Artificial Intelligence Enabled Histological Prediction of Remission or Activity and Clinical Outcomes in Ulcerative Colitis.

BACKGROUND & AIMS: Microscopic inflammation has significant prognostic value in ulcerative colitis (UC); however, its assessment is complex with high interobserver variability. We aimed to develop and validate an artificial intelligence (AI) computer-aided diagnosis system to evaluate UC biopsies and predict prognosis. METHODS: A total of 535 digitalized biopsies (273 patients) were graded according to the PICaSSO Histologic Remission Index (PHRI), Robarts, and Nancy Histological Index. A convolutional neural network classifier was trained to distinguish remission from activity on a subset of 118 biopsies, calibrated on 42 and tested on 375. The model was additionally tested to predict the corresponding endoscopic assessment and occurrence of flares at 12 months. The system output was compared with human assessment. Diagnostic performance was reported as sensitivity, specificity, prognostic prediction through Kaplan-Meier, and hazard ratios of flares between active and remission groups. We externally validated the model in 154 biopsies (58 patients) with similar characteristics but more histologically active patients. RESULTS: The system distinguished histological activity/remission with sensitivity and specificity of 89% and 85% (PHRI), 94% and 76% (Robarts Histological Index), and 89% and 79% (Nancy Histological Index). The model predicted the corresponding endoscopic remission/activity with 79% and 82% accuracy for UC endoscopic index of severity and Paddington International virtual ChromoendoScopy ScOre, respectively. The hazard ratio for disease flare-up between histological activity/remission groups according to pathologist-assessed PHRI was 3.56, and 4.64 for AI-assessed PHRI. Both histology and outcome prediction were confirmed in the external validation cohort. CONCLUSION: We developed and validated an AI model that distinguishes histologic remission/activity in biopsies of UC and predicts flare-ups. This can expedite, standardize, and enhance histologic assessment in practice and trials.

A virtual chromoendoscopy artificial intelligence system to detect endoscopic and histologic activity/remission and predict clinical outcomes in ulcerative colitis.

BACKGROUND: Endoscopic and histological remission (ER, HR) are therapeutic targets in ulcerative colitis (UC). Virtual chromoendoscopy (VCE) improves endoscopic assessment and the prediction of histology; however, interobserver variability limits standardized endoscopic assessment. We aimed to develop an artificial intelligence (AI) tool to distinguish ER/activity, and predict histology and risk of flare from white-light endoscopy (WLE) and VCE videos. METHODS: 1090 endoscopic videos (67 280 frames) from 283 patients were used to develop a convolutional neural network (CNN). UC endoscopic activity was graded by experts using the Ulcerative Colitis Endoscopic Index of Severity (UCEIS) and Paddington International virtual ChromoendoScopy ScOre (PICaSSO). The CNN was trained to distinguish ER/activity on endoscopy videos, and retrained to predict HR/activity, defined according to multiple indices, and predict outcome; CNN and human agreement was measured. RESULTS: The AI system detected ER (UCEIS ≤ 1) in WLE videos with 72 % sensitivity, 87 % specificity, and an area under the receiver operating characteristic curve (AUROC) of 0.85; for detection of ER in VCE videos (PICaSSO ≤ 3), the sensitivity was 79 %, specificity 95 %, and the AUROC 0.94. The prediction of HR was similar between WLE and VCE videos (accuracies ranging from 80 % to 85 %). The model's stratification of risk of flare was similar to that of physician-assessed endoscopy scores. CONCLUSIONS: Our system accurately distinguished ER/activity and predicted HR and clinical outcome from colonoscopy videos. This is the first computer model developed to detect inflammation/healing on VCE using the PICaSSO and the first computer tool to provide endoscopic, histologic, and clinical assessment.

PICaSSO Histologic Remission Index (PHRI) in ulcerative colitis: development of a novel simplified histological score for monitoring mucosal healing and predicting clinical outcomes and its applicability in an artificial intelligence system.

