Kikuchi-Fujimoto disease: A comprehensive review

Kikuchi-Fujimoto disease, a rare form of necrotizing lymphadenitis, is an uncommon, benign, self-limiting disorder of obscure etiology. It affects mostly young adults of both genders. Clinically, it presents with fever and lymphadenopathy of a firm to rubbery consistency frequently involving cervical lymph nodes while weight loss, splenomegaly, leucopenia, and elevated erythrocyte sedimentation rate feature in severely affected patients. Cutaneous involvement occurs in about 30%-40% of cases as facial erythema and nonspecific erythematous papules, plaques, acneiform or morbilliform lesions of great histologic heterogeneity. Both Kikuchi-Fujimoto disease and systemic lupus erythematosus share an obscure and complex relationship as systemic lupus erythematosus may occasionally precede, develop subsequently, or sometimes be associated concurrently with Kikuchi-Fujimoto disease. It is often mistaken for non-Hodgkin lymphoma while lupus lymphadenitis, cat-scratch disease, Sweet's syndrome, Still's disease, drug eruptions, infectious mononucleosis, and viral or tubercular lymphadenitis are other common differentials. Fine needle aspiration cytology mostly has features of nonspecific reactive lymphadenitis and immunohistochemistry studies usually show variable features of uncertain diagnostic value. Since its diagnosis is exclusively from histopathology, it needs to be evaluated more carefully; an early lymph node biopsy will obviate the need for unnecessary investigations and therapeutic trials. Its treatment with systemic corticosteroids, hydroxychloroquine, or antimicrobial agents mostly remains empirical. The article reviews clinicoepidemiological, diagnostic, and management aspects of KFD from the perspective of practicing clinicians.

Recent application of artificial intelligence on histopathologic image-based prediction of gene mutation in solid cancers

PURPOSE

Evaluation of genetic mutations in cancers is important because distinct mutational profiles help determine individualized drug therapy. However, molecular analyses are not routinely performed in all cancers because they are expensive, time-consuming and not universally available. Artificial intelligence (AI) has shown the potential to determine a wide range of genetic mutations on histologic image analysis. Here, we assessed the status of mutation prediction AI models on histologic images by a systematic review.

METHODS

A literature search using the MEDLINE, Embase and Cochrane databases was conducted in August 2021. The articles were shortlisted by titles and abstracts. After a full-text review, publication trends, study characteristic analysis and comparison of performance metrics were performed.

RESULTS

Twenty-four studies were found mostly from developed countries, and their number is increasing. The major targets were gastrointestinal, genitourinary, gynecological, lung and head and neck cancers. Most studies used the Cancer Genome Atlas, with a few using an in-house dataset. The area under the curve of some of the cancer driver gene mutations in particular organs was satisfactory, such as 0.92 of BRAF in thyroid cancers and 0.79 of EGFR in lung cancers, whereas the average of all gene mutations was 0.64, which is still suboptimal.

CONCLUSION

AI has the potential to predict gene mutations on histologic images with appropriate caution. Further validation with larger datasets is still required before AI models can be used in clinical practice to predict gene mutations.

A homozygous loss-of-function C1S mutation is associated with Kikuchi-Fujimoto disease

BACKGROUND

Kikuchi-Fujimoto disease (KFD) is a self-limited inflammatory disease of unknown pathogenesis. Familial cases have been described and defects in classical complement components C1q and C4 have been identified in some patients.

MATERIAL AND METHODS

We describe genetic and immune investigations of a 16 years old Omani male, a product of consanguineous marriage, who presented with typical clinical and histological features of KFD.

RESULTS

We identified a novel homozygous single base deletion in C1S (c.330del; p. Phe110LeufsTer23) resulting in a defect in the classical complement pathway. The patient was negative for all serological markers of SLE. In contrast, two female siblings (also homozygous for the C1S mutation), one has autoimmune thyroid disease (Hashimoto thyroiditis) and a positive ANA and the other sibling has serology consistent with SLE.

CONCLUSION

We report the first association between C1s deficiency and KFD.

Comprehensive immunoprofile analysis of prognostic markers in pancreaticobiliary tract cancers

Pancreaticobiliary tract cancer has a poor prognosis with unmet needs in a new target treatment. Some studies have reported that an enhancement of T-cell immunity is associated with a good prognosis. The aim of this study is to investigate the immunoprofile as a prognostic marker of pancreaticobiliary tract cancers. Unresectable pancreatic ductal adenocarcinoma (PDAC, n = 80) and biliary tract cancer (BTC, n = 74) diagnosed between January 2012 and December 2018 in Samsung Medical Center were analyzed. Expression levels of CD8, FOXP3, PD-1, PD-L1, and CXCL13 in PDAC and BTC tissue samples were examined with immunohistochemical staining, which was evaluated with various clinical factors. In PDAC, higher degree of PD-L1 expression was significantly associated with shorter overall survival (OS) (p = 0.0095). On the other hand, higher infiltrations of PD-1+ immune cells (p = 0.0002) and CD8+ T cells (p = 0.0067) were associated with longer OS. In BTC, higher FOXP3+ (p = 0.0343) and CD8+ (p = 0.0028) cell infiltrations were associated with better survival. Low infiltration of CD8+ (p = 0.0148), FOXP3+ (p = 0.0208), PD-1+ (p = 0.0318) cells in PDAC, and FOXP3+ cells (p = 0.005) in BTC were considerably related to metastasis. In a combined evaluation of clinical factors and immunoprofiles, univariate analysis revealed that operation after chemotherapy (p < 0.0001), mass size (p = 0.0004), metastasis (p = 0.006), PD-L1 (p < 0.0001), PD-1 (p = 0.003) and CD8 (p = 0.0063) was significantly associated with OS in PDAC, and CD8 (p = 0.007) was statistically related to OS in BTC. In multivariate analysis, prognostic factors were operation after chemotherapy (p = 0.021) in PDAC and CD8 (p = 0.037) in BTC. Therefore, immunoprofile analysis of cells expressing CD8, FOXP3, PD-1, and PD-L1 might have prognostic values in patients with pancreaticobiliary tract cancers.

Validation of a Machine Learning Expert Supporting System, ImmunoGenius, Using Immunohistochemistry Results of 3000 Patients with Lymphoid Neoplasms

(1) Background: Differential diagnosis using immunohistochemistry (IHC) panels is a crucial step in the pathological diagnosis of hematolymphoid neoplasms. In this study, we evaluated the prediction accuracy of the ImmunoGenius software using nationwide data to validate its clinical utility. (2) Methods: We collected pathologically confirmed lymphoid neoplasms and their corresponding IHC results from 25 major university hospitals in Korea between 2015 and 2016. We tested ImmunoGenius using these real IHC panel data and compared the precision hit rate with previously reported diagnoses. (3) Results: We enrolled 3052 cases of lymphoid neoplasms with an average of 8.3 IHC results. The precision hit rate was 84.5% for these cases, whereas it was 95.0% for 984 in-house cases. (4) Discussion: ImmunoGenius showed excellent results in most B-cell lymphomas and generally showed equivalent performance in T-cell lymphomas. The primary reasons for inaccurate precision were atypical IHC profiles of certain cases, lack of disease-specific markers, and overlapping IHC profiles of similar diseases. We verified that the machine-learning algorithm could be applied for diagnosis precision with a generally acceptable hit rate in a nationwide dataset. Clinical and histological features should also be taken into account for the proper use of this system in the decision-making process.

Immune profiling and prognostic model of pancreatic cancer using quantitative pathology and single-cell RNA sequencing

BACKGROUND

Pancreatic ductal adenocarcinoma (PDAC) has a complex tumor immune microenvironment (TIME), the clinical value of which remains elusive. This study aimed to delineate the immune landscape of PDAC and determine the clinical value of immune features in TIME.

METHODS

Univariable and multivariable Cox regression analyses were performed to evaluate the clinical value of immune features and establish a new prognostic model. We also conducted single-cell RNA sequencing (scRNA-seq) to further characterize the immune profiles of PDAC and explore cell-to-cell interactions.

