arXiv:2511.17146v1 Announce Type: new 
Abstract: Traditional loss functions in medical image segmentation, such as Dice, often under-segment small lesions because their small relative volume contributes negligibly to the overall loss. To address this, instance-wise loss functions and metrics have been proposed to evaluate segmentation quality on a per-lesion basis. We introduce CC-DiceCE, a loss function based on the CC-Metrics framework, and compare it with the existing blob loss. Both are benchmarked against a DiceCE baseline within the nnU-Net framework, which provides a robust and standardized setup. We find that CC-DiceCE loss increases detection (recall) with minimal to no degradation in segmentation performance, albeit at the cost of slightly more false positives. Furthermore, our multi-dataset study shows that CC-DiceCE generally outperforms blob loss.

تم تقديم دالة خسارة جديدة، CC-DiceCE، لتجزئة الآفات الدماغية الصغيرة، حيث تعالج القيود التي تواجه دوال الخسارة التقليدية مثل Dice التي غالبًا ما تفشل في تجزئة الآفات الصغيرة بشكل كافٍ. تم تقييم هذه الدالة المعتمدة على الحالة مقابل طرق موجودة ضمن إطار عمل nnU-Net، مما يظهر تحسينات في معدلات الكشف مع تأثير ضئيل على الأداء العام للتجزئة.

Se ha introducido una nueva función de pérdida, CC-DiceCE, para la segmentación de pequeñas lesiones cerebrales, abordando las limitaciones de las funciones de pérdida tradicionales como Dice, que a menudo no logran segmentar adecuadamente las lesiones pequeñas. Esta función de pérdida basada en instancias se compara con métodos existentes dentro del marco nnU-Net, demostrando tasas de detección mejoradas con un impacto mínimo en el rendimiento general de segmentación.

Une nouvelle fonction de perte, CC-DiceCE, a été introduite pour la segmentation des petites lésions cérébrales, répondant aux limites des fonctions de perte traditionnelles comme Dice qui échouent souvent à segmenter adéquatement les petites lésions. Cette fonction de perte instance-wise est comparée à des méthodes existantes dans le cadre de nnU-Net, montrant des taux de détection améliorés avec un impact minimal sur la performance globale de segmentation.

A new loss function, CC-DiceCE, has been introduced for small cerebral lesion segmentation, addressing the limitations of traditional loss functions like Dice that often fail to adequately segment small lesions. This instance-wise loss function is benchmarked against existing methods within the nnU-Net framework, demonstrating improved detection rates with minimal impact on overall segmentation performance.

Learning to Look Closer: A New Instance-Wise Loss for Small Cerebral Lesion Segmentation

arXiv:2403.17770v2 Announce Type: replace-cross 
Abstract: Despite the significant success achieved by deep learning methods in medical image segmentation, researchers still struggle in the computer-aided diagnosis of abdominal lymph nodes due to the complex abdominal environment, small and indistinguishable lesions, and limited annotated data. To address these problems, we present a pipeline that integrates the conditional diffusion model for lymph node generation and the nnU-Net model for lymph node segmentation to improve the segmentation performance of abdominal lymph nodes through synthesizing a diversity of realistic abdominal lymph node data. We propose LN-DDPM, a conditional denoising diffusion probabilistic model (DDPM) for lymph node (LN) generation. LN-DDPM utilizes lymph node masks and anatomical structure masks as model conditions. These conditions work in two conditioning mechanisms: global structure conditioning and local detail conditioning, to distinguish between lymph nodes and their surroundings and better capture lymph node characteristics. The obtained paired abdominal lymph node images and masks are used for the downstream segmentation task. Experimental results on the abdominal lymph node datasets demonstrate that LN-DDPM outperforms other generative methods in the abdominal lymph node image synthesis and better assists the downstream abdominal lymph node segmentation task.

تم تطوير خط أنابيب جديد يدمج نماذج الانتشار الشرطية وnnU-Net لتحسين تقسيم العقد اللمفاوية البطنية، حيث يتناول التحديات مثل البيئات المعقدة والبيانات المعلّمة المحدودة. يستخدم هذا النهج LN-DDPM، وهو نموذج احتمالي لإزالة الضوضاء الشرطية، لتوليد بيانات عقد لمفاوية متنوعة وواقعية، مما يحسن أداء التقسيم.

Se ha desarrollado un nuevo pipeline que integra modelos de difusión condicional y nnU-Net para mejorar la segmentación de ganglios linfáticos abdominales, abordando desafíos como entornos complejos y datos anotados limitados. Este enfoque utiliza LN-DDPM, un modelo probabilístico de difusión de eliminación de ruido, para generar datos de ganglios linfáticos diversos y realistas, mejorando así el rendimiento de la segmentación.

Un nouveau pipeline intégrant des modèles de diffusion conditionnels et nnU-Net a été développé pour améliorer la segmentation des ganglions lymphatiques abdominaux, en s'attaquant à des défis tels que des environnements complexes et des données annotées limitées. Cette approche utilise LN-DDPM, un modèle probabiliste de diffusion de débruitage conditionnel, pour générer des données de ganglions lymphatiques diverses et réalistes, améliorant ainsi les performances de segmentation.

A new pipeline integrating conditional diffusion models and nnU-Net has been developed to enhance the segmentation of abdominal lymph nodes, addressing challenges such as complex environments and limited annotated data. This approach utilizes LN-DDPM, a conditional denoising diffusion probabilistic model, to generate diverse and realistic lymph node data, improving segmentation performance.

Learning to Look Closer: A New Instance-Wise Loss for Small Cerebral Lesion Segmentation

Was this article worth reading? Share it

LucidQuery AI

WasItAI

Attentive AI