Trustworthy Applications of ML Algorithms in Medicine - Discussion and Preliminary Results for a Problem of Small Vessels Disease Diagnosis

Ferlin, Maria; Klawikowska, Zuzanna; Julia, Niemierko; Grzywińska, Małgorzata; Kwasigroch, Arkadiusz; Szurowska, Edyta

doi:10.1007/978-3-031-16159-9_1

Cited by 1 publication

(1 citation statement)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In many fields, including sensitive and socially relevant ones such as medicine, the explainability of the model is crucial for its trustworthy and, thus, safe use [37,77,78]. The MIL model prediction might be interpreted by skilfully visualising the critical instances discerned by an aggregation operator corresponding to the attention mechanism (Figure 4, Equation ( 1)).…”

Section: Attention Pooling Mechanismmentioning

confidence: 99%

Attention-Based Deep Learning System for Classification of Breast Lesions—Multimodal, Weakly Supervised Approach

Bobowicz,

Rygusik,

Buler

et al. 2023

Cancers

View full text Add to dashboard Cite

Breast cancer is the most frequent female cancer, with a considerable disease burden and high mortality. Early diagnosis with screening mammography might be facilitated by automated systems supported by deep learning artificial intelligence. We propose a model based on a weakly supervised Clustering-constrained Attention Multiple Instance Learning (CLAM) classifier able to train under data scarcity effectively. We used a private dataset with 1174 non-cancer and 794 cancer images labelled at the image level with pathological ground truth confirmation. We used feature extractors (ResNet-18, ResNet-34, ResNet-50 and EfficientNet-B0) pre-trained on ImageNet. The best results were achieved with multimodal-view classification using both CC and MLO images simultaneously, resized by half, with a patch size of 224 px and an overlap of 0.25. It resulted in AUC-ROC = 0.896 ± 0.017, F1-score 81.8 ± 3.2, accuracy 81.6 ± 3.2, precision 82.4 ± 3.3, and recall 81.6 ± 3.2. Evaluation with the Chinese Mammography Database, with 5-fold cross-validation, patient-wise breakdowns, and transfer learning, resulted in AUC-ROC 0.848 ± 0.015, F1-score 78.6 ± 2.0, accuracy 78.4 ± 1.9, precision 78.8 ± 2.0, and recall 78.4 ± 1.9. The CLAM algorithm’s attentional maps indicate the features most relevant to the algorithm in the images. Our approach was more effective than in many other studies, allowing for some explainability and identifying erroneous predictions based on the wrong premises.

show abstract

Section: Attention Pooling Mechanismmentioning

confidence: 99%