scholarly journals Application of ultrasound artificial intelligence in the differential diagnosis between benign and malignant breast lesions of BI-RADS 4A

BMC Cancer ◽  
2020 ◽  
Vol 20 (1) ◽  
Author(s):  
Sihua Niu ◽  
Jianhua Huang ◽  
Jia Li ◽  
Xueling Liu ◽  
Dan Wang ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Differential Diagnosis ◽  
Breast Imaging ◽  
Texture Features ◽  
Matrix Analysis ◽  
Width Ratio ◽  
Malignant Group ◽  
Malignant Lesions ◽  
Occurrence Matrix ◽  
Benign Group

Abstract Background The classification of Breast Imaging Reporting and Data System 4A (BI-RADS 4A) lesions is mostly based on the personal experience of doctors and lacks specific and clear classification standards. The development of artificial intelligence (AI) provides a new method for BI-RADS categorisation. We analysed the ultrasonic morphological and texture characteristics of BI-RADS 4A benign and malignant lesions using AI, and these ultrasonic characteristics of BI-RADS 4A benign and malignant lesions were compared to examine the value of AI in the differential diagnosis of BI-RADS 4A benign and malignant lesions. Methods A total of 206 lesions of BI-RADS 4A examined using ultrasonography were analysed retrospectively, including 174 benign lesions and 32 malignant lesions. All of the lesions were contoured manually, and the ultrasonic morphological and texture features of the lesions, such as circularity, height-to-width ratio, margin spicules, margin coarseness, margin indistinctness, margin lobulation, energy, entropy, grey mean, internal calcification and angle between the long axis of the lesion and skin, were calculated using grey level gradient co-occurrence matrix analysis. Differences between benign and malignant lesions of BI-RADS 4A were analysed. Results Significant differences in margin lobulation, entropy, internal calcification and ALS were noted between the benign group and malignant group (P = 0.013, 0.045, 0.045, and 0.002, respectively). The malignant group had more margin lobulations and lower entropy compared with the benign group, and the benign group had more internal calcifications and a greater angle between the long axis of the lesion and skin compared with the malignant group. No significant differences in circularity, height-to-width ratio, margin spicules, margin coarseness, margin indistinctness, energy, and grey mean were noted between benign and malignant lesions. Conclusions Compared with the naked eye, AI can reveal more subtle differences between benign and malignant BI-RADS 4A lesions. These results remind us carefully observation of the margin and the internal echo is of great significance. With the help of morphological and texture information provided by AI, doctors can make a more accurate judgment on such atypical benign and malignant lesions.

scholarly journals Application of ultrasound artificial intelligence in the differential diagnosis between benign and malignant breast lesions of BI-RADS 4A

2020 ◽  
Author(s):  
Sihua Niu ◽  
Jianhua Huang ◽  
Jia Li ◽  
Xueling Liu ◽  
Dan Wang ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Differential Diagnosis ◽  
Breast Imaging ◽  
Texture Features ◽  
Matrix Analysis ◽  
Width Ratio ◽  
Malignant Group ◽  
Malignant Lesions ◽  
Occurrence Matrix ◽  
Benign Group

Abstract Background: The classification of Breast Imaging Reporting and Data System 4A (BI-RADS 4A) lesions is mostly based on the personal experience of doctors and lacks specific and clear classification standards. The development of artificial intelligence (AI) provides a new method for BI-RADS categorisation. We analysed the ultrasonic morphological and texture characteristics of BI-RADS 4A benign and malignant lesions using AI, and these ultrasonic characteristics of BI-RADS 4A benign and malignant lesions were compared to examine the value of AI in the differential diagnosis of BI-RADS 4A benign and malignant lesions.Methods: A total of 206 lesions of BI-RADS 4A examined using ultrasonography were analysed retrospectively, including 174 benign lesions and 32 malignant lesions. All of the lesions were contoured manually, and the ultrasonic morphological and texture features of the lesions, such as circularity, height-to-width ratio, margin spicules, margin coarseness, margin indistinctness, margin lobulation, energy, entropy, grey mean, internal calcification and angle between the long axis of the lesion and skin, were calculated using grey level gradient co-occurrence matrix analysis. Differences between benign and malignant lesions of BI-RADS 4A were analysed.Results: Significant differences in margin lobulation, entropy, internal calcification and ALS were noted between the benign group and malignant group (P=0.013, 0.045, 0.045, and 0.002, respectively). The malignant group had more margin lobulations and lower entropy compared with the benign group, and the benign group had more internal calcifications and a greater angle between the long axis of the lesion and skin compared with the malignant group. No significant differences in circularity, height-to-width ratio, margin spicules, margin coarseness, margin indistinctness, energy, and grey mean were noted between benign and malignant lesions.Conclusions: Compared with the naked eye, AI can reveal more subtle differences between benign and malignant BI-RADS 4A lesions. These results remind us carefully observation of the margin and the internal echo is of great significance. With the help of morphological and texture information provided by AI, doctors can make a more accurate judgment on such atypical benign and malignant lesions.

