scholarly journals Improving the diagnostic performance of ultrasound in classifying breast lesions: the potential value of S-detect for residents-in-training

2019 ◽  
Author(s):  
Chenyang Zhao ◽  
Mengsu Xiao ◽  
Yuxin Jiang ◽  
He Liu ◽  
Ming Wang ◽  
...  
Keyword(s):  
Diagnostic Performance ◽  
Color Doppler ◽  
Intraclass Correlation ◽  
Area Under The Curve ◽  
Computer Assisted ◽  
Breast Lesions ◽  
Training Methods ◽  
Potential Value ◽  
Experienced Radiologist ◽  
Assisted Diagnosis

Abstract Background To explore the potential value of S-Detect™, a high-end computer-assisted diagnosis (CAD) software system for residents-in-training. Methods Routine breast ultrasound (US) examinations were conducted and assessed by an experienced radiologist. Archived images of the lesions (including grayscale, color Doppler flow and elastography images) were retrospectively assessed by each of five in-training residents who were blinded to the histopathological findings and any other US diagnosis. The diagnostic performances of S-Detect™ and the five residents were measured and compared. Afterwards, category 4a lesions assessed by the residents were downgraded when classified as possibly benign by S-Detect™. The diagnostic performance of the integrated results was compared with the original results of the residents. Results A total of 195 focal breast lesions were consecutively enrolled, including 82 malignant lesions and 113 benign lesions. S-Detect™ presented higher specificity and area under the curve (AUC)than the residents. After combination with S-Detect™ in category 4a lesions, the specificity and AUC of the five residents were significantly improved. The intraclass correlation coefficient (ICC) of the five residents also increased after integration. Conclusions With the help of the CAD software, the specificity, overall diagnostic performances and interobserver agreements of the residents greatly improved. S-Detect™ can be utilized as an assistant tool for residents-in-training in classifying breast lesions.

scholarly journals Reducing the number of unnecessary biopsies of US-BI-RADS 4a lesions through a deep learning method for residents-in-training: a cross-sectional study

BMJ Open ◽  
2020 ◽  
Vol 10 (6) ◽  
pp. e035757
Author(s):  
Chenyang Zhao ◽  
Mengsu Xiao ◽  
He Liu ◽  
Ming Wang ◽  
Hongyan Wang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Breast Imaging ◽  
Diagnostic Performance ◽  
Intraclass Correlation ◽  
Cross Sectional Study ◽  
Computer Assisted ◽  
Sectional Study ◽  
Benign Lesions ◽  
Cross Sectional ◽  
Experienced Radiologist

ObjectiveThe aim of the study is to explore the potential value of S-Detect for residents-in-training, a computer-assisted diagnosis system based on deep learning (DL) algorithm.MethodsThe study was designed as a cross-sectional study. Routine breast ultrasound examinations were conducted by an experienced radiologist. The ultrasonic images of the lesions were retrospectively assessed by five residents-in-training according to the Breast Imaging Report and Data System (BI-RADS) lexicon, and a dichotomic classification of the lesions was provided by S-Detect. The diagnostic performances of S-Detect and the five residents were measured and compared using the pathological results as the gold standard. The category 4a lesions assessed by the residents were downgraded to possibly benign as classified by S-Detect. The diagnostic performance of the integrated results was compared with the original results of the residents.ParticipantsA total of 195 focal breast lesions were consecutively enrolled, including 82 malignant lesions and 113 benign lesions.ResultsS-Detect presented higher specificity (77.88%) and area under the curve (AUC) (0.82) than the residents (specificity: 19.47%–48.67%, AUC: 0.62–0.74). A total of 24, 31, 38, 32 and 42 identified as BI-RADS 4a lesions by residents 1, 2, 3, 4 and 5 were downgraded to possibly benign lesions by S-Detect, respectively. Among these downgraded lesions, 24, 28, 35, 30 and 40 lesions were proven to be pathologically benign, respectively. After combining the residents' results with the results of the software in category 4a lesions, the specificity and AUC of the five residents significantly improved (specificity: 46.02%–76.11%, AUC: 0.71–0.85, p<0.001). The intraclass correlation coefficient of the five residents also increased after integration (from 0.480 to 0.643).ConclusionsWith the help of the DL software, the specificity, overall diagnostic performance and interobserver agreement of the residents greatly improved. The software can be used as adjunctive tool for residents-in-training, downgrading 4a lesions to possibly benign and reducing unnecessary biopsies.

