Novel histopathologic feature identified through image analysis augments stage II colorectal cancer clinical reporting

Artificial intelligence-based morphological fingerprinting of megakaryocytes: a new tool for assessing disease in MPN patients

Accurate diagnosis and classification of myeloproliferative neoplasms (MPNs) requires integration of clinical, morphological, and genetic findings. Despite major advances in our understanding of the molecular and genetic basis of MPNs, the morphological assessment of bone marrow trephines (BMT) is critical in differentiating MPN subtypes and their reactive mimics. However, morphological assessment is heavily constrained by a reliance on subjective, qualitative, and poorly reproducible criteria. To improve the morphological assessment of MPNs, we have developed a machine learning approach for the automated identification, quantitative analysis, and abstract representation of megakaryocyte features using reactive/nonneoplastic BMT samples (n = 43) and those from patients with established diagnoses of essential thrombocythemia (n = 45), polycythemia vera (n = 18), or myelofibrosis (n = 25). We describe the application of an automated workflow for the identification and delineation of relevant histological features from routinely prepared BMTs. Subsequent analysis enabled the tissue diagnosis of MPN with a high predictive accuracy (area under the curve = 0.95) and revealed clear evidence of the potential to discriminate between important MPN subtypes. Our method of visually representing abstracted megakaryocyte features in the context of analyzed patient cohorts facilitates the interpretation and monitoring of samples in a manner that is beyond conventional approaches. The automated BMT phenotyping approach described here has significant potential as an adjunct to standard genetic and molecular testing in established or suspected MPN patients, either as part of the routine diagnostic pathway or in the assessment of disease progression/response to treatment.

Automated Detection and Classification of Desmoplastic Reaction at the Colorectal Tumour Front Using Deep Learning

The categorisation of desmoplastic reaction (DR) present at the colorectal cancer (CRC) invasive front into mature, intermediate or immature type has been previously shown to have high prognostic significance. However, the lack of an objective and reproducible assessment methodology for the assessment of DR has been a major hurdle to its clinical translation. In this study, a deep learning algorithm was trained to automatically classify immature DR on haematoxylin and eosin digitised slides of stage II and III CRC cases (n = 41). When assessing the classifier's performance on a test set of patient samples (n = 40), a Dice score of 0.87 for the segmentation of myxoid stroma was reported. The classifier was then applied to the full cohort of 528 stage II and III CRC cases, which was then divided into a training (n = 396) and a test set (n = 132). Automatically classed DR was shown to have superior prognostic significance over the manually classed DR in both the training and test cohorts. The findings demonstrated that deep learning algorithms could be applied to assist pathologists in the detection and classification of DR in CRC in an objective, standardised and reproducible manner.

Poorly differentiated clusters in colorectal cancer: a current review and implications for future practice

Poorly differentiated clusters (PDC), defined as small groups of ≥5 tumour cells without glandular differentiation, have gained recent attention as a promising prognostic factor in colorectal cancer (CRC). Numerous studies have shown PDC to be significantly associated with other adverse histopathological features and worse clinical outcomes. PDC may hold particular promise in stage II colon cancer, where risk stratification plays a critical role in patient selection for adjuvant chemotherapy. In addition, emerging evidence suggests that PDC can predict lymph node metastasis in endoscopically resected pT1 CRC, potentially helping the selection of patients for oncological resection. In 'head-to-head' comparisons, PDC grade has consistently outperformed conventional histological grading systems both in terms of risk stratification and reproducibility. With a number of large-scale studies now available, this review evaluates the evidence regarding the prognostic significance of PDC, considers its relationship with other emerging invasive front prognostic markers (such as tumour budding and stroma type), assesses its 'practice readiness', addressing issues such as interobserver reproducibility, scoring methodologies and special histological subtypes (e.g. micropapillary and mucinous carcinoma), and draws attention to ongoing challenges and areas in need of further study. Finally, emerging data on the role of PDC in non-colorectal cancers are briefly considered.

