Assessment of diagnostic value of unilateral systematic biopsy combined with targeted biopsy in detecting clinically significant prostate cancer.

Objectives: This retrospective study assessed the diagnostic accuracy of targeted biopsy (TB) and unilateral systematic biopsy in detecting clinically significant prostate cancer (csPCa) in 222 men with single magnetic resonance imaging (MRI) lesions (Prostate Imaging Reporting and Data System [PI-RADS] ≥ 3). Methods: Patients underwent multiparametric MRI and MRI/ultrasound fusion TB and 12-needle standard biopsy (SB) from September 2016 to June 2021. The study compared the diagnostic performance of TB + iSB (ipsilateral), TB + contralateral system biopsy (cSB) (contralateral), and TB alone for csPCa using the χ 2 test and analysis of variance. Results: Among 126 patients with csPCa (ISUP ≥ 2), detection rates for TB + iSB, TB + cSB, and TB were 100, 98.90, and 100% for lesions, respectively. TB + iSB showed the highest sensitivity and negative predictive value. No significant differences in accuracy were found between TB + iSB and the gold standard for type 3 lesions (P = 1). For types 4-5, detection accuracy was comparable across methods (P = 0.314, P = 0.314, P = 0.153). TB had the highest positive needle count rate, with TB + iSB being second for type 3 lesions (4.08% vs 6.57%, P = 0.127). Conclusion: TB + iSB improved csPCa detection rates and reduced biopsy numbers, making it a viable alternative to TB + SB for single MRI lesions.

Attention-Guided Learning with Feature Reconstruction for Skin Lesion Diagnosis using Clinical and Ultrasound Images.

Skin lesion is one of the most common diseases, and most categories are highly similar in morphology and appearance. Deep learning models effectively reduce the variability between classes and within classes, and improve diagnostic accuracy. However, the existing multi-modal methods are only limited to the surface information of lesions in skin clinical and dermatoscopic modalities, which hinders the further improvement of skin lesion diagnostic accuracy. This requires us to further study the depth information of lesions in skin ultrasound. In this paper, we propose a novel skin lesion diagnosis network, which combines clinical and ultrasound modalities to fuse the surface and depth information of the lesion to improve diagnostic accuracy. Specifically, we propose an attention-guided learning (AL) module that fuses clinical and ultrasound modalities from both local and global perspectives to enhance feature representation. The AL module consists of two parts, attention-guided local learning (ALL) computes the intra-modality and inter-modality correlations to fuse multi-scale information, which makes the network focus on the local information of each modality, and attention-guided global learning (AGL) fuses global information to further enhance the feature representation. In addition, we propose a feature reconstruction learning (FRL) strategy which encourages the network to extract more discriminative features and corrects the focus of the network to enhance the model's robustness and certainty. We conduct extensive experiments and the results confirm the superiority of our proposed method. Our code is available at: https://github.com/XCL-hub/AGFnet.

Allogeneic CD19-targeted CAR-T therapy in patients with severe myositis and systemic sclerosis.

Allogeneic chimeric antigen receptor (CAR)-T cells hold great promise for expanding the accessibility of CAR-T therapy, whereas the risks of allograft rejection have hampered its application. Here, we genetically engineered healthy-donor-derived, CD19-targeting CAR-T cells using CRISPR-Cas9 to address the issue of immune rejection and treated one patient with refractory immune-mediated necrotizing myopathy and two patients with diffuse cutaneous systemic sclerosis with these cells. This study was registered at ClinicalTrials.gov (NCT05859997). The infused cells persisted for over 3 months, achieving complete B cell depletion within 2 weeks of treatment. During the 6-month follow-up, we observed deep remission without cytokine release syndrome or other serious adverse events in all three patients, primarily shown by the significant improvement in the clinical response index scores for the two diseases, respectively, and supported by the observations of reversal of inflammation and fibrosis. Our results demonstrate the high safety and promising immune modulatory effect of the off-the-shelf CAR-T cells in treating severe refractory autoimmune diseases.

Advantages of ultrasound imaging for the early diagnosis of psoriatic arthritis in patients with moderate to severe psoriasis.

