DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classification

Abstract

Multiple instance learning (MIL) has been increasingly used in the classification of histopathology whole slide images (WSIs). However, MIL approaches for this specific classification problem still face unique challenges, particularly those related to small sample cohorts. In these, there are limited number of WSI slides (bags), while the resolution of a single WSI is huge, which leads to a large number of patches (instances) cropped from this slide. To address this issue, we propose to virtually enlarge the number of bags by introducing the concept of pseudo-bags, on which a double-tier MIL framework is built to effectively use the intrinsic features. Besides, we also contribute to deriving the instance probability under the framework of attentionbased MIL, and utilize the derivation to help construct and analyze the proposed framework. The proposed method outperforms other latest methods on the CAMELYON-16 by substantially large margins, and is also better in performance on the TCGA lung cancer dataset. The proposed framework is ready to be extended for wider MIL applications. The code is available at: https://github. com/hrzhang1123/DTFD-MIL

Syndrome Types Classification Method of Skin Diseases Based on Tongue Hierarchical Feature Fusion

“…With the continuous development of artificial intelligence technology, computer vision is being applied in various areas of the medical field, including medical image processing [7], [8], [9], intelligent medical systems [10], and disease prediction [11]. The objective and intelligent research of tongue diagnosis is an important research direction, which can assist doctors in diagnosing diseases quickly and accurately through auxiliary diagnosis and treatment systems.…”

Multi-instance embedding learning with deconfounded instance-level prediction

“…( 7) is that the employed d(•, •) has a significant impact on embedding results. Therefore, by considering the probability distribution of instances in the bag, we design a new bag-level embedding with feature distillation [21] as follows:…”

“…A label is assigned to the bag, but not to the individual instances. To date, MIL has also been frequently utilized in a variety of applications, such as image classification [18,19], text categorization [9,17], sentiment analysis [1], web index recommendation [12,16], whole slide images [8,21], and video anomaly detection [7]. Among them, the embedding-based approaches are one of the representative researches in MIL, with the primary notion of transforming bags into a new feature vector and establishing the learning process using SIL methods [17,22].…”

Artificial intelligence-based real-time histopathology of gastric cancer using confocal laser endomicroscopy

“…Subsequently, the AI model is utilized to detect tumor areas within each patch image 17 . Alternatively, a whole-slide-image-level diagnosis can be achieved through the implementation of weakly supervised learning models 18 . As these methodologies continue to evolve, the comprehensive validation of AI models for interpretation becomes imperative, particularly when considering their deployment as standalone modalities 19 .…”

“…This system has potential applications in intraoperative margin assessment 22 , and margin diagnosis of endoscopic submucosal dissection specimens 18 . As the real-world environment introduces various factors and artifacts into CLES images, there is the potential for decreased performance compared to our current results.…”