A high-throughput digital script for multiplexed immunofluorescent analysis and quantification of sarcolemmal and sarcomeric proteins in muscular dystrophies

The primary molecular endpoint for many Duchenne muscular dystrophy (DMD) clinical trials is the induction, or increase in production, of dystrophin protein in striated muscle. For accurate endpoint analysis, it is essential to have reliable, robust and objective quantification methodologies capable of detecting subtle changes in dystrophin expression. In this work, we present further development and optimisation of an automated, digital, high-throughput script for quantitative analysis of multiplexed immunofluorescent (IF) whole slide images (WSI) of dystrophin, dystrophin associated proteins (DAPs) and regenerating myofibres (fetal/developmental myosin-positive) in transverse sections of DMD, Becker muscular dystrophy (BMD) and control skeletal muscle biopsies. The script enables extensive automated assessment of myofibre morphometrics, protein quantification by fluorescence intensity and sarcolemmal circumference coverage, colocalisation data for dystrophin and DAPs and regeneration at the single myofibre and whole section level. Analysis revealed significant variation in dystrophin intensity, percentage coverage and amounts of DAPs between differing DMD and BMD samples. Accurate identification of dystrophin via a novel background subtraction method allowed differential assessment of DAP fluorescence intensity within dystrophin positive compared to dystrophin negative sarcolemma regions. This enabled surrogate quantification of molecular functionality of dystrophin in the assembly of the DAP complex. Overall, the digital script is capable of multiparametric and unbiased analysis of markers of myofibre regeneration and dystrophin in relation to key DAPs and enabled better characterisation of the heterogeneity in dystrophin expression patterns seen in BMD and DMD alongside the surrogate assessment of molecular functionality of dystrophin. Both these aspects will be of significant relevance to ongoing and future DMD and other muscular dystrophies clinical trials to help benchmark therapeutic efficacy.

Deep learning assessment of breast terminal duct lobular unit involution: Towards automated prediction of breast cancer risk

Terminal duct lobular unit (TDLU) involution is the regression of milk-producing structures in the breast. Women with less TDLU involution are more likely to develop breast cancer. A major bottleneck in studying TDLU involution in large cohort studies is the need for labor-intensive manual assessment of TDLUs. We developed a computational pathology solution to automatically capture TDLU involution measures. Whole slide images (WSIs) of benign breast biopsies were obtained from the Nurses' Health Study. A set of 92 WSIs was annotated for acini, TDLUs and adipose tissue to train deep convolutional neural network (CNN) models for detection of acini, and segmentation of TDLUs and adipose tissue. These networks were integrated into a single computational method to capture TDLU involution measures including number of TDLUs per tissue area, median TDLU span and median number of acini per TDLU. We validated our method on 40 additional WSIs by comparing with manually acquired measures. Our CNN models detected acini with an F1 score of 0.73±0.07, and segmented TDLUs and adipose tissue with Dice scores of 0.84±0.13 and 0.87±0.04, respectively. The inter-observer ICC scores for manual assessments on 40 WSIs of number of TDLUs per tissue area, median TDLU span, and median acini count per TDLU were 0.71, 0.81 and 0.73, respectively. Intra-observer reliability was evaluated on 10/40 WSIs with ICC scores of >0.8. Inter-observer ICC scores between automated results and the mean of the two observers were: 0.80 for number of TDLUs per tissue area, 0.57 for median TDLU span, and 0.80 for median acini count per TDLU. TDLU involution measures evaluated by manual and automated assessment were inversely associated with age and menopausal status. We developed a computational pathology method to measure TDLU involution. This technology eliminates the labor-intensiveness and subjectivity of manual TDLU assessment, and can be applied to future breast cancer risk studies.