Background: Psoriatic arthritis (PsA) is an immune-mediated form of chronic inflammatory arthritis associated with psoriasis (PsO). It constitutes a significant comorbidity of PsO and is distinguished by the presence of widespread musculoskeletal inflammation. Objective: The aim of this study is to precisely detect asymptomatic PsA using ultrasound (US) examinations and to distinguish between various stages of PsO. Methods: All patients with moderate-to-severe PsO, who consented to undergo musculoskeletal US examinations during their hospitalization between September 2020 and January 2022, were enrolled in the study. We compared patients' demographic characteristics, comorbidities, disease duration, relevant laboratory parameters, and musculoskeletal US findings. Results: A total of 547 patients with PsO were included in the study, and 114 of them received a diagnosis of PsA. Furthermore, 16.45 % of patients with moderate to severe PsO displayed subclinical PsA. We observed a significantly higher frequency of abnormal US findings in patients with PsA compared to those without PsA, with a sensitivity of 95.61 % and a specificity of 79.22 %. Additionally, the incidence of enthesitis and synovitis varied significantly between PsA and non-PsA patients, and they were identified as independent variables predicting the presence of PsA. Furthermore, the interphalangeal joint, knee joint, and calcaneal tendon were the most frequently affected areas in PsA, as indicated by the observed US changes. Conclusion: Ultrasound examination proves to be a valuable tool for detecting subclinical PsA, facilitating early screening of the condition. Particular attention should be directed towards changes in the interphalangeal joint, knee joint, and calcaneal tendon when reviewing ultrasound images of asymptomatic patients.

Correction to: Multi-View Feature Transformation Based SVM+ for Computer-Aided Diagnosis of Liver Cancers With Ultrasound Image.

Presents corrections to the paper, Multi-View Feature Transformation Based SVM+ for Computer-Aided Diagnosis of Liver Cancers With Ultrasound Image.

Role of high-frequency ultrasound in differentiating benign and malignant skin lesions: potential and limitations.

PURPOSE: This study examined the diagnostic value of high-frequency ultrasound (HFUS) features in differentiating between benign and malignant skin lesions. METHODS: A total of 1,392 patients with 1,422 skin lesions who underwent HFUS examinations were included in an initial dataset (cohort 1) to identify features indicative of malignancy. Qualitative clinical and HFUS characteristics were recorded for all lesions. To determine which HFUS and clinical features were suggestive of malignancy, univariable and multivariable logistic regression analyses were employed. The diagnostic performance of HFUS features combined with clinical information was evaluated. This assessment was validated using internal data (cohort 2) and multicenter external data (cohort 3). RESULTS: Features significantly associated with malignancy included age above 60 years; lesion location in the head, face, and neck or genital regions; changes in macroscopic appearance; crawling or irregular growth pattern; convex or irregular base; punctate hyperechogenicity; blood flow signals; and feeding arteries. The area under the receiver operating characteristic curve, sensitivity, and specificity of HFUS features combined with clinical information were 0.946, 92.5%, and 86.9% in cohort 1; 0.870, 93.1%, and 80.8% in cohort 2 (610 lesions); and 0.864, 86.2%, and 86.6% in cohort 3 (170 lesions), respectively. However, HFUS is not suitable for evaluating lesions less than 0.1 mm in thickness or lesions exhibiting surface hyperkeratosis. CONCLUSION: In a clinical setting, the integration of HFUS with clinical information exhibited good diagnostic performance in differentiating malignant and benign skin lesions. However, its utility was limited in evaluating extremely thin lesions and those exhibiting hyperkeratosis.

Genetically Designed Living Bacteria with Melanogenesis for Tumor-Specific Pigmentation and Therapeutic Intervention.

Visual observation and therapeutic intervention against tumors hold significant appeal for tumor treatment, particularly in meeting the demands of intraoperative navigation. From a clinical perspective, the naked-eye visualization of tumors provides a direct and convenient approach to identifying tumors and navigating during surgery. Nevertheless, there is an ongoing need to develop effective solutions in this frontier. Genetically engineered microorganisms are promising as living therapeutics for combatting malignant tumors, leveraging precise tumor targeting and versatile programmed functionalities. Here, genetically modified Escherichia coli (E. coli) MG1655 bacterial cells are introduced, called MelaBac cells, designed to express tyrosinase continuously. This bioengineered melanogenesis produces melanin capable of pigmenting both subcutaneous CT26 xenografts and chemically induced colorectal cancer (CRC). Additionally, MelaBac cells demonstrate the initiation of photonic hyperthermia therapy and immunotherapy against tumors, offering promising selective therapeutic interventions with high biocompatibility.