Histological remission is evolving as an important treatment target in UC. We aimed to develop a simple histological index, aligned to endoscopy, correlated with clinical outcomes, and suited to apply to an artificial intelligence (AI) system to evaluate inflammatory activity. METHODS: Using a set of 614 biopsies from 307 patients with UC enrolled into a prospective multicentre study, we developed the Paddington International virtual ChromoendoScopy ScOre (PICaSSO) Histologic Remission Index (PHRI). Agreement with multiple other histological indices and validation for inter-reader reproducibility were assessed. Finally, to implement PHRI into a computer-aided diagnosis system, we trained and tested a novel deep learning strategy based on a CNN architecture to detect neutrophils, calculate PHRI and identify active from quiescent UC using a subset of 138 biopsies. RESULTS: PHRI is strongly correlated with endoscopic scores (Mayo Endoscopic Score and UC Endoscopic Index of Severity and PICaSSO) and with clinical outcomes (hospitalisation, colectomy and initiation or changes in medical therapy due to UC flare-up). A PHRI score of 1 could accurately stratify patients' risk of adverse outcomes (hospitalisation, colectomy and treatment optimisation due to flare-up) within 12 months. Our inter-reader agreement was high (intraclass correlation 0.84). Our preliminary AI algorithm differentiated active from quiescent UC with 78% sensitivity, 91.7% specificity and 86% accuracy. CONCLUSIONS: PHRI is a simple histological index in UC, and it exhibits the highest correlation with endoscopic activity and clinical outcomes. A PHRI-based AI system was accurate in predicting histological remission.

The claustrum of the sheep and its connections to the visual cortex.

The present study analyses the organization and selected neurochemical features of the claustrum and visual cortex of the sheep, based on the patterns of calcium-binding proteins expression. Connections of the claustrum with the visual cortex have been studied by tractography. Parvalbumin-immunoreactive (PV-ir) and Calbindin-immunoreactive (CB-ir) cell bodies increased along the rostro-caudal axis of the nucleus. Calretinin (CR)-labeled somata were few and evenly distributed along the rostro-caudal axis. PV and CB distribution in the visual cortex was characterized by larger round and multipolar cells for PV, and more bitufted neurons for CB. The staining pattern for PV was the opposite of that of CR, which showed densely stained but rare cell bodies. Tractography shows the existence of connections with the caudal visual cortex. However, we detected no contralateral projection in the visuo-claustral interconnections. Since sheep and goats have laterally placed eyes and a limited binocular vision, the absence of contralateral projections could be of prime importance if confirmed by other studies, to rule out the role of the claustrum in stereopsis.

Does Quantification of Carotid Plaque Surface Irregularities Better Detect Symptomatic Plaques Compared to the Subjective Classification?

OBJECTIVES: To evaluate the interobserver agreement of color Doppler ultrasound (CDUS) and contrast-enhanced ultrasound (CEUS) for quantification of carotid plaque surface irregularities and to correlate objective and subjective measures with stroke occurrence. METHODS: This work was an observational study involving 54 patients with 62 internal carotid artery or carotid bulb plaques (31 symptomatic) undergoing CDUS and CEUS between February 2016 and February 2018, with retrospective interpretation of prospectively acquired data. Plaques were included if causing moderate (50%-69%) or severe (70%-99%) stenosis based on velocity criteria, and their surface was classified as smooth, irregular, or ulcerated based on CEUS. The surface irregularities were quantified in the form of a surface irregularity index by 2 observers, based on CDUS and CEUS. The surface irregularity index was evaluated for interobserver agreement with CDUS and CEUS and correlated with the occurrence of stroke, as was the subjective characterization of the plaque surface. RESULTS: Color Doppler ultrasound and CEUS showed good interobserver agreement (intraclass correlation coefficients, 0.979 and 0.952, respectively). Plaques were characterized as smooth in 30.6% of cases, irregular in 50%, and ulcerated in 19.4%. The subjective classification of the plaque surface did not correlate with stroke occurrence (P > .05, χ2 ). Surface irregularity index values were significantly higher for symptomatic plaques with both CDUS and CEUS (P < .05). CONCLUSIONS: Color Doppler ultrasound and CEUS can quantify carotid plaque surface irregularities with good interobserver agreement. The resulting quantitative measure was significantly higher in symptomatic plaques, whereas the subjective characterization of plaque surface failed to differ between symptomatic and asymptomatic plaques.

Fetal Abdominal Aorta: Doppler and Structural Evaluation of Endothelial Function in Intrauterine Growth Restriction and Controls.