Novel Internationally Verified Method Reports Desmoplastic Reaction as the Most Significant Prognostic Feature For Disease-specific Survival in Stage II Colorectal Cancer

Multiple histopathologic features have been reported as candidates for predicting aggressive stage II colorectal cancer (CRC). These include tumor budding (TB), poorly differentiated clusters (PDC), Crohn-like lymphoid reaction and desmoplastic reaction (DR) categorization. Although their individual prognostic significance has been established, their association with disease-specific survival (DSS) has not been compared in stage II CRC. This study aimed to evaluate and compare the prognostic value of the above features in a Japanese (n=283) and a Scottish (n=163) cohort, as well as to compare 2 different reporting methodologies: analyzing each feature from across every tissue slide from the whole tumor and a more efficient methodology reporting each feature from a single slide containing the deepest tumor invasion. In the Japanese cohort, there was an excellent agreement between the multi-slide and single-slide methodologies for TB, PDC, and DR (κ=0.798 to 0.898) and a good agreement when assessing Crohn-like lymphoid reaction (κ=0.616). TB (hazard ratio [HR]=1.773; P=0.016), PDC (HR=1.706; P=0.028), and DR (HR=2.982; P<0.001) based on the single-slide method were all significantly associated with DSS. DR was the only candidate feature reported to be a significant independent prognostic factor (HR=2.982; P<0.001) with both multi-slide and single-slide methods. The single-slide result was verified in the Scottish cohort, where multivariate Cox regression analysis reported that DR was the only significant independent feature (HR=1.778; P=0.002) associated with DSS. DR was shown to be the most significant of all the analyzed histopathologic features to predict disease-specific death in stage II CRC. We further show that analyzing the features from a single-slide containing the tumor's deepest invasion is an efficient and quicker method of evaluation.

MCCC2 overexpression predicts poorer prognosis and promotes cell proliferation in colorectal cancer

PURPOSES

Recently, Methylcrotonoyl-CoA carboxylase 2 (MCCC2) is reported to be involved in tumor formation and progression. However, MCCC2 has nerve been reported in colorectal cancer. In this study, we aimed to investigate the role of MCCC2 in colorectal cancer.

METHODS

118 colorectal cancer and matched adjacent normal tissues were enrolled in this study. The expression level of MCCC2 was measured by quantificational real-time polymerase chain reaction (qRT-PCR) and immunohistochemistry (IHC). The clinical significance of MCCC2 and its influence on cell proliferation was further analyzed.

RESULTS

Results shown that the mRNA levels of MCCC2 in colorectal cancer tissues were significantly increased compared with those in normal tissues (P < .0001). MCCC2 high-expression was observed in 56.8% colorectal cancer tissues, which was significantly higher than those in normal controls (9.3%, P < .0001). MCCC2 high-expression correlated with tumor size, T stage, lymph node metastasis, distant metastasis, clinical stage and differentiation in colorectal cancer (P < .05). Moreover, MCCC2 high-expression predicted poorer prognosis and could be as an independent prognostic factor. In addition, MCCC2 knockdown significantly inhibited cell proliferation compared with these controls, while MCCC2 overexpression could reverse the effect.

CONCLUSION

These data indicate MCCC2 overexpression promotes cell proliferation and predicts poorer prognosis in colorectal cancer.

Prognostic significance of mesothelin expression in colorectal cancer disclosed by area-specific four-point tissue microarrays