scholarly journals Application of ultrasound artificial intelligence in the differential diagnosis between benign and malignant breast lesions of BI-RADS 4A

2020 ◽  
Author(s):  
Sihua Niu ◽  
Jianhua Huang ◽  
Jia Li ◽  
Xueling Liu ◽  
Dan Wang ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Differential Diagnosis ◽  
Breast Imaging ◽  
Texture Features ◽  
Matrix Analysis ◽  
Width Ratio ◽  
Malignant Group ◽  
Malignant Lesions ◽  
Occurrence Matrix ◽  
Benign Group

Abstract Background: The classification of Breast Imaging Reporting and Data System 4A (BI-RADS 4A) lesions is mostly based on the personal experience of doctors and lacks specific and clear classification standards. The development of artificial intelligence (AI) provides a new method for BI-RADS categorisation. We analysed the ultrasonic morphological and texture characteristics of BI-RADS 4A benign and malignant lesions using AI, and these ultrasonic characteristics of BI-RADS 4A benign and malignant lesions were compared to examine the value of AI in the differential diagnosis of BI-RADS 4A benign and malignant lesions.Methods: A total of 206 lesions of BI-RADS 4A examined using ultrasonography were analysed retrospectively, including 174 benign lesions and 32 malignant lesions. All of the lesions were contoured manually, and the ultrasonic morphological and texture features of the lesions, such as circularity, height-to-width ratio, margin spicules, margin coarseness, margin indistinctness, margin lobulation, energy, entropy, grey mean, internal calcification and angle between the long axis of the lesion and skin, were calculated using grey level gradient co-occurrence matrix analysis. Differences between benign and malignant lesions of BI-RADS 4A were analysed.Results: Significant differences in margin lobulation, entropy, internal calcification and ALS were noted between the benign group and malignant group (P=0.013, 0.045, 0.045, and 0.002, respectively). The malignant group had more margin lobulations and lower entropy compared with the benign group, and the benign group had more internal calcifications and a greater angle between the long axis of the lesion and skin compared with the malignant group. No significant differences in circularity, height-to-width ratio, margin spicules, margin coarseness, margin indistinctness, energy, and grey mean were noted between benign and malignant lesions.Conclusions: Compared with the naked eye, AI can reveal more subtle differences between benign and malignant BI-RADS 4A lesions. These results remind us carefully observation of the margin and the internal echo is of great significance. With the help of morphological and texture information provided by AI, doctors can make a more accurate judgment on such atypical benign and malignant lesions.

scholarly journals Application of Ultrasound Artificial Intelligence in the Differential Diagnosis Between Benign and Malignant Breast Lesions of BI-RADS 4A

2020 ◽  
Author(s):  
SIHUA Niu ◽  
Jianhua Huang ◽  
Jia Li ◽  
Xueling Liu ◽  
Dan Wang ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Differential Diagnosis ◽  
Breast Imaging ◽  
Matrix Analysis ◽  
Width Ratio ◽  
Grey Level ◽  
Edge Roughness ◽  
Malignant Group ◽  
Malignant Lesions ◽  
Benign Group

Abstract Background: The classification of Breast Imaging Reporting and Data System 4A (BI-RADS 4A) lesions is entirely based on the personal experience of doctors and lacks specific and clear classification standards. The development of artificial intelligence (AI) provides a new method for BI-RADS category. We analysed the morphological and texture characteristics of BI-RADS 4A benign and malignant lesions using AI, and the ultrasonic characteristics of BI-RADS 4A benign and malignant lesions were compared to examine the value of AI in the differential diagnosis of BI-RADS 4A benign and malignant lesions.Methods: A total of 206 lesions of BI-RADS 4A examined using ultrasonography were analysed retrospectively, including 174 benign lesions and 32 malignant lesions. All of the lesions were contoured manually, and the morphological and texture features of the lesions, such as circularity, depth-to-width ratio, number of spicules, edge roughness, edge fuzziness, margin lobules, energy, entropy, mean grey level, grey level variance, grey level similarity, internal calcification and angle between the long axis of the lesion and skin（ALS） of the ROI, were calculated using grey level gradient co-occurrence matrix analysis. The differences between benign and malignant lesions of BI-RADS 4A were analysed.Results: There were significant differences between the benign group and malignant group in margin lobules, entropy, internal calcification and ALS (P=0.013, 0.045, 0.045, 0.002, respectively). The malignant group had more margin lobules and lower entropy than the benign group, and the benign group had more internal calcification and a larger ALS than the malignant group. There were no significant differences in circularity, depth-to-width ratio, number of spicules, edge roughness, edge fuzziness, energy, mean of grey level, grey level variance, and grey level similarity between benign and malignant lesions.Conclusion: For benign and malignant lesions of BI-RADS 4A, margin lobules and internal echo uniformity are the critical points of differentiation. Some of the characteristics of atypical benign and malignant lesions are blurry or even inverted, which may lead to a deviation of the characteristics of benign and malignant lesions.

