Search

Musculoskeletal (MSK) diseases are widespread, with the World Health Organization estimating in 2019 that 1.71 billion people worldwide are afflicted with the condition [1]. MSK conditions include low back pain, knee osteoarthritis, and rheumatoid arthritis, among others, all of which induce debilitating pain and require early diagnosis to improve prognosis of treatment outcomes. Imaging is a crucial tool for diagnosis, and among available options, Magnetic Resonance Imaging (MRI) is a preferred modality for its sharp soft-tissue contrast, high-resolution images, and lack of ionizing radiation. However, acquisition and processing of MR images has numerous challenges: (1) acquisitions are time-consuming, and therefore expensive and susceptible to motion artifacts; (2) special sequences require toxic contrast agent administration, which have safety concerns; and (3) analysis of acquired images to identify patients most requiring clinical intervention is laborious. This work proposes using deep learning to address various aspects of these challenges. I will be presenting 5 applications and uses of deep learning algorithms:1. To accelerate a 3D fat-suppressed knee MR sequence, showing that optimizing reconstruction algorithms for one tissue of clinical interest can improve its performance in other tissues of clinical interest. 2. For image reconstruction of accelerated compositional MR acquisitions in the knee, hip and lumbar spine, optimizing reconstructed images for tissues of heightened clinical interest (cartilage and intervertebral discs). 3. To automatically segment bone and cartilage from 8X accelerated knee MR acquisitions. 4. To synthesize post-contrast wrist MR images from pre-contrast scans in rheumatoid arthritis patients. 5. To predict if patients would require a total knee replacement within 5 years, using MR imaging and demographic variables.

Malignant melanoma is an aggressive type of skin cancer. Gene mutations can make the disease progress faster, but specialised treatment exists. Today, gene mutations are detected with DNA-analysis which is costly and time-consuming. The aim of our thesis is to investigate whether deep learning can be used to differentiate whole-slide images of tumours with different gene mutations. This was done in two steps, first whole-slide images were segmented based on tissue types, and then classification of gene mutations was done. The tissue segmentation was done using the deep convolutional network Inception v3, modified to a four class output. Image tiles of the size 244 x 244 pixels were used to train and evaluate the network, with F1-score 0.84 on tumour tissue. Two different methods to predict mutation status were tested. First, image features extracted from the segmentation network were fed into binary classifiers to separate images of tumours with and without NRAS mutation. Due to unsatisfactory results, another method was tested. A new Inception v3 network was trained to distinguish between NRAS and BRAF mutated tumours. Data from the public database The Cancer Genome Atlas was used for training and evaluation. Further testing was done on two independent test sets. Only tiles with 90% or higher probability of being tumour according to the segmentation network were used. The classification network was tested tilewise (AUC 0.53-0.66) and patientwise with AUC-values around 0.60 for all datasets. The results indicate that it is possible to separate tissue images based on gene mutations. We believe that deep learning networks like these have great potential of being integrated into diagnostics of malignant melanoma. This could lead to faster and more accessible gene mutation diagnostics around the world., Malignt melanom är en aggressiv form av hudcancer. Genmutationer kan påskynda sjukdomsförloppet och spridningen av tumörer, men specialanpassad behandling finns att tillgå. Idag används DNA-analys för att upptäcka genmutationer, vilket är kostsamt och tidskrävande. Syftet med vårt examensarbete är att undersöka om djupinlärning (deep learning) kan användas för att hitta genmutationer från vävnadsbilder på malignt melanom. Detta har vi gjort i två steg, först genom att hitta tumörrik vävnad i mikroskopbilder, och sedan utföra klassificering av mutationer på dessa regioner. Segmentering av olika vävnadstyper gjordes med hjälp av det djupa neurala nätverket Inception v3. Bildurklipp av storleken 244 x 244 pixlar användes för att träna och testa nätverket med F1-score 0,84 på tumörvävnad. För att utföra klassificering av genmutationer testades två metoder. Först testade vi på att skilja på vävnadsbilder med och utan NRAS-mutationer med hjälp av s.k. features, numeriska värden som hämtats ut från segmenteringsnätverket. Försöket gav inte tillfredsställande resultat och därför tränades istället ett nytt Inception v3-nätverk till att göra klassificering av tumörbilder med NRAS- och BRAF-mutationer. Nätverket tränades på bilder från databasen The Cancer Genome Atlas och testades på ytterligare två separata dataset. Endast urklipp med mer än 90% sannolikhet att vara tumörvävnad enligt segmenteringsnätverket användes. Klassificeringen testades både urklippsvis (AUC 0,53-0,66) och patientvis med AUC-värden runt 0,60 för samtliga dataset. Resultaten visar på att det är möjligt att skilja på bilder på tumörvävnad med olika genmutationer. Vi tror att liknande djupa neurala nätverk har stor potential att integreras i diagnostiken av malignt melanom. Det skulle kunna innebära snabbare och mer tillgänglig diagnostik av genmutationer., Deep Learning - the key to revolutionise specialised skin cancer treatment? Malignant melanoma is an aggressive type of skin cancer that develops from moles. Gene mutations can make the disease progress faster, but if the mutations are detected, it is possible to specialise the treatment. Using deep learning as a complement in diagnostics is state of the art in many medical fields. It is a type of artificial intelligence that can detect patterns that are invisible for the human eye. In our thesis we have shown that it is possible to use deep learning to predict the mutation status of melanoma using microscopy images. With further development, this method could possible replace advanced, expensive and time consuming lab analyses. The technique could contribute to more rapid and accessible diagnostics around the world. Malignant melanoma is increasing at a high pace all over the world. With the exception of lung cancer in women, it is the cancer type that is increasing the most in prevalence. Specialised treatment is an important step of defeating cancer. Gene mutations in malignant melanoma enhance tumour growth which makes the disease progress faster. The two most common mutations are present in 40% and 20% of the cases, respectively. Since specialised treatment exists, detection of these mutations is crucial. Today, this is done with costly and time-consuming DNA analysis. However, recent studies show that deep learning can be used to detect the mutation status from tissue images alone. For a better chance at saving a patient's life, early detection and comprehensive patient investigation play vital roles. It is common to visually inspect cancer tissue in a microscope to mark out the tumour areas. However, this is a tedious task performed manually by a specialist. Deep learning is a subfield of artificial intelligence and it can be used to automatically mark the different tissue types, without the need for human participation. In our thesis, we have trained a deep

