Quantitative assessment and classification of tissue-based biomarker expression with color content analysis

Digital morphometry and cluster analysis identifies four types of melanocyte during uveal melanoma progression

BACKGROUND

Several types of benign and malignant uveal melanocytes have been described based on their histological appearance. However, their characteristics have not been quantified, and their distribution during progression from normal choroidal melanocytes to primary tumors and metastases has not been reported.

METHODS

A total of 1,245,411 digitally scanned melanocytes from normal choroid, choroidal nevi, primary uveal melanomas, and liver metastases were entered into two-step cluster analyses to delineate cell types based on measured morphometric characteristics and expression of protein markers.

RESULTS

Here we show that a combination of the area and circularity of cell nuclei, and BAP-1 expression in nuclei and cytoplasms yields the highest silhouette of cohesion and separation. Normal choroidal melanocytes and three types of uveal melanoma cells are outlined: Epithelioid (large, rounded nuclei; BAP-1 low; IGF-1R, IDO, and TIGIT high), spindle A (small, elongated nuclei; BAP-1 high; IGF-1R low; IDO, and TIGIT intermediate), and spindle B (large, elongated nuclei; BAP-1, IGF-1R, IDO, and TIGIT low). In normal choroidal tissue and nevi, only normal melanocytes and spindle A cells are represented. Epithelioid and spindle B cells are overrepresented in the base and apex, and spindle A cells in the center of primary tumors. Liver metastases contain no normal melanocytes or spindle A cells.

CONCLUSIONS

Four basic cell types can be outlined in uveal melanoma progression: normal, spindle A and B, and epithelioid. Differential expression of tumor suppressors, growth factors, and immune checkpoints could contribute to their relative over- and underrepresentation in benign, primary tumor, and metastatic samples.

Comparing Deep Learning and Immunohistochemistry in Determining the Site of Origin for Well-Differentiated Neuroendocrine Tumors

Background

Determining the site of origin for metastatic well-differentiated neuroendocrine tumors (WDNETs) is challenging, and immunohistochemical (IHC) profiles do not always lead to a definitive diagnosis. We sought to determine if a deep-learning convolutional neural network (CNN) could improve upon established IHC profiles in predicting the site of origin in a cohort of WDNETs from the common primary sites.

Materials and Methods

Hematoxylin and eosin (H&E)-stained tissue microarrays (TMAs) were created using 215 WDNETs arising from the known primary sites. A CNN trained and tested on 60% (n = 130) and 40% (n = 85) of these cases, respectively. One hundred and seventy-nine cases had TMA tissue remaining for the IHC analysis. These cases were stained with IHC markers pPAX8, CDX2, SATB2, and thyroid transcription factor-1 (markers of pancreas/duodenum, ileum/jejunum/duodenum, colorectum/appendix, and lung WDNET sites of origin, respectively). The CNN diagnosis was deemed correct if it designated a majority or plurality of the tumor area as the known site of origin. The IHC diagnosis was deemed correct if the most specific marker for a particular site of origin met an H-score threshold determined by two pathologists.

Results

When all cases were considered, the CNN correctly identified the site of origin at a lower rate compared to IHC (72% vs. 82%, respectively). Of the 85 cases in the CNN test set, 66 had sufficient TMA material for IHC stains, thus 66 cases were available for a direct case-by-case comparison of IHC versus CNN. The CNN correctly identified 70% of these cases, while IHC correctly identified 76%, a finding that was not statistically significant (P = 0.56).

Conclusion

A CNN can identify WDNET site of origin at an accuracy rate close to the current gold standard IHC methods.

Screening for Lynch Syndrome by Immunohistochemistry of Mismatch Repair Proteins: Significance of Indeterminate Result and Correlation With Mutational Studies

CONTEXT.—

Immunohistochemical expression of mismatch repair (MMR) protein is a well-accepted method for routine screening for Lynch syndrome with relatively high sensitivity and specificity. Occasionally, however, immunohistochemistry (IHC) can yield an equivocal result with poor reproducibility and the potential for misdiagnosis.

OBJECTIVE.—

To determine the frequency and significance of indeterminate MMR IHC expression in patients routinely screened for Lynch syndrome and correlation with germline mutation studies.

DESIGN.—

Semiquantitative scoring of MMR IHC was performed by image analysis in 479 cases, of which 380 were colorectal and 99 endometrial cancer. Scores of 10% or more, less than 10%, and 0% were used as cutoffs for retained, indeterminate, and loss of expression, respectively. Negative and indeterminate IHC results were confirmed by mutational studies.

