Classification Of Tumor Types Research Articles

An Effective analysis of brain tumor detection using deep learning

INTRODUCTION: Cancer remains a significant health concern, with early detection crucial for effective treatment. Brain tumors, in particular, require prompt diagnosis to improve patient outcomes. Computational models, specifically deep learning (DL), have emerged as powerful tools in medical image analysis, including the detection and classification of brain tumors. DL leverages multiple processing layers to represent data, enabling enhanced performance in various healthcare applications.
 OBJECTIVES: This paper aims to discuss key topics in DL relevant to the analysis of brain tumors, including segmentation, prediction, classification, and assessment. The primary objective is to employ magnetic resonance imaging (MRI) pictures for the identification and categorization of brain malignancies. By reviewing prior research and findings comprehensively, this study provides valuable insights for academics and professionals in deep learning seeking to contribute to brain tumor identification and classification.
 METHODS: The methodology involves a systematic review of existing literature on DL applications in brain tumor analysis, focusing on MRI imaging. Various DL techniques, including convolutional neural networks (CNNs), recurrent neural networks (RNNs), and hybrid models, are explored for their efficacy in tasks such as tumor segmentation, prediction of tumor characteristics, classification of tumor types, and assessment of treatment response.
 RESULTS: The review reveals significant advancements in DL-based approaches for brain tumor analysis, with promising results in segmentation accuracy, tumor subtype classification, and prediction of patient outcomes. Researchers have developed sophisticated DL architectures tailored to address the complexities of brain tumor imaging data, leading to improved diagnostic capabilities and treatment planning.
 CONCLUSION: Deep learning holds immense potential for revolutionizing the diagnosis and management of brain tumors through MRI-based analysis. This study underscores the importance of leveraging DL techniques for accurate and efficient brain tumor identification and classification. By synthesizing prior research and highlighting key findings, this paper provides valuable guidance for researchers and practitioners aiming to contribute to the field of medical image analysis and improve outcomes for patients with brain malignancies.

Utilizing the amide proton transfer technique to characterize diffuse gliomas based on the WHO 2021 classification of CNS tumors.

Diffuse gliomas present a significant challenge for healthcare systems globally. While brain MRI plays a vital role in diagnosis, prognosis, and treatment monitoring, accurately characterizing gliomas using conventional MRI techniques alone is challenging. In this study, we explored the potential of utilizing the amide proton transfer (APT) technique to predict tumor grade and type based on the WHO 2021 Classification of CNS Tumors. Forty-two adult patients with histopathologically confirmed brain gliomas were included in the study. They underwent 3T MRI imaging, which involved APT sequence. Multinomial and binary logistic regression models were employed to classify patients into clinically relevant groups based on MRI findings and demographic variables. We found that the best model for tumor grade classification included patient age along with APT values. The highest sensitivity (88%) was observed for Grade 4 tumors, while Grade 3 tumors showed the highest specificity (79%). For tumor type classification, our model incorporated four predictors: APT values, patient's age, necrosis, and the presence of hemorrhage. The glioblastoma group had the highest sensitivity and specificity (87%), whereas balanced accuracy was the lowest for astrocytomas (0.73). The APT technique shows great potential for noninvasive evaluation of diffuse gliomas. The changes in the classification of gliomas as per the WHO 2021 version of the CNS Tumor Classification did not affect its usefulness in predicting tumor grade or type.

A hybrid thyroid tumor type classification system using feature fusion, multilayer perceptron and bonobo optimization.

Thyroid tumor is considered to be a very rare form of cancer. But recent researches and surveys highlight the fact that it is becoming prevalent these days because of various factors. This paper proposes a novel hybrid classification system that is able to identify and classify the above said four different types of thyroid tumors using high end artificial intelligence techniques. The input data set is obtained from Digital Database of Thyroid Ultrasound Images through Kaggle repository and augmented for achieving a better classification performance using data warping mechanisms like flipping, rotation, cropping, scaling, and shifting. The input data after augmentation goes through preprocessing with the help of bilateral filter and is contrast enhanced using dynamic histogram equalization. The ultrasound images are then segmented using SegNet algorithm of convolutional neural network. The features needed for thyroid tumor classification are obtained from two different algorithms called CapsuleNet and EfficientNetB2 and both the features are fused together. This process of feature fusion is carried out to heighten the accuracy of classification. A Multilayer Perceptron Classifier is used for classification and Bonobo optimizer is employed for optimizing the results produced. The classification performance of the proposed model is weighted using metrics like accuracy, sensitivity, specificity, F1-score, and Matthew's correlation coefficient. It can be observed from the results that the proposed multilayer perceptron based thyroid tumor type classification system works in an efficient manner than the existing classifiers like CANFES, Spatial Fuzzy C means, Deep Belief Networks, Thynet and Generative adversarial network and Long Short-Term memory.