Effect of GLCM Texture Features on the Medio-Lateral Oblique (MLO) View of Digital Mammograms for Breast Cancer Detection

2020 ◽  
Vol 9 (2) ◽  
pp. 25-44
Author(s):  
Usha N. ◽  
Sriraam N. ◽  
Kavya N. ◽  
Bharathi Hiremath ◽  
Anupama K Pujar ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Classification Accuracy ◽  
Breast Imaging ◽  
Texture Features ◽  
Support Vector ◽  
Risk Of Death ◽  
Automated Method ◽  
Occurrence Matrix ◽  
Aided Diagnosis ◽  
Mammogram Images

Breast cancer is one among the most common cancers in women. The early detection of breast cancer reduces the risk of death. Mammograms are an efficient breast imaging technique for breast cancer screening. Computer aided diagnosis (CAD) systems reduce manual errors and helps radiologists to analyze the mammogram images. The mammogram images are typically in two views, cranial-caudal (CC) and medio lateral oblique (MLO) views. MLO contains pectoral muscles (chest muscles) at the upper right or left corner of the image. In this study, it was removed by using a semi-automated method. All the normal and abnormal images were filtered and enhanced to improve the quality. GLCM (Gray Level Co-occurrence Matrix) texture features were extracted and analyzed by changing the number of features in a feature set. Linear Support Vector Machine (LSVM) was used as classifier. The classification accuracy was improved as the number of features in GLCM feature set increases. Simulation results show an overall classification accuracy of 96.7% with 19 GLCM features using SVM classifiers.

scholarly journals Dilemma of the differential diagnosis of hilar cholangiocarcinoma and benign diseases:a single-center retrospective study

2020 ◽  
Author(s):  
Liwei Pang ◽  
Shangzhi Hu ◽  
Wanlin Dai ◽  
Shuodong Wu ◽  
Jing Kong
Keyword(s):  
Differential Diagnosis ◽  
Hilar Cholangiocarcinoma ◽  
Characteristic Curve ◽  
Age At Onset ◽  
Clinical Manifestations ◽  
Serum Levels ◽  
Institutional Review ◽  
Malignant Group ◽  
Informed Consent Document ◽  
Benign Group

Abstract Hilar cholangiocarcinoma, which lacks specific clinical manifestations, remains very difficult to distinguish from benign disease. This distinction is further complicated by the complex hilar anatomy. We conducted the present study to evaluate the differential diagnosis of these conditions. Sixty-five patients underwent resection surgery for suspected hilar cholangiocarcinoma between January 2011 and October 2018. Institutional Review Board of Shengjing hospital agreed this study and all particpants sign an informed consent document prior to participation in a research study. Following a postoperative pathology analysis, all patients were divided into 2 groups: malignant group (54 patients with HCCA) and benign group (11 cases with benign lesions). Compared to the benign group, the malignant group had a significantly higher median age and serum CA19-9, CEA, ALT, BILT, and BILD levels (P <0.05). By contrast, the groups did not differ significantly in terms of the sex distribution, clinical manifestations, serum levels of AST and ALKP, and imaging findings. In a receiver operating characteristic curve analysis, we identified a CA19-9 cut-off point of 233.15 U/ml for the differential diagnosis and CEA cut-off point of 2.98 ng/ml for the differential diagnosis. The differential diagnosis of HCCA and benign hilar lesions remains difficult. However, we found that patients with HCCA tended to have an older age at onset and higher serum levels of CA19-9, CEA, BILT, ALT, and BILD. Furthermore, patients with a serum CA19-9 level >233.15 U/ml and CEA level >2.98 ng/ml are more likely to have malignant disease.

scholarly journals The Potential Value of Texture Analysis Based on Dynamic Contrast-Enhanced MR Images in the Grading of Breast Phyllode Tumors