scholarly journals Differing Benefits of Artificial Intelligence-based Computer-aided Diagnosis (AI-CAD) for Breast US According to Workflow and Experience Level

2021 ◽  
Author(s):  
Si Eun Lee ◽  
Kyunghwa Han ◽  
Ji Hyun Youk ◽  
Jee Eun Lee ◽  
Ji-Young Hwang ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Diagnostic Performance ◽  
Independent Reading ◽  
Computer Assisted ◽  
Breast Lesions ◽  
Experience Level ◽  
Experience Levels ◽  
Conversion Rates ◽  
Assisted Diagnosis ◽  
Aided Diagnosis

Abstract Background: To evaluate how artificial intelligence-based computer-assisted diagnosis (AI-CAD) for breast ultrasound (US) influences diagnostic performance and agreements between radiologists with varying experience levels in different workflows.Methods: From Apr 2017 to Jun 2018, images of 492 breast lesions (200 malignant and 292 benign masses) in 472 women were included. Six radiologists (3 inexperienced with < 1 year of experience, 3 experienced with 10-15 years of experience) individually reviewed US images with and without the aid of AI-CAD, first in sequential and then in independent reading. Diagnostic performances and interobserver agreements were calculated and compared between radiologists and AI-CAD. Results: After implementing AI-CAD, specificity, PPV and accuracy significantly improved, regardless of experience and workflow (all P<0.001, respectively). Overall area under the receiving operator characteristics curve (AUC) significantly increased in independent reading, but only for inexperienced radiologists. Agreements for BI-RADS descriptors generally increased when AI-CAD was used (κ=0.29-0.63 to 0.35-0.73). Inexperienced radiologists tended to concede to AI-CAD results more easily than experienced radiologists, especially in independent reading (P<0.001). Conversion rates for final assessment changes from BI-RADS 2 or 3 to BI-RADS higher than 4a or vice versa were also significantly higher in independent reading than sequential reading (overall: 15.8% and 6.2%, respectively, P<0.001) for both inexperienced and experienced radiologists. Conclusions: Using AI-CAD to interpret breast US improves the specificity, PPV and accuracy of radiologists regardless of experience level. AI-CAD may work better in independent reading to improve diagnostic performance and agreements between radiologists, especially for inexperienced radiologists.Trial registration: retrospectively registered

A qualitative and quantitative assessment of simultaneous strain, shear wave, and point shear wave elastography to distinguish malignant and benign breast lesions

2020 ◽  
pp. 028418512096142
Author(s):  
Yasemin Altıntas ◽  
Mehmet Bayrak ◽  
Ömer Alabaz ◽  
Medih Celiktas
Keyword(s):  
Shear Wave ◽  
Diagnostic Performance ◽  
Area Under The Curve ◽  
Shear Wave Elastography ◽  
Strain Ratio ◽  
Breast Lesions ◽  
Breast Masses ◽  
Malignant Breast ◽  
The Mean ◽  
Us Elastography

Background Ultrasound (US) elastography has become a routine instrument in ultrasonographic diagnosis that measures the consistency and stiffness of tissues. Purpose To distinguish benign and malignant breast masses using a single US system by comparing the diagnostic parameters of three kinds of breast elastography simultaneously added to B-mode ultrasonography. Material and Methods A total of 163 breast lesions in 159 consecutive women who underwent US-guided core needle biopsy were included in this prospective study. Before the biopsy, the lesions were examined with B-mode ultrasonography and strain (SE), shear wave (SWE), and point shear wave (STQ) elastography. The strain ratio was computed and the Tsukuba score determined. The mean elasticity values using SWE and STQ were computed and converted to Young’s modulus E (kPa). Results All SE, SWE, and STQ parameters showed similar diagnostic performance. The SE score, SE ratio, SWEmean, SWEmax, STQmean, and STQmax yielded higher specificity than B-mode US alone to differentiate benign and malignant masses. The sensitivity of B-mode US, SWE, and STQ was slightly higher than that of the SE score and SE ratio. The SE score, SE ratio, SWEmean, SWEmax, STQmean, and STQmax had significantly higher positive predictive value and diagnostic accuracy than B-mode US alone. The area under the curve for each of these elastography methods in differentiating benign and malignant breast lesions was 0.93, 0.93, 0.98, 0.97, 0.98, and 0.96, respectively; P<0.001 for all measurements. Conclusion SE (ratio and score), SWE, and STQ had higher diagnostic performance individually than B-mode US alone in distinguishing between malignant and benign breast masses.

