Tissue Classification Algorithm Research Articles

Automatic and real-time tissue sensing for autonomous intestinal anastomosis using hybrid MLP-DC-CNN classifier-based optical coherence tomography.

Anastomosis is a common and critical part of reconstructive procedures within gastrointestinal, urologic, and gynecologic surgery. The use of autonomous surgical robots such as the smart tissue autonomous robot (STAR) system demonstrates an improved efficiency and consistency of the laparoscopic small bowel anastomosis over the current da Vinci surgical system. However, the STAR workflow requires auxiliary manual monitoring during the suturing procedure to avoid missed or wrong stitches. To eliminate this monitoring task from the operators, we integrated an optical coherence tomography (OCT) fiber sensor with the suture tool and developed an automatic tissue classification algorithm for detecting missed or wrong stitches in real time. The classification results were updated and sent to the control loop of STAR robot in real time. The suture tool was guided to approach the object by a dual-camera system. If the tissue inside the tool jaw was inconsistent with the desired suture pattern, a warning message would be generated. The proposed hybrid multilayer perceptron dual-channel convolutional neural network (MLP-DC-CNN) classification platform can automatically classify eight different abdominal tissue types that require different suture strategies for anastomosis. In MLP, numerous handcrafted features (∼1955) were utilized including optical properties and morphological features of one-dimensional (1D) OCT A-line signals. In DC-CNN, intensity-based features and depth-resolved tissues' attenuation coefficients were fully exploited. A decision fusion technique was applied to leverage the information collected from both classifiers to further increase the accuracy. The algorithm was evaluated on 69,773 testing A-line data. The results showed that our model can classify the 1D OCT signals of small bowels in real time with an accuracy of 90.06%, a precision of 88.34%, and a sensitivity of 87.29%, respectively. The refresh rate of the displayed A-line signals was set as 300 Hz, the maximum sensing depth of the fiber was 3.6 mm, and the running time of the image processing algorithm was ∼1.56 s for 1,024 A-lines. The proposed fully automated tissue sensing model outperformed the single classifier of CNN, MLP, or SVM with optimized architectures, showing the complementarity of different feature sets and network architectures in classifying intestinal OCT A-line signals. It can potentially reduce the manual involvement of robotic laparoscopic surgery, which is a crucial step towards a fully autonomous STAR system.

Impact of Pre- and Post-Processing Steps for Supervised Classification of Colorectal Cancer in Hyperspectral Images.

Recent studies have shown that hyperspectral imaging (HSI) combined with neural networks can detect colorectal cancer. Usually, different pre-processing techniques (e.g., wavelength selection and scaling, smoothing, denoising) are analyzed in detail to achieve a well-trained network. The impact of post-processing was studied less. We tested the following methods: (1) Two pre-processing techniques (Standardization and Normalization), with (2) Two 3D-CNN models: Inception-based and RemoteSensing (RS)-based, with (3) Two post-processing algorithms based on median filter: one applies a median filter to a raw predictions map, the other applies the filter to the predictions map after adopting a discrimination threshold. These approaches were evaluated on a dataset that contains ex vivo hyperspectral (HS) colorectal cancer records of 56 patients. (1) Inception-based models perform better than RS-based, with the best results being 92% sensitivity and 94% specificity; (2) Inception-based models perform better with Normalization, RS-based with Standardization; (3) Our outcomes show that the post-processing step improves sensitivity and specificity by 6.6% in total. It was also found that both post-processing algorithms have the same effect, and this behavior was explained. HSI combined with tissue classification algorithms is a promising diagnostic approach whose performance can be additionally improved by the application of the right combination of pre- and post-processing.

Clinical validation of computer vision and artificial intelligence algorithms for wound measurement and tissue classification in wound care

One of the most important challenges in the management and treatment of complex wounds is the observation and measurement of different indicators that can be observed on the wound over time. This article will present the idea of addressing this challenge with the use of images captured on a mobile device. The aim of this work is to evaluate the use of digitization systems in the field of chronic wound management as tools that support the professional in improving patient care and decision making, as well as to use computer vision and artificial intelligence to improve wound assessment. An approach based on visual recognition and a classification system is proposed; visual recognition using superpixel techniques to determine the region of interest of the wound, as well as calculating its area and a classification system based on convolutional networks to classify its tissues. We found that our proposed approach, Visual Computing methods to detect Wound contour and measurement (with a Median Relative Error of 2.907 and inter-rater reliability of 0.98%) and Tissue Classification CNN with excellent results using Resnet50 with 0.85 of accuracy.

