Automatic Small Bowel Tumor Diagnosis by Using Multi-Scale Wavelet-Based Analysis in Wireless Capsule Endoscopy Images

BACKGROUND: Wireless capsule endoscopy has been introduced as an innovative, non-invasive diagnostic technique for evaluation of the gastrointestinal tract, reaching places where conventional endoscopy is unable to. However, the output of this technique is an 8 hours video, whose analysis by the expert physician is very time consuming. Thus, a computer assisted diagnosis tool to help the physicians to evaluate CE exams faster and more accurately is an important technical challenge and an excellent economical opportunity. METHOD: The set of features proposed in this paper to code textural information is based on statistical modeling of second order textural measures extracted from co-occurrence matrices. To cope with both joint and marginal non-Gaussianity of second order textural measures, higher order moments are used. These statistical moments are taken from the two-dimensional color-scale feature space, where two different scales are considered. Second and higher order moments of textural measures are computed from the co-occurrence matrices computed from images synthesized by the inverse wavelet transform of the wavelet transform containing only the selected scales for the three color channels. The dimensionality of the data is reduced by using Principal Component Analysis. RESULTS: The proposed textural features are then used as the input of a classifier based on artificial neural networks. Classification performances of 93.1% specificity and 93.9% sensitivity are achieved on real data. These promising results open the path towards a deeper study regarding the applicability of this algorithm in computer aided diagnosis systems to assist physicians in their clinical practice.

Identification of de Novo Germline Mutations in the HRPT2 Gene in Two Apparently Sporadic Cases with Challenging Parathyroid Tumor Diagnoses

The diagnosis of parathyroid carcinomas is often difficult. HRPT2 mutations have been identified in familial [hyperparathyroidism-jaw tumor (HPT-JT) syndrome] and sporadic parathyroid carcinomas, supporting that HRPT2 mutations may confer a malignant potential to parathyroid tumors. In this study, we report the clinical, histopathological, and genetic investigation of two unrelated cases, whom had apparently sporadic malignant parathyroid tumors, initially diagnosed as adenomas. In one case, the differential diagnosis was complicated by cervical seeding of parathyroid tumor cells. Genetic studies identified de novo HRPT2 germline mutations in cases 1 (c.518_521delTGTC [p.Ser174LysfsX27]) and 2 (c.226 C > T [p.Arg76X]), unveiling the hereditary HPT-JT syndrome in both patients. Furthermore, the identification of somatic mutations in the patients‟ parathyroid tumors provided evidence for complete inactivation of the HRPT2 gene, which was consistent with the tumor malignant features. The sensitivity of parafibromin immunostaining to detect HRPT2 mutations was limited. The present data suggests that patients with apparently sporadic parathyroid carcinomas, or parathyroid tumors with atypical histological features, should undergo molecular genetic testing, as it may detect germline HRPT2 mutations. Establishing the diagnosis of hereditary HPT-JT syndrome is relevant for clinical counseling and management of the carriers and their relatives.

Genetic Screening of LCA in Belgium: Predominance of CEP290 and Identification of Potential Modifier Alleles in AHI1 of CEP290-Related Phenotypes

Leber Congenital Amaurosis (LCA), the most severe inherited retinal dystrophy, is genetically heterogeneous, with 14 genes accounting for 70% of patients. Here, 91 LCA probands underwent LCA chip analysis and subsequent sequencing of 6 genes (CEP290, CRB1, RPE65, GUCY2D, AIPL1and CRX), revealing mutations in 69% of the cohort, with major involvement of CEP290 (30%). In addition, 11 patients with early-onset retinal dystrophy (EORD) and 13 patients with Senior-Loken syndrome (SLS), LCA-Joubert syndrome (LCA-JS) or cerebello-oculo-renal syndrome (CORS) were included. Exhaustive re-inspection of the overall phenotypes in our LCA cohort revealed novel insights mainly regarding the CEP290-related phenotype. The AHI1 gene was screened as a candidate modifier gene in three patients with the same CEP290 genotype but different neurological involvement. Interestingly, a heterozygous novel AHI1 mutation, p.Asn811Lys, was found in the most severely affected patient. Moreover, AHI1 screening in five other patients with CEP290-related disease and neurological involvement revealed a second novel missense variant, p.His758Pro, in one LCA patient with mild mental retardation and autism. These two AHI1 mutations might thus represent neurological modifiers of CEP290-related disease.