-
Frontiers in Oncology 2023We aimed to develop an ultrasound-based radiomics model to distinguish between sclerosing adenosis (SA) and invasive ductal carcinoma (IDC) to avoid misdiagnosis and...
OBJECTIVES
We aimed to develop an ultrasound-based radiomics model to distinguish between sclerosing adenosis (SA) and invasive ductal carcinoma (IDC) to avoid misdiagnosis and unnecessary biopsies.
METHODS
From January 2020 to March 2022, 345 cases of SA or IDC that were pathologically confirmed were included in the study. All participants underwent pre-surgical ultrasound (US), from which clinical information and ultrasound images were collected. The patients from the study population were randomly divided into a training cohort (n = 208) and a validation cohort (n = 137). The US images were imported into MaZda software (Version 4.2.6.0) to delineate the region of interest (ROI) and extract features. Intragroup correlation coefficient (ICC) was used to evaluate the consistency of the extracted features. The least absolute shrinkage and selection operator (LASSO) logistic regression and cross-validation were performed to obtain the radiomics score of the features. Based on univariate and multivariate logistic regression analyses, a model was developed. 56 cases from April 2022 to December 2022 were included for independent validation of the model. The diagnostic performance of the model and the radiomics scores were evaluated by performing the receiver operating characteristic (ROC) analysis. The calibration curve and decision curve analysis (DCA) were used for calibration and evaluation. Leave-One-Out Cross-Validation (LOOCV) was used for the stability of the model.
RESULTS
Three predictors were selected to develop the model, including radiomics score, palpable mass and BI-RADS. In the training cohort, validation cohort and independent validation cohort, AUC of the model and radiomics score were 0.978 and 0.907, 0.946 and 0.886, 0.951 and 0.779, respectively. The model showed a statistically significant difference compared with the radiomics score (<0.05). The Kappa value of the model was 0.79 based on LOOCV. The Brier score, calibration curve, and DCA showed the model had a good calibration and clinical usefulness.
CONCLUSIONS
The model based on radiomics, ultrasonic features, and clinical manifestations can be used to distinguish SA from IDC, which showed good stability and diagnostic performance. The model can be considered a potential candidate diagnostic tool for breast lesions and can contribute to effective clinical diagnosis.
PubMed: 36959807
DOI: 10.3389/fonc.2023.1090617 -
European Journal of Breast Health Apr 2019Juvenile papillomatosis of the breast, also known as Swiss cheese disease, is a rare and benign proliferative disorder affecting young women. These patients tend to have...
Juvenile papillomatosis of the breast, also known as Swiss cheese disease, is a rare and benign proliferative disorder affecting young women. These patients tend to have a strong family history of cancer. The lesion typically presents as a localized mass without sharp borders. Clinical presentation resembles that of a precancerous lesion. For this reason, JP is often misdiagnosed in the preoperative period. However postoperative histopathological examination reveals distinct microscopic features, such as duct papillomatosis, cysts and sclerosing adenosis, which confirm the diagnosis of juvenile papillomatosis. We report two cases of juvenile papillomatosis. Both cases were preoperatively diagnosed as benign proliferative lesions with fibrocystic changes. However, after surgical excision, histopathological examination showed juvenile papillomatosis. Interestingly, both patients had a strong family history of breast cancer in both the paternal and maternal line. More research is needed to assess the correlation between a family history of breast cancer and the juvenile papillomatosis.
PubMed: 31001616
DOI: 10.5152/ejbh.2019.4362 -
Head and Neck Pathology Jun 2022Sclerosing polycystic adenosis, initially considered a non-neoplastic salivary gland lesion and classified as such in the 2017 WHO Classification of Head and Neck...