Harmonization of Rapid Evaporative Ionization Mass Spectrometry Workflows across Four Sites and Testing Using Reference Material and Local Food-Grade Meats.

Rapid evaporative ionization mass spectrometry (REIMS) is a direct tissue metabolic profiling technique used to accurately classify tissues using pre-built mass spectral databases. The reproducibility of the analytical equipment, methodology and tissue classification algorithms has yet to be evaluated over multiple sites, which is an essential step for developing this technique for future clinical applications. In this study, we harmonized REIMS methodology using single-source reference material across four sites with identical equipment: Imperial College London (UK); Waters Research Centre (Hungary); Maastricht University (The Netherlands); and Queen's University (Canada). We observed that method harmonization resulted in reduced spectral variability across sites. Each site then analyzed four different types of locally-sourced food-grade animal tissue. Tissue recognition models were created at each site using multivariate statistical analysis based on the different metabolic profiles observed in the m/z range of 600-1000, and these models were tested against data obtained at the other sites. Cross-validation by site resulted in 100% correct classification of two reference tissues and 69-100% correct classification for food-grade meat samples. While we were able to successfully minimize between-site variability in REIMS signals, differences in animal tissue from local sources led to significant variability in the accuracy of an individual site's model. Our results inform future multi-site REIMS studies applied to clinical samples and emphasize the importance of carefully-annotated samples that encompass sufficient population diversity.

Comparison of preprocessing techniques to reduce nontissue-related variations in hyperspectral reflectance imaging.

.SignificanceHyperspectral reflectance imaging can be used in medicine to identify tissue types, such as tumor tissue. Tissue classification algorithms are developed based on, e.g., machine learning or principle component analysis. For the development of these algorithms, data are generally preprocessed to remove variability in data not related to the tissue itself since this will improve the performance of the classification algorithm. In hyperspectral imaging, the measured spectra are also influenced by reflections from the surface (glare) and height variations within and between tissue samples.AimTo compare the ability of different preprocessing algorithms to decrease variations in spectra induced by glare and height differences while maintaining contrast based on differences in optical properties between tissue types.ApproachWe compare eight preprocessing algorithms commonly used in medical hyperspectral imaging: standard normal variate, multiplicative scatter correction, min–max normalization, mean centering, area under the curve normalization, single wavelength normalization, first derivative, and second derivative. We investigate conservation of contrast stemming from differences in: blood volume fraction, presence of different absorbers, scatter amplitude, and scatter slope—while correcting for glare and height variations. We use a similarity metric, the overlap coefficient, to quantify contrast between spectra. We also investigate the algorithms for clinical datasets from the colon and breast.ConclusionsPreprocessing reduces the overlap due to glare and distance variations. In general, the algorithms standard normal variate, min–max, area under the curve, and single wavelength normalization are the most suitable to preprocess data used to develop a classification algorithm for tissue classification. The type of contrast between tissue types determines which of these four algorithms is most suitable.

Multispectral Image under Tissue Classification Algorithm in Screening of Cervical Cancer.