Predicting tall-cell subtype of papillary thyroid carcinomas independently with preoperative multimodal ultrasound.

OBJECTIVES: This study aimed to explore the differences between tall-cell subtype of papillary thyroid carcinoma (TCPTC) and classical papillary thyroid carcinoma (cPTC) using multimodal ultrasound, and identify independent risk factors for TCPTC to compensate the deficiency of preoperative cytological and molecular diagnosis on PTC subtypes. METHODS: Forty-six TCPTC patients and 92 cPTC patients were included. Each patient received grey-scale ultrasound, colour Dopplor flow imaging (CDFI) and shear-wave elastography (SWE) preoperatively. Clinicopathologic information, grey-scale ultrasound features, CDFI features and SWE features of 98 lesions were compared using univariate analysis to find out predictors of TCPTC, based on which, a predictive model was built to differentiate TCPTC from cPTC and validated with 40 patients. RESULTS: Univariate and multivariate analyses identified that extra-thyroidal extension (odds ratio [OR], 15.12; 95% CI, 2.26-115.44), aspect ratio (≥0.91) (OR, 29.34; 95% CI, 1.29-26.23), and maximum diameter ≥14.6 mm (OR, 20.79; 95% CI, 3.87-111.47) were the independent risk factors for TCPTC. Logistic regression equation: P = 1/1+ExpΣ[-5.099 + 3.004 × (if size ≥14.6 mm) + 2.957 × (if aspect ratio ≥ 0.91) + 2.819 × (if extra-thyroidal extension). The prediction model had a good discrimination performance for TCPTC: the area under the receiver-operator-characteristic curve, sensitivity, and specificity were 0.928, 0.848, and 0.954 in cohort 1, and the corresponding values in cohort 2 were 0.943, 0.923, and 0.926, respectively. CONCLUSION: Ultrasound has the potential for differential diagnosis of TCPTC from cPTC. A prediction model based on ultrasound characteristics (extra-thyroidal extension, aspect ratio ≥0.91, and maximum diameter ≥14.6 mm) was useful in predicting TCPTC. ADVANCES IN KNOWLEDGE: Multimodal ultrasound prediction of TCPTC was a supplement to preoperative cytological diagnosis and molecular diagnosis of PTC subtypes.

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.

Assessment of the Diagnostic Performance of Clinical Examinations and High-Frequency Ultrasound in Patients With Pigmented Skin Tumors.

OBJECTIVES: To investigate whether the integration of high-frequency ultrasound (HFUS) to routine clinical examinations could improve diagnostic performance and management decision for pigmented skin tumors. METHODS: Three general practitioners trained previously and a dermatologist independently assessed pigmented skin tumors and rendered management decision based on clinical examinations alone or clinical examinations integrating HFUS. RESULTS: After integrating HFUS, the diagnostic area under the curve (AUC) (0.658-0.693 versus 0.848, all P < .05) and specificity (46.6-58.6% versus 89.7%, all P < .05) for pigmented skin malignancies were improved for general practitioners, meanwhile unnecessary biopsy rate reduced (42.9-53.6% versus 10.7%, P < .001). To the dermatologist, the diagnostic AUC (0.822 versus 0.949, P < .001), sensitivity (81.7% versus 96.7%, P = .012) and specificity (0.828 versus 0.931, P = .031) improved significantly, meanwhile both missed biopsy rate (14.5% versus 4.8%, P = .031) and unnecessary biopsy rate (19.6% versus 7.1%, P = .016) decreased. Additionally, the diagnostic performance of the general practitioner with integrating HFUS could be comparable with the dermatologist based on clinical examinations alone (all P > .05). CONCLUSIONS: As a complementary tool of clinical examinations, HFUS could help physicians differentiate pigmented skin malignancies and manage decision.

Ultrasound-Driven Non-Metallic Fenton-Active Center Construction for Extensive Chemodynamic Therapy.

