John Thornton

YNICL Journal 2019 Journal Article

Prion disease diagnosis using subject-specific imaging biomarkers within a multi-kernel Gaussian process

• Liane S. Canas
• Carole H. Sudre
• Enrico De Vita
• Akin Nihat
• Tze How Mok
• Catherine F. Slattery
• Ross W. Paterson
• Alexander J.M. Foulkes

Prion diseases are a group of rare neurodegenerative conditions characterised by a high rate of progression and highly heterogeneous phenotypes. Whilst the most common form of prion disease occurs sporadically (sporadic Creutzfeldt-Jakob disease, sCJD), other forms are caused by prion protein gene mutations, or exposure to prions in the diet or by medical procedures, such us surgeries. To date, there are no accurate quantitative imaging biomarkers that can be used to predict the future clinical diagnosis of a healthy subject, or to quantify the progression of symptoms over time. Besides, CJD is commonly mistaken for other forms of dementia. Due to the heterogeneity of phenotypes and the lack of a consistent geometrical pattern of disease progression, the approaches used to study other types of neurodegenerative diseases are not satisfactory to capture the progression of human form of prion disease. In this paper, using a tailored framework, we aim to classify and stratify patients with prion disease, according to the severity of their illness. The framework is initialised with the extraction of subject-specific imaging biomarkers. The extracted biomakers are then combined with genetic and demographic information within a Gaussian Process classifier, used to calculate the probability of a subject to be diagnosed with prion disease in the next year. We evaluate the effectiveness of the proposed method in a cohort of patients with inherited and sporadic forms of prion disease. The model has shown to be effective in the prediction of both inherited CJD (92% of accuracy) and sporadic CJD (95% of accuracy). However the model has shown to be less effective when used to stratify the different stages of the disease, in which the average accuracy is 85%, whilst the recall is 59%. Finally, our framework was extended as a differential diagnosis tool to identify both forms of CJD among another neurodegenerative disease. In summary we have developed a novel method for prion disease diagnosis and prediction of clinical onset using multiple sources of features, which may have use in other disorders with heterogeneous imaging features.

YNICL Journal 2019 Journal Article

Somatotopic organization of corticospinal/corticobulbar motor tracts in controls and patients with tumours: A combined fMRI–DTI study

• Neven M. Hazzaa
• Laura Mancini
• John Thornton
• Tarek A. Yousry

OBJECTIVES: To investigate the relative somatotopic organization of the motor corticospinal/corticobulbar foot, hand, lip and tongue fascicles by combining fMRI with DTI and to examine the influence of subjacent intrinsic tumours on these fascicles. METHODS: The study was approved by the local ethics committee. Seven male and three female volunteers (median age: 35 years) and one female and eight male patients with brain tumours (median age: 37 years) were scanned on a 1.5-T MRI scanner. fMRI data, analysed using SPM5, identified the motor task-driven fMRI grey matter activations of the hand, foot, lips and tongue as seed regions for probabilistic tractography. The relationship between the components of the CST was assessed and the distances between them were measured. A statistical comparison was performed comparing these distances in the group of healthy hemispheres with those of the group of non-affected hemispheres and healthy hemispheres. RESULTS: Hand fascicles were identified in all subjects (38/38, 100%), followed by foot (32/38, 84%), lip (31/38, 81%) and tongue fascicles (28/38, 74%). At superior levels, the hand fascicles were anterolateral to the foot fascicles in 77-93% of healthy hemispheres (HH), in 50-71% of non-affected patients' hemispheres (pH) and in 67-89% of affected PH. At inferior levels, the hand fascicles were either anteromedial in 46-45% of HH or anterior in 75% of non-affected PH and in 67-83% of affected PH. Tongue and lip fascicles overlapped in 25-45% of HH, in 10-20% of non-affected PH and in 15-25% of affected PH. No significant difference was found between the group of affected hemispheres and that of healthy and non-affected hemispheres. CONCLUSION: The somatotopy of the hand fascicles in relation to the foot fascicles was anterolateral in patients and volunteers at superior levels but anteromedial in volunteers and mostly anterior in patients at inferior levels. The lip and tongue fascicles generally overlapped. Intracranial tumours displaced the motor fascicles without affecting their relative somatotopy.