The objectives of this study were to improve the efficiency and accuracy of early clinical diagnosis of cervical cancer and to explore the application of tissue classification algorithm combined with multispectral imaging in screening of cervical cancer. 50 patients with suspected cervical cancer were selected. Firstly, the multispectral imaging technology was used to collect the multispectral images of the cervical tissues of 50 patients under the conventional white light waveband, the narrowband green light waveband, and the narrowband blue light waveband. Secondly, the collected multispectral images were fused, and then the tissue classification algorithm was used to segment the diseased area according to the difference between the cervical tissues without lesions and the cervical tissues with lesions. The difference in the contrast and other characteristics of the multiband spectrum fusion image would segment the diseased area, which was compared with the results of the disease examination. The average gradient, standard deviation (SD), and image entropy were adopted to evaluate the image quality, and the sensitivity and specificity were selected to evaluate the clinical application value of discussed method. The fused spectral image was compared with the image without lesions, it was found that there was a clear difference, and the fused multispectral image showed a contrast of 0.7549, which was also higher than that before fusion (0.4716), showing statistical difference (P < 0.05). The average gradient, SD, and image entropy of the multispectral image assisted by the tissue classification algorithm were 2.0765, 65.2579, and 4.974, respectively, showing statistical difference (P < 0.05). Compared with the three reported indicators, the values of the algorithm in this study were higher. The sensitivity and specificity of the multispectral image with the tissue classification algorithm were 85.3% and 70.8%, respectively, which were both greater than those of the image without the algorithm. It showed that the multispectral image assisted by tissue classification algorithm can effectively screen the cervical cancer and can quickly, efficiently, and safely segment the cervical tissue from the lesion area and the nonlesion area. The segmentation result was the same as that of the doctor's disease examination, indicating that it showed high clinical application value. This provided an effective reference for the clinical application of multispectral imaging technology assisted by tissue classification algorithm in the early screening and diagnosis of cervical cancer.

Feasibility of Ex Vivo Margin Assessment with Hyperspectral Imaging during Breast-Conserving Surgery: From Imaging Tissue Slices to Imaging Lumpectomy Specimen

Developing algorithms for analyzing hyperspectral images as an intraoperative tool for margin assessment during breast-conserving surgery requires a dataset with reliable histopathologic labels. The feasibility of using tissue slices hyperspectral dataset with a high correlation with histopathology for developing an algorithm for analyzing the images from the surface of lumpectomy specimens was investigated. We presented a method to acquire hyperspectral images from the lumpectomy surface with a high correlation with histopathology. The tissue slices dataset was compared with the dataset obtained on lumpectomy specimen and the wavelengths with a penetration depth up to the minimum sample thickness of the tissue slices were used to develop a tissue classification algorithm. Spectral differences were observed between tissue slices and lumpectomy datasets due to differences in the sample thickness between both datasets; wavelengths with a high penetration depth were able to penetrate through the thinner tissue slices, affecting the captured signal. By using only wavelengths with a penetration depth up to the minimum sample thickness of the tissue slices, the adipose tissue could be discriminated from other tissue types, but differentiating malignant from connective tissue was more challenging.

Applying machine learning to optical coherence tomography images for automated tissue classification in brain metastases

PurposeA precise resection of the entire tumor tissue during surgery for brain metastases is essential to reduce local recurrence. Conventional intraoperative imaging techniques all have limitations in detecting tumor remnants. Therefore, there is a need for innovative new imaging methods such as optical coherence tomography (OCT). The purpose of this study is to discriminate brain metastases from healthy brain tissue in an ex vivo setting by applying texture analysis and machine learning algorithms for tissue classification to OCT images.MethodsTumor and healthy tissue samples were collected during resection of brain metastases. Samples were imaged using OCT. Texture features were extracted from B-scans. Then, a machine learning algorithm using principal component analysis (PCA) and support vector machines (SVM) was applied to the OCT scans for classification. As a gold standard, an experienced pathologist examined the tissue samples histologically and determined the percentage of vital tumor, necrosis and healthy tissue of each sample. A total of 14.336 B-scans from 14 tissue samples were included in the classification analysis.ResultsWe were able to discriminate vital tumor from healthy brain tissue with an accuracy of 95.75%. By comparing necrotic tissue and healthy tissue, a classification accuracy of 99.10% was obtained. A generalized classification between brain metastases (vital tumor and necrosis) and healthy tissue was achieved with an accuracy of 96.83%.ConclusionsAn automated classification of brain metastases and healthy brain tissue is feasible using OCT imaging, extracted texture features and machine learning with PCA and SVM. The established approach can prospectively provide the surgeon with additional information about the tissue, thus optimizing the extent of tumor resection and minimizing the risk of local recurrences.