Accurate and reliable quantification of brain metabolites measured in vivo using H-1 magnetic resonance spectroscopy (MRS) is a topic of continued interest. Aside from differences in the basic approach to quantification, the quantification of metabolite data acquired at different sites and on different platforms poses an additional methodological challenge. In this study, spectrally edited gamma-aminobutyric acid (GABA) MRS data were analyzed and GABA levels were quantified relative to an internal tissue water reference. Data from 284 volunteers scanned across 25 research sites were collected using GABA+ (GABA + co-edited macromolecules (MM)) and MM-suppressed GABA editing. The unsuppressed water signal from the volume of interest was acquired for concentration referencing. Whole-brain T-1-weighted structural images were acquired and segmented to determine gray matter, white matter and cerebrospinal fluid voxel tissue fractions. Water-referenced GABA measurements were fully corrected for tissue-dependent signal relaxation and water visibility effects. The cohort-wide coefficient of variation was 17% for the GABA + data and 29% for the MM-suppressed GABA data. The mean within-site coefficient of variation was 10% for the GABA + data and 19% for the MM-suppressed GABA data. Vendor differences contributed 53% to the total variance in the GABA + data, while the remaining variance was attributed to site- (11%) and participant-level (36%) effects. For the MM-suppressed data, 54% of the variance was attributed to site differences, while the remaining 46% was attributed to participant differences. Results from an exploratory analysis suggested that the vendor differences were related to the unsuppressed water signal acquisition. Discounting the observed vendor-specific effects, water-referenced GABA measurements exhibit similar levels of variance to creatine-referenced GABA measurements. It is concluded that quantification using internal tissue water referencing is a via