RESULTS

There was a significant difference in the immune profiles between PDAC and adjacent noncancerous tissues. Several novel immune features were captured by quantitative pathological analysis on multiplex immunohistochemistry (mIHC), some of which were significantly correlated with the prognosis of patients with PDAC. A risk score-based prognostic model was established based on these immune features. We also constructed a user-friendly nomogram plot to predict the overall survival (OS) of patients by combining the risk score and clinicopathological features. Both mIHC and scRNA-seq analysis revealed PD-L1 expression was low in PDAC. We found that PD1 + cells were distributed in different T cell subpopulations, and were not enriched in a specific subpopulation. In addition, there were other conserved receptor-ligand pairs (CCL5-SDC1/4) besides the PD1-PD-L1 interaction between PD1 + T cells and PD-L1 + tumor cells.

CONCLUSION

Our findings reveal the immune landscape of PDAC and highlight the significant value of the combined application of mIHC and scRNA-seq for uncovering TIME, which might provide new clues for developing immunotherapy combination strategies.

Application of artificial intelligence in diagnosis and treatment of colorectal cancer: A novel Prospect

In the past few decades, according to the rapid development of information technology, artificial intelligence (AI) has also made significant progress in the medical field. Colorectal cancer (CRC) is the third most diagnosed cancer worldwide, and its incidence and mortality rates are increasing yearly, especially in developing countries. This article reviews the latest progress in AI in diagnosing and treating CRC based on a systematic collection of previous literature. Most CRCs transform from polyp mutations. The computer-aided detection systems can significantly improve the polyp and adenoma detection rate by early colonoscopy screening, thereby lowering the possibility of mutating into CRC. Machine learning and bioinformatics analysis can help screen and identify more CRC biomarkers to provide the basis for non-invasive screening. The Convolutional neural networks can assist in reading histopathologic tissue images, reducing the experience difference among doctors. Various studies have shown that AI-based high-level auxiliary diagnostic systems can significantly improve the readability of medical images and help clinicians make more accurate diagnostic and therapeutic decisions. Moreover, Robotic surgery systems such as da Vinci have been more and more commonly used to treat CRC patients, according to their precise operating performance. The application of AI in neoadjuvant chemoradiotherapy has further improved the treatment and efficacy evaluation of CRC. In addition, AI represented by deep learning in gene sequencing research offers a new treatment option. All of these things have seen that AI has a promising prospect in the era of precision medicine.

PARP-1 Expression Influences Cancer Stem Cell Phenotype in Colorectal Cancer Depending on p53

Poly(ADP-ribose) polymerase-1 (PARP-1) is a protein involved in multiple physiological processes. Elevated PARP-1 expression has been found in several tumours, being associated with stemness and tumorigenesis. In colorectal cancer (CRC), some controversy among studies has been described. In this study, we analysed the expression of PARP-1 and cancer stem cell (CSC) markers in CRC patients with different p53 status. In addition, we used an in vitro model to evaluate the influence of PARP-1 in CSC phenotype regarding p53. In CRC patients, PARP-1 expression correlated with the differentiation grade, but this association was only maintained for tumours harbouring wild-type p53. Additionally, in those tumours, PARP-1 and CSC markers were positively correlated. In mutated p53 tumours, no associations were found, but PARP-1 was an independent factor for survival. According to our in vitro model, PARP-1 regulates CSC phenotype depending on p53 status. PARP-1 overexpression in a wild type p53 context increases CSC markers and sphere forming ability. By contrast, those features were reduced in mutated p53 cells. These results could implicate that patients with elevated PARP-1 expression and wild type p53 could benefit from PARP-1 inhibition therapies, meanwhile it could have adverse effects for those carrying mutated p53 tumours.

Deep Learning-Based Classification and Targeted Gene Alteration Prediction from Pleural Effusion Cell Block Whole-Slide Images

Cytopathological examination is one of the main examinations for pleural effusion, and especially for many patients with advanced cancer, pleural effusion is the only accessible specimen for establishing a pathological diagnosis. The lack of cytopathologists and the high cost of gene detection present opportunities for the application of deep learning. In this retrospective analysis, data representing 1321 consecutive cases of pleural effusion were collected. We trained and evaluated our deep learning model based on several tasks, including the diagnosis of benign and malignant pleural effusion, the identification of the primary location of common metastatic cancer from pleural effusion, and the prediction of genetic alterations associated with targeted therapy. We achieved good results in identifying benign and malignant pleural effusions (0.932 AUC (area under the ROC curve)) and the primary location of common metastatic cancer (0.910 AUC). In addition, we analyzed ten genes related to targeted therapy in specimens and used them to train the model regarding four alteration statuses, which also yielded reasonable results (0.869 AUC for ALK fusion, 0.804 AUC for KRAS mutation, 0.644 AUC for EGFR mutation and 0.774 AUC for NONE alteration). Our research shows the feasibility and benefits of deep learning to assist in cytopathological diagnosis in clinical settings.

Role of artificial intelligence in risk prediction, prognostication, and therapy response assessment in colorectal cancer: current state and future directions

Artificial Intelligence (AI) is a branch of computer science that utilizes optimization, probabilistic and statistical approaches to analyze and make predictions based on a vast amount of data. In recent years, AI has revolutionized the field of oncology and spearheaded novel approaches in the management of various cancers, including colorectal cancer (CRC). Notably, the applications of AI to diagnose, prognosticate, and predict response to therapy in CRC, is gaining traction and proving to be promising. There have also been several advancements in AI technologies to help predict metastases in CRC and in Computer-Aided Detection (CAD) Systems to improve miss rates for colorectal neoplasia. This article provides a comprehensive review of the role of AI in predicting risk, prognosis, and response to therapies among patients with CRC.

The effect of SMAD4 on the prognosis and immune response in hypopharyngeal carcinoma

Objectives

In malignant tumors, elevated infiltration of intratumoral CD8+ cytotoxic T cells predicts a beneficial prognosis, whereas high levels of CD15+ neutrophils in peritumor tissues indicate poor prognosis. It is unclear how SMAD4, which promotes favorable clinical outcomes and antitumor immunoregulation, along with CD8+ cytotoxic T cells and CD15+ neutrophils exert an influence on hypopharyngeal carcinoma (HPC).

Materials and methods

Specimens were collected from 97 patients with HPC. Immunohistological analyses of SMAD4, CD8+ cytotoxic T cell and CD15+ neutrophil expression were performed. SMAD4 nuclear intensity was measured, meanwhile, CD8+ cytotoxic T cells and CD15+ neutrophils were counted under a microscope. The prognostic role of SMAD4 was determined using the log-rank test and univariate and multivariate analyses. The relationship among SMAD4, CD8+ cytotoxic T cells, and CD15+ neutrophils was estimated by Mann-Whitney U test.

Results

High levels of SMAD4 were associated with favorable overall survival (OS) and disease-free survival (DFS) in HPC. Multivariate analysis suggested that SMAD4 is an independent predictor of OS and DFS. A high density of intratumoral CD8+ cytotoxic T cells and low accumulation of CD15+ neutrophils in the peritumor area were associated with longer OS and DFS. Furthermore, SMAD4 was linked to the levels of intratumoral CD8+ cytotoxic T cells and peritumoral CD15+ neutrophils. Patients with high SMAD4/high intratumoral CD8+ cytotoxic T cells or high SMAD4/low peritumoral CD15+ neutrophils showed the best prognosis.

Conclusion

SMAD4, CD8+ cytotoxic T cell level, and CD15+ neutrophil level have prognostic value in HPC. SMAD4 is a promising prognostic marker reflecting immune response in HPC.

Trends in AI-powered Classification of Thyroid Neoplasms Based on Histopathology Images - a Systematic Review

Background

Assessment of thyroid nodules histopathology using AI is crucial for an accurate diagnosis. This systematic review analyzes recent works employing deep learning approaches for classifying thyroid nodules based on histopathology images, evaluating their performance, and identifying limitations.

Methods

Eligibility criteria focused on peer-reviewed English papers published in the last 5 years, applying deep learning to categorize thyroid histopathology images. The PubMed database was searched using relevant keyword combinations.

