State of machine and deep learning in histopathological applications in digestive diseases

Abstract

Machine learning (ML)- and deep learning (DL)-based imaging modalities have exhibited the capacity to handle extremely high dimensional data for a number of computer vision tasks. While these approaches have been applied to numerous data types, this capacity can be especially leveraged by application on histopathological images, which capture cellular and structural features with their high-resolution, microscopic perspectives. Already, these methodologies have demonstrated promising performance in a variety of applications like disease classification, cancer grading, structure and cellular localizations, and prognostic predictions. A wide range of pathologies requiring histopathological evaluation exist in gastroenterology and hepatology, indicating these as disciplines highly targetable for integration of these technologies. Gastroenterologists have also already been primed to consider the impact of these algorithms, as development of real-time endoscopic video analysis software has been an active and popular field of research. This heightened clinical awareness will likely be important for future integration of these methods and to drive interdisciplinary collaborations on emerging studies. To provide an overview on the application of these methodologies for gastrointestinal and hepatological histopathological slides, this review will discuss general ML and DL concepts, introduce recent and emerging literature using these methods, and cover challenges moving forward to further advance the field.

Prediction for Mitosis-Karyorrhexis Index Status of Pediatric Neuroblastoma via Machine Learning Based 18F-FDG PET/CT Radiomics

“…Radiomics analysis of 18 F-FDG PET/CT can predict the status of TERTp-mutation status of high-grade gliomas [13], EGFR mutation in lung adenocarcinoma [14], hormone receptor distribution, proliferation rate, lymph node and distant metastasis of breast carcinoma [15]. The application of machine learning methodologies on histopathological images is a blossoming field with significant potential for clinical impact [16]. There have been no studies to date, however, which utilize radiomics based on 18 F-FDG PET/CT to predict the MKI status in pediatric neuroblastoma.…”

Computational analysis of peripheral blood smears detects disease-associated cytomorphologies

“…Finally, we show that morphotypes are enriched with known cell types and that our approach validates externally, generalizing to PBS from other centers obtained using different slide scanners. However, further studies would be required to validate the described morphotypes in a clinical setting — the expert analysis of PBS considering the morphotypes here discovered would be the ideal validation, and more diverse training and validation cohorts could further confirm the generalization capabilities of automated cytomorphology, which can still be affected by preparation- and scanner-specific artifacts and noise 59,60 . Efforts like the National MDS Natural History Study, to be concluded in 2025, seek to constitute the first multicentre cohort and tissue-bank for MDS 61 and could be used as a more comprehensive assessment of the generalization of computational cytomorphology in the context of MDS.…”

Deep Neural Network for Automatic Assessment of Dysphonia

“…This topic is widely studied in the area of automatic medical image processing. The challenges for artificial intelligence to achieve clinical value have been addressed in numerous works [33,34,35,36,37,38]. Many of these challenges are common to those found in vocal pathology.…”