Differentiating non-lactating mastitis and malignant breast tumors by deep-learning based AI automatic classification system: A preliminary study

Zhou, Ying; Feng, Bo-Jian; Yue, Wenwen; Liu, Yuan; Xu, Zhenbo; Wang, Xing; Zhao, Xiaolan; Yao, Jin-Cao; Wang, Shurong; Xu, Dianguo

doi:10.3389/fonc.2022.997306

Cited by 7 publications

(3 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Both GLM and BC typically present as breast masses with indistinct borders and rm consistency, and may be accompanied by enlarged ipsilateral axillary lymph nodes. Although modern research has improved the non-invasive differential diagnosis of GLM and BC through various radiological techniques, such as sonogram radiomics model 22 , contrast-enhanced ultrasound 23 , ultrasound elastography 24 , deep-learning based AI automatic classi cation system 25 , and ARFI elastography 26 , the gold standard for diagnosing GLM still requires tissue biopsy. In some cases, multiple biopsies may be necessary for clinical differential diagnosis.…”

Section: Discussionmentioning

confidence: 99%

Circulating miR-451a, miR-5571-3p, CLN6, HSD11B1 and PDE4 levels in differential diagnosis of Granulomatous lobular mastitis, breast cancer and breast fibroadenoma

LING,

WU,

DENG

et al. 2023

Preprint

View full text Add to dashboard Cite

This study aimed to investigate the diagnostic value of miR-451a, miR-5571-3p, CLN6, HSD11B1, and PDE4 as potential biomarkers for distinguishing patients with Granulomatous lobular mastitis (GLM), breast cancer (BC), and breast fibroadenoma. A total of 55 participants were included in each group. The serum expressions of miR-451a and miR-5571-3p were significantly higher in the GLM (0.95 ± 0.47, 7.20 ± 3.99) and control groups (0.21 ± 0.13, 1.74 ± 1.49) than in the BC group (p < 0.01). Meanwhile, the expression of miR-451a and miR-5571-3p in GLM was significantly higher than in the control group (0.21 ± 0.13, 1.74 ± 1.49; p < 0.001). The levels of CLN6 in the GLM(1.37 ± 0.87) and BC((1.57 ± 0.84) groups were higher than those in the control group (p < 0.001). Furthermore, HSD11B1 and PDE4 expressions were significantly increased in the BC (1.92 ± 1.14, 1.54 ± 0.88) and GLM (1.07 ± 0.70, 0.85 ± 0.51) groups compared to the control group (p < 0.01), with higher levels observed in the BC group than in the GLM group (p < 0.01). Taken together, these findings suggest that serum miR-451a, miR-5571-3p, and CLN6 may serve as noninvasive biomarkers for differentiating GLM, BC, and breast fibroadenoma. This study provides a basis for future investigations in the differential diagnosis of these breast diseases.

show abstract

Section: Discussionmentioning

confidence: 99%

Circulating miR-451a, miR-5571-3p, CLN6, HSD11B1 and PDE4 levels in differential diagnosis of Granulomatous lobular mastitis, breast cancer and breast fibroadenoma

LING,

WU,

DENG

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Extensive literature has highlighted the efficacy of deep learning in assessing breast images, helping detect malignant and benign breast tumors for both lactating and non-lactating women [49 -54]. This has helped improve the precision of breast ultrasound and mammogram examinations, involving the use of medical imaging previously taken in medical facilities to enhance the evaluation of breast-related illnesses and allow better accuracy in diagnosis for medical personnel [53]. Nevertheless, these studies relied on images gathered from specialized equipment found only in healthcare facilities, not extending their evaluation on external body images, making their main focus on helping healthcare practitioners in diagnosis.…”

Section: Current Research Supporting Lactating Mothersmentioning

confidence: 99%

Augmenting Telepostpartum Care With Vision-Based Detection of Breastfeeding-Related Conditions: Algorithm Development and Validation

