Meta-Heuristic Algorithm-Tuned Neural Network for Breast Cancer Diagnosis Using Ultrasound Images.

Breast cancer is the most menacing cancer among all types of cancer in women around the globe. Early diagnosis is the only way to increase the treatment options which then decreases the death rate and increases the chance of survival in patients. However, it is a challenging task to differentiate abnormal breast tissues from normal tissues because of their structure and unclear boundaries. Therefore, early and accurate diagnosis and classification of breast lesions into malignant or benign lesions is an active domain of research. Over the decade, numerous artificial neural network (ANN)-based techniques were adopted in order to diagnose and classify breast cancer due to the unique characteristics of learning key features from complex data via a training process. However, these schemes have limitations like slow convergence and longer training time. To address the above mentioned issues, this paper employs a meta-heuristic algorithm for tuning the parameters of the neural network. The main novelty of this work is the computer-aided diagnosis scheme for detecting abnormalities in breast ultrasound images by integrating a wavelet neural network (WNN) and the grey wolf optimization (GWO) algorithm. Here, breast ultrasound (US) images are preprocessed with a sigmoid filter followed by interference-based despeckling and then by anisotropic diffusion. The automatic segmentation algorithm is adopted to extract the region of interest, and subsequently morphological and texture features are computed. Finally, the GWO-tuned WNN is exploited to accomplish the classification task. The classification performance of the proposed scheme is validated on 346 ultrasound images. Efficiency of the proposed methodology is evaluated by computing the confusion matrix and receiver operating characteristic (ROC) curve. Numerical analysis revealed that the proposed work can yield higher classification accuracy when compared to the prevailing methods and thereby proves its potential in effective breast tumor detection and classification. The proposed GWO-WNN method (98%) gives better accuracy than other methods like SOM-SVM (87.5), LOFA-SVM (93.62%), MBA-RF (96.85%), and BAS-BPNN (96.3%).

Hybrid Model for Detection of Cervical Cancer Using Causal Analysis and Machine Learning Techniques.

Cervical cancer has become the third most common form of cancer in the in-universe, after the widespread breast cancer. Human papillomavirus risk of infection is linked to the majority of cancer cases. Preventive care, the most expensive way of fighting cancer, can protect about 37% of cancer cases. The Pap smear examination is a standard screening procedure for the initial screening of cervical cancer. However, this manual test procedure generates many false-positive outcomes due to individual errors. Various researchers have extensively investigated machine learning (ML) methods for classifying cervical Pap cells to enhance manual testing. The random forest method is the most popular method for anticipating features from a high-dimensional cancer image dataset. However, the random forest method can get too slow and inefficient for real-time forecasts when too many decision trees are used. This research proposed an efficient feature selection and prediction model for cervical cancer datasets using Boruta analysis and SVM method to deal with this challenge. A Boruta analysis method is used. It is improved from of random forest method and mainly discovers feature subsets from the data source that are significant to assigned classification activity. The proposed model's primary aim is to determine the importance of cervical cancer screening factors for classifying high-risk patients depending on the findings. This research work analyses cervical cancer and various risk factors to help detect cervical cancer. The proposed model Boruta with SVM and various popular ML models are implemented using Python and various performance measuring parameters, i.e., accuracy, precision, F1-Score, and recall. However, the proposed Boruta analysis with SVM performs outstanding over existing methods.

[Mid-term results in the treatment of osteochondritis dissecans of the femoral condyles using osteochondral grafting (mosaic arthroplasty)]. / Résultats à moyen terme du traitement des ostéochondrites disséquantes des condyles fémoraux par greffe ostéochondrale en mosaïque.

Several surgical procedures, including mosaic arthroplasty, can be used to treat patients with cartilage loss in the femoral condyles. This study aims to assess mid-term clinical and radiological results as well as the main prognostics elements. We conducted a retrospective epidemiological study over a period of 15 years. During the study period we collected data from 35 workable medical records of patients with osteochondritis dissecans of the femoral condyles treated by mosaic arthroplasty, with an average follow-up of 24 months. The level of complaints as well as preoperative knee function were evaluated and compared with the healthy knee according to the International Cartilage Repair Society (ICRS) score, the International Knee Documentation Committee (IKDC) score and visual analogue scale (VAS). It was less than 60% in 27 patients. During the follow-up period, the results were analyzed according to Hughston's functional and radiological criteria. After an average follow-up of 24 months, algoneurodystrophy was reported in 5 cases with a single case of haemarthrosis. A net ICRS score improvement was observed with a mean increasing from 54% to 74% on the follow-up visit. Most of patients were satisfied or very satisfied (82.9%). The elements of good prognosis recognized in our study included: a mean time between symptom onset and surgery of less of 18 months, having deep lesions with a diameter less than 02 cm and having lesions in the internal condyle. The treatment of cartilage loss is necessarily based on the correction of its direct and indirect causes namely the morphotype, the laxity and meniscus capital. No consensus in the decision-making was reached and no one could confirm the superiority of a technique in relation to the other but we can say that cartilage defect which sizes from 2 to 4 cm² may be the best indication for mosaic arthroplasty.

