Submit to Cancers Review for Cancers Propose a Special Issue

Journal Browser

► Journal Browser

Surgical Pathology in the Digital Era

Special Issue Editors
Special Issue Information
Keywords
Published Papers

A special issue of Cancers (ISSN 2072-6694). This special issue belongs to the section "Cancer Pathophysiology".

Deadline for manuscript submissions: closed (31 May 2021) | Viewed by 40776

Share This Special Issue

Special Issue Editor

Dr. Francesco Merolla

E-Mail Website
Guest Editor

Department of Medicine and Health Sciences “V. Tiberio”, University of Molise, Via F. Crispi, 86100 Campobasso, CB, Italy
Interests: pathology; molecular pathology; molecular oncology; digital pathology; computer science; artificial intelligence

Special Issue Information

Dear Colleagues,

Digital pathology is a dynamic information environment based on the acquisition, management, and interpretation of pathology information generated from a digitized glass slide.

The increasing interest in the field and the implementation of digital workflow in pathology facilities is leading to the larger and larger datasets that are used to train computational approaches based on artificial intelligence algorithms.

AI-algorithms hold the promise to transform the way pathologists will face the diagnosis and the assessment of prognostic and predictive markers of human tumors. AI can provide the pathologists with powerful tools in primary diagnosis and tumor risk stratification, e.g., in correcting potential bias in the interpretation of immunohistochemistry signals, calculating correlations between image-extracted features and patients’ outcome, and quantifying stromal features that are not traditionally assessed, not even visible by human eyes. Furthermore, if properly trained, the computational approach has also proved to classify the histologic images with a high degree of accuracy.

This Special Issue of Cancers is focused on new research articles and timely reviews on all aspects of Digital Pathology as applied to the study and characterization of human cancers.

Prof. Francesco Merolla
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Cancers is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2900 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

digital pathology
pathology
machine learning
deep learning
artificial intelligence
cancer biomarkers

Published Papers (9 papers)

Download All Papers

Research

11 pages, 3415 KiB

Open AccessArticle

Deep Learning for Automatic Subclassification of Gastric Carcinoma Using Whole-Slide Histopathology Images

by Hyun-Jong Jang, In-Hye Song and Sung-Hak Lee

Cancers 2021, 13(15), 3811; https://doi.org/10.3390/cancers13153811 - 29 Jul 2021

Cited by 10 | Viewed by 2976

Abstract

Histomorphologic types of gastric cancer (GC) have significant prognostic values that should be considered during treatment planning. Because the thorough quantitative review of a tissue slide is a laborious task for pathologists, deep learning (DL) can be a useful tool to support pathologic workflow. In the present study, a fully automated approach was applied to distinguish differentiated/undifferentiated and non-mucinous/mucinous tumor types in GC tissue whole-slide images from The Cancer Genome Atlas (TCGA) stomach adenocarcinoma dataset (TCGA-STAD). By classifying small patches of tissue images into differentiated/undifferentiated and non-mucinous/mucinous tumor tissues, the relative proportion of GC tissue subtypes can be easily quantified. Furthermore, the distribution of different tissue subtypes can be clearly visualized. The patch-level areas under the curves for the receiver operating characteristic curves for the differentiated/undifferentiated and non-mucinous/mucinous classifiers were 0.932 and 0.979, respectively. We also validated the classifiers on our own GC datasets and confirmed that the generalizability of the classifiers is excellent. The results indicate that the DL-based tissue classifier could be a useful tool for the quantitative analysis of cancer tissue slides. By combining DL-based classifiers for various molecular and morphologic variations in tissue slides, the heterogeneity of tumor tissues can be unveiled more efficiently. Full article

(This article belongs to the Special Issue Surgical Pathology in the Digital Era)

► Show Figures

Figure 1

22 pages, 13620 KiB

Open AccessArticle

Global Chromatin Changes Resulting from Single-Gene Inactivation—The Role of SMARCB1 in Malignant Rhabdoid Tumor

by Colin Kenny, Elaine O’Meara, Mevlüt Ulaş, Karsten Hokamp and Maureen J. O’Sullivan

