUC: 0.81-0.84) and the monomodal ACNN model (macroaverage AUC: 0.73-0.75) in predicting four-classification breast cancer molecular subtypes, which was also better than that of preoperative CNB (AUC: 0.89-0.99 vs. 0.67-0.82, p < 0.05). In addition, the multimodal ACNN model outperformed the other two ACNN models in predicting five-classification molecular subtypes (AUC: 0.87-0.94 vs. 0.78-0.81 vs. 0.71-0.78) and identifying triple negative from non-triple negative breast cancers (AUC: 0.934-0.970 vs. 0.688-0.830 vs. 0.536-0.650, p < 0.05). Moreover, the multimodal ACNN model obtained satisfactory prediction performance for both T1 and non-T1 lesions (AUC: 0.957-0.958 and 0.932-0.985). INTERPRETATION: The multimodal US-based ACNN model is a potential noninvasive decision-making method for the management of patients with breast cancer in clinical practice. FUNDING: This work was supported in part by the National Natural Science Foundation of China (Grants 81725008 and 81927801), Shanghai Municipal Health Commission (Grants 2019LJ21 and SHSLCZDZK03502), and the Science and Technology Commission of Shanghai Municipality (Grants 19441903200, 19DZ2251100, and 21Y11910800).

A Comparative Analysis of Two Machine Learning-Based Diagnostic Patterns with Thyroid Imaging Reporting and Data System for Thyroid Nodules: Diagnostic Performance and Unnecessary Biopsy Rate.

Background: The risk stratification system of the American College of Radiology Thyroid Imaging Reporting and Data System (ACR TI-RADS) for thyroid nodules is affected by low diagnostic specificity. Machine learning (ML) methods can optimize the diagnostic performance in medical image analysis. However, it is unknown which ML-based diagnostic pattern is more effective in improving diagnostic performance for thyroid nodules and reducing nodule biopsies. Therefore, we compared ML-assisted visual approaches and radiomics approaches with ACR TI-RADS in diagnostic performance and unnecessary fine-needle aspiration biopsy (FNAB) rate for thyroid nodules. Methods: This retrospective study evaluated a data set of ultrasound (US) and shear wave elastography (SWE) images in patients with biopsy-proven thyroid nodules (≥1 cm) from the Shanghai Tenth People's Hospital (743 nodules in 720 patients from September 2017 to January 2019) and an independent test data set from the Ma'anshan People's Hospital (106 nodules in 102 patients from February 2019 to April 2019). Six US features and five SWE parameters from the radiologists' interpretation were used for building the ML-assisted visual approaches. The radiomics features extracted from the US and SWE images were used with ML methods for developing the radiomics approaches. The diagnostic performance for differentiating thyroid nodules and the unnecessary FNAB rate of the ML-assisted visual approaches and the radiomics approaches were compared with ACR TI-RADS. Results: The ML-assisted US visual approach had the best diagnostic performance than the US radiomics approach and ACR TI-RADS (area under the curve [AUC]: 0.900 vs. 0.789 vs. 0.689 for the validation data set, 0.917 vs. 0.770 vs. 0.681 for the test data set). After adding SWE, the ML-assisted visual approach had a better diagnostic performance than US alone (AUC: 0.951 vs. 0.900 for the validation data set, 0.953 vs. 0.917 for the test data set). When applying the ML-assisted US+SWE visual approach, the unnecessary FNAB rate decreased from 30.0% to 4.5% in the validation data set and from 37.7% to 4.7% in the test data set in comparison to ACR TI-RADS. Conclusions: The ML-assisted dual modalities visual approach can assist radiologists to diagnose thyroid nodules more effectively and considerably reduce the unnecessary FNAB rate in the clinical management of thyroid nodules.

Effect of different sulfadimidine addition methods on its degradation behaviour in swine manure.

