| 51. |
- Bajic, Dragan, et al.
(författare)
-
Asymmetric Development of the Hippocampal Region Is Common : A Fetal MR Imaging Study
- 2012
-
Ingår i: American Journal of Neuroradiology. - 0195-6108 .- 1936-959X. ; 33:3, s. 513-518
-
Tidskriftsartikel (refereegranskat)abstract
- BACKGROUND AND PURPOSE: Hippocampal development is poorly understood. This study evaluated the normal development of the hippocampal region during the fetal period by using MR imaging. MATERIALS AND METHODS: MR images of 63 fetuses without intracranial pathology were reviewed independently by 2 radiologists with no knowledge of the fetal GA. Three MR images were performed postmortem and 60 in vivo. The progress of hippocampal inversion was analyzed in coronal sections, and the left and right sides of the hippocampal region were compared in every case. RESULTS: The fetuses in the postmortem examinations were at GWs 17-18 and in the in vivo examinations, at GWs 19-36. The hippocampal sulcus was open, bi- or unilaterally, in 39 fetuses. The oldest was at GW 32. The sulcus was closed at GW 21 at the earliest, unilaterally. In 26/63 fetuses (41%), the deepening or closure of the hippocampal sulcus or hippocampal inversion was asymmetric; in 23 fetuses, the right side developed faster. A shallow collateral sulcus was found earliest at GW 17. A deep collateral sulcus was visible earliest at GW 26 unilaterally, but in all fetuses from GW 31 onward, it was seen bilaterally. The orientation of the collateral sulcus was not related to the GA. CONCLUSIONS: There are wide individual temporal variations in the development and the inversion process of the hippocampal sulcus as well as in the formation of the collateral sulcus. Asymmetric development is common, and in most of the asymmetric cases, the right hippocampus develops faster.
|
|
| 52. |
- Bajic, Dragan, et al.
(författare)
-
Development of the hippocampal region demonstrated on fetal MRI : A preliminary report
- 2011
-
Ingår i: NRJ Digital. - 2239-7493. ; 1:12, s. 555-557
-
Tidskriftsartikel (refereegranskat)abstract
- Coronal slices of three fetal MRIs performed post mortem and 37 performed in utero, all without intracranial pathology, was assessed. Progress of the hippocampal inversion was analyzed, the left and right sides were compared and occurrence of the collateral sulcus was revealed. The fetuses in the post mortem examinations were at gestation weeks (GW) 17-18 and in the in utero examinations at GW 19-35. The symmetric development of the hippocampal sulcus was revealed in 26 subjects and asymmetric in 14. The non-ovoid hippocampal formation could be evaluated at GW 24 at earliest and an ovoid hippocampus at GW 29. The collateral sulcus could be recognized at GW 17 in post mortem and at GW 22 in in utero examinations. From GW 29 onwards it was seen in all fetuses and it was symmetric in all but one case. Evaluation of the hippocampi is difficult on fetal MRI, especially in in utero examinations. The hippocampal development is not fulfilled at GW 21 as presumed. There is a wide temporal variation in the development of the hippocampal region, and the developmental process does not progress simultaneously in the right and left side of the same individual.
|
|
| 53. |
|
|
| 54. |
- Banerjee, Subhashis, et al.
(författare)
-
Deep Curriculum Learning for Follow-up MRI Registration in Glioblastoma
- 2023
-
Ingår i: Medical Imaging 2023. - : SPIE -Society of Photo-Optical Instrumentation Engineers. - 9781510660335 - 9781510660342
-
Konferensbidrag (refereegranskat)abstract
- This paper presents a weakly supervised deep convolutional neural network-based approach to perform voxel-level3D registration between subsequent follow-up MRI scans of the same patient. To handle the large deformation inthe surrounding brain tissues due to the tumor’s mass effect we proposed curriculum learning-based training forthe network. Weak supervision helps the network to concentrate more focus on the tumor region and resectioncavity through a saliency detection network. Qualitative and quantitative experimental results show the proposedregistration network outperformed two popular state-of-the-art methods.
|
|
| 55. |
- Banerjee, Subhashis, et al.