Classification of tumor types using XGBoost machine learning model: a vector space transformation of genomic alterations

BackgroundMachine learning (ML) represents a powerful tool to capture relationships between molecular alterations and cancer types and to extract biological information. Here, we developed a plain ML model aimed at distinguishing cancer types based on genetic lesions, providing an additional tool to improve cancer diagnosis, particularly for tumors of unknown origin.MethodsTCGA data from 9,927 samples spanning 32 different cancer types were downloaded from cBioportal. A vector space model type data transformation technique was designed to build consistently homogeneous new datasets containing, as predictive features, calls for somatic point mutations and copy number variations at chromosome arm-level, thus allowing the use of the XGBoost classifier models. Considering the imbalance in the dataset, due to large difference in the number of cases for each tumor, two preprocessing strategies were considered: i) setting a percentage cut-off threshold to remove less represented cancer types, ii) dividing cancer types into different groups based on biological criteria and training a specific XGBoost model for each of them. The performance of all trained models was mainly assessed by the out-of-sample balanced accuracy (BACC) and the AUC scores.ResultsThe XGBoost classifier achieved the best performance (BACC 77%; AUC 97%) on a dataset containing the 10 most represented tumor types. Moreover, dividing the 18 most represented cancers into three different groups (endocrine-related carcinomas, other carcinomas and other cancers),such analysis models achieved 78%, 71% and 86% BACC, respectively, with AUC scores greater than 96%. In addition, the model capable of linking each group to a specific cancer type reached 81% BACC and 94% AUC. Overall, the diagnostic potential of our model was comparable/higher with respect to others already described in literature and based on similar molecular data and ML approaches.ConclusionsA boosted ML approach able to accurately discriminate different cancer types was developed. The methodology builds datasets simpler and more interpretable than the original data, while keeping enough information to accurately train standard ML models without resorting to sophisticated Deep Learning architectures. In combination with histopathological examinations, this approach could improve cancer diagnosis by using specific DNA alterations, processed by a replicable and easy-to-use automated technology. The study encourages new investigations which could further increase the classifier’s performance, for example by considering more features and dividing tumors into their main molecular subtypes.

ConvAttenMixer: Brain tumor detection and type classification using convolutional mixer with external and self-attention mechanisms

Attention-based methods have recently demonstrated notable advancements in brain tumor classification. To further advance and strengthen this development, we have developed ConvAttenMixer, a transformer model that incorporates convolutional layers along with two attention mechanisms: self-attention and external attention. The proposed model utilizes two blocks of convolution mixers to effectively process and blend across patches, thereby enhancing the model's ability to capture spatial and channel-wise dependencies in MRI brain images. The self-attention block enables the model to prioritize important regions within the image and establish dependencies by assigning weights to each part based on their relevance to the task. This allows the model to emphasize crucial local features, disregard irrelevant ones, and capture interactions between different patches. On the other hand, the external attention block focuses more on significant global features and captures interactions among different images, enabling the model to establish dependencies and correlations across all samples. The classification head in the proposed model is a simple yet effective block designed to process the output feature maps using a squeeze-and-excitation mechanism, which in turn assigns higher weights to important channels and suppresses less-relevant channels. For experimentation, our ConvAttenMixer model was trained on a dataset consisting of 5712 MRI scans and subsequently tested on 1311 scans for classification into glioma, meningioma, pituitary tumor, and no-tumor images. Different variants of the proposed model were tested and evaluated. The optimally performing architecture was evaluated against the state-of-the-art baselines, namely self-attention MLP, external attention MLP, attention-based pooling convolutional net, and convolutional mixer net. Extensive experiments demonstrated that ConvAttenMixer outperformed the other baselines, which employed either self-attention or external attention mechanisms, while requiring significantly less computational memory. The suggested model exhibited higher precision, recall, and f-measure, achieving the highest accuracy of 0.9794 compared with the baselines' accuracy, which ranged from 0.87 to 0.93. The ConvAttenMixer model demonstrates the ability to operate locally on the patch level using self-attention and globally on the sample level using external attention, as well as prioritize important information on the spatial level and channel level using convolution mixers and the squeeze-and-excitation mechanism.

