Liver lesion changes analysis in longitudinal CECT scans by simultaneous deep learning voxel classification with SimU-Net

Szeskin, Adi; Rochman, Shalom; Weiss, Snir; Lederman, Richard J.; Joskowicz, Leo

doi:10.1016/j.media.2022.102675

Cited by 12 publications

(8 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A fourth advantage is performing whole-body lesion tracking. Previous works have been limited to brain (Metcalf et al 1992, Kikinis et al 1999, Gerig et al 2000, Shahar and Greenspan 2005, Köhler et al 2019, Kuckertz et al 2021, liver (Kuckertz et al 2022, Szeskin et al 2023, or bone tissue . The fifth advantage is performing lesion tracking with multiple image modalities (PET/CT and PET/MR), whereas previous works that developed whole-body lesion matching were limited to PET/CT (Hering et al 2021, Santoro-Fernandes et al 2021 or CT images (Yan et al 2018).…”

Section: Discussionmentioning

confidence: 99%

“…Subsequent developments investigated individual tracking of brain lesions identified in MR images (Kikinis et al 1999, Gerig et al 2000, Bosc et al 2003, Köhler et al 2019, Kuckertz et al 2021. Methodologies for tracking of cancer lesions have also been investigated for lung, liver, and lymphatic lesions using CT images (Moltz et al 2009, Xu et al 2011, Kuckertz et al 2022, Szeskin et al 2023. Methodologies to track lesions spread through the whole-body were previously developed using PET/CT images, however these were constrained to bone or soft tissue lesions (Santoro-Fernandes et al 2021).…”

Section: Introductionmentioning

confidence: 99%

“…n q , K Finally, in step 6, the lesion tracking information of the image series is summarized as a lesion graph (Yan et al 2018, Kuckertz et al 2021, Szeskin et al 2023. This structure has one layer per image in the series and each node represents one lesion in each time-point, if many lesion components are clustered, each component is still represented by an individual node in the lesion graph.…”

mentioning

confidence: 99%

See 2 more Smart Citations

An automated methodology for whole-body, multimodality tracking of individual cancer lesions

Santoro-Fernandes,

Huff,

Rivetti

et al. 2024

Phys. Med. Biol.

View full text Add to dashboard Cite

Objective: Manual analysis of individual cancer lesions to assess disease response is clinically impractical and requires automated lesion tracking methodologies. However, no methodology has been developed for whole-body individual lesion tracking, across an arbitrary number of scans, and acquired with various imaging modalities. Approach: This study introduces a lesion tracking methodology and benchmarked it using 23 68Ga-DOTATATE PET/CT and PET/MR images of eight neuroendocrine tumor patients. The methodology consists of six steps: (1) Alignment of multiple scans via image registration, (2) Body-part labeling, (3) Automatic lesion-wise dilation, (4) Clustering of lesions based on local lesion shape metrics, (5) Assignment of lesion tracks, and (6) Output of a lesion graph. Registration performance was evaluated via landmark distance, lesion matching accuracy was evaluated between each image pair, and lesion tracking accuracy was evaluated via identical track ratio. Sensitivity studies were performed to evaluate the impact of lesion dilation (fixed vs. automatic dilation), anatomic location, image modalities (inter- vs. intra-modality), registration mode (direct vs. indirect registration), and track size (number of time-points and lesions) on lesion matching and tracking performance. Main Results: Manual contouring yielded 956 lesions, 1,570 lesion-matching decisions, and 493 lesion tracks. The median residual registration error was 2.5 mm. The automatic lesion dilation led to 0.90 overall lesion matching accuracy, and an 88% identical track ratio. The methodology is robust regarding anatomic locations, image modalities, and registration modes. The number of scans had a moderate negative impact on the identical track ratio (94% for 2 scans, 91% for 3 scans, and 81% for 4 scans). The number of lesions substantially impacted the identical track ratio (93% for 2 nodes vs. 54% for ≥5 nodes). Significance: The developed methodology resulted in high lesion-matching accuracy and enables automated lesion tracking in PET/CT and PET/MR.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

An automated methodology for whole-body, multimodality tracking of individual cancer lesions

Santoro-Fernandes,

Huff,

Rivetti

et al. 2024

Phys. Med. Biol.