Accurate and reliable quantification of brain metabolites measured in vivo using H-1 magnetic resonance spectroscopy (MRS) is a topic of continued interest. Aside from differences in the basic approach to quantification, the quantification of metabolite data acquired at different sites and on different platforms poses an additional methodological challenge. In this study, spectrally edited gamma-aminobutyric acid (GABA) MRS data were analyzed and GABA levels were quantified relative to an internal tissue water reference. Data from 284 volunteers scanned across 25 research sites were collected using GABA+ (GABA + co-edited macromolecules (MM)) and MM-suppressed GABA editing. The unsuppressed water signal from the volume of interest was acquired for concentration referencing. Whole-brain T-1-weighted structural images were acquired and segmented to determine gray matter, white matter and cerebrospinal fluid voxel tissue fractions. Water-referenced GABA measurements were fully corrected for tissue-dependent signal relaxation and water visibility effects. The cohort-wide coefficient of variation was 17% for the GABA + data and 29% for the MM-suppressed GABA data. The mean within-site coefficient of variation was 10% for the GABA + data and 19% for the MM-suppressed GABA data. Vendor differences contributed 53% to the total variance in the GABA + data, while the remaining variance was attributed to site- (11%) and participant-level (36%) effects. For the MM-suppressed data, 54% of the variance was attributed to site differences, while the remaining 46% was attributed to participant differences. Results from an exploratory analysis suggested that the vendor differences were related to the unsuppressed water signal acquisition. Discounting the observed vendor-specific effects, water-referenced GABA measurements exhibit similar levels of variance to creatine-referenced GABA measurements. It is concluded that quantification using internal tissue water referencing is a via

Objective NT-proBNP (N-terminal pro-B-type natriuretic peptide) and cardiac troponin T (cTNT) are associated with cognitive performance. Whether this extends to individualsApproach and Results In 3011 individuals (608 years; 49% women), NT-proBNP and cTNT, memory, information processing speed and executive functioning, grey matter (GM) and white matter, and white matter hyperintensity (WMH) volumes were determined. We used regression, adjusted for educational level, cardiovascular factors, and lifestyle factors, to test whether cross-sectional associations between biomarkers and cognitive performance and structural brain changes were modified by age (0.10). Higher cTNT was associated with greater WMH (0.18 [95% CI, -0.01 to 0.37]; P-interaction,>0.10) but not with GM (0.07 [95% CI, -6.87 to 7.02]; P-interaction,Conclusions Biomarkers of cardiac injury are continuously associated with structural brain changes in both older and younger individuals but with poorer cognitive performance only in older individuals. These findings stress the continuous nature of the heart-brain axis in the development of cognitive impairment.

OBJECTIVEStructural brain abnormalities are key risk factors for brain diseases, such as dementia, stroke, and depression, in type 2 diabetes. It is unknown whether structural brain abnormalities already occur in prediabetes. Therefore, we investigated whether both prediabetes and type 2 diabetes are associated with lacunar infarcts (LIs), white matter hyperintensities (WMHs), cerebral microbleeds (CMBs), and brain atrophy.RESEARCH DESIGN and METHODSWe used data from 2,228 participants (1,373 with normal glucose metabolism [NGM], 347 with prediabetes, and 508 with type 2 diabetes (oversampled); mean age 59.2 +/- 8.2 years; 48.3% women) of the Maastricht Study, a population-based cohort study. Diabetes status was determined with an oral glucose tolerance test. Brain imaging was performed with 3 Tesla MRI. Results were analyzed with multivariable logistic and linear regression analyses.RESULTSPrediabetes and type 2 diabetes were associated with the presence of LIs (odds ratio 1.61 [95% CI 0.98-2.63] and 1.67 [1.04-2.68], respectively; P-trend = 0.027), larger WMH (beta 0.07 log10-transformed mL [log-mL] [95% CI 0.00-0.15] and 0.21 log-mL [0.14-0.28], respectively; P-trendCONCLUSIONSPrediabetes is associated with structural brain abnormalities, with further deterioration in type 2 diabetes. These results indicate that, in middle-aged populations, structural brain abnormalities already occur in prediabetes, which may suggest that the treatment of early dysglycemia may contribute to the prevention of brain diseases.