PURPOSE: The human aorta stores strain energy in the distended wall during systole through the extracellular matrix of the tunica media that could be influenced by blood pressure, flow, or increased peripheral resistance. In intrauterine growth restriction (IUGR) fetuses, the increased aorta intima media thickness (aIMT) could reflect a different extracellular matrix composition and, therefore, functionality. The aim of this study was to analyze the resistance to flow in the fetal descending aorta and its relation to aIMT and systolic and diastolic fetal abdominal aorta diameters in IUGR fetuses and controls. MATERIALS AND METHODS: This is a prospective case control study of single pregnancies collected at a tertiary center for feto-maternal medicine in Northeast Italy. An IUGR group as cases and a group of fetuses appropriate for gestational age (AGA) as controls were included. RESULTS: We found a greater PI of the fetal abdominal aorta in the IUGR group (1.82) than in the AGA group (1.21) (p < 0.05). The change between the systolic and diastolic fetal abdominal aorta diameters was significantly greater in IUGR fetuses (0.10 mm (IQR 0.07 - 0.28)) than in the AGA group (0.04 mm (0.03 - 0.05)) (p < 0.05). In the IUGR group aIMT was significantly correlated with peak systolic velocity (PSV) and systolic-diastolic aorta diameter change, while these two correlations were not found in the control group. CONCLUSION: The change between the systolic and diastolic fetal abdominal aorta diameters in IUGR cases during the early third trimester of pregnancy was significantly increased and aIMT in the IUGR group was significantly correlated to systolic-diastolic diameter change and PSV, probably reflecting aortic wall adaptation to blood flow changes in IUGR fetuses.

Grade and location of power Doppler are predictive of damage progression in rheumatoid arthritis patients in clinical remission by anti-tumour necrosis factor α.

Objectives: To investigate power Doppler (PD) signal, grade and location and their association with radiographic progression in RA patients in remission. Methods: A prospective observational study was conducted in 125 consecutive RA patients in stable 28-joint DAS (DAS28) remission (⩾6 months) achieved on anti-TNF-α. At baseline, patients in stable remission underwent radiographic and US examination of the wrists and MCP, PIP and MTP joints. Semi-quantitative PD scoring (0-3) was recorded. We scored PD according to two locations: capsular or within synovial tissue without bone contact (location 1) and with bone contact or penetrating bone cortex (location 2). Radiographic progression was evaluated at the 1 year follow-up and defined as a change in van der Heijde-modified total Sharp score >0. Risk ratios (RRs) of radiographic progression according to presence, grade and location of PD were calculated. Results: Four patients were excluded because of missing data. At baseline, 59/121 (48.7%) patients had a PD signal in one or more joints. PD location 2 was found in 74.6% patients (44/59). At the 1 year follow-up, 17/121 patients experienced radiographic progression: all had PD signal in one or more joints at baseline (RR 2.47, P < 0.0001). Radiographic progression was associated with the following baseline US features: PD grade 2 (RR 4.58, P < 0.01), PD grade 3 (RR 3.49, P < 0.05), total PD score ⩾2 (sum of all PD scores) (RR 3.19, P < 0.0001) and PD location 2 (RR 3.49, P < 0.0001). Conclusion: Higher PD grades and PD in contact with/or penetrating bone are associated with radiographic progression in patients in DAS28 remission.

MR and CEUS monitoring of patients with severe rheumatoid arthritis treated with biological agents: a preliminary study.

PURPOSE: This study was done to propose a study protocol for patients with rheumatoid arthritis (RA) treated with biological agents, by evaluating the contribution of contrast-enhanced magnetic resonance (CE-MR) imaging, a software programme that calculates the volume of synovitis on CE-MR images, and contrast-enhanced ultrasound (CEUS). MATERIALS AND METHODS: Sixteen patients with RA receiving treatment with biologics were analysed. The patients underwent clinical examination, CE-MR imaging and CEUS on the same day. Images were postprocessed with the software and evaluated independently by three physicians in terms of RAMRIS (Rheumatoid Arthritis Magnetic Resonance Imaging Score), SAMIS (Simplified Rheumatoid Arthritis Magnetic Resonance Imaging Score) and CEUS grade. The techniques were correlated statistically. RESULTS: The RAMRIS and SAMIS scores were found to correlate statistically. CE-MR imaging correlated with the clinical data (p < 0.05), whereas CEUS did not. The data provided by the software did not correlate statistically with the other techniques. The most painful joint was consistently found to be the joint with most synovitis. CONCLUSIONS: CE-MR imaging may be used prior to treatment and for long-term follow-up. CEUS might be useful in the short-term follow-up, as it seems to provide an indication of the presence or absence of disease, though not of its severity. The software is a very useful tool that can supplement, but not replace, the other techniques.

