Unsupervised anomaly localization in high-resolution breast scans using deep pluralistic image completion

要約

タイトル: 深層多様画像完了を用いた高解像度乳房スキャンの非教師異常部位の特定

要約:

– 乳房の異常検出は、異常画像が希少であり、乳房組織の変動が多いため、難しいタスクである。
– 一般的な異常検出研究は、医療画像データセットに適用すると不十分であることが多い。
– 画像完了の観点から問題を解決すると、周囲を条件にした自動完了の外観と元の外観の差異によって、異常部位を示すことができる。
– しかし、同じ周囲に対して多くの適切な完了方法があるため、評価基準は不正確になる可能性がある。
– MCD（最小完了距離）という新しい指標を提案し、不正確な完了方法に対して有効な多様な完了を生成するスペーシャルドロップアウトと組み合わせることで、高解像度の乳房スキャンで異常の特定に優れた性能を発揮する。

要約(オリジナル)

Automated tumor detection in Digital Breast Tomosynthesis (DBT) is a difficult task due to natural tumor rarity, breast tissue variability, and high resolution. Given the scarcity of abnormal images and the abundance of normal images for this problem, an anomaly detection/localization approach could be well-suited. However, most anomaly localization research in machine learning focuses on non-medical datasets, and we find that these methods fall short when adapted to medical imaging datasets. The problem is alleviated when we solve the task from the image completion perspective, in which the presence of anomalies can be indicated by a discrepancy between the original appearance and its auto-completion conditioned on the surroundings. However, there are often many valid normal completions given the same surroundings, especially in the DBT dataset, making this evaluation criterion less precise. To address such an issue, we consider pluralistic image completion by exploring the distribution of possible completions instead of generating fixed predictions. This is achieved through our novel application of spatial dropout on the completion network during inference time only, which requires no additional training cost and is effective at generating diverse completions. We further propose minimum completion distance (MCD), a new metric for detecting anomalies, thanks to these stochastic completions. We provide theoretical as well as empirical support for the superiority over existing methods of using the proposed method for anomaly localization. On the DBT dataset, our model outperforms other state-of-the-art methods by at least 10\% AUROC for pixel-level detection.

arxiv情報

提供元, 利用サービス

arxiv.jp, OpenAI