Classification of colorectal tissue images from high throughput tissue microarrays by ensemble deep learning methods

Tissue microarray (TMA) core images are a treasure trove for artificial intelligence applications. However, a common problem of TMAs is multiple sectioning, which can change the content of the intended tissue core and requires re-labelling. Here, we investigate different ensemble methods for colorectal tissue classification using high-throughput TMAs. Hematoxylin and Eosin (H&E) core images of 0.6 mm or 1.0 mm diameter from three international cohorts were extracted from 54 digital slides (n = 15,150 cores). After TMA core extraction and color enhancement, five different flows of independent and ensemble deep learning were applied. Training and testing data with 2144 and 13,006 cores included three classes: tumor, normal or “other” tissue. Ground-truth data were collected from 30 ngTMA slides (n = 8689 cores). A test augmentation is applied to reduce the uncertain prediction. Predictive accuracy of the best method, namely Soft Voting Ensemble of one VGG and one CapsNet models was 0.982, 0.947 and 0.939 for normal, “other” and tumor, which outperformed to independent or ensemble learning with one base-estimator. Our high-accuracy algorithm for colorectal tissue classification in high-throughput TMAs is amenable to images from different institutions, core sizes and stain intensity. It helps to reduce error in TMA core evaluations with previously given labels.

Reliability assessment of tissue classification algorithms for multi‐center and multi‐scanner data

AbstractBackgroundGray and white matter volumes are important imaging markers of pathology and disease progression. Such measures are usually estimated from tissue segmentation maps produced by image processing pipelines. However, the reliability of the produced segmentations when using multi‐center and multi‐scanner data remains understudied. Here, we assess the robustness of six publicly available tissue classification pipelines across images acquired from different scanners models and sites.MethodData included 90 T1‐weighted images of a single individual, scanned in 73 sessions across 27 sites (Duchesne et al., 2019). An average T1‐weighted image template was created out of all scans (Fonov et al., 2009). For each algorithm, their respective segmentation masks on this template was used as a silver standard (Figure 1). Dice Kappa similarity scores between these silver standards and individual segmentations and variability in tissue volumes across segmentations were assessed for Atropos (Avants et al., 2011); BISON (Dadar and Collins, 2019); Classify_Clean (Cocosco et al., 2003); FAST5.0 (Zhang et al., 2001); FreeSurfer6.0.0 (Fischl, 2012); and SPM12 (Penny et al., 2011). We also estimated the sample size necessary to detect a significant 1% volume reduction based on the variability of the estimates from each method within and across scanner models (80% power, 2‐tailed significance).ResultAcross tissue types, BISON had the lowest overall variability in Dice Kappa, followed by SPM12 (Figure 2). For GM, BISON had the highest overall Dice Kappa (0.94±0.01), followed by SPM12 (0.93±0.01) and Atropos (0.92±0.03); while Atropos had the highest overall Dice Kappa for WM (0.94±0.02), followed by BISON (0.93±0.01) and SPM12 (0.93±0.01). BISON had the lowest overall variability in its volumetric estimates (GM:57.60±0.4, WM:34.49±0.4, CSF:7.90±0.3), followed by FreeSurfer (GM: 49.80±0.7, WM: 39.52±0.8, CSF: 10.71±1.2), and SPM12 (GM:57.76±1.3, WM:33.08±1.1, CSF:9.12±0.9, Figure 3). BISON also had the smallest sample size requirement across all scanners and tissue types, followed by FreeSurfer, and SPM12 (Table 1). As expected, the necessary sample sizes decreased when using data from a specific scanner.ConclusionOur comparisons provide a benchmark on the reliability of currently used tissue classification techniques and the amount of variability that can be expected when using large multi‐center and multi‐scanner databases.

Reliability assessment of tissue classification algorithms for multi-center and multi-scanner data

