Assessment of deep learning algorithms to predict histopathological diagnosis of breast cancer: first Moroccan prospective study on a private dataset.

OBJECTIVE: Breast cancer is a critical public health issue and a leading cause of cancer-related deaths among women worldwide. Its early diagnosis and detection can effectively help in increasing the chances of survival rate. For this reason, the diagnosis and classification of breast cancer using Deep learning algorithms have attracted a lot of attention. Therefore, our study aimed to design a computational approach based on deep convolutional neural networks for an efficient classification of breast cancer histopathological images by using our own created dataset. We collected overall 328 digital slides, from 116 of surgical breast specimens diagnosed with invasive breast carcinoma of non-specific type, and referred to the histopathology department of the National Institute of Oncology in Rabat, Morocco. We used two models of deep neural network architectures in order to accurately classify the images into one of three categories: normal tissue-benign lesions, in situ carcinoma or invasive carcinoma. RESULTS: Both Resnet50 and Xception models achieved comparable results, with a small advantage to Xception extracted features. We reported high degrees of overall correct classification accuracy (88%), and sensitivity (95%) for detection of carcinoma cases, which is important for diagnostic pathology workflow in order to assist pathologists for diagnosing breast cancer with precision. The results of the present study showed that the designed classification model has a good generalization performance in predicting diagnosis of breast cancer, in spite of the limited size of the data. To our knowledge, this approach can be highly compared with other common methods in the automated analysis of breast cancer images reported in literature.

Minimally invasive repair of pectus excavatum using the Nuss technique in children and adolescents: indications, outcomes, and limitations.

BACKGROUND: Pectus excavatum (PE) is a common congenital deformity. The Nuss technique for minimally invasive repair of PE involves thoracoscopy-assisted insertion of a bar or plate behind the deformity to displace the sternum anteriorly. Our objective here was to clarify the indications and limitations of the Nuss technique based on a review of 70 patients. MATERIALS AND METHODS: A retrospective review of children managed at two centres identified 70 patients who had completed their growth and had their plate removed. Mean age was 13.8 years (range, 6-19 years). The reason for surgery was cosmetic disfigurement in 66 (95%) patients. The original Nuss technique was used in 63 patients, whereas 7 patients required an additional sub-xiphoid approach. Time to implant removal ranged from 8 months to 3 years. RESULTS: The cosmetic outcome was considered satisfactory by the patients in 64 (91%) cases and by the surgeon in 60 (85.7%) cases. Major complications requiring further surgery occurred in 6 (8.5%) patients and consisted of haemothorax (n=2), chest wall sepsis (n=2, including 1 after implant removal), allergy (n=1), and implant displacement (n=1). Early or delayed minor complications occurred in 46 (65%) patients and resolved either spontaneously or after non-surgical therapy. DISCUSSION: The minimal scarring and reliably good outcomes support the widespread use of the Nuss technique in children and adolescents. Our complication rates (minor, 65%; and major, 8.5%) are consistent with previous publications. In our opinion, contra-indications to thoracoscopic PE correction consist of a history of cardio-thoracic surgery and the finding by computed tomography of a sternum-to-spine distance of less than 5 cm or of sternum rotation greater than 35°. In these situations, we recommend a sub- and retro-xiphoid approach to guide implant insertion or a classic sterno-chondroplasty procedure. LEVEL OF EVIDENCE: Level IV, retrospective descriptive cohort study.

[Desmoplastic ameloblastoma in a 7 year old child]. / Améoblastome desmoplastique chez un enfant de 7 ans.

Desmoplastic ameloblastoma is a benign, locally aggressive neoplasm of proliferating odontogenic epithelial origin. It is seen among old patients from 17 to 72 years with an average age 42 years and without predilection of sex. We report the case of a 7 year old child, having presented since the 5 years age, a gingival tumefaction on the left higher incisivo-canin group which increased volume gradually. The stomatologic examination showed a gingival tumefaction covered with a healthy mucous membrane, ovoid form and measuring 3 cm on its horizontal axis. The tomodensitometry of the jawbone showed in front of the 21st and the 22nd tooth, the presence of an osseous lesion associating of the hearths of osteolysis and osteocondensation with rupture of cortical and invasion of the soft tissue. A curetting of the lesion was carried out and the anatomopathologic examination retained the diagnosis of desmoplastic ameloblastoma. The characteristic of our observation is the youth of the patient. In addition, the desmoplastic ameloblastoma is relatively rare, is characterized by an anatomical distribution, a radiological appearance and a morphological aspect differents from the traditional ameloblastoma. A radical surgical treatment is suggested for this tumour to avoid recurrency.