Learning binary and sparse permutation-invariant representations for fast and memory efficient whole slide image search

Hemati, Sobhan; Kalra, Shivam; Babaie, Morteza; Tizhoosh, Hamid R.

doi:10.1016/j.compbiomed.2023.107026

Cited by 6 publications

(4 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While most of the computational pathology tasks are designed to classify or detect the presence of pathological lesions in gigapixel WSIs, the presence of computationally redundant normal tissue in WSIs is often ignored. While a large body of scientific work has been done in the field of WSI retrieval systems to address the numerical representation of the WSI 13,[24][25][26] and WSI search engines 7,8,27,28 , no study has addressed the effect of normal tissue in the indexing and search pipeline. Therefore, removing normal tissue is not an established practice in this field.…”

Section: Discussionmentioning

confidence: 99%

Creating an atlas of normal tissue for pruning WSI patching through anomaly detection

Nejat,

Alsaafin,

Alabtah

et al. 2024

Sci Rep

View full text Add to dashboard Cite

Patching whole slide images (WSIs) is an important task in computational pathology. While most of them are designed to classify or detect the presence of pathological lesions in a WSI, the confounding role and redundant nature of normal histology are generally overlooked. In this paper, we propose and validate the concept of an “atlas of normal tissue” solely using samples of WSIs obtained from normal biopsies. Such atlases can be employed to eliminate normal fragments of tissue samples and hence increase the representativeness of the remaining patches. We tested our proposed method by establishing a normal atlas using 107 normal skin WSIs and demonstrated how established search engines like Yottixel can be improved. We used 553 WSIs of cutaneous squamous cell carcinoma to demonstrate the advantage. We also validated our method applied to an external dataset of 451 breast WSIs. The number of selected WSI patches was reduced by 30% to 50% after utilizing the proposed normal atlas while maintaining the same indexing and search performance in leave-one-patient-out validation for both datasets. We show that the proposed concept of establishing and using a normal atlas shows promise for unsupervised selection of the most representative patches of the abnormal WSI patches.

show abstract

Section: Discussionmentioning

confidence: 99%

Creating an atlas of normal tissue for pruning WSI patching through anomaly detection

Nejat,

Alsaafin,

Alabtah

et al. 2024

Sci Rep

View full text Add to dashboard Cite

show abstract

“…While most of the computational pathology tasks are designed to classify or detect the presence of pathological lesions in gigapixel WSIs, the presence of computationally redundant normal tissue in WSIs is often ignored. While a large body of scientific work has been done in the field of WSI retrieval systems to address the numerical representation of the WSI 12,[23][24][25] and WSI search engines 7,8,26,27 , no study has addressed the effect of normal tissue in the indexing and search pipeline. There- clusion as part of their workflow 28 , the potential effect of redundant normal tissue in WSI retrieval is an unknown area.…”

Section: Discussionmentioning

confidence: 99%

Creating an Atlas of Normal Tissue for Pruning WSI Patching Through Anomaly Detection

Nejat,

Alsaafin,

Alabtah

et al. 2023

Preprint

View full text Add to dashboard Cite

Patching whole slide images (WSIs) is an important task in computational pathology. While most of the are designed to classify or detect the presence of pathological lesions in a WSI, the confounding role and redundant nature of normal histology are generally overlooked. In this paper, we propose and validate the concept of an “atlas of normal tissue” solely using samples of WSIs obtained from normal biopsies. Such atlases can be employed to eliminate normal fragments of tissue samples and hence increase the representativeness the remaining patches. We tested our proposed method by establishing a normal atlas using 107 normal skin WSIs and demonstrated how established search engines like Yottixel can be improved. We used 553 WSIs of cutaneous squamous cell carcinoma to demonstrate the advantage. We also validated our method applied to an external dataset of 451 breast WSIs. The number of selected WSI patches was reduced by 30% to 50% after utilizing the proposed normal atlas while maintaining the same indexing and search performance in leave-one-patient-out validation for both datasets. We show that the proposed concept of establishing and using a normal atlas shows promise for unsupervised selection of the most representative patches of the abnormal WSI patches.

show abstract

“…It aims to provide a concise representation or prototype for the entire class of instances (Sun et al, 2017;Csurka et al, 2004;Csurka and Perronnin, 2011). Some recent works on WSI such as PMIL (Yu et al, 2023), ProtoMIL (Yu et al, 2023), and (Hemati et al, 2022) have shown the potential of using representation or prototype for clas-sification. The prototypes and image representations can be learned separately (Yu et al, 2023) or together (Yu et al, 2023) or concisely to binary and sparse (Hemati et al, 2022).…”

Section: Introductionmentioning

confidence: 99%

“…Some recent works on WSI such as PMIL (Yu et al, 2023), ProtoMIL (Yu et al, 2023), and (Hemati et al, 2022) have shown the potential of using representation or prototype for clas-sification. The prototypes and image representations can be learned separately (Yu et al, 2023) or together (Yu et al, 2023) or concisely to binary and sparse (Hemati et al, 2022). These methods limit the selection of the prototypes only based on certain representative instances or patches which can lead to a wrong choice of prototypical embeddings.…”

Section: Introductionmentioning

confidence: 99%

Leukocyte Classification Using Multimodal Architecture Enhanced by Knowledge Distillation

Yang¹,

Mehta²,

Mahapatra³

et al. 2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Recently, a lot of automated white blood cells (WBC) or leukocyte classification techniques have been developed. However, all of these methods only utilize a single modality microscopic image i.e. either blood smear or fluorescence based, thus missing the potential of a better learning from multimodal images. In this work, we develop an efficient multimodal architecture based on a first of its kind multimodal WBC dataset for the task of WBC classification. Specifically, our proposed idea is developed in two steps -1) First, we learn modality specific independent subnetworks inside a single network only; 2) We further enhance the learning capability of the independent subnetworks by distilling knowledge from high complexity independent teacher networks. With this, our proposed framework can achieve a high performance while maintaining low complexity for a multimodal dataset. Our unique contribution is twofold -1) We present a first of its kind multimodal WBC dataset for WBC classification; 2) We develop a high performing multimodal architecture which is also efficient and low in complexity at the same time.

show abstract

Learning binary and sparse permutation-invariant representations for fast and memory efficient whole slide image search

Cited by 6 publications

References 17 publications

Creating an atlas of normal tissue for pruning WSI patching through anomaly detection

Creating an atlas of normal tissue for pruning WSI patching through anomaly detection

Creating an Atlas of Normal Tissue for Pruning WSI Patching Through Anomaly Detection

Leukocyte Classification Using Multimodal Architecture Enhanced by Knowledge Distillation

Contact Info

Product

Resources

About