View full text Add to dashboard Cite

show abstract

“…Both of them usually establish two or more parallel neural networks to represent longitudinal images. Afterward, the DFC-based methods utilize a similarity function to quantify the differences among features from longitudinal images [10, 11], which are usually correlated to the treatment response. It is similar to the way clinicians evaluate tumor treatment response where they typically rely on visual comparison between pre- and post-treatment CT images.…”

Section: Introductionmentioning

confidence: 99%

LOMIA-T: A Transformer-based LOngitudinal Medical Image Analysis framework for predicting treatment response of esophageal cancer

Sun,

Li,

Chen

et al. 2024

Preprint

View full text Add to dashboard Cite

Deep learning models based on medical images have made significant strides in predicting treatment outcomes. However, previous methods have primarily concentrated on single time-point images, neglecting the temporal dynamics and changes inherent in longitudinal medical images. Thus, we propose a Transformer-based longitudinal image analysis framework (LOMIA-T) to contrast and fuse latent representations from pre- and post-treatment medical images for predicting treatment response. Specifically, we first design a treatment response-based contrastive loss to enhance latent representation by discerning evolutionary processes across various disease stages. Then, we integrate latent representations from pre- and post-treatment CT images using a cross-attention mechanism. Considering the redundancy in the dual-branch output features induced by the cross-attention mechanism, we propose a clinically interpretable feature fusion strategy to predict treatment response. Experimentally, the proposed framework outperforms several state-of-the-art longitudinal image analysis methods on an in-house Esophageal Squamous Cell Carcinoma (ESCC) dataset, encompassing 170 pre- and post-treatment contrast-enhanced CT image pairs from ESCC patients underwent neoadjuvant chemoradiotherapy. Ablation experiments validate the efficacy of the proposed treatment response-based contrastive loss and feature fusion strategy. The codes will be made available at https://github.com/syc19074115/LOMIA-T.

show abstract

“…In a recent paper [ 9 ], we described a novel automatic pipeline for the simultaneous detection of liver lesions and their changes in longitudinal contrast-enhanced CT liver scans. This pipeline includes SimU-Net, a simultaneous multi-channel 3D U-Net model trained on pairs of registered scans of each patient.…”

Section: Introductionmentioning

confidence: 99%

Two is better than one: longitudinal detection and volumetric evaluation of brain metastases after Stereotactic Radiosurgery with a deep learning pipeline

Hammer,

Najjar,

Kahanov

et al. 2024

J Neurooncol

Self Cite

View full text Add to dashboard Cite

Purpose Close MRI surveillance of patients with brain metastases following Stereotactic Radiosurgery (SRS) treatment is essential for assessing treatment response and the current disease status in the brain. This follow-up necessitates the comparison of target lesion sizes in pre- (prior) and post-SRS treatment (current) T1W-Gad MRI scans. Our aim was to evaluate SimU-Net, a novel deep-learning model for the detection and volumetric analysis of brain metastases and their temporal changes in paired prior and current scans. Methods SimU-Net is a simultaneous multi-channel 3D U-Net model trained on pairs of registered prior and current scans of a patient. We evaluated its performance on 271 pairs of T1W-Gad MRI scans from 226 patients who underwent SRS. An expert oncological neurosurgeon manually delineated 1,889 brain metastases in all the MRI scans (1,368 with diameters > 5 mm, 834 > 10 mm). The SimU-Net model was trained/validated on 205 pairs from 169 patients (1,360 metastases) and tested on 66 pairs from 57 patients (529 metastases). The results were then compared to the ground truth delineations. Results SimU-Net yielded a mean (std) detection precision and recall of 1.00±0.00 and 0.99±0.06 for metastases > 10 mm, 0.90±0.22 and 0.97±0.12 for metastases > 5 mm of, and 0.76±0.27 and 0.94±0.16 for metastases of all sizes. It improves lesion detection precision by 8% for all metastases sizes and by 12.5% for metastases < 10 mm with respect to standalone 3D U-Net. The segmentation Dice scores were 0.90±0.10, 0.89±0.10 and 0.89±0.10 for the above metastases sizes, all above the observer variability of 0.80±0.13. Conclusion Automated detection and volumetric quantification of brain metastases following SRS have the potential to enhance the assessment of treatment response and alleviate the clinician workload.

show abstract

Liver lesion changes analysis in longitudinal CECT scans by simultaneous deep learning voxel classification with SimU-Net

Cited by 12 publications

References 29 publications

An automated methodology for whole-body, multimodality tracking of individual cancer lesions

An automated methodology for whole-body, multimodality tracking of individual cancer lesions

LOMIA-T: A Transformer-based LOngitudinal Medical Image Analysis framework for predicting treatment response of esophageal cancer

Two is better than one: longitudinal detection and volumetric evaluation of brain metastases after Stereotactic Radiosurgery with a deep learning pipeline

Contact Info

Product

Resources

About