Chemodynamic therapy (CDT) is an emerging tumor microenvironment-responsive cancer therapeutic strategy based on Fenton/Fenton-like reactions. However, the effectiveness of CDT is subject to the slow kinetic rate and non-homogeneous distribution of H2 O2 . In this study, a conceptual non-metallic "Fenton-active" center construction strategy is proposed to enhance CDT efficiency using Bi0.44 Ba0.06 Na0.5 TiO2.97 (BNBT-6) nanocrystals. The separated charge carriers under a piezoelectric-induced electric field synchronize the oxidation of H2 O and reduction of H2 O2 , which consequently increases hydroxyl radical (·OH) yield even under low H2 O2 levels. Moreover, acceptor doping induces electron-rich oxygen vacancies to facilitate the dissociation of H2 O2 and H2 O and further promote ·OH generation. In vitro and in vivo experiments demonstrate that BNBT-6 induces extensive intracellular oxidative stress and enhances cell-killing efficiency by activating necroptosis in addition to the conventional apoptotic pathway. This study proposes a novel design approach for nanomaterials used in CDT and presents a new treatment strategy for apoptosis-resistant tumors.

A 5G-based telerobotic ultrasound system provides qualified abdominal ultrasound services for patients on a rural island: a prospective and comparative study of 401 patients.

PURPOSE: To explore the feasibility of a 5G-based telerobotic ultrasound (US) system for providing qualified abdominal US services on a rural island. METHODS: This prospective study involved two medical centers (the tele-radiologist site's hospital and the patient site's hospital) separated by 72 km. Patients underwent 5G-based telerobotic US by tele-radiologists and conventional US by on-site radiologists from September 2020 to March 2021. The clinical feasibility and diagnostic performance of the 5G-based telerobotic abdominal US examination were assessed based on safety, duration, image quality, diagnostic findings, and questionnaires. RESULTS: A total of 401 patients (217 women and 184 men; mean age, 54.96 ± 15.43 years) were enrolled. A total of 90.1% of patients indicated no discomfort with the telerobotic US examination. For the examination duration, telerobotic US took longer than conventional US (12.54 ± 3.20 min vs. 7.23 ± 2.10 min, p = 0.001). For image quality scores, the results of the two methods were similar (4.54 ± 0.63 vs. 4.57 ± 0.61, p = 0.112). No significant differences were found between the two methods in measurements for the aorta, portal vein, gallbladder, kidney (longitudinal diameter), prostate, and uterus; however, telerobotic US underestimated the transverse diameter of the kidney (p < 0.05). A total of 504 positive results, including 31 different diseases, were detected. Among them, 455 cases were identified by the two methods; 17 cases were identified by telerobotic US only; and 32 cases were identified by conventional US only. There was good consistency in the diagnosis of 29 types of disease between the two methods (κ = 0.773-1.000). Furthermore, more than 90% of patients accepted the telerobotic US examination and agreed to pay additional fees in future. CONCLUSION: The 5G-based telerobotic US system can expand access to abdominal US services for patients in rural areas, thereby reducing health care disparities.

Tele-Mentored Handheld Ultrasound System for General Practitioners: A Prospective, Descriptive Study in Remote and Rural Communities.

BACKGROUND: Rural general practitioners (GPs) have insufficient diagnostic information to deal with complex clinical scenarios due to the inequality in medical imaging resources in rural and remote communities. The objective of this study is to explore the value of a tele-mentored handheld ultrasound (tele-HHUS) system, allowing GPs to provide ultrasound (US) services in rural and remote communities. METHODS: Overall, 708 patients underwent tele-HHUS examination between March and October 2021 and March and April 2022 across thirteen primary hospitals and two tertiary-care general hospitals. All US examinations were guided and supervised remotely in real time by US experts more than 300 km away using the tele-HHUS system. The following details were recorded: location of tele-HHUS scanning, primary complaints, clinical diagnosis, and US findings. The recommendations (referral or follow-up) based on clinical experience alone were compared with those based on clinical experience with tele-HHUS information. RESULTS: Tele-HHUS examinations were performed both in hospital settings (90.6%, 642/708) and out of hospital settings (9.4%, 66/708). Leaving aside routine physical examinations, flank pain (14.2%, 91/642) was the most common complaint in inpatients, while chest distress (12.1%, 8/66) and flank discomfort (12.1%, 8/66) were the most common complaints in out-of-hospital settings. Additionally, the referral rate increased from 5.9% to 8.3% (kappa = 0.202; p = 0.000). CONCLUSIONS: The tele-HHUS system can help rural GPs perform HHUS successfully in remote and rural communities. This novel mobile telemedicine model is valuable in resource-limited areas.

