Background Automated segmentation of glioma subregions on multiparametric MRI can be improved by changing either the network architecture or the information presented to the network. These two design levers are usually studied together, which makes their individual contributions difficult to see. We present an integrated analysis of two completed, independent studies, each of which isolates one lever. Methods In the architecture-level study (Slice), SIBA-UNet—a 2D U-Net combining depthwise separable convolution, inverted-bottleneck blocks and attention-guided skip fusion—was trained on 128×128 multimodal slices from BraTS 2020 with a patient-level split, and a sigmoid decision threshold was selected on validation data. In the representation-level study (Subtract), CMSR-3D augmented the four standard MRI sequences with four voxel-wise cross-modal subtraction maps (T1−T1CE, T2−FLAIR, FLAIR−T1CE, T2−T1CE) and evaluated 4-, 6- and 8-channel inputs with an identical 3D U-Net on 1,251 BraTS-GLI 2023 cases (1,001/125/125 split). Results SIBA-UNet reached an overall validation Dice of 0.8601 at a validation-selected threshold of 0.51, with reported subregion Dice of 0.8795 (necrotic core), 0.8501 (edema) and 0.9125 (enhancing tumor); the source ablation was only partially reported. With the architecture held fixed, the 8-channel CMSR-3D configuration gave the highest mean Dice among the evaluated inputs (0.8699 vs. 0.8534 for the 4-channel baseline) and the lowest mean HD95 (5.9859 vs. 8.2308), whereas either two-map subset alone changed mean Dice by at most 0.0037. Conclusions Architecture design and input-representation design are separable levers for brain tumor segmentation. The controlled representation ablation indicates that the complete set of subtraction maps was more informative than either subset under a fixed 3D U-Net. Both studies were evaluated internally on their respective datasets, and their numerical results are not directly compared because the datasets, dimensionality and evaluation protocols differ.
Abstract This study proposes a 2.5D input framework for brain tumor segmentation in multi-sequence magnetic resonance imaging (MRI), aiming to balance computational efficiency and spatial context compared to conventional 2D approaches. While 2D methods are efficient but limited in capturing inter-slice information, the...
Sawehel Tlahig, Max Bindemann, T. Schanze· Current Directions in Biomed...· 0 citations
Automated prostate lesion detection from diffusion-weighted MR imaging (DWI) conventionally relies on reconstructed images and does not fully use all acquisition information. We present an end-to-end network that uses complex multicoil DWI data and coil sensitivity information for prostate lesion segmentation. We inclu...
Lukas T. Rotkopf, Marc Schlimbach, K. Kröninger et al.· 0 citations
Brain tumor segmentation from MRI is crucial for diagnosis, treatment planning, and patient monitoring, yet many automated segmentation models struggle to capture global contextual information while preserving fine spatial details, leading to inaccurate delineation of complex tumor boundaries and reduced clinical relia...
A. Karim, I. Purnama, Kusmanto Kusmanto et al.· Jurnal Teknik Informatika (J...· 0 citations
VGG16-MCA UNet is presented, a hybrid architecture pairing an ImageNet-pretrained VGG16 encoder with a decoder in which a Multi-Channel Attention (MCA) module recalibrates features after each skip-connection fusion, trained with the Focal Tversky loss to counter severe foreground-background imbalance.
Shubham Gajjar, Deep Joshi, Avi Poptani et al.· arXiv.org· 0 citations
Its high multi-center adaptability and stability in small-lesion segmentation make it suitable for cross-institutional promotion, providing reliable anatomical references for prognosis assessment, doctor-patient communication, and rehabilitation monitoring.
Jia-Tong Wang, Hong-Xun Cui, Yong-Hui Liu et al.· 0 citations
Accurate segmentation of biomedical images is essential for medical diagnosis and treatment planning, enabling automated and reliable analysis of complex imaging data. Despite the widespread use of U-Net and its variants, challenges remain, including internal covariate shifts and suboptimal feature extraction, which...