Effectiveness of computer-aided diagnosis (CADx) of breast pathology using immunohistochemistry results of core needle biopsy samples for synaptophysin, oestrogen receptor and CK14/p63 for classification of epithelial proliferative lesions of the breast

Maeda, Ichiro; Kubota, Manabu; Ohta, Jitsuo; Shinno, Kimika; Tajima, Shinya; Ariizumi, Yasushi; Doi, Masatomo; Oana, Yoshiyasu; Kanemaki, Yoshihide; Tsugawa, Koichiro; Ueno, Toshiharu; Takagi, Masayuki

doi:10.1136/jclinpath-2017-204478

Cited by 8 publications

(5 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For pathologists, immunostaining (IHC) can accurately locate the site of organization and is an auxiliary method for diagnosing BC. IHC analysis of breast tumours has advantages in the following four aspects: (a) can distinguish between benign and malignant breast tumours; (b) can assess interstitial infiltration; (c) can distinguish between ductal and lobular tumours; and (d) can detect expression of proteins associated with BC treatment and prognosis, to guide endocrine therapy and prognosis 98‐101 . At present, IHC is the best diagnostic method for oestrogen receptor (ER) and progesterone receptor (PR) in BC 102 .…”

Section: Molecular Biotechnology Examinationmentioning

confidence: 99%

“…Aberrant methylation of RhoBTB2 gene may affect expression of the RhoBTB2 gene, which influences PR protein status, become the factor that induce BC endocrine therapy and prognosis. [98][99][100][101] At present, IHC is the best diagnostic method for oestrogen receptor (ER) and progesterone receptor (PR) in BC. 102 The basic principle of IHC (as shown in Figure 7) is antigen-specific binding of antibodies, and these antibodies are usually labelled with colour reagents (such as fluorescein and metal ion) to detect the antigen, protein, peptides, etc IHC can screen and diagnose BC patients by evaluating the level of marker proteins.…”

Section: Rhobtb2mentioning

confidence: 99%

See 1 more Smart Citation

A review on methods for diagnosis of breast cancer cells and tissues

et al. 2020

View full text Add to dashboard Cite

Breast cancer has seriously been threatening physical and mental health of women in the world, and its morbidity and mortality also show clearly upward trend in China over time. Through inquiry, we find that survival rate of patients with early‐stage breast cancer is significantly higher than those with middle‐ and late‐stage breast cancer, hence, it is essential to conduct research to quickly diagnose breast cancer. Until now, many methods for diagnosing breast cancer have been developed, mainly based on imaging and molecular biotechnology examination. These methods have great contributions in screening and confirmation of breast cancer. In this review article, we introduce and elaborate the advances of these methods, and then conclude some gold standard diagnostic methods for certain breast cancer patients. We lastly discuss how to choose the most suitable diagnostic methods for breast cancer patients. In general, this article not only summarizes application and development of these diagnostic methods, but also provides the guidance for researchers who work on diagnosis of breast cancer.

show abstract

Section: Molecular Biotechnology Examinationmentioning

confidence: 99%

Section: Rhobtb2mentioning

confidence: 99%

A review on methods for diagnosis of breast cancer cells and tissues

et al. 2020

View full text Add to dashboard Cite

show abstract

“…In the field of breast cancer, the current artificial intelligence technology is mainly used in early imaging screening (6)(7)(8), and pathologists use virtual microscopes and remote pathological digital section consultations (9). Maeda and other studies used 200 hollow-core needle biopsy breast specimens to perform immunohistochemical staining on their estrogen receptor (ER), synaptophysin, and CKl4/p63, scan the whole section, and analyze the nuclear and cytoplasmic staining with image analysis software as proof of diagnosis cases with high ER expression may indicate malignancy (10).…”

Section: Figure 10mentioning

confidence: 99%

Assisted computer and imaging system improve accuracy of breast tumor size assessment after neoadjuvant chemotherapy