2021 ◽  
Vol 11 ◽  
Author(s):  
Xiaoguang Li ◽  
Hong Guo ◽  
Chao Cong ◽  
Huan Liu ◽  
Chunlai Zhang ◽  
...  
Keyword(s):  
Texture Analysis ◽  
Roc Curve ◽  
Breast Imaging ◽  
Statistical Significance ◽  
Texture Features ◽  
Imaging Findings ◽  
Mr Images ◽  
Dynamic Contrast Enhanced ◽  
Contrast Enhanced ◽  
Occurrence Matrix

PurposeTo explore the value of texture analysis (TA) based on dynamic contrast-enhanced MR (DCE-MR) images in the differential diagnosis of benign phyllode tumors (BPTs) and borderline/malignant phyllode tumors (BMPTs).MethodsA total of 47 patients with histologically proven phyllode tumors (PTs) from November 2012 to March 2020, including 26 benign BPTs and 21 BMPTs, were enrolled in this retrospective study. The whole-tumor texture features based on DCE-MR images were calculated, and conventional imaging findings were evaluated according to the Breast Imaging Reporting and Data System (BI-RADS). The differences in the texture features and imaging findings between BPTs and BMPTs were compared; the variates with statistical significance were entered into logistic regression analysis. The receiver operating characteristic (ROC) curve was used to assess the diagnostic performance of models from image-based analysis, TA, and the combination of these two approaches.ResultsRegarding texture features, three features of the histogram, two features of the gray-level co-occurrence matrix (GLCM), and three features of the run-length matrix (RLM) showed significant differences between the two groups (all p < 0.05). Regarding imaging findings, however, only cystic wall morphology showed significant differences between the two groups (p = 0.014). The areas under the ROC curve (AUCs) of image-based analysis, TA, and the combination of these two approaches were 0.687 (95% CI, 0.518–0.825, p = 0.014), 0.886 (95% CI, 0.760–0.960, p < 0.0001), and 0.894 (95% CI, 0.754–0.970, p < 0.0001), respectively.ConclusionTA based on DCE-MR images has potential in differentiating BPTs and BMPTs.

Peripheral Lymphadenopathies in Childhood: Experience at a Pediatric Oncology Department in Turkey

2020 ◽  
pp. 66-73
Author(s):  
Tuğçe Kalın Güngör ◽  
Handan Uğur Dinçaslan ◽  
Emel Cabi Ünal ◽  
Nurdan Taçyıldız ◽  
Leman Gülsan Yavuz
Keyword(s):  
Differential Diagnosis ◽  
Clinical Laboratory ◽  
Laboratory Findings ◽  
Abnormal Chest ◽  
Malignant Group ◽  
Chest X Ray ◽  
Systemic Symptoms ◽  
Reactive Hyperplasia ◽  
Physical Findings ◽  
Benign Group

Introduction: Palpable lymph nodes are very common physical examination findings in childhood, and sometimes it can be challenging to say if it is benign or malignant. Objectives: This retrospective study evaluated 157 children admitted to an oncology department because of lymphadenopathy and aimed to determine the clinical, laboratory, and epidemiologic data valuable for differential diagnosis. Materials and Methods: One hundred fifty-two cases were analyzed, which were defined as either malignant or benign by the etiology. The benign cases were also defined to three groups as ‘viral lymphadenopathy’, ‘bacterial lymphadenopathy’, and ‘other reactive lymphadenopathy’. Results: A specific cause for lymphadenopathy was documented in 61 (40,1%) cases. Of 152 cases, benign causes were detected in 133 (87,5%), and malignant causes were detected in 19 (12,5%) cases. The most frequent cause in the benign group was reactive hyperplasia (59,8%) and in the malignant group was lymphoma (7,3%). A biopsy was performed from 19 of the cases for diagnosis. Malign causes were detected in 12 (58%), and benign causes were detected in the remaining 7 (42%). In terms of differential diagnosis, some symptoms, physical findings, and laboratory tests showed meaningful differences between the case groups Conclusions: The following findings were determined as being important to alert physicians about the probability of a malignant disorder: location of lymphadenopathy, number of associated systemic symptoms, size of lymph node, abnormal laboratory findings, abnormal chest X-ray.

scholarly journals Dilemma of the differential diagnosis of hilar cholangiocarcinoma and benign diseases:a single-center retrospective study

2019 ◽  
Author(s):  
Liwei Pang
Keyword(s):  
Differential Diagnosis ◽  
Hilar Cholangiocarcinoma ◽  
Characteristic Curve ◽  
Age At Onset ◽  
Laboratory Data ◽  
Clinical Manifestations ◽  
Serum Levels ◽  
Imaging Findings ◽  
Malignant Group ◽  
Benign Group