BackgroundGray and white matter volume difference and change are important imaging markers of pathology and disease progression in neurology and psychiatry. Such measures are usually estimated from tissue segmentation maps produced by publicly available image processing pipelines. However, the reliability of the produced segmentations when using multi-center and multi-scanner data remains understudied. Here, we assess the robustness of six publicly available tissue classification pipelines across images acquired from different MR scanners and sites. MethodsWe used 90 T1-weighted images of a single individual, scanned in 73 sessions across 27 different sites to assess the robustness of the tissue classification tools. Variability in Dice similarity index values and tissue volumes was assessed for Atropos, BISON, Classify_Clean, FAST, FreeSurfer, and SPM12. ResultsBISON had the highest overall Dice coefficient for GM, followed by SPM12 and Atropos; while Atropos had the highest overall Dice coefficient for WM, followed by BISON and SPM12. BISON had the lowest overall variability in its volumetric estimates, followed by FreeSurfer, and SPM12. All methods also had significant differences between some of their estimates across different scanner manufacturers (e.g. BISON had significantly higher GM estimates and correspondingly lower WM estimates for GE scans compared to Philips and Siemens), and different signal-to-noise ratio (SNR) levels (e.g. FAST and FreeSurfer had significantly higher WM volume estimates for high versus medium and low SNR tertiles as well as correspondingly lower GM volume estimates). ConclusionsOur comparisons provide a benchmark on the reliability of the publicly used tissue classification techniques and the amount of variability that can be expected when using large multi-center and multi-scanner databases.

Single fiber OCT imager for breast tissue classification based on deep learning.

We investigated a deep learning strategy to analyze optical coherence tomography image for accurate tissue characterization based on a single fiber OCT probe. We obtained OCT data from human breast tissue specimens. Using OCT data obtained from adipose breast tissue (normal tissue) and diseased tissue as confirmed in histology, we trained and validated a convolutional neural network (CNN) for accurate breast tissue classification. We demonstrated tumor margin identification based CNN classification of tissue at different spatial locations. We further demonstrated CNN tissue classification in OCT imaging based on a manually scanned single fiber probe. Our results demonstrated that OCT imaging capability integrated into a low-cost, disposable single fiber probe, along with sophisticated deep learning algorithms for tissue classification, allows minimally invasive tissue characterization, and can be used for cancer diagnosis or surgical margin assessment.

3D confocal laser-scanning microscopy for large-area imaging of the corneal subbasal nerve plexus

The capability of corneal confocal microscopy (CCM) to acquire high-resolution in vivo images of the densely innervated human cornea has gained considerable interest in using this non-invasive technique as an objective diagnostic tool for staging peripheral neuropathies. Morphological alterations of the corneal subbasal nerve plexus (SNP) assessed by CCM have been shown to correlate well with the progression of neuropathic diseases and even predict future-incident neuropathy. Since the field of view of single CCM images is insufficient for reliable characterisation of nerve morphology, several image mosaicking techniques have been developed to facilitate the assessment of the SNP in large-area visualisations. Due to the limited depth of field of confocal microscopy, these approaches are highly sensitive to small deviations of the focus plane from the SNP layer. Our contribution proposes a new automated solution, combining guided eye movements for rapid expansion of the acquired SNP area and axial focus plane oscillations to guarantee complete imaging of the SNP. We present results of a feasibility study using the proposed setup to evaluate different oscillation settings. By comparing different image selection approaches, we show that automatic tissue classification algorithms are essential to create high-quality mosaic images from the acquired 3D datasets.

Quantitative Assessment of Trimethyltin, Kainic Acid and Pyrithiamine Neurotoxicity in Rat Brain and its Correlation with MR Imaging

Toxicagents such as trimethlytin (TMT), kainic acid (KA) and pyrithiamine (PT) induce neurotoxicity. Previous studies have reported degeneration in cortex, hippocampus, olfactory bulb, thalamus a swell as various other brain areas following exposure. Quantitative assessment of the extent of the degeneration is essential for understanding the functional changes due to such toxicity. In the current study, quantitative analyses of the pathological changes associated with single i.p. injections of TMT(12 mg/kg), KA (10 mg/kg) and PT (.25 mg/kg) were performed using tissue classification and area quantification algorithms based on stain color and OD available in HALO™ image analysis software. Sections containing brain areas to be compared to MRI images were chosen from 81 coronal sections of the whole rat brain stained with amino‐cupric silver and subsequently digitalized. Rats treated with TMT showed degeneration in amygdaloid nucleus (11.79%), cortex (7.71%), hippocampus(6.28%), hypothalamus (5.81%), septal region(4.92%), olfactory bulb (4.72%), thalamus (2.82%), nucleus accumbens (2.34%), caudateputamen (2.11%) and substantia nigra (0.40%). Cortical and hippocampaldegeneration in KA treated animals were 5.78% and 4.47%, respectively. Thalamusand olfactory degeneration in PT treated rats were 3.99% and 1.56% respectively. Saline treated animals served as controls and showed &lt;0.3% changes in these brain areas. Quantification results of histopathology using image analysis were supported by the pathology score where the affected area was scored based on a severity scale. MRI T2 responses in hippocampus and cortex were compared to the toxicity in TMT treated animals as determined via histopathology quantification. Receiver Operating Characteristic (ROC) curves were generated to correlate histopathology and MRI responses. Correlation of MR imaging with quantitative histopathology analyses showed that MRI signals were in concordance with the histopathology and could effectively estimate loci and extent of neurodegeneration. Results suggest that MRI can be used as non‐invasive biomarker for the detection of drug‐induced neuropathology.Support or Funding InformationCenter for Drug Evaluation and Research ‐ Critical Path Award and National Center for Toxicological Research, Food and Drug AdministrationThis abstract is from the Experimental Biology 2018 Meeting. There is no full text article associated with this abstract published in The FASEB Journal.

