Universal Loss Reweighting to Balance Lesion Size Inequality in 3D Medical Image Segmentation

Shirokikh, Boris; Shevtsov, Alexey; Kurmukov, Anvar; Dalechina, Alexandra; Krivov, Egor; Kostjuchenko, Valery; Golanov, Andrey; Belyaev, Mikhail

doi:10.1007/978-3-030-59719-1_51

Cited by 17 publications

(27 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The inference time is typically less than 5 seconds. On the hold-out dataset, our model achieves 0.9 Recall level at the 3.8 False Positive predictions per image and 0.71 object-wise Dice Score [18].…”

Section: B Deep Learning Modelmentioning

confidence: 95%

“…In [15], the improved patch sampling technique was proposed. Several works [16], [17], [18] proposed to reweight a loss function to achieve higher segmentation scores.…”

Section: A Related Workmentioning

confidence: 99%

“…Tumor sampling increases the detection quality of the model, especially for the small tumors, which is more carefully evaluated in [16]. Secondly, we supplement the Binary Cross-Entropy (BCE) loss function with the inverse weighting strategy [18]. Inverse weighting assigns larger weights to smaller lesions (inversely proportional to the lesion volume), thus further increasing the model's ability to detect small lesions.…”

Section: B Deep Learning Modelmentioning

confidence: 99%

See 2 more Smart Citations

Systematic Clinical Evaluation of a Deep Learning Method for Medical Image Segmentation: Radiosurgery Application

Shirokikh

Dalechina

Shevtsov

et al. 2022

IEEE J. Biomed. Health Inform.

Self Cite

View full text Add to dashboard Cite

We systematically evaluate a Deep Learning model in a 3D medical image segmentation task. With our model, we address the flaws of manual segmentation: high inter-rater contouring variability and time consumption of the contouring process. The main extension over the existing evaluations is the careful and detailed analysis that could be further generalized on other medical image segmentation tasks. Firstly, we analyze the changes in the inter-rater detection agreement. We show that the model reduces the number of detection disagreements by 48% (p < 0.05). Secondly, we show that the model improves the interrater contouring agreement from 0.845 to 0.871 surface Dice Score (p < 0.05). Thirdly, we show that the model accelerates the delineation process between 1.6 and 2.0 times (p < 0.05). Finally, we design the setup of the clinical experiment to either exclude or estimate the evaluation biases; thus, preserving the significance of the results. Besides the clinical evaluation, we also share intuitions and practical ideas for building an efficient DLbased model for 3D medical image segmentation.

show abstract

Section: B Deep Learning Modelmentioning

confidence: 95%

“…In [15], the improved patch sampling technique was proposed. Several works [16], [17], [18] proposed to reweight a loss function to achieve higher segmentation scores.…”

Section: A Related Workmentioning

confidence: 99%

Section: B Deep Learning Modelmentioning

confidence: 99%

See 1 more Smart Citation

Systematic Clinical Evaluation of a Deep Learning Method for Medical Image Segmentation: Radiosurgery Application

Shirokikh

Dalechina

Shevtsov

et al. 2022

IEEE J. Biomed. Health Inform.

Self Cite

View full text Add to dashboard Cite

show abstract

“…In [13], the improved patch sampling technique was proposed. Finally, several works [14], [15], [16] proposed to reweight a loss function to achieve higher segmentation scores.…”

Section: A Related Workmentioning

confidence: 99%

“…Thus, Tumor Sampling considerably increases the object-wise Recall of the model, especially for the small tumors, which is more carefully evaluated in [14]. Secondly, we supplement the Binary Cross-Entropy (BCE) loss function with the inverse weighting strategy [16]. Inverse weighting assigns larger weights to smaller lesions (inversely proportional to the lesion volume), thus further increasing the CNN's ability to detect small lesions.…”

Section: Deep Learning Modelmentioning

confidence: 99%

Systematic Clinical Evaluation of A Deep Learning Method for Medical Image Segmentation: Radiosurgery Application