Sclerosing polycystic adenosis, initially considered a non-neoplastic salivary gland lesion and classified as such in the 2017 WHO Classification of Head and Neck Tumors, has been the subject of controversy regarding its possible neoplastic nature. The reporting of recurrent PI3K pathway alteration represents evidence to support these lesions as being neoplastic and more appropriately referred to as sclerosing polycystic adenoma (SPA). Herein, we provide additional evidence that supports the classification of SPA as a true neoplasm. Eight cases of SPA were identified in our database and consultation files. All cases were subjected to PTEN immunohistochemistry (IHC) and next-generation sequencing (NGS). In addition, one patient underwent genetic counseling and germline testing. The cases included 5 men and 3 women with a mean age of 41 years (range 11-78) and all tumors arose in the parotid gland. One patient had multiple recurrences over a period of 2 years. Morphologically the tumors were circumscribed and characterized by an admixture of acini, ducts and cysts embedded in a fibrotic/sclerotic stroma. The cells lining the ducts and cysts showed variable granular, vacuolated, foamy and apocrine cytoplasmic features, as well as acinar cells contained intracytoplasmic brightly eosinophilic granules. The apocrine intraductal proliferations showed mild to moderate atypia in 6 cases. One case showed overt malignant morphology that ranged from intraductal carcinoma to invasive salivary duct carcinoma. Seven cases tested for PTEN IHC showed loss of nuclear expression in the acinar and ductal cells with retained PTEN expression in the myoepithelial cell and stroma. NGS detected PIK3CA or PIK3R1 genetic alterations in 7 cases, including a novel TFG-PIK3CA fusion. Coexisting PTEN mutations were seen in 4 cases, including in a patient with clinical stigmata of Cowden syndrome and confirmed by germline genetic testing. Our findings herein documented including recurrence of tumor, malignant transformation, high prevalence of PI3K pathway oncogenic alterations and the possible heretofore undescribed association with Cowden syndrome add support to classifying SPA as true neoplasms justifying their designation as adenoma, rather than adenosis.
Topics: Adenoma; Adolescent; Adult; Aged; Child; Class I Phosphatidylinositol 3-Kinases; Cysts; Female; Hamartoma Syndrome, Multiple; Humans; Hyperplasia; Male; Middle Aged; Phosphatidylinositol 3-Kinases; Young Adult
PubMed: 34410594
DOI: 10.1007/s12105-021-01374-w -
Medicine Dec 2018In the recent 20 years, primary vaginal adenosis is extremely rare and the data of clinical presentations, management, and outcome have not been studied...
In the recent 20 years, primary vaginal adenosis is extremely rare and the data of clinical presentations, management, and outcome have not been studied systematically.In this retrospective study, women with vaginal adenosis between January 1997 and June 2017 were identified from the hospital's medical records. Data on patient age, history, symptoms, mass location, size, diagnosis, complications, treatment, and recurrence were analyzed by SPSS 20.0.Twenty women were histopathologically diagnosed as having vaginal adenosis (mean age, 37.9 ± 10.6 years). All patients denied utero exposure. The most common symptom was vaginal pain or abnormal bleeding. For all patients, the local vaginal lesions were surgically excised. Seven patients had complications with endometriosis. 15 patients lived without recurrence, and 1 patient underwent postoperative local recurrence after 81 months. Primary vaginal squamous cell carcinoma in another patient was confirmed to arise from adenosis; she survived with disease. The remaining 3 patients developed carcinoma of different types in varied periods of a disease-free state (5 months, 30 months, and 23 years, respectively); 1 patient died of progressive disease, and 2 patients survived with disease.Primary vaginal adenosis is a spontaneous lesion with a propensity for late canceration. Local lesion resection is the primary treatment.
Topics: Adult; Female; Follow-Up Studies; Humans; Retrospective Studies; Vagina; Vaginal Diseases
PubMed: 30544435
DOI: 10.1097/MD.0000000000013470 -
The Journal of Pathology Jun 2021Artificial intelligence (AI)-based systems applied to histopathology whole-slide images have the potential to improve patient care through mitigation of challenges posed...