Results

Out of 103 articles, 11 studies met inclusion criteria. They used convolutional neural networks to classify thyroid neoplasm. Most studies aimed for basic tumor subtyping; however, 3 studies targeted the prediction of tumor-associated mutation. Accuracy ranged from 77% to 100%, with most over 90%.

Discussion

The findings from our analysis reveal the effectiveness of deep learning in identifying discriminative morphological patterns from histopathology images, thus enhancing the accuracy of thyroid nodule histopathological classification. Key limitations were small sample sizes, subjective annotation, and limited dataset diversity. Further research with larger diverse datasets, model optimization, and real-world validation is essential to translate these tools into clinical practice.

Case report: Advanced primary squamous cell carcinoma in the periampullary area with upregulation of programmed cell death-ligand 1 expression and response to sintilimab immunotherapy

Primary squamous cell carcinoma (SCC) of the periampullary area is exceedingly rare. We report a case of a 45-year-old woman who presented with progressive upper abdominal pain and melena. Laboratory testing revealed an elevated level of carcinoembryonic antigen. Esophagogastroduodenoscopy revealed a very large irregular ulcerated tumor in the periampullary area. Contrast-enhanced computed tomography (CT) of the chest, abdomen, and pelvis, 18 F-fluorodeoxyglucose positron emission tomography/CT, and thin-prep cytologic test excluded metastasis of the primary tumor to the periampullary area from other sites. Immunohistochemistry revealed positive p40 and cytokeratin (CK)5/6, indicating SCC. The expression of programmed cell death-ligand 1 (PD-L1) in tumor cells was upregulated, and the patient responded well to chemotherapy combined with immunotherapy. To the best of our knowledge, this is the first reported case of advanced primary SCC in the periampullary area with high expression of PD-L1.

Real-Life Barriers to Diagnosis of Early Mycosis Fungoides: An International Expert Panel Discussion

Mycosis fungoides (MF) is a rare, primary cutaneous T-cell lymphoma that is challenging to diagnose due to its heterogeneous clinical presentation and complex histology. The subtlety of the initial clinical appearance of MF can result in diagnostic delays and hesitancy to refer suspected cases to specialist clinics. An unmet need remains for greater awareness and education. Therefore, an international expert panel of dermatologists, oncologists, hematologists, and dermatopathologists convened to discuss and identify barriers to early and accurate MF diagnosis that could guide clinicians toward making a correct diagnosis. Confirmation of MF requires accurate assessment of symptoms and clinical signs, and subsequent correlation with dermatopathological findings. This review summarizes the expert panel's guidance, based on the literature and real-life experience, for dermatologists to help include MF in their list of differential diagnoses, along with simple clinical and histopathologic checklists that may help clinicians to suspect and identify potential MF lesions and reduce diagnostic delays.

Clinicopathological characteristics of high microsatellite instability/mismatch repair-deficient colorectal cancer: A narrative review

Colorectal cancers (CRCs) with high microsatellite instability (MSI-H) and deficient mismatch repair (dMMR) show molecular and clinicopathological characteristics that differ from those of proficient mismatch repair/microsatellite stable CRCs. Despite the importance of MSI-H/dMMR status in clinical decision making, the testing rates for MSI and MMR in clinical practice remain low, even in high-risk populations. Additionally, the real-world prevalence of MSI-H/dMMR CRC may be lower than that reported in the literature. Insufficient MSI and MMR testing fails to identify patients with MSI-H/dMMR CRC, who could benefit from immunotherapy. In this article, we describe the current knowledge of the clinicopathological features, molecular landscape, and radiomic characteristics of MSI-H/dMMR CRCs. A better understanding of the importance of MMR/MSI status in the clinical characteristics and prognosis of CRC may help increase the rates of MMR/MSI testing and guide the development of more effective therapies based on the unique features of these tumors.

Improving quality control in the routine practice for histopathological interpretation of gastrointestinal endoscopic biopsies using artificial intelligence

BACKGROUND

Colorectal and gastric cancer are major causes of cancer-related deaths. In Korea, gastrointestinal (GI) endoscopic biopsy specimens account for a high percentage of histopathologic examinations. Lack of a sufficient pathologist workforce can cause an increase in human errors, threatening patient safety. Therefore, we developed a digital pathology total solution combining artificial intelligence (AI) classifier models and pathology laboratory information system for GI endoscopic biopsy specimens to establish a post-analytic daily fast quality control (QC) system, which was applied in clinical practice for a 3-month trial run by four pathologists.

METHODS AND FINDINGS

Our whole slide image (WSI) classification framework comprised patch-generator, patch-level classifier, and WSI-level classifier. The classifiers were both based on DenseNet (Dense Convolutional Network). In laboratory tests, the WSI classifier achieved accuracy rates of 95.8% and 96.0% in classifying histopathological WSIs of colorectal and gastric endoscopic biopsy specimens, respectively, into three classes (Negative for dysplasia, Dysplasia, and Malignant). Classification by pathologic diagnosis and AI prediction were compared and daily reviews were conducted, focusing on discordant cases for early detection of potential human errors by the pathologists, allowing immediate correction, before the pathology report error is conveyed to the patients. During the 3-month AI-assisted daily QC trial run period, approximately 7-10 times the number of slides compared to that in the conventional monthly QC (33 months) were reviewed by pathologists; nearly 100% of GI endoscopy biopsy slides were double-checked by the AI models. Further, approximately 17-30 times the number of potential human errors were detected within an average of 1.2 days.

CONCLUSIONS

The AI-assisted daily QC system that we developed and established demonstrated notable improvements in QC, in quantitative, qualitative, and time utility aspects. Ultimately, we developed an independent AI-assisted post-analytic daily fast QC system that was clinically applicable and influential, which could enhance patient safety.

Artificial Intelligence-Based Prediction of Recurrence after Curative Resection for Colorectal Cancer from Digital Pathological Images

BACKGROUND

To develop an artificial intelligence-based model to predict recurrence after curative resection for stage I-III colorectal cancer from digitized pathological slides.

PATIENTS AND METHODS

In this retrospective study, 471 consecutive patients who underwent curative resection for stage I-III colorectal cancer at our institution from 2004 to 2015 were enrolled, and 512 randomly selected tiles from digitally scanned images of hematoxylin and eosin-stained tumor tissue sections were used to train a convolutional neural network. Five-fold cross-validation was used to validate the model. The association between recurrence and the model's output scores were analyzed in the test cohorts.

RESULTS

The area under the receiver operating characteristic curve of the cross-validation was 0.7245 [95% confidence interval (CI) 0.6707-0.7783; P < 0.0001]. The score successfully classified patients into those with better and worse recurrence free survival (P < 0.0001). Multivariate analysis revealed that a high score was significantly associated with worse recurrence free survival [odds ratio (OR) 1.857; 95% CI 1.248-2.805; P = 0.0021], which was independent from other predictive factors: male sex (P = 0.0238), rectal cancer (P = 0.0396), preoperative abnormal carcinoembryonic antigen (CEA) level (P = 0.0216), pathological T3/T4 stage (P = 0.0162), and pathological positive lymph node metastasis (P < 0.0001).

CONCLUSIONS

The artificial intelligence-based prediction model discriminated patients with a high risk of recurrence. This approach could help decision-makers consider the benefits of adjuvant chemotherapy.

Deep Learning-Based Prediction of Molecular Tumor Biomarkers from H&E: A Practical Review

Molecular and genomic properties are critical in selecting cancer treatments to target individual tumors, particularly for immunotherapy. However, the methods to assess such properties are expensive, time-consuming, and often not routinely performed. Applying machine learning to H&E images can provide a more cost-effective screening method. Dozens of studies over the last few years have demonstrated that a variety of molecular biomarkers can be predicted from H&E alone using the advancements of deep learning: molecular alterations, genomic subtypes, protein biomarkers, and even the presence of viruses. This article reviews the diverse applications across cancer types and the methodology to train and validate these models on whole slide images. From bottom-up to pathologist-driven to hybrid approaches, the leading trends include a variety of weakly supervised deep learning-based approaches, as well as mechanisms for training strongly supervised models in select situations. While results of these algorithms look promising, some challenges still persist, including small training sets, rigorous validation, and model explainability. Biomarker prediction models may yield a screening method to determine when to run molecular tests or an alternative when molecular tests are not possible. They also create new opportunities in quantifying intratumoral heterogeneity and predicting patient outcomes.