De Souza,

Viswanath,

Echterhoff

et al. 2024

JMIR AI

View full text Add to dashboard Cite

Background Breastfeeding benefits both the mother and infant and is a topic of attention in public health. After childbirth, untreated medical conditions or lack of support lead many mothers to discontinue breastfeeding. For instance, nipple damage and mastitis affect 80% and 20% of US mothers, respectively. Lactation consultants (LCs) help mothers with breastfeeding, providing in-person, remote, and hybrid lactation support. LCs guide, encourage, and find ways for mothers to have a better experience breastfeeding. Current telehealth services help mothers seek LCs for breastfeeding support, where images help them identify and address many issues. Due to the disproportional ratio of LCs and mothers in need, these professionals are often overloaded and burned out. Objective This study aims to investigate the effectiveness of 5 distinct convolutional neural networks in detecting healthy lactating breasts and 6 breastfeeding-related issues by only using red, green, and blue images. Our goal was to assess the applicability of this algorithm as an auxiliary resource for LCs to identify painful breast conditions quickly, better manage their patients through triage, respond promptly to patient needs, and enhance the overall experience and care for breastfeeding mothers. Methods We evaluated the potential for 5 classification models to detect breastfeeding-related conditions using 1078 breast and nipple images gathered from web-based and physical educational resources. We used the convolutional neural networks Resnet50, Visual Geometry Group model with 16 layers (VGG16), InceptionV3, EfficientNetV2, and DenseNet169 to classify the images across 7 classes: healthy, abscess, mastitis, nipple blebs, dermatosis, engorgement, and nipple damage by improper feeding or misuse of breast pumps. We also evaluated the models’ ability to distinguish between healthy and unhealthy images. We present an analysis of the classification challenges, identifying image traits that may confound the detection model. Results The best model achieves an average area under the receiver operating characteristic curve of 0.93 for all conditions after data augmentation for multiclass classification. For binary classification, we achieved, with the best model, an average area under the curve of 0.96 for all conditions after data augmentation. Several factors contributed to the misclassification of images, including similar visual features in the conditions that precede other conditions (such as the mastitis spectrum disorder), partially covered breasts or nipples, and images depicting multiple conditions in the same breast. Conclusions This vision-based automated detection technique offers an opportunity to enhance postpartum care for mothers and can potentially help alleviate the workload of LCs by expediting decision-making processes.

show abstract

“…These applications include cancer screening and diagnosis [ 37 , 38 , 39 , 40 ], diagnosis and classification [ 41 , 42 , 43 , 44 ], predicting prognosis and treatment response [ 45 , 46 , 47 , 48 , 49 ], automated segmentation [ 50 , 51 , 52 , 53 , 54 ], and radiology-pathology correlation (radiogenomics) [ 55 , 56 , 57 , 58 ]. In particular, within the field of diagnosis and classification, the ability of AI models to classify benign vs. malignant tumours has been shown to achieve high accuracy, sensitivity, and specificity in various organs, such as in the case of breast [ 59 , 60 , 61 ], prostate [ 62 , 63 ], lung [ 38 , 64 , 65 , 66 ], and brain lesions [ 67 , 68 ]. This review article aims to provide an overview of the current evidence on the effectiveness of machine learning in differentiating bone lesions on various imaging modalities.…”

Section: Introductionmentioning

confidence: 99%

Application of Machine Learning for Differentiating Bone Malignancy on Imaging: A Systematic Review

Ong

Zhu

Tan

et al. 2023

Cancers

View full text Add to dashboard Cite

An accurate diagnosis of bone tumours on imaging is crucial for appropriate and successful treatment. The advent of Artificial intelligence (AI) and machine learning methods to characterize and assess bone tumours on various imaging modalities may assist in the diagnostic workflow. The purpose of this review article is to summarise the most recent evidence for AI techniques using imaging for differentiating benign from malignant lesions, the characterization of various malignant bone lesions, and their potential clinical application. A systematic search through electronic databases (PubMed, MEDLINE, Web of Science, and clinicaltrials.gov) was conducted according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. A total of 34 articles were retrieved from the databases and the key findings were compiled and summarised. A total of 34 articles reported the use of AI techniques to distinguish between benign vs. malignant bone lesions, of which 12 (35.3%) focused on radiographs, 12 (35.3%) on MRI, 5 (14.7%) on CT and 5 (14.7%) on PET/CT. The overall reported accuracy, sensitivity, and specificity of AI in distinguishing between benign vs. malignant bone lesions ranges from 0.44–0.99, 0.63–1.00, and 0.73–0.96, respectively, with AUCs of 0.73–0.96. In conclusion, the use of AI to discriminate bone lesions on imaging has achieved a relatively good performance in various imaging modalities, with high sensitivity, specificity, and accuracy for distinguishing between benign vs. malignant lesions in several cohort studies. However, further research is necessary to test the clinical performance of these algorithms before they can be facilitated and integrated into routine clinical practice.

show abstract

Differentiating non-lactating mastitis and malignant breast tumors by deep-learning based AI automatic classification system: A preliminary study

Cited by 7 publications

References 35 publications

Circulating miR-451a, miR-5571-3p, CLN6, HSD11B1 and PDE4 levels in differential diagnosis of Granulomatous lobular mastitis, breast cancer and breast fibroadenoma

Circulating miR-451a, miR-5571-3p, CLN6, HSD11B1 and PDE4 levels in differential diagnosis of Granulomatous lobular mastitis, breast cancer and breast fibroadenoma

Augmenting Telepostpartum Care With Vision-Based Detection of Breastfeeding-Related Conditions: Algorithm Development and Validation

Application of Machine Learning for Differentiating Bone Malignancy on Imaging: A Systematic Review

Contact Info

Product

Resources

About