Zhang¹,

Ma²,

Chen³

et al. 2021

Transl Cancer Res TCR

View full text Add to dashboard Cite

Background: The use of neoadjuvant therapy (NAT) in patients with early breast cancer is becoming increasingly common. The purpose of this study was to explore the combined use of breast pathology cabinet X-ray system (CXS) to accurately assess the response to neoadjuvant treatment of breast cancer and establish a standard evaluation system.Methods: A total of 100 patients with breast cancer after neoadjuvant treatment were randomly selected.Preoperative imaging evaluation of tumor masses were significantly degenerated, and they were randomly divided into experimental and control groups of 50 cases each. Compared with the traditional two methods of material extraction, the effective material extraction rate is comparative. Take the two largest diameters of the largest two-dimensional surface of the tumor bed as the measurement object, the macro-description value is D1/D2, the radiographic system description measurement value is the experimental group d1/d2, and the correction under the microscope is worth the true size of the tumor bed H1/H2 as the final test standard, calculate the difference between D1/D2 and d1/d2 with H1 and H2, and compare the difference between d1− H1, d2 − H2 and D1− H1, D2 − H2. Results:The average group of tissue samples in the experimental group was 16.4, and the average group of tissue samples in the control group was 16.7, and there was no difference between the two groups; The effective tissue blocks of tumor bed samples in the experimental group were11.8, and the control group was 7.5. There is difference between the two groups. The average effective percentage of tumor bed in the experimental group was 72%, and the average effective percentage of tumor bed in the control group was 44.8%. The difference was also statistically significant; d1− H1, d2 − H2 and D1− H1, D2 − H2 are all different.Conclusions: CXS assists the collection of breast tumor bed, which can significantly improve the efficiency of tumor bed collection and save the cost of collection. Compared with the maximum diameter of the tumor bed by eyes, the CXS mapping value is closer to the value measured under the microscope.

show abstract

“…Recently, research regarding convolutional neural networks (CNNs) for CAD has expanded to include chest X-rays, computed tomography (CT), and high-resolution CT (HR-CT) [3]. Furthermore, several studies have investigated the application of CAD based on magnetic resonance imaging (MRI) and functional MRI, as well as ultrasound images, infrared thermography, electroencephalography (EEG), digital histopathology, and endoscopy photographs [4,5,6,7]. Previous research has demonstrated that CAD is useful for diagnosing [8] and characterizing patterns [9] of tuberculosis, with decent diagnostic accuracy.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning Algorithms with Demographic Information Help to Detect Tuberculosis in Chest Radiographs in Annual Workers’ Health Examination Data

Heo

Kim

Yun

et al. 2019

IJERPH

View full text Add to dashboard Cite

We aimed to use deep learning to detect tuberculosis in chest radiographs in annual workers’ health examination data and compare the performances of convolutional neural networks (CNNs) based on images only (I-CNN) and CNNs including demographic variables (D-CNN). The I-CNN and D-CNN models were trained on 1000 chest X-ray images, both positive and negative, for tuberculosis. Feature extraction was conducted using VGG19, InceptionV3, ResNet50, DenseNet121, and InceptionResNetV2. Age, weight, height, and gender were recorded as demographic variables. The area under the receiver operating characteristic (ROC) curve (AUC) was calculated for model comparison. The AUC values of the D-CNN models were greater than that of I-CNN. The AUC values for VGG19 increased by 0.0144 (0.957 to 0.9714) in the training set, and by 0.0138 (0.9075 to 0.9213) in the test set (both p < 0.05). The D-CNN models show greater sensitivity than I-CNN models (0.815 vs. 0.775, respectively) at the same cut-off point for the same specificity of 0.962. The sensitivity of D-CNN does not attenuate as much as that of I-CNN, even when specificity is increased by cut-off points. Conclusion: Our results indicate that machine learning can facilitate the detection of tuberculosis in chest X-rays, and demographic factors can improve this process.

show abstract

Effectiveness of computer-aided diagnosis (CADx) of breast pathology using immunohistochemistry results of core needle biopsy samples for synaptophysin, oestrogen receptor and CK14/p63 for classification of epithelial proliferative lesions of the breast

Abstract: The CADx system was able to analyse sufficient data for all types of epithelial proliferative lesions of the breast including invasive breast cancer. This system may be useful for pathological diagnosis of breast CNB in routine investigations.

Cited by 8 publications

References 23 publications

A review on methods for diagnosis of breast cancer cells and tissues

A review on methods for diagnosis of breast cancer cells and tissues

Assisted computer and imaging system improve accuracy of breast tumor size assessment after neoadjuvant chemotherapy

Deep Learning Algorithms with Demographic Information Help to Detect Tuberculosis in Chest Radiographs in Annual Workers’ Health Examination Data

Contact Info

Product

Resources

About