Ultrasonographic diagnosis of adnexal masses: interobserver agreement in the interpretation of videos, using IOTA terminology

ObjectivesAim of this study is to estimate interobserver agreement in classifying adnexal tumors using IOTA terms, simple rules and subjective assessment. In addition, we related observers’ accuracy with their experience in gynecological ultrasonography and the year of IOTA certification.MethodsEleven observers with three different levels of experience evaluated videoclips of 70 adnexal masses, defining tumor type according to IOTA terms and definitions, classifying the mass using IOTA Simple rules and Subjective assessment as well as providing Color Score evaluation. Sensitivity, specificity and area under the ROC curve were calculated and the year of IOTA certification was related with operators’ accuracy through Pearson correlation coefficient. Interobserver agreement was estimated calculating percentage of agreement, Fleiss kappa and Cohen’s kappa.ResultsWe found a positive correlation between the year of IOTA certification and operators’ accuracy (Pearson coefficient 0.694), especially among the observers with the least experience, the residents (p = 0.003). For tumor type classification, identification of papillary projections and classification of tumors using subjective assessment, agreement among all observers was moderate (Fleiss kappa 0.455, 0.552, and 0.476, respectively) and increased with the years of experience. Agreement in the application of Simple Rules was moderate in all examiners with IOTA certification, with Fleiss kappa in the range of (0.403, 0.498). For Color Score assignment interobserver agreement among all observers was fair (Cohen’s kappa 0.380).ConclusionsEven among expert examiners, the results of adnexal lesion assessment can be inconsistent. Experience impacts on accuracy and agreement in subjective assessment, while the application of Simple Rules can mitigate the role of experience in interobserver agreement. The knowledge of IOTA models among residents seams to improve their diagnostic accuracy, showing the benefits of IOTA terminology for in training sonographers.

Advances on Liquid Biopsy Analysis for Glioma Diagnosis.

Gliomas comprise the most frequent primary central nervous system (CNS) tumors, characterized by remarkable genetic and epigenetic heterogeneity, difficulty in monitoring, and increased relapse and mortality rates. Tissue biopsy is an established method of tumor cell collection and analysis that enables diagnosis, classification of different tumor types, and prediction of prognosis upon confirmation of tumor's location for surgical removal. However, it is an invasive and often challenging procedure that cannot be used for frequent patient screening, detection of mutations, disease monitoring, or resistance to therapy. To this end, the minimally invasive procedure of liquid biopsy has emerged, allowing effortless tumor sampling and enabling continuous monitoring. It is considered a novel preferable way to obtain faster data on potential tumor risk, personalized diagnosis, prognosis, and recurrence evaluation. The purpose of this review is to describe the advances on liquid biopsy for glioma diagnosis and management, indicating several biomarkers that can be utilized to analyze tumor characteristics, such as cell-free DNA (cfDNA), cell-free RNA (cfRNA), circulating proteins, circulating tumor cells (CTCs), and exosomes. It further addresses the benefit of combining liquid biopsy with radiogenomics to facilitate early and accurate diagnoses, enable precise prognostic assessments, and facilitate real-time disease monitoring, aiming towards more optimal treatment decisions.

Opportunities and Advances in Radiomics and Radiogenomics for Pediatric Medulloblastoma Tumors.

Recent advances in artificial intelligence have greatly impacted the field of medical imaging and vastly improved the development of computational algorithms for data analysis. In the field of pediatric neuro-oncology, radiomics, the process of obtaining high-dimensional data from radiographic images, has been recently utilized in applications including survival prognostication, molecular classification, and tumor type classification. Similarly, radiogenomics, or the integration of radiomic and genomic data, has allowed for building comprehensive computational models to better understand disease etiology. While there exist excellent review articles on radiomics and radiogenomic pipelines and their applications in adult solid tumors, in this review article, we specifically review these computational approaches in the context of pediatric medulloblastoma tumors. Based on our systematic literature research via PubMed and Google Scholar, we provide a detailed summary of a total of 15 articles that have utilized radiomic and radiogenomic analysis for survival prognostication, tumor segmentation, and molecular subgroup classification in the context of pediatric medulloblastoma. Lastly, we shed light on the current challenges with the existing approaches as well as future directions and opportunities with using these computational radiomic and radiogenomic approaches for pediatric medulloblastoma tumors.