Cancers 2021, 13(11), 2561; https://doi.org/10.3390/cancers13112561 - 23 May 2021

Cited by 5 | Viewed by 3619

Abstract

Human cancer typically results from the stochastic accumulation of multiple oncogene-activating and tumor-suppressor gene-inactivating mutations. However, this process takes time and especially in the context of certain pediatric cancer, fewer but more ‘impactful’ mutations may in short order produce the full-blown cancer phenotype. This is well exemplified by the highly aggressive malignant rhabdoid tumor (MRT), where the only gene classically showing recurrent inactivation is SMARCB1, a subunit member of the BAF chromatin-remodeling complex. This is true of all three presentations of MRT including MRT of kidney (MRTK), MRT of the central nervous system (atypical teratoid rhabdoid tumor—ATRT) and extracranial, extrarenal rhabdoid tumor (EERT). Our reverse modeling of rhabdoid tumors with isogenic cell lines, either induced or not induced, to express SMARCB1 showed widespread differential chromatin remodeling indicative of altered BAF complex activity with ensuant histone modifications when tested by chromatin immunoprecipitation followed by sequencing (ChIP-seq). The changes due to reintroduction of SMARCB1 were preponderantly at typical enhancers with tandem BAF complex occupancy at these sites and related gene activation, as substantiated also by transcriptomic data. Indeed, for both MRTK and ATRT cells, there is evidence of an overlap between SMARCB1-dependent enhancer activation and tissue-specific lineage-determining genes. These genes are inactive in the tumor state, conceivably arresting the cells in a primitive/undifferentiated state. This epigenetic dysregulation from inactivation of a chromatin-remodeling complex subunit contributes to an improved understanding of the complex pathophysiological basis of MRT, one of the most lethal and aggressive human cancers. Full article

(This article belongs to the Special Issue Surgical Pathology in the Digital Era)

► Show Figures

Figure 1

12 pages, 5661 KiB

Open AccessArticle

PD-L1 Multiplex and Quantitative Image Analysis for Molecular Diagnostics

by Fatima Abdullahi Sidi, Victoria Bingham, Stephanie G. Craig, Stephen McQuaid, Jacqueline James, Matthew P. Humphries and Manuel Salto-Tellez

Cancers 2021, 13(1), 29; https://doi.org/10.3390/cancers13010029 - 23 Dec 2020

Cited by 12 | Viewed by 5815

Abstract

Multiplex immunofluorescence (mIF) and digital image analysis (DIA) have transformed the ability to analyse multiple biomarkers. We aimed to validate a clinical workflow for quantifying PD-L1 in non-small cell lung cancer (NSCLC). NSCLC samples were stained with a validated mIF panel. Immunohistochemistry (IHC) was conducted and mIF slides were scanned on an Akoya Vectra Polaris. Scans underwent DIA using QuPath. Single channel immunofluorescence was concordant with single-plex IHC. DIA facilitated quantification of cell types expressing single or multiple phenotypic markers. Considerations for analysis included classifier accuracy, macrophage infiltration, spurious staining, threshold sensitivity by DIA, sensitivity of cell identification in the mIF. Alternative sequential detection of biomarkers by DIA potentially impacted final score. Strong concordance was observed between 3,3’-Diaminobenzidine (DAB) IHC slides and mIF slides (R² = 0.7323). Comparatively, DIA on DAB IHC was seen to overestimate the PD-L1 score more frequently than on mIF slides. Overall, concordance between DIA on DAB IHC slides and mIF slides was 95%. DIA of mIF slides is rapid, highly comparable to DIA on DAB IHC slides, and enables comprehensive extraction of phenotypic data and specific microenvironmental detail intrinsic to the sample. Exploration of the clinical relevance of mIF in the context of immunotherapy treated cases is warranted. Full article

(This article belongs to the Special Issue Surgical Pathology in the Digital Era)

► Show Figures

Figure 1

12 pages, 1928 KiB

Open AccessArticle

Deep Learning Predicts Underlying Features on Pathology Images with Therapeutic Relevance for Breast and Gastric Cancer

by Renan Valieris, Lucas Amaro, Cynthia Aparecida Bueno de Toledo Osório, Adriana Passos Bueno, Rafael Andres Rosales Mitrowsky, Dirce Maria Carraro, Diana Noronha Nunes, Emmanuel Dias-Neto and Israel Tojal da Silva