Mesothelin (MSLN) is a cell surface glycoprotein present in many cancer types. Its expression is generally associated with an unfavorable prognosis. This study examined the prognostic significance of MSLN expression in different areas of individual colorectal cancers (CRCs) using tissue microarrays (TMAs) by enrolling 314 patients with stage II (T3-T4, N0, M0) CRCs. Using formalin-fixed paraffin-embedded tissue blocks from patients, TMA blocks were constructed. Tissue core specimens were obtained from submucosal invasive front (Fr-sm), subserosal invasive front (Fr-ss), central area (Ce), and rolled edge (Ro) of each tumor. Using these four-point TMA sets, MSLN expression was immunohistochemically surveyed. The area-specific prognostic significance of MSLN expression was evaluated. A deep learning convolutional neural network algorithm was used for imaging analysis and evaluating our judgment's objectivity. MSLN staining ratio was positively correlated between the manual and machine-learning analyses (r = 0.71). The correlation coefficient between Ro and Ce, Ro and Fr-sm, and Ro and Fr-ss was r = 0.63, r = 0.54, and r = 0.61, respectively. Disease-specific survival curves for the MSLN-positive and MSLN-negative groups in Fr-sm, Fr-ss, and Ro were significantly different (five-year survival rates 88.1% and 95.5% (P = 0.024), 85.0 and 96.2% (P = 0.0087), 87.8 and 95.5% (P = 0.051), and 77.9 and 95.8% (P = 0.046) for Fr-sm, Fr-ss, Ce, and Ro, respectively). The analysis performed using area-specific four-point TMAs clearly demonstrated that MSLN expression in stage II CRC was relatively homogeneous within tumors. Additionally, high MSLN expression showed or tended to show unfavorable prognostic significance regardless of the tumor area.

Deep Learning for Whole Slide Image Analysis: An Overview

The widespread adoption of whole slide imaging has increased the demand for effective and efficient gigapixel image analysis. Deep learning is at the forefront of computer vision, showcasing significant improvements over previous methodologies on visual understanding. However, whole slide images have billions of pixels and suffer from high morphological heterogeneity as well as from different types of artifacts. Collectively, these impede the conventional use of deep learning. For the clinical translation of deep learning solutions to become a reality, these challenges need to be addressed. In this paper, we review work on the interdisciplinary attempt of training deep neural networks using whole slide images, and highlight the different ideas underlying these methodologies.

Specific immune cell and lymphatic vessel signatures identified by image analysis in renal cancer

Anti-angiogenic therapy and immune checkpoint inhibition are novel treatment strategies for patients with renal cell carcinoma. Various components and structures of the tumor microenvironment are potential predictive biomarkers and also attractive treatment targets. Macrophages, tumor infiltrating lymphocytes, vascular and lymphatic vessels represent an important part of the tumor immune environment, but their functional phenotypes and relevance for clinical outcome are yet ill defined. We applied Tissue Phenomics methods including image analysis for the standardized quantification of specific components and structures within the tumor microenvironment to profile tissue sections from 56 clear cell renal cell carcinoma patients. A characteristic composition and unique spatial relationship of CD68+ macrophages and tumor infiltrating lymphocytes correlated with overall survival. An inverse relationship was found between vascular (CD34) and lymphatic vessel (LYVE1) density. In addition, outcome was significantly better in patients with high blood vessel density in the tumors, whereas increased lymphatic vessel density in the tumors was associated with worse outcome. The Tissue Phenomics imaging analysis approach allowed visualization and simultaneous quantification of immune environment components, adding novel contextual information, and biological insights with potential applications in treatment response prediction.

Automated tumour budding quantification by machine learning augments TNM staging in muscle-invasive bladder cancer prognosis

Tumour budding has been described as an independent prognostic feature in several tumour types. We report for the first time the relationship between tumour budding and survival evaluated in patients with muscle invasive bladder cancer. A machine learning-based methodology was applied to accurately quantify tumour buds across immunofluorescence labelled whole slide images from 100 muscle invasive bladder cancer patients. Furthermore, tumour budding was found to be correlated to TNM (p = 0.00089) and pT (p = 0.0078) staging. A novel classification and regression tree model was constructed to stratify all stage II, III, and IV patients into three new staging criteria based on disease specific survival. For the stratification of non-metastatic patients into high or low risk of disease specific death, our decision tree model reported that tumour budding was the most significant feature (HR = 2.59, p = 0.0091), and no clinical feature was utilised to categorise these patients. Our findings demonstrate that tumour budding, quantified using automated image analysis provides prognostic value for muscle invasive bladder cancer patients and a better model fit than TNM staging.