Software for brain tumor diagnosis on magnetic resonance imaging

BACKGROUND: The main reason for the development and implementation of artificial intelligence (AI) technologies in neuro-oncology is the high prevalence of brain tumors reaching up to 200 cases per 100,000 population. The incidence of a primary focus in the brain is 5%10%; however, 60%70% of those who die from malignant neoplasms have metastases in the brain. Magnetic resonance imaging (MRI) is the most common method for primary non-invasive diagnosis of brain tumors and monitoring disease progression. One of the challenges is the classification of tumor types and determination of clinical parameters (size and volume) for the conduct, diagnosis, and treatment procedures, including surgery.
 AIM: To develope a software module for the differential diagnosis of brain neoplasms on MRI images.
 METHODS: The software module is based on the developed Siberian Brain Tumor Dataset (SBT), which contains information on over 1000 neurosurgical patients with fully verified (histologically and immunohistochemically) postoperative diagnoses. The data for research and development was presented by the Federal Neurosurgical Center (Novosibirsk). The module uses two- and three-dimensional computer vision models with pre-processed MRI sequence data included in the following packages: pre-contrast T1-weighted image (WI), post-contrast T1-WI, T2-WI, and T2-WI with fluid-attenuated inversion-recovery technique. The models allow to detect and recognize with high accuracy 4 types of neoplasms, such as meningioma, neurinoma, glioblastoma, and astrocytoma, and segment and distinguish components and sizes: ET (tumor core absorbing Gd-containing contrast), TC (tumor core) = ET + Necr (necrosis) + NenTu, and WT (whole tumor) = TC + Ed (peritumoral edema).
 RESULTS: The developed software module shows high segmentation results on SBT by Dice metric for ET 0.846, TC 0.867, WT 0.9174, Sens 0.881, and Spec 1.000 areas. The testing and validation were done at the international BraTS Challenge 2021 competition. The test dataset yielded DiceET 0.86588, DiceTC 0.86932, and DiceWT 0.921 values, placing the developed software module in the top ten. According to the classification, the results demonstrate high accuracy rates of up to 92% in patient analysis (up to 89% in slice analysis), a very high potential, and a perspective for future research in this area.
 CONCLUSIONS: The developed software module may be used for training specialists and in clinical diagnostics.

Abstract 5440: Deep-learning model for tumor type classification enables enhanced clinical decision support in cancer diagnosis

Abstract Background: Knowledge of a patient’s tumor type is essential for guiding clinical treatment decisions in cancer, but histologically-based diagnosis remains challenging for a subset of cancers. Genomic alterations are highly indicative of tumor type and can be used to build classifiers that predict diagnoses, but most genomic-based classification methods use whole genome sequencing (WGS) data which is not feasible for widespread clinical implementation at present. Clinical sequencing is typically performed using cancer gene panels that target individual mutations, often drivers, but previous tumor type classifiers developed using driver-based features alone perform poorly. We hypothesize that a classifier developed using state-of-the-art deep-learning methods and a sufficiently large training cohort would be able to overcome previous accuracy limitations and support the development of a clinically-relevant tumor type prediction model. Methods: We present Deep Genome-Derived Diagnosis (GDD-ENS), an ensemble-based deep-learning tumor type classification method trained using data from cancer gene panel sequencing. We specifically use data from MSK-IMPACT, an FDA-authorized clinical sequencing assay that reports genomic alterations including mutations, indels, copy number alterations, and gene fusions across 505 cancer-associated genes. We aggregated a discovery cohort of 35,372 patients with solid tumors profiled with MSK-IMPACT across 38 common cancer types and used this set to generate 4,487 somatic mutation features for development. Results: GDD-ENS achieves 78.8% accuracy on a held out validation cohort of 6971 patients. For the 71.9% of predictions assigned a high confidence by the model, accuracy increases to 92.7%, rivaling WGS-based models. We use Shapley Values to report prediction-specific feature importance, and aggregate them across cancer types to show GDD-ENS identifies known cancer type-genomic alteration trends. GDD-ENS also, with high accuracy, identifies patients with cancer types not included in the 38 common types using metrics derived from ensemble statistics. For patients where non-genomic information could further guide predictions, we implement a customizable prediction-specific adaptive prior distribution and report improved accuracy after adjusting predictions to account for features such as metastatic sample biopsy site. Finally, we apply GDD-ENS to a set of 1,123 patients with Cancers of Unknown Primary (CUP) and return high confidence predictions for 49% of these patients, in some cases matching predictions on CUP samples with diagnoses that were later confirmed through additional sampling and disease progression. Conclusions: Integrating GDD-ENS into prospective clinical sequencing workflows will enable clinically-relevant tumor type predictions that can guide treatment decisions in real-time. Citation Format: Madison Darmofal, Shalabh Suman, Gurnit Atwal, Jie-Fu Chen, Anna Varghese, Jason C. Chang, Anoop Balakrishnan Rema, Aijazuddin Syed, Quaid Morris, Michael Berger. Deep-learning model for tumor type classification enables enhanced clinical decision support in cancer diagnosis. [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2023; Part 1 (Regular and Invited Abstracts); 2023 Apr 14-19; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2023;83(7_Suppl):Abstract nr 5440.

