Improved performance and consistency of deep learning 3D liver segmentation with heterogeneous cancer stages in magnetic resonance imaging

Purpose Accurate liver segmentation is key for volumetry assessment to guide treatment decisions. Moreover, it is an important pre-processing step for cancer detection algorithms. Liver segmentation can be especially challenging in patients with cancer-related tissue changes and shape deformation. The aim of this study was to assess the ability of state-of-the-art deep learning 3D liver segmentation algorithms to generalize across all different Barcelona Clinic Liver Cancer (BCLC) liver cancer stages. Methods This retrospective study, included patients from an institutional database that had arterial-phase T1-weighted magnetic resonance images with corresponding manual liver segmentations. The data was split into 70/15/15% for training/validation/testing each proportionally equal across BCLC stages. Two 3D convolutional neural networks were trained using identical U-net-derived architectures with equal sized training datasets: one spanning all BCLC stages (“All-Stage-Net": AS-Net), and one limited to early and intermediate BCLC stages (“Early-Intermediate-Stage-Net": EIS-Net). Segmentation accuracy was evaluated by the Dice Similarity Coefficient (DSC) on a dataset spanning all BCLC stages and a Wilcoxon signed-rank test was used for pairwise comparisons. Results 219 subjects met the inclusion criteria (170 males, 49 females, 62.8±9.1 years) from all BCLC stages. Both networks were trained using 129 subjects: AS-Net training comprised 19, 74, 18, 8, and 10 BCLC 0, A, B, C, and D patients, respectively; EIS-Net training comprised 21, 86, and 22 BCLC 0, A, and B patients, respectively. DSCs (mean±SD) were 0.954±0.018 and 0.946±0.032 for AS-Net and EIS-Net (p<0.001), respectively. The AS-Net 0.956±0.014 significantly outperformed the EIS-Net 0.941±0.038 on advanced BCLC stages (p<0.001) and yielded similarly good segmentation performance on early and intermediate stages (AS-Net: 0.952±0.021; EIS-Net: 0.949±0.027; p = 0.107). Conclusion To ensure robust segmentation performance across cancer stages that is independent of liver shape deformation and tumor burden, it is critical to train deep learning models on heterogeneous imaging data spanning all BCLC stages.

Download Full-text

Using Convolutional Encoder Networks to Determine the Optimal Magnetic Resonance Image for the Automatic Segmentation of Multiple Sclerosis

Applied Sciences ◽

10.3390/app11188335 ◽

2021 ◽

Vol 11 (18) ◽

pp. 8335

Author(s):

Shaurnav Ghosh ◽

Marc Huo ◽

Mst Shamim Ara Shawkat ◽

Serena McCalla

Keyword(s):

Multiple Sclerosis ◽

Deep Learning ◽

Magnetic Resonance ◽

Statistical Significance ◽

Automatic Segmentation ◽

Magnetic Resonance Images ◽

Dice Similarity Coefficient ◽

Learning Models ◽

Mri Sequences ◽

Convolutional Encoder

Multiple Sclerosis (MS) is a neuroinflammatory demyelinating disease that affects over 2,000,000 individuals worldwide. It is characterized by white matter lesions that are identified through the segmentation of magnetic resonance images (MRIs). Manual segmentation is very time-intensive because radiologists spend a great amount of time labeling T1-weighted, T2-weighted, and FLAIR MRIs. In response, deep learning models have been created to reduce segmentation time by automatically detecting lesions. These models often use individual MRI sequences as well as combinations, such as FLAIR2, which is the multiplication of FLAIR and T2 sequences. Unlike many other studies, this seeks to determine an optimal MRI sequence, thus reducing even more time by not having to obtain other MRI sequences. With this consideration in mind, four Convolutional Encoder Networks (CENs) with different network architectures (U-Net, U-Net++, Linknet, and Feature Pyramid Network) were used to ensure that the optimal MRI applies to a wide array of deep learning models. Each model had used a pretrained ResNeXt-50 encoder in order to conserve memory and to train faster. Training and testing had been performed using two public datasets with 30 and 15 patients. Fisher’s exact test was used to evaluate statistical significance, and the automatic segmentation times were compiled for the top two models. This work determined that FLAIR is the optimal sequence based on Dice Similarity Coefficient (DSC) and Intersection over Union (IoU). By using FLAIR, the U-Net++ with the ResNeXt-50 achieved a high DSC of 0.7159.

