Improved classification of colorectal polyps on histopathological images with ensemble learning and stain normalization

Artificial intelligence predicts pregnancy complications based on cytokine profiles

BACKGROUND

Early prediction of pregnancy complications is important for adequate and timely prevention, management, and reducing maternal/fetal pathogenesis.

OBJECTIVE

To study the prognostic value of cytokines as predictors of pregnancy complications using unbiased artificial intelligence/machine learning (AI/ML) methods.

METHODS

For this study, we used our previously published data on 127 women with pregnancy complications and 97 women with a history of normal delivery and undergoing a normal delivery. A panel of seven cytokines were analyzed from activated peripheral blood mononuclear cells (PBMC). AI/ML methods such as kNN, SVM, decision tree, and ensemble classification were applied to explore the possible use of AI/ML to compare and predict normal gestation and normal delivery as opposed to different pregnancy complications such as recurrent spontaneous miscarriage (RSM), preterm delivery (PTD), pregnancy-induced hypertension (PIH), and premature rupture of fetal membranes (PROM).

RESULTS

The study examined cytokine levels in various pregnancy conditions, revealing significant differences, particularly in the levels of IL-2 and IFN-γ, across age-matched comparisons. Additionally, binary classification tasks demonstrated notable accuracies and f-measures for methodologies such as Ensemble (Bagged), QDA, and SVM (Cubic), showcasing their effectiveness in distinguishing between normal delivery and different pregnancy complications.

CONCLUSION

The study provides a machine learning-based methodology for the prediction of pregnancy complications based on levels of cytokines produced by peripheral blood cells.

Investigation on potential bias factors in histopathology datasets

Deep neural networks (DNNs) have demonstrated remarkable capabilities in medical applications, including digital pathology, where they excel at analyzing complex patterns in medical images to assist in accurate disease diagnosis and prognosis. However, concerns have arisen about potential biases in The Cancer Genome Atlas (TCGA) dataset, a comprehensive repository of digitized histopathology data and serves as both a training and validation source for deep learning models, suggesting that over-optimistic results of model performance may be due to reliance on biased features rather than histological characteristics. Surprisingly, recent studies have confirmed the existence of site-specific bias in the embedded features extracted for cancer-type discrimination, leading to high accuracy in acquisition site classification. This biased behavior motivated us to conduct an in-depth analysis to investigate potential causes behind this unexpected biased ability toward site-specific pattern recognition. The analysis was conducted on two cutting-edge DNN models: KimiaNet, a state-of-the-art DNN trained on TCGA images, and the self-trained EfficientNet. In this research study, the balanced accuracy metric is used to evaluate the performance of a model trained to classify data centers, which was originally designed to learn cancerous patterns, with the aim of investigating the potential factors contributing to the higher balanced accuracy in data center detection.

ProDiv: Prototype-driven consistent pseudo-bag division for whole-slide image classification

BACKGROUND AND OBJECTIVE

Pathology image classification is one of the most essential auxiliary processes in cancer diagnosis. To overcome the problem of inadequate Whole-Slide Image (WSI) samples with weak labels, pseudo-bag-based multiple instance learning (MIL) methods have attracted wide attention in pathology image classification. In this type of method, the division scheme of pseudo-bags is usually a primary factor affecting classification performance. In order to improve the division of WSI pseudo-bags on existing random/clustering approaches, this paper proposes a new Prototype-driven Division (ProDiv) scheme for the pseudo-bag-based MIL classification framework on pathology images.

METHODS

This scheme first designs an attention-based method to generate a bag prototype for each slide. On this basis, it further groups WSI patch instances into a series of instance clusters according to the feature similarities between the prototype and patches. Finally, pseudo-bags are obtained by randomly combining the non-overlapping patch instances of different instance clusters. Moreover, the design scheme of our ProDiv considers practicality, and it could be smoothly assembled with almost all the MIL-based WSI classification methods in recent years.

RESULTS

Empirical results show that our ProDiv, when integrated with several existing methods, can deliver classification AUC improvements of up to 7.3% and 10.3%, respectively on two public WSI datasets.

