Assessment of Digital Pathology Imaging Biomarkers Associated with Breast Cancer Histologic Grade.

BACKGROUND: Evaluating histologic grade for breast cancer diagnosis is standard and associated with prognostic outcomes. Current challenges include the time required for manual microscopic evaluation and interobserver variability. This study proposes a computer-aided diagnostic (CAD) pipeline for grading tumors using artificial intelligence. METHODS: There were 138 patients included in this retrospective study. Breast core biopsy slides were prepared using standard laboratory techniques, digitized, and pre-processed for analysis. Deep convolutional neural networks (CNNs) were developed to identify the regions of interest containing malignant cells and to segment tumor nuclei. Imaging-based features associated with spatial parameters were extracted from the segmented regions of interest (ROIs). Clinical datasets and pathologic biomarkers (estrogen receptor, progesterone receptor, and human epidermal growth factor 2) were collected from all study subjects. Pathologic, clinical, and imaging-based features were input into machine learning (ML) models to classify histologic grade, and model performances were tested against ground-truth labels at the patient-level. Classification performances were evaluated using receiver-operating characteristic (ROC) analysis. RESULTS: Multiparametric feature sets, containing both clinical and imaging-based features, demonstrated high classification performance. Using imaging-derived markers alone, the classification performance demonstrated an area under the curve (AUC) of 0.745, while modeling these features with other pathologic biomarkers yielded an AUC of 0.836. CONCLUSION: These results demonstrate an association between tumor nuclear spatial features and tumor grade. If further validated, these systems may be implemented into pathology CADs and can assist pathologists to expeditiously grade tumors at the time of diagnosis and to help guide clinical decisions.

Pigmented eyelid cysts revisited: apocrine retention cyst chromhidrosis.

A minority of eyelid hidrocystomas are pigmented containing brown-black contents. Chromhidrosis describes the excretion of colored secretions composed of lipofuscin pigments in apocrine gland-rich anatomic locations. The objective of this study is to evaluate the clinicopathologic features of pigmented eyelid cysts. A case-control study was conducted, examining consecutive pigmented and nonpigmented eyelid hidrocystoma excision specimens. Over a 4-year period, 9 pigmented eyelid hidrocystomas were identified, representing 13% (9/70) of all hidrocystoma excisions. Compared to controls (n = 14), no difference existed for age [mean age 59 (44-78 years) vs. 60 (42-82 years)] or size [mean diameter 2.3 (1-4 mm) vs. 2.7 (1-5 mm)] (pigmented vs. nonpigmented, respectively), but a trend for female, left side, and lower lid predominance for pigmented hidrocystomas existed: 8:1 versus 7:7 F:M; 7:2 versus 7:7 left:right; 8:1 versus 9:5 lower:upper eyelid (pigmented vs. nonpigmented, respectively). Clinically, the pigmented cysts' color varied from dark blue, brown, and to black, and on gross examination, they expressed dark brown to black granular liquid contents. Applying histologic criteria of Jakobiec and Zakka, 8 of 9 and 14 of 14 pigmented and nonpigmented hidrocystomas were of apocrine type. Seven of 9 (78%) pigmented cysts and 6 of 14 (43%) nonpigmented hidrocystomas contained granular eosinophilic cyst contents and/or intracellular cytoplasmic granular pigmented deposits by light microscopy. (The pigmented cyst contents did not survive processing in 2 cases.) By histochemistry (periodic acid Schiff with diastase, Sudan Black, and Fite acid-fast positive staining) and ultraviolet fluorescence, these sediments were determined to be lipofuscin pigments. No hidrocystomas had melanin deposits, and one case had hemosiderin deposits in a scarred cyst wall in addition to cyst lipofuscin pigments. In studies of chromhidrosis, both normal and chromhidrotic apocrine glands contain lipofuscin pigments; the sole difference lies in the amount of lipofuscin granules. Similarly, for eyelid apocrine hidrocystomas, lipofuscin pigments exist in both groups. Presumptively, the amount of lipofuscin and degree of its oxidation distinguish pigmented from nonpigmented apocrine hidrocystomas.