Automated Analysis of Lymphocytic Infiltration, Tumor Budding, and Their Spatial Relationship Improves Prognostic Accuracy in Colorectal Cancer

Both immune profiling and tumor budding significantly correlate with colorectal cancer patient outcome but are traditionally reported independently. This study evaluated the association and interaction between lymphocytic infiltration and tumor budding, coregistered on a single slide, in order to determine a more precise prognostic algorithm for patients with stage II colorectal cancer. Multiplexed immunofluorescence and automated image analysis were used for the quantification of CD3⁺CD8⁺ T cells, and tumor buds (TBs), across whole slide images of three independent cohorts (training cohort: n = 114, validation cohort 1: n = 56, validation cohort 2: n = 62). Machine learning algorithms were used for feature selection and prognostic risk model development. High numbers of TBs [HR = 5.899; 95% confidence interval (CI) 1.875-18.55], low CD3⁺ T-cell density (HR = 9.964; 95% CI, 3.156-31.46), and low mean number of CD3⁺CD8⁺ T cells within 50 μm of TBs (HR = 8.907; 95% CI, 2.834-28.0) were associated with reduced disease-specific survival. A prognostic signature, derived from integrating TBs, lymphocyte infiltration, and their spatial relationship, reported a more significant cohort stratification (HR = 18.75; 95% CI, 6.46-54.43), than TBs, Immunoscore, or pT stage. This was confirmed in two independent validation cohorts (HR = 12.27; 95% CI, 3.524-42.73; HR = 15.61; 95% CI, 4.692-51.91). The investigation of the spatial relationship between lymphocytes and TBs within the tumor microenvironment improves accuracy of prognosis of patients with stage II colorectal cancer through an automated image analysis and machine learning workflow.

Identifying prognostic structural features in tissue sections of colon cancer patients using point pattern analysis

Diagnosis and prognosis of cancer are informed by the architecture inherent in cancer patient tissue sections. This architecture is typically identified by pathologists, yet advances in computational image analysis facilitate quantitative assessment of this structure. In this article, we develop a spatial point process approach to describe patterns in cell distribution within tissue samples taken from colorectal cancer (CRC) patients. In particular, our approach is centered on the Palm intensity function. This leads to taking an approximate-likelihood technique in fitting point processes models. We consider two Neyman-Scott point processes and a void process, fitting these point process models to the CRC patient data. We find that the parameter estimates of these models may be used to quantify the spatial arrangement of cells. Importantly, we observe characteristic differences in the spatial arrangement of cells between patients who died from CRC and those alive at follow up.

A principled machine learning framework improves accuracy of stage II colorectal cancer prognosis

Accurate prognosis is fundamental in planning an appropriate therapy for cancer patients. Consequent to the heterogeneity of the disease, intra- and inter-pathologist variability, and the inherent limitations of current pathological reporting systems, patient outcome varies considerably within similarly staged patient cohorts. This is particularly true when classifying stage II colorectal cancer patients using the current TNM guidelines. The aim of the present work is to address this problem through the use of machine learning. In particular, we introduce a data driven framework which makes use of a large number of diverse types of features, readily collected from immunofluorescence imagery. Its outstanding performance in predicting mortality in stage II patients (AUROC = 0:94), exceeds that of current clinical guidelines such as pT stage (AUROC = 0:65), and is demonstrated on a cohort of 173 colorectal cancer patients.

Measuring multiple parameters of CD8+ tumor-infiltrating lymphocytes in human cancers by image analysis

BACKGROUND

Immuno-oncology and cancer immunotherapies are areas of intense research. The numbers and locations of CD8+ tumor-infiltrating lymphocytes (TILs) are important measures of the immune response to cancer with prognostic, pharmacodynamic, and predictive potential. We describe the development, validation, and application of advanced image analysis methods to characterize multiple immunohistochemistry-derived CD8 parameters in clinical and nonclinical tumor tissues.