OBJECTIVEStructural brain abnormalities are key risk factors for brain diseases, such as dementia, stroke, and depression, in type 2 diabetes. It is unknown whether structural brain abnormalities already occur in prediabetes. Therefore, we investigated whether both prediabetes and type 2 diabetes are associated with lacunar infarcts (LIs), white matter hyperintensities (WMHs), cerebral microbleeds (CMBs), and brain atrophy.RESEARCH DESIGN and METHODSWe used data from 2,228 participants (1,373 with normal glucose metabolism [NGM], 347 with prediabetes, and 508 with type 2 diabetes (oversampled); mean age 59.2 +/- 8.2 years; 48.3% women) of the Maastricht Study, a population-based cohort study. Diabetes status was determined with an oral glucose tolerance test. Brain imaging was performed with 3 Tesla MRI. Results were analyzed with multivariable logistic and linear regression analyses.RESULTSPrediabetes and type 2 diabetes were associated with the presence of LIs (odds ratio 1.61 [95% CI 0.98-2.63] and 1.67 [1.04-2.68], respectively; P-trend = 0.027), larger WMH (beta 0.07 log10-transformed mL [log-mL] [95% CI 0.00-0.15] and 0.21 log-mL [0.14-0.28], respectively; P-trendCONCLUSIONSPrediabetes is associated with structural brain abnormalities, with further deterioration in type 2 diabetes. These results indicate that, in middle-aged populations, structural brain abnormalities already occur in prediabetes, which may suggest that the treatment of early dysglycemia may contribute to the prevention of brain diseases.

Objective NT-proBNP (N-terminal pro-B-type natriuretic peptide) and cardiac troponin T (cTNT) are associated with cognitive performance. Whether this extends to individualsApproach and Results In 3011 individuals (608 years; 49% women), NT-proBNP and cTNT, memory, information processing speed and executive functioning, grey matter (GM) and white matter, and white matter hyperintensity (WMH) volumes were determined. We used regression, adjusted for educational level, cardiovascular factors, and lifestyle factors, to test whether cross-sectional associations between biomarkers and cognitive performance and structural brain changes were modified by age (0.10). Higher cTNT was associated with greater WMH (0.18 [95% CI, -0.01 to 0.37]; P-interaction,>0.10) but not with GM (0.07 [95% CI, -6.87 to 7.02]; P-interaction,Conclusions Biomarkers of cardiac injury are continuously associated with structural brain changes in both older and younger individuals but with poorer cognitive performance only in older individuals. These findings stress the continuous nature of the heart-brain axis in the development of cognitive impairment.

Purpose: To assess image quality and to quantify the accuracy of relative electron densities (rho(e)) and effective atomic numbers (Z(eff)) for three dual-energy computed tomography (DECT) scanners: a novel single-source split-filter (i. e., twin-beam) and two dual-source scanners.Methods: Measurements were made with a second generation dual-source scanner at 80/140Sn kVp, a third-generation twin-beam single-source scanner at 120 kVp with gold (Au) and tin (Sn) filters, and a third-generation dual-source scanner at 90/150Sn kVp. Three phantoms with tissue inserts were scanned and used for calibration and validation of parameterized methods to extract rho(e) and Z(eff), whereas iodine and calcium inserts were used to quantify Contrast-to-Noise-Ratio (CNR). Spatial resolution in tomographic images was also tested.Results: The third-generation scanners have an image resolution of 6.2, similar to 0.5 lp/cm higher than the second generation scanner. The twin-beam scanner has low imaging contrast for iodine materials due to its limited spectral separation. The parameterization methods resulted in calibrations with low fit residuals for the dual-source scanners, yielding values of rho(e) and Z(eff) close to the reference values (errors within 1.2% for rho(e) and 6.2% for Z(eff) for a dose of 20 mGy, excluding lung substitute tissues). The twin-beam scanner presented overall higher errors (within 3.2% for rho(e) and 28% for Z(eff), also excluding lung inserts) and also larger variations for uniform inserts.Conclusions: Spatial resolution is similar for the three scanners. The twin-beam is able to derive qe and Z(eff), but with inferior accuracy compared to both dual-source scanners. (C) 2016 American Association of Physicists in Medicine