Confident texture-based laryngeal tissue classification for early stage diagnosis support.

Early stage diagnosis of laryngeal squamous cell carcinoma (SCC) is of primary importance for lowering patient mortality or after treatment morbidity. Despite the challenges in diagnosis reported in the clinical literature, few efforts have been invested in computer-assisted diagnosis. The objective of this paper is to investigate the use of texture-based machine-learning algorithms for early stage cancerous laryngeal tissue classification. To estimate the classification reliability, a measure of confidence is also exploited. From the endoscopic videos of 33 patients affected by SCC, a well-balanced dataset of 1320 patches, relative to four laryngeal tissue classes, was extracted. With the best performing feature, the achieved median classification recall was 93% [interquartile range [Formula: see text]]. When excluding low-confidence patches, the achieved median recall was increased to 98% ([Formula: see text]), proving the high reliability of the proposed approach. This research represents an important advancement in the state-of-the-art computer-assisted laryngeal diagnosis, and the results are a promising step toward a helpful endoscope-integrated processing system to support early stage diagnosis.

Evaluation of Robust Classifier Algorithm for Tissue Classification under Various Noise Levels

Evaluation of Robust Classifier Algorithm for Tissue Classification under Various Noise Levels

Population of 224 realistic human subject-based computational breast phantoms.

To create a database of highly realistic and anatomically variable 3D virtual breast phantoms based on dedicated breast computed tomography (bCT) data. A tissue classification and segmentation algorithm was used to create realistic and detailed 3D computational breast phantoms based on 230 + dedicated bCT datasets from normal human subjects. The breast volume was identified using a coarse three-class fuzzy C-means segmentation algorithm which accounted for and removed motion blur at the breast periphery. Noise in the bCT data was reduced through application of a postreconstruction 3D bilateral filter. A 3D adipose nonuniformity (bias field) correction was then applied followed by glandular segmentation using a 3D bias-corrected fuzzy C-means algorithm. Multiple tissue classes were defined including skin, adipose, and several fractional glandular densities. Following segmentation, a skin mask was produced which preserved the interdigitated skin, adipose, and glandular boundaries of the skin interior. Finally, surface modeling was used to produce digital phantoms with methods complementary to the XCAT suite of digital human phantoms. After rejecting some datasets due to artifacts, 224 virtual breast phantoms were created which emulate the complex breast parenchyma of actual human subjects. The volume breast density (with skin) ranged from 5.5% to 66.3% with a mean value of 25.3% ± 13.2%. Breast volumes ranged from 25.0 to 2099.6 ml with a mean value of 716.3 ± 386.5 ml. Three breast phantoms were selected for imaging with digital compression (using finite element modeling) and simple ray-tracing, and the results show promise in their potential to produce realistic simulated mammograms. This work provides a new population of 224 breast phantoms based on in vivo bCT data for imaging research. Compared to previous studies based on only a few prototype cases, this dataset provides a rich source of new cases spanning a wide range of breast types, volumes, densities, and parenchymal patterns.

Simultaneous fingerprint and high-wavenumber fiber-optic Raman spectroscopy improves in vivo diagnosis of esophageal squamous cell carcinoma at endoscopy.