Automatic Detection of Benign Brain Tumors Using Statistical Analysis

Tumor is an uncontrolled growth of harmful cells within the skull that raises intracranial pressure. In the field of medical research, medical picture classification is critical. Imaging plays a crucial role in the diagnosis of brain tumors. Magnetic resonance imaging is a noninvasive, 3-dimensional imaging technique that produces high-quality images. The interpretation of an image might not be completely precise and require the assistance of a second opinion, variability in diagnosis made by different doctors and even by the same doctor under different circumstances due to job load, observation accuracy for the physician, picture clarity, noise, or the physician's vision or mood. Based on the previously mentioned reasons, we have developed a computer-aided diagnosis system to aid in the identification or detection of benign tumor in brain magnetic resonance imaging scans. In the first stage of this study, image enhancement and correct segmentation processes have been conducted into the images in order to facilitate the system to give an accurate classification of brain tumor type. In the second stage, we investigated several statistical features using a technique called gray-level co-occurrence matrix. The implementation of this technique was done with software called MATLAB (Matrix Laboratory) to determine the best features for diagnosing benign tumors of the brain. Gray-level co-occurrence matrix is second-order statistical analysis that describes spatial relationships and the information about the pixel position that has a similar gray-level value; we have found that some features have a big cutoff range between normal and abnormal tissues. Classification was done using back-propagation artificial neural network. The detection findings and quantitative data analysis show that our suggested system is effective, with a detection accuracy of 99.8%.

Brain tumor segmentation by cascaded multiscale multitask learning framework based on feature aggregation

Brain tumor analysis in MRI images is a significant and challenging issue because misdiagnosis can lead to death. Diagnosis and evaluation of brain tumors in the early stages increase the probability of successful treatment. However, the complexity and variety of tumors, shapes, and locations make their segmentation and classification complex. Numerous researchers have proposed brain tumor segmentation and classification methods in this regard. This paper presents an approach that simultaneously segments and classifies brain tumors in MRI images using a framework that contains MRI image enhancement and tumor region detection. Eventually, a network based on a multitask learning approach is proposed. The proposed network, called Multiscale Cascaded Multitask Network, is based on a multitask learning approach containing segmentation and classification tasks. A multiscale approach and cascade approach in layers of encoder and decoder have been applied to improve segmentation accuracy in the proposed network. In addition, to increase the classification accuracy, a feature aggregation module has been introduced that integrates different levels of features to better tumor type classification. Simultaneously learning the two tasks of segmentation and classification, along with applying the mentioned approaches, has improved the results in both tasks. Subjective and objective results indicate that the segmentation and classification results based on evaluation metrics are better or comparable to the state-of-the-art. Our proposed method has reached 96.27 and 95.88 for DCS and mean IoU, respectively, for segmentation and 97.988 accuracies for classification.

The Current State of Adult Glial Tumor Patients' Care in Kazakhstan: Challenges in Diagnosis and Patterns in Survival Outcomes.