Cancers 2020, 12(12), 3687; https://doi.org/10.3390/cancers12123687 - 9 Dec 2020

Cited by 30 | Viewed by 5355

Abstract

DNA repair deficiency (DRD) is an important driver of carcinogenesis and an efficient target for anti-tumor therapies to improve patient survival. Thus, detection of DRD in tumors is paramount. Currently, determination of DRD in tumors is dependent on wet-lab assays. Here we describe an efficient machine learning algorithm which can predict DRD from histopathological images. The utility of this algorithm is demonstrated with data obtained from 1445 cancer patients. Our method performs rather well when trained on breast cancer specimens with homologous recombination deficiency (HRD), AUC (area under curve) = 0.80. Results for an independent breast cancer cohort achieved an AUC = 0.70. The utility of our method was further shown by considering the detection of mismatch repair deficiency (MMRD) in gastric cancer, yielding an AUC = 0.81. Our results demonstrate the capacity of our learning-base system as a low-cost tool for DRD detection. Full article

(This article belongs to the Special Issue Surgical Pathology in the Digital Era)

► Show Figures

Figure 1

15 pages, 4316 KiB

Open AccessArticle

Single-Cell Spatial Analysis of Tumor and Immune Microenvironment on Whole-Slide Image Reveals Hepatocellular Carcinoma Subtypes

by Haiyue Wang, Yuming Jiang, Bailiang Li, Yi Cui, Dengwang Li and Ruijiang Li

Cancers 2020, 12(12), 3562; https://doi.org/10.3390/cancers12123562 - 28 Nov 2020

Cited by 19 | Viewed by 4406

Abstract

Hepatocellular carcinoma (HCC) is a heterogeneous disease with diverse characteristics and outcomes. Here, we aim to develop a histological classification for HCC by integrating computational imaging features of the tumor and its microenvironment. We first trained a multitask deep-learning neural network for automated single-cell segmentation and classification on hematoxylin- and eosin-stained tissue sections. After confirming the accuracy in a testing set, we applied the model to whole-slide images of 304 tumors in the Cancer Genome Atlas. Given the single-cell map, we calculated 246 quantitative image features to characterize individual nuclei as well as spatial relations between tumor cells and infiltrating lymphocytes. Unsupervised consensus clustering revealed three reproducible histological subtypes, which exhibit distinct nuclear features as well as spatial distribution and relation between tumor cells and lymphocytes. These histological subtypes were associated with somatic genomic alterations (i.e., aneuploidy) and specific molecular pathways, including cell cycle progression and oxidative phosphorylation. Importantly, these histological subtypes complement established molecular classification and demonstrate independent prognostic value beyond conventional clinicopathologic factors. Our study represents a step forward in quantifying the spatial distribution and complex interaction between tumor and immune microenvironment. The clinical relevance of the imaging subtypes for predicting prognosis and therapy response warrants further validation. Full article

(This article belongs to the Special Issue Surgical Pathology in the Digital Era)

► Show Figures

Figure 1

13 pages, 1936 KiB

Open AccessArticle

Integrative Data Augmentation with U-Net Segmentation Masks Improves Detection of Lymph Node Metastases in Breast Cancer Patients

by Yong Won Jin, Shuo Jia, Ahmed Bilal Ashraf and Pingzhao Hu

Cancers 2020, 12(10), 2934; https://doi.org/10.3390/cancers12102934 - 12 Oct 2020

