Delayed brain development of Rolandic epilepsy profiled by deep learning-based neuroanatomic imaging.

OBJECTIVES: Although Rolandic epilepsy (RE) has been regarded as a brain developmental disorder, neuroimaging studies have not yet ascertained whether RE has brain developmental delay. This study employed deep learning-based neuroanatomic biomarker to measure the changed feature of "brain age" in RE. METHODS: The study constructed a 3D-CNN brain age prediction model through 1155 cases of typically developing children's morphometric brain MRI from open-source datasets and further applied to a local dataset of 167 RE patients and 107 typically developing children. The brain-predicted age difference was measured to quantitatively estimate brain age changes in RE and further investigated the relevancies with cognitive and clinical variables. RESULTS: The brain age estimation network model presented a good performance for brain age prediction in typically developing children. The children with RE showed a 0.45-year delay of brain age by contrast with typically developing children. Delayed brain age was associated with neuroanatomic changes in the Rolandic regions and also associated with cognitive dysfunction of attention. CONCLUSION: This study provided neuroimaging evidence to support the notion that RE has delayed brain development. KEY POINTS: • The children with Rolandic epilepsy showed imaging phenotypes of delayed brain development with increased GM volume and decreased WM volume in the Rolandic regions. • The children with Rolandic epilepsy had a 0.45-year delay of brain-predicted age by comparing with typically developing children, using 3D-CNN-based brain age prediction model. • The delayed brain age was associated with morphometric changes in the Rolandic regions and attentional deficit in Rolandic epilepsy.

Transformer guided progressive fusion network for 3D pancreas and pancreatic mass segmentation.

Pancreatic masses are diverse in type, often making their clinical management challenging. This study aims to address the task of various types of pancreatic mass segmentation and detection while accurately segmenting the pancreas. Although convolution operation performs well at extracting local details, it experiences difficulty capturing global representations. To alleviate this limitation, we propose a transformer guided progressive fusion network (TGPFN) that utilizes the global representation captured by the transformer to supplement long-range dependencies lost by convolution operations at different resolutions. TGPFN is built on a branch-integrated network structure, where the convolutional neural network and transformer branches first perform separate feature extraction in the encoder, and then the local and global features are progressively fused in the decoder. To effectively integrate the information of the two branches, we design a transformer guidance flow to ensure feature consistency, and present a cross-network attention module to capture the channel dependencies. Extensive experiments with nnUNet (3D) show that TGPFN improves the mass segmentation (Dice: 73.93% vs. 69.40%) and detection accuracy (detection rate: 91.71% vs. 84.97%) on 416 private CTs, and also obtains performance improvements of mass segmentation (Dice: 43.86% vs. 42.07%) and detection (detection rate: 83.33% vs. 71.74%) on 419 public CTs.

M3Net: A multi-scale multi-view framework for multi-phase pancreas segmentation based on cross-phase non-local attention.

The complementation of arterial and venous phases visual information of CTs can help better distinguish the pancreas from its surrounding structures. However, the exploration of cross-phase contextual information is still under research in computer-aided pancreas segmentation. This paper presents M3Net, a framework that integrates multi-scale multi-view information for multi-phase pancreas segmentation. The core of M3Net is built upon a dual-path network in which individual branches are set up for two phases. Cross-phase interactive connections bridging the two branches are introduced to interleave and integrate dual-phase complementary visual information. Besides, we further devise two types of non-local attention modules to enhance the high-level feature representation across phases. First, we design a location attention module to generate cross-phase reliable feature correlations to suppress the misalignment regions. Second, the depth-wise attention module is used to capture the channel dependencies and then strengthen feature representations. The experiment data consists of 224 internal CTs (106 normal and 118 abnormal) with 1 mm slice thickness, and 66 external CTs (29 normal and 37 abnormal) with 5 mm slice thickness. We achieve new state-of-the-art performance with average DSC of 91.19% on internal data, and promising result with average DSC of 86.34% on external data.

A deep learning algorithm to improve readers' interpretation and speed of pancreatic cystic lesions on dual-phase enhanced CT.

PURPOSE: To develop a deep learning model (DLM) to improve readers' interpretation and speed in the differentiation of pancreatic cystic lesions (PCLs) on dual-phase enhanced CT, and a low contrast media dose, external testing set validated the model. MATERIALS AND METHODS: Dual-phase enhanced CT images of 363 patients with 368 PCLs obtained from two centers were retrospectively assessed. Based on the examination date, a training and validation set of 266 PCLs, an internal testing set of 52 PCLs were designated from center 1. An external testing set included 50 PCLs from center 2. Clinical and radiological characteristics were compared. The DLM was developed using 3D specially designed densely connected convolutional networks for PCL differentiation. Radiomic features were extracted to build a traditional radiomics model (RM). Performance of the DLM, traditional RM, and three readers was compared. RESULTS: The accuracy for differential diagnosis was 0.904 with DLM, which was the highest in the internal testing set. Accuracy differences between the DLM and senior radiologist were not significant both in the internal and external testing set (both p > 0.05). With the help of the DLM, the accuracy and specificity of the junior radiologist were significantly improved (all p < 0.05), and all readers' diagnostic time was shortened (all p < 0.05). CONCLUSION: The DLM achieved senior radiologist-level performance in differentiating benign and malignant PCLs which could improve the junior radiologist's interpretation and speed of PCLs on CT.