Machine Learning in Melanoma Diagnosis. Limitations About to be Overcome. / Uso del aprendizaje automático en el diagnóstico del melanoma. Limitaciones por superar.

BACKGROUND: Automated image classification is a promising branch of machine learning (ML) useful for skin cancer diagnosis, but little has been determined about its limitations for general usability in current clinical practice. OBJECTIVE: To determine limitations in the selection of skin cancer images for ML analysis, particularly in melanoma. METHODS: Retrospective cohort study design, including 2,849 consecutive high-quality dermoscopy images of skin tumors from 2010 to 2014, for evaluation by a ML system. Each dermoscopy image was assorted according to its eligibility for ML analysis. RESULTS: Of the 2,849 images chosen from our database, 968 (34%) met the inclusion criteria for analysis by the ML system. Only 64.7% of nevi and 36.6% of melanoma met the inclusion criteria. Of the 528 melanomas, 335 (63.4%) were excluded. An absence of normal surrounding skin (40.5% of all melanomas from our database) and absence of pigmentation (14.2%) were the most common reasons for exclusion from ML analysis. DISCUSSION: Only 36.6% of our melanomas were admissible for analysis by state-of-the-art ML systems. We conclude that future ML systems should be trained on larger datasets which include relevant non-ideal images from lesions evaluated in real clinical practice. Fortunately, many of these limitations are being overcome by the scientific community as recent works show.

Assessment of ranges of rest postures of human lower limbs.

BACKGROUND: Several comfort perception models have proposed an objective method to evaluate "effects in the internal body" and "perceived comfort". Postural comfort is one aspect of comfort/discomfort perception, and this current work adds to existing knowledge toward a more objectified posture evaluation for comfort. OBJECTIVE: The authors have used the concept of Range of Rest Posture (RRP), as proposed by Apostolico et al. The study focused on the identification of RRP within the Comfort Range of Motion (CROM) for lower limbs. METHODS: The proposed method is based on extensive experimental work involving 114 healthy individuals (59 males and 55 females) ranging from 20 to 40 years old. The age range was narrowed to avoid an age-clustering of results due to inhomogeneity of the statistical sample. Data were processed using statistical methods for identifying the RRP in the experimental CROM. Several Maximum Level of Comfort (MLC) positions were found within the RRP. RESULTS: RRPs for lower limbs of men and women have been identified and can be used for virtual comfort assessment. CONCLUSIONS: This paper shows a method to evaluate in a more objective way the subjective postural comfort perception and results allow researchers to improve models for the virtual preventive comfort assessment.

[Gastric lymphoma: diagnostic radiology in the staging of the disease]. / Il linfoma gastrico: la diagnostica radiologica nello staging della malattia.

In the staging of gastric lymphoma, the radiologist has very important role, because he has many means to define correctly the stage. Conventional radiology is useful for detection of the lesion. Moreover, Ultrasound, Computed Tomography, and Magnetic Resonance are useful to define parietal extension and eventual nodal involvement. Lymphography remains a study kept to negative or doubt cases. In the future, the Magnetic Resonance will have a bigger role than now, in the definition of abdominal and pelvis nodal involvement.

[Mitral valve prolapse. Age and sex incidence, echocardiographic diagnosis and clinical and electrocardiographic correlations]. / Prolasso della mitrale. Incidenza per età e sesso, diagnosi ecocardiografica e correlazioni cliniche ed elettrocardiografiche.

The paper reports an electrocardiographic and M and B-mode echocardiographical study in 3682 non-selected patients among which a total of 241 were identified with mitral valve prolapse. In males the highest frequency was found during the second decade of life with a tendency to decrease with increasing age. In females, who were found to be the most severely affected (2:1 in relation to males), two peaks of incidence were observed during the third and fifth decade, with a greater frequency in the latter and a marked absence of cases in the fourth decade. Many echocardiographically diagnosed mitral prolapses were both clinically and electrocardiographically silent; moreover it was observed that the risks of this complication increased in parallel to the thinness and redundance of the mitralic flap affected by prolapse and the dilation of the valvular ring.