Sulfadimidine (SM2) is commonly used in the swine industry and enters the environment via faeces. In recent years, advances in the ecotoxicology of SM2 have become a popular research interest with two common research methods including swine manure collection from swine fed with a diet containing SM2 and directly adding SM2. The purpose of this experiment was to compare SM2 degradation behaviour in pig manure with two different SM2 addition methods. The results showed that the degradation half-lives of SM2 in manure from SM2-fed swine treatment were 33.2 and 32.0 days at the initial addition level of SM2 at 32.1 and 64.3 mg/kg, respectively. This was significantly longer than that in manure directly adding SM2 treatment with the half-lives of 21.4 and 14.8 days. The metabolite of SM2 N4-acetyl-sulfamethazine occurred in manure from SM2-fed swine treatment but was not detected in directly adding SM2 treatment. The pH in manure from SM2-fed swine treatment was significantly lower than that in directly adding SM2 treatment, but the values of organic carbon, total nitrogen, and electrical conductivity in manure from SM2-fed swine treatment were significantly higher than those in manure directly adding SM2 treatment. Meanwhile, although the copy number of bacteria had no significant difference between two treatments, there was a significant difference in bacteria diversity. Results of the present study demonstrated that the presence of the metabolites, chemical property, and microbial diversity might be the reason for different SM2 degradation behaviours on different addition methods. Thus, the method using manure with SM2 collected from swine could obtain more accurate results for the ecotoxicological study of SM2.

Serum cystatin C level is associated with carotid intima-media thickening and plaque.

BACKGROUND AND AIM: Chronic kidney disease has recently been shown to be a major risk factor for cardiovascular disease and carotid intima-media thickness has been widely used as a biomarker for early detection of cardiovascular disease. The aim of this study was to confirm whether carotid thickening and carotid plaque are associated with preclinical chronic kidney disease in individuals without clinical cardiovascular disease and chronic kidney disease. MATERIAL AND METHODS: We conducted a cross-sectional study on participants from Maanshan City, China. All participants underwent carotid ultrasonography. Kidney function was measured using cystatin C, serum creatinine, blood urea nitrogen and blood uric acid. Demographics and risk factors for cardiovascular diseases were obtained from each participant. RESULTS: A total of 927 subjects were surveyed; 453 (48.87%) were men and 474 (51.13%) were women. A total of 525 (56.63%) of the participants were found to have carotid thickening of which 281 (53.52%) were men and 244 (46.48%) were women. Kidney function was strongly associated with carotid thickening and plaque in the unadjusted analysis. However, cystatin C was the only measure of kidney function that was significantly associated with carotid thickening and plaque in the adjusted analysis (in order to select risk factors from sex, age, BMI, hypertension, diabetes, smoking, total cholesterol, triglyceride, high-density lipoprotein, low-density lipoprotein, apolipoprotein A, apolipoprotein B, cystatin C, creatinine, blood urea nitrogen, blood uric, estimated GFR). CONCLUSION: Cystatin C, an alternative measure of kidney function, was more strongly associated with carotid thickening and plaque than other measures of kidney function.

Gold-catalyzed oxidative rearrangement of homopropargylic ether via oxonium ylide.

Synthetically useful α,ß-unsaturated carbonyl compounds were obtained from gold-catalyzed oxidative rearrangement of homopropargylic ether under mild reaction conditions. Gold carbenoid and oxonium ylide are proposed as key intermediates.

4,6-Dichloro-5-(2-meth-oxy-phen-oxy)-2,2'-bipyrimidine.

In the title compound, C(15)H(10)Cl(2)N(4)O(2), the dichloro-pyrimidine and meth-oxy-phen-oxy parts are approximately perpendicular [dihedral angle = 89.9 (9)°]. The dihedral angle between the two pyrimidine rings is 36.3 (4)° In the crystal, there are no hydrogen bonds but the mol-ecules are held together by short inter-molecular C⋯N [3.206 (3) Å] contacts and C-H⋯π inter-actions.