Download Full-text

Knee Cartilage Thickness Differs Alongside Ages: A 3-T Magnetic Resonance Research Upon 2,481 Subjects via Deep Learning

Frontiers in Medicine ◽

10.3389/fmed.2020.600049 ◽

2021 ◽

Vol 7 ◽

Author(s):

Liping Si ◽

Kai Xuan ◽

Jingyu Zhong ◽

Jiayu Huo ◽

Yue Xing ◽

...

Keyword(s):

Regression Analysis ◽

Deep Learning ◽

Magnetic Resonance ◽

Knee Joint ◽

Magnetic Resonance Images ◽

Cartilage Thickness ◽

Imaging Data ◽

Knee Cartilage ◽

Large Collection ◽

The Relationship

Background: It was difficult to distinguish the cartilage thinning of an entire knee joint and to track the evolution of cartilage morphology alongside ages in the general population, which was of great significance for studying osteoarthritis until big imaging data and artificial intelligence are fused. The purposes of our study are (1) to explore the cartilage thickness in anatomical regions of the knee joint among a large collection of healthy knees, and (2) to investigate the relationship between the thinning pattern of the cartilages and the increasing ages.Methods: In this retrospective study, 2,481 healthy knees (subjects ranging from 15 to 64 years old, mean age: 35 ± 10 years) were recruited. With magnetic resonance images of knees acquired on a 3-T superconducting scanner, we automatically and precisely segmented the cartilage via deep learning and calculated the cartilage thickness in 14 anatomical regions. The thickness readings were compared using ANOVA by considering the factors of age, sex, and side. We further tracked the relationship between the thinning pattern of the cartilage thickness and the increasing ages by regression analysis.Results: The cartilage thickness was always thicker in the femur than corresponding regions in the tibia (p < 0.05). Regression analysis suggested cartilage thinning alongside ages in all regions (p < 0.05) except for medial and lateral anterior tibia in both females and males (p > 0.05). The thinning speed of men was faster than women in medial anterior and lateral anterior femur, yet slower in the medial patella (p < 0.05).Conclusion: We established the calculation method of cartilage thickness using big data and deep learning. We demonstrated that cartilage thickness differed across individual regions in the knee joint. Cartilage thinning alongside ages was identified, and the thinning pattern was consistent in the tibia while inconsistent in patellar and femoral between sexes. These findings provide a potential reference to detect cartilage anomaly.

Download Full-text

Transductive Transfer Learning for Domain Adaptation in Brain Magnetic Resonance Image Segmentation

Frontiers in Neuroscience ◽

10.3389/fnins.2021.608808 ◽

2021 ◽

Vol 15 ◽

Author(s):

Kaisar Kushibar ◽

Mostafa Salem ◽

Sergi Valverde ◽

Àlex Rovira ◽

Joaquim Salvi ◽

...

Keyword(s):

Image Segmentation ◽

Deep Learning ◽

Magnetic Resonance ◽

Transfer Learning ◽

Domain Adaptation ◽

Brain Mri ◽

Magnetic Resonance Images ◽

Medical Image Segmentation ◽

Dice Similarity Coefficient ◽

Shift Effect

Segmentation of brain images from Magnetic Resonance Images (MRI) is an indispensable step in clinical practice. Morphological changes of sub-cortical brain structures and quantification of brain lesions are considered biomarkers of neurological and neurodegenerative disorders and used for diagnosis, treatment planning, and monitoring disease progression. In recent years, deep learning methods showed an outstanding performance in medical image segmentation. However, these methods suffer from generalisability problem due to inter-centre and inter-scanner variabilities of the MRI images. The main objective of the study is to develop an automated deep learning segmentation approach that is accurate and robust to the variabilities in scanner and acquisition protocols. In this paper, we propose a transductive transfer learning approach for domain adaptation to reduce the domain-shift effect in brain MRI segmentation. The transductive scenario assumes that there are sets of images from two different domains: (1) source—images with manually annotated labels; and (2) target—images without expert annotations. Then, the network is jointly optimised integrating both source and target images into the transductive training process to segment the regions of interest and to minimise the domain-shift effect. We proposed to use a histogram loss in the feature level to carry out the latter optimisation problem. In order to demonstrate the benefit of the proposed approach, the method has been tested in two different brain MRI image segmentation problems using multi-centre and multi-scanner databases for: (1) sub-cortical brain structure segmentation; and (2) white matter hyperintensities segmentation. The experiments showed that the segmentation performance of a pre-trained model could be significantly improved by up to 10%. For the first segmentation problem it was possible to achieve a maximum improvement from 0.680 to 0.799 in average Dice Similarity Coefficient (DSC) metric and for the second problem the average DSC improved from 0.504 to 0.602. Moreover, the improvements after domain adaptation were on par or showed better performance compared to the commonly used traditional unsupervised segmentation methods (FIRST and LST), also achieving faster execution time. Taking this into account, this work presents one more step toward the practical implementation of deep learning algorithms into the clinical routine.