Genetic Heterogeneity, Tumor Microenvironment and Immunotherapy in Triple-Negative Breast Cancer

Heterogeneity of triple-negative breast cancer is well known at clinical, histopathological, and molecular levels. Genomic instability and greater mutation rates, which may result in the creation of neoantigens and enhanced immunogenicity, are additional characteristics of this breast cancer type. Clinical outcome is poor due to early age of onset, high metastatic potential, and increased likelihood of distant recurrence. Consequently, efforts to elucidate molecular mechanisms of breast cancer development, progression, and metastatic spread have been initiated to improve treatment options and improve outcomes for these patients. The extremely complex and heterogeneous tumor immune microenvironment is made up of several cell types and commonly possesses disorganized gene expression. Altered signaling pathways are mainly associated with mutated genes including p53, PIK3CA, and MAPK, and which are positively correlated with genes regulating immune response. Of note, particular immunity-associated genes could be used in prognostic indexes to assess the most effective management. Recent findings highlight the fact that long non-coding RNAs also play an important role in shaping tumor microenvironment formation, and can mediate tumor immune evasion. Identification of molecular signatures, through the use of multi-omics approaches, and effector pathways that drive early stages of the carcinogenic process are important steps in developing new strategies for targeted cancer treatment and prevention. Advances in immunotherapy by remodeling the host immune system to eradicate tumor cells have great promise to lead to novel therapeutic strategies. Current research is focused on combining immune checkpoint inhibition with chemotherapy, PARP inhibitors, cancer vaccines, or natural killer cell therapy. Targeted therapies may improve therapeutic response, eliminate therapeutic resistance, and improve overall patient survival. In the future, these evolving advancements should be implemented for personalized medicine and state-of-art management of cancer patients.

Development of quality assurance program for digital pathology by the Korean Society of Pathologists

Background: Digital pathology (DP) using whole slide imaging is a recently emerging game changer technology that can fundamentally change the way of working in pathology. The Digital Pathology Study Group (DPSG) of the Korean Society of Pathologists (KSP) published a consensus report on the recommendations for pathologic practice using DP. Accordingly, the need for the development and implementation of a quality assurance program (QAP) for DP has been raised.Methods: To provide a standard baseline reference for internal and external QAP for DP, the members of the Committee of Quality Assurance of the KSP developed a checklist for the Redbook and a QAP trial for DP based on the prior DPSG consensus report. Four leading institutes participated in the QAP trial in the first year, and we gathered feedback from these institutes afterwards.Results: The newly developed checklists of QAP for DP contain 39 items (216 score): eight items for quality control of DP systems; three for DP personnel; nine for hardware and software requirements for DP systems; 15 for validation, operation, and management of DP systems; and four for data security and personal information protection. Most participants in the QAP trial replied that continuous education on unfamiliar terminology and more practical experience is demanding.Conclusions: The QAP for DP is essential for the safe implementation of DP in pathologic practice. Each laboratory should prepare an institutional QAP according to this checklist, and consecutive revision of the checklist with feedback from the QAP trial for DP needs to follow.

Comparison of Clinical Characteristics and Risk Factors for Recurrence of Kikuchi-Fujimoto Disease Between Children and Adult

Purpose

Kikuchi-Fujimoto disease (KFD) is a rare, benign, and self-limited disease, characterized by cervical lymphadenopathy and fever. Herein, we analyzed the differences in its clinical manifestations and risk factors for recurrence between children and adults.

Patients and Methods

We retrospectively reviewed the medical records of patients diagnosed with KFD at a tertiary referral hospital between 2005 and 2019. Patients were divided into two groups based on their age: children (<19 years) and adults (≥19 years).

Results

During the 14-year study period, 127 patients were diagnosed with KFD. Among these, 34 (26.8%) were children and 93 (73.2%) were adults. The fever duration was longer and the frequency of myalgia was higher in adults than in children; however, no other significant symptomatic differences were noted between the two groups. Lymph node evaluation was mainly performed using ultrasound in children (61.8%) and computed tomography in adults (78.5%). Moreover, the frequency of antibiotic use was higher in children than in adults (76.5% vs 54.8%, P = 0.027). In adults, multivariable logistic regression analysis revealed anti-nuclear antibody (ANA) positivity (titer ≥1:80) as a risk factor for recurrence (odds ratio: 7.813; 95% confidence interval = 1.818-33.333; P = 0.006).

Conclusion

The clinical features of KFD in children and adults were similar; however, the preferred imaging study and frequency of antibiotic use differed significantly between the two groups. Furthermore, in adults, ANA positivity was associated with KFD recurrence. Thus, patients with KFD who present with ANA positivity at diagnosis will benefit from a regular follow-up for monitoring KFD recurrence.

Therapeutic strategies for gastric cancer targeting immune cells: Future directions

Gastric cancer (GC) is a malignancy with a high incidence and mortality, and the emergence of immunotherapy has brought survival benefits to GC patients. Compared with traditional therapy, immunotherapy has the advantages of durable response, long-term survival benefits, and lower toxicity. Therefore, targeted immune cells are the most promising therapeutic strategy in the field of oncology. In this review, we introduce the role and significance of each immune cell in the tumor microenvironment of GC and summarize the current landscape of immunotherapy in GC, which includes immune checkpoint inhibitors, adoptive cell therapy (ACT), dendritic cell (DC) vaccines, reduction of M2 tumor-associated macrophages (M2 TAMs), N2 tumor-associated neutrophils (N2 TANs), myeloid-derived suppressor cells (MDSCs), effector regulatory T cells (eT_regs), and regulatory B cells (B_regs) in the tumor microenvironment and reprogram TAMs and TANs into tumor killer cells. The most widely used immunotherapy strategies are the immune checkpoint inhibitor programmed cell death 1/programmed death-ligand 1 (PD-1/PD-L1) antibody, cytotoxic T lymphocyte–associated protein 4 (CTLA-4) antibody, and chimeric antigen receptor T (CAR-T) in ACT, and these therapeutic strategies have significant anti-tumor efficacy in solid tumors and hematological tumors. Targeting other immune cells provides a new direction for the immunotherapy of GC despite the relatively weak clinical data, which have been confirmed to restore or enhance anti-tumor immune function in preclinical studies and some treatment strategies have entered the clinical trial stage, and it is expected that more and more effective immune cell–based therapeutic methods will be developed and applied.

Roles of tumor-associated neutrophils in tumor metastasis and its clinical applications

Metastasis, a primary cause of death in patients with malignancies, is promoted by intrinsic changes in both tumor and non-malignant cells in the tumor microenvironment (TME). As major components of the TME, tumor-associated neutrophils (TANs) promote tumor progression and metastasis through communication with multiple growth factors, chemokines, inflammatory factors, and other immune cells, which together establish an immunosuppressive TME. In this review, we describe the potential mechanisms by which TANs participate in tumor metastasis based on recent experimental evidence. We have focused on drugs in chemotherapeutic regimens that target TANs, thereby providing a promising future for cancer immunotherapy.

Tumor Budding Is an Independent Prognostic Factor in Pancreatic Adenocarcinoma and It Positively Correlates with PD-L1 Expression on Tumor Cells

Pancreatic adenocarcinoma is one of the leading causes of cancer-related death in developed countries. Only 15% of patients are candidates for radical surgery, and adequate prognostication may guide proper postsurgical management. We aimed to retrospectively assess the prognostic significance of the immunohistochemical expression of immune checkpoint receptors (PD-L1 and VISTA), markers of systemic inflammation, thrombosis in the tumor area, and the tumor budding in the group of 107 patients diagnosed with pancreatic adenocarcinoma in a single center. The high expression of PD-L1 on tumor cells (TCs) was associated with worse overall survival (OS, p = 0.041, log-rank). On the contrary, high PD-L1 or VISTA on tumor-associated immune cells (TAICs) was correlated with better OS (p = 0.006 and p = 0.008, respectively, log-rank). The joint status of PD-L1 on TCs and TAICs stratified patients into three prognostic groups. The cases with high-grade budding were characterized by higher PD-L1 expression on TCs (p = 0.008) and elevated systemic inflammatory markers. Moreover, budding was identified as the independent prognostic factor in multivariate Cox regression analysis (HR = 2.87; 95% CI = 1.75−4.68; p < 0.001). To conclude, the pattern of PD-L1 and VISTA expression was associated with survival in univariate analysis. Tumor budding accurately predicts outcomes in pancreatic cancer and should be incorporated into routine histopathological practice.