Abstract Objective Hilar cholangiocarcinoma, which lacks specific clinical manifestations, remains very difficult to distinguish from benign disease. This distinction is further complicated by the complex hilar anatomy. We conducted the present study to evaluate the differential diagnosis of these conditions. Methods Sixty-five patients underwent resection surgery for suspected hilar cholangiocarcinoma between January 2011 and October 2018. Following a postoperative pathology analysis, all patients were divided into 2 groups: malignant group (54 patients with HCCA) and benign group (11 cases with benign lesions). The patients' clinical data, including general demographics (sex, age), clinical manifestations (jaundice, abdominal discomfort, fever, weight loss), laboratory data [alanine aminotransferase (ALT), aspartate aminotransferase (AST), alkaline phosphatase (ALKP), total bilirubin (BILT), indirect bilirubin (BILD), carbohydrate antigen (CA) 19-9, carcinoembryonic antigen (CEA)], and imaging findings, were included in a retrospective analysis. Results Compared to the benign group, the malignant group had a significantly higher median age and serum CA19-9, CEA, ALT, BILT, and BILD levels (P <0.05). By contrast, the groups did not differ significantly in terms of the sex distribution, clinical manifestations, serum levels of AST and ALKP, and imaging findings. In a receiver operating characteristic curve analysis, we identified a CA19-1 cut-off point of 233.15 U/ml for the differential diagnosis, with a sensitivity of 56% and specificity of 91%. Furthermore, we identified a CEA cut-off point of 2.98 ng/ml for the differential diagnosis, with a sensitivity of 61% and specificity of 90%. Conclusion The differential diagnosis of HCCA and benign hilar lesions remains difficult. However, we found that patients with HCCA tended to have an older age at onset and higher serum levels of CA19-9, CEA, BILT, ALT, and BILD. Furthermore, patients with a serum CA19-9 level >233.15 U/ml and CEA level >2.98 ng/ml are more likely to have malignant disease.

scholarly journals Comparison of miRNA expressions among benign, premalignant and malignant lesions of the larynx: could they be transformation biomarkers?

2021 ◽  
Vol 50 (1) ◽  
Author(s):  
Fatma Ruya Tuncturk ◽  
Ibrahim Akalin ◽  
Lokman Uzun ◽  
Tulay Zenginkinet
Keyword(s):  
Treatment Options ◽  
Premalignant Lesions ◽  
Gene Expressions ◽  
Laryngeal Lesions ◽  
Malignant Group ◽  
Malignant Lesions ◽  
Polymerase Chain ◽  
Benign Group ◽  
Malignancy Potential

Abstract Background The malignancy potential of the laryngeal lesions are one of the major concerns of the surgeons about choosing the treatment options, forming surgical margins, deciding the follow-up periods. Finding a biomarker to overcome these concerns are ongoing challenges and recently microRNAs (miRNAs) are attributed as possible candidates since they can regulate gene expressions in the human genome. The objective of our study was to investigate their capability as a transformation biomarker for malignant laryngeal lesions. Materials and methods We investigated mature miRNA expressions in paraffin-embedded surgical specimens of human laryngeal tissues grouped as benign, premalignant or malignant (n = 10 in each). miRNA profiling was carried out by quantitative Real-Time polymerase chain reaction (RT-qPCR) and data were analyzed according to fold regulation. Results Our results demonstrated that 9 miRNAs were upregulated as the lesions become more malignant. Among them Hs_miR-183_5p, Hs_miR-155_5p, and Hs_miR-106b_3p expressions were significantly 4.16 (p = 0.032), 2.72 (p = 0.028) and 3.01 (p = 0.022) fold upregulated respectively in premalignant lesions compared to the benign lesions. Moreover, their expressions were approximately 2.76 fold higher in the malignant group than in the premalignant group compared to the benign group. Besides them, significant 7.57 (p = 0.036), 4.45 (p = 0.045) and 5.98 (p = 0.023) fold upregulations of Hs_miR-21_5p, Hs_miR-218_3p, and Hs_miR-210_3p were noticed in the malignant group but not in the premalignant group when compared to the benign group, respectively. Conclusion MiRNAs might have important value to help the clinicians for their concerns about the malignancy potentials of the laryngeal lesions. Hs_miR-183_5p, Hs_miR-155_5p, and Hs_miR-106b_3p might be followed as transformation marker, whereas Hs_miR-21_5p, Hs_miR-218_3p, and Hs_miR-210_3p might be a biomarker prone to malignancy.

Sign in / Sign up

Export Citation Format

Share Document