Download Full-text

Autosegmentation of Prostate Zones and Cancer Regions from Biparametric Magnetic Resonance Images by Using Deep-Learning-Based Neural Networks

Sensors ◽

10.3390/s21082709 ◽

2021 ◽

Vol 21 (8) ◽

pp. 2709

Author(s):

Chih-Ching Lai ◽

Hsin-Kai Wang ◽

Fu-Nien Wang ◽

Yu-Ching Peng ◽

Tzu-Ping Lin ◽

...

Keyword(s):

Magnetic Resonance Imaging ◽

Deep Learning ◽

Magnetic Resonance ◽

Peripheral Zone ◽

Magnetic Resonance Images ◽

Dice Similarity Coefficient ◽

Resonance Imaging ◽

Prostate Mri ◽

Diffusion Weighted Images ◽

Apparent Diffusion

The accuracy in diagnosing prostate cancer (PCa) has increased with the development of multiparametric magnetic resonance imaging (mpMRI). Biparametric magnetic resonance imaging (bpMRI) was found to have a diagnostic accuracy comparable to mpMRI in detecting PCa. However, prostate MRI assessment relies on human experts and specialized training with considerable inter-reader variability. Deep learning may be a more robust approach for prostate MRI assessment. Here we present a method for autosegmenting the prostate zone and cancer region by using SegNet, a deep convolution neural network (DCNN) model. We used PROSTATEx dataset to train the model and combined different sequences into three channels of a single image. For each subject, all slices that contained the transition zone (TZ), peripheral zone (PZ), and PCa region were selected. The datasets were produced using different combinations of images, including T2-weighted (T2W) images, diffusion-weighted images (DWI) and apparent diffusion coefficient (ADC) images. Among these groups, the T2W + DWI + ADC images exhibited the best performance with a dice similarity coefficient of 90.45% for the TZ, 70.04% for the PZ, and 52.73% for the PCa region. Image sequence analysis with a DCNN model has the potential to assist PCa diagnosis.

Download Full-text

Application of deep learning in detecting neurological disorders from magnetic resonance images: a survey on the detection of Alzheimer’s disease, Parkinson’s disease and schizophrenia

Brain Informatics ◽

10.1186/s40708-020-00112-2 ◽

2020 ◽

Vol 7 (1) ◽

Cited By ~ 6

Author(s):

Manan Binth Taj Noor ◽

Nusrat Zerin Zenia ◽

M Shamim Kaiser ◽

Shamim Al Mamun ◽

Mufti Mahmud

Keyword(s):

Alzheimer’S Disease ◽

Parkinson’S Disease ◽

Alzheimer's Disease ◽

Parkinson's Disease ◽

Deep Learning ◽

Magnetic Resonance ◽

Neurological Disorders ◽

Magnetic Resonance Images ◽

Future Research ◽

Comparative Performance

Abstract Neuroimaging, in particular magnetic resonance imaging (MRI), has been playing an important role in understanding brain functionalities and its disorders during the last couple of decades. These cutting-edge MRI scans, supported by high-performance computational tools and novel ML techniques, have opened up possibilities to unprecedentedly identify neurological disorders. However, similarities in disease phenotypes make it very difficult to detect such disorders accurately from the acquired neuroimaging data. This article critically examines and compares performances of the existing deep learning (DL)-based methods to detect neurological disorders—focusing on Alzheimer’s disease, Parkinson’s disease and schizophrenia—from MRI data acquired using different modalities including functional and structural MRI. The comparative performance analysis of various DL architectures across different disorders and imaging modalities suggests that the Convolutional Neural Network outperforms other methods in detecting neurological disorders. Towards the end, a number of current research challenges are indicated and some possible future research directions are provided.

Download Full-text