Purpose: To assess image quality and to quantify the accuracy of relative electron densities (rho(e)) and effective atomic numbers (Z(eff)) for three dual-energy computed tomography (DECT) scanners: a novel single-source split-filter (i. e., twin-beam) and two dual-source scanners.Methods: Measurements were made with a second generation dual-source scanner at 80/140Sn kVp, a third-generation twin-beam single-source scanner at 120 kVp with gold (Au) and tin (Sn) filters, and a third-generation dual-source scanner at 90/150Sn kVp. Three phantoms with tissue inserts were scanned and used for calibration and validation of parameterized methods to extract rho(e) and Z(eff), whereas iodine and calcium inserts were used to quantify Contrast-to-Noise-Ratio (CNR). Spatial resolution in tomographic images was also tested.Results: The third-generation scanners have an image resolution of 6.2, similar to 0.5 lp/cm higher than the second generation scanner. The twin-beam scanner has low imaging contrast for iodine materials due to its limited spectral separation. The parameterization methods resulted in calibrations with low fit residuals for the dual-source scanners, yielding values of rho(e) and Z(eff) close to the reference values (errors within 1.2% for rho(e) and 6.2% for Z(eff) for a dose of 20 mGy, excluding lung substitute tissues). The twin-beam scanner presented overall higher errors (within 3.2% for rho(e) and 28% for Z(eff), also excluding lung inserts) and also larger variations for uniform inserts.Conclusions: Spatial resolution is similar for the three scanners. The twin-beam is able to derive qe and Z(eff), but with inferior accuracy compared to both dual-source scanners. (C) 2016 American Association of Physicists in Medicine

Ready-to-eat foods that does not receive a heat treatment before being consumed can be at risk of foodborne hazards and spoilage, so it would be of great interest to have a method for monitoring their safety. This work expands on and enhances previous successfully studies with hyperspectral imaging in the SW-NIR range. Specifically, a k-nearest-neighbours model was developed to classify the salmon tissue into white myocommata stripes (fat) and muscle (lean) tissue. Partial Least Squares models developed confirm that a spatial segmentation should be performed before a shelf life model can be calculated. Employing the fat spectra and only the 7 most correlated wavelengths, a support vector machine model was calculated to classify into days 0, 10, 20, 40 and 60 with 87.2% prediction accuracy. These results make the method developed very promising as a non-destructive method to analyse the shelf life of vacuum-packed chilled smoked salmon fillets.

The prognosis for patients with advanced head and neck (H&N) cancer is very poor and treatment is challenging. These patients are standardly treated with radiotherapy with or without chemotherapy. These treatments are associated with a high treatment related late toxicity that affects the quality of life and social contacts in 20% of the patients. Side effects reported in all studies concern loss of swallowing and salivary function leading to difficulties in speaking and eating. Clinical studies have shown that the addition of a local hyperthermia treatment to a (chemo)radiation treatment signifcantly improve the treatment outcome without increasing treatment related late toxicity. Application of hyperthermia in the challenging H&N region using multi antenna-element applicators requires hyperthermia treatment planning (HTP). This thesis focuses on the development of an accurate and efficient patient model generation for patient-specific HTP based on electromagnetic (EM) and temperature modeling. The first two chapters include the automatic generation of 3D patient-models from Computed Tomography (CT) scans (chapter 2) or CT and Magnetic Resonance Imaging (MRI) scans (chapter 3). Chapter 4 and 5 include temperature simulation guided H&N hyperthermia using optimized thermal tissue property values.

Supervised classification is widely used for image segmentation. To work effectively, these techniques need large amounts of labeled training data, that is representative of the test data. Different patient groups, different scanners or different scanning protocols can lead to differences between the images, thus representative data might not be available. Transfer learning techniques can be used to account for these differences, thus taking advantage of all the available data acquired with different protocols. We investigate the use of classifier ensembles, where each classifier is weighted according to the similarity between the data it is trained on, and the data it needs to segment. We examine 3 asymmetric similarity measures that can be used in scenarios where no labeled data from a newly introduced scanner or scanning protocol is available. We show that the asymmetry is informative and the direction of measurement needs to be chosen carefully. We also show that a point set similarity measure is robust across different studies, and outperforms state-of-the-art results on a multi-center brain tissue segmentation task.

