Universal encoding of pan-cancer histology by deep texture representations

Komura, Daisuke; Kawabe, Akihiro; Fukuta, Keisuke; Sano, Kentaro; Umezaki, Taizo; Koda, Hirotomo; Suzuki, Ryôhei; Tominaga, Kunihiko; Ochi, Mieko; Konishi, Hiroki; Masakado, Fumiya; Saito, Noriyuki; Sato, Yasuyoshi; Onoyama, Takumi; Nishida, Shu; Furuya, Genta; Katoh, Hiroto; Yamashita, Hiroharu; Kakimi, Kazuhiro; Seto, Yasuyuki; Ushiku, Tetsuo; Fukayama, Masashi; Ishikawa, Shumpei

doi:10.1016/j.celrep.2022.110424

Cited by 29 publications

(22 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This result suggests that our histopathologic morphology-based prediction model likely focuses on features that are correlated with gene expression changes, which cannot be identified by IHC. Other studies have also investigated the relationship between histopathological morphology and molecular profile 15 , 32 ; for example, Chen et al reported a change in the highly predictive area when the molecular profile was combined with a WSI-based prognostic model 15 . Their findings indicated that histopathological morphology is correlated with the molecular profile, similar to the findings of our study.…”

Section: Discussionmentioning

confidence: 99%

Extracting interpretable features for pathologists using weakly supervised learning to predict p16 expression in oropharyngeal cancer

Adachi,

Taki,

Sakamoto

et al. 2024

Sci Rep

Self Cite

View full text Add to dashboard Cite

One drawback of existing artificial intelligence (AI)-based histopathological prediction models is the lack of interpretability. The objective of this study is to extract p16-positive oropharyngeal squamous cell carcinoma (OPSCC) features in a form that can be interpreted by pathologists using AI model. We constructed a model for predicting p16 expression using a dataset of whole-slide images from 114 OPSCC biopsy cases. We used the clustering-constrained attention-based multiple-instance learning (CLAM) model, a weakly supervised learning approach. To improve performance, we incorporated tumor annotation into the model (Annot-CLAM) and achieved the mean area under the receiver operating characteristic curve of 0.905. Utilizing the image patches on which the model focused, we examined the features of model interest via histopathologic morphological analysis and cycle-consistent adversarial network (CycleGAN) image translation. The histopathologic morphological analysis evaluated the histopathological characteristics of image patches, revealing significant differences in the numbers of nuclei, the perimeters of the nuclei, and the intercellular bridges between p16-negative and p16-positive image patches. By using the CycleGAN-converted images, we confirmed that the sizes and densities of nuclei are significantly converted. This novel approach improves interpretability in histopathological morphology-based AI models and contributes to the advancement of clinically valuable histopathological morphological features.

show abstract

Section: Discussionmentioning

confidence: 99%

Extracting interpretable features for pathologists using weakly supervised learning to predict p16 expression in oropharyngeal cancer

Adachi,

Taki,

Sakamoto

et al. 2024

Sci Rep

Self Cite

View full text Add to dashboard Cite

show abstract

“…AI and deep learning techniques have successfully been applied in medical image diagnosis. Examples include dermoscopic diagnosis of melanoma [11] , [15] , detection of diabetic retinopathy in retinal fundus photographs [26] , endoscopic diagnosis and progression assessment of gastric cancer [13] , classification and mutation prediction of lung cancer using histological images [14] , and prediction of genomic features and the response to immune checkpoint therapies of various cancers from histological images [27] . In urology, Shkolyar et al [16] developed deep learning models that detected bladder cancer with sensitivity of 90.9% and specificity of 98.6%.…”

Section: Discussionmentioning

confidence: 99%

Deep Learning Models for Cystoscopic Recognition of Hunner Lesion in Interstitial Cystitis

Iwaki¹,

Akiyama²,

Nosato³

et al. 2023

European Urology Open Science

View full text Add to dashboard Cite

“…A variety of exciting deep‐learning applications have focused on other biologically and clinically important research areas, including real‐time AI to assist in intraoperative diagnosis [ 83 , 84 , 85 ], biologically inspired AI to improve interpretability [ 86 ], efficient search of archival histopathology images to facilitate decision‐making [ 87 , 88 ] and federated learning to encourage cross‐centre collaboration and protect data privacy [ 89 ].…”

Section: Deep Learning To Predict Clinical Outcomes and Beyondmentioning

confidence: 99%

Application of digital pathology‐based advanced analytics of tumour microenvironment organisation to predict prognosis and therapeutic response

Wilkins

2023

The Journal of Pathology

View full text Add to dashboard Cite

In recent years, the application of advanced analytics, especially artificial intelligence (AI), to digital H&E images, and other histological image types, has begun to radically change how histological images are used in the clinic. Alongside the recognition that the tumour microenvironment (TME) has a profound impact on tumour phenotype, the technical development of highly multiplexed immunofluorescence platforms has enhanced the biological complexity that can be captured in the TME with high precision. AI has an increasingly powerful role in the recognition and quantitation of image features and the association of such features with clinically important outcomes, as occurs in distinct stages in conventional machine learning. Deep‐learning algorithms are able to elucidate TME patterns inherent in the input data with minimum levels of human intelligence and, hence, have the potential to achieve clinically relevant predictions and discovery of important TME features. Furthermore, the diverse repertoire of deep‐learning algorithms able to interrogate TME patterns extends beyond convolutional neural networks to include attention‐based models, graph neural networks, and multimodal models. To date, AI models have largely been evaluated retrospectively, outside the well‐established rigour of prospective clinical trials, in part because traditional clinical trial methodology may not always be suitable for the assessment of AI technology. However, to enable digital pathology‐based advanced analytics to meaningfully impact clinical care, specific measures of ‘added benefit’ to the current standard of care and validation in a prospective setting are important. This will need to be accompanied by adequate measures of explainability and interpretability. Despite such challenges, the combination of expanding datasets, increased computational power, and the possibility of integration of pre‐clinical experimental insights into model development means there is exciting potential for the future progress of these AI applications. © 2023 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.

show abstract

Universal encoding of pan-cancer histology by deep texture representations

Cited by 29 publications

References 41 publications

Extracting interpretable features for pathologists using weakly supervised learning to predict p16 expression in oropharyngeal cancer

Extracting interpretable features for pathologists using weakly supervised learning to predict p16 expression in oropharyngeal cancer

Deep Learning Models for Cystoscopic Recognition of Hunner Lesion in Interstitial Cystitis

Application of digital pathology‐based advanced analytics of tumour microenvironment organisation to predict prognosis and therapeutic response

Contact Info

Product

Resources

About