The study aimed to analyze the 5-year survival of adult patients with glial tumors and to define characteristics that are associated with the disease outcomes in Kazakhstan. Medical records of patients that were surgically treated at the National Center for Neurosurgery during the 5-year period from 2016 to 2020 were collected retrospectively. Patients with a histologically confirmed diagnosis of diffuse astrocytic or oligodendroglial tumor type were included and their survival was assessed with life tables, Kaplan-Meier plot, and Cox regression using STATA 16 statistical software. Almost half of the patients had glioblastoma. The 5-year survival rate of the whole sample was 45.93%. Among Grade 4 patients, 15.6% survived the 5-year mark. Differences in survival between grades 1-3 were not significant. Grade 1 patients demonstrated worse survival rates compared to Grade 2 patients (69% vs. 74%). Worse survival rates were observed among patients of Russian ethnicity and in rural residents. The study described the unusual patterns in survival rates of glial tumor patients in Kazakhstan, pointing to the need for reassessment of diagnostic accuracy and resulting treatment of glial patients in Kazakhstan, and the need to introduce molecular and genetic parameters in tumor type classification. Moreover, the observed difference in survival of different ethnic groups and residents of rural and urban areas should be further investigated and addressed by healthcare professionals.

CustOmics: A versatile deep-learning based strategy for multi-omics integration

The availability of patient cohorts with several types of omics data opens new perspectives for exploring the disease's underlying biological processes and developing predictive models. It also comes with new challenges in computational biology in terms of integrating high-dimensional and heterogeneous data in a fashion that captures the interrelationships between multiple genes and their functions. Deep learning methods offer promising perspectives for integrating multi-omics data. In this paper, we review the existing integration strategies based on autoencoders and propose a new customizable one whose principle relies on a two-phase approach. In the first phase, we adapt the training to each data source independently before learning cross-modality interactions in the second phase. By taking into account each source's singularity, we show that this approach succeeds at taking advantage of all the sources more efficiently than other strategies. Moreover, by adapting our architecture to the computation of Shapley additive explanations, our model can provide interpretable results in a multi-source setting. Using multiple omics sources from different TCGA cohorts, we demonstrate the performance of the proposed method for cancer on test cases for several tasks, such as the classification of tumor types and breast cancer subtypes, as well as survival outcome prediction. We show through our experiments the great performances of our architecture on seven different datasets with various sizes and provide some interpretations of the results obtained. Our code is available on (https://github.com/HakimBenkirane/CustOmics).

Does the apparent diffusion coefficient from diffusion-weighted MRI imaging aid in the characterization of malignant soft tissue tumors and sarcomas.

To identify trends in apparent diffusion coefficient (ADC) measurements from diffusion-weighted imaging (DWI) with respect to tumor type classification and other tumor characteristics whether common malignant soft tissue tumors can be distinguished. A consecutive series of extremity malignant soft tissue tumors and soft tissue sarcomas (STS) among 78 adult patients with conventional MRI and DWI were included. Each case was evaluated with respect to T1/T2 signal alterations and heterogeneity, presence of peritumoral edema, necrosis, cystic changes, internal hemorrhage, and maximum longitudinal dimension blinded to the histology. The ADC mean and minimum were obtained using a free-hand region of interest of the whole tumor and the darkest (lowest signal area) ADC area of the tumor. Kruskal-Wallis and Wilcoxon Rank-Sum Tests were used to determine associations and significance between tumor subtypes. Intraclass correlation (ICC) and kappa calculations were utilized to assess inter-reader agreements for ADC values and reader diagnosis. Liposarcomas showed more heterogenous T1W images with hyperintense T1W signal when compared to tumors not classified as liposarcoma (P = 0.046 and P = 0.010, respectively). Liposarcomas were relatively consistent in demonstrating an absence of hemorrhage (81.8%) while undifferentiated pleomorphic sarcomas consistently showed intralesional hemorrhage (90%). When comparing individual tumor classifications against the rest of the samples, lymphomas registered lower mean and minimum ADC values in the whole tumor and in themost hypointense area of the tumor for both readers (P < 0.05). The interobserver agreement between the two readers was good to excellent for all four ADC measurements (ICC = 0.65-0.98). Diffusion-weighted imaging generated ADC measurements are reproducible but currently offer limited insight in being able to differentiate among different malignant soft tissue tumor and sarcoma histologies.T1W and T2W signal characteristics also offer limited insight indifferentiating between soft tissue malignancies.

MIMESIS: minimal DNA-methylation signatures to quantify and classify tumor signals in tissue and cell-free DNA samples.