This paper describes an automatic tissue segmentation algorithm for brain MRI of children with cerebral palsy (CP) who exhibit severe cortical malformations. Many of the currently popular brain segmentation techniques rely on registered atlas priors and so generalize poorly to severely injured data sets, because of large discrepancies between the target brain and healthy (or injured) atlases. We propose a prior-less approach combined with a modification of the Expectation Maximization (EM)/Markov Random Field (MRF) segmentation by imposing a continuous weighting scheme to penalize intensity discrepancies between pairs of neighbors within each clique neighborhood, to provide robustness to the unique clinical problem of severe anatomical distortion. This approach was applied to gray matter segmentations in 20 3D T1-weighted MRIs, of which 17 were of CP patients exhibiting severe malformation. We compare our adaptive algorithm to the popular 'FreeSurfer', 'NiftySeg', 'FAST' and 'Atropos' segmentations, which collectively are state-of-The-Art surface deformation and EM approaches. The algorithm driven approach yielded improved segmentations (DSC 0.66 v 0.44 (FreeSurfer) v 0.60 (NiftySeg with 100% atlas prior relaxation) v 0.59 (FAST) v 0.64 (Atropos)) of the cerebral cortex relative to several ground-Truth manual segmentations, when compared to the existing approaches.

White matter changes (WMC) are the focus of intensive research and have been linked to cognitive impairment and depression in the elderly. Cumbersome manual outlining procedures make research on WMC labor intensive and prone to subjective bias. We present a fast, fully automated method for WMC segmentation using a cascade of reduced support vector machines (SVMs) with active learning. Data of 102 subjects was used in this study. Two MRI sequences (T1-weighted and FLAIR) and masks of manually outlined WMC from each subject were used for the image analysis. The segmentation framework comprises pre-processing, classification (training and core segmentation) and post-processing. After pre-processing, the model was trained on two subjects and tested on the remaining 100 subjects. The effectiveness and robustness of the classification was assessed using the receiver operating curve technique. The cascade of SVMs segmentation framework outputted accurate results with high sensitivity (90%) and specificity (99.5%) values, with the manually outlined WMC as reference. An algorithm for the segmentation of WMC is proposed. This is a completely competitive and fast automatic segmentation framework, capable of using different input sequences, without changes or restrictions of the image analysis algorithm., QC 20121217

The success of oral surgery is subject to accurate advanced planning. In order to properly plan for dental surgery or a suitable implant placement, it is necessary an accurate segmentation of the jaw tissues: the teeth, the cortical bone, the trabecular core and over all, the inferior alveolar nerve. This manuscript presents a new automatic method that is based on fuzzy connectedness object extraction and mathematical morphology processing. The method uses computed tomography data to extract different views of the jaw: a pseudo-orthopantomographic view to estimate the path of the nerve and cross-sectional views to segment the jaw tissues. The method has been tested in a groundtruth set consisting of more than 9000 cross-sections from 20 different patients and has been evaluated using four similarity indicators (the Jaccard index, Dice's coefficient, point-to-point and point-to-curve distances), achieving promising results in all of them (0.726 ± 0.031, 0.840 ± 0.019, 0.144 ± 0.023 mm and 0.163 ± 0.025 mm, respectively). The method has proven to be significantly automated and accurate, with errors around 5% (of the diameter of the nerve), and is easily integrable in current dental planning systems. © 2012 Elsevier Ireland Ltd.

The waiting period of subplate evolution is a critical phase for the proper formation of neural connections in the brain. During this time, which corresponds to 15 to 24 postconceptual weeks (PCW) in the human fetus, thalamocortical and cortico-cortical afferents wait in and are in part guided by molecules embedded in the extracellular matrix of the subplate. Recent advances in fetal MRI techniques now allow us to study the developing brain anatomy in 3D from in utero imaging. We describe a reliable segmentation protocol to delineate the boundaries of the subplate from T2-W MRI. The reliability of the protocol was evaluated in terms of intra-rater reproducibility on a subset of the subjects. We also present the first 3D quantitative analyses of temporal changes in subplate volume, thickness, and contrast from 18 to 24 PCW. Our analysis shows that firstly, global subplate volume increases in proportion with the supratentorial volume; the subplate remained approximately one-third of supratentorial volume. Secondly, we found both global and regional growth in subplate thickness and a linear increase in the median and maximum subplate thickness through the waiting period. Furthermore, we found that posterior regions--specifically the occipital pole, ventral occipito-temporal region, and planum temporale--of the developing brain underwent the most statistically significant increases in subplate thickness. During this period, the thickest region was the developing somatosensory/motor cortex. The subplate growth patterns reported here may be used as a baseline for comparison to abnormal fetal brain development.