Shirokikh¹,

Dalechina²,

Shevtsov³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

We systematically evaluate a Deep Learning (DL) method in a 3D medical image segmentation task. Our segmentation method is integrated into the radiosurgery treatment process and directly impacts the clinical workflow. With our method, we address the relative drawbacks of manual segmentation: high inter-rater contouring variability and high time consumption of the contouring process. The main extension over the existing evaluations is the careful and detailed analysis that could be further generalized on other medical image segmentation tasks. Firstly, we analyze the changes in the inter-rater detection agreement. We show that the segmentation model reduces the ratio of detection disagreements from 0.162 to 0.085 (p < 0.05). Secondly, we show that the model improves the inter-rater contouring agreement from 0.845 to 0.871 surface Dice Score (p < 0.05). Thirdly, we show that the model accelerates the delineation process in between 1.6 and 2.0 times (p < 0.05). Finally, we design the setup of the clinical experiment to either exclude or estimate the evaluation biases, thus preserve the significance of the results. Besides the clinical evaluation, we also summarize the intuitions and practical ideas for building an efficient DL-based model for 3D medical image segmentation.

show abstract

HFCF‐Net: A hybrid‐feature cross fusion network for COVID‐19 lesion segmentation from CT volumetric images

et al. 2022

View full text Add to dashboard Cite

Background The coronavirus disease 2019 (COVID‐19) spreads rapidly across the globe, seriously threatening the health of people all over the world. To reduce the diagnostic pressure of front‐line doctors, an accurate and automatic lesion segmentation method is highly desirable in clinic practice. Purpose Many proposed two‐dimensional (2D) methods for sliced‐based lesion segmentation cannot take full advantage of spatial information in the three‐dimensional (3D) volume data, resulting in limited segmentation performance. Three‐dimensional methods can utilize the spatial information but suffer from long training time and slow convergence speed. To solve these problems, we propose an end‐to‐end hybrid‐feature cross fusion network (HFCF‐Net) to fuse the 2D and 3D features at three scales for the accurate segmentation of COVID‐19 lesions. Methods The proposed HFCF‐Net incorporates 2D and 3D subnets to extract features within and between slices effectively. Then the cross fusion module is designed to bridge 2D and 3D decoders at the same scale to fuse both types of features. The module consists of three cross fusion blocks, each of which contains a prior fusion path and a context fusion path to jointly learn better lesion representations. The former aims to explicitly provide the 3D subnet with lesion‐related prior knowledge, and the latter utilizes the 3D context information as the attention guidance of the 2D subnet, which promotes the precise segmentation of the lesion regions. Furthermore, we explore an imbalance‐robust adaptive learning loss function that includes image‐level loss and pixel‐level loss to tackle the problems caused by the apparent imbalance between the proportions of the lesion and non‐lesion voxels, providing a learning strategy to dynamically adjust the learning focus between 2D and 3D branches during the training process for effective supervision. Result Extensive experiments conducted on a publicly available dataset demonstrate that the proposed segmentation network significantly outperforms some state‐of‐the‐art methods for the COVID‐19 lesion segmentation, yielding a Dice similarity coefficient of 74.85%. The visual comparison of segmentation performance also proves the superiority of the proposed network in segmenting different‐sized lesions. Conclusions In this paper, we propose a novel HFCF‐Net for rapid and accurate COVID‐19 lesion segmentation from chest computed tomography volume data. It innovatively fuses hybrid features in a cross manner for lesion segmentation, aiming to utilize the advantages of 2D and 3D subnets to complement each other for enhancing the segmentation performance. Benefitting from the cross fusion mechanism, the proposed HFCF‐Net can segment the lesions more accurately with the knowledge acquired from both subnets.

show abstract

Universal Loss Reweighting to Balance Lesion Size Inequality in 3D Medical Image Segmentation

Cited by 17 publications

References 18 publications

Systematic Clinical Evaluation of a Deep Learning Method for Medical Image Segmentation: Radiosurgery Application

Systematic Clinical Evaluation of a Deep Learning Method for Medical Image Segmentation: Radiosurgery Application

Systematic Clinical Evaluation of A Deep Learning Method for Medical Image Segmentation: Radiosurgery Application

HFCF‐Net: A hybrid‐feature cross fusion network for COVID‐19 lesion segmentation from CT volumetric images

Contact Info

Product

Resources

About