Recent Application of Artificial Intelligence in Non-Gynecological Cancer Cytopathology: A Systematic Review

State-of-the-art artificial intelligence (AI) has recently gained considerable interest in the healthcare sector and has provided solutions to problems through automated diagnosis. Cytological examination is a crucial step in the initial diagnosis of cancer, although it shows limited diagnostic efficacy. Recently, AI applications in the processing of cytopathological images have shown promising results despite the elementary level of the technology. Here, we performed a systematic review with a quantitative analysis of recent AI applications in non-gynecological (non-GYN) cancer cytology to understand the current technical status. We searched the major online databases, including MEDLINE, Cochrane Library, and EMBASE, for relevant English articles published from January 2010 to January 2021. The searched query terms were: "artificial intelligence", "image processing", "deep learning", "cytopathology", and "fine-needle aspiration cytology." Out of 17,000 studies, only 26 studies (26 models) were included in the full-text review, whereas 13 studies were included for quantitative analysis. There were eight classes of AI models treated of according to target organs: thyroid (n = 11, 39%), urinary bladder (n = 6, 21%), lung (n = 4, 14%), breast (n = 2, 7%), pleural effusion (n = 2, 7%), ovary (n = 1, 4%), pancreas (n = 1, 4%), and prostate (n = 1, 4). Most of the studies focused on classification and segmentation tasks. Although most of the studies showed impressive results, the sizes of the training and validation datasets were limited. Overall, AI is also promising for non-GYN cancer cytopathology analysis, such as pathology or gynecological cytology. However, the lack of well-annotated, large-scale datasets with Z-stacking and external cross-validation was the major limitation found across all studies. Future studies with larger datasets with high-quality annotations and external validation are required.

Intratumoral Budding in Pretreatment Biopsies, among Tumor Microenvironmental Components, Can Predict Prognosis and Neoadjuvant Therapy Response in Colorectal Adenocarcinoma

Background and Objectives: The prediction of the prognosis and effect of neoadjuvant therapy is vital for patients with advanced or unresectable colorectal carcinoma (CRC). Materials and Methods: We investigated several tumor microenvironment factors, such as intratumoral budding (ITB), desmoplastic reaction (DR), and Klintrup-Mäkinen (KM) inflammation grade, and the tumor-stroma ratio (TSR) in pretreatment biopsy samples (PBSs) collected from patients with advanced or unresectable CRC. A total of 85 patients with 74 rectal carcinomas and 11 colon cancers treated at our hospital were enrolled; 66 patients had curative surgery and 19 patients received palliative treatment. Results: High-grade ITB was associated with recurrence (p = 0.002), death (p = 0.034), and cancer-specific death (p = 0.034). Immature DR was associated with a higher grade of clinical tumor-node-metastasis stage (cTNM) (p = 0.045), cN category (p = 0.045), and cM category (p = 0.046). The KM grade and TSR were not related to any clinicopathological factors. High-grade ITB had a significant relationship with tumor regression in patients who received curative surgery (p = 0.049). Conclusions: High-grade ITB in PBSs is a potential unfavorable prognostic factor for patients with advanced CRC. Immature DR, TSR, and KM grade could not predict prognosis or therapy response in PBSs.

Clinical actionability of triaging DNA mismatch repair deficient colorectal cancer from biopsy samples using deep learning

Background

We aimed to develop a deep learning (DL) model to predict DNA mismatch repair (MMR) status in colorectal cancers (CRC) based on hematoxylin and eosin-stained whole-slide images (WSIs) and assess its clinical applicability.

Methods

The DL model was developed and validated through three-fold cross validation using 441 WSIs from the Cancer Genome Atlas (TCGA) and externally validated using 78 WSIs from the Pathology AI Platform (PAIP), and 355 WSIs from surgical specimens and 341 WSIs from biopsy specimens of the Sun Yet-sun University Cancer Center (SYSUCC). Domain adaption and multiple instance learning (MIL) techniques were adopted for model development. The performance of the models was evaluated using the area under the receiver operating characteristic curve (AUROC). A dual-threshold strategy was also built from the surgical cohorts and validated in the biopsy cohort. Sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), F1-score, and the percentage of patients avoiding IHC testing were evaluated.

Findings

The MIL model achieved an AUROC of 0·8888±0·0357 in the TCGA-validation cohort, 0·8806±0·0232 in the PAIP cohort, 0·8457±0·0233 in the SYSUCC-surgical cohort, and 0·7679±0·0342 in the SYSUCC-biopsy cohort. A dual-threshold triage strategy was used to rule-in and rule-out dMMR patients with remaining uncertain patients recommended for further IHC testing, which kept sensitivity higher than 90% and specificity higher than 95% on deficient MMR patient triage from both the surgical and biopsy specimens, result in more than half of patients avoiding IHC based MMR testing.

Interpretation

A DL-based method that could directly predict CRC MMR status from WSIs was successfully developed, and a dual-threshold triage strategy was established to minimize the number of patients for further IHC testing.

Funding

The study was funded by the National Natural Science Foundation of China (82073159, 81871971 and 81700576), the Natural Science Foundation of Guangdong Province (No. 2021A1515011792 and No.2022A1515012403) and Medical Scientific Research Foundation of Guangdong Province of China (No. A2020392).

Tumor Budding as a Marker for Poor Prognosis and Epithelial-Mesenchymal Transition in Lung Cancer: A Systematic Review and Meta-Analysis

Introduction

Currently, tumor budding (TB) is considered to predict the prognosis of patients. The prognostic significance of TB has also been explored in patients with lung cancer, but has not been fully clarified. In the present meta-analysis, we evaluated the prognostic significance, clinicopathological value, and relationship with epithelial–mesenchymal transition (EMT) of TB in lung cancer.

Methods

The MEDLINE, EMBASE, and Cochrane databases were searched up to July 7, 2021, for the relevant articles that showed the relationship between TB and prognosis in patients with lung cancer. For statistical analysis, we used pooled hazard ratios (HRs) with their corresponding 95% confidence intervals (CIs) to assess the correlation between high-grade TB expression and overall survival (OS), disease-free survival (DFS), progression-free survival (PFS), clinicopathological factors, and EMT markers.

Results

A total of 3,784 patients from 10 independent studies were included in the statistical analysis. Our results indicated that high-grade TB was significantly associated with poor OS [HR 1.64 (95% CI, 1.43–1.87)] and DFS [HR 1.65 (95% CI, 1.22–2.25)]. In terms of clinicopathological characteristics, high-grade TB was associated with larger tumor size, higher T and N stage, pleural invasion, vascular invasion, lymphatic invasion, and severe nuclear atypia. Interestingly, smoking showed significant association with high-grade TB, despite the fact that previous studies could not show a significant relationship between them. Furthermore, through our systematic analysis, high-grade TB showed a significant relationship with EMT markers.

Conclusion

Our findings indicate that high-grade TB is associated with a worse prognosis in patients with lung cancer. TB evaluation should be implemented in routine pathological diagnosis, which may guide the patient’s treatment.