This work aims to evaluate clinical value of a fiber-optic Raman spectroscopy technique developed for in vivo diagnosis of esophageal squamous cell carcinoma (ESCC) during clinical endoscopy. We have developed a rapid fiber-optic Raman endoscopic system capable of simultaneously acquiring both fingerprint (FP)(800–1800 cm−1) and high-wavenumber (HW)(2800–3600 cm−1) Raman spectra from esophageal tissue in vivo. A total of 1172 in vivo FP/HW Raman spectra were acquired from 48 esophageal patients undergoing endoscopic examination. The total Raman dataset was split into two parts: 80% for training; while 20% for testing. Partial least squares-discriminant analysis (PLS-DA) and leave-one patient-out, cross validation (LOPCV) were implemented on training dataset to develop diagnostic algorithms for tissue classification. PLS-DA-LOPCV shows that simultaneous FP/HW Raman spectroscopy on training dataset provides a diagnostic sensitivity of 97.0% and specificity of 97.4% for ESCC classification. Further, the diagnostic algorithm applied to the independent testing dataset based on simultaneous FP/HW Raman technique gives a predictive diagnostic sensitivity of 92.7% and specificity of 93.6% for ESCC identification, which is superior to either FP or HW Raman technique alone. This work demonstrates that the simultaneous FP/HW fiber-optic Raman spectroscopy technique improves real-time in vivo diagnosis of esophageal neoplasia at endoscopy.

Automatic myocardium segmentation of LGE MRI by deformable models with prior shape data

Background Previously a myocardial tissue classification algorithm has been developed to locate and quantify infarct in a given myocardial region-of-interest specified on late gadolinium enhancement (LGE) MR images [1]. To complete the automation requires an endocardial and epicardial contour detection algorithm to replace the current practice of manual contouring that is time-consuming and subject to intraand inter-observer variability. Challenges include: 1) the intensity inhomogeneity of both the healthy and infarct myocardium; 2) the existence of an infarct on a given slice is not known a priori; 3) a subendocardial infarct region’s boundary can be easily mistaken for the endocardial contour due to the proximity and strength of the edge (gradient); and 4) incorporating prior anatomical information (e.g., cine steady-state free precession (SSFP) MRI) while allowing for possible motion between separate studies.

Cerebrospinal Fluid Space Alterations in Melancholic Depression

Melancholic depression is a biologically homogeneous clinical entity in which structural brain alterations have been described. Interestingly, reports of structural alterations in melancholia include volume increases in Cerebro-Spinal Fluid (CSF) spaces. However, there are no previous reports of CSF volume alterations using automated whole-brain voxel-wise approaches, as tissue classification algorithms have been traditionally regarded as less reliable for CSF segmentation. Here we aimed to assess CSF volumetric alterations in melancholic depression and their clinical correlates by means of a novel segmentation algorithm (‘new segment’, as implemented in the software Statistical Parametric Mapping-SPM8), incorporating specific features that may improve CSF segmentation. A three-dimensional Magnetic Resonance Image (MRI) was obtained from seventy patients with melancholic depression and forty healthy control subjects. Although imaging data were pre-processed with the ‘new segment’ algorithm, in order to obtain a comparison with previous segmentation approaches, tissue segmentation was also performed with the ‘unified segmentation’ approach. Melancholic patients showed a CSF volume increase in the region of the left Sylvian fissure, and a CSF volume decrease in the subarachnoid spaces surrounding medial and lateral parietal cortices. Furthermore, CSF increases in the left Sylvian fissure were negatively correlated with the reduction percentage of depressive symptoms at discharge. None of these results were replicated with the ‘unified segmentation’ approach. By contrast, between-group differences in the left Sylvian fissure were replicated with a non-automated quantification of the CSF content of this region. Left Sylvian fissure alterations reported here are in agreement with previous findings from non-automated CSF assessments, and also with other reports of gray and white matter insular alterations in depressive samples using automated approaches. The reliable characterization of CSF alterations may help in the comprehensive characterization of brain structural abnormalities in psychiatric samples and in the development of etiopathogenic hypotheses relating to the disorders.