Artificial intelligence (AI)-based systems applied to histopathology whole-slide images have the potential to improve patient care through mitigation of challenges posed by diagnostic variability, histopathology caseload, and shortage of pathologists. We sought to define the performance of an AI-based automated prostate cancer detection system, Paige Prostate, when applied to independent real-world data. The algorithm was employed to classify slides into two categories: benign (no further review needed) or suspicious (additional histologic and/or immunohistochemical analysis required). We assessed the sensitivity, specificity, positive predictive values (PPVs), and negative predictive values (NPVs) of a local pathologist, two central pathologists, and Paige Prostate in the diagnosis of 600 transrectal ultrasound-guided prostate needle core biopsy regions ('part-specimens') from 100 consecutive patients, and to ascertain the impact of Paige Prostate on diagnostic accuracy and efficiency. Paige Prostate displayed high sensitivity (0.99; CI 0.96-1.0), NPV (1.0; CI 0.98-1.0), and specificity (0.93; CI 0.90-0.96) at the part-specimen level. At the patient level, Paige Prostate displayed optimal sensitivity (1.0; CI 0.93-1.0) and NPV (1.0; CI 0.91-1.0) at a specificity of 0.78 (CI 0.64-0.89). The 27 part-specimens considered by Paige Prostate as suspicious, whose final diagnosis was benign, were found to comprise atrophy (n = 14), atrophy and apical prostate tissue (n = 1), apical/benign prostate tissue (n = 9), adenosis (n = 2), and post-atrophic hyperplasia (n = 1). Paige Prostate resulted in the identification of four additional patients whose diagnoses were upgraded from benign/suspicious to malignant. Additionally, this AI-based test provided an estimated 65.5% reduction of the diagnostic time for the material analyzed. Given its optimal sensitivity and NPV, Paige Prostate has the potential to be employed for the automated identification of patients whose histologic slides could forgo full histopathologic review. In addition to providing incremental improvements in diagnostic accuracy and efficiency, this AI-based system identified patients whose prostate cancers were not initially diagnosed by three experienced histopathologists. © 2021 The Authors. The Journal of Pathology published by John Wiley & Sons, Ltd. on behalf of The Pathological Society of Great Britain and Ireland.
Topics: Aged; Aged, 80 and over; Artificial Intelligence; Biopsy; Biopsy, Large-Core Needle; Humans; Machine Learning; Male; Middle Aged; Pathologists; Prostate; Prostatic Neoplasms
PubMed: 33904171
DOI: 10.1002/path.5662 -
Modern Pathology : An Official Journal... Mar 2004The diagnosis of limited adenocarcinoma of the prostate is one of the more difficult challenges in surgical pathology. This paper highlights the methodological approach... (Review)
Review
The diagnosis of limited adenocarcinoma of the prostate is one of the more difficult challenges in surgical pathology. This paper highlights the methodological approach to diagnosing limited cancer, based on a constellation of features more commonly present in adenocarcinoma than benign glands. In assessing small foci of atypical glands on needle biopsy, one looks for differences between the benign glands and the atypical glands in terms of nuclear features, cytoplasmic features, and intraluminal contents. Only a few features, such as glomerulations, mucinous fibroplasia (collagenous micronodules), and perineural invasion are diagnostic in and of themselves for prostate cancer. Immunohistochemistry may be a useful adjunct in the diagnosis of limited adenocarcinoma of the prostate, although as with any immunohistochemical studies, there are problems with both sensitivity and specificity. Basal cell markers, such as high molecular weight cytokeratin and more recently, p63, highlight basal cells found in benign glands, yet are absent in adenocarcinoma of the prostate. However, not all benign glands label uniformly with basal cell markers. Certain mimickers of adenocarcinoma of the prostate are even less frequently labeled uniformly with these stains. Consequently, negative staining in a small focus of atypical glands for basal cell markers is not diagnostic of adenocarcinoma of the prostate. More recently, a marker has been identified that relatively selectively labels adenocarcinoma of the prostate. AMACR will label the cytoplasm of approximately 80% of limited adenocarcinoma of the prostate cases on needle biopsy. In positive cases, not all of the glands will be positive and those that are positive are often not intensely positive. Certain variants of adenocarcinoma of the prostate that are a little more difficult to recognize, such as foamy glands adenocarcinoma, pseudohyperplastic adenocarcinoma, and atrophic adenocarcinoma, are labeled with AMACR in only approximately 60-70% of cases. In addition to problems with sensitivity, AMACR is not entirely specific for adenocarcinoma, and will label almost all cases of high-grade prostatic intraepithelial neoplasia, some foci of adenosis, and even some entirely benign glands. Finally, this paper will briefly cover the significance of atypical or suspicious prostate needle biopsies, and how to report the key diagnostic and prognostic information on needle biopsy.