US-Elastography for Breast Lesion Characterization: Prospective Comparison of US BIRADS, Strain Elastography and Shear wave Elastography

2020 ◽  
Author(s):  
Vito Cantisani ◽  
Emanuele David ◽  
Richard G. Barr ◽  
Maija Radzina ◽  
Valeria de Soccio ◽  
...  
Keyword(s):  
Shear Wave ◽  
Diagnostic Performance ◽  
Color Doppler ◽  
Shear Wave Elastography ◽  
Strain Ratio ◽  
Breast Lesions ◽  
Strain Elastography ◽  
Prospective Comparison ◽  
Malignant Breast ◽  
Sensitivity Specificity

Abstract Purpose To evaluate the diagnostic performance of strain elastography (SE) and 2 D shear wave elastography (SWE) and SE/SWE combination in comparison with conventional multiparametric ultrasound (US) with respect to improving BI-RADS classification results and differentiating benign and malignant breast lesions using a qualitative and quantitative assessment. Materials and Methods In this prospective study, 130 histologically proven breast masses were evaluated with baseline US, color Doppler ultrasound (CDUS), SE and SWE (Toshiba Aplio 500 with a 7–15 MHz wide-band linear transducer). Each lesion was classified according to the BIRADS lexicon by evaluating the size, the B-mode and color Doppler features, the SE qualitative (point color scale) and SE semi-quantitative (strain ratio) methods, and quantitative SWE. Histological results were compared with BIRADS, strain ratio (SR) and shear wave elastography (SWE) all performed by one investigator blinded to the clinical examination and mammographic results at the time of the US examination. The area under the ROC curve (AUC) was calculated to evaluate the diagnostic performance of B-mode US, SE, SWE, and their combination. Results Histological examination revealed 47 benign and 83 malignant breast lesions. The accuracy of SR was statistically significantly higher than SWE (sensitivity, specificity and AUC were 89.2 %, 76.6 % and 0.83 for SR and 72.3 %, 66.0 % and 0.69 for SWE, respectively, p = 0.003) but not higher than B-mode US (B-mode US sensitivity, specificity and AUC were 85.5 %, 78.8 %, 0.821, respectively, p = 1.000). Conclusion Our experience suggests that conventional US in combination with both SE and SWE is a valid tool that can be useful in the clinical setting, can improve BIRADS category assessment and may help in the differentiation of benign from malignant breast lesions, with SE having higher accuracy than SWE.

scholarly journals A Comparative Assessment of MR BI-RADS 4 Breast Lesions With Kaiser Score and Apparent Diffusion Coefficient Value

2021 ◽  
Vol 11 ◽  
Author(s):  
Lingsong Meng ◽  
Xin Zhao ◽  
Lin Lu ◽  
Qingna Xing ◽  
Kaiyu Wang ◽  
...  
Keyword(s):  
Diffusion Coefficient ◽  
Apparent Diffusion Coefficient ◽  
Breast Imaging ◽  
Diagnostic Performance ◽  
Area Under The Curve ◽  
Lower Sensitivity ◽  
Breast Lesions ◽  
Roc Curve Analysis ◽  
Apparent Diffusion Coefficient Value ◽  
Apparent Diffusion