CONCLUSIONS

ProDiv could almost always bring obvious performance improvements to compared MIL models on typical metrics, which suggests the effectiveness of our scheme. Experimental visualization also visually interprets the correctness of the proposed ProDiv.

Pal J, Safa Erenay F. Medical Informatics as a Concept and Field-Based Medical Informatics Research: The Case of Turkey

Aim: This study aimed to evaluate the position of Turkey in the field of Medical Informatics and assess the general structure of research by analyzing Medical Informatics research with bibliometric methods. Material and Methods: In this study, we conducted a bibliometric analysis of research and review articles generated between 1980 and 2023 from the Web of Science bibliometric data source, utilizing bibliometric methods through the R bibliometrix tool and VosViewer. Results: In the field of medical informatics research in Turkey, the country holds the 27th position with 905 articles, 15,610 citations, and an impressive impact factor of 51, along with an average citation rate of 17.25 per article, based on bibliometric analysis conducted between 1980 and 2023. Notable institutions in this field include Middle East Technical University, Hacettepe University, and Selçuk University. The prominent research topics encompass "neural network(s), machine learning, support vector, health care, decision support, deep learning, EEG signals, classification accuracy," reflecting the areas of intensive investigation. Conclusion: In Turkey, the field of medical informatics has lagged slightly behind basic engineering sciences or medical sciences. The domain exhibits a multidisciplinary structure intersecting with various engineering fields such as computer science, software engineering, industrial engineering, artificial intelligence engineering, and electronic engineering. To enhance productivity in this field, greater collaboration with other research areas can be pursued. Additionally, it is recommended to urgently establish four-year undergraduate programs specifically dedicated to medical informatics or health informatics at universities.

An effective colorectal polyp classification for histopathological images based on supervised contrastive learning

Early detection of colon adenomatous polyps is pivotal in reducing colon cancer risk. In this context, accurately distinguishing between adenomatous polyp subtypes, especially tubular and tubulovillous, from hyperplastic variants is crucial. This study introduces a cutting-edge computer-aided diagnosis system optimized for this task. Our system employs advanced Supervised Contrastive learning to ensure precise classification of colon histopathology images. Significantly, we have integrated the Big Transfer model, which has gained prominence for its exemplary adaptability to visual tasks in medical imaging. Our novel approach discerns between in-class and out-of-class images, thereby elevating its discriminatory power for polyp subtypes. We validated our system using two datasets: a specially curated one and the publicly accessible UniToPatho dataset. The results reveal that our model markedly surpasses traditional deep convolutional neural networks, registering classification accuracies of 87.1% and 70.3% for the custom and UniToPatho datasets, respectively. Such results emphasize the transformative potential of our model in polyp classification endeavors.

A Novel Heteromorphous Convolutional Neural Network for Automated Assessment of Tumors in Colon and Lung Histopathology Images

The automated assessment of tumors in medical image analysis encounters challenges due to the resemblance of colon and lung tumors to non-mitotic nuclei and their heteromorphic characteristics. An accurate assessment of tumor nuclei presence is crucial for determining tumor aggressiveness and grading. This paper proposes a new method called ColonNet, a heteromorphous convolutional neural network (CNN) with a feature grafting methodology categorically configured for analyzing mitotic nuclei in colon and lung histopathology images. The ColonNet model consists of two stages: first, identifying potential mitotic patches within the histopathological imaging areas, and second, categorizing these patches into squamous cell carcinomas, adenocarcinomas (lung), benign (lung), benign (colon), and adenocarcinomas (colon) based on the model's guidelines. We develop and employ our deep CNNs, each capturing distinct structural, textural, and morphological properties of tumor nuclei, to construct the heteromorphous deep CNN. The execution of the proposed ColonNet model is analyzed by its comparison with state-of-the-art CNNs. The results demonstrate that our model surpasses others on the test set, achieving an impressive F1 score of 0.96, sensitivity and specificity of 0.95, and an area under the accuracy curve of 0.95. These outcomes underscore our hybrid model's superior performance, excellent generalization, and accuracy, highlighting its potential as a valuable tool to support pathologists in diagnostic activities.