DNA-methylation alterations are common in cancer and display unique characteristics that make them ideal markers for tumor quantification and classification. Here we present MIMESIS, a computational framework exploiting minimal DNA-methylation signatures composed by a few dozen informative DNA-methylation sites to quantify and classify tumor signals in tissue and cell-free DNA samples. Extensive analyses of multiple independent and heterogenous datasets including >7200 samples demonstrate the capability of MIMESIS to provide precise estimations of tumor content and to enable accurate classification of tumor type and molecular subtype. To assess our framework for clinical applications, we designed a MIMESIS-informed assay incorporating the minimal signatures for breast cancer. Using both artificial samples and clinical serial cell-free DNA samples from patients with metastatic breast cancer, we show that our approach provides accurate estimations of tumor content, sensitive detection of tumor signal and the ability to capture clinically relevant molecular subtype in patients' circulation. This study provides evidence that our extremely parsimonious approach can be used to develop cost-effective and highly scalable DNA-methylation assays that could support and facilitate the implementation of precision oncology in clinical practice.

Somatic BAP1 Loss in Ovarian Serous Borderline Tumor and Recurrent Low-grade Serous Carcinoma From a Germline BAP1 Mutation Carrier.

To the Editor: In a recent issue, Dr. Oliva and colleagues proposed the use of the immunohistochemical markers, Claudin-4 and BAP1, to distinguish between low-grade serous neoplasms and peritoneal mesothelioma 1. This article is of particular interest to us, as we have recently published on a cohort of 119 clinically annotated low-grade serous carcinomas, confirmed by central pathology review, with molecular profiling by targeted next-generation sequencing 2. In this cohort, we encountered 1 patient who represents an unusual exception to relying on loss of BAP1 expression to exclude the diagnosis of a low-grade serous neoplasm. This was a 59-yr-old female who underwent comprehensive surgical staging for bilateral ovarian masses. Final pathology revealed a stage IIIC serous borderline tumor involving bilateral ovaries (Fig. 1A), associated with noninvasive peritoneal implants and involvement of pelvic lymph nodes. After 7 yrs, she developed recurrent disease involving the sigmoid colon, in the form of metastatic low-grade serous carcinoma (Fig. 1B). Both primary and recurrent tumors showed a similar immunophenotype, characterized by strong diffuse expression of epithelial/Mullerian markers, including Claudin-4 (Fig. 1C), BerEP4, PAX8, ER, and PR, while negative for markers of mesothelial differentiation, namely, calretinin, and D2-40. Somatic mutational profiling by targeted next-generation sequencing revealed the low-grade serous carcinoma to harbor a BAP1 frameshift mutation (Y241Lfs*2). Germline testing further revealed a heterozygous BAP1 germline mutation (c.1110dupC, p.Met371Hisfs*27). Loss of BAP1 expression by immunohistochemistry in the low-grade serous carcinoma, as well as the prior serous borderline tumor (Fig. 1D), was consistent with bi-allelic inactivation of BAP1 as an early event in the molecular pathogenesis of this case.FIG. 1: Low-grade serous neoplasms associated with germline BAP1 mutation. (A) Ovarian serous borderline tumor showing characteristic hierarchical branching papillae lined by stratified columnar epithelium (inset: ciliated cells observed at high-magnification, consistent with tubal differentiation). (B) Recurrent invasive low-grade serous carcinoma involving muscularis propria of the sigmoid colon, showing infiltrating nests and micropapillae composed of tumor cells with small monotonous nuclei, and scattered psammoma bodies. Immunohistochemical analysis of the serous borderline tumor showing (C) diffuse expression of Claudin-4 and (D) loss of BAP1 expression in tumor cells with retained nuclear staining in non-neoplastic stromal cells.To our knowledge, this represents the first reported case of a BAP1-deficient low-grade serous neoplasm. It illustrates how genetic alterations of oncogenes and tumor suppressor genes are not tissue or disease-specific and emphasizes the importance of applying several cell lineage markers, along with morphologic correlation, for appropriate diagnostic classification of tumor type.