Cited by 26 | Viewed by 4416

Abstract

Deep learning models have potential to improve performance of automated computer-assisted diagnosis tools in digital histopathology and reduce subjectivity. The main objective of this study was to further improve diagnostic potential of convolutional neural networks (CNNs) in detection of lymph node metastasis in breast cancer patients by integrative augmentation of input images with multiple segmentation channels. For this retrospective study, we used the PatchCamelyon dataset, consisting of 327,680 histopathology images of lymph node sections from breast cancer. Images had labels for the presence or absence of metastatic tissue. In addition, we used four separate histopathology datasets with annotations for nucleus, mitosis, tubule, and epithelium to train four instances of U-net. Then our baseline model was trained with and without additional segmentation channels and their performances were compared. Integrated gradient was used to visualize model attribution. The model trained with concatenation/integration of original input plus four additional segmentation channels, which we refer to as ConcatNet, was superior (AUC 0.924) compared to baseline with or without augmentations (AUC 0.854; 0.884). Baseline model trained with one additional segmentation channel showed intermediate performance (AUC 0.870-0.895). ConcatNet had sensitivity of 82.0% and specificity of 87.8%, which was an improvement in performance over the baseline (sensitivity of 74.6%; specificity of 80.4%). Integrated gradients showed that models trained with additional segmentation channels had improved focus on particular areas of the image containing aberrant cells. Augmenting images with additional segmentation channels improved baseline model performance as well as its ability to focus on discrete areas of the image. Full article

(This article belongs to the Special Issue Surgical Pathology in the Digital Era)

► Show Figures

Figure 1

17 pages, 2442 KiB

Open AccessArticle

Immuno-Interface Score to Predict Outcome in Colorectal Cancer Independent of Microsatellite Instability Status

by Ausrine Nestarenkaite, Wakkas Fadhil, Allan Rasmusson, Susanti Susanti, Efthymios Hadjimichael, Aida Laurinaviciene, Mohammad Ilyas and Arvydas Laurinavicius

Cancers 2020, 12(10), 2902; https://doi.org/10.3390/cancers12102902 - 9 Oct 2020

Cited by 12 | Viewed by 2474

Abstract

Tumor-associated immune cells have been shown to predict patient outcome in colorectal (CRC) and other cancers. Spatial digital image analysis-based cell quantification increases the informative power delivered by tumor microenvironment features and leads to new prognostic scoring systems. In this study we evaluated the intratumoral density of immunohistochemically stained CD8, CD20 and CD68 cells in 87 cases of CRC (48 were microsatellite stable, MSS, and 39 had microsatellite instability, MSI) in both the intratumoral tumor tissue and within the tumor-stroma interface zone (IZ) which was extracted by a previously developed unbiased hexagonal grid analytics method. Indicators of immune-cell gradients across the extracted IZ were computed and explored along with absolute cell densities, clinicopathological and molecular data, including gene mutation (BRAF, KRAS, PIK3CA) and MSI status. Multiple regression modeling identified (p < 0.0001) three independent prognostic factors: CD8+ and CD20+ Immunogradient indicators, that reflect cell migration towards the tumor, were associated with improved patient survival, while the infiltrative tumor growth pattern was linked to worse patient outcome. These features were combined into CD8-CD20 Immunogradient and immuno-interface scores which outperformed both tumor-node-metastasis (TNM) staging and molecular characteristics, and importantly, revealed high prognostic value both in MSS and MSI CRCs. Full article

(This article belongs to the Special Issue Surgical Pathology in the Digital Era)

► Show Figures

Figure 1

11 pages, 2721 KiB

Open AccessArticle

A Machine-learning Approach for the Assessment of the Proliferative Compartment of Solid Tumors on Hematoxylin-Eosin-Stained Sections

by Francesco Martino, Silvia Varricchio, Daniela Russo, Francesco Merolla, Gennaro Ilardi, Massimo Mascolo, Giovanni Orabona dell’Aversana, Luigi Califano, Guglielmo Toscano, Giuseppe De Pietro, Maria Frucci, Nadia Brancati, Filippo Fraggetta and Stefania Staibano