Diagnostic value of high-frequency ultrasound (HFUS) in evaluation of subcutaneous lesions.

BACKGROUND: It is unknown whether high-frequency ultrasound (HFUS) can evaluate invisible subcutaneous lesions. We aimed to investigate the diagnostic value of HFUS in invisible subcutaneous lesions. METHOD: Patients with invisible subcutaneous lesions were prospectively recruited from two centres. Before undergoing biopsy or surgery, each lesion was independently evaluated by two clinicians. One provides a clinical diagnosis by only clinical examination and the other provides an integrated diagnosis by combining clinical examination and HFUS information. Diagnoses were classified as correct, wrong, and indeterminate. A total of 391 lesions from 355 patients were enrolled, including 225 epidermoid cysts, 77 lipomas, 25 pilomatrixomas, 21 haemangiomas, 19 dermatofibromas, 11 dermatofibrosarcoma protuberans (DFSP), 7 neurofibromas, and 6 leiomyomas. Using pathological results as the gold standard, diagnostic performance was compared. RESULTS: The number of correct diagnoses increased from 185 (47.3%) by clinical examination alone to 316 (80.8%) after the addition of HFUS (P < 0.05). Meanwhile, the indeterminate diagnosis rate decreased from 143 (36.6%) to 10 (2.6%). Using HFUS, the accuracy improved significantly for epidermoid cysts (59.6% vs. 86.7%), lipomas (50.6% vs. 94.8%), pilomatrixomas (0% vs. 48.0%), haemangiomas (23.8% vs. 57.1%), and DFSPs (0% vs. 81.8%) (all p < 0.05). However, HFUS did not significantly improve the diagnostic accuracy of dermatofibromas (15.8% vs. 21.1%, p > 0.999), neurofibromas (42.9% vs. 71.4%, p = 0.625), or leiomyomas (16.7% vs. 100%, p = 0.063). CONCLUSION: Combining HFUS and clinical examination can generally improve the diagnostic accuracy and decrease the indeterminacy of invisible subcutaneous lesions, especially epidermoid cysts, lipomas, pilomatrixomas, haemangiomas, and DFSPs. However, for some rare lesions, HFUS cannot provide useful information.

Traditional Chinese Medicine Shi-Bi-Man regulates lactic acid metabolism and drives hair follicle stem cell activation to promote hair regeneration.

BACKGROUND: As a supplement for promoting hair health, Shi-Bi-Man (SBM) is a prescription comprising various traditional Chinese medicines. Though SBM has been reported to promote hair regeneration, its molecular mechanism remains unclear. Cynomolgus monkeys (Macaca fascicularis) are non-human primates with a gene expression profile similar to that of humans. The purpose of this research is to evaluate the effect of SBM on promoting hair regeneration in cynomolgus monkeys and to reveal the underlying mechanism. METHODS: The effect of SBM on hair regeneration was observed by skin administration on 6 cynomolgus monkeys with artificial back shaving. The molecular mechanism of SBM was studied using single-cell RNA sequencing (scRNA-seq) in combination with quantitative polymerase chain reaction (qPCR) detection for gene transcription level, and immunofluorescence staining verification for protein level. RESULTS: SBM significantly induced hair regeneration in cynomolgus monkeys, increased hair follicle number and facilitated hair follicle development. ScRNA-seq revealed an increase in the number of hair follicle stem cells (HFSCs) with a higher activation state, as evidenced by the higher expression of activation marker LDHA related to metabolism and the proliferation marker MKI67. Immunofluorescence analysis at the protein level and qPCR at the mRNA level confirmed the sequencing data. Cellchat analysis revealed an enrichment of ligand-receptor pairs involved in intercellular communication in Laminin-related pathways. CONCLUSION: SBM significantly promotes hair regeneration in cynomolgus monkeys. Mechanically, SBM can up-regulate LDHA-mediated lactic acid metabolism and drive HFSC activation, which in turn promotes the proliferation and differentiation of HFSCs.

B-mode ultrasound based CAD for liver cancers via multi-view privileged information learning.