Artificial intelligence and endo-histo-omics: new dimensions of precision endoscopy and histology in inflammatory bowel disease.

Integrating artificial intelligence into inflammatory bowel disease (IBD) has the potential to revolutionise clinical practice and research. Artificial intelligence harnesses advanced algorithms to deliver accurate assessments of IBD endoscopy and histology, offering precise evaluations of disease activity, standardised scoring, and outcome prediction. Furthermore, artificial intelligence offers the potential for a holistic endo-histo-omics approach by interlacing and harmonising endoscopy, histology, and omics data towards precision medicine. The emerging applications of artificial intelligence could pave the way for personalised medicine in IBD, offering patient stratification for the most beneficial therapy with minimal risk. Although artificial intelligence holds promise, challenges remain, including data quality, standardisation, reproducibility, scarcity of randomised controlled trials, clinical implementation, ethical concerns, legal liability, and regulatory issues. The development of standardised guidelines and interdisciplinary collaboration, including policy makers and regulatory agencies, is crucial for addressing these challenges and advancing artificial intelligence in IBD clinical practice and trials.

Developmental programming of cardiovascular risk in intrauterine growth-restricted twin fetuses according to aortic intima thickness.

OBJECTIVES: We aimed to test the hypothesis that aortic intima thickness is greater in intrauterine growth-restricted (IUGR) twin fetuses compared to normally developing twins, thus defining an increased cardiovascular risk that reflects genetic factors in fetuses sharing the same womb. METHODS: We conducted a prospective study performed on twins from January 2009 to July 2011. Twins were classified into 3 groups: IUGR fetuses with an estimated fetal weight below the 10th percentile and an umbilical artery pulsatility index of greater than 2 SDs (group A), fetuses with an estimated fetal weight below the 10th percentile and normal Doppler findings (group B), and fetuses with an estimated fetal weight appropriate for gestational age (group C). Aortic intima thickness was measured at a median gestational age of 32 weeks. Values were compared among groups and between each twin and cotwin, also considering sex and chorionicity. RESULTS: Twenty-five fetuses were classified as group A, 36 as group B, and 95 as group C. The median aortic intima thickness values were 0.9 mm in group A, 0.7 mm in group B, and 0.6 mm in group C (P < .0001). There was a statistically significant difference between the aortic intima thickness of the twins and cotwins in groups A and B (P < .0001). Sex and chorionicity did not correlate with aortic intima thickness. CONCLUSIONS: In this study, IUGR fetuses with Doppler abnormalities had greater aortic intima thickness, and IUGR twins with normal Doppler findings had intermediate thickness, supporting a genetic predisposition to cardiovascular risk independent of sex and chorionicity.

Age-related changes in the primary auditory cortex of newborn, adults and aging bottlenose dolphins (Tursiops truncatus) are located in the upper cortical layers.

Introduction: The auditory system of dolphins and whales allows them to dive in dark waters, hunt for prey well below the limit of solar light absorption, and to communicate with their conspecific. These complex behaviors require specific and sufficient functional circuitry in the neocortex, and vicarious learning capacities. Dolphins are also precocious animals that can hold their breath and swim within minutes after birth. However, diving and hunting behaviors are likely not innate and need to be learned. Our hypothesis is that the organization of the auditory cortex of dolphins grows and mature not only in the early phases of life, but also in adults and aging individuals. These changes may be subtle and involve sub-populations of cells specificall linked to some circuits. Methods: In the primary auditory cortex of 11 bottlenose dolphins belonging to three age groups (calves, adults, and old animals), neuronal cell shapes were analyzed separately and by cortical layer using custom computer vision and multivariate statistical analysis, to determine potential minute morphological differences across these age groups. Results: The results show definite changes in interneurons, characterized by round and ellipsoid shapes predominantly located in upper cortical layers. Notably, neonates interneurons exhibited a pattern of being closer together and smaller, developing into a more dispersed and diverse set of shapes in adulthood. Discussion: This trend persisted in older animals, suggesting a continuous development of connections throughout the life of these marine animals. Our findings further support the proposition that thalamic input reach upper layers in cetaceans, at least within a cortical area critical for their survival. Moreover, our results indicate the likelihood of changes in cell populations occurring in adult animals, prompting the need for characterization.

