Simultaneous Cell Detection and Classification with an Asymmetric Deep Autoencoder in Bone Marrow Histology Images

Song, Tzu-Hsi; Sánchez, Vı́ctor; EIDaly, Hesham; Rajpoot, Nasir M.

doi:10.1007/978-3-319-60964-5_72

Cited by 6 publications

(5 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Neural image compression [ 29 ] compares several self-supervised pretext training tasks to create feature-rich WSI representations but is impeded by dimensionality [ 30 ], due to the sheer number of parameters associated with each compressed slide. Finally, several autoencoder and derivative methods have been applied to learn compact patch-wise representations without labels to a variety of application areas, including nuclei detection [ 31 , 32 ], cell detection and classification [ 33 ], drug efficacy prediction [ 34 ], tumor subtype classification [ 35 ], and lymph node metastases detection [ 36 ].…”

Section: Introductionmentioning

confidence: 99%

Contrastive Multiple Instance Learning: An Unsupervised Framework for Learning Slide-Level Representations of Whole Slide Histopathology Images without Labels

Tavolara

Gürcan

Niazi

2022

Cancers

View full text Add to dashboard Cite

Recent methods in computational pathology have trended towards semi- and weakly-supervised methods requiring only slide-level labels. Yet, even slide-level labels may be absent or irrelevant to the application of interest, such as in clinical trials. Hence, we present a fully unsupervised method to learn meaningful, compact representations of WSIs. Our method initially trains a tile-wise encoder using SimCLR, from which subsets of tile-wise embeddings are extracted and fused via an attention-based multiple-instance learning framework to yield slide-level representations. The resulting set of intra-slide-level and inter-slide-level embeddings are attracted and repelled via contrastive loss, respectively. This resulted in slide-level representations with self-supervision. We applied our method to two tasks— (1) non-small cell lung cancer subtyping (NSCLC) as a classification prototype and (2) breast cancer proliferation scoring (TUPAC16) as a regression prototype—and achieved an AUC of 0.8641 ± 0.0115 and correlation (R2) of 0.5740 ± 0.0970, respectively. Ablation experiments demonstrate that the resulting unsupervised slide-level feature space can be fine-tuned with small datasets for both tasks. Overall, our method approaches computational pathology in a novel manner, where meaningful features can be learned from whole-slide images without the need for annotations of slide-level labels. The proposed method stands to benefit computational pathology, as it theoretically enables researchers to benefit from completely unlabeled whole-slide images.

show abstract

Section: Introductionmentioning

confidence: 99%

Contrastive Multiple Instance Learning: An Unsupervised Framework for Learning Slide-Level Representations of Whole Slide Histopathology Images without Labels

Tavolara

Gürcan

Niazi

2022

Cancers

View full text Add to dashboard Cite

show abstract

“…In our previous works, the hybrid deep autoencoder (HDAE) network has been shown to be very efficient for nuclear/cell detection [21]. We have also previously designed a synchronized DL network to perform detection and classification simultaneously [26]. However, our previous network [26] can not efficiently reduce the intra-influence between detection and classification components to achieve the same performance as independent network process.…”

Section: Related Workmentioning

confidence: 99%

“…We have also previously designed a synchronized DL network to perform detection and classification simultaneously [26]. However, our previous network [26] can not efficiently reduce the intra-influence between detection and classification components to achieve the same performance as independent network process. In this paper, we propose an improved synchronized autoencoder (AE) model with a novel neighborhood selection mechanism to improve the performance of simultaneous detection and classification of erythroid and myeloid cells in bone marrow trephine histopathology images.…”

Section: Related Workmentioning

confidence: 99%

“…We quantitatively compare our network's performance to that of other current conventional and DL approaches. First, we compare the detection performance of the Syn-AHDA network to that attained by LIPSyM [8], SSAE [4] and SC-CNN [19], HDAE network [21], and our previous Syn-AHDA network [26]. Table I lists these results in terms of precision, recall, and F1-score.…”

Section: B Network Setting and Trainingmentioning

confidence: 99%

See 1 more Smart Citation

Simultaneous Cell Detection and Classification in Bone Marrow Histology Images

Song

Sánchez

EIDaly

et al. 2019

IEEE J. Biomed. Health Inform.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The predicted detected center points of nuclei are obtained by applying the deep auto encoder to unseen patches and using a second model, here a CNN or SSAE, to perform cell classification on the resulting predicted centers. In an extension [85] to this first work, the classification CNN and the SSAE were coupled to create a model that first detects then classifies cells in WSIs. The coupling is done by adding two branches to the auto encoder: one classifies the detected cells and the other predicts probability maps.…”

Section: Classification Modelsmentioning

confidence: 99%

Deep Learning Models for Digital Pathology

BenTaieb,

Hamarneh

2019

Preprint

View full text Add to dashboard Cite

Histopathology images; microscopy images of stained tissue biopsies contain fundamental prognostic information that forms the foundation of pathological analysis and diagnostic medicine. However, diagnostics from histopathology images generally rely on a visual cognitive assessment of tissue slides which implies an inherent element of interpretation and hence subjectivity. Access to digitized histopathology images enabled the development of computational systems aiming at reducing manual intervention and automating parts of pathologists' workflow. Specifically, applications of deep learning to histopathology image analysis now offer opportunities for better quantitative modeling of disease appearance and hence possibly improved prediction of disease aggressiveness and patient outcome. However digitized histopathology tissue slides are unique in a variety of ways and come with their own set of computational challenges. In this survey, we summarize the different challenges facing computational systems for digital pathology and provide a review of state-of-the-art works that developed deep learning-based solutions for the predictive modeling of histopathology images from a detection, stain normalization, segmentation, and tissue classification perspective. We then discuss the challenges facing the validation and integration of such deep learning-based computational systems in clinical workflow and reflect on future opportunities for histopathology derived image measurements and better predictive modeling.

show abstract

Simultaneous Cell Detection and Classification with an Asymmetric Deep Autoencoder in Bone Marrow Histology Images

Cited by 6 publications

References 10 publications

Contrastive Multiple Instance Learning: An Unsupervised Framework for Learning Slide-Level Representations of Whole Slide Histopathology Images without Labels

Contrastive Multiple Instance Learning: An Unsupervised Framework for Learning Slide-Level Representations of Whole Slide Histopathology Images without Labels

Simultaneous Cell Detection and Classification in Bone Marrow Histology Images

Deep Learning Models for Digital Pathology

Contact Info

Product

Resources

About