The waiting period of subplate evolution is a critical phase for the proper formation of neural connections in the brain. During this time, which corresponds to 15 to 24 postconceptual weeks (PCW) in the human fetus, thalamocortical and cortico-cortical afferents wait in and are in part guided by molecules embedded in the extracellular matrix of the subplate. Recent advances in fetal MRI techniques now allow us to study the developing brain anatomy in 3D from in utero imaging. We describe a reliable segmentation protocol to delineate the boundaries of the subplate from T2-W MRI. The reliability of the protocol was evaluated in terms of intra-rater reproducibility on a subset of the subjects. We also present the first 3D quantitative analyses of temporal changes in subplate volume, thickness, and contrast from 18 to 24 PCW. Our analysis shows that firstly, global subplate volume increases in proportion with the supratentorial volume; the subplate remained approximately one-third of supratentorial volume. Secondly, we found both global and regional growth in subplate thickness and a linear increase in the median and maximum subplate thickness through the waiting period. Furthermore, we found that posterior regions—specifically the occipital pole, ventral occipito-temporal region, and planum temporale—of the developing brain underwent the most statistically significant increases in subplate thickness. During this period, the thickest region was the developing somatosensory/motor cortex. The subplate growth patterns reported here may be used as a baseline for comparison to abnormal fetal brain development.

The waiting period of subplate evolution is a critical phase for the proper formation of neural connections in the brain. During this time, which corresponds to 15 to 24 postconceptual weeks (PCW) in the human fetus, thalamocortical and cortico-cortical afferents wait in and are in part guided by molecules embedded in the extracellular matrix of the subplate. Recent advances in fetal MRI techniques now allow us to study the developing brain anatomy in 3D from in utero imaging. We describe a reliable segmentation protocol to delineate the boundaries of the subplate from T2-W MRI. The reliability of the protocol was evaluated in terms of intra-rater reproducibility on a subset of the subjects. We also present the first 3D quantitative analyses of temporal changes in subplate volume, thickness, and contrast from 18 to 24 PCW. Our analysis shows that firstly, global subplate volume increases in proportion with the supratentorial volume; the subplate remained approximately one-third of supratentorial volume. Secondly, we found both global and regional growth in subplate thickness and a linear increase in the median and maximum subplate thickness through the waiting period. Furthermore, we found that posterior regions—specifically the occipital pole, ventral occipito-temporal region, and planum temporale—of the developing brain underwent the most statistically significant increases in subplate thickness. During this period, the thickest region was the developing somatosensory/motor cortex. The subplate growth patterns reported here may be used as a baseline for comparison to abnormal fetal brain development.

The waiting period of subplate evolution is a critical phase for the proper formation of neural connections in the brain. During this time, which corresponds to 15 to 24 postconceptual weeks (PCW) in the human fetus, thalamocortical and cortico-cortical afferents wait in and are in part guided by molecules embedded in the extracellular matrix of the subplate. Recent advances in fetal MRI techniques now allow us to study the developing brain anatomy in 3D from in utero imaging. We describe a reliable segmentation protocol to delineate the boundaries of the subplate from T2-W MRI. The reliability of the protocol was evaluated in terms of intra-rater reproducibility on a subset of the subjects. We also present the first 3D quantitative analyses of temporal changes in subplate volume, thickness, and contrast from 18 to 24 PCW. Our analysis shows that firstly, global subplate volume increases in proportion with the supratentorial volume; the subplate remained approximately one-third of supratentorial volume. Secondly, we found both global and regional growth in subplate thickness and a linear increase in the median and maximum subplate thickness through the waiting period. Furthermore, we found that posterior regions--specifically the occipital pole, ventral occipito-temporal region, and planum temporale--of the developing brain underwent the most statistically significant increases in subplate thickness. During this period, the thickest region was the developing somatosensory/motor cortex. The subplate growth patterns reported here may be used as a baseline for comparison to abnormal fetal brain development.