B-mode ultrasound-based computer-aided diagnosis model can help sonologists improve the diagnostic performance for liver cancers, but it generally suffers from the bottleneck due to the limited structure and internal echogenicity information in B-mode ultrasound images. Contrast-enhanced ultrasound images provide additional diagnostic information on dynamic blood perfusion of liver lesions for B-mode ultrasound images with improved diagnostic accuracy. Since transfer learning has indicated its effectiveness in promoting the performance of target computer-aided diagnosis model by transferring knowledge from related imaging modalities, a multi-view privileged information learning framework is proposed to improve the diagnostic accuracy of the single-modal B-mode ultrasound-based diagnosis for liver cancers. This framework can make full use of the shared label information between the paired B-mode ultrasound images and contrast-enhanced ultrasound images to guide knowledge transfer It consists of a novel supervised dual-view deep Boltzmann machine and a new deep multi-view SVM algorithm. The former is developed to implement knowledge transfer from the multi-phase contrast-enhanced ultrasound images to the B-mode ultrasound-based diagnosis model via a feature-level learning using privileged information paradigm, which is totally different from the existing learning using privileged information paradigm that performs knowledge transfer in the classifier. The latter further fuses and enhances feature representation learned from three pre-trained supervised dual-view deep Boltzmann machine networks for the classification task. An experiment is conducted on a bimodal ultrasound liver cancer dataset. The experimental results show that the proposed framework outperforms all the compared algorithms with the best classification accuracy of 88.91 ± 1.52%, sensitivity of 88.31 ± 2.02%, and specificity of 89.50 ± 3.12%. It suggests the effectiveness of our proposed MPIL framework for the BUS-based CAD of liver cancers.

Multi-View Feature Transformation Based SVM+ for Computer-Aided Diagnosis of Liver Cancers With Ultrasound Images.

It is feasible to improve the performance of B-mode ultrasound (BUS) based computer-aided diagnosis (CAD) for liver cancers by transferring knowledge from contrast-enhanced ultrasound (CEUS) images. In this work, we propose a novel feature transformation based support vector machine plus (SVM+) algorithm for this transfer learning task by introducing feature transformation into the SVM+ framework (named FSVM+). Specifically, the transformation matrix in FSVM+ is learned to minimize the radius of the enclosing ball of all samples, while the SVM+ is used to maximize the margin between two classes. Moreover, to capture more transferable information from multiple CEUS phase images, a multi-view FSVM+ (MFSVM+) is further developed, which transfers knowledge from three CEUS images from three phases, i.e., arterial phase, portal venous phase, and delayed phase, to the BUS-based CAD model. MFSVM+ innovatively assigns appropriate weights for each CEUS image by calculating the maximum mean discrepancy between a pair of BUS and CEUS images, which can capture the relationship between source and target domains. The experimental results on a bi-modal ultrasound liver cancer dataset demonstrate that MFSVM+ achieves the best classification accuracy of 88.24±1.28%, sensitivity of 88.32±2.88%, specificity of 88.17±2.91%, suggesting its effectiveness in promoting the diagnostic accuracy of BUS-based CAD.

The Value of Ultrasound for Differentiating Trichilemmal Cysts From Epidermoid Cysts.

OBJECTIVES: This study was aimed to evaluate the diagnostic performance of ultrasound (US) in differentiating trichilemmal cysts (TCs) from epidermoid cysts (ECs). METHODS: Based on clinical and ultrasound features, a prediction model was established and validated. 164 cysts in the pilot cohort and another 69 in the validation cohort diagnosed with TCs or ECs histopathologically were evaluated. The same radiologist performed all ultrasound examinations. RESULTS: For clinic features, TCs tended to occur in females compared with ECs (66.7 vs 28.5%; P < .001). In addition, TCs were prone to occur in the hairy area compared with ECs (77.8 vs 13.1%; P < .001). For ultrasound features, the internal hyperechogenicity and cystic change were more likely to appear in TCs in comparison with ECs (92.6 vs 25.5%; P < .001; 70.4 vs 23.4%; P < .001, respectively). Upon the features mentioned above, a prediction model was established with the areas under the receiver operating characteristic curves of 0.936 and 0.864 in the pilot and validation cohorts, respectively. CONCLUSIONS: US is promising for differentiating TCs from ECs and is valuable for their clinical management.