Atopic dermatitis associated with HPV 38 lower leg verrucosis.

We describe a 45-year-old woman with atopic dermatitis who presented with a progressive, papular eruption over her anterior lower legs that began 30 years earlier. Biopsy with polymerase chain reaction analysis revealed lichenified plane warts harboring human papillomavirus 38 DNA. No signs or family history of epidermodysplasia verruciformis existed. Local trauma from shaving, barrier dysfunction, and decreased cell immunity and interferon production associated with atopic dermatitis are likely responsible for this presentation of lower leg verrucosis.

Calcifications associated with basal cell carcinoma: prevalence, characteristics, and correlations.

BACKGROUND: Carcinoma-associated calcifications (Ca(2+)) are a common phenomenon. In the skin, basal cell carcinomas (BCC) can be associated with Ca(2+). OBJECTIVE: To examine the prevalence, characteristics, and clinicopathologic correlations of BCC associated with Ca(2+). MATERIAL AND METHODS: Eighty-three BCC with Ca(2+) were retrieved, 27 (11.1%) of which were identified from a review of 243 consecutive BCC. Ca(2+) were classified into 4 types: type 1, Ca(2+) within BCC epithelium; type 2, Ca(2+) in BCC keratocysts; type 3, BCC tumor necrosis with Ca(2+); and type 4, free Ca(2+) adjacent to BCC. Clinical and pathologic features were assessed and compared with BCC without Ca(2+). Expression of hair-associated proteins (hair keratins (K31, K32, and K35) and matrical transcription factors (LEF1, HOXC13, and ß-catenin) were examined in a subset of BCC with Ca(2+) and compared with matched controls without Ca(2+). RESULTS: Compared with BCC without Ca(2+), BCC with Ca(2+) were significantly more likely to show a nodular keratinizing phenotype with keratocyst formation, background solar elastosis, active regression, and areas of tumor necrosis (all P ≤ 0.03). Comparing all BCC, high-risk BCC (mostly infiltrative) had significantly higher frequency of Ca(2+) than low-risk (mostly nodular) BCC (44% vs. 25%; P = 0.009). The median and mean number of Ca(2+) deposits per specimen were 2 and 3 ± 4, range 1-30. In decreasing frequency, type 2 Ca(2+) (58%), type 4 (53%), type 3 (14%), and type 1 (10%) were found. In 9 cases (11%), type 2 and type 4 Ca(2+) were linearly arranged, ostensibly after a follicular or eccrine duct tract. In 5 cases (6%), initial histologic sections showed type 4 dermal Ca(2+) without evidence of BCC; level sections revealed BCC in the adjacent tissue. Neither BCC with nor BCC without Ca(2+) showed evidence of matrical differentiation by immunophenotypic analysis. CONCLUSIONS: A minority of BCC exhibits Ca(2+) that are associated with BCC-related keratin and/or necrosis. Like other follicular-derived tumors (trichilemmal cyst, pilomatricoma, and trichoepithelioma), BCC produce keratins that are ostensibly predisposed to calcification but are not related to matrical differentiation (mature hair keratin formation). Either due to transtumor elimination or due to tumor regression, Ca(2+) are frequently found free in solar elastotic or fibrotic dermis: a histologic clue in sun-damaged skin to the presence of BCC in the surrounding dermis.

Circulating and disseminated tumor cells in the management of breast cancer.