Recent Applications of Artificial Intelligence from Histopathologic Image-Based Prediction of Microsatellite Instability in Solid Cancers: A Systematic Review

Cancers with high microsatellite instability (MSI-H) have a better prognosis and respond well to immunotherapy. However, MSI is not tested in all cancers because of the additional costs and time of diagnosis. Therefore, artificial intelligence (AI)-based models have been recently developed to evaluate MSI from whole slide images (WSIs). Here, we aimed to assess the current state of AI application to predict MSI based on WSIs analysis in MSI-related cancers and suggest a better study design for future studies. Studies were searched in online databases and screened by reference type, and only the full texts of eligible studies were reviewed. The included 14 studies were published between 2018 and 2021, and most of the publications were from developed countries. The commonly used dataset is The Cancer Genome Atlas dataset. Colorectal cancer (CRC) was the most common type of cancer studied, followed by endometrial, gastric, and ovarian cancers. The AI models have shown the potential to predict MSI with the highest AUC of 0.93 in the case of CRC. The relatively limited scale of datasets and lack of external validation were the limitations of most studies. Future studies with larger datasets are required to implicate AI models in routine diagnostic practice for MSI prediction.

iMIL4PATH: A Semi-Supervised Interpretable Approach for Colorectal Whole-Slide Images

Simple Summary

Nowadays, colorectal cancer is the third most incident cancer worldwide and, although it can be detected by imaging techniques, diagnosis is always based on biopsy samples. This assessment includes neoplasia grading, a subjective yet important task for pathologists. With the growing availability of digital slides, the development of robust and high-performance computer vision algorithms can help to tackle such a task. In this work, we propose an approach to automatically detect and grade lesions in colorectal biopsies with high sensitivity. The presented model attempts to support slide decision reasoning in terms of the spatial distribution of lesions, focusing the pathologist’s attention on key areas. Thus, it can be integrated into clinical practice as a second opinion or as a flag for details that may have been missed at first glance.

Abstract

Colorectal cancer (CRC) diagnosis is based on samples obtained from biopsies, assessed in pathology laboratories. Due to population growth and ageing, as well as better screening programs, the CRC incidence rate has been increasing, leading to a higher workload for pathologists. In this sense, the application of AI for automatic CRC diagnosis, particularly on whole-slide images (WSI), is of utmost relevance, in order to assist professionals in case triage and case review. In this work, we propose an interpretable semi-supervised approach to detect lesions in colorectal biopsies with high sensitivity, based on multiple-instance learning and feature aggregation methods. The model was developed on an extended version of the recent, publicly available CRC dataset (the CRC+ dataset with 4433 WSI), using 3424 slides for training and 1009 slides for evaluation. The proposed method attained 90.19% classification ACC, 98.8% sensitivity, 85.7% specificity, and a quadratic weighted kappa of 0.888 at slide-based evaluation. Its generalisation capabilities are also studied on two publicly available external datasets.

Development and validation of apoptosis-related signature and molecular subtype to improve prognosis prediction in osteosarcoma patients

BACKGROUND

Previous evidence has shown that apoptosis performs integral functions in the tumorigenesis and development of various tumors. Therefore, this study aimed to establish a molecular subtype and prognostic signature based on apoptosis-related genes (ARGs) to understand the molecular mechanisms and predict prognosis in patients with osteosarcoma.

METHODS

The GEO and TARGET databases were utilized to obtain the expression levels of ARGs and clinical information of osteosarcoma patients. Consensus clustering analysis was used to explore the different molecular subtypes based on ARGs. GO, KEGG, GSEA, ESTIMATE, and ssGSEA analyses were performed to examine the differences in biological functions and immune characteristics between the distinct molecular subtypes. Then, we constructed an ARG signature by LASSO analysis. The prognostic significance of the ARG signature in osteosarcoma was determined by Kaplan-Meier plotter, Cox regression, and nomogram analyses.

RESULTS

Two apoptosis-related subtypes were identified. Cluster 1 had a better prognosis, higher immunogenicity, and immune cell infiltration, as well as a better response to immunotherapy than Cluster 2. We discovered that patients in the high-risk cohort had a lower survival rate than those in the low-risk cohort according to the ARG signature. Furthermore, Cox regression analysis confirmed that a high risk score independently acted as an unfavorable prognostic marker. Additionally, the nomogram combining risk scores with clinical characteristics can improve prediction efficiency.

CONCLUSION

We demonstrated that patients suffering from osteosarcoma may be classified into two apoptosis-related subtypes. Moreover, we developed an ARG prognostic signature to predict the prognosis status of osteosarcoma patients.

Current Trend of Artificial Intelligence Patents in Digital Pathology: A Systematic Evaluation of the Patent Landscape

The integration of digital pathology (DP) with artificial intelligence (AI) enables faster, more accurate, and thorough diagnoses, leading to more precise personalized treatment. As technology is advancing rapidly, it is critical to understand the current state of AI applications in DP. Therefore, a patent analysis of AI in DP is required to assess the application and publication trends, major assignees, and leaders in the field. We searched five major patent databases, namely, those of the USPTO, EPO, KIPO, JPO, and CNIPA, from 1974 to 2021, using keywords such as DP, AI, machine learning, and deep learning. We discovered 6284 patents, 523 of which were used for trend analyses on time series, international distribution, top assignees; word cloud analysis; and subject category analyses. Patent filing and publication have increased exponentially over the past five years. The United States has published the most patents, followed by China and South Korea (248, 117, and 48, respectively). The top assignees were Paige.AI, Inc. (New York City, NY, USA) and Siemens, Inc. (Munich, Germany) The primary areas were whole-slide imaging, segmentation, classification, and detection. Based on these findings, we expect a surge in DP and AI patent applications focusing on the digitalization of pathological images and AI technologies that support the vital role of pathologists.

Deep Learning on Histopathological Images for Colorectal Cancer Diagnosis: A Systematic Review

Colorectal cancer (CRC) is the second most common cancer in women and the third most common in men, with an increasing incidence. Pathology diagnosis complemented with prognostic and predictive biomarker information is the first step for personalized treatment. The increased diagnostic load in the pathology laboratory, combined with the reported intra- and inter-variability in the assessment of biomarkers, has prompted the quest for reliable machine-based methods to be incorporated into the routine practice. Recently, Artificial Intelligence (AI) has made significant progress in the medical field, showing potential for clinical applications. Herein, we aim to systematically review the current research on AI in CRC image analysis. In histopathology, algorithms based on Deep Learning (DL) have the potential to assist in diagnosis, predict clinically relevant molecular phenotypes and microsatellite instability, identify histological features related to prognosis and correlated to metastasis, and assess the specific components of the tumor microenvironment.

PARP-1 Expression and BRCA1 Mutations in Breast Cancer Patients' CTCs

Simple Summary

Recent estimates have shown that approx. 70% of individuals with BRCA1 mutations will develop breast cancer by the age of 70. To make matters worse, breast cancer patients with BRCA1 mutations are more likely to have the more aggressive triple-negative breast cancer. PARPs, belong to a family of nuclear enzymes, which are involved in many cellular processes, including DNA repair. PARP inhibitors have been approved for the treatment of BRCA-mutated breast cancer. The aim of the study was the determination of PARP-1 expression in the context of the presence of BRCA1 mutations in circulating tumor cells of breast cancer patients. PARP-1 (nuclear) expression and BRCA1 mutations were mainly detected in triple negative breast cancer patients, and the latter were correlated with decreased survival. Our data suggest that PARP-1, in conjunction with BRCA1, could potentially be used as (a) biomarker(s) for patients’ stratification.

Abstract

BRCA1 and PARP are involved in DNA damage repair pathways. BRCA1 mutations have been linked to higher likelihood of triple negative breast cancer (TNBC). The aim of the study was to determine PARP-1 expression and BRCA1 mutations in circulating tumor cells (CTCs) of BC patients. Fifty patients were enrolled: 23 luminal and 27 TNBC. PARP expression in CTCs was identified by immunofluorescence. Genotyping was performed by PCR-Sanger sequencing in the same samples. PARP-1 expression was higher in luminal (61%) and early BC (54%), compared to TNBC (41%) and metastatic (33%) patients. In addition, PARP-1 distribution was mostly cytoplasmic in luminal patients (p = 0.024), whereas it was mostly nuclear in TNBC patients. In cytokeratin (CK)-positive patients, those with the CK⁺PARP⁺ phenotype had longer overall survival (OS, log-rank p = 0.046). Overall, nine mutations were detected; M1 and M2 were completely new and M4, M7 and M8 were characterized as pathogenic. M7 and M8 were predominantly found in metastatic TNBC patients (p = 0.014 and p = 0.002). Thus, PARP-1 expression and increased mutagenic burden in TNBC patients’ CTCs, could be used as an indicator to stratify patients regarding therapeutic approaches.

