TCNN: A Transformer Convolutional Neural Network for artifact classification in whole slide images

Shakarami, Ashkan; Nicolè, Lorenzo; Terreran, Matteo; Tos, Angelo Paolo Dei; Ghidoni, Stefano

doi:10.1016/j.bspc.2023.104812

Cited by 4 publications

(4 citation statements)

References 80 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, making use of attention mechanisms or employing multi-scale features. SeTranSurv [25], ATTransU-Net [2], TCNN [1], SwinCup [48], and DHUnet [49], TransNuSS [50] are some examples of hybrid transformer-CNN models that have been developed for different histopathological imaging tasks.…”

Section: Different Ways Of Employing Transformers For Histopathologic...mentioning

confidence: 99%

“…Histopathological imaging has been regarded as a technique for identifying nearly all types of cancers since it provides a more thorough understanding of the diseases [ 1 , 2 ]. They are a very important source of primary information in clinical domains, which assists pathologists in performing cancer diagnosis.…”

Section: Introductionmentioning

confidence: 99%

“…They are a very important source of primary information in clinical domains, which assists pathologists in performing cancer diagnosis. Histopathological images are mostly used for cancer grading and offer more detailed information for diagnosis when compared to other medical imaging techniques, including magnetic resonance imaging (MRI), computerized tomography (CT), transrectal ultrasound (TRUS), mammography, and many others, and diseases are also examined by identifying the cells and tissue present in lesions [1,3]. For various cancer types, pathologists may choose treatment plans based on histopathological images coupled with genomic records.…”

Section: Introductionmentioning

confidence: 99%

“…In particular, it provides readers in this field of study with a thorough understanding of transformer-based techniques in histopathological image analysis and also establishes the foundation for future innovation to improve the performance of transformer architectures in this domain. To this end, our key contributions include: (1) this work provides a thorough evaluation of more than 100 research publications across the histopathological imaging field to cover the most recent innovations; (2) it provides a thorough overview of the entire domain by classifying the research papers according to how they apply to histopathological imaging, as shown in Fig. 2; (3) it classified each of these applications, pointed out task-specific challenges, and highlighted the approaches used to address them based on the proposed work, as demonstrated in Tables 1, 2, 3, 4, and 5 in ''Current progress'' , ''Discussion'' Section it provides a thorough analysis of designing transformer-based approaches for handling more difficult real-world challenges and also compares transformers with CNN-based models based on recently published works.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A survey of Transformer applications for histopathological image analysis: New developments and future directions

Atabansi,

Nie,

Liu

et al. 2023

BioMed Eng OnLine

View full text Add to dashboard Cite

Transformers have been widely used in many computer vision challenges and have shown the capability of producing better results than convolutional neural networks (CNNs). Taking advantage of capturing long-range contextual information and learning more complex relations in the image data, Transformers have been used and applied to histopathological image processing tasks. In this survey, we make an effort to present a thorough analysis of the uses of Transformers in histopathological image analysis, covering several topics, from the newly built Transformer models to unresolved challenges. To be more precise, we first begin by outlining the fundamental principles of the attention mechanism included in Transformer models and other key frameworks. Second, we analyze Transformer-based applications in the histopathological imaging domain and provide a thorough evaluation of more than 100 research publications across different downstream tasks to cover the most recent innovations, including survival analysis and prediction, segmentation, classification, detection, and representation. Within this survey work, we also compare the performance of CNN-based techniques to Transformers based on recently published papers, highlight major challenges, and provide interesting future research directions. Despite the outstanding performance of the Transformer-based architectures in a number of papers reviewed in this survey, we anticipate that further improvements and exploration of Transformers in the histopathological imaging domain are still required in the future. We hope that this survey paper will give readers in this field of study a thorough understanding of Transformer-based techniques in histopathological image analysis, and an up-to-date paper list summary will be provided at https://github.com/S-domain/Survey-Paper.

show abstract