Despite the advances in early detection and treatment of cancer, patients continue to die of the disease even when they seek care at an early stage. For patients with breast cancer, it is now possible to detect circulating tumor cells (CTCs) in the bloodstream and disseminated tumor cells (DTCs) in the bone marrow by using immunocytochemical and molecular methods. CTCs and DTCs have been found to share similar genotypic and phenotypic characteristics with so-called breast cancer stem cells, a finding that could potentially explain the eventual relapse of disease in a patient previously considered to have been cured by primary therapy. In some studies, the presence of CTCs or DTCs at the time of diagnosis of breast cancer is an independent adverse prognostic variable. However, before CTC/DTC testing can achieve standard-of-care status, there must be improvement in the sensitivity, precision, and reproducibility of the detection methods.

MammaPrint 70-gene signature: another milestone in personalized medical care for breast cancer patients.

The MammaPrint assay (Agendia BV, The Netherlands) is the first fully commercialized microarray-based multigene assay designed to individualize treatment for patients with breast cancer. MammaPrint, the first assay to be cleared at the 510(k) level by the US FDA's new in vitro diagnostic multivariate index assay classification, is offered as a prognostic test for women under the age of 61 years with either estrogen receptor-positive or -negative, lymph node-negative breast cancer. Unlike the Oncotype DX assay (Genomic Health, CA, USA), this test requires freshly prepared tissues collected into an RNA preservative solution. The 70 genes that comprise the MammaPrint assay are focused primarily on proliferation with additional genes associated with invasion, metastasis, stromal integrity and angiogenesis. The Microarray In Node-negative Disease may Avoid Chemotherapy (MINDACT) trial, sponsored by the European Organization for Research and Treatment of Cancer, involves the assessment of patients in the adjuvant treatment setting by the standard clinicopathologic prognostic factors included on Adjuvant! Online and by the 70-gene MammaPrint assay. The following article will consider the basic biology, technology, ease of clinical use, level of clinical validation and potential clinical utility of this test.

The HER-2 receptor and breast cancer: ten years of targeted anti-HER-2 therapy and personalized medicine.

The human epidermal growth factor receptor (HER-2) oncogene encodes a transmembrane tyrosine kinase receptor that has evolved as a major classifier of invasive breast cancer and target of therapy for the disease. The validation of the general prognostic significance of HER-2 gene amplification and protein overexpression in the absence of anti-HER-2 targeted therapy is discussed in a study of 107 published studies involving 39,730 patients, which produced an overall HER-2-positive rate of 22.2% and a mean relative risk for overall survival (OS) of 2.74. The issue of HER-2 status in primary versus metastatic breast cancer is considered along with a section on the features of metastatic HER-2-positive disease. The major marketed slide-based HER-2 testing approaches, immunohistochemistry, fluorescence in situ hybridization, and chromogenic in situ hybridization, are presented and contrasted in detail against the background of the published American Society of Clinical Oncology-College of American Pathologists guidelines for HER-2 testing. Testing issues, such as the impact of chromosome 17 polysomy and local versus central HER-2 testing, are also discussed. Emerging novel HER-2 testing techniques, including mRNA-based testing by real-time polymerase chain reaction and DNA microarray methods, HER-2 receptor dimerization, phosphorylated HER-2 receptors, and HER-2 status in circulating tumor cells, are also considered. A series of biomarkers potentially associated with resistance to trastuzumab is discussed with emphasis on the phosphatase and tensin homologue deleted on chromosome ten/Akt and insulin-like growth factor receptor pathways. The efficacy results for the more recently approved small molecule HER-1/HER-2 kinase inhibitor lapatinib are also presented along with a more limited review of markers of resistance for this agent. Additional topics in this section include combinations of both anti-HER-2 targeted therapies together as well as with novel agents including bevacizumab, everolimus, and tenespimycin. A series of novel HER-2-targeting agents is also presented, including pertuzumab, ertumaxomab, HER-2 vaccines, and recently discovered tyrosine kinase inhibitors. Biomarkers predictive of HER-2 targeted therapy toxicity are included, and the review concludes with a consideration of HER-2 status in the prediction of response to non-HER-2 targeted treatments including hormonal therapy, anthracyclines, and taxanes.