Cancers 2020, 12(5), 1344; https://doi.org/10.3390/cancers12051344 - 25 May 2020

Cited by 20 | Viewed by 4750

Abstract

We introduce a machine learning-based analysis to predict the immunohistochemical (IHC) labeling index for the cell proliferation marker Ki67/MIB1 on cancer tissues based on morphometrical features extracted from hematoxylin and eosin (H&E)-stained formalin-fixed, paraffin-embedded (FFPE) tumor tissue samples. We provided a proof-of-concept prediction of the Ki67/MIB1 IHC positivity of cancer cells through the definition and quantitation of single nuclear features. In the first instance, we set our digital framework on Ki67/MIB1-stained OSCC (oral squamous cell carcinoma) tissue sample whole slide images, using QuPath as a working platform and its integrated algorithms, and we built a classifier in order to distinguish tumor and stroma classes and, within them, Ki67-positive and Ki67-negative cells; then, we sorted the morphometric features of tumor cells related to their Ki67 IHC status. Among the evaluated features, nuclear hematoxylin mean optical density (NHMOD) presented as the best one to distinguish Ki67/MIB1 positive from negative cells. We confirmed our findings in a single-cell level analysis of H&E staining on Ki67-immunostained/H&E-decolored tissue samples. Finally, we tested our digital framework on a case series of oral squamous cell carcinomas (OSCC), arranged in tissue microarrays; we selected two consecutive sections of each OSCC FFPE TMA (tissue microarray) block, respectively stained with H&E and immuno-stained for Ki67/MIB1. We automatically detected tumor cells in H&E slides and generated a “false color map” (FCM) based on NHMOD through the QuPath measurements map tool. FCM nearly coincided with the actual immunohistochemical result, allowing the prediction of Ki67/MIB1 positive cells in a direct visual fashion. Our proposed approach provides the pathologist with a fast method of identifying the proliferating compartment of the tumor through a quantitative assessment of the nuclear features on H&E slides, readily appreciable by visual inspection. Although this technique needs to be fine-tuned and tested on larger series of tumors, the digital analysis approach appears to be a promising tool to quickly forecast the tumor’s proliferation fraction directly on routinely H&E-stained digital sections. Full article

(This article belongs to the Special Issue Surgical Pathology in the Digital Era)

► Show Figures

Figure 1

12 pages, 5340 KiB

Open AccessArticle

Improving the Diagnostic Accuracy of the PD-L1 Test with Image Analysis and Multiplex Hybridization

by Matthew P. Humphries, Victoria Bingham, Fatima Abdullahi Sidi, Stephanie G. Craig, Stephen McQuaid, Jacqueline James and Manuel Salto-Tellez

Cancers 2020, 12(5), 1114; https://doi.org/10.3390/cancers12051114 - 29 Apr 2020

Cited by 30 | Viewed by 5983

Abstract

Targeting of the programmed cell death protein (PD-1)/programmed death-ligand 1 (PD-L1) axis with checkpoint inhibitors has changed clinical practice in non-small cell lung cancer (NSCLC). However, clinical assessment remains complex and ambiguous. We aim to assess whether digital image analysis (DIA) and multiplex immunofluorescence can improve the accuracy of PD-L1 diagnostic testing. A clinical cohort of routine NSCLC patients reflex tested for PD-L1 (SP263) immunohistochemistry (IHC), was assessed using DIA. Samples of varying assessment difficulty were assessed by multiplex immunofluorescence. Sensitivity, specificity, and concordance was evaluated between manual diagnostic evaluation and DIA for chromogenic and multiplex IHC. PD-L1 expression by DIA showed significant concordance (R² = 0.8248) to manual assessment. Sensitivity and specificity was 86.8% and 91.4%, respectively. Evaluation of DIA scores revealed 96.8% concordance to manual assessment. Multiplexing enabled PD-L1+/CD68+ macrophages to be readily identified within PD-L1+/cytokeratin+ or PD-L1-/cytokeratin+ tumor nests. Assessment of multiplex vs. chromogenic IHC had a sensitivity and specificity of 97.8% and 91.8%, respectively. Deployment of DIA for PD-L1 diagnostic assessment is an accurate process of case triage. Multiplex immunofluorescence provided higher confidence in PD-L1 assessment and could be offered for challenging cases by centers with appropriate expertise and specialist equipment. Full article

(This article belongs to the Special Issue Surgical Pathology in the Digital Era)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Surgical Pathology in the Digital Era

Share This Special Issue

Special Issue Editor

Special Issue Information

Keywords

Published Papers (9 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI