Disentangled Autoencoder for Cross-Stain Feature Extraction in Pathology Image Analysis

Hecht, Helge; Sarhan, Mhd Hasan; Popovici, Vlad

doi:10.3390/app10186427

Cited by 9 publications

(7 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Subsequently, numerous researchers (Adhikari et al, 2019;Badrinarayanan et al, 2017;Kolhar and Jagtap, 2021;Milioto et al, 2018;Peng et al, 2019) used convolutional encoder-decoder networks for semantic segmentation. The Visual Geometry Group (VGG) (Simonyan and Zisserman, 2015), ResNet (He et al, 2015), and InceptionV3 (Szegedy et al, 2015) networks achieve top-5 accuracy of 92.7%, 93.3%, and 93.9%, respectively on ImageNet dataset (Deng et al, 2009), which proves that these networks have good features extraction ability and often (Gao et al, 2020;Hecht et al, 2020;Majeed et al, 2018;Ou et al, 2019;Panda et al, 2022;Shah et al, 2022;Zou et al, 2021) used as a backbone in various CNN architectures developed for semantic segmentation. Therefore, the performance of the proposed models in this study was compared to the above-mentioned models while having these networks as an encoder backbone.…”

Section: Comparison With the State-of-the-art Networkmentioning

confidence: 93%

Lightweight convolutional neural network models for semantic segmentation of in-field cotton bolls

Singh¹,

Tewari²,

Biswas³

et al. 2023

Artificial Intelligence in Agriculture

View full text Add to dashboard Cite

Section: Comparison With the State-of-the-art Networkmentioning

confidence: 93%

Lightweight convolutional neural network models for semantic segmentation of in-field cotton bolls

Singh¹,

Tewari²,

Biswas³

et al. 2023

Artificial Intelligence in Agriculture

View full text Add to dashboard Cite

“…When there is a lack of data, autoencoders can also produce generated data for data augmenting. Autoencoders offer potential in drug development since they may be used to analyse molecular information for identifying possible therapeutic targets (Astaraki et al, 2022; Hecht et al, 2020; Lomacenkova & Arandjelović, 2021; Uzunova et al, 2019).…”

Section: Applications Of Deep and Machine Learning In Medical Fieldsmentioning

confidence: 99%

Advancements in medical diagnosis and treatment through machine learning: A review

Ahsan,

Khan,

Khan

et al. 2023

Expert Systems

View full text Add to dashboard Cite

The aptness of machine learning (ML) to learn from large datasets, discover trends, and make predictions has demonstrated its potential to metamorphose the medical field. Medical data analysis with ML algorithms can improve patient outcomes in terms of both treatment and diagnosis. This paper investigates the numerous possibilities of ML in the medical industries, including radiology, pathology, genomics, and clinical decision‐making. It also goes over the benefits and drawbacks of ML in various sectors as well as the limitations that come with its application. It illustrates the potential advantages of ML, such as better accuracy and efficiency in diagnosis and individualized treatment programs, through a review of previous studies. Lastly, it provides perspectives on prospective advancements and prospects for the discipline. This study also intends to investigate the applications of deep learning (DL) in the medical field. DL algorithms have performed exceptionally satisfactorily in several healthcare‐related fields. The main conclusions of the study are summarized, and their ramifications for the healthcare sector are discussed in this paper's conclusion. This paper intends to contribute to a greater understanding of the prevailing state of the discipline and the possibility for future developments by emphasizing the prospects of these methodologies to alter medical study and clinical practice.

show abstract

“…Then, for each slide, one or more FRs are selected, based on traits derived from the slide review process (e.g., the presence of tumor), and used as masks for the identification of image areas for the extraction of small image subregions with a fixed pixel resolution at a fixed magnification level (patches). After the extraction, the patches are filtered to exclude To extract feature vectors from the patches, the study protocol envisages the use of Variational Autoencoders (VAs), a class of Deep Neural Networks consisting of two main blocks of networks: an encoder and a decoder (30). These are designed to: (i) perform the encoding of the input data into a lower dimensional embedding, and (ii) reconstruct the input from the lower dimensional space.…”

Section: Computational Histopathologymentioning

confidence: 99%

Cohort profile: the Turin prostate cancer prognostication (TPCP) cohort

Destefanis,

Fiano,

Milani

et al. 2023

Front. Oncol.

View full text Add to dashboard Cite

IntroductionProstate cancer (PCa) is the most frequent tumor among men in Europe and has both indolent and aggressive forms. There are several treatment options, the choice of which depends on multiple factors. To further improve current prognostication models, we established the Turin Prostate Cancer Prognostication (TPCP) cohort, an Italian retrospective biopsy cohort of patients with PCa and long-term follow-up. This work presents this new cohort with its main characteristics and the distributions of some of its core variables, along with its potential contributions to PCa research.MethodsThe TPCP cohort includes consecutive non-metastatic patients with first positive biopsy for PCa performed between 2008 and 2013 at the main hospital in Turin, Italy. The follow-up ended on December 31st 2021. The primary outcome is the occurrence of metastasis; death from PCa and overall mortality are the secondary outcomes. In addition to numerous clinical variables, the study’s prognostic variables include histopathologic information assigned by a centralized uropathology review using a digital pathology software system specialized for the study of PCa, tumor DNA methylation in candidate genes, and features extracted from digitized slide images via Deep Neural Networks.ResultsThe cohort includes 891 patients followed-up for a median time of 10 years. During this period, 97 patients had progression to metastatic disease and 301 died; of these, 56 died from PCa. In total, 65.3% of the cohort has a Gleason score less than or equal to 3 + 4, and 44.5% has a clinical stage cT1. Consistent with previous studies, age and clinical stage at diagnosis are important prognostic factors: the crude cumulative incidence of metastatic disease during the 14-years of follow-up increases from 9.1% among patients younger than 64 to 16.2% for patients in the age group of 75-84, and from 6.1% for cT1 stage to 27.9% in cT3 stage.DiscussionThis study stands to be an important resource for updating existing prognostic models for PCa on an Italian cohort. In addition, the integrated collection of multi-modal data will allow development and/or validation of new models including new histopathological, digital, and molecular markers, with the goal of better directing clinical decisions to manage patients with PCa.

show abstract

Disentangled Autoencoder for Cross-Stain Feature Extraction in Pathology Image Analysis

Cited by 9 publications

References 28 publications

Lightweight convolutional neural network models for semantic segmentation of in-field cotton bolls

Lightweight convolutional neural network models for semantic segmentation of in-field cotton bolls

Advancements in medical diagnosis and treatment through machine learning: A review

Cohort profile: the Turin prostate cancer prognostication (TPCP) cohort

Contact Info

Product

Resources

About