(författare)
-
Segmentation of Intracranial Aneurysm Remnant in MRA using Dual-Attention Atrous Net
- 2021
-
Ingår i: 25th International Conference on Pattern Recognition (ICPR). - 9781728188089 ; , s. 9265-9272
-
Konferensbidrag (refereegranskat)abstract
- Due to the advancement of non-invasive medical imaging modalities like Magnetic Resonance Angiography (MRA), an increasing number of Intracranial Aneurysm (IA) cases are being reported in recent years. The IAs are typically treated by so-called endovascular coiling, where blood flow in the IA is prevented by embolization with a platinum coil. Accurate quantification of the IA Remnant (IAR), i.e. the volume with blood flow present post treatment is the utmost important factor in choosing the right treatment planning. This is typically done by manually segmenting the aneurysm remnant from the MRA volume. Since manual segmentation of volumetric images is a labour-intensive and error-prone process, development of an automatic volumetric segmentation method is required. Segmentation of small structures such as IA, that may largely vary in size, shape, and location is considered extremely difficult. Similar intensity distribution of IAs and surrounding blood vessels makes it more challenging and susceptible to false positive. In this paper we propose a novel 3D CNN architecture called Dual-Attention Atrous Net (DAtt-ANet), which can efficiently segment IAR volumes from MRA images by reconciling features at different scales using the proposed Parallel Atrous Unit (PAU) along with the use of self-attention mechanism for extracting fine-grained features and intra-class correlation. The proposed DAtt-ANet model is trained and evaluated on a clinical MRA image dataset of IAR consisting of 46 subjects. We compared the proposed DAtt-ANet with five state-of-the-art CNN models based on their segmentation performance. The proposed DAtt-ANet outperformed all other methods and was able to achieve a five-fold cross-validation DICE score of 0.73 +/- 0.06.
|
|
| 56. |
- Banerjee, Subhashis, et al.
(författare)
-
Streamlining neuroradiology workflow with AI for improved cerebrovascular structure monitoring
- 2024
-
Ingår i: Scientific Reports. - : Nature Publishing Group. - 2045-2322. ; 14:1
-
Tidskriftsartikel (refereegranskat)abstract
- Radiological imaging to examine intracranial blood vessels is critical for preoperative planning and postoperative follow-up. Automated segmentation of cerebrovascular anatomy from Time-Of-Flight Magnetic Resonance Angiography (TOF-MRA) can provide radiologists with a more detailed and precise view of these vessels. This paper introduces a domain generalized artificial intelligence (AI) solution for volumetric monitoring of cerebrovascular structures from multi-center MRAs. Our approach utilizes a multi-task deep convolutional neural network (CNN) with a topology-aware loss function to learn voxel-wise segmentation of the cerebrovascular tree. We use Decorrelation Loss to achieve domain regularization for the encoder network and auxiliary tasks to provide additional regularization and enable the encoder to learn higher-level intermediate representations for improved performance. We compare our method to six state-of-the-art 3D vessel segmentation methods using retrospective TOF-MRA datasets from multiple private and public data sources scanned at six hospitals, with and without vascular pathologies. The proposed model achieved the best scores in all the qualitative performance measures. Furthermore, we have developed an AI-assisted Graphical User Interface (GUI) based on our research to assist radiologists in their daily work and establish a more efficient work process that saves time.
|
|
| 57. |
- Banerjee, Subhashis, et al.
(författare)
-
Topology-Aware Learning for Volumetric Cerebrovascular Segmentation
- 2022
-
Ingår i: 2022 IEEE International Symposium on Biomedical Imaging (IEEE ISBI 2022). - : IEEE. - 9781665429238 ; , s. 1-4
-
Konferensbidrag (refereegranskat)abstract
- This paper presents a topology-aware learning strategy for volumetric segmentation of intracranial cerebrovascular structures. We propose a multi-task deep CNN along with a topology-aware loss function for this purpose. Along with the main task (i.e. segmentation), we train the model to learn two related auxiliary tasks viz. learning the distance transform for the voxels on the surface of the vascular tree and learning the vessel centerline. This provides additional regularization and allows the encoder to learn higher-level intermediate representations to boost the performance of the main task. We compare the proposed method with six state-of-the-art deep learning-based 3D vessel segmentation methods, by using a public Time-Of-Flight Magnetic Resonance Angiography (TOF-MRA) dataset. Experimental results demonstrate that the proposed method has the best performance in this particular context.
|
|
| 58. |
- Bannbers, Elin, et al.