Decomposition-based framework for tumor classification and prediction of treatment response from longitudinal MRI

Objective. In the field of radiation oncology, the benefit of MRI goes beyond that of providing high soft-tissue contrast images for staging and treatment planning. With the recent clinical introduction of hybrid MRI linear accelerators it has become feasible to map physiological parameters describing diffusion, perfusion, and relaxation during the entire course of radiotherapy, for example. However, advanced data analysis tools are required for extracting qualified prognostic and predictive imaging biomarkers from longitudinal MRI data. In this study, we propose a new prediction framework tailored to exploit temporal dynamics of tissue features from repeated measurements. We demonstrate the framework using a newly developed decomposition method for tumor characterization. Approach. Two previously published MRI datasets with multiple measurements during and after radiotherapy, were used for development and testing: T 2-weighted multi-echo images obtained for two mouse models of pancreatic cancer, and diffusion-weighted images for patients with brain metastases. Initially, the data was decomposed using the novel monotonous slope non-negative matrix factorization (msNMF) tailored for MR data. The following processing consisted of a tumor heterogeneity assessment using descriptive statistical measures, robust linear modelling to capture temporal changes of these, and finally logistic regression analysis for stratification of tumors and volumetric outcome. Main Results. The framework was able to classify the two pancreatic tumor types with an area under curve (AUC) of 0.999, P < 0.001 and predict the tumor volume change with a correlation coefficient of 0.513, P = 0.034. A classification of the human brain metastases into responders and non-responders resulted in an AUC of 0.74, P = 0.065. Significance. A general data processing framework for analyses of longitudinal MRI data has been developed and applications were demonstrated by classification of tumor type and prediction of radiotherapy response. Further, as part of the assessment, the merits of msNMF for tumor tissue decomposition were demonstrated.

Events in CNS Tumor Pathology Post-2016 WHO CNS: cIMPACT-NOW Updates and Other Advancements: A Comprehensive Review Plus a Summary of the Salient Features of 2021 WHO CNS 5.

The 2016 World Health Organization Classification (WHO) of Tumors of the Central Nervous System (CNS) represented a major change. It recommended an "integrated diagnosis" comprising histologic and molecular information facilitating a more precise diagnosis of specific CNS tumors. Its goal was to provide greater diagnostic precision and reproducibility resulting in more clinical relevance and predictive value, ultimately leading to better patient care. Advances in molecular classification, mostly resulting from DNA methylation array profiling of CNS tumors, were occurring at a very rapid pace and required more rapid integration into clinical practice. cIMPACT-NOW updates and other recent papers plus salient features of 2021 WHO CNS5 in this comprehensive write-up were reviewed. CNS tumor classification needs to be updated at a rapid pace and mechanisms put into place to guide diagnosticians and clinicians in the interim period if major changes in the classification of tumor types came to light. Recognizing the need to integrate these into clinical practice more rapidly and without inordinate delay, the International Society of Neuropathology (ISN) 2016 sponsored an initiative called cIMPACT-NOW. Goal of cIMPACT-NOW was to provide clarification regarding contentious issues arising in the wake of the 2016 WHO CNS update as well as report new advancements in molecular classification of CNS tumors and new tumor entities emerging as a result of these advancements. cIMPACT-NOW updates: It thus laid the foundation for the 5th edition of the WHO Classification of CNS tumors (2021 WHO CNS 5). We have discussed cIMPACT updates in detail in this review. In addition, molecular diagnostics including DNA methylation-based classification of CNS tumors and the practical use of molecular classification in the prognostication and treatment of CNS tumors is discussed. Finally, the salient features of the new CNS tumor classification are summarized.

Tumor type classification and candidate cancer-specific biomarkers discovery via semi-supervised learning.

Identifying cancer-related differentially expressed genes provides significant information for diagnosing tumors, predicting prognoses, and effective treatments. Recently, deep learning methods have been used to perform gene differential expression analysis using microarray-based high-throughput gene profiling and have achieved good results. In this study, we proposed a new robust multiple-datasets-based semi-supervised learning model, MSSL, to perform tumor type classification and candidate cancer-specific biomarkers discovery across multiple tumor types and multiple datasets, which addressed the following long-lasting obstacles: (1) the data volume of the existing single dataset is not enough to fully exert the advantages of deep learning; (2) a large number of datasets from different research institutions cannot be effectively used due to inconsistent internal variances and low quality; (3) relatively uncommon cancers have limited effects on deep learning methods. In our article, we applied MSSL to The Cancer Genome Atlas (TCGA) and the Gene Expression Comprehensive Database (GEO) pan-cancer normalized-level3 RNA-seq data and got 97.6% final classification accuracy, which had a significant performance leap compared with previous approaches. Finally, we got the ranking of the importance of the corresponding genes for each cancer type based on classification results and validated that the top genes selected in this way were biologically meaningful for corresponding tumors and some of them had been used as biomarkers, which showed the efficacy of our method.