METHODS

Commercial resection tumors from nine cancer types, and paired screening/on-drug biopsies of non-small-cell lung carcinoma (NSCLC) patients enrolled in a phase 1/2 clinical trial investigating the PD-L1 antibody therapy durvalumab (NCT01693562), were immunostained for CD8. Additional NCT01693562 samples were immunostained with a CD8/PD-L1 dual immunohistochemistry assay. Whole-slide scanning was performed, tumor regions were annotated by a pathologist, and images were analyzed with customized algorithms using Definiens Developer XD software. Validation of image analysis data used cell-by-cell comparison to pathologist scoring across a range of CD8+ TIL densities of all nine cancers, relying primarily on 95% confidence in having at least moderate agreement regarding Lin concordance correlation coefficient (CCC = 0.88-0.99, CCC_lower = 0.65-0.96).

RESULTS

We found substantial variability in CD8+ TILs between individual patients and across the nine types of human cancer. Diffuse large B-cell lymphoma had several-fold more CD8+ TILs than some other cancers. TIL densities were significantly higher in the invasive margin versus tumor center for carcinomas of head and neck, kidney and pancreas, and NSCLC; the reverse was true only for prostate cancer. In paired patient biopsies, there were significantly increased CD8+ TILs 6 weeks after onset of durvalumab therapy (mean of 365 cells/mm2 over baseline; P = 0.009), consistent with immune activation. Image analysis accurately enumerated CD8+ TILs in PD-L1+ regions of lung tumors using the dual assay and also measured elongate CD8+ lymphocytes which constituted a fraction of overall TILs.

CONCLUSIONS

Validated image analysis accurately enumerates CD8+ TILs, permitting comparisons of CD8 parameters among tumor regions, individual patients, and cancer types. It also enables the more complex digital solutions needed to better understand cancer immunity, like analysis of multiplex immunohistochemistry and spatial evaluation of the various components comprising the tumor microenvironment.

TRIAL REGISTRATION

ClinicalTrials.gov identifier: NCT01693562 . Study code: CD-ON-MEDI4736-1108. Interventional study (ongoing but not currently recruiting). Actual study start date: August 29, 2012. Primary completion date: June 23, 2017 (final data collection date for primary outcome measure).

Nuclear features of infiltrating urothelial carcinoma are distinguished from low-grade noninvasive papillary urothelial carcinoma by image analysis

Recent advances in computer technology have been made and image analysis (IA) has been introduced into pathological fields. The present study aimed to investigate the utility of IA for the evaluation of nuclear features and staining of immunohistochemistry (IHC) for Ki-67, p53 and GATA-binding protein 3 (GATA-3) in urothelial carcinoma tissue samples. A total of 49 cases of urothelial carcinoma tissue samples were obtained by transurethral resection of bladder tumors, which included 11 low-grade papillary urothelial carcinomas (LGPUCs), 1 non-invasive high-grade urothelial carcinoma and 37 infiltrating urothelial carcinomas (IUCs). Whole slide imaging (WSI) and IA were performed in Feulgen reaction and IHC-stained tissue samples. There was a significant difference in the average nuclear density, standard deviation (SD) of nuclear size and SD of nuclear minimum and maximum diameter between LGPUC and IUC, which is equivalent to the diagnostic features of IUC in nuclear variability, and hyperchromatic nuclei. In addition, the present study revealed that the SD of nuclear density was significantly different between the two groups. Regarding IA in IHC-stained tissue samples, Ki-67 was significantly overexpressed in IUC. Furthermore, the GATA-3 expression level in IUC samples with muscle invasion was significantly downregulated compared with that in non-muscle invasive tumors. The results of the present study suggest that IA in combination with WSI may be a beneficial tool for evaluating morphometric characteristics and performing semi-quantitative analysis of IHC.