ObjectivesTo investigate the diagnostic performance of the Kaiser score and apparent diffusion coefficient (ADC) to differentiate Breast Imaging Reporting and Data System (BI-RADS) Category 4 lesions at dynamic contrast-enhanced (DCE) MRI.MethodsThis was a single-institution retrospective study of patients who underwent breast MRI from March 2020 to June 2021. All image data were acquired with a 3-T MRI system. Kaiser score of each lesion was assigned by an experienced breast radiologist. Kaiser score+ was determined by combining ADC and Kaiser score. Receiver operating characteristic (ROC) curve analysis was performed to evaluate the diagnostic performance of Kaiser score+, Kaiser score, and ADC. The area under the curve (AUC) values were calculated and compared by using the Delong test. The differences in sensitivity and specificity between different indicators were determined by the McNemar test.ResultsThe study involved 243 women (mean age, 43.1 years; age range, 18–67 years) with 268 MR BI-RADS 4 lesions. Overall diagnostic performance for Kaiser score (AUC, 0.902) was significantly higher than for ADC (AUC, 0.81; p = 0.004). There were no significant differences in AUCs between Kaiser score and Kaiser score+ (p = 0.134). The Kaiser score was superior to ADC in avoiding unnecessary biopsies (p &lt; 0.001). Compared with the Kaiser score alone, the specificity of Kaiser score+ increased by 7.82%, however, at the price of a lower sensitivity.ConclusionFor MR BI-RADS category 4 breast lesions, the Kaiser score was superior to ADC mapping regarding the potential to avoid unnecessary biopsies. However, the combination of both indicators did not significantly contribute to breast cancer diagnosis of this subgroup.

Clinical Application of Computer-Aided Diagnosis According to S-Detect in Category 4 Breast Lesions: Prospective Single-Center Study (Preprint)

2020 ◽  
Author(s):  
Pengfei Sun ◽  
Chen Chen ◽  
Weiqi Wang ◽  
Lei Liang ◽  
Dan Luo ◽  
...  
Keyword(s):  
Clinical Management ◽  
Diagnostic Performance ◽  
Breast Biopsy ◽  
Computer Aided Diagnosis ◽  
Breast Lesions ◽  
Breast Masses ◽  
Computer Aided ◽  
Conventional Ultrasound ◽  
Us Findings ◽  
Aided Diagnosis

BACKGROUND Computer-aided diagnosis (CAD) is a useful tool that can provide a reference for the differential diagnosis of benign and malignant breast lesion. Previous studies have demonstrated that CAD can improve the diagnostic performance. However, conventional ultrasound (US) combined with CAD were used to adjust the classification of category 4 lesions has been few assessed. OBJECTIVE The objective of our study was to evaluate the diagnosis performance of conventional ultrasound combined with a CAD system S-Detect in the category of BI-RADS 4 breast lesions. METHODS Between December 2018 and May 2020, we enrolled patients in this study who received conventional ultrasound and S-Detect before US-guided biopsy or surgical excision. The diagnostic performance was compared between US findings only and the combined use of US findings with S-Detect, which were correlated with pathology results. RESULTS A total of 98 patients (mean age 51.06 ±16.25 years, range 22-81) with 110 breast masses (mean size1.97±1.38cm, range0.6-8.5) were included in this study. Of the 110 breast masses, 64/110 (58.18%) were benign, 46/110 (41.82%) were malignant. Compared with conventional ultrasound, a significant increase in specificity (0% to 53.12%, P<.001), accuracy (41.81% to70.19%, P<.001) were noted, with no statistically significant decrease on sensitivity(100% to 95.65% ,P=.48). According to S-Detect-guided US BI-RADS re-classification, 30 out of 110 (27.27%) breast lesions underwent a correct change in clinical management, 74of 110 (67.27%) breast lesions underwent no change and 6 of 110 (5.45%) breast lesions underwent an incorrect change in clinical management. The biopsy rate decreased from 100% to 67.27 % (P<.001).Benign masses among subcategory 4a had higher rates of possibly benign assessment on S-Detect for the US only (60% to 0%, P<.001). CONCLUSIONS S-Detect can be used as an additional diagnostic tool to improve the specificity and accuracy in clinical practice. S-Detect have the potential to be used in downgrading benign masses misclassified as BI-RADS category 4 on US by radiologist, and may reduce unnecessary breast biopsy. CLINICALTRIAL none