Topics: Adenocarcinoma; Biopsy, Needle; Coloring Agents; Diagnosis, Differential; Eosine Yellowish-(YS); Fluorescent Dyes; Hematoxylin; Humans; Immunohistochemistry; Male; Prostate; Prostatic Neoplasms; Staining and Labeling
PubMed: 14739905
DOI: 10.1038/modpathol.3800050 -
PloS One 2021Breast cancer is the cancer with the highest incidence of malignant tumors in women, which seriously endangers women's health. With the help of computer vision...
Breast cancer is the cancer with the highest incidence of malignant tumors in women, which seriously endangers women's health. With the help of computer vision technology, it has important application value to automatically classify pathological tissue images to assist doctors in rapid and accurate diagnosis. Breast pathological tissue images have complex and diverse characteristics, and the medical data set of breast pathological tissue images is small, which makes it difficult to automatically classify breast pathological tissues. In recent years, most of the researches have focused on the simple binary classification of benign and malignant, which cannot meet the actual needs for classification of pathological tissues. Therefore, based on deep convolutional neural network, model ensembleing, transfer learning, feature fusion technology, this paper designs an eight-class classification breast pathology diagnosis model BCDnet. A user inputs the patient's breast pathological tissue image, and the model can automatically determine what the disease is (Adenosis, Fibroadenoma, Tubular Adenoma, Phyllodes Tumor, Ductal Carcinoma, Lobular Carcinoma, Mucinous Carcinoma or Papillary Carcinoma). The model uses the VGG16 convolution base and Resnet50 convolution base as the parallel convolution base of the model. Two convolutional bases (VGG16 convolutional base and Resnet50 convolutional base) obtain breast tissue image features from different fields of view. After the information output by the fully connected layer of the two convolutional bases is fused, it is classified and output by the SoftMax function. The model experiment uses the publicly available BreaKHis data set. The number of samples of each class in the data set is extremely unevenly distributed. Compared with the binary classification, the number of samples in each class of the eight-class classification is also smaller. Therefore, the image segmentation method is used to expand the data set and the non-repeated random cropping method is used to balance the data set. Based on the balanced data set and the unbalanced data set, the BCDnet model, the pre-trained model Resnet50+ fine-tuning, and the pre-trained model VGG16+ fine-tuning are used for multiple comparison experiments. In the comparison experiment, the BCDnet model performed outstandingly, and the correct recognition rate of the eight-class classification model is higher than 98%. The results show that the model proposed in this paper and the method of improving the data set are reasonable and effective.
Topics: Biopsy; Breast; Breast Neoplasms; Datasets as Topic; Deep Learning; Female; Humans; Image Processing, Computer-Assisted
PubMed: 34252112
DOI: 10.1371/journal.pone.0253764 -
SpringerPlus Dec 2013Adenomyoepithelial adenosis of the breast is an extremely rare type of adenosis. We herein present the case of a 35-year-old woman, who presented with a small painless...
Adenomyoepithelial adenosis of the breast is an extremely rare type of adenosis. We herein present the case of a 35-year-old woman, who presented with a small painless hard lump and elastic soft induration of 5 cm in diameter in her left breast. Clinical examination and diagnostic workup were suggestive of a breast carcinoma, and a modified radical mastectomy and sentinel node biopsy were performed. Histopathological examination revealed adenomyoepithelial adenosis along with fibrocystic change and small invasive ductal carcinoma, slightly away from the adenosis. The presented case was thought to be initial-stage adenomyoepithelial adenosis and independently developing breast cancer. From a review of five reported cases of adenomyoepithelial adenosis, complete resection of the tumor and coexisting malignant disease may be recommended, owing to the tendency to develop breast cancer or malignant adenomyoepithelioma, or recurrence.
PubMed: 23450635
DOI: 10.1186/2193-1801-2-50 -
Modern Pathology : An Official Journal... Jan 2017Acinic cell carcinoma is an indolent form of invasive breast cancer, whereas microglandular adenosis has been shown to be a neoplastic proliferation. Both entities...
Genetic analysis of microglandular adenosis and acinic cell carcinomas of the breast provides evidence for the existence of a low-grade triple-negative breast neoplasia family.
