Simone Bendazzoli

Mehdi Astaraki, Simone Bendazzoli, Iuliana Toma-Dasu

Target segmentation in CT images of Head&Neck (H&N) region is challenging due to low contrast between adjacent soft tissue. The SegRap 2023 challenge has been focused on benchmarking the segmentation algorithms of Nasopharyngeal Carcinoma (NPC) which would be employed as auto-contouring tools for radiation treatment planning purposes. We propose a fully-automatic framework and develop two models for a) segmentation of 45 Organs at Risk (OARs) and b) two Gross Tumor Volumes (GTVs). To this end, we preprocess the image volumes by harmonizing the intensity distributions and then automatically cropping the volumes around the target regions. The preprocessed volumes were employed to train a standard 3D U-Net model for each task, separately. Our method took second place for each of the tasks in the validation phase of the challenge. The proposed framework is available at https://github.com/Astarakee/segrap2023

Simone Bendazzoli, Antonios Tzortzakakis, Andreas Abrahamsson et al.

Early cancer detection is crucial for improving patient outcomes, and 18F FDG PET/CT imaging plays a vital role by combining metabolic and anatomical information. Accurate lesion detection remains challenging due to the need to identify multiple lesions of varying sizes. In this study, we investigate the effect of adding anatomy prior information to deep learning-based lesion detection models. In particular, we add organ segmentation masks from the TotalSegmentator tool as auxiliary inputs to provide anatomical context to nnDetection, which is the state-of-the-art for lesion detection, and Swin Transformer. The latter is trained in two stages that combine self-supervised pre-training and supervised fine-tuning. The method is tested in the AutoPET and Karolinska lymphoma datasets. The results indicate that the inclusion of anatomical priors substantially improves the detection performance within the nnDetection framework, while it has almost no impact on the performance of the vision transformer. Moreover, we observe that Swin Transformer does not offer clear advantages over conventional convolutional neural network (CNN) encoders used in nnDetection. These findings highlight the critical role of the anatomical context in cancer lesion detection, especially in CNN-based models.

Simone Bendazzoli, Mehdi Astaraki

Tumor segmentation in PET-CT images is challenging due to the dual nature of the acquired information: low metabolic information in CT and low spatial resolution in PET. U-Net architecture is the most common and widely recognized approach when developing a fully automatic image segmentation method in the medical field. We proposed a two-step approach, aiming to refine and improve the segmentation performances of tumoral lesions in PET-CT. The first step generates a prior tumor appearance map from the PET-CT volumes, regarded as prior tumor information. The second step, consisting of a standard U-Net, receives the prior tumor appearance map and PET-CT images to generate the lesion mask. We evaluated the method on the 1014 cases available for the AutoPET 2022 challenge, and the results showed an average Dice score of 0.701 on the positive cases.

Mehdi Astaraki, Simone Bendazzoli

The automatic segmentation of pathological regions within whole-body PET-CT volumes has the potential to streamline various clinical applications such as diagno-sis, prognosis, and treatment planning. This study aims to address this challenge by contributing to the AutoPET MICCAI 2024 challenge through a proposed workflow that incorporates image preprocessing, tracer classification, and lesion segmentation steps. The implementation of this pipeline led to a significant enhancement in the segmentation accuracy of the models. This improvement is evidenced by an average overall Dice score of 0.548 across 1611 training subjects, 0.631 and 0.559 for classi-fied FDG and PSMA subjects of the training set, and 0.792 on the preliminary testing phase dataset.

Simone Bendazzoli, Sanna Persson, Mehdi Astaraki et al.

The integration of Artificial Intelligence (AI) into clinical workflows requires robust collaborative platforms that are able to bridge the gap between technical innovation and practical healthcare applications. This paper introduces MAIA (Medical Artificial Intelligence Assistant), an open-source platform designed to facilitate interdisciplinary collaboration among clinicians, researchers, and AI developers. Built on Kubernetes, MAIA offers a modular, scalable environment with integrated tools for data management, model development, annotation, deployment, and clinical feedback. Key features include project isolation, CI/CD automation, integration with high-computing infrastructures and in clinical workflows. MAIA supports real-world use cases in medical imaging AI, with deployments in both academic and clinical environments. By promoting collaborations and interoperability, MAIA aims to accelerate the translation of AI research into impactful clinical solutions while promoting reproducibility, transparency, and user-centered design. We showcase the use of MAIA with different projects, both at KTH Royal Institute of Technology and Karolinska University Hospital.

Jingru Fu, Simone Bendazzoli, Örjan Smedby et al.

Significant advances have been made toward building accurate automatic segmentation models for adult gliomas. However, the performance of these models often degrades when applied to pediatric glioma due to their imaging and clinical differences (domain shift). Obtaining sufficient annotated data for pediatric glioma is typically difficult because of its rare nature. Also, manual annotations are scarce and expensive. In this work, we propose Domain-Adapted nnU-Net (DA-nnUNet) to perform unsupervised domain adaptation from adult glioma (source domain) to pediatric glioma (target domain). Specifically, we add a domain classifier connected with a gradient reversal layer (GRL) to a backbone nnU-Net. Once the classifier reaches a very high accuracy, the GRL is activated with the goal of transferring domain-invariant features from the classifier to the segmentation model while preserving segmentation accuracy on the source domain. The accuracy of the classifier slowly degrades to chance levels. No annotations are used in the target domain. The method is compared to 8 different supervised models using BraTS-Adult glioma (N=1251) and BraTS-PED glioma data (N=99). The proposed method shows notable performance enhancements in the tumor core (TC) region compared to the model that only uses adult data: ~32% better Dice scores and ~20 better 95th percentile Hausdorff distances. Moreover, our unsupervised approach shows no statistically significant difference compared to the practical upper bound model using manual annotations from both datasets in TC region. The code is shared at https://github.com/Fjr9516/DA_nnUNet.

Xiangde Luo, Jia Fu, Yunxin Zhong et al.

Radiation therapy is a primary and effective NasoPharyngeal Carcinoma (NPC) treatment strategy. The precise delineation of Gross Tumor Volumes (GTVs) and Organs-At-Risk (OARs) is crucial in radiation treatment, directly impacting patient prognosis. Previously, the delineation of GTVs and OARs was performed by experienced radiation oncologists. Recently, deep learning has achieved promising results in many medical image segmentation tasks. However, for NPC OARs and GTVs segmentation, few public datasets are available for model development and evaluation. To alleviate this problem, the SegRap2023 challenge was organized in conjunction with MICCAI2023 and presented a large-scale benchmark for OAR and GTV segmentation with 400 Computed Tomography (CT) scans from 200 NPC patients, each with a pair of pre-aligned non-contrast and contrast-enhanced CT scans. The challenge's goal was to segment 45 OARs and 2 GTVs from the paired CT scans. In this paper, we detail the challenge and analyze the solutions of all participants. The average Dice similarity coefficient scores for all submissions ranged from 76.68\% to 86.70\%, and 70.42\% to 73.44\% for OARs and GTVs, respectively. We conclude that the segmentation of large-size OARs is well-addressed, and more efforts are needed for GTVs and small-size or thin-structure OARs. The benchmark will remain publicly available here: https://segrap2023.grand-challenge.org