Applications of Artificial Intelligence in Screening, Diagnosis, Treatment, and Prognosis of Colorectal Cancer

Colorectal cancer (CRC) is one of the most common cancers worldwide. Accurate early detection and diagnosis, comprehensive assessment of treatment response, and precise prediction of prognosis are essential to improve the patients’ survival rate. In recent years, due to the explosion of clinical and omics data, and groundbreaking research in machine learning, artificial intelligence (AI) has shown a great application potential in clinical field of CRC, providing new auxiliary approaches for clinicians to identify high-risk patients, select precise and personalized treatment plans, as well as to predict prognoses. This review comprehensively analyzes and summarizes the research progress and clinical application value of AI technologies in CRC screening, diagnosis, treatment, and prognosis, demonstrating the current status of the AI in the main clinical stages. The limitations, challenges, and future perspectives in the clinical implementation of AI are also discussed.

A deep learning model for molecular label transfer that enables cancer cell identification from histopathology images

Deep-learning classification systems have the potential to improve cancer diagnosis. However, development of these computational approaches so far depends on prior pathological annotations and large training datasets. The manual annotation is low-resolution, time-consuming, highly variable and subject to observer variance. To address this issue, we developed a method, H&E Molecular neural network (HEMnet). HEMnet utilizes immunohistochemistry as an initial molecular label for cancer cells on a H&E image and trains a cancer classifier on the overlapping clinical histopathological images. Using this molecular transfer method, HEMnet successfully generated and labeled 21,939 tumor and 8782 normal tiles from ten whole-slide images for model training. After building the model, HEMnet accurately identified colorectal cancer regions, which achieved 0.84 and 0.73 of ROC AUC values compared to p53 staining and pathological annotations, respectively. Our validation study using histopathology images from TCGA samples accurately estimated tumor purity, which showed a significant correlation (regression coefficient of 0.8) with the estimation based on genomic sequencing data. Thus, HEMnet contributes to addressing two main challenges in cancer deep-learning analysis, namely the need to have a large number of images for training and the dependence on manual labeling by a pathologist. HEMnet also predicts cancer cells at a much higher resolution compared to manual histopathologic evaluation. Overall, our method provides a path towards a fully automated delineation of any type of tumor so long as there is a cancer-oriented molecular stain available for subsequent learning. Software, tutorials and interactive tools are available at: https://github.com/BiomedicalMachineLearning/HEMnet.

The fine-needle aspiration cytology and clinical findings of Kikuchi-Fujimoto disease in pediatric patients: a retrospective clinical study

BACKGROUND

Histological evaluation of lymph node is crucial for the definitive diagnosis of Kikuchi-Fujimoto disease (KFD). However, lymph node biopsy under local anesthesia is often difficult in pediatric patients.

OBJECTIVES

We evaluated cytological findings for pediatric patients with prolonged cervical lymphadenitis clinically suggestive of KFD and investigated the clinical characteristics of patients diagnosed with KFD by fine-needle aspiration cytology (FNAC).

METHODS

This retrospective clinical study included 58 Japanese pediatric patients with cervical lymphadenitis who underwent FNAC.

RESULTS

Cytological diagnosis was KFD for 22 and suspicion of KFD for 11 patients. The remaining 25 patients were diagnosed with non-specific lymphadenitis (NSL). Tenderness was independently associated with a higher frequency of both KFD in narrow and broad senses, compared with NSL (p = .009; p = .038). The percentage of patients who underwent FNAC within 28 days from symptom onset tended to be higher among patients with KFD in a narrow sense than those with NSL (p = .052).

CONCLUSION

This study indicated that the period from symptom onset to FNAC (<28 days) and the symptom of tenderness were associated with the cytological diagnosis of KFD.

Kikuchi Disease in Children: Case Report and Review of the Literature

BACKGROUND

Kikuchi disease (KD) is a rare and generally benign condition of uncertain etiology that presents with nonspecific symptoms including fever and cervical lymphadenopathy. Clinical presentations can vary. Here, we present an atypical case of KD in a 10-year-old girl, as well as an updated literature review of the clinical presentation, laboratory features and management of KD in children.

METHODS

Studies (published up until February 2020) were identified through searches of PubMed using the following search items: Kikuchi-Fujimoto disease or histiocytic necrotizing lymphadenitis or Kikuchi disease. Our primary search resulted in 1117 publications. A total of 34 publications with a total of 670 patients were included in the final analysis.

RESULTS

All children present with lymphadenopathy. Almost all (96.3%) have cervical lymphadenopathy. Fever is recorded in the majority of children (77.1%). Analysis of laboratory features found that the majority of children have leukopenia (56.0%) and a raised erythrocyte sedimentation rate (56.0%). Over 30% have a raised C-reactive protein and anemia. Other features such as leukocytosis, thrombocytopenia and antinuclear antibodies positivity are less common. KD is mostly self-limiting, but steroids, hydroxychloroquine and intravenous immunoglobulin are used in protracted courses. Their efficacy has yet to be established in clinical trials.

CONCLUSIONS

The presentation of KD is variable, and there is no specific set of symptoms or laboratory features that reliably establishes the diagnosis. Thus, histopathology is crucial. Definitive evaluation and establishment of effective treatments will require future prospective research studies for a more comprehensive description of the clinical course and effects of treatment. Given the rarity of the disease, this will have to be performed in collaborative consortia.

Clinical Analysis of 44 Children with Subacute Necrotizing Lymphadenitis

Objective

Methods

Results

Conclusion

Automated Diagnosis of Cervical Intraepithelial Neoplasia in Histology Images via Deep Learning

Artificial intelligence has enabled the automated diagnosis of several cancer types. We aimed to develop and validate deep learning models that automatically classify cervical intraepithelial neoplasia (CIN) based on histological images. Microscopic images of CIN3, CIN2, CIN1, and non-neoplasm were obtained. The performances of two pre-trained convolutional neural network (CNN) models adopting DenseNet-161 and EfficientNet-B7 architectures were evaluated and compared with those of pathologists. The dataset comprised 1106 images from 588 patients; images of 10% of patients were included in the test dataset. The mean accuracies for the four-class classification were 88.5% (95% confidence interval [CI], 86.3–90.6%) by DenseNet-161 and 89.5% (95% CI, 83.3–95.7%) by EfficientNet-B7, which were similar to human performance (93.2% and 89.7%). The mean per-class area under the receiver operating characteristic curve values by EfficientNet-B7 were 0.996, 0.990, 0.971, and 0.956 in the non-neoplasm, CIN3, CIN1, and CIN2 groups, respectively. The class activation map detected the diagnostic area for CIN lesions. In the three-class classification of CIN2 and CIN3 as one group, the mean accuracies of DenseNet-161 and EfficientNet-B7 increased to 91.4% (95% CI, 88.8–94.0%), and 92.6% (95% CI, 90.4–94.9%), respectively. CNN-based deep learning is a promising tool for diagnosing CIN lesions on digital histological images.

Kikuchi-Fujimoto disease in the Eastern Mediterranean zone

Kikuchi–Fujimoto disease (KFD) is a rare benign and self-limiting syndrome. We aim to review cases of KFD at our institution as a rare illness in the Arab ethnic descent and to analyse reports from most countries in the East Mediterranean zone. This is a retrospective study in which the histopathology database was searched for the diagnosis of KFD. A full review of KFD patients’ medical records was done. Data regarding demographic features, clinical presentation, laboratory findings, comorbidities, and management protocols were obtained. Published KFD cases from east Mediterranean countries were discussed and compared to other parts of the world. Out of 1968 lymph node biopsies studied, 11 (0.6%) cases of KFD were identified. The mean age of patients with KFD was 32 years (4–59). 73% (8/11) were females. The disease was self-limiting in 5 patients (45%); corticosteroid therapy was needed in 4 patients (34%). One patient was treated with methotrexate and one with antibiotics. One patient died as a consequence of lymphoma. Jordanians and Mediterranean populations, especially those of Arab ethnic background, seem to have low rates of KFD. The genetic susceptibility theory may help to explain the significantly higher disease prevalence among East Asians. Early diagnosis of KFD—although challenging—is essential to reduce the morbidity related to this illness.

