A Communication Intervention for Training Southern European Oncologists to Recognize Psychosocial Morbidity in Cancer. I - Development of the Model and Preliminary Results on Physicians' Satisfaction

BACKGROUND: The detection of psychosocial distress is a significant communication problem in Southern Europe and other countries. Work in this area is hampered by a lack of data. Because not much is known about training aimed at improving the recognition of psychosocial disorders in cancer patients, we developed a basic course model for medical oncology professionals. METHODS: A specific educational and experiential model (12 hours divided into 2 modules) involving formal teaching (ie, journal articles, large-group presentations), practice in small groups (ie, small-group exercises and role playing), and discussion in large groups was developed with the aim of improving the ability of oncologists to detect emotional disturbances in cancer patients (ie, depression, anxiety, and adjustment disorders). RESULTS: A total of 30 oncologists from 3 Southern European countries (Italy, Portugal, and Spain) participated in the workshop. The training course was well accepted by most participants who expressed general satisfaction and a positive subjective perception of the utility of the course for clinical practice. Of the total participants, 28 physicians (93.3%) thought that had they been exposed to this material sooner, they would have incorporated the techniques received in the workshop into their practices; 2 participants stated they would likely have done so. Half of the doctors (n = 15) believed that their clinical communication techniques were improved by participating in the workshop, and the remaining half thought that their abilities to communicate with cancer patients had improved. CONCLUSIONS: This model is a feasible approach for oncologists and is easily applicable to various oncology settings. Further studies will demonstrate the effectiveness of this method for improving oncologists skills in recognizing emotional disorders in their patients with cancer.

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.