[Neurogenic paraosteopathy of the elbow: results of surgical arthrolysis (a retrospective study of 37 cases)]. / La para-ostéopathie neurogène du coude: résultat de l'arthrolyse chirurgicale (étude rétrospective de 37 cas).

Neurogenic paraosteoarthropathies are ectopic ossifications which develop near the joints. They are a process of neo-ectopic osteogenesis occurring after central or peripheral neurological lesions, in some types of comas (oxygen carbon intoxication, prolonged sedation) and following peripheral traumas including burns. They inolve almost exclusively the large proximal joints of the limbs. Elbow is the second area of involvment. The purpose of our study was to analyze the results of surgical arthrolysis in 37 patients with elbow stiffness due to neurogenic osteoarthropathy of the elbow. We conducted a retrospective study of 35 patients and 37 elbows over a 25-year period. Preoperative assessment included clinical and radiological examination. Since 2003 the patients had undergone systematic elbow arthroscopy. The gold standard surgical treatment was arthrolysis. All patients underwent functional rehabilitation protocol. Outcomes were analyzed after a mean 5-year follow-up period (6 months - 10 years). Neurogenic paraosteoarthropathy was caused by head injury with coma in 58.8% of cases. Preoperative assessment showed bending stiffness in the majority of cases (88%), severe or very severe in 64.7% of cases. Intraoperatively functional elbow range of motion from -30° to 130° was obtained in 61.7% of cases and in 41% of cases in the long term. Ulnar nerve liberation was satisfactory in 92% of cases. No postoperative instability of the elbow was reported. Two patients with definitive neurological lesions had osteoma recurrence. The results were equivalent regardless surgical delay. Surgical arthrolysis is an effective treatment for neurogenic osteomas of the elbow.

[Turrett's exostoses: about 35 casesk]. / Les exostoses de Turrett's: à propos de 35 cas.

We conducted a retrospective study of 35 patients with subungual exostosis of the hallux, also known as Turrett's exostosis, in the Department of Orthopedics and Traumatology at the Senior Military Hospital of Instruction of Tunis over the period between 1995 and 2015. We here summarize the outcomes of patients treated for this disease. The average age of patients was 29 years, with a sex ratio of 1.7. The median consultation time was six months. This delay in consultation was caused by a diagnostic error due to clinical picture resemblance with ingrown nail. Diagnosis was always confirmed by frontal and profile X-ray of the involved hallux. Treatment was based on total resection of the exostosis either through large ungual window or by latero-ungual approach. Anatomo-pathological examination was performed systematically. It allowed to confirm the benignity of the disease in all cases. All patients recovered and returned to their previous activity, on average, in 2 months. No patient had a recurrence.

[Results of the deltoid flap for surgery of rotator cuff tears]. / Resultats du lambeau deltoidien dans la chirurgie des ruptures de la coiffe des rotateurs.

AIM: Was to evaluate the results of deltoid flap for the treatment of massive rotator cuff tears. METHODS: This retrospective study included 20 shoulders in 20 patients with a painful massive, irreparable rotator cuff tears. The average patient age was 54 years. They were all treated with acromioplasty and a deltoid flap according to Augereau technique. Follow-up averaged 6 years 3 months (range 18 months - 11 years 4 months). Clinical and radiologic evaluations were done before and after surgery. Function was evaluated according to Constant's score. RESULTS: The Constant's score increased from 24.6/100 to 54.45/100. Eighty five per cent of patients were satisfied. Results on pain were good, with an average of Constant's score of 11/15. However, improvement strength or motion was not significative, with an average of 7.1/25 and 22.8/40 respectively. CONCLUSION: This study concludes that, this technique is a simple surgical procedure and their results on pain were good. Therefore, we conceder it is an excellent indication for the treatment of massive rotator cuff tears in adults after medical treatment failure.