(författare)
-
Lower levels of prepulse inhibition in luteal phase cycling women in comparison with postmenopausal women
- 2010
-
Ingår i: Psychoneuroendocrinology. - : Elsevier BV. - 0306-4530 .- 1873-3360. ; 35:3, s. 422-429
-
Tidskriftsartikel (refereegranskat)abstract
- Menopause denotes the end of the reproductive period in a woman's life and is characterized by gradually declining plasma levels of ovarian hormones. Mounting evidence suggests that prepulse inhibition (PPI) is sensitive to fluctuations in estradiol and progesterone. Deficits in PPI are associated with conditions characterized by increased levels of ovarian steroids, such as the mid-luteal phase of the menstrual cycle and the third trimester of pregnancy. The aim of the current study was to further elucidate ovarian steroid-related effects on PPI by examining 43 women with regular menstrual cycles, 20 healthy postmenopausal women without hormone replacement treatment (HRT) and 21 healthy postmenopausal women with ongoing estradiol-only or estradiol and progesterone therapy (EPT). Cycling women were tested during the late luteal phase of the menstrual cycle while postmenopausal women were tested on any arbitrary day. The PPI was measured by electromyography. Cycling women exhibited lower levels of PPI than postmenopausal women (p<0.05). There were no differences in PPI between postmenopausal HRT users and non-users. However, postmenopausal women with estradiol serum concentrations in the cycling range had lower PPI than postmenopausal women with low estradiol concentrations (groupxPPI interaction, p<0.05). In conclusion, the results further suggest a role for the ovarian steroids in PPI regulation as PPI is increased in postmenopausal women in comparison to regularly menstruating women examined during the late luteal phase. Furthermore, postmenopausal women with estradiol levels in the cycling range had lower PPI than postmenopausal women with low estradiol levels.
|
|
| 59. |
- Bannbers, Elin, et al.
(författare)
-
Patients with premenstrual dysphoric disorder have increased startle modulation during anticipation in the late luteal phase period in comparison to control subjects
- 2011
-
Ingår i: Psychoneuroendocrinology. - : Elsevier BV. - 0306-4530 .- 1873-3360. ; 36:8, s. 1184-1192
-
Tidskriftsartikel (refereegranskat)abstract
- The acoustic startle response (ASR) is a withdrawal reflex to sudden or noxious auditory stimuli and, most importantly, an unbiased measure of emotional processing of appetitive and aversive stimuli. By exposing subjects to fearful situations, such as aversive pictures, the ASR may be enhanced, suggesting that amygdala modulates the startle circuit during threat situations. As one previous study, investigating affective modulation of the ASR in women with premenstrual dysphoric disorder (PMDD), discovered no difference during picture viewing it is possible that the mood changes observed in PMDD relate to anxious anticipation rather than to direct stimulus responding. Hence we sought to examine the effects of PMDD on picture anticipation and picture response. Sixteen PMDD patients and 16 controls watched slide shows containing pleasant and unpleasant pictures and positive and negative anticipation stimuli during the follicular and luteal phase of the menstrual cycle. Simultaneously, semi-randomized startle probes (105dB) were delivered and the ASR was assessed with electromyography. Compared with control subjects, PMDD patients displayed an enhanced startle modulation by positive and negative anticipation stimuli in the luteal phase of the menstrual cycle. This finding was mainly driven by increased modulation in the luteal phase in comparison to the follicular phase among PMDD patients but also by an increased modulation in patients compared to controls during luteal phase. This suggests that the neural circuits underlying response to emotional anticipation are more sensitive during this period and emphasize the need of examining the neural correlates of anticipatory processes in women with PMDD.
|
|
| 60. |
|
|