Acinic cell carcinoma is an indolent form of invasive breast cancer, whereas microglandular adenosis has been shown to be a neoplastic proliferation. Both entities display a triple-negative phenotype, and may give rise to and display somatic genomic alterations typical of high-grade triple-negative breast cancers. Here we report on a comparison of previously published data on eight carcinoma-associated microglandular adenosis and eight acinic cell carcinomas subjected to targeted massively parallel sequencing targeting all exons of 236 genes recurrently mutated in breast cancer and/or DNA repair-related. Somatic mutations, insertions/ deletions, and copy number alterations were detected using state-of-the-art bioinformatic algorithms. All cases were of triple-negative phenotype. A median of 4.5 (1-13) and 4.0 (1-7) non-synonymous somatic mutations per carcinoma-associated microglandular adenosis and acinic cell carcinoma were identified, respectively. TP53 was the sole highly recurrently mutated gene (75% in microglandular adenosis versus 88% in acinic cell carcinomas), and TP53 mutations were consistently coupled with loss of heterozygosity of the wild-type allele. Additional somatic mutations shared by both groups included those in BRCA1, PIK3CA, and INPP4B. Recurrent (n=2) somatic mutations restricted to microglandular adenosis or acinic cell carcinomas included those affecting PTEN and MED12 or ERBB4, respectively. No significant differences in the repertoire of somatic mutations were detected between microglandular adenosis and acinic cell carcinomas, and between this group of lesions and 77 triple-negative carcinomas from The Cancer Genome Atlas. Microglandular adenosis and acinic cell carcinomas, however, were genetically distinct from estrogen receptor-positive and/or HER2-positive breast cancers from The Cancer Genome Atlas. Our findings support the contention that microglandular adenosis and acinic cell carcinoma are part of the same spectrum of lesions harboring frequent TP53 somatic mutations, and likely represent low-grade forms of triple-negative disease with no/minimal metastatic potential, of which a subset has the potential to progress to high-grade triple-negative breast cancer.
Topics: BRCA1 Protein; Breast; Breast Neoplasms; Carcinoma, Acinar Cell; Class I Phosphatidylinositol 3-Kinases; Female; Fibrocystic Breast Disease; Gene Expression Regulation, Neoplastic; High-Throughput Nucleotide Sequencing; Humans; Mediator Complex; Neoplasm Grading; Phosphoric Monoester Hydrolases; Receptor, ErbB-4; Triple Negative Breast Neoplasms
PubMed: 27713419
DOI: 10.1038/modpathol.2016.161 -
Archives of Pathology & Laboratory... Feb 2017-A review of amended pathology reports provides valuable information regarding defects in the surgical pathology process. (Review)
Review
CONTEXT
-A review of amended pathology reports provides valuable information regarding defects in the surgical pathology process.
OBJECTIVE
-To review amended breast pathology reports with emphasis placed on interpretative errors and their mechanisms of detection.
DESIGN
-All amended pathology reports for breast surgical specimens for a 5-year period at a large academic medical center were retrospectively identified and classified based on an established taxonomy.
RESULTS
-Of 12 228 breast pathology reports, 122 amended reports were identified. Most (88 cases; 72%) amendments were due to noninterpretative errors, including 58 report defects, 12 misidentifications, and 3 specimen defects. A few (34 cases; 27.9%) were classified as misinterpretations, including 14 major diagnostic changes (11.5% of all amendments). Among major changes, there were cases of missed microinvasion or small foci of invasion, missed micrometastasis, atypical ductal hyperplasia overcalled as ductal carcinoma in situ, ductal carcinoma in situ involving sclerosing adenosis mistaken for invasive carcinoma, lymphoma mistaken for invasive carcinoma, and amyloidosis misdiagnosed as fat necrosis. Nine major changes were detected at interpretation of receptor studies and were not associated with clinical consequences. Three cases were associated with clinical consequences, and of note, the same pathologist interpreted the corresponding receptor studies.
CONCLUSIONS
-Review of amended reports was a useful method for identifying error frequencies, types, and methods of detection. Any time that a case is revisited for ancillary studies or other reasons, it is an opportunity for the surgical pathologist to reconsider one's own or another's diagnosis.
Topics: Breast Neoplasms; Female; Humans; Medical Errors; Pathology, Surgical; Quality Assurance, Health Care; Retrospective Studies
PubMed: 27959581
DOI: 10.5858/arpa.2016-0018-OA