The fractal and textural analysis of glomeruli in obese and non-obese patients

Background

Fractal dimension is an indirect indicator of signal complexity. The aim was to evaluate the fractal and textural analysis parameters of glomeruli in obese and non-obese patients with glomerular diseases and association of these parameters with clinical features.

Methods

The study included 125 patients mean age 46 ± 15.2 years: obese (BMI ≥ 27 kg/m²—63 patients) and non-obese (BMI < 27 kg/m²—62 patients). Serum concentration of creatinine, protein, albumin, cholesterol, trygliceride, and daily proteinuria were measured. Formula Chronic Kidney Disease Epidemiology Colaboration (CKD-EPI) equation was calculated. Fractal (fractal dimension, lacunarity) and textural (angular second moment (ASM), textural correlation (COR), inverse difference moment (IDM), textural contrast (CON), variance) analysis parameters were compared between two groups.

Results

Obese patients had higher mean value of variance (t = 1.867), ASM (t = 1.532) and CON (t = 0.394) but without significant difference (P > 0.05) compared to non-obese. Mean value of COR (t = 0.108) and IDM (t = 0.185) were almost the same in two patient groups. Obese patients had higher value of lacunarity (t = 0.499) in comparison with non-obese, the mean value of fractal dimension (t = 0.225) was almost the same in two groups. Significantly positive association between variance and creatinine concentration (r = 0.499, P < 0.01), significantly negative association between variance and CKD-EPI (r = -0.448, P < 0.01), variance and sex (r = -0.339, P < 0.05) were found.

Conclusions

Variance showed significant correlation with serum creatinine concentration, CKD-EPI and sex. CON and IDM were significantly related to sex. Fractal and textural analysis parameters of glomeruli could become a supplement to histopathologic analysis of kidney tissue.

•

Variance showed significant correlation with eGFR calculated by CKD- EPI formula.

•

Significant correlation between variance and serum creatinine was found.

•

Textural contrast and inverse difference moment were significantly related to sex.

•

Fractal analysis of glomeruli could become supplement to histopathologic analysis.

•

Textural analyses of kidney tissue should become useful to histopathologic analysis.

Artificial intelligence in pathological evaluation of gastrointestinal cancers

The integration of artificial intelligence (AI) has shown promising benefits in many fields of diagnostic histopathology, including for gastrointestinal cancers (GCs), such as tumor identification, classification, and prognosis prediction. In parallel, recent evidence suggests that AI may help reduce the workload in gastrointestinal pathology by automatically detecting tumor tissues and evaluating prognostic parameters. In addition, AI seems to be an attractive tool for biomarker/genetic alteration prediction in GC, as it can contain a massive amount of information from visual data that is complex and partially understandable by pathologists. From this point of view, it is suggested that advances in AI could lead to revolutionary changes in many fields of pathology. Unfortunately, these findings do not exclude the possibility that there are still many hurdles to overcome before AI applications can be safely and effectively applied in actual pathology practice. These include a broad spectrum of challenges from needs identification to cost-effectiveness. Therefore, unlike other disciplines of medicine, no histopathology-based AI application, including in GC, has ever been approved either by a regulatory authority or approved for public reimbursement. The purpose of this review is to present data related to the applications of AI in pathology practice in GC and present the challenges that need to be overcome for their implementation.

Artificial intelligence, machine learning, and deep learning for clinical outcome prediction

AI is a broad concept, grouping initiatives that use a computer to perform tasks that would usually require a human to complete. AI methods are well suited to predict clinical outcomes. In practice, AI methods can be thought of as functions that learn the outcomes accompanying standardized input data to produce accurate outcome predictions when trialed with new data. Current methods for cleaning, creating, accessing, extracting, augmenting, and representing data for training AI clinical prediction models are well defined. The use of AI to predict clinical outcomes is a dynamic and rapidly evolving arena, with new methods and applications emerging. Extraction or accession of electronic health care records and combining these with patient genetic data is an area of present attention, with tremendous potential for future growth. Machine learning approaches, including decision tree methods of Random Forest and XGBoost, and deep learning techniques including deep multi-layer and recurrent neural networks, afford unique capabilities to accurately create predictions from high dimensional, multimodal data. Furthermore, AI methods are increasing our ability to accurately predict clinical outcomes that previously were difficult to model, including time-dependent and multi-class outcomes. Barriers to robust AI-based clinical outcome model deployment include changing AI product development interfaces, the specificity of regulation requirements, and limitations in ensuring model interpretability, generalizability, and adaptability over time.

Various Uses of PD1/PD-L1 Inhibitor in Oncology: Opportunities and Challenges

The occurrence and development of cancer are closely related to the immune escape of tumor cells and immune tolerance. Unlike previous surgical, chemotherapy, radiotherapy and targeted therapy, tumor immunotherapy is a therapeutic strategy that uses various means to stimulate and enhance the immune function of the body, and ultimately achieves the goal of controlling tumor cells.With the in-depth understanding of tumor immune escape mechanism and tumor microenvironment, and the in-depth study of tumor immunotherapy, immune checkpoint inhibitors represented by Programmed Death 1/Programmed cell Death-Ligand 1(PD-1/PD-L1) inhibitors are becoming increasingly significant in cancer medication treatment. employ a variety of ways to avoid detection by the immune system, a single strategy is not more effective in overcoming tumor immune evasion and metastasis. Combining different immune agents or other drugs can effectively address situations where immunotherapy is not efficacious, thereby increasing the chances of success and alternative access to alternative immunotherapy. Immune combination therapies for cancer have become a hot topic in cancer treatment today. In this paper, several combination therapeutic modalities of PD1/PD-L1 inhibitors are systematically reviewed. Finally, an analysis and outlook are provided in the context of the recent advances in combination therapy with PD1/PD-L1 inhibitors and the pressing issues in this field.

Advances in Digital Pathology: From Artificial Intelligence to Label-Free Imaging

BACKGROUND

Digital pathology, in its primary meaning, describes the utilization of computer screens to view scanned histology slides. Digitized tissue sections can be easily shared for a second opinion. In addition, it allows tissue image analysis using specialized software to identify and measure events previously observed by a human observer. These tissue-based readouts were highly reproducible and precise. Digital pathology has developed over the years through new technologies. Currently, the most discussed development is the application of artificial intelligence to automatically analyze tissue images. However, even new label-free imaging technologies are being developed to allow imaging of tissues by means of their molecular composition.

SUMMARY

This review provides a summary of the current state-of-the-art and future digital pathologies. Developments in the last few years have been presented and discussed. In particular, the review provides an outlook on interesting new technologies (e.g., infrared imaging), which would allow for deeper understanding and analysis of tissue thin sections beyond conventional histopathology.

KEY MESSAGES

In digital pathology, mathematical methods are used to analyze images and draw conclusions about diseases and their progression. New innovative methods and techniques (e.g., label-free infrared imaging) will bring significant changes in the field in the coming years.

Deep learning-based histopathological segmentation for whole slide images of colorectal cancer in a compressed domain

Automatic pattern recognition using deep learning techniques has become increasingly important. Unfortunately, due to limited system memory, general preprocessing methods for high-resolution images in the spatial domain can lose important data information such as high-frequency information and the region of interest. To overcome these limitations, we propose an image segmentation approach in the compressed domain based on principal component analysis (PCA) and discrete wavelet transform (DWT). After inference for each tile using neural networks, a whole prediction image was reconstructed by wavelet weighted ensemble (WWE) based on inverse discrete wavelet transform (IDWT). The training and validation were performed using 351 colorectal biopsy specimens, which were pathologically confirmed by two pathologists. For 39 test datasets, the average Dice score, the pixel accuracy, and the Jaccard score were 0.804 ± 0.125, 0.957 ± 0.025, and 0.690 ± 0.174, respectively. We can train the networks for the high-resolution image with the large region of interest compared to the result in the low-resolution and the small region of interest in the spatial domain. The average Dice score, pixel accuracy, and Jaccard score are significantly increased by 2.7%, 0.9%, and 2.7%, respectively. We believe that our approach has great potential for accurate diagnosis.