Computer-Aided Imaging Analysis of Probe-Based Confocal Laser Endomicroscopy With Molecular Labeling and Gene Expression Identifies Markers of Response to Biological Therapy in IBD Patients: The Endo-Omics Study.

BACKGROUND: We aimed to predict response to biologics in inflammatory bowel disease (IBD) using computerized image analysis of probe confocal laser endomicroscopy (pCLE) in vivo and assess the binding of fluorescent-labeled biologics ex vivo. Additionally, we investigated genes predictive of anti-tumor necrosis factor (TNF) response. METHODS: Twenty-nine patients (15 with Crohn's disease [CD], 14 with ulcerative colitis [UC]) underwent colonoscopy with pCLE before and 12 to 14 weeks after starting anti-TNF or anti-integrin α4ß7 therapy. Biopsies were taken for fluorescein isothiocyanate-labeled infliximab and vedolizumab staining and gene expression analysis. Computer-aided quantitative image analysis of pCLE was performed. Differentially expressed genes predictive of response were determined and validated in a public cohort. RESULTS: In vivo, vessel tortuosity, crypt morphology, and fluorescein leakage predicted response in UC (area under the receiver-operating characteristic curve [AUROC], 0.93; accuracy 85%, positive predictive value [PPV] 89%; negative predictive value [NPV] 75%) and CD (AUROC, 0.79; accuracy 80%; PPV 75%; NPV 83%) patients. Ex vivo, increased binding of labeled biologic at baseline predicted response in UC (UC) (AUROC, 83%; accuracy 77%; PPV 89%; NPV 50%) but not in Crohn's disease (AUROC 58%). A total of 325 differentially expressed genes distinguished responders from nonresponders, 86 of which fell within the most enriched pathways. A panel including ACTN1, CXCL6, LAMA4, EMILIN1, CRIP2, CXCL13, and MAPKAPK2 showed good prediction of anti-TNF response (AUROC >0.7). CONCLUSIONS: Higher mucosal binding of the drug target is associated with response to therapy in UC. In vivo, mucosal and microvascular changes detected by pCLE are associated with response to biologics in inflammatory bowel disease. Anti-TNF-responsive UC patients have a less inflamed and fibrotic state pretreatment. Chemotactic pathways involving CXCL6 or CXCL13 may be novel targets for therapy in nonresponders.

A novel DSP zebrafish model reveals training- and drug-induced modulation of arrhythmogenic cardiomyopathy phenotypes.

Arrhythmogenic cardiomyopathy (AC) is an inherited disorder characterized by progressive loss of the ventricular myocardium causing life-threatening ventricular arrhythmias, syncope and sudden cardiac death in young and athletes. About 40% of AC cases carry one or more mutations in genes encoding for desmosomal proteins, including Desmoplakin (Dsp). We present here the first stable Dsp knock-out (KO) zebrafish line able to model cardiac alterations and cell signalling dysregulation, characteristic of the AC disease, on which environmental factors and candidate drugs can be tested. Our stable Dsp knock-out (KO) zebrafish line was characterized by cardiac alterations, oedema and bradycardia at larval stages. Histological analysis of mutated adult hearts showed reduced contractile structures and abnormal shape of the ventricle, with thinning of the myocardial layer, vessels dilation and presence of adipocytes within the myocardium. Moreover, TEM analysis revealed "pale", disorganized and delocalized desmosomes. Intensive physical training protocol caused a global worsening of the cardiac phenotype, accelerating the progression of the disease. Of note, we detected a decrease of Wnt/ß-catenin signalling, recently associated with AC pathogenesis, as well as Hippo/YAP-TAZ and TGF-ß pathway dysregulation. Pharmacological treatment of mutated larvae with SB216763, a Wnt/ß-catenin agonist, rescued pathway expression and cardiac abnormalities, stabilizing the heart rhythm. Overall, our Dsp KO zebrafish line recapitulates many AC features observed in human patients, pointing at zebrafish as a suitable system for in vivo analysis of environmental modulators, such as the physical exercise, and the screening of pathway-targeted drugs, especially related to the Wnt/ß-catenin signalling cascade.

An adaptive registration algorithm for zebrafish larval brain images.

BACKGROUND AND OBJECTIVE: Zebrafish (Danio rerio) in their larval stages have grown increasingly popular as excellent vertebrate models for neurobiological research. Researchers can apply various tools in order to decode the neural structure patterns which can aid the understanding of vertebrate brain development. In order to do so, it is essential to map the gene expression patterns to an anatomical reference precisely. However, high accuracy in sample registration is sometimes difficult to achieve due to laboratory- or protocol-dependent variabilities. METHODS: In this paper, we propose an accurate adaptive registration algorithm for volumetric zebrafish larval image datasets using a synergistic combination of attractive Free-Form-Deformation (FFD) and diffusive Demons algorithms. A coarse registration is achieved first for 3D volumetric data using a 3D affine transformation. A localized registration algorithm in form of a B-splines based FFD is applied next on the coarsely registered volume. Finally, the Demons algorithm is applied on this FFD registered volume for achieving fine registration by making the solution noise resilient. RESULTS: Results Experimental procedures are carried out on a number of 72 hpf (hours post fertilization) 3D confocal zebrafish larval datasets. Comparisons with state-of-the-art methods including some ablation studies clearly demonstrate the effectiveness of the proposed method. CONCLUSIONS: Our adaptive registration algorithm significantly aids Zebrafish imaging analysis over current methods for gene expression anatomical mapping, such as Vibe-Z. We believe the proposed solution would be able to overcome the requirement of high quality images which currently limits the applicability of Zebrafish in neuroimaging research.

A Deep Graph Cut Model For 3D Brain Tumor Segmentation.

Brain tumor segmentation plays a key role in tumor diagnosis and surgical planning. In this paper, we propose a solution to the 3D brain tumor segmentation problem using deep learning and graph cut from the MRI data. In particular, the probability maps of a voxel to belong to the object (tumor) and background classes from the UNet are used to improve the energy function of the graph cut. We derive new expressions for the data term, the region term and the weight factor balancing the data term and the region term for individual voxels in our proposed model. We validate the performance of our model on the publicly available BRATS 2018 dataset. Our segmentation accuracy with a dice similarity score of 0.92 is found to be higher than that of the graph cut and the UNet applied in isolation as well as over a number of state of the art approaches.

The primary visual cortex of Cetartiodactyls: organization, cytoarchitectonics and comparison with perissodactyls and primates.

Cetartiodactyls include terrestrial and marine species, all generally endowed with a comparatively lateral position of their eyes and a relatively limited binocular field of vision. To this day, our understanding of the visual system in mammals beyond the few studied animal models remains limited. In the present study, we examined the primary visual cortex of Cetartiodactyls that live on land (sheep, Père David deer, giraffe); in the sea (bottlenose dolphin, Risso's dolphin, long-finned pilot whale, Cuvier's beaked whale, sperm whale and fin whale); or in an amphibious environment (hippopotamus). We also sampled and studied the visual cortex of the horse (a closely related perissodactyl) and two primates (chimpanzee and pig-tailed macaque) for comparison. Our histochemical and immunohistochemical results indicate that the visual cortex of Cetartiodactyls is characterized by a peculiar organization, structure, and complexity of the cortical column. We noted a general lesser lamination compared to simians, with diminished density, and an apparent simplification of the intra- and extra-columnar connections. The presence and distribution of calcium-binding proteins indicated a notable absence of parvalbumin in water species and a strong reduction of layer 4, usually enlarged in the striated cortex, seemingly replaced by a more diffuse distribution in neighboring layers. Consequently, thalamo-cortical inputs are apparently directed to the higher layers of the column. Computer analyses and statistical evaluation of the data confirmed the results and indicated a substantial correlation between eye placement and cortical structure, with a markedly segregated pattern in cetaceans compared to other mammals. Furthermore, cetacean species showed several types of cortical lamination which may reflect differences in function, possibly related to depth of foraging and consequent progressive disappearance of light, and increased importance of echolocation.

Predicting functional impairment trajectories in amyotrophic lateral sclerosis: a probabilistic, multifactorial model of disease progression.

OBJECTIVE: To employ Artificial Intelligence to model, predict and simulate the amyotrophic lateral sclerosis (ALS) progression over time in terms of variable interactions, functional impairments, and survival. METHODS: We employed demographic and clinical variables, including functional scores and the utilisation of support interventions, of 3940 ALS patients from four Italian and two Israeli registers to develop a new approach based on Dynamic Bayesian Networks (DBNs) that models the ALS evolution over time, in two distinct scenarios of variable availability. The method allows to simulate patients' disease trajectories and predict the probability of functional impairment and survival at different time points. RESULTS: DBNs explicitly represent the relationships between the variables and the pathways along which they influence the disease progression. Several notable inter-dependencies were identified and validated by comparison with literature. Moreover, the implemented tool allows the assessment of the effect of different markers on the disease course, reproducing the probabilistically expected clinical progressions. The tool shows high concordance in terms of predicted and real prognosis, assessed as time to functional impairments and survival (integral of the AU-ROC in the first 36 months between 0.80-0.93 and 0.84-0.89 for the two scenarios, respectively). CONCLUSIONS: Provided only with measurements commonly collected during the first visit, our models can predict time to the loss of independence in walking, breathing, swallowing, communicating, and survival and it can be used to generate in silico patient cohorts with specific characteristics. Our tool provides a comprehensive framework to support physicians in treatment planning and clinical decision-making.

Constrained multiple instance learning for ulcerative colitis prediction using histological images.

BACKGROUND AND OBJECTIVE: Ulcerative colitis (UC) is an inflammatory bowel disease (IBD) affecting the colon and the rectum characterized by a remitting-relapsing course. To detect mucosal inflammation associated with UC, histology is considered the most stringent criteria. In turn, histologic remission (HR) correlates with improved clinical outcomes and has been recently recognized as a desirable treatment target. The leading biomarker for assessing histologic remission is the presence or absence of neutrophils. Therefore, the finding of this cell in specific colon structures indicates that the patient has UC activity. However, no previous studies based on deep learning have been developed to identify UC based on neutrophils detection using whole-slide images (WSI). METHODS: The methodological core of this work is a novel multiple instance learning (MIL) framework with location constraints able to determine the presence of UC activity using WSI. In particular, we put forward an effective way to introduce constraints about positive instances to effectively explore additional weakly supervised information that is easy to obtain and enjoy a significant boost to the learning process. In addition, we propose a new weighted embedding to enlarge the relevance of the positive instances. RESULTS: Extensive experiments on a multi-center dataset of colon and rectum WSIs, PICASSO-MIL, demonstrate that using the location information we can improve considerably the results at WSI-level. In comparison with prior MIL settings, our method allows for 10% improvements in bag-level accuracy. CONCLUSION: Our model, which introduces a new form of constraints, surpass the results achieved from current state-of-the-art methods that focus on the MIL paradigm. Our method can be applied to other histological concerns where the morphological features determining a positive WSI are tiny and similar to others in the image.

Deep learning for the prediction of treatment response in depression.

BACKGROUND: Mood disorders are characterized by heterogeneity in severity, symptoms and treatment response. The possibility of selecting the correct therapy on the basis of patient-specific biomarker may be a considerable step towards personalized psychiatry. Machine learning methods are gaining increasing popularity in the medical field. Once trained, the possibility to consider single patients in the analyses instead of whole groups makes them particularly appealing to investigate treatment response. Deep learning, a branch of machine learning, lately gained attention, due to its effectiveness in dealing with large neuroimaging data and to integrate them with clinical, molecular or -omics biomarkers. METHODS: In this mini-review, we summarize studies that use deep learning methods to predict response to treatment in depression. We performed a bibliographic search on PUBMED, Google Scholar and Web of Science using the terms "psychiatry", "mood disorder", "depression", "treatment", "deep learning", "neural networks". Only studies considering patients' datasets are considered. RESULTS: Eight studies met the inclusion criteria. Accuracies in prediction of response to therapy were considerably high in all studies, but results may be not easy to interpret. LIMITATIONS: The major limitation for the current studies is the small sample size, which constitutes an issue for machine learning methods. CONCLUSIONS: Deep learning shows promising results in terms of prediction of treatment response, often outperforming regression methods and reaching accuracies of around 80%. This could be of great help towards personalized medicine. However, more efforts are needed in terms of increasing datasets size and improved interpretability of results.