Influence of diabetes on diagnostic performance of computed tomography angiography of the calf arteries in acute limb ischemia

2021 ◽  
pp. 028418512110069
Author(s):  
Talha Butt ◽  
Leena Lehti ◽  
Jan Apelqvist ◽  
Anders Gottsäter ◽  
Stefan Acosta
Keyword(s):  
Computed Tomography ◽  
Computed Tomography Angiography ◽  
Diagnostic Performance ◽  
Intraclass Correlation ◽  
Arterial Occlusion ◽  
Limb Ischemia ◽  
Arterial Disease ◽  
Diabetic Patients ◽  
Acute Limb Ischemia ◽  
Below The Knee

Background Patients with diabetes mellitus (DM) have a more extensive distal arterial occlusive disease compared to non-diabetic patients. Diagnostic imaging is a necessity to identify the location and extent of the arterial occlusion in acute limb ischemia (ALI). Computed tomography angiography (CTA) is the most commonly used modality and the diagnostic performance with CTA of calf arteries may be questioned. Purpose To evaluate diagnostic performance of CTA of calf arteries in ALI and to compare patients with and without DM. Material and Methods All thrombolytic treatments performed during 2001–2008 in patients with ALI were included. Initial digital subtraction angiography (DSA) and CTA of all patients were classified according to the Inter-Society Consensus for the Management of Peripheral Arterial Disease (TASC II) below-the-knee arteries and compared to CTA. Two raters assessed the CTA images independently. Inter-rater reliability was expressed as intraclass correlation (ICC) with 95% confidence intervals (CI). Results Patients with (n = 23) and without (n = 85) DM had lower ( P = 0.006) glomerular filtration rate. ICC between CTA and DSA was 0.33 (95% CI –0.22 to 0.56) and 0.71 (95% CI 0.38–0.68) in patients with and without DM, respectively. Sensitivity with CTA for TASC D lesions in patients with and without DM was 0.14 (95% CI –0.12 to 0.40) and 0.64 (95% CI 0.48–0.80), respectively. Conclusion The sensitivity of CTA for assessment of infra-popliteal TASC D lesions in patients with ALI was not acceptable in patients with DM in contrast to those without DM. Another imaging option at present times should be considered for patients with DM.

scholarly journals Aggregation-and-Attention Network for brain tumor segmentation

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Chih-Wei Lin ◽  
Yu Hong ◽  
Jinfu Liu
Keyword(s):  
Brain Tumor ◽  
Semantic Information ◽  
Spatial Relationship ◽  
Tumor Segmentation ◽  
Computer Assisted ◽  
Brain Tumor Segmentation ◽  
Attention Network ◽  
Multi Scale ◽  
Assisted Diagnosis ◽  
The Brain

Abstract Background Glioma is a malignant brain tumor; its location is complex and is difficult to remove surgically. To diagnosis the brain tumor, doctors can precisely diagnose and localize the disease using medical images. However, the computer-assisted diagnosis for the brain tumor diagnosis is still the problem because the rough segmentation of the brain tumor makes the internal grade of the tumor incorrect. Methods In this paper, we proposed an Aggregation-and-Attention Network for brain tumor segmentation. The proposed network takes the U-Net as the backbone, aggregates multi-scale semantic information, and focuses on crucial information to perform brain tumor segmentation. To this end, we proposed an enhanced down-sampling module and Up-Sampling Layer to compensate for the information loss. The multi-scale connection module is to construct the multi-receptive semantic fusion between encoder and decoder. Furthermore, we designed a dual-attention fusion module that can extract and enhance the spatial relationship of magnetic resonance imaging and applied the strategy of deep supervision in different parts of the proposed network. Results Experimental results show that the performance of the proposed framework is the best on the BraTS2020 dataset, compared with the-state-of-art networks. The performance of the proposed framework surpasses all the comparison networks, and its average accuracies of the four indexes are 0.860, 0.885, 0.932, and 1.2325, respectively. Conclusions The framework and modules of the proposed framework are scientific and practical, which can extract and aggregate useful semantic information and enhance the ability of glioma segmentation.

Sign in / Sign up

Export Citation Format

Share Document