AAAI Conference 2014 Conference Paper

Tailoring Local Search for Partial MaxSAT

• Shaowei Cai
• Chuan Luo
• John Thornton
• Kaile Su

Partial MaxSAT (PMS) is a generalization to SAT and MaxSAT. Many real world problems can be encoded into PMS in a more natural and compact way than SAT and MaxSAT. In this paper, we propose new ideas for local search for PMS, which mainly rely on the distinction between hard and soft clauses. We use these ideas to develop a local search PMS algorithm called Dist. Experimental results on PMS benchmarks from MaxSAT Evaluation 2013 show that Dist significantly outperforms state-of-the-art PMS algorithms, including both local search algorithms and complete ones, on random and crafted benchmarks. For the industrial benchmark, Dist dramatically outperforms previous local search algorithms and is comparable with complete algorithms.

AIJ Journal 2008 Journal Article

Modelling and solving temporal reasoning as propositional satisfiability

• Duc Nghia Pham
• John Thornton
• Abdul Sattar

Representing and reasoning about time dependent information is a key research issue in many areas of computer science and artificial intelligence. One of the best known and widely used formalisms for representing interval-based qualitative temporal information is Allen's interval algebra (IA). The fundamental reasoning task in IA is to find a scenario that is consistent with the given information. This problem is in general NP-complete. In this paper, we investigate how an interval-based representation, or IA network, can be encoded into a propositional formula of Boolean variables and/or predicates in decidable theories. Our task is to discover whether satisfying such a formula can be more efficient than finding a consistent scenario for the original problem. There are two basic approaches to modelling an IA network: one represents the relations between intervals as variables and the other represents the end-points of each interval as variables. By combining these two approaches with three different Boolean satisfiability (SAT) encoding schemes, we produced six encoding schemes for converting IA to SAT. In addition, we also showed how IA networks can be formulated into satisfiability modulo theories (SMT) formulae based on the quantifier-free integer difference logic (QF-IDL). These encodings were empirically studied using randomly generated IA problems of sizes ranging from 20 to 100 nodes. A general conclusion we draw from these experimental results is that encoding IA into SAT produces better results than existing approaches. More specifically, we show that the new point-based 1-D support SAT encoding of IA produces consistently better results than the other alternatives considered. In comparison with the six different SAT encodings, the SMT encoding came fourth after the point-based and interval-based 1-D support schemes and the point-based direct scheme. Further, we observe that the phase transition region maps directly from the IA encoding to each SAT or SMT encoding, but, surprisingly, the location of the hard region varies according to the encoding scheme. Our results also show a fixed performance ranking order over the various encoding schemes.

IJCAI Conference 2007 Conference Paper

• Duc Nghia Pham
• John Thornton
• Abdul Sattar

Local search procedures for solving satisfiability problems have attracted considerable attention since the development of GSAT in 1992. However, recent work indicates that for many real-world problems, complete search methods have the advantage, because modern heuristics are able to effectively exploit problem structure. Indeed, to develop a local search technique that can effectively deal with variable dependencies has been an open challenge since 1997.

AAAI Conference 2004 Conference Paper

Additive versus Multiplicative Clause Weighting for SAT

• John Thornton
• Stuart Bain

This paper examines the relative performance of additive and multiplicative clause weighting schemes for propositional satisfiability testing. Starting with one of the most recently developed multiplicative algorithms (SAPS), an experimental study was constructed to isolate the effects of multiplicative in comparison to additive weighting, while controlling other key features of the two approaches, namely the use of random versus flat moves, deterministic versus probabilistic weight smoothing and multiple versus single inclusion of literals in the local search neighborhood. As a result of this investigation we developed a pure additive weighting scheme (PAWS) which can outperform multiplicative weighting on a range of difficult problems, while requiring considerably less effort in terms of parameter tuning. We conclude that additive weighting shows better scaling properties because it makes less distinction between costs and so considers a larger domain of possible moves.

AAAI Conference 1998 Conference Paper

Using Arc Weights to Improve Iterative Repair

• John Thornton

One of the surprising findings from the study of CNF satisfiability in the 1990’s has been the success of iterative repair techniques, and in particular of weighted iterative repair. However, attempts to improve weighted iterative repair have either produced marginal benefits or rely on domain specific heuristics. This paper introduces a new extension of constraint weighting called Arc Weighting Iterative Repair, that is applicable outside the CNF domain and can significantly improve the performance of constraint weighting. The new weighting strategy extends constraint weighting by additionally weighting the connections or arcs between constraints. These arc weights represent increased knowledge of the search space and can be used to guide the search more efficiently. The main aim of the research is to develop an arc weighting algorithm that creates more benefit than overhead in reducing moves in the search space. Initial empirical tests indicate the algorithm does reduce search steps and times for a selection of CNF and CSP problems.