RESULTS.—

Four hundred eighteen of 479 cases (87.2%) were reported as retained expression, 45 (9.3%) as loss of expression, and 16 (3.3%) as indeterminate expression. Fifteen of 45 (33.3%) and 8 of 16 (50%) with loss and indeterminate expression, respectively, were found to have Lynch syndrome by germline studies. The overall frequency of Lynch syndrome in our patient population was 4.8% (23 of 479), and 34.7% of these (8 of 23) were associated with indeterminate IHC expression. In the indeterminate group, MLH1 germline mutation was the most frequent (6 of 13; 46.2%), followed by MSH6 (4 of 13; 30.7%).

CONCLUSIONS.—

Our findings provide further evidence that indeterminate IHC should be further investigated for possible MMR germline mutation. Guidelines for interpretation of MMR IHC and the establishment of more objective criteria for defining indeterminate results are important to improve the sensitivity and specificity of the IHC assay.

A fully automated image analysis method to quantify lung fibrosis in the bleomycin-induced rat model

Intratracheal administration of bleomycin induces fibrosis in the lung, which is mainly assessed by histopathological grading that is subjective. Current literature highlights the need of reproducible and quantitative pulmonary fibrosis analysis. If some quantitative studies looked at fibrosis parameters separately, none of them quantitatively assessed both aspects: lung tissue remodeling and collagenization. To ensure reliable quantification, support vector machine learning was used on digitalized images to design a fully automated method that analyzes two important aspects of lung fibrosis: (i) areas having substantial tissue remodeling with appearance of dense fibrotic masses and (ii) collagen deposition. Fibrotic masses were identified on low magnification images and collagen detection was performed at high magnification. To insure a fully automated application the tissue classifier was trained on several independent studies that were performed over a period of four years. The detection method generates two different values that can be used to quantify lung fibrosis development: (i) percent area of fibrotic masses and (ii) percent of alveolar collagen. These two parameters were validated using independent studies from bleomycin- and saline-treated animals. A significant change of these lung fibrosis quantification parameters- increased amount of fibrotic masses and increased collagen deposition- were observed upon intratracheal administration of bleomycin and subsequent significant beneficial treatments effects were observed with BIBF-1120 and pirfenidone.

Correlation of neuroendocrine features with prognosis of non-small cell lung cancer

The improvement in histological diagnostic tools, including neuroendocrine markers by immunohistochemistry (IHC), has led to increased recognition of non-small cell lung cancer (NSCLC) with neuroendocrine (NE) feature. However, little is known regarding the prevalence and clinical implications of NE feature in patients with NSCLC. In this study, we performed IHC in a tissue microarray containing 451 Chinese NSCLC cases, and analyzed correlation of the expression of neuroendocrine marker with pathological and clinical features of NSCLC. The result showed that NE feature in NSCLC was detectable in almost 30% of studied patients, and tumors with NE feature were significantly correlated with pathological classification, clinical stages and cell differentiation of NSCLC. Our data also revealed that NE feature indicated worse overall survival and disease free survival. Compared with mutant p53, NE markers showed more significance as for prognostic evaluation. Multi-factor COX analysis further suggested a potential clinical impact for NE feature as an independent indicator of poor prognosis for NSCLC patients.

Computer-based image analysis in breast pathology

Whole slide imaging (WSI) has the potential to be utilized in telepathology, teleconsultation, quality assurance, clinical education, and digital image analysis to aid pathologists. In this paper, the potential added benefits of computer-assisted image analysis in breast pathology are reviewed and discussed. One of the major advantages of WSI systems is the possibility of doing computer-based image analysis on the digital slides. The purpose of computer-assisted analysis of breast virtual slides can be (i) segmentation of desired regions or objects such as diagnostically relevant areas, epithelial nuclei, lymphocyte cells, tubules, and mitotic figures, (ii) classification of breast slides based on breast cancer (BCa) grades, the invasive potential of tumors, or cancer subtypes, (iii) prognosis of BCa, or (iv) immunohistochemical quantification. While encouraging results have been achieved in this area, further progress is still required to make computer-based image analysis of breast virtual slides acceptable for clinical practice.

Free digital image analysis software helps to resolve equivocal scores in HER2 immunohistochemistry

Evaluation of human epidermal growth factor receptor 2 (HER2) immunohistochemistry (IHC) is subject to interobserver variation and lack of reproducibility. Digital image analysis (DIA) has been shown to improve the consistency and accuracy of the evaluation and its use is encouraged in current testing guidelines. We studied whether digital image analysis using a free software application (ImmunoMembrane) can assist in interpreting HER2 IHC in equivocal 2+ cases. We also compared digital photomicrographs with whole-slide images (WSI) as material for ImmunoMembrane DIA. We stained 750 surgical resection specimens of invasive breast cancers immunohistochemically for HER2 and analysed staining with ImmunoMembrane. The ImmunoMembrane DIA scores were compared with the originally responsible pathologists' visual scores, a researcher's visual scores and in situ hybridisation (ISH) results. The originally responsible pathologists reported 9.1 % positive 3+ IHC scores, for the researcher this was 8.4 % and for ImmunoMembrane 9.5 %. Equivocal 2+ scores were 34 % for the pathologists, 43.7 % for the researcher and 10.1 % for ImmunoMembrane. Negative 0/1+ scores were 57.6 % for the pathologists, 46.8 % for the researcher and 80.8 % for ImmunoMembrane. There were six false positive cases, which were classified as 3+ by ImmunoMembrane and negative by ISH. Six cases were false negative defined as 0/1+ by IHC and positive by ISH. ImmunoMembrane DIA using digital photomicrographs and WSI showed almost perfect agreement. In conclusion, digital image analysis by ImmunoMembrane can help to resolve a majority of equivocal 2+ cases in HER2 IHC, which reduces the need for ISH testing.

Analysis of the intra- and intertumoral heterogeneity of hypoxia in pancreatic cancer patients receiving the nitroimidazole tracer pimonidazole

Background:

Hypoxia is thought to be an adverse feature of pancreatic cancer, but direct measurement in patients is technically challenging. To address this, we characterised the intra/interpatient heterogeneity of hypoxia in surgical specimens from patients who received the 2-nitroimidazole tracer pimonidazole pre-operatively.

Methods:

Pimondazole was given intravenously 16–20 h before pancreatectomy, and the extent and intratumoral heterogeneity of hypoxia determined by image analysis applied to multiple tissue blocks stained by immunohistochemistry. Intra/interpatient heterogeneity was estimated by variance component analysis.

Results:

Pimonidazole staining was analysed in 10 tumours. The extent of labelling varied amongst patients (0–26%), with a broader range of hypoxia in the epithelial (1–39%) compared with the stromal (1–13%) compartments. Variance component analysis demonstrated greater inter- than intrapatient variability of hypoxia, and that multiple (4–5) tumour sections are required to provide a consistent evaluation of its extent in individual tumours.

Conclusions:

There is significant intra- and intertumoral heterogeneity of hypoxia in pancreatic cancers, and these do not appear to be generally more hypoxic than other cancer types. This study establishes the feasibility to assess hypoxia in pancreatic cancer patients using pimonidazole, but questions the reliability of measurements made using a single tissue section.

Observer performance in the use of digital and optical microscopy for the interpretation of tissue-based biomarkers

BACKGROUND

We conducted a validation study of digital pathology for the quantitative assessment of tissue-based biomarkers with immunohistochemistry.

OBJECTIVE

To examine observer agreement as a function of viewing modality (digital versus optical microscopy), whole slide versus tissue microarray (TMA) review, biomarker type (HER2 incorporating membranous staining and Ki-67 with nuclear staining), and data type (continuous and categorical).

METHODS

Eight pathologists reviewed 50 breast cancer whole slides (25 stained with HER2 and 25 with Ki-67) and 2 TMAs (1 stained with HER2, 1 with Ki-67, each containing 97 cores), using digital and optical microscopy.

RESULTS

Results showed relatively high overall interobserver and intermodality agreement, with different patterns specific to biomarker type. For HER2, there was better interobserver agreement for optical compared to digital microscopy for whole slides as well as better interobserver and intermodality agreement for TMAs. For Ki-67, those patterns were not observed.

CONCLUSIONS

The differences in agreement patterns when examining different biomarkers and different scoring methods and reviewing whole slides compared to TMA stress the need for validation studies focused on specific pathology tasks to eliminate sources of variability that might dilute findings. The statistical uncertainty observed in our analyses calls for adequate sampling for each individual task rather than pooling cases.

Reproducibility in the automated quantitative assessment of HER2/neu for breast cancer

Background:

With the emerging role of digital imaging in pathology and the application of automated image-based algorithms to a number of quantitative tasks, there is a need to examine factors that may affect the reproducibility of results. These factors include the imaging properties of whole slide imaging (WSI) systems and their effect on the performance of quantitative tools. This manuscript examines inter-scanner and inter-algorithm variability in the assessment of the commonly used HER2/neu tissue-based biomarker for breast cancer with emphasis on the effect of algorithm training.

Materials and Methods:

A total of 241 regions of interest from 64 breast cancer tissue glass slides were scanned using three different whole-slide images and were analyzed using two different automated image analysis algorithms, one with preset parameters and another incorporating a procedure for objective parameter optimization. Ground truth from a panel of seven pathologists was available from a previous study. Agreement analysis was used to compare the resulting HER2/neu scores.

Results:

The results of our study showed that inter-scanner agreement in the assessment of HER2/neu for breast cancer in selected fields of view when analyzed with any of the two algorithms examined in this study was equal or better than the inter-observer agreement previously reported on the same set of data. Results also showed that discrepancies observed between algorithm results on data from different scanners were significantly reduced when the alternative algorithm that incorporated an objective re-training procedure was used, compared to the commercial algorithm with preset parameters.

Conclusion:

Our study supports